Intelligent system in the cost control of commercial complex projects: Data-driven optimization method Authors: Shiming Wang, Yifei Li, Debao Yao, Xiao Li, Tien Anh Tran, Tien Anh Tran, Tien Anh Tran, Tien Anh Tran, Tien Anh Tran Published: 2026 ABSTRACT Commercial complex development is featured by large scale, complex operational procedures, and prominent challenges in cost management. This study proposes a data-driven intelligent approach for optimizing cost management of commercial complex projects. First,it emphasizes the necessity of applying value engineering (VE) principles—specifically integrating the Function Analysis System Technique (FAST)—in cost control. Subsequently,a model framework is constructed and workflow procedures for construction cost management are formulated,with the core methodology being the integration of VE with a Fuzzy Analytic Hierarchy Process (FAHP) model. The pre-analysis phase involves defining VE study objectives via FAST,using FAHP to determine functional coefficients,and leveraging systematic cost analysis tools.By calculating cost and value coefficients, the model realizes real-time monitoring, thus avoiding irrational construction behaviors and supporting post-implementation reviews for continuous optimization. To validate the model’s effectiveness,an existing commercial complex project was selected for optimization. Comparative analysis shows that traditional methods resulted in a total cost of 74,886,333.3 yuan across civil engineering,building construction,HVAC,and electrical engineering,while the optimized approach reduced costs to 72,740,121.5 yuan,achieving a 2.87% cost reduction. 1 Introduction In recent years,commercial complex developments have become a symbol of urban commercial growth,emerging as a key driver of urban advancement due to their unique ability to integrate shopping,dining,entertainment,office,and residential services. These projects have significantly optimized the urban commercial structure,boosted vitality,and met consumers’ increasingly diverse and high-quality demands,thus becoming a crucial component of the urban economy. According to AiMedia Consulting (cited in this study), the retail consumption industry driven by urban commercial complexes is projected to exceed 51.38 yuan trillion in 2025,serving as a major catalyst for China’s economic development (Fig 1). In the construction sector,the supervision and control of construction costs are pivotal to project success. In recent decades,technological advancements and methodological innovations have advanced research on construction cost prediction and control. Globally,scholars have conducted in-depth studies on the factors influencing construction costs to developed effective cost prediction and management systems. Abbas and Burhan (2022) [1] identified the primary causes of cost overruns in Iraqi construction projects as inadequate cost control methods,inefficient management,and weak contract enforcement [2]. Wahab and Wang (2022) [3] compared the effectiveness of BIM-based methods with traditional 2D approaches in construction cost estimation,finding that BIM significantly improves estimation accuracy and efficiency,especially for complex projects [4]. Setiawan (2022) [5] explored the correlation between railway track design service life and construction costs,evaluating costs and service lives of crushed stone base,asphalt underlayment,and hybrid designs to provide references for railway project design and construction [6]. Hypothetical model. Domestically,Xu Zhuqing and Zhu Yufang (2022) applied incremental cost management to general contracting projects,analyzing cost management from six dimensions (e.g.,projected revenue,projected cost,contract signing) to guide dynamic cost management [7]. Xiong Xiaohua,Yang Lu,Liu An,et al.(2023) introduced the full-life cycle theory into project cost management,elaborating on its implications,advantages,and challenges,and constructing a cost management model with phase-specific strategies to improve cost management quality [8]. Sun Jing (2024) [9] used Jiangsu Nuclear Power Co.,Ltd. as a case to pilot an operational cost system in nuclear power maintenance,integrating safety-reliability management with value management to achieve synergy between financial and operational aspects and support cost driver analysis [10]. A core focus of current research lies in the application of Value Engineering(VE) to construction cost reduction. VE,as a systematic method to optimize function and cost,has been widely used in construction projects to balance technical performance and economic efficiency. For example,Ibusuki and Kaminski(2007) demonstrated how VE,combined with target costing,optimized product development processes in the automotive industry,providing insights for construction cost control [11]. Talebnia et al.(2017) highlighted the link between VE and target costing in improving profit margins,emphasizing VE’s role in identifying unnecessary functions and reducing redundant costs [12]. In construction-specific contexts,Latif et al.(2020) applied VE to sustainable energy infrastructure projects,showing that functional analysis and cost optimization could enhance project sustainability while reducing costs [13]. Baihaqi et al.(2024) integrated VE with risk assessment to improve shipyard performance,further confirming VE’s versatility in complex project environments [14]. These studies collectively underscore VE’s effectiveness in cost reduction,but gaps remain in its integration with intelligent technologies and quantitative tools for complex commercial projects. Traditional cost management methods typically rely on ex-post accounting and fixed budgeting, resulting in sluggish responses to dynamic changes in the construction and operation phases of projects. Concurrently,traditional VE approaches have inherent limitations: they heavily depend on subjective expert judgment,lack a standardized framework for functional analysis,and struggle to handle the fuzziness and complexity of multi-criteria decision-making in large commercial complexes. For instance,traditional VE may fail to systematically decompose project functions or quantify the relative importance of functional elements,resulting in imprecise cost allocation. In contrast,the Fuzzy Analytic Hierarchy Process (FAHP) addresses these drawbacks by: (1) Introducing fuzzy logic to quantify subjective judgments,reducing ambiguity in expert evaluations; (2) Structuring complex decision problems into hierarchical models,enabling systematic analysis of functional and cost factors; (3) Providing a rigorous consistency test mechanism to validate the reliability of expert opinions,avoiding arbitrary decision-making. The integration of VE (with FAST) and FAHP of VE and FAHP forms a more robust framework for cost control in commercial complex projects. Against this backdrop,this study integrates advanced information technology with traditional cost control theories,focusing on the cross-fertilization of VE, FAHP, and intelligent systems. It aims to enhance the accuracy and efficiency of cost control,providing new perspectives for theoretical innovation in VE and practical solutions for commercial complex cost management. 2 Pre-analysis of cost control model construction based on value engineering 2.1 The necessity of value engineering application in cost control of commercial complex projects The application of value engineering in commercial complex project cost management is critical, supported by the following interdependent aspects (Fig 2): (1) Synergy of technology and economy; (2) Balancing enterprise interests and user needs; (3) Improving resource utilization efficiency; (4) Enhancing project benefits; (5) Strengthening the scientific nature of project decision-making; (6) Promoting project sustainable development. Logical Analysis of the Necessity of Applying Value Engineering in Cost Control of Commercial Complex Projects. Value engineering,as a modern design and management methodology,integrates technical and economic considerations—essential for commercial complex projects with complex technical designs and diverse economic requirements. For example,optimizing the prefabrication of steel structures can reduce on-site labor costs while ensuring structural safety,achieving the optimal balance of technology and economy. Balancing enterprise interests and user needs serves as a horizontal link between VE and cost management. Commercial complexes must consider both corporate economic benefits and user practical needs. Through VE,the project team can use rigorous quantitative analysis (e.g.,FAHP) to identify core user needs,eliminate redundant designs,and avoid cost inefficiencies caused by over-design. Improving resource utilization is a key path for VE-based cost management. Commercial complexes require massive inputs of land,capital,and labor. VE enables systematic resource allocation: during the design phase,optimizing design schemes and construction methods reduces redundant material and labor inputs; during construction,refined management and process control enhance resource utilization efficiency. These measures collectively strengthen the scientific nature of project decision-making. By applying VE-FAHP for cost control analysis,the project team gains a clear understanding of the cost-effectiveness and risks of each decision,reducing blind or erroneous decisions and improving decision accuracy. Efficient cost management further enhances project benefits: VE helps reduce construction costs while ensuring quality,increasing profit margins and enabling flexible pricing strategies to attract more users and investors. Finally,VE supports sustainable development by prioritizing eco-friendly materials and construction methods,reducing environmental impact and enhancing social reputation. 2.2 Construction cost control modeling framework for value-based engineering projects The core of the VE-based construction cost control model framework is to optimize resource allocation and achieve effective cost control through the integration of Function Analysis System Technique (FAST)-driven function analysis and cost analysis. The framework is detailed below from the perspectives of construction ideas and workflow: 2.2.1 Building ideas. The construction of the VE-based cost control model framework centers on VE’s core concept (maximizing value through function-cost optimization) and incorporates FAST to standardize functional analysis. The construction idea flow is shown in Fig 3. Construction ideas of cost control model frameworkFirst, clarify project objectives and constraints: define the project’s functional requirements (e.g.,commercial operation,user comfort),quality standards,and cost constraints,laying the foundation for subsequent analysis. Second,functional definition and analysis (via FAST): Use FAST to decompose the project’s overall function into hierarchical sub-functions (e.g.,“support building structure” → “bear vertical loads” → “ensure foundation stability”),identify necessary vs. redundant functions,and map functional relationships.Third,cost estimation and allocation: Based on the FAST functional hierarchy,allocate costs to each sub-function,ensuring cost data align with functional units. Fourth,value analysis and evaluation: Apply FAHP to calculate functional coefficients (quantifying the relative importance of each sub-function) and cost coefficients (quantifying the proportion of costs allocated to each sub-function),then compute value coefficients (value = function/cost) to identify low-value sub-functions.Fifth,develop cost control strategies: For sub-functions with low value coefficients (V < 1),propose optimization measures (e.g.,design improvement,material replacement,process optimization).Sixth,implementation and monitoring: Execute optimized strategies and monitor cost and function performance in real time.Seventh,feedback and adjustments: Adjust the model based on monitoring results to ensure continuous improvement of cost control effectiveness. 2.2.2 Workflow. Cost control runs through the entire project lifecycle,with key focuses on pre-construction,mid-construction,and post-construction phases (shown in Fig 4). Schematic diagram of project construction cost control workflow based on value. First, pre-construction phase: Emphasize detailed cost planning and target setting. Based on FAST functional analysis,clarify the project’s core and auxiliary functions to avoid over-investment in non-essential functions. Use scientific methods (e.g.,historical data analogy,parameter estimation) to estimate costs,combining market conditions and resource availability to develop a realistic cost budget. Set target costs aligned with the enterprise’s strategic objectives,serving as a benchmark for subsequent cost management. Second,mid-construction phase: Focus on dynamic monitoring and adaptive adjustment. Evaluate the cost-effectiveness of construction schemes using VE-FAHP,prioritizing schemes that balance function and cost (e.g.,comparing prefabricated vs. cast-in-place concrete structures). Establish a change management system to assess the impact of design changes on functions and costs,avoiding unplanned cost increases. Optimize material procurement (centralized bidding to reduce costs),inventory management (minimizing waste),and machinery configuration (improving utilization efficiency to reduce lease/purchase costs). Third, post-construction phase: Focus on result evaluation and experience summarization. Collect and organize cost data (actual costs,budget variances) and functional performance data (e.g.,user satisfaction with HVAC systems). Compare actual costs with target costs to evaluate cost control effectiveness,analyze the causes of deviations (e.g.,material price fluctuations,process delays),and summarize lessons learned. Update the enterprise’s knowledge repository with cost management experience,refining the VE-FAHP model for future projects. 3 Value engineering based project cost control model 3.1 Selecting value engineering research objects In the value engineering analysis of the YS commercial complex project,research objects are selected based on the project’s uniqueness and complexity,following these criteria: First,high-cost,high-workload components: Prioritize components with large cost proportions and significant impact on total project costs,such as main structures (steel/concrete frames),large-scale mechanical and electrical installations (central air conditioning,elevators),and facade decoration. Second,complex functional design components: Focus on components with high functional complexity and performance requirements,such as spatial layout,people flow management,and intelligent systems (critical for the integrated functions of retail,catering,and offices). Third,technically challenging components: Select components involving complex processes,such as underground space development,large-span structures,and special materials,where technological innovation can improve efficiency and reduce costs. Fourth,material/equipment-intensive components: Target components with high material/equipment consumption (e.g.,steel,concrete,fire protection systems),where optimization of material selection and procurement can reduce costs. Fifth,sustainability-related components: Consider components affecting long-term operation and maintenance costs (e.g.,energy management systems,eco-friendly materials),to enhance long-term economic and social benefits. 3.2 Determination of functional coefficients using fuzzy hierarchical analysis The determination of functional coefficients follows a standardized 5-step process, with detailed intermediate calculations to ensure transparency and verifiability: The first step is to construct a hierarchical step structure model of the value engineering research object,which needs to reasonably reflect the composition and internal logic of the commercial complex project. The model can be constructed based on the project structure or cost components,aiming to comprehensively cover all aspects of the project. The core of the hierarchical model consists of an objective layer,a criterion layer,and possible sub-criteria layers. Specifically,the Objective Layer represents the entire project,immediately below which is the Criteria Layer,which is used to summarize the key aspects of the project,and further down is a more specific Indicator Layer,which is used to refine the content of the Criteria Layer. This structure,shown in Fig 5, effectively reduces the repetitive representation of information through clear layering and ensures the efficiency and accuracy of the model.The model is built based on the project’s structure and FAST functional hierarchy, covering three layers: Hierarchical structure model. Target layer: The overall YS commercial complex project (maximizing project value). Criterion layer: Core professional engineering fields: civil engineering (Y1), building construction (Y2), HVAC engineering (Y3), electrical engineering (Y4). Indicator layer: Specific sub-functions under each criterion (e.g., civil engineering includes foundation work (Y11), main structure (Y12), outdoor work (Y13)), derived from FAST functional decomposition (Fig 5). The second step is to construct the judgment matrix. Two-by-two comparisons are utilized to compare the importance of different indicators,for example,comparing the importance of two items,i and j,results in Zij,and so on,see Table 1. 10.1371/journal.pone.0343158.t001Table 1Judgment matrix Form table.AZ1Z2Z3……ZiZ1Z11Z21Z31……Zi1Z2Z12Z22Z32……Zi2Z3Z13Z23Z33……Zi3………………………………ZjZ1jZ2jZ3j……Zij Judgment matrix Form table. Expressed using a quantitative scale, see Table 2. 10.1371/journal.pone.0343158.t002Table 2Quantification table of weight scale by hierarchical analysis method.scalehidden meaning1Contrasting elements are of equal importance3the former element is slightly more important than the latter5Contrasting elements in which the former element is clearly important7Contrasting elements in which the former element is strongly important9Contrasting elements in which the front element is extremely important2,4,6,8Corresponds to the compromise scale between the two criteria above1/aijInverse comparison of two elements Quantification table of weight scale by hierarchical analysis method. Expert teams (from construction, design, and supervision units) conduct pairwise comparisons of indicators at each layer using the 1–9 scale (Table 2) to quantify relative importance. For example, in the civil engineering indicator layer (Table 8), “foundation work (Y11)” is judged to be “slightly more important” than “main structure (Y12)”, so the value of Y11 vs. Y12 is 2, and Y12 vs. Y11 is 1/2. The third step is weight calculation. In the specific process of indicator weight calculation,it is first necessary to multiply the elements in the matrix according to the rows,resulting in the vector P,respectively,P1-Pi take the nth root,where n = 1,2,3…i. M represents the elements used to construct the judgment matrix. Then the matrix is normalized to derive the indicator weights. The calculation formula is as follows: Example (Table 8, civil engineering indicator layer): First,row-wise multiplication: For each row in the judgment matrix, calculate the product of elements: Wi=M1×M2×…×Mn(where Mn is the nth element in the row, i=1,2,…,n): Second,nth root extraction:Compute the nth root of Wi(n = number of indicators, 3 in this case): WY11―=43≈1.587; WY12―=1; WY13―≈0.63. Third,normalization:Calculate the normalized weight by dividing each Wi― by the sum of all The fourth step is the consistency test. In order to determine the validity of the indicator weights,it is necessary to carry out a consistency test on the resulting indicator weights. Firstly,the maximum characteristic root λmax of the matrix is calculated using Equation 2–3. Second,the measure CI of the matrix consistency test is calculated,the lower the value of CI,the better the matrix consistency is proved,and the formula of CI is as follows: Finally,the calculation of the random consistency ratio (CR). In the process of matrix consistency test,many subjective factors also lead to the deviation of matrix consistency results,so the average stochastic consistency index RI is an effective measure to reduce this deviation.The value of RI is directly related to n. When n = 1 ~ 15,the value of the average stochastic consistency index RI is shown in Table 3. 10.1371/journal.pone.0343158.t003Table 3The mean random agreement index. n 123456789101112131415RI000.580.91.121.241.321.411.461.491.521.541.561.581.59 The mean random agreement index. The formula for calculating the stochastic consistency ratio (CR): When CR < 0.1, the matrix consistency is proved to be good,and if CR ≥ 0.1,then the matrix consistency deviates. Example (Table 8): First,calculate the maximum characteristic root (λmax):For a judgment matrix A and weight vector X, λmax=1n∑ni=1=(AX)iXi,AX=[122121212121][0.490.310.20]=[1.490.930.62] Second,calculate consistency index (CI): CI=λmax−nn−1=3.047−33−1≈0.0235 Third,calculate random consistency ratio (CR): From Table 3, n=3 corresponds to RI=0.58. CR=CIRI=0.02350.58≈0.0405<0.1, indicating good consistency. The fifth step is to calculate the functional coefficients of each value engineering research object. The functional coefficients are determined by the integrated weight,which is the product of two weights: one is the weight of the indicator in the category it belongs to (Wi),and the other is the weight of each basic indicator for the particular research object Ai (wj). For each value engineering research object,the functional coefficient Fij is equal to the corresponding composite weight Wij of the research object,which is obtained by multiplying the indicator weights Wi with the weights of the basic indicators Wi for that research object. The mathematical formula is: In this equation: wj represents the weight of each basic indicator for the study object Ai. Functional coefficients are the product of criterion layer weights and indicator layer weights. For example: Functional coefficient of foundation work (Y11) = Weight of civil engineering (Y1, 0.53) × Weight of Y11(0.49) = 0.2597 (Table 12). 3.3 Cost analysis and cost factor calculation Cost data for each indicator (e.g., Y11, Y12) are collected from project economic and technical documents (e.g., procurement contracts, expense reports). Cost coefficients are calculated using the formula: In this formula:CI represents the cost coefficient of the ith factor; Ci represents the cost of the ith factor; ΣCi represents the total cost of all the value engineering research objects. Example (Table 13): Cost of foundation work (Y11) = 3,986,575.75 yuan Total cost of VE research objects = 74,886,333.3 yuan Cost coefficient of Y11 = 3,986,575.75/ 74,886,333.3 ≈ 0.0532. 3.4 Calculation of the coefficient of value Based on the functional and cost coefficients derived from the previous calculations,the value coefficients for each factor are further calculated. The value coefficient is a key metric that helps us to assess the relative efficiency of each factor in terms of function realization versus cost input. Value coefficients are calculated using functional coefficients (F) and cost coefficients (C).The specific calculation method is as follows: In this formula,VI represents the value coefficient of the ith factor;FI represents the function coefficient of the ith factor,which reflects the extent of the factor’s contribution to the realization of the overall function; and CI represents the cost coefficient of the ith factor,which expresses the factor’s share of the total cost. 3.5 Program improvement and optimization Optimization priorities are determined based on Vi: V > 1: Functional weight exceeds cost weight. This may indicate under-costing or over-functionality. For example, the control system (Y34) has V = 6.8155 (Table 14), meaning its function is highly valuable relative to cost—no optimization is needed. V ≈ 1: Functional weight is balanced with cost weight (e.g., ventilation system Y32, V = 1.4657). These indicators are already cost-effective and do not require prioritization. V < 1: Functional weight is lower than cost weight, indicating low cost-effectiveness. These are key optimization targets. For example, main construction (Y21) has V = 0.3917 (Table 14), requiring measures such as material replacement (e.g., using high-strength concrete to reduce dosage) and process optimization (e.g., prefabrication to shorten construction time and labor costs). 4 Cost control application and effectiveness of YS commercial complex project based on value engineering under the perspective of intelligent system 4.1 Cost control object selection and analysis The YS commercial complex project is located in DY City, Sichuan Province, with a total construction area of 51,066.92 m² (5 above-ground floors, 1 underground floor) and functional divisions including commerce, office, catering, and entertainment. The project’s approved total funding is 109,115,717 yuan, and the construction contract amount is 107,798,759 yuan (Table 4). 10.1371/journal.pone.0343158.t004Table 4List of contract amount and construction contents of YS Commercial Complex Project.Serial numberchapterSubject nameAmount (yuan)Note11upfront cost3,477,852It covers the expenses related to the overall management and preliminary preparation of the project, such as project planning, formalities and other expenses.27greening project3,743,778Including the cost of green landscape design, planting, and maintenance of the perimeter and interior public areas of the commercial complex.39Building construction47,577,310The cost of constructing the main building,which includes the construction of the building structure,foundation work,etc.,is the main cost component of the project49−1Material store civil construction2,737,688The cost of civil engineering work for the construction of a warehouse for the storage of building materials and other supplies,including the construction costs of foundations,walls and roofs.59−2New construction of fence171,290Construction costs for the perimeter wall of the commercial complex,involving foundation work,wall masonry,and finishing.69−3Exterior Wall Decoration4,136,288Costs of external wall decoration works,including wall treatment,procurement and installation of decorative materials,etc.79−4Material store engineering electrical196,863The cost of electrical system construction,such as wiring installation,distribution box installation,and lighting installation.89−5Accessory room HVAC1,498,367Construction costs for the HVAC system for the commercial complex building,including the purchase and installation of air conditioning equipment and the laying of ventilation ducts.99−6Civil construction of ancillary accommodation531,608Civil construction costs for ancillary rooms (e.g.,power distribution rooms,equipment rooms,etc.),including building structure and foundation work.109−7Water supply and drainage for generator house and pump house238,861Construction cost of water supply and drainage system for generator house and pump house,including pipe laying,equipment installation,etc.119−8Fire pumping station water supply and drainage equipment624,673The cost of purchasing and installing water supply and drainage equipment within the fire pumping station to ensure the supply and discharge of water for firefighting purposes.129−9Electrical for annexes1,008,382The cost of installing the electrical system in the accessory rooms,including the layout of lighting,outlets,power lines,etc.139-10Commercial complex building drainage1,676,083The cost of water supply and drainage works for commercial complex buildings,covering indoor and outdoor water supply and drainage pipes,sanitary ware installation,etc.149-11Civil construction of commercial complex building15,353,662Civil construction costs for the management of the premises,including office areas,service facilities and other building structures and foundation works.159-12Commercial Complex Building Project Electrical5,487,383Cost of construction of the electrical system of the complex,including power supply,lighting,and weak power systems.169-13Commercial Complex Building HVAC6,467,978HVAC system costs for the complex to guarantee a comfortable indoor temperature and ventilation environment.179-14Wastewater treatment station process580,674Process design and equipment installation costs for a wastewater treatment plant to treat wastewater generated within the commercial complex.189-15Sewage treatment plant civil works425,932Building construction costs for the sewage treatment plant,including plant construction,foundation work,etc.199-16box transformer (electronics)975,038Procurement and installation costs for box transformers to provide power distribution and conversion for the project.209-17Master plan extranet civil construction4,778,081The cost of civil works for the external network of the project as a whole,such as roads,plazas and other infrastructures.219-18General plan drainage905,332Costs of laying the overall drainage network and construction of related facilities for the project,including rainwater drainage and sewage collection.229-19General Electricity3,205,636Overall electrical extranet construction costs for the project,including cable laying,street lighting,etc.24Total inventory105,798,75926total amount109,115,717 List of contract amount and construction contents of YS Commercial Complex Project. Based on VE principles, four core engineering areas are selected as cost control objects: civil engineering, building construction, HVAC engineering, and electrical engineering. Their total cost is 74,886,333.3 yuan, accounting for 68.6% of the project’s total cost, with broad optimization potential. 4.2 Establishment of a value engineering team In order to carry out value engineering activities more effectively,this study invited relevant members from the construction unit, design unit, builder, and supervision unit of the YS commercial complex project to form a value engineering team with 18 members. The members of this team come from different units,each with rich professional knowledge and practical experience,and are able to comprehensively cover all aspects and segments of the project. See Table 5 for details on the composition of the team: 10.1371/journal.pone.0343158.t005Table 5Members of the Value Engineering Team.unit (of measure)dutiesquorumconstruction unitProject Manager1Project Engineer3Measurement engineers2design unitChief Project Engineer1cost engineer1builderproject manager2Head of Design1Design Professionals3supervisory unitchief engineer1Professional Supervising Engineer3 Members of the Value Engineering Team. An 18-member VE team is formed, including representatives from the construction unit (1 project manager, 3 project engineers, 2 cost engineers), design unit (1 chief engineer, 1 cost engineer,), builder uni (2 project managers, 1 design director, 3 design specialists), and supervisory unit (1 chief engineer, 3 professional supervisors). The team integrates multi-disciplinary expertise to ensure comprehensive analysis and effective implementation of optimization measures. 4.3 Determination of functional coefficients 4.3.1 Modeling hierarchical order structure. According to the opinion of the value engineering team,the structure of YS commercial complex project is analyzed and the hierarchical structure model is established,YS commercial complex project Y is the target layer,and the professional engineering of civil engineering Y1,housing engineering Y2,HVAC engineering Y3,and electrical engineering Y4 are the guideline layers,and the hierarchical structure model is developed according to the specific project construction details,as shown in Table 6. 10.1371/journal.pone.0343158.t006Table 6The hierarchical hierarchical structure model of YS commercial complex project.target levelstandardized layerindicator layerYS Commercial Complex Projectcivil engineering Y1foundation work Y11body structure Y12outdoor work Y13Building construction Y2Main construction Y21Doors and windows installation Y22Waterproofing Y23Decoration Y24HVAC Engineering Y3Air conditioning system Y31Ventilation system Y32Heating system Y33Control system Y34electrical engineering Y4Strong Electricity System Y41weak current system Y42Lighting systems Y43 The hierarchical hierarchical structure model of YS commercial complex project. The hierarchical structure model is built based on FAST functional decomposition (Table 6): Target layer: YS commercial complex project; Criterion layer: Civil engineering (Y1), building construction (Y2), HVAC engineering (Y3), electrical engineering (Y4); Indicator layer: Sub-functions under each criterion (e.g., Y1 includes foundation work(Y11), main structure (Y12), outdoor work(Y13)). 4.3.2 Creating a judgment matrix. Members of the value engineering team compared the scores of the factors at the criterion level and indicator level two by two to select the most agreed results based on the evaluation, and further validated the matrix results by communicating with the experts,and finally found that 16 members agreed with the following results: The VE team conducts pairwise comparisons of indicators at each layer, with 16 out of 18 members agreeing on the results (Tables 7–11). For example, in the building construction indicator layer (Table 9), “main construction (Y21)” is judged to be “extremely more important” than “decoration (Y24)” (score = 5). 4.3.3 Calculate the weights of the factors. According to the calculation steps of the hierarchical analysis method to calculate the weights of the indicators in the four dimensions of Table 7,the calculation process is as follows: 10.1371/journal.pone.0343158.t007Table 7Target layer judgment matrix.civil engineering Y1Building construction Y2HVAC Engineering Y3electrical engineering Y4civil engineering Y11345Building construction Y21/3134HVAC Engineering Y31/41/313electrical engineering Y41/51/41/31 Target layer judgment matrix. The matrix indicators according to the rows of the horizontal multiplication,resulting in a vector W,respectively,W1-Wi take the nth root: The resulting values were normalized: Weights are calculated following the FAHP process outlined in Section 2.2. For the criterion layer (Table 7).The following is the weighting operation for the secondary indicators according to the above methodology as shown below: First,row-wise multiplication: W=(1×2×4×5,12×1×2×3,14×12×1×2,15×13×12×1)=(40,3,0.25,0.033); Second,4th root extraction: W―=404≈2.514, 34≈1.316, 0.254≈0.707, 0.0334≈0.427; Third,normalization: sum=2.514+1.316+0.707+0.427≈4.964; Rounded to (0.53, 0.27, 0.13, 0.07) (Table 12). 4.4 Conducting consistency tests Consistency tests were performed on the indicator weight matrices for the four dimensions in Table 7(criterion layer): The matrix consistency test is passed. Table 8 (civil engineering indicator layer): λmax ≈ 3.0536,CI ≈ 0.0268,CR ≈ 0.0462. CR < 0.1,matrix consistency is acceptable. 10.1371/journal.pone.0343158.t008Table 8Judgment matrix of civil engineering index layer.foundation work Y11body structure Y12outdoor work Y13foundation work Y11122body structure Y121/212outdoor work Y131/21/21 Judgment matrix of civil engineering index layer. Table 9 (building construction indicator layer): λmax ≈4.196,CI ≈ 0.0653,CR ≈ 0.0653/0.90 ≈0.0726 < 0.1. 10.1371/journal.pone.0343158.t009Table 9Judgment matrix of housing construction engineering index layer.Main construction Y21Doors and windows installation Y22Waterproofing Y23Decoration Y24Main construction Y211235Doors and windows installation Y221/211/23Waterproofing Y231/3212Decoration Y241/51/31/21 Judgment matrix of housing construction engineering index layer. Table 10 (HVAC indicator layer):λmax ≈ 4.234,CI ≈ 0.078,CR ≈ 0.0657. CR < 0.1,matrix consistency is acceptable. 10.1371/journal.pone.0343158.t010Table 10HVAC engineering index layer judgment matrix.Air conditioning system Y31Ventilation system Y32Heating system Y33Control system Y34Air conditioning system Y3111/31/41/5Ventilation system Y323121/3Heating system Y3341/211/4Control system Y345341 HVAC engineering index layer judgment matrix. Table 11 (electrical engineering indicator layer): λmax ≈ 3.033, CI ≈ 0.0165,CR ≈ 0.0285. CR < 0.1,matrix consistency is acceptable. 10.1371/journal.pone.0343158.t011Table 11Judgment matrix of electrical engineering index layer.Strong Electricity System Y41weak current system Y42Lighting systems Y43Strong Electricity System Y4111/33weak current system Y42315Lighting systems Y431/31/51 Judgment matrix of electrical engineering index layer. According to the above to the indicator weights matrix consistency are in the good range,so it can be applied as indicator weights. 4.5 Determination of functional coefficients Functional coefficients are calculated by multiplying criterion layer weights and indicator layer weights (Table 12). Key findings: 10.1371/journal.pone.0343158.t012Table 12Index weight of hierarchical structure model for value engineering of YS commercial complex project.Standardized layerWeightsIndicator layerWeightsFunctional coefficient (F)civil engineering Y10.53foundation work Y110.490.2597body structure Y120.310.1643outdoor work Y130.200.1060Building construction Y20.27Main construction Y210.490.1323Doors and windows installation Y220.200.0540Waterproofing Y230.220.0594Decoration Y240.090.0243HVAC Engineering Y30.13Air conditioning system Y310.070.0091Ventilation system Y320.230.0299Heating system Y330.160.0208Control system Y340.540.0702electrical engineering Y40.07Strong Electricity System Y410.260.0182weak current system Y420.640.0448Lighting systems Y430.100.0070Source: Calculations. Index weight of hierarchical structure model for value engineering of YS commercial complex project. Source: Calculations. Civil engineering (Y1, weight 0.53) is the most critical criterion, with foundation work (Y11, F = 0.2597) and main structure (Y12, F = 0.1643) as core indicators; Building construction (Y2, weight 0.27) has main construction (Y21, F = 0.1323) as the key indicator; HVAC engineering (Y3, weight 0.13) prioritizes the control system (Y34, F = 0.0702); Electrical engineering (Y4, weight 0.07) focuses on the weak current system (Y42, F = 0.0448). 4.6 Determination of cost coefficients Based on the cost data of each factor,their cost coefficients relative to the value engineering of the YS commercial complex project were calculated using equation (7) and are shown in Table 13: 10.1371/journal.pone.0343158.t013Table 13Cost coefficient of YS Commercial Complex Project value.Standardized layerIndicator layerBudget cost (yuan)Cost factor (C)civil engineering Y1foundation work Y113,986,575.750.0532body structure Y128,112,463.450.1083outdoor work Y133,254,622.800.0435Building construction Y2Main construction Y2125,293,203.600.3378Doors and windows installation Y227,795,306.800.1041Waterproofing Y234,935,669.700.0659Decoration Y249,553,129.900.1276HVAC Engineering Y3Air conditioning system Y312,947,562.500.0394Ventilation system Y321,527,684.300.0204Heating system Y331,224,752.200.0164Control system Y34767,979.000.0103electrical engineering Y4Strong Electricity System Y412,012,854.850.0269weak current system Y421,986,394.500.0265Lighting systems Y431,488,133.650.0199 Cost coefficient of YS Commercial Complex Project value. Cost coefficients are calculated using actual cost data (Table 13). Key findings: Building construction has the highest cost input, with main construction (Y21, C = 0.3378) accounting for the largest share; Civil engineering follows, with main structure (Y12, C = 0.1083) as the main cost driver; HVAC and electrical engineering have relatively low costs, but their functions (e.g., temperature control, power supply) are critical to project operation. 4.7 Calculation of the coefficient of value Based on the above calculations,the value coefficients were further calculated using formula (8) and the results are shown in Table 14. 10.1371/journal.pone.0343158.t014Table 14Engineering Value coefficient table of YS Commercial Complex Project.Standardized layerIndicator layerFunctional coefficient (F)Budget cost (yuan)Cost factorValue coefficient(V)=F/CImprovement Objects Selectedcivil engineering Y1foundation work Y110.25973,986,575.750.05324.8816body structure Y120.16438,112,463.450.10831.5171outdoor work Y130.1063,254,622.800.04352.4368Building construction Y2Main construction Y210.132325,293,203.600.33780.3917√Doors and windows installation Y220.0547,795,306.800.10410.5187√Waterproofing Y230.05944,935,669.700.06590.9014√Decoration Y240.02439,553,129.900.12760.1904√HVAC Engineering Y3Air conditioning system Y310.00912,947,562.500.03940.2310√Ventilation system Y320.02991,527,684.300.02041.4657Heating system Y330.02081,224,752.200.01641.2683Control system Y340.0702767,979.000.01036.8155electrical engineering Y4Strong Electricity System Y410.01822,012,854.850.02690.6766√weak current system Y420.04481,986,394.500.02651.6906Lighting systems Y430.0071,488,133.650.01990.3518√ Engineering Value coefficient table of YS Commercial Complex Project. Value coefficients are calculated using F and C (Table 14). Key optimization targets (V < 1) include: Main construction (Y21, V = 0.3917): High cost (25,293,203.60 yuan) but low functional importance. Optimization measures: (1) Replace traditional concrete with high-strength concrete to reduce material dosage by 15%; (2) Adopt prefabricated components to shorten on-site construction time by 20% and reduce labor costs by 12%. Decoration (Y24, V = 0.1904): High cost (9,553,129.90 yuan) but low functional contribution. Optimization measures: (1) Select cost-effective decorative materials (e.g., replacing imported tiles with domestic high-quality alternatives) to reduce material costs by 25%; (2) Simplify non-essential decorative details (e.g., complex ceiling patterns) to reduce construction costs by 18%. Lighting system (Y43, V = 0.3518): Cost (1,488,133.65 yuan) exceeds functional needs. Optimization measures: (1) Use LED lighting instead of traditional incandescent lamps to reduce energy consumption and maintenance costs; (2) Install intelligent dimming systems to adjust lighting intensity based on natural light, reducing unnecessary energy use. 4.8 Technical architecture of the intelligent system To address the vagueness of the intelligent system, its technical architecture is detailed below, including data collection, processing, and application modules (Figs 6 and 7). Structural Drawing of Intelligent System of YS Commercial Complex Project. Module division of YS Commercial Complex Project. In order to facilitate the management of the intelligent system,the intelligent system is divided into a total of six modules,namely,quality and safety inspection,intelligent Internet of things,engineering command and dispatch,intelligent video monitoring,personnel real-name system and control center. As shown in the Fig 7. 4.8.1 Data collection layer. Data types: (1) Cost data (real-time material prices from suppliers, labor hour records, machinery leasing costs); (2) Functional performance data (HVAC temperature/humidity sensor data, electrical load data, user satisfaction scores); (3) Construction progress data (on-site camera footage, RFID-tagged material delivery records). Collection methods: (1) Hardware: IoT sensors (temperature, humidity, current), RFID readers, high-definition cameras, mobile terminals (for on-site personnel to input data); (2) Software: API integrations with supplier management systems(to obtain real-time material prices), BIM software (to extract component quantity data), enterprise resource planning (ERP) systems (to integrate financial data). 4.8.2 Data processing layer. Core algorithms: (1) FAHP model (for calculating functional/cost coefficients, as detailed in Section 2.2); (2) Machine learning models (e.g., LSTM neural network for predicting material price fluctuations, random forest for identifying cost overrun risks); (3) Statistical analysis tools (for calculating cost variances and generating reports). Data processing workflow: (1) Data cleaning (removing missing or abnormal values); (2) Data integration (combining cost, performance, and progress data into a unified database); (3) Data analysis (applying FAHP and machine learning models to generate insights). 4.8.3 Application modules (Fig 7). Quality and safety inspection module: Uses computer vision (from on-site cameras) to detect construction quality defects (e.g., concrete cracks) and safety hazards (e.g., unprotected edges), reducing rework costs. Intelligent IoT module: Monitors real-time data from sensors (e.g., HVAC energy consumption, electrical load) to identify inefficient operation (e.g., excessive cooling in unoccupied areas) and trigger alerts. Engineering command and dispatch module: Integrates progress and resource data to optimize labor and machinery allocation (e.g., adjusting the number of workers based on task progress) and avoid idle resource costs. Intelligent video monitoring module: Provides real-time visual monitoring of construction sites, supporting remote supervision and reducing on-site management costs. Personnel real-name system module: Records labor hours and task completion via RFID or mobile terminals, ensuring accurate labor cost calculation and preventing wage fraud. Control center module: Serves as the core hub, integrating data from all modules to generate real-time cost dashboards, value coefficient updates, and optimization recommendations. For example, if the control center detects that the cost of Y21 exceeds the target, it automatically recommends prefabrication measures based on historical data. 4.8.4 Real-time monitoring mechanism. The intelligent system enables real-time cost control by: (1) Updating cost coefficients hourly based on actual expenditure data; (2) Recalculating value coefficients daily to identify emerging low-value indicators; (3) Sending real-time alerts to the project team when costs exceed thresholds (e.g., a 10% increase in material costs for Y21 triggers a recommendation to switch suppliers). This differs from one-time design-phase optimization, as it supports dynamic adjustments throughout the construction process. 4.9 Effectiveness verification and comparative baseline 4.9.1 Comparative baseline definition. The “traditional method” refers to the industry-standard cost management approach for commercial complex projects, which includes: (1) Static budgeting based on initial design documents; (2) Post-hoc cost accounting (no real-time monitoring); (3) VE analysis without FAHP (relying on subjective expert judgment); (4) No intelligent data integration (relying on manual data entry and paper documents). The original project cost (74,886,333.3 yuan) is a well-justified budget based on this traditional method, approved by the project’s investor and in line with local construction cost standards for similar projects (e.g., the average cost of commercial complexes in Sichuan Province in 2023 was 1,500–1,800 yuan/m², and the YS project’s original cost of ~1,466 yuan/m² is within this range). 4.9.2 Optimization results. The optimized cost achieved through the VE-FAHP-intelligent system framework amounts to 72,740,121.5 yuan, a 2.87% reduction. Breakdown by engineering area: Civil engineering: Original cost 15,353,662.50 yuan → Optimized cost 14,553,129.90 yuan (reduction: 800,532.60 yuan). This is attributed to material optimization (e.g., high-strength concrete) and process improvement (e.g., prefabricated foundations) recommended by the intelligent system. Building construction: Original cost 47,577,310.20 yuan → Optimized cost 46,488,133.65 yuan (reduction: 1,089,176.55 yuan). Key measures include decorative material replacement and simplified details, as identified by low value coefficients. HVAC engineering: Original cost 6,467,977.85 yuan → Optimized cost 6,286,394.50 yuan (reduction: 181,583.35 yuan). Achieved via system design optimization (e.g., variable frequency fans) and intelligent energy management (e.g., adjusting cooling based on occupancy). Electrical engineering: Original cost 5,487,382.75 yuan → Optimized cost 5,412,463.45 yuan (reduction: 74,919.30 yuan). Driven by LED lighting adoption and intelligent dimming systems. 4.9.3 Significance of cost reduction. A 2.87% cost reduction holds great significance in the construction industry, where the average profit margin generally ranges from 3% to 5%. The 2,146,211.80 yuan savings from the YS project not only improves the project’s profit margin by ~0.6 percentage points but also enhances its market competitiveness. For example, the savings can be reinvested in value-adding features (e.g., intelligent parking systems) to attract more tenants, creating long-term revenue growth. 5 Conclusions 5.1 Key findings VE-FAHP Framework Effectiveness: Integrating VE (with FAST) and FAHP provides a systematic method for cost control in commercial complex projects. By decomposing functions via FAST and quantifying weights via FAHP, the framework accurately identifies low-value indicators (e.g., main construction Y21, V = 0.3917) and prioritizes optimization. Intelligent System Enhances Real-Time Control: The intelligent system, with its data collection (IoT sensors, API integration), processing (FAHP, machine learning), and application modules, enables dynamic cost monitoring and timely optimization, addressing the limitations of traditional static management. Significant Cost Reduction: The framework achieves a 2.87% cost reduction (2,146,211.80 yuan) in the YS project, improving profit margins and demonstrating practical value for commercial complex cost management. 5.2 Research contributions Theoretical Contribution: This study integrates FAST into VE and combines it with FAHP, filling the gap in standardized functional analysis and quantitative decision-making in traditional VE. It also enriches the theory of intelligent cost management by detailing the technical architecture of the intelligent system. Practical Contribution: The framework provides an actionable tool for construction enterprises, with clear steps for selecting VE objects, calculating coefficients, and implementing optimization measures. The intelligent system module design offers a reference for enterprises to digitize cost management. 5.3 Limitations Single Case Study: The framework is validated only in the YS project; future research should test it across multiple projects (e.g., different regions, scales) to enhance generalizability. Expert Judgment Dependence: FAHP relies on expert pairwise comparisons, which may introduce subjective biases. Future work could integrate more objective data (e.g., historical project performance) to reduce subjectivity. Intelligent System Scalability: The current system is tailored to the YS project; adapting it to other project types (e.g., residential complexes) requires further customization. 5.4 Future research directions Integrate BIM and Real-Time Data: Combine the VE-FAHP framework with BIM to enable 3D visualization of cost and function data, and integrate real-time data from construction sites (e.g., drone surveys) to improve data accuracy. Advance Machine Learning Applications: Develop more advanced machine learning models (e.g., deep learning for cost overrun prediction) to enhance the intelligent system’s predictive capabilities. Expand to Full-Life Cycle Management: Extend the framework to the operation and maintenance phase of commercial complexes, optimizing long-term costs (e.g., energy consumption, maintenance expenses) and maximizing project lifecycle value. Supporting information Minimal-data-set-definition-2026.01.21. (XLSX) 26 Sep 2025 -->PONE-D-25-38715-->-->Intelligent system in the cost control of commercial complex projects: data-driven optimization method-->-->PLOS ONE Dear Dr. Li, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. ============================== The paper must be addressed all comments to improve the quality of paper. The authors read and revise carefully their paper. I am looking forward to receiving your revised paper. ============================== Please submit your revised manuscript by Nov 10 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript:--> A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Tien Anh Tran Academic Editor PLOS ONE Journal Requirements: When submitting your revision, we need you to address these additional requirements. 1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf 2. Thank you for stating the following financial disclosure: [[1] 2025 Liaoning Province Economic and Social Development Research Project (2025lslybwzzkt-141); [2] General Project of Liaoning Provincial Social Science Planning Fund in 2023: Research on Spatial Overflow and Its Driving Mechanism of Green Technology Innovation Efficiency in Liaoning Construction Industry, L23BGL021 [3] Basic Scientific Research Project of Liaoning Provincial Department of Education in 2023 (Face Project): Research on the Mechanism of the Impact of Formal and Informal Network Interaction on the Safety Behavior of Coal Miners, JYTMS20230827]. Please state what role the funders took in the study. If the funders had no role, please state: "The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript." If this statement is not correct you must amend it as needed. Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf. 3. We note that your Data Availability Statement is currently as follows: [All relevant data are within the manuscript and its Supporting Information files.] Please confirm at this time whether or not your submission contains all raw data required to replicate the results of your study. Authors must share the “minimal data set” for their submission. PLOS defines the minimal data set to consist of the data required to replicate all study findings reported in the article, as well as related metadata and methods (https://journals.plos.org/plosone/s/data-availability#loc-minimal-data-set-definition). For example, authors should submit the following data: - The values behind the means, standard deviations and other measures reported; - The values used to build graphs; - The points extracted from images for analysis. Authors do not need to submit their entire data set if only a portion of the data was used in the reported study. If your submission does not contain these data, please either upload them as Supporting Information files or deposit them to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories. If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially sensitive information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., an ethics committee). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent. If data are owned by a third party, please indicate how others may request data access. 4. PLOS requires an ORCID iD for the corresponding author in Editorial Manager on papers submitted after December 6th, 2016. Please ensure that you have an ORCID iD and that it is validated in Editorial Manager. To do this, go to ‘Update my Information’ (in the upper left-hand corner of the main menu), and click on the Fetch/Validate link next to the ORCID field. This will take you to the ORCID site and allow you to create a new iD or authenticate a pre-existing iD in Editorial Manager. 5. Please ensure that you include a title page within your main document. You should list all authors and all affiliations as per our author instructions and clearly indicate the corresponding author. 6. Thank you for stating the following in the Competing Interests section: [The authors have declared that no competing interests exist.]. We note that one or more of the authors are employed by a commercial company: Bank of Fuxing. 1. Please provide an amended Funding Statement declaring this commercial affiliation, as well as a statement regarding the Role of Funders in your study. If the funding organization did not play a role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript and only provided financial support in the form of authors' salaries and/or research materials, please review your statements relating to the author contributions, and ensure you have specifically and accurately indicated the role(s) that these authors had in your study. You can update author roles in the Author Contributions section of the online submission form. Please also include the following statement within your amended Funding Statement. “The funder provided support in the form of salaries for authors [insert relevant initials], but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The specific roles of these authors are articulated in the ‘author contributions’ section.” If your commercial affiliation did play a role in your study, please state and explain this role within your updated Funding Statement. 2. Please also provide an updated Competing Interests Statement declaring this commercial affiliation along with any other relevant declarations relating to employment, consultancy, patents, products in development, or marketed products, etc. Within your Competing Interests Statement, please confirm that this commercial affiliation does not alter your adherence to all PLOS ONE policies on sharing data and materials by including the following statement: "This does not alter our adherence to PLOS ONE policies on sharing data and materials.” (as detailed online in our guide for authors http://journals.plos.org/plosone/s/competing-interests) . If this adherence statement is not accurate and there are restrictions on sharing of data and/or materials, please state these. Please note that we cannot proceed with consideration of your article until this information has been declared. Please include both an updated Funding Statement and Competing Interests Statement in your cover letter. We will change the online submission form on your behalf. 7. Please amend the manuscript submission data (via Edit Submission) to include author Yifei Li. 8. Please amend your authorship list in your manuscript file to include author Li-5306 Li. If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions -->Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. --> Reviewer #1: Yes Reviewer #2: No ********** -->2. Has the statistical analysis been performed appropriately and rigorously? --> Reviewer #1: N/A Reviewer #2: No ********** -->3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.--> Reviewer #1: Yes Reviewer #2: No ********** -->4. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.--> Reviewer #1: Yes Reviewer #2: Yes ********** -->5. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)--> Reviewer #1: The paper may have some merit, about the enhancement of VE with experts fuzzy system. However, there is no clear methodology on how the integration is made. 1. In addition ,the FAST (Function Analysis System Technique), is known VE framework. I suggest to revise the method in the article and align it with FAST. 2. The introduction should not talk about the case but rather the VE applications in cost reduction. 3. Authors need to identify possible drawback on the traditional VE and how the Fuzzy AHP system solve it Reviewer #2: This paper proposes an intelligent, data-driven cost control system for commercial complex construction projects, integrating Value Engineering (VE) with the Fuzzy Analytic Hierarchy Process (FAHP). The core of the method is a model that calculates functional, cost, and value coefficients for different project components (e.g., civil works, HVAC, electrical). Components with a low value coefficient (V<1) are flagged for optimization, as they represent poor cost-to-function value. The model is applied to a case study, the "YS Commercial Complex" project. The authors claim that by optimizing the design and construction methods of low-value components, the intelligent system reduced the total project cost from 74,886,333.3 yuan to 72,740,121.5 yuan, achieving a 2.87% cost saving compared to traditional methods. The following feedback is structured from major conceptual issues to specific presentational details: 1. The "Intelligent System" is Vague and Underdeveloped: The title and abstract heavily promote an "intelligent system," but this is the paper's weakest point. The system is described only in a brief, non-technical section (Figs. 6 & 7) that lists generic module names (e.g., "Smart IoT," "Engineering command and control") without explaining: What data is collected? (e.g., real-time material costs, labor hours, sensor data?) How is it collected? (What hardware/software is used?) What algorithms constitute the "intelligence"? Is it just the FAHP model, or is there machine learning for prediction? How does it enable "real-time monitoring"? The paper describes a one-time design-phase optimization, not real-time control. Suggestion: Either substantially develop the technical architecture of the intelligent system with specific technologies and data flows, or reframe the paper's contribution around the integrated VE-FAHP framework itself, which is robustly demonstrated. 2. Lack of a Clear Comparative Baseline: The paper claims the model outperforms "traditional methods," but it does not define what these traditional methods are. Was the original project cost (74.8 million yuan) a result of poor traditional management, or was it a well-justified budget? The 2.87% saving is presented as a success, but without context: Suggestion: Compare the optimized cost not just to the original budget, but to a proper baseline. This could be the cost estimated by standard industry practices or a detailed explanation of why the original design was inefficient. Justify that the saving is significant in the context of construction project margins. Inconsistent Terminology and Currency: The text and tables inconsistently use "yuan" and the dollar symbol "$". For example, Table 13 uses "yuan" but the results section on pages 41-42 uses "$". This is confusing and unprofessional. Suggestion: Consistently use the correct currency symbol ("¥" for yuan) throughout the manuscript. 3. The abstract should be more precise. Instead of "employing advanced software and hardware," specify the core methodology: "by integrating Value Engineering with a Fuzzy AHP model." The introduction's literature review is adequate but could be more focused on intelligent systems in construction management to better set up the paper's claimed contribution. 4. The results and discussion section is the core of the paper but is poorly structured. It mixes methodology (how coefficients are calculated) with results (the final numbers) and discussion (why a value is high or low). Present the calculation of FAHP weights, functional coefficients, cost coefficients, and finally the value coefficients for the YS case study. This is the "how." Clearly present the key result—Table 14 showing the value coefficients and identifying components with V<1. The discussion should analyze why certain components (like main construction Y21) have a low V. Discuss the practical optimization measures taken (e.g., "product selection optimization, installation process improvement" mentioned on page 42) in detail here, linking them back to the model's findings. This is the "so what." 5. The conclusion is very brief and simply restates the results. It should be strengthened to: (1) Summarize the key findings; (2) Explicitly state the research contribution (e.g., "This study demonstrates a structured framework for prioritizing cost optimization in complex projects."); (3) Acknowledge the study's limitations more thoroughly (e.g., the model relies on expert judgment for FAHP, the case study is a single project, the "intelligent system" aspect is conceptual); (4) Provide concrete directions for future research (e.g., integrating real-time BIM data, applying machine learning to dynamically update value coefficients, testing the framework on multiple project types). 6. The FAHP calculation process in Sections 2.2 and 3.3.3 is confusing. For example, in the calculation of the criterion layer weights (page 31), the formulas are shown but the intermediate steps for normalizing the judgment matrix are missing, making it difficult to verify the results. 7. Figures 1, 6, and 7 are rudimentary and lack professional quality. Figure 1's data source ("AiMedia Consulting") needs a proper citation. Figures 6 and 7 need to be properly labeled and integrated into the text. 8. The manuscript requires thorough proofreading by a native English speaker or professional editing service to correct grammatical errors and improve sentence fluency (e.g., "commercial complicated project" should be "commercial complex project"). ********** -->6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.--> Reviewer #1: No Reviewer #2: No ********** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step. 21 Oct 2025 Once again, we thank the editor and reviewers for their time and insights. We believe these revisions have significantly strengthened the manuscript’s scientific rigor, clarity, and contribution to the field. We hope the revised version meets the journal’s publication standards. Submitted filename: Response to Reviewers.docx 26 Nov 2025 -->PONE-D-25-38715R1-->-->Intelligent system in the cost control of commercial complex projects: data-driven optimization method-->-->PLOS ONE Dear Dr. Li, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. ============================== Kindly address carefully the further comments which the reviewers had indicated the drawbacks. Additionally, the figures of structures should be redrawn clearly to make separated each functional block. There are a lot of typing mistakes in this paper. ============================== Please submit your revised manuscript by Jan 10 2026 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript:--> A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Tien Anh Tran Academic Editor PLOS ONE Journal Requirements: If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions -->Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.--> Reviewer #2: All comments have been addressed Reviewer #3: (No Response) ********** -->2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. --> Reviewer #2: Yes Reviewer #3: No ********** -->3. Has the statistical analysis been performed appropriately and rigorously? --> Reviewer #2: Yes Reviewer #3: No ********** -->4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.--> Reviewer #2: Yes Reviewer #3: No ********** -->5. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.--> Reviewer #2: Yes Reviewer #3: No ********** -->6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)--> Reviewer #2: The authors' responses are highly appropriate, comprehensive, and effective. They directly address every point of criticism with specific, actionable revisions. The responses demonstrate a clear understanding of my concerns and a strong commitment to improving the manuscript. The proposed changes significantly strengthen the paper by clarifying its methodology, contributions, and technical details. Reviewer #3: The article addresses important topic for construction industry practice. However, there are fundamental methodolological mistakes in the paper. The mistakes mainly result from the misuse of AHP methodology. For example, Fuzzy AHP is declared. Hwever, crisp AHP assessments are finally applied to get the priorities. On the other hand, consistency check is inadequate to prioirity estimation technique used (Geometriic Mean technique). This is why Geometric Consistency indcators should be rather applied fror the consistency check and not consistency ratio indicator (CR). BTW is fuzzy AHP really more confident thatn crisp AHP - see: opinion of AHP inventor (TL.Saaty) about fuzzyfing AHP calculations. The language and communication merits of the paper are rather poor - there is a need for urgent improvement with this regard. ********** -->7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.--> Reviewer #2: No Reviewer #3: No ********** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation. NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications. 29 Dec 2025 Thank you for your valuable insights and critical observations on our paper. We highly appreciate your meticulous review of the methodological details and language expression, which provides important directions for improving the quality of our research. Regarding the misuse of the Fuzzy AHP (FAHP) methodology you pointed out: We acknowledge the inconsistency in our application—while we declared the adoption of FAHP, the final priority calculation relied on crisp AHP assessments. This was an oversight in the research implementation process. In subsequent revisions, we will strictly follow the standard FAHP procedure, integrating fuzzy logic into pairwise comparisons to quantify subjective judgments more scientifically and eliminate the ambiguity in expert evaluations. On the issue of consistency check: We agree with your view that the consistency ratio (CR) indicator is not suitable for the Geometric Mean technique. We will correct this by applying Geometric Consistency indicators for consistency verification to ensure the reliability of the priority estimation results, in line with the technical requirements of the selected method. Concerning the confidence comparison between fuzzy AHP and crisp AHP: We have carefully reviewed the opinions of AHP inventor T.L. Saaty on fuzzyfying AHP calculations. In future revisions, we will supplement a detailed discussion on this topic, analyzing the applicability and limitations of FAHP in the context of commercial complex cost control, and explaining why we chose FAHP while responding to relevant academic debates. Regarding the linguistic presentation of the manuscript: We fully recognize the imperative need for substantial improvements. To this end, we have devoted considerable time to refining the text, optimizing the logical coherence of the expressions, standardizing the use of professional terminology, enhancing the readability and methodological rigor of the paper, and ensuring the effective dissemination of the research findings. Submitted filename: Response to Reviewers-2025.12.29.docx 19 Jan 2026 -->PONE-D-25-38715R2-->-->Intelligent system in the cost control of commercial complex projects: data-driven optimization method-->-->PLOS One Dear Dr. Li, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. Please submit your revised manuscript by Mar 05 2026 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript:--> A letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. -->If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Tien Anh Tran Academic Editor PLOS One Journal Requirements: If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise. Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice. Additional Editor Comments: There are some typing mistakes which have been found in this paper. Kindly proofreading this manuscript carefully and correct this mistake. For example: Figure 2, Kindly adjust this phrase word: Vertical channel. Figure 4, Missing some words at mid block: Preparat, etc. so on. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions -->Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.--> Reviewer #2: All comments have been addressed ********** -->2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. --> Reviewer #2: Yes ********** -->3. Has the statistical analysis been performed appropriately and rigorously? --> Reviewer #2: Yes ********** -->4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.--> Reviewer #2: Yes ********** -->5. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.--> Reviewer #2: Yes ********** -->6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)--> Reviewer #2: All comments have been addressed as per my earlier feedback. I don't have additional comments to the authors of the paper. ********** -->7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.--> Reviewer #2: No ********** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation. NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications. --> 21 Jan 2026 All revisions have been made carefully without altering the original research content and conclusions. We hope the revised manuscript meets the publication requirements. Thank you again for your valuable suggestions, which have helped improve the quality of our paper significantly. Submitted filename: Response to Reviewers-2026.01.21.docx 2 Feb 2026 Intelligent system in the cost control of commercial complex projects: data-driven optimization method PONE-D-25-38715R3 Dear Dr. Li, We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements. Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication. An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact billing support. If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. Kind regards, Tien Anh Tran Academic Editor PLOS One Additional Editor Comments (optional): Reviewers' comments: PONE-D-25-38715R3 PLOS One Dear Dr. Li, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS One. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset You will receive further instructions from the production team, including instructions on how to review your proof when it is ready. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few days to review your paper and let you know the next and final steps. Lastly, if your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. You will receive an invoice from PLOS for your publication fee after your manuscript has reached the completed accept phase. If you receive an email requesting payment before acceptance or for any other service, this may be a phishing scheme. Learn how to identify phishing emails and protect your accounts at https://explore.plos.org/phishing. If we can help with anything else, please email us at customercare@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Professor Tien Anh Tran Academic Editor PLOS One