Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{194681,
        author = {Shreyas D and Roopitha G Nayak and Umamahesh P},
        title = {Deep Learning Based Human Detection Using UWB Radar Signals},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {5113-5119},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194681},
        abstract = {Ultra-Wideband (UWB) radar technology has become a promising alternative for detecting humans in settings where conventional camera systems are either ineffective or unsuitable. This study introduces a method that uses deep learning to identify human presence through UWB radar signal data. Radar signals are transformed into visual formats and examined with Convolutional Neural Networks (CNNs) to determine if a person is present or not. Two datasets consisting of radar signal images gathered under different conditions, including varying angles, distances, and human postures, are utilized for the experiments. The system uses preprocessing methods such as adjusting image size, standardizing data, and converting labels into numerical form prior to training the model. Several CNN models with different numbers of convolutional layers, pooling techniques, and dropout settings are tested to identify the best-performing model for detecting humans using radar data. Performance is measured through evaluation metrics like accuracy, precision, recall, F1-score, and confusion matrices. The experimental results show that the suggested deep learning method effectively differentiates between human and non-human radar signals with high precision. The research emphasizes the promise of integrating UWB radar sensing with deep learning methods for privacy-conscious human detection in areas like security surveillance, healthcare, smart homes, and search-and-rescue missions.},
        keywords = {UWB Radar, Human Detection, Deep Learning, Convolutional Neural Networks, Radar Signal Processing, Machine Learning, Indoor Sensing, Tensorflow.},
        month = {March},
        }