Deep Kronecker LeNet for human motion classification with feature extraction
Thottempudi Pardhu, Vijay Kumar, Kalyan C Durbhakula · 2024
Read Deep Kronecker LeNet for human motion classification with feature extraction by Thottempudi Pardhu, Vijay Kumar, Kalyan C Durbhakula (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11586406.txt.
Description
Thottempudi Pardhu and co-authors classify human motion through walls using radar and a new deep network tuned by a wolf-inspired optimizer. Motion checks matter for health care and security work. Cameras raise privacy worries that radar avoids.
Ultra-wideband radar pulses pass through walls to catch movement. The signals are gridded, then mined for key features. Their network fuses a Kronecker design with a classic LeNet. A fuzzy twist adjusts the network's inner layers. A spotted grey wolf algorithm tunes the settings. The system sorts motions without filming anyone directly. Through-wall sensing suits elder care and rescue work. Accuracy gains are reported against rival models in tests.
Catalog record
| CREATOR | Thottempudi Pardhu, Vijay Kumar, Kalyan C Durbhakula |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 72 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |