The author presents the RISAR method, utilizing reconfigurable intelligent surfaces to enhance human activity recognition with Wi-Fi signals, achieving high accuracy and efficiency.
The author proposes H-HAR, a new approach to Human Activity Recognition that focuses on hierarchy-aware label relationship modeling to enhance model performance and interpretation.
RISAR significantly enhances human activity recognition accuracy using Wi-Fi signals.
The article presents an Android application that recognizes daily human activities and calculates the calories burned in real-time using smartphone sensors, particularly the accelerometer.
This paper introduces TRIS-HAR, a novel system that leverages transmissive reconfigurable intelligent surfaces (TRIS) and a state-space model called HiMamba to significantly improve the accuracy of through-the-wall human activity recognition using radio frequency signals.
본 논문에서는 투과형 재구성 가능 지능형 표면(TRIS) 기술을 활용하여 복잡한 실내 환경에서 무선 신호 전파를 개선하고, 이를 통해 벽을 통과하는 시나리오에서도 높은 정확도를 달성하는 인간 활동 인식 시스템(TRIS-HAR)을 제안합니다.
This research introduces a novel Temporal Fusion Graph Convolutional Network (TFGCN) enhanced with Spectral Normalized Residual connections (SN-Res) and a Gaussian Process (GP) kernel to improve human activity recognition, segmentation, and out-of-distribution detection by quantifying prediction uncertainty.
本文提出了一種名為時間融合圖卷積網路 (TFGCN) 的新方法,用於理解人類活動,特別關注解決過度分割問題,並通過譜歸一化殘差連接增強對新穎觀察的處理,從而提高機器人在人機協作場景中的性能。
This research proposes a novel method for generalizable indoor human activity recognition using through-the-wall radar, addressing the challenge of varying human physiques by employing micro-Doppler corner point cloud representation and dynamic graph learning for robust and accurate activity classification across different individuals.
Temporal Action Localization (TAL) models, originally designed for video analysis, demonstrate superior performance compared to traditional inertial-based models in offline Human Activity Recognition (HAR) tasks using data from wearable inertial sensors.