Human activity recognition (HAR) with WiFi channel state information (CSI) is attractive for privacy-preserving, device-free sensing, yet real deployments still struggle with three coupled issues: robustness across rooms and bands, efficiency on edge hardware, and unified support for multiple tasks. We present UN-2DCNN, a lightweight 2D-CNN pipeline tailored to indoor, multi-user CSI sensing. The design reduces temporal redundancy via a simple temporal skipping augmentation, learns a compact 128-D representation with a small CNN+GAP backbone, and injects reliability feedback through uncertainty-aware feature scaling (UAFS): Stage-1 predictive entropy is mapped to a gating weight that rescales features before a second decision head. A channel-attention MLP further suppresses spurious subcarrier responses. Evaluated on a recent multi-user CSI benchmark across classrooms, meeting rooms, and empty environments at 2.4/5 GHz, UN-2DCNN consistently outperforms competitive RNN/Transformer baselines while using only ∼1M parameters and maintaining sub-2 s test-time latency. Beyond higher accuracy, the model exhibits faster, smoother convergence and improved calibration (fewer overconfident errors). Ablations confirm that removing attention, UAFS, or the second-stage head yields consistent drops, and simple temporal skipping on the data side complements model-side selectivity. These results indicate that reliability-aware, lightweight designs can deliver practical accuracy–efficiency trade-offs for CSI-based perception on edge/IoT platforms.

Wi-Fi Channel State Information (CSI)-based human activity recognition (HAR) leverages rich channel propagation characteristics to enable non-intrusive, privacy-preserving, and device-free sensing. In multi-user wireless environments, however, HAR faces significant challenges, including multi-path interference, signal overlap, label ambiguity, cross-domain channel variability, and constraints imposed by real-time deployment on resource-limited edge devices. This paper presents MuECNet (Multi-user Enhanced Convolutional Network), a lightweight and modular deep learning framework designed to operate under realistic multi-user, multi-activity CSI sensing conditions. MuECNet integrates three key components: (i) an Enhanced Convolutional Encoding Module (ECEM) for fine-grained temporal–spectral feature extraction that preserves channel propagation signatures; (ii) a Branch-wise Feature Normalization (BFN) module for user-specific channel representation learning; and (iii) an adaptive Decision Module for multi-label activity inference. To improve robustness under diverse and dynamic channel conditions, we introduce MixUp-based data augmentation to emulate activity overlap and reduce label ambiguity. Evaluations on the WiMANS dataset show that MuECNet achieves 64.46% (2.4 GHz) and 64.15% (5 GHz) accuracy with only 1.19M parameters, 1.74G FLOPs, and 0.28 s inference latency, outperforming baseline models such as ABLSTM and THAT while reducing model size by up to 75%. Ablation studies confirm the contribution of each module, with accuracy drops of up to 6.41% when removed. These results demonstrate that MuECNet provides a robust and communication-efficient solution for integrating CSI-based sensing into future wireless networks and IoT systems.

Millimeter-wave (mmWave) radar has emerged as a powerful sensing modality for human activity recognition (HAR) owing to its capability to capture 3D point cloud sequences without privacy concerns. However, effectively modeling the sparse, irregular, and non-uniform nature of radar data remains a major challenge. Existing approaches often rely on highly complex network architectures to improve accuracy, which leads to excessive computational overhead and poor scalability. To overcome these limitations, this paper proposes a compact hybrid feature extraction network for voxelized radar point cloud classification, which performs early-stage spatio-temporal fusion and is termed STFusionNet (Spatial-Temporal Fusion Network). The STFusionNet comprises (i) a lightweight 3D convolutional front-end, which treats consecutive temporal frames as input channels to encode motion dynamics into a compact volumetric representation and further aggregates features along the depth axis; (ii) a minimalist 2D convolutional backbone after a Depth-to-Channel Folding operation, which captures spatial features with minimal computational cost. Extensive experiments on the public MMActivity and MiliPoint datasets demonstrate that our model achieves competitive accuracy (e.g., 92.20% on MMActivity and 72.86% on MiliPoint) with only about 50K parameters and 46 MMac, outperforming or matching representative spatio-temporal baselines under a much lower computational budget. Extensive ablation experiments verify the contribution of key components, while statistical significance tests confirm the reliability of the performance improvements. These results confirm that STFusionNet offers a robust, efficient, and generalizable solution for mmWave radar-based HAR in Internet of Things (IoT) applications.

Wi-Fi-based Human Activity Recognition (HAR) using Channel State Information (CSI) has received significant attention due to its non-intrusive nature and wide applicability in smart cities, healthcare, and smart home systems. Despite its potential, real-world deployment faces a major challenge: ensuring the model’s ability to generalize across different users, who exhibit distinct behaviors and encounter diverse environmental factors. This issue, termed Cross-User Generalization (CUG), arises from distribution shifts caused by variations in users’ body shapes, postures, movements, and environmental conditions. To address this challenge, we propose a cross-domain generalization framework based on an Attention-based Bidirectional Long Short-Term Memory (ABLSTM) network. The proposed framework enhances the generalization capabilities of HAR models by leveraging multi-source training and incorporating attention mechanisms for effective temporal feature learning. Specifically, the model learns user-invariant features across diverse training users and adapts to new users without requiring direct exposure to their data. Extensive experiments on a multi-user CSI dataset demonstrate that the ABLSTM model improves average test accuracy by 2.0%–6.7% compared to BiLSTM and GRU models, and over 18.0% compared to MLP-based models, while achieving the lowest training and testing loss. This methodology offers a robust and scalable solution for Wi-Fi-based HAR, promoting reliable deployment in complex, multi-user environments encountered in smart cities, healthcare monitoring, and security surveillance.

As the global population continues to age and technologies such as the Internet of Things (IoT) and edge computing advance rapidly, indoor human activity recognition (HAR) based on Wi-Fi channel state information (CSI) has gained significant research attention. However, the high computational complexity of existing HAR methods limits their deployment on resource-constrained devices. To address this challenge, we propose a lightweight HAR method using branch decision lightweight two-stream convolution-augmented transformer (BLTHAT) model, which integrates depthwise separable convolutions (DSC) and an improved framework structure to enhance computational efficiency. Additionally, we introduce the branch fusion network (BFN), a decision-making module designed to optimize feature processing and improve model robustness. Further enhancements in attention mechanisms and regularization strategies contribute to reducing complexity while maintaining high recognition accuracy. Comprehensive experiments were conducted on a multi-label dataset. The results demonstrate that our proposed HAR method achieves high computational efficiency with minimal complexity, making it well-suited for IoT applications. Ablation studies further confirm that the multi-branch structure of the BFN module enhances feature extraction without significantly increasing computational overhead.

As economic development and social well-being demands grow, road maintenance and safety have become paramount. This study introduces an intelligent road damage detection system using the You Only Look Once v5s (Yolov5s) network, aimed at improving the efficiency and accuracy of road condition assessments through advanced deep learning techniques. A comparative analysis of object detection algorithms, including You Only Look Once version 3 (Yolov3), Single Shot MultiBox Detector (SSD), and YOLOv5$s$, highlights YOLOv5s's superior speed and accuracy balance. Experimen-tal results demonstrate YOLOv5s's exceptional performance in accuracy, recall, and mean Average Precision (mAP) metrics. This intelligent system offers a robust technical solution to the global challenge of road maintenance, significantly enhancing road safety and maintenance effectiveness.