Pervasive and Mobile Computing最新文献

{"title":"SMOTE-Enhanced CNN-Bi-LSTM for wearable sensor-based human activity recognition","authors":"Ahmed Arafa ,&nbsp;Hadeer Harfoush ,&nbsp;Nawal El-Fishawy ,&nbsp;Marwa Radad","doi":"10.1016/j.pmcj.2026.102161","DOIUrl":"10.1016/j.pmcj.2026.102161","url":null,"abstract":"<div><div>Human Activity Recognition (HAR) refers to the automatic recognition of various human physical activities such as walking, sitting, and standing. HAR based on wearable sensors and smartphones has gained significant attention due to its wide range of applications in healthcare, sports, rehabilitation, and smart environments. Despite extensive research, challenges remain in modeling complex spatial–temporal dependencies within activity sequences and addressing class imbalance issues in sensor-based datasets. In this paper, we propose a hybrid deep learning model that integrates a Convolutional Neural Network (CNN) for spatial feature extraction followed by a Bidirectional Long Short-Term Memory (Bi-LSTM) for bi-directional sequential analysis and a fully connected layer for classifying the different types of activities. To address data imbalance and enhance the model robustness, three oversampling techniques — Random Oversampling (ROS), Adaptive Synthetic Sampling (ADASYN), and Synthetic Minority Over-sampling Technique (SMOTE) — were experimentally evaluated, with SMOTE demonstrating superior performance. The proposed model was trained and evaluated on six publicly available benchmark datasets: MHealth, PAMAP2, WISDM, UCI-HAR, USC-HAD and Opportunity datasets, achieving F1-score at 100%, 97.99%, 99.0%, 94.81%, 91.13% and 90.95% respectively. Comparative results demonstrate that the proposed framework outperforms several state-of-the-art methods across multiple datasets, confirming its robustness, reliability, and generalization capability for diverse human activity recognition scenarios.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102161"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145915147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Centralized sequential federated learning: single-server simulation for cross-region load forecasting","authors":"Cong Zhou ,&nbsp;Ming Li ,&nbsp;Longfa Yuan ,&nbsp;Nanwei Ding ,&nbsp;Ruijun Tie ,&nbsp;Zheng Zeng ,&nbsp;Zhen Li","doi":"10.1016/j.pmcj.2026.102176","DOIUrl":"10.1016/j.pmcj.2026.102176","url":null,"abstract":"<div><div>To address data distribution heterogeneity (non-IID) and training-efficiency challenges in cross-regional electric load forecasting, this paper proposes a Centralized Sequential Federated Learning (CSFL) framework. In a single-server, centrally stored setting, CSFL emulates multi-regional “clients” via logical partitions, employs sequential local training with central aggregation, and incorporates a dynamic learning-rate decay coupled with round resets to promote progressive integration of cross-regional features. Combined with a feature-engineering pipeline based on Ward’s minimum-variance clustering and Pearson correlation analysis, CSFL substantially improves cross-regional forecasting performance. Experiments show that, compared with directly applying a single local model across regions, CSFL reduces the average forecasting error by 22.3%, and its gains are statistically significant according to five independent runs with a paired <em>t</em>-test (<span><math><mrow><mi>p</mi><mo>=</mo><mn>0.032</mn></mrow></math></span>). The method achieves efficient cross-regional knowledge fusion in a single-server environment, offering a high-performing and easily deployable solution for power grid dispatch centers.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102176"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AutoCompress: Improving network efficiency for distributed wireless sensing applications","authors":"Yamini Shankar,&nbsp;Ayon Chakraborty","doi":"10.1016/j.pmcj.2026.102178","DOIUrl":"10.1016/j.pmcj.2026.102178","url":null,"abstract":"<div><div>Radio Frequency (RF)-based wireless sensing provides a privacy-preserving and non-intrusive alternative to vision-based systems for human activity recognition and environmental monitoring. However, transmitting high dimensional Channel State Information (CSI) from multiple distributed sensors leads to severe network congestion, especially at scale. We propose <span>AutoCompress</span>, a model-aware framework that intelligently compresses CSI spectrograms by prioritizing the most informative elements. Using Sparse Sensor Placement Optimization for Classification (SSPOC), <span>AutoCompress</span> computes element-wise importance scores for each spectrogram. These scores guide a sensor-subcarrier selection strategy under bandwidth constraints, implemented via the Prioritized Weighted Subcarrier-Sensor Cover (PWSSC) algorithm. Evaluated on the UT-HAR dataset and a real-world Nexmon-based testbed, <span>AutoCompress</span> achieves an average <span><math><mrow><mo>&gt;</mo><mn>4000</mn><mo>×</mo></mrow></math></span> reduction in data transmission, improves network throughput by 35.5%, and reduces latency by <span><math><mrow><mo>&gt;</mo><mn>90</mn><mtext>%</mtext></mrow></math></span>-all while maintaining high inference accuracy, compared to baseline uncompressed CSI data transmission. These results demonstrate <span>AutoCompress</span> as a scalable, interpretable, and bandwidth-efficient solution for distributed wireless sensing systems.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102178"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and implementation of a platform for stateful agents at the edge","authors":"Claudio Cicconetti ,&nbsp;Emanuele Carlini ,&nbsp;Chen Chen ,&nbsp;Roman Kolcun ,&nbsp;Richard Mortier","doi":"10.1016/j.pmcj.2026.102175","DOIUrl":"10.1016/j.pmcj.2026.102175","url":null,"abstract":"<div><div>Edge–cloud computing infrastructures are increasingly widespread as they combine the flexibility of cloud-native development tools with the performance and security of distributed computing environments. Function-as-a-Service has emerged as a powerful abstraction that overcomes the limitations of a micro-service architecture. However, it generally does not support stateful functions, making it unsuitable for many practical applications in, e.g., Internet of Things (IoT) and real-time analytics. In this paper, we explore a novel paradigm, based on stateful asynchronous agents, that goes beyond traditional serverless computing. We focus on several key technical aspects: programming model, deployment procedures, design of a flexible compute node, and state management. We illustrate our paradigm using the <em>EDGELESS</em> platform as a concrete implementation of this stateful agents’ pattern. We report proof-of-concept experiment results obtained in a testbed with heterogeneous resource-constrained edge nodes that showcase some distinguishing features of our platform: scalable management of lightweight function instances, the advantage of keeping the state local at function instances, and delegated orchestration to enable a third-party agent to make migration decisions in a group of local nodes.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102175"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TCP-HAR: On-Device Transferable and Copyright-Preserving Human Activity Recognition","authors":"Alessio Sacco ,&nbsp;Bruno Palermo ,&nbsp;Giulio Figliolino ,&nbsp;Chiara Contoli ,&nbsp;Guido Marchetto ,&nbsp;Flavio Esposito","doi":"10.1016/j.pmcj.2026.102163","DOIUrl":"10.1016/j.pmcj.2026.102163","url":null,"abstract":"<div><div>Teaching a machine to accurately identify human activities from sensor data poses a significant challenge, which is further compounded by considerations of data privacy, resource costs, and responsiveness, particularly within the constraints of devices like smartphones. While current solutions efficiently identify activities, trained models are barely portable in scenarios composed of diverse activities and limited battery life devices, such as smartphones. This paper introduces Transferable and Copyright-Preserving Human Activity Recognition (TCP-HAR), a mobile-based HAR system that integrates digital watermarking, Federated Learning (FL), Transfer Learning (TL), and compression techniques to provide efficient human activity recognition while providing copyright protection of deep neural network models over Android smartphones. Our solution optimizes the utilization of FL, TL, and their combination (FTL) by extensively testing standalone TL models in offline contexts and comparing these results with FL across a network of mobile devices. Our findings highlight the benefits of TCP-HAR for mobile environments in terms of accuracy, F1-score, and training time. In addition, our proposed watermarking mechanism is robust yet computationally efficient, ensuring ownership verification without compromising the scalability of the TFL process.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"117 ","pages":"Article 102163"},"PeriodicalIF":3.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146079112","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Traffic analysis and resource adaptation in large-scale 5G multi-layer edge networks","authors":"Marcello Pietri ,&nbsp;Natalia Selini Hadjidimitriou ,&nbsp;Marco Mamei ,&nbsp;Marco Picone ,&nbsp;Enrico Rossini ,&nbsp;Edoardo Maria Sanna ,&nbsp;Jovanka Adzic ,&nbsp;Andrea Buldorini","doi":"10.1016/j.pmcj.2025.102158","DOIUrl":"10.1016/j.pmcj.2025.102158","url":null,"abstract":"<div><div>In this research, we propose automating network management through data-driven intelligence, with a particular focus on anomalies and network traffic during specific events or periods. We analyze a large dataset collected by Orange mobile network operator in France with the goal of forecasting mobile demand for different classes of services. To model the underlying network infrastructure, we introduce a model for the underlying network based on a hierarchy of virtualization layers and slices. Building on this model, we propose algorithms to optimize the resources allocated to network slices and traffic distribution within the operator’s network. Network performance is evaluated as the fraction of time the mobile traffic is within the capacity of the network. Our results demonstrate that dynamic reallocation of resources among slices, and dynamic load balancing (traffic shaping) between nodes notably improves network performance. These results provide insights into critical aspects related to future 5G network management.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"116 ","pages":"Article 102158"},"PeriodicalIF":3.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sybil-aware adaptive defence framework for robust federated learning","authors":"Dnyanesh Khedekar ,&nbsp;Tanmaya Mahapatra ,&nbsp;Amitesh Singh Rajput","doi":"10.1016/j.pmcj.2025.102157","DOIUrl":"10.1016/j.pmcj.2025.102157","url":null,"abstract":"<div><div>Federated Learning (FL) enables distributed learning of sensitive and multi-location data to enhance data privacy and avoid data leakages. In FL, participating clients only share the trained local model updates to the external server for global aggregation. However, FL is vulnerable to security threats like adaptive data poisoning attacks in non-IID data scenarios, especially coordinated attacks by colluding sybils. Existing defences struggle against sybils as their focus has been on either analysing model behaviour or strengthening aggregation mechanisms. Sybils can collude by sharing their model updates with each other in the external environment. They can then strategically manipulate and share poisoned model updates for global aggregation, specifically employing label-flipping attacks. This paper introduces a novel defence framework that shifts the focus from model analysis to sybil behaviour analysis utilizing historical pairwise cosine similarity of client updates during the training process. By establishing a dynamic threshold and analysing patterns of similarity change among participating clients, the proposed defence framework detects sybils exhibiting coordinated data poisoning and excludes them from the subsequent global aggregation process. This approach is adaptable to various underlying aggregation methods, providing a robust defence against collusive data poisoning attacks and improving model resilience and convergence even under challenging non-IID settings. Comprehensive evaluations demonstrate a significant reduction in the Attack Success Ratio, i.e. from over 40% to below 1%, showcasing its superior efficacy compared to state-of-the-art defences against targeted data poisoning attacks.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"116 ","pages":"Article 102157"},"PeriodicalIF":3.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145790984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A self-adaptive framework for child healthcare in IoT environment using AI-based prediction","authors":"Euijong Lee ,&nbsp;Jaemin Jeong ,&nbsp;Gyuchan Jo ,&nbsp;Taegyeom Lee ,&nbsp;Gee-Myung Moon ,&nbsp;Young-Duk Seo ,&nbsp;Ji-Hoon Jeong","doi":"10.1016/j.pmcj.2025.102153","DOIUrl":"10.1016/j.pmcj.2025.102153","url":null,"abstract":"<div><div>Childhood overweight and obesity have emerged as some of the most serious global public health challenges, as they can lead to a variety of health-related problems and the early development of chronic diseases. The healthcare domain has been transformed by the integration of the Internet of Things (IoT), leading to the development of digital healthcare solutions. This integration has led to an increase in the health data collected from a variety of IoT sources. Consequently, advanced technologies are required to analyze health data, and Artificial Intelligence (AI) has been employed to extract meaningful insights from the data. Moreover, these technologies can be effectively applied in healthcare to address childhood overweight and obesity. A self-adaptive framework is proposed to manage childhood weight using lifelog data from IoT environments. An ensemble-based learning model is applied to predict weight using the lifelog data. A smartphone application providing real-world services was developed, and lifelog data were collected from a cohort of 362 children aged 104 to 152 months. Reasonable results were obtained, indicating that the proposed ensemble model can predict childhood weight change using lifelog data with an accuracy of 0.9711 and an F1-score 0.9725. Also, the results indicated that appropriate rewards can encourage human involvement and positively influence data quality.The results demonstrated the efficiency of the proposed framework with human involvement in weight prediction. The experimental results demonstrate the efficiency of the proposed framework and its potential application in healthcare services to enhance children’s health.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"116 ","pages":"Article 102153"},"PeriodicalIF":3.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145738157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The structure design of the smart sock prototype integrated with stretchable hybrid electronic temperature sensing yarn for real-time temperature monitoring","authors":"Sumonta Ghosh ,&nbsp;Fenye Meng ,&nbsp;Rony Shaha ,&nbsp;Jiyong Hu","doi":"10.1016/j.pmcj.2025.102136","DOIUrl":"10.1016/j.pmcj.2025.102136","url":null,"abstract":"<div><div>Rapid advances in electronic textiles have enabled the development of smart socks with temperature-sensing capabilities for real-time foot temperature monitoring, where stretchability, user comfort, durability, bending, washability, sensing location error during wear, and higher manufacturing cost are drawbacks. This study introduces a smart sock prototype that integrates highly stretchable hybrid electronic temperature-sensing (SHETS) yarns in key physiological foot regions—hallux, metatarsal, midfoot, and heel—to detect temperature variations and address the challenges of existing and commercial products. Structural design of SHETS yarns involved wrapping, novel interconnection, encapsulation, and braiding techniques to integrate miniature thermistor within the yarn structure, showing high stretchability, durability, washability, and sensing accuracy. Low-power microcontroller transmits analog data to a digital format, and the web-based interface enables users to monitor data through mobile phone applications in real-time. The prototype demonstrates high accuracy, durability, and reliability under various conditions, with average temperature error ranging from ±0.23 °C to ±0.27 °C. The prototype maintains durability and stability in hot, cold, and sweaty conditions. Physical activities like walking, running, and cycling demonstrate the durability and stability of foot temperature changes, while extended wear shows low power consumption and stability. The device withstands over 30 washing cycles with minimal accuracy loss (maximum ±0.28 °C error) and retains the mechanical and electrical properties of SHETS yarn under repeated stretching and bending. Additionally, the android-based intelligent foot alert system enhances usability by providing real-time monitoring and alerts on smartphones, offering a cost-effective, energy-efficient, and user-friendly solution for proactive foot health management. Available code: <span><span>https://github.com/Sumonta-e-textile/Smart-Materials-and-Electronic-Textiles-Lab</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"116 ","pages":"Article 102136"},"PeriodicalIF":3.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145659149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MDWD-KAN: Multilevel discrete wavelet decomposition with Kolmogorov–Arnold network for fall detection and activity recognition using wearable sensors","authors":"Zhiyuan Jiang ,&nbsp;Sike Ni ,&nbsp;Mohammed A.A. Al-qaness","doi":"10.1016/j.pmcj.2026.102160","DOIUrl":"10.1016/j.pmcj.2026.102160","url":null,"abstract":"<div><div>Fall detection and Human Activity Recognition (HAR) are crucial applications in pervasive and mobile computing, enabling real-time monitoring of individuals – especially the elderly or patients – for enhanced safety and health management. Wearable devices have emerged as a critical tool for continuous activity monitoring, enabling real-time detection and intervention. However, the quality of data collected by wearable sensors faces several challenges, including noise interference, instability due to wearing, and individual differences. To address these challenges, this paper proposes a feature stepwise fusion detection system based on a multilevel discrete wavelet decomposition with Kolmogorov–Arnold Network, namely MDWD-KAN. This model utilizes multilevel wavelet decomposition to perform multiresolution analysis on sensor signals, extracting multilevel features and effectively enhancing feature stability and noise resistance. Additionally, through a heterogeneous model and a multilevel feature fusion strategy, MDWD-KAN achieves complementary low-frequency and high-frequency features, improving the recognition capability for complex motion patterns. Experiments were conducted on three public datasets: MobiAct, SisFall, and UniMiB-SHAR. The results show that MDWD-KAN achieves average recognition accuracies of 99.67%, 99.90%, and 99.65%, respectively, for binary classification (fall and non-fall), and 98.85%, 85.45%, and 96.86%, respectively, for multiclassification.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"116 ","pages":"Article 102160"},"PeriodicalIF":3.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145925535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}