Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed

Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741

Browse

Start date: 2020End date: 2026Type: search.filters.itemtype.Proceedings PaperAuthor: search.filters.author.Soyak, Ece GelalAuthor: search.filters.author.Dogan, Emine Berjin

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    PublicationMetadata only
    Neural Network-Based Human Detection Using Raw UWB Radar Data
    (IEEE, 2024) Dogan, Emine Berjin; Yousefi, Mohammad; Soyak, Ece Gelal; Karamzadeh, Saeid; Kolosovs, D; Bahcesehir University; Bahcesehir University; Bahcesehir University; Bahcesehir University
    Ultra-Wideband (UWB) radar technology is a widely used technology for human detection and tracking through walls, because of its effectiveness in low-visibility situations. This study demonstrates a neural network-based identification of human presence using raw data obtained directly from the UWB radar. First, measurements have been collected with different human subjects at different positions relative to the UWB radar. A convolutional neural network (CNN) model has been trained on this dataset, to detect the presence of a human. Next, the algorithm effectiveness is deeply investigated using the Gradient-weighted Class Activation Mapping (Grad-CAM) method, and the observations on detected presence are discussed.
  • No Thumbnail Available
    PublicationMetadata only
    Improving the Robustness of CNN-Based Human Detection in Multiple Raw UWB Radar Datasets
    (IEEE, 2024) Yousefi, Mohammad; Dogan, Emine Berjin; Soyak, Ece Gelal; Karamzadeh, Saeid; Bahcesehir University; Bahcesehir University; Bahcesehir University; Bahcesehir University
    Ultra-wideband (UWB) radar technology has gained significant attention for human detection, vital sign monitoring, and activity recognition applications. In this study, a robust deep-learning model capable of detecting human presence in different environments is developed. The model uses only the raw data obtained directly from the radar without preprocessing. The model is trained and tested on different datasets collected via the UWB radar. Transfer learning has been applied to fine-tune the model on datasets to improve the performance and generalization of the model. This study demonstrates the effectiveness of transfer learning in adapting UWB radar-based human detection models to different environments.