Snoring and breath-stopping are key symptoms of sleep apnea. Most existing studies primarily focus on wearable devices or smartphone-based systems. Wearable devices can be uncomfortable, while smartphone-based systems often require specific angles, distances, or positions, making them sensitive to environmental changes. This paper proposes a contactless and engagement-free system for snoring and breath-stopping detection using a seismic sensor. Distinguishing between snoring, breath-stopping, and normal breathing from raw data alone is challenging. Snoring features typically reside in a higher frequency range than breath-stopping and normal breathing, with breath-stopping features appearing in a lower frequency range. Calculating the differential and integral of raw data can enhance features in low and high frequencies, respectively. We introduce AFFCL, an attention feature fusion and contrastive learning framework to leverage information from differential and integral signals. AFFCL generates both shared and exclusive features from the differential and integral signals and employs an attention mechanism for feature fusion. Additionally, cluster-level supervised contrastive learning in AFFCL further enhances system performance. Our system has been performed 5-fold cross-validation on 44 people, which achieves an average accuracy of 93.40% and an F1 score of 92.42%. The accuracy for detecting breath-stopping, snoring, and normal breathing are 89.54%, 94.60%, and 96.06%, respectively. Evaluation results demonstrate that our system effectively identifies breath-stopping and snoring.

The recognition of Activities of Daily Living (ADLs) from event-triggered ambient sensors is an essential task in Ambient Assisted Living, yet existing methods remain constrained by representation-level limitations. Sequence-based approaches preserve temporal order of sensor activations but are sensitive to noise and lack spatial awareness, while image-based approaches capture global patterns and implicit spatial correlations but compress fine-grained temporal dynamics and distort sensor layouts. Naïve fusion (e.g., feature concatenation) fails to enforce alignment between sequence- and image-based representation views, underutilizing their complementary strengths. We propose Contrastive Alignment for ADL Recognition from Event-Triggered Sensor Streams (CARE), an end-to-end framework that jointly optimizes representation learning via Sequence–Image Contrastive Alignment (SICA) and classification via cross-entropy, ensuring both cross-representation alignment and task-specific discriminability. CARE integrates (i) time-aware, noise-resilient sequence encoding with (ii) spatially-informed and frequency-sensitive image representations, and employs (iii) a joint contrastive-classification objective for end-to-end learning of aligned and discriminative embeddings. Evaluated on three CASAS datasets, CARE achieves state-of-the-art performance (89.8% on Milan, 88.9% on Cairo, and 73.3% on Kyoto7) and demonstrates robustness to sensor malfunctions and layout variability, highlighting its potential for reliable ADL recognition in smart homes. We release our code at https://github.com/Jhziiiig/CARE.

Smart homes equipped with ambient sensors enable privacy conscious monitoring of Activities of Daily Living (ADLs), but produce event-triggered sensor logs that differ fundamentally from regularly sampled time series. These data are discrete, symbolic, irregular, and spatially grounded, exhibiting strong structural dependencies across sensor states and locations. Collecting sufficiently diverse labeled data with adequate structural coverage remains challenging, motivating the need for realistic synthetic data generation. Existing time-series generation methods are designed for continuous or regularly sampled temporal signals and are poorly aligned with smart-home sensor data, where realism fundamentally requires jointly preserving coherent statistical patterns, physical feasibility, and activity-level semantic consistency. We propose ADLGen, a unified framework for synthesizing symbolic, event-triggered sensor sequences. ADLGen integrates a representation tailored to symbolic event data, a generation process that enforces spatial constraints while balancing diversity and coherence, and an LLM-based semantic evaluation and refinement stage for identifying and correcting behavioral inconsistencies, with efficient offline deployment through compact local models. Experiments show that ADLGen synthesizes sequences that closely match real data while improving intrinsic realism, downstream activity recognition, rare-activity learning, and cross-home generalization over strong baselines.

Fine-tuning large language models (LLMs) faces significant memory challenges due to the high cost of back-propagation.MeZO addresses this issue using zeroth-order (ZO) optimization, matching memory usage to inference but suffering from slow convergence due to varying curvatures across model parameters.To overcome this limitation, we propose HELENE, a scalable and memoryefficient optimizer that integrates annealed A-GNB gradients with diagonal Hessian estimation and layer-wise clipping as a second-order pre-conditioner.HELENE provably accelerates and stabilizes convergence by reducing dependence on total parameter space and scaling with the larger layer dimension.Experiments on RoBERTa-large and OPT-1.3Bdemonstrate superior performances, achieving up to 20× speedup over MeZO with an average accuracy improvement of 1.5%.HELENE also supports full and parameter-efficient fine-tuning methods, outperforming several state-of-the-art optimizers.

Wireless Powered Communication Network (WPCN) is a new paradigm to allow low-power wireless devices to exchange data packets and receive stable energy transfer from a power source and thus support autonomous and sustainable network operations without battery replacements. In recent years, we have witnessed the growing deployment of WPCNs in both industrial and consumer IoT systems to support time-triggered and event-triggered monitoring applications. In this article, we present a novel reinforcement learning (RL)-based on-demand path planning framework to plan the trajectory of a Mobile Charger (MC) and schedule the charging sequence of wireless devices to sustain the network operations. A modified Deep Q-learning approach is designed to charge the wireless devices by balancing between their residual energy level and the distance from the MC to the device. This approach minimizes the total distance that the MC travels while ensuring that individual residual energy of a given set of devices is above a designated threshold. Extensive experimental results from both the Gazebo-based high-fidelity simulation and Turtlebot-based physical testbed demonstrate that our approach outperforms the classic scheduling methods (e.g., Nearest Job Next and Earliest Deadline First), state-of-the-art scheduling methods(Extended Particle Swarm Optimization, Enhanced Teaching–Learning-Based Optimization Algorithm and Spatiotemporal Optimization for Charging Scheduling), learning-based methods (e.g., Proximal Policy Optimization and Advantage Actor-Critic) with similar sample sizes for training.

In harsh underwater environments, the localization of network nodes faces severe challenges due to open deployment environments. Most existing underwater localization methods suffer from privacy leaks. However, privacy protection schemes applied in terrestrial networks are not viable for underwater acoustic networks due to stratification effects and multipath complexities. In this paper, we introduce a secure localization scheme for underwater wireless sensor networks (UWSNs) utilizing cooperative beamforming among mobile underwater anchor nodes. With this scheme, the underwater sensor communicates and ranges with mobile anchor nodes to perform self-localization via time difference of arrival (TDOA) algorithm. However, the presence of eavesdroppers poses a threat by intercepting information emitted by the anchors. To avoid localization information leakage, then we model the secure localization requirement as a multi-anchors multi-objective dual joint optimization problem to enhance both security and energy performance. The deep reinforcement learning (DRL)-based multi-agent deep deterministic policy gradient (MADDPG) algorithm is applied to solve the optimization problem. Both simulation and field experimental results robustly validate the efficiency and accuracy of the proposed secure localization scheme.

In harsh underwater environments, position accuracy and privacy of sensors are equally important. Most underwater localization schemes suffer from privacy leakage, and privacy protection schemes for terrestrial networks are not applicable to underwater acoustic networks with stratification effects and multipath. Therefore, this paper proposes a secure localization scheme based on autonomous underwater vehicle (AUV) formation cooperative beamforming for underwater wire-less sensor networks (UWSNs) considering acoustic channel char-acteristic. The underwater sensor receives position information from multiple AUV anchors and utilizes time difference of arrival (TDOA) for self-localization. Eavesdroppers exist to overhear the information emitted by the anchors, thereby destroying the entire localization system. We model the secure localization requirement as a multi-AUV multi-objective dual joint optimization problem to optimize the security and energy performance, and adopt the deep reinforcement learning (DRL)-based multi-agent deep deterministic policy gradient (MADDPG) algorithm to solve it. Simulation and sea experimental results corroborate the efficiency and accuracy of the proposed secure localization scheme.

Underwater acoustic (UWA) communication faces security challenges owing to the open nature of the UWA channel and the uncertainty of the underwater node deployment environment. Key generation schemes based on physical layer information do not require predefined keys or the introduction of additional assistance nodes, which is feasible in resource-constrained underwater scenarios. This article proposes an underwater key generation scheme that includes a channel probing protocol and a key generation algorithm. Based on the spatio-temporal dynamic characteristics of the UWA channel, the amplitude of and time delay information about the channel impulse responses (CIRs) are combined as channel parameters to generate the raw keys. Further, a synchronous probing approach is designed to decrease the probing time difference between the forward and backward channels to enhance the reciprocity of the measurements. The results of the field experiments demonstrated the effectiveness of the key generation scheme and the performance improvements resulting from synchronous probing.

Body Mass Index (BMI) is a critical metric for assessing public health and identifying populations at risk for obesity-related conditions. Traditional BMI monitoring methods often raise privacy concerns and require active cooperation from individuals, limiting their applicability in real-world scenarios. This paper introduces a novel approach to BMI monitoring that leverages proximal federated learning (PFL) using commodity WiFi devices. Our method addresses the challenges of data heterogeneity and intermittent connectivity in FL. By our approach, the Adaptive Elastic Stochastic Alternating Direction Method of Multipliers (AESADMM), an optimization algorithm designed to handle data heterogeneity and intermittent connectivity in FL scenarios, our system collects Channel State Information (CSI) from WiFi signals to passively classify BMI based on the impact of different body shapes on signal propagation. This approach ensures privacy preservation and eliminates the need for active participant involvement. Theoretical analysis and empirical results demonstrate the superior accuracy, reduced communication costs, and enhanced scalability of our proposed method compared to existing personalized FL frameworks, showcasing its potential as an effective tool for large-scale BMI monitoring in diverse environments.

The widespread deployment of machine learning techniques in ubiquitous computing environments has sparked interests in exploiting the vast amount of data stored on mobile devices. To preserve data privacy, federated learning (FL) has been proposed to learn a shared model by performing distributed training locally on participating devices and aggregating the local models into a global one. Reinforcement learning (RL) can improve indoor localization by accounting for environmental dynamics, but has been trained on centralized data. An FL version of RL can help train a global localization model using data from different user clients whereas keeping data on device without centralization. We propose a personalized federated RL for indoor localization that addresses two major challenges. Due to the limited network connectivity of mobile devices, under the federated computing setting, it is impractical to aggregate updates from all clients in any learning iteration. Data gathered on different devices are heterogeneous, imposing difficulty in training high accuracy models. In our approach, each client performs RL to learn an action policy that can quickly search for a target based on its own data (e.g., personalized) and then a central server communicates with clients only for their model updates and learns a global model that is in the proximity of all client models (e.g., federated). Empirical evaluations demonstrate superior performance of the proposed approach in terms of localization accuracy and steadiness over existing methods. We further extend our approach to few-shot learning that can quickly position a new user with sparse annotated location data.

Considering the high complexity of actual railway line conditions, this paper proposes a two-level energy-efficient timetable optimization method empowered by time-energy Pareto solution to reduce energy consumption while maintaining the existing infrastructure unchanged. At the train-level, an efficient equivalence method for actual line conditions, including varying slopes, curves, and tunnels is proposed to formulate the train driving process as a multi-objective optimization model to balance the time cost and energy consumption. An improved non-dominated sorting genetic algorithm II (INSGA-II) enhanced by differential evolution (DE) and a new crowding distance (NCD) operator is further proposed to access the time-energy Pareto solution of the potential speed profile for a single train by comparing different control strategies. At the timetable-level, an integer linear programming (ILP) model is designed with the computed train-level Pareto solution to optimize the energy-efficient timetable by restricting the headway between trains, in which a novel operation time-based branch-and-bound (BBOT) method is proposed to enable quick search of optimal control strategy and thus allows for accurate output of the optimal timetable while retaining real simulation results. A case study on the actual operation data of the Beijing-Jinan section of the Beijing-Shanghai high-speed railway shows that the optimized timetable can save up to 18.69% of energy when the train is on time. In cases of train delays, the total savings under 8-min, 9-min, and 14-min delay scenarios are 4.69%, 9.93%, and 8.05%, respectively compared to the method using time-oriented strategies, which have demonstrated the effectiveness of the proposed two-level optimization formulation.

Accurate prediction of crop yield under the conditions of climate change is crucial to ensure food security. Transformers have shown remarkable success in modeling sequential data and hold the potential for improving crop yield prediction. To understand how weather and meteorological sequence variables affect crop yield, the positional encoding used in Transformers is typically shared across different sample sequences. We argue that it is necessary and beneficial to differentiate the positional encoding for distinct samples based on time-invariant properties of the sequences. Particularly, the sequence variables influencing crop yield vary according to static variables such as geographical locations. Sample data from southern areas may benefit from more tailored positional encoding different from that for northern areas. We propose a novel transformer based architecture for accurate and robust crop yield prediction, by introducing a Customized Positional Encoding (CPE) that encodes a sequence adaptively according to static information associated with the sequence. Empirical studies demonstrate the effectiveness of the proposed novel architecture and show that partially lin- earized attention better captures the bias introduced by side information than softmax re-weighting. The resultant crop yield prediction model is robust to climate change, with mean-absolute-error reduced by up to 26% compared to the best baseline model in extreme drought years.

This paper explores the challenges of implementing Federated Learning (FL) in practical scenarios featuring isolated nodes with data heterogeneity, which can only be connected to the server through wireless links in an infrastructure-less environment. To overcome these challenges, we propose a novel mobilizing personalized FL approach, which aims to facilitate mobility and resilience. Specifically, we develop a novel optimization algorithm called Random Walk Stochastic Alternating Direction Method of Multipliers (RWSADMM). RWSADMM capitalizes on the server's random movement toward clients and formulates local proximity among their adjacent clients based on hard inequality constraints rather than requiring consensus updates or introducing bias via regularization methods. To mitigate the computational burden on the clients, an efficient stochastic solver of the approximated optimization problem is designed in RWSADMM, which provably converges to the stationary point almost surely in expectation. Our theoretical and empirical results demonstrate the provable fast convergence and substantial accuracy improvements achieved by RWSADMM compared to baseline methods, along with its benefits of reduced communication costs and enhanced scalability.

Learning feature interactions can be the key for multivariate predictive modeling. ReLU-activated neural networks create piecewise linear prediction models, and other nonlinear activation functions lead to models with only high-order feature interactions. Recent methods incorporate candidate polynomial terms of fixed orders into deep learning, which is subject to the issue of combinatorial explosion, or learn the orders that are difficult to adapt to different regions of the feature space. We propose a Polyhedron Attention Module (PAM) to create piecewise polynomial models where the input space is split into polyhedrons which define the different pieces and on each piece the hyperplanes that define the polyhedron boundary multiply to form the interactive terms, resulting in interactions of adaptive order to each piece. PAM is interpretable to identify important interactions in predicting a target. Theoretic analysis shows that PAM has stronger expression capability than ReLU-activated networks. Extensive experimental results demonstrate the superior classification performance of PAM on massive datasets of the click-through rate prediction and PAM can learn meaningful interaction effects in a medical problem.

The demand for indoor localization services in the Internet of Things (IoT) has been increasing dramatically during the last decade. Many indoor localization systems adopt Wi-Fi fingerprinting with received signal strength indicators (RSSIs) as a source of sensors to localize an object because it is cost effective and can give high accuracy. However, the fluctuation of wireless signals resulting from environmental uncertainties leads to considerable variations in RSSIs, which poses a challenge to accurate localization on a single floor, not to mention multifloor or even 3-D localization. Most existing multifloor methods employ a sequential approach where a different algorithm is tailored for each step in the sequence to determine the floor and then the location of an object. In this article, we formulate the indoor localization problem as a Markov decision process rather than a typical classification or regression problem. A deep reinforcement learning method is used to bisect the search space in a hierarchy from the entire building down to a prespecified distance scale to the object position. This approach significantly reduces the time complexity of the searching fromO(N3) toO(logN), where N indicates the localization resolution. The proposed method tackles environmental dynamics with Wi-Fi fingerprinting for 3-D continuous space. The experimental results demonstrate the high accuracy, efficiency, and robustness of the proposed approach.

The location-based services for Internet of Things (IoTs) have attracted extensive research effort during the last decades. Wi-Fi fingerprinting with received signal strength indicator (RSSI) has been widely adopted in vast indoor localization systems due to its relatively low cost and the potency for high accuracy. However, the fluctuation of wireless signal resulting from environment uncertainties leads to considerable variations on RSSIs, which poses grand challenges to the fingerprint-based indoor localization regarding positioning accuracy. In this paper, we propose a top-down searching method using a deep reinforcement learning agent to tackle environment dynamics in indoor positioning with Wi-Fi fingerprints. Our model learns an action policy that is capable to localize 75% of the targets in an area of 25000m2within 0.55m.

Abstract Real‐time streaming of shape deformations in a shared distributed virtual environment is a challenging task due to the difficulty of transmitting large amounts of 3D animation data to multiple receiving parties at a high frame rate. In this paper, we present a framework for streaming 3D shape deformations, which allows shapes with multi‐resolutions to share the same deformations simultaneously in real time. The geometry and motion of deformingmeshorpoint‐sampledsurfaces are compactly encoded, transmitted, and reconstructed using the spectra of the manifold harmonics. A receiver‐based multi‐resolution surface reconstruction approach is introduced, which allows deforming shapes to switch smoothly between continuous multi‐resolutions. On the basis of this dynamic reconstruction scheme, a frame rate control algorithm is further proposed to achieve rendering at interactive rates. We also demonstrate an efficient interpolation‐based strategy to reduce computing of deformation. The experiments conducted on bothmeshandpoint‐sampledsurfaces show that our approach achieves efficient performance even if deformations of complex 3D surfaces are streamed. Copyright © 2013 John Wiley & Sons, Ltd.

With growing number of high quality 3D models published online, the technique of generating efficient and economical 3D model previews has raised increasing concerns. Although several previous work has been done on the preview of static mesh, that of animated mesh is different and more complex due to the difficulty in describing the animation. In this paper, we present a novel method of automatic preview generation for 3D mesh animation. A new measure named inter-frame surface saliency, which evaluates both inter-frame motions and surface saliency in each frame, is introduced. Given an animated mesh, an energy function combining this measure and camera smoothness is constructed for the representative viewpoints selection in key frames, and then an optimal camera path is generated. Finally, a brief but informative preview could be created by moving the camera along this path with frame rate control.