Previous studies on human activity recognition (HAR) using mmWave radar in IoT scenarios have relied on complex network architectures and heavy preprocessing, making them computationally expensive and difficult to deploy on resource-constrained edge devices (e.g., smart homes, healthcare). To address this, we propose LWDSC-Net, a lightweight wavelet dual-branch coupling network that embodies a novel, physically-interpretable design paradigm. Inspired by classic signal processing, LWDSC-Net embeds a 1D Haar wavelet transform (WT) as a front-end layer, enabling an end-to-end, structured decoupling of raw signals to construct a dual-branch structure with low and high frequencies (LF & HF) without external manual preprocessing. This signal-architecture co-design dedicates each branch to its respective frequency components, with the multi-level WT concept further extended to the HF branch. For the LF component branch, we propose an improved lightweight temporal convolutional network (LightTCN), which builds the feed-forward network using depthwise convolution. LightTCN reduces the depth of module stacking and efficiently models long-term global dependencies across the entire action sequence. For the HF components branch, we propose the wavelet-domain depthwise separable convolution (WD-DSC) module. It enhances micro-motion features by combining secondary wavelet reconstruction with wavelet-domain convolution, and further refines local detail information through deep convolutional layers. Experimental results show that LWDSC-Net achieves an accuracy of 98.76% on the public dataset while significantly reducing the number of model parameters and computational complexity. More importantly, deployment on an NVIDIA Jetson Nano confirms its excellent real-world performance, featuring ultra-low latency and power consumption, which highlights its outstanding potential for edge deployment.

High-rise fires pose significant risks due to their complex structures and high population density, making timely and effective detection methods essential. Compared to traditional sensor-or camera-based detection methods, wireless sensingbased human-fire classification (HFC) methods offer significant cost-effectiveness advantages. While Channel State Information (CSI) provides more detailed and accurate channel data compared to Received Signal Strength (RSS), its acquisition and processing are more challenging. On the other hand, RSS-based methods are easier to implement and more cost-effective. Therefore, selecting appropriate methods for specific scenarios is crucial to achieving a balance between performance and cost-effectiveness. To this end, this paper proposes an innovative method called Wi-HFC, which leverages deep learning to evaluate the performance of RSS and CSI in various human-fire classification tasks. Specifically, a dataset of RSS and CSI data from five classification tasks in real fire scenarios was collected and evaluated using a custom-designed convolutional neural network-based deep learning model. Experimental results indicate that RSS is a cost-effective choice for short distances or simple environments, whereas CSI demonstrates significant advantages in scenarios requiring higher accuracy and involving greater environmental complexity. Furthermore, the developed dataset is publicly available at https://github.com/T-bjq/Wi-HFC-dataset, providing resources for further research.

Incurable Alzheimer's disease (AD) plagues many elderly people and families. It is important to accurately diagnose and predict it at an early stage. However, the existing methods have shortcomings, such as inability to learn local and global information and the inability to extract effective features. In this paper, we propose a lightweight classification network Local and Global Graph ConvNeXt. This model has a hybrid architecture of convolutional neural network and Transformers. We build the Global NeXt Block and the Local NeXt Block to extract the local and global features of the structural magnetic resonance imaging (sMRI). These two blocks are optimized by adding global multilayer perceptron and locally grouped attention, respectively. Then, the features are fed into the pixel graph neural network to aggregate the valid pixel features using mask attention. In addition, we decoupled the loss by category to optimize the calculation of the loss. This method was tested on slices of the processed sMRI datasets from ADNI and achieved excellent performance. Our model achieves 95.81% accuracy with fewer parameters and floating point operations per second (FLOPS) than other classical efficient models in the diagnosis of AD.

Due to the presence of redundancy and interference, frame sampling is a promising but challenging solution to mitigate the expensive computation of video action recognition. Although the motion prior has shown great potential for frame selection, existing motion-based strategies suffer from limitations in terms of robustness and interpretive evaluation. In this paper, we devise a robust frame sampling strategy called positive motion guided sampler (PMGSampler). It consists of two procedures, local motion capture and global motion statistics. At the local level, we propose two concepts about inter-frame motion amplitude and motion continuity, which helps to perceive the movement of subjects and identify abnormal events that may generate negative pseudo-motion information. Then, through a global analysis of the obtained local motions, the sampler becomes more sensitive to informative frames and robust to outliers. The proposed sampler can be applied to most existing models for improving recognition accuracy. We conduct extensive experiments on four widely-used benchmarks to demonstrate the superiority of our PMGSampler over other methods of the same type. In addition, to analyse how sampled frames influence action recognition, we present a visual interpretation method for video models, termed as spatio-temporal class activation map (STCAM). By introducing spatial and temporal branches, our STCAM is able to visualise the salience of spatio-temporal features. With the help of STCAM, we can further intuitively evaluate the performance of different sampling strategies.

The electromagnetic environments have become more complex with the development of wireless communication technology. Signal modulation classification has attracted extensive attention due to its application in electronic countermeasures and physical layer security threat prevention under complex electromagnetic environments. Excellent classification performance requirements challenge the adaptability of the method and the ability to extract modulation characteristics. This paper proposes an automated machine learning framework, AutoSMC, for signal modulation classification. An adaptive signal augmentation method is proposed to adapt to the network changes during the search process. In order to extract the modulation features effectively, an scalable convolutional random fourier feature block is proposed. Moreover, the initial search space of the framework is given. The Bayesian Optimization is used to drive hyperparameter optimization to achieve AutoSMC and obtain the optimal method state. Great experiments were carried out on RADIOML 2016.10A and RADIOML 2016.10B. Experimental evaluations on these datasets show that our approach AutoSMC achieves state-of-the-art results compared to the most relevant signal modulation classification methods.

Trajectory recovery aims to restore missing data for reconstructing high-quality human mobility trajectory, which benefits a wide range of intelligent transportation system applications ranging from urban planning to travel recommendation. Inspired by the inherent regularity of human mobility, existing approaches capture spatial-temporal transition regularities in historical trajectory for data recovery. Although promising, existing solutions suffer from two limitations.i)These methods fail to recover occasionally-visited points (OVP) due to the lack of semantic information when learning spatial-temporal transition regularities.ii)The information before and after missing data is not be fully utilized for trajectory recovery. To overcome the limitations, we propose a novel semantic-aware trajectory recovery framework. First, we leverage heterogeneous information network (HIN) to encode various semantic correlations for obtaining rich semantic embeddings, which are fused with temporal information to form spatial-temporal semantic context. Then, we develop a behavior attention mechanism to capture semantic behavior transition regularities for trajectory recovery based on the bidirectional spatial-temporal semantic context before and after missing data. Extensive experiments on four real-world datasets show that our proposed method outperforms the state-of-the-arts by 7%-11% in term of recall, F1-score and mean average precision.

Hyperspectral image classification (HSIC) has attracted widespread attention due to its important application in environment alterations and geophysical disaster monitoring. However, surface cultivation is not static as time passes, which leads to different hyperspectral images information collected from the same area at different time periods. Therefore, researchers are currently eager to construct a HSIC model that continuously acquires new classes of data. During the continuous learning process, the model is expected to not only effective in extracting unique spatial-spectral features of the hyperspectral image, but also ensures the ability to maintain the old classes knowledge while learning new data. To achieve this purpose, we propose a method which based on geometric spatial-spectral feature integration network with class incremental learning (GS2FIN-CIL) framework in continuous learning to make the model adaptable to new classes data and not overly forgetting the old classes knowledge during the training process. We conduct extensive experiments with the proposed GS2FIN-CIL method on widely-used hyperspectral datasets including Indian Pines, PaviaU and Salinas. The experimental results show that our GS2FIN-CIL method can achieve significantly improved results compared to current state-of-the-art class incremental learning methods, allowing for efficient adaptation and utilization of spatial-spectral features in processing new classes of hyperspectral images and alleviating the problem of catastrophic forgetting of learned old classes knowledge. The GS2FIN-CIL method could be successfully applied to the challenge of adding new classes data in HSIC task.

An adaptive multiple input and multiple output (MIMO) system based on the unified belief propagation (BP) detection is proposed. A BP detector composed of a serial of component detectors is first presented. With a unified design of the BP detector, a multi-rate MIMO system adaptive to channel variations is then developed, which aims at achieving the maximal throughput performance. The usage of the unified BP detector eliminates the multiple detector modules at the receiver in conventional multi-mode adaptive MIMO systems. Further, the linear complexity to space time block length and parallel operation of the unified BP detection provide the advantages of low complexity, low detection delay and smooth switching between different data rates. With the average receiving signal-to-noise ratio (SNR) based switching mechanism, the proposed adaptive MIMO framework adaptively chooses the appropriate rate for the transmission. Simulation results are provided to show the BER and complexity performance of a specific BP detector as well as the throughput performance of the adaptive scheme.

A bidirectional adaptive detection method was proposed to prevent error propagation based on sequential Gaussian approximation algorithm for MIMO systems. Conventional sequential Gaussian approximation detection executes a tree search at the receiver, when the number of searching paths is large, error propagation is well prevented at the cost of high complexity, when few paths are searched, serious error propagation may occur. In the new method, transmitted symbols were estimated parallel both in sequential order and inverse order, and the number of searching paths was determined by comparing the results of bidirectional detection, which can effectively prevent error propagation at reduced complexity. The novel algorithm can be executed at low delay because of parallel computing, and shows good performance at low complexity.

This paper describes how to use XML Web services and public key cryptography on small devices in consumer settings to achieve a high level of interoperation and security. This is done while maintaining the strict performance requirements that are expected from low-cost devices operating with limited energy and other resources.

AIMD is a widely-used network congestion control scheme. Despite its discontinuous control behavior, the majority of contemporary literature employed a statistically-averaged continuous model to approximate AIMD without considering its discontinuity. The design of a discontinuous control system must be based on rules that are entirely different from that of continuous control systems. Ignoring discontinuity issues results in great discrepancy between analytical models and the practice. In this paper we use the sliding mode control (SMC) theory to investigate congestion control without ignoring its discontinuity. Based on the SMC theory, the design of discontinuous (congestion) control systems must consider the relative degree and zero dynamics of the system, in order to guarantee asymptotic stability. This framework can precisely reflect the behavior of the control rules and the controlled objective of a congestion control system. We show that the relative degree of the control system of rate-based, AIMD flow-control algorithms is two. That is, to apply sound control principles to the design of AIMD algorithms, one should use both the queue length error and its first order time derivative to construct the switching function of the control model of an active queue management scheme. Based on the SMC model, one can quantify the tradeoffs among the convergence speed, the amount of throttling adjustments, and the degree of oscillations. We show quantitatively that one can guarantee stability conditions, drastically reduce oscillation of AIMD without significant loss of fairness and stability, and quantitative understanding of the tradeoffs among oscillation, delay and fairness.

Proposes a coordinated defense scheme of distributed denial of service (DDoS) network attacks, based on the backward-propagation, on-off control strategy. When a DDoS attack is in effect, a high concentration of malicious packet streams are routed to the victim in a short time, making it a hot spot. A similar problem has been observed in multiprocessor systems, where a hot spot is formed when a large number of processors access simultaneously shared variables in the same memory module. Despite the similar terminologies used here, solutions for multiprocessor hot spot problems cannot be applied to that in the Internet, because the hot traffic in DDoS may only represent a small fraction of the Internet traffic, and the attack strategies on the Internet are far more sophisticated than that in the multiprocessor systems. The performance impact on the hot spot is related to the total hot packet rate that can be tolerated by the victim. We present a backward pressure propagation, feedback control scheme to defend DDoS attacks. We use a generic network model to analyze the dynamics of network traffic, and develop the algorithms for rate-based and queue-length-based feedback control. We show a simple design to implement our control scheme on a practical switch queue architecture.