Ana Patrícia Rocha, Afonso Guimarães, Ilídio C. Oliveira, José Maria Fernandes, Miguel Oliveira e Silva, Samuel Silva, António Teixeira
{"title":"In-bed gesture recognition to support the communication of people with Aphasia","authors":"Ana Patrícia Rocha, Afonso Guimarães, Ilídio C. Oliveira, José Maria Fernandes, Miguel Oliveira e Silva, Samuel Silva, António Teixeira","doi":"10.1016/j.pmcj.2025.102029","DOIUrl":"10.1016/j.pmcj.2025.102029","url":null,"abstract":"<div><div>People with language impairments can have difficulties expressing themselves to others, leading to major limitations to their safety, independence, and quality of life in general. Aphasia is an example of an acquired language impairment that affects many people (around 2 million in the United States), being commonly caused by stroke, but also by other brain injuries. Several augmentative and alternative communication solutions are available to help people with communication difficulties, but they are generally not suitable for all contexts of use (e.g., lying in bed). In the scope of the “APH-ALARM” project, which aimed at developing solutions to support people with Aphasia, we envision a system for the bedroom that enables conveying messages to be sent to a caregiver or relative, for example. Focusing on gesture input, in this contribution, we investigated if smartwatch sensors and machine learning (ML) can be used to recognise arm gestures executed while lying. We explored different factors, namely the feature set, size of the sliding window used for feature extraction, and ML classifier. The results obtained with data gathered from ten subjects are promising, with the best factor combinations for the user-independent solution leading to a mean macro F1 score of 94% or 95%. They demonstrate the potential of using wearables to develop a gesture input modality for the in-bed scenario, which can also potentially be extended to other contexts (e.g., sitting in a bed, chair, or sofa, or standing). This research also provides useful insights that inform future work, including the development and deployment of communication support systems that can benefit not only people with communication difficulties (e.g., more independence), but also those caring for them (e.g., more peace of mind).</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"109 ","pages":"Article 102029"},"PeriodicalIF":3.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143562321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Matteo Mendula , Paolo Bellavista , Marco Levorato , Sharon Ladron de Guevara Contreras
{"title":"A novel middleware for adaptive and efficient split computing for real-time object detection","authors":"Matteo Mendula , Paolo Bellavista , Marco Levorato , Sharon Ladron de Guevara Contreras","doi":"10.1016/j.pmcj.2025.102028","DOIUrl":"10.1016/j.pmcj.2025.102028","url":null,"abstract":"<div><div>Real-world applications requiring real-time responsiveness frequently rely on energy-intensive and compute-heavy neural network algorithms. Strategies include deploying distributed and optimized Deep Neural Networks on mobile devices, which can lead to considerable energy consumption and degraded performance, or offloading larger models to edge servers, which requires low-latency wireless channels. Here we present Furcifer, a novel middleware that autonomously adjusts the computing strategy (i.e., local computing, edge computing, or split computing) based on context conditions. Utilizing container-based services and low-complexity predictors that generalize across environments, Furcifer supports supervised compression as a viable alternative to pure local or remote processing in real-time environments. An extensive set of experiments coversdiverse scenarios, including both stable and highly dynamic channel environments with unpredictable changes in connection quality and load. In moderate-varying scenarios, Furcifer demonstrates significant benefits: achieving a 2x reduction in energy consumption, a 30% higher mean Average Precision score compared to local computing, and a three-fold FPS increase over static offloading. In highly dynamic environments with unreliable connectivity and rapid increases in concurrent clients, Furcifer’s predictive capabilities preserves up to 30% energy, achieving a 16% higher accuracy rate, and completing 80% more frame inferences compared to pure local computing and approaches without trend forecasting, respectively.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"108 ","pages":"Article 102028"},"PeriodicalIF":3.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vasileios Tsouvalas , Samaneh Mohammadi , Ali Balador , Tanir Ozcelebi , Francesco Flammini , Nirvana Meratnia
{"title":"EncCluster: Scalable functional encryption in federated learning through weight clustering and probabilistic filters","authors":"Vasileios Tsouvalas , Samaneh Mohammadi , Ali Balador , Tanir Ozcelebi , Francesco Flammini , Nirvana Meratnia","doi":"10.1016/j.pmcj.2025.102021","DOIUrl":"10.1016/j.pmcj.2025.102021","url":null,"abstract":"<div><div>Federated Learning (FL) enables model training across decentralized devices by communicating solely local model updates to an aggregation server. Although such limited data sharing makes FL more secure than centralized approached, FL remains vulnerable to inference attacks during model update transmissions. Existing secure aggregation approaches rely on differential privacy or cryptographic schemes like Functional Encryption (FE) to safeguard individual client data. However, such strategies can reduce performance or introduce unacceptable computational and communication overheads on clients running on edge devices with limited resources. In this work, we present <span>EncCluster</span>, a novel method that integrates model compression through weight clustering with recent decentralized FE and privacy-enhancing data encoding using probabilistic filters to deliver strong privacy guarantees in FL without affecting model performance or adding unnecessary burdens to clients. We performed a comprehensive evaluation, spanning various datasets and architectures, to demonstrate <span>EncCluster</span> scalability across encryption levels. Our findings reveal that <span>EncCluster</span> significantly reduces communication costs — below even conventional FedAvg — and accelerates encryption by more than four times over all baselines; at the same time, it maintains high model accuracy and enhanced privacy assurances.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"108 ","pages":"Article 102021"},"PeriodicalIF":3.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuan Wu , Gaorong Zhao , Likairui Zhang , Xinrong Hu , Lei Ding
{"title":"HearDrinking: Drunkenness detection and BACs predictions based on acoustic signal","authors":"Yuan Wu , Gaorong Zhao , Likairui Zhang , Xinrong Hu , Lei Ding","doi":"10.1016/j.pmcj.2025.102020","DOIUrl":"10.1016/j.pmcj.2025.102020","url":null,"abstract":"<div><div>Alcohol poisoning is a severe health concern resulting from excessive drinking and can be life-threatening. By utilizing home monitoring, individuals can quickly determine their blood alcohol content, thus preventing it from reaching hazardous levels. However, most existing systems for drunkenness detection require extra hardware or much effort from the user, making these systems impractical for detecting drunkenness in real life. Motivated by this, we present a device-free, noise-resistant drunkenness detection system named HearDrinking based on smartphone, which utilizes microphone of smartphone to record human’s voice activity, then mine drunkenness related features to yield accurate drunkenness detection. However, using acoustic signal to detect drunkenness is non-trivial since voice activities are prone to be interfered by ambient noise, and extracting fine-grained representations related to drunkenness from voice activities remains unresolved. On one hand, HearDrinking employs a multi-modal fusion method to realize noise-resistant voice activity detection. On the other hand, HearDrinking initially calculates the log-Mel spectrograms from the speech signal. The log-Mel spectrograms contain temporal and spectral information absent in image data. Therefore, conventional convolutions designed for images often have limited effectiveness in extracting features from log-Mel spectrograms. To overcome this limitation, we integrate Omni-dimensional Dynamic Convolution (ODConv) with ShuffleNetV2, creating OD-ShuffleNetV2. ODConv replaces certain conventional convolutions in the ShuffleNetV2 network. Multiple convolution cores are fused based on the log-Mel spectrogram, taking into account multi-dimensional attention, thereby optimizing the network structure. Comprehensive experiments with 15 participants reveal drunkenness detection accuracy of 96.08% and Blood Alcohol Content (BAC) predictions with an average error of 5 mg/dl.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"108 ","pages":"Article 102020"},"PeriodicalIF":3.0,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395035","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}
Mingzhou Yang, Bharat Jayaprakash, Subhankar Ghosh, Hyeonjung Tari Jung, Matthew Eagon, William F. Northrop, Shashi Shekhar
{"title":"Climate smart computing: A perspective","authors":"Mingzhou Yang, Bharat Jayaprakash, Subhankar Ghosh, Hyeonjung Tari Jung, Matthew Eagon, William F. Northrop, Shashi Shekhar","doi":"10.1016/j.pmcj.2025.102019","DOIUrl":"10.1016/j.pmcj.2025.102019","url":null,"abstract":"<div><div>Climate change is a societal grand challenge and many nations have signed the Paris Agreement (2015) aiming for net-zero emissions. The computing community has an opportunity to contribute significantly to addressing climate change across all its dimensions, including understanding, resilience, mitigation, and adaptation. Traditional computing methods face major challenges. For example, machine learning is overwhelmed due to non-stationarity (e.g., climate change), data paucity (e.g., rare climate events), the high cost of ground truth collection, and the need to observe natural laws (e.g., conservation of mass). This paper shares a perspective on a range of climate-smart computing challenges and opportunities based on multi-decade scholarly activities and acknowledges the broader societal debate on climate solutions. Moreover, it envisions advancements in computing methods specifically designed to tackle the challenges posed by climate change. It calls for a broad array of computer science strategies and innovations to be developed to address the multifaceted challenges of climate change.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"108 ","pages":"Article 102019"},"PeriodicalIF":3.0,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395036","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 Real-time skeleton-based fall detection algorithm based on temporal convolutional networks and transformer encoder","authors":"Xiaoqun Yu , Chenfeng Wang , Wenyu Wu , Shuping Xiong","doi":"10.1016/j.pmcj.2025.102016","DOIUrl":"10.1016/j.pmcj.2025.102016","url":null,"abstract":"<div><div>As the population of older individuals living independently rises, coupled with the heightened risk of falls among this demographic, the need for automatic fall detection systems becomes increasingly urgent to ensure timely medical intervention. Computer vision (CV)-based methodologies have emerged as a preferred approach among researchers due to their contactless and pervasive nature. However, existing CV-based solutions often suffer from either poor robustness or prohibitively high computational requirements, impeding their practical implementation in elderly living environments. To address these challenges, we introduce TCNTE, a real-time skeleton-based fall detection algorithm that combines Temporal Convolutional Network (TCN) with Transformer Encoder (TE). We also successfully mitigate the severe class imbalance issue by implementing weighted focal loss. Cross-validation on multiple publicly available vision-based fall datasets demonstrates TCNTE's superiority over individual models (TCN and TE) and existing state-of-the-art fall detection algorithms, achieving remarkable accuracies (front view of UP-Fall: 99.58 %; side view of UP-Fall: 98.75 %; Le2i: 97.01 %; GMDCSA-24: 92.99 %) alongside practical viability. Visualizations using t-distributed stochastic neighbor embedding (t-SNE) reveal TCNTE's superior separation margin and cohesive clustering between fall and non-fall classes compared to TCN and TE. Crucially, TCNTE is designed for pervasive deployment in mobile and resource-constrained environments. Integrated with YOLOv8 pose estimation and BoT-SORT human tracking, the algorithm operates on NVIDIA Jetson Orin NX edge device, achieving an average frame rate of 19 fps for single-person and 17 fps for two-person scenarios. With its validated accuracy and impressive real-time performance, TCNTE holds significant promise for practical fall detection applications in older adult care settings.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102016"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143155592","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}
Iratxe Landa , Guillermo Diaz , Iker Sobron , Iñaki Eizmendi , Manuel Velez
{"title":"Machinery detection by impulsive noise recognition using WiFi sensing","authors":"Iratxe Landa , Guillermo Diaz , Iker Sobron , Iñaki Eizmendi , Manuel Velez","doi":"10.1016/j.pmcj.2025.102018","DOIUrl":"10.1016/j.pmcj.2025.102018","url":null,"abstract":"<div><div>Engines and electrical devices in operation generate electromagnetic pulses, also called impulsive noise (IN), that interfere with wireless signals. The IN shall affect the channel estimation process and is, therefore, present in the channel state information (CSI) provided by wireless receivers. In this paper, impulsive noise (IN) is used as a fingerprint of electrical devices to identify the IN sources that interfere with a WiFi signal, taking into account that each individual machine has a unique pattern of impulsive noise. In this sense, the WiFi CSI provides valuable information to recognize the IN sources through deep learning (DL) strategies. Two DL models have been proposed and tested on two experimental data sets for multiclass and multilabel analysis; in multiclass, devices can operate alone during the measurement, and in multilabel, multiple devices can work simultaneously in a more realistic scenario. The model transferability between location and days has also been evaluated by analyzing two different IN feature sets for device classification with the Few-shot-learning (FSL) model. Results show that the proposed DL models can recognize multiple devices working simultaneously through the IN and also offer an acceptable transferability performance (<span><math><mo>∼</mo></math></span> 80% accuracy for a five-class problem).</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102018"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348979","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}
Vincent Bode , Carsten Trinitis , Martin Schulz , David Buettner , Tobias Preclik
{"title":"Advancing user-space networking for DDS message-oriented middleware: Further extensions","authors":"Vincent Bode , Carsten Trinitis , Martin Schulz , David Buettner , Tobias Preclik","doi":"10.1016/j.pmcj.2025.102013","DOIUrl":"10.1016/j.pmcj.2025.102013","url":null,"abstract":"<div><div>Due to the flexibility it offers, publish–subscribe messaging middleware is a popular choice in Industrial IoT (IIoT) applications. The Data Distribution Service (DDS) is a widely used industry standard for these systems with a focus on versatility and extensibility, implemented by multiple vendors and present in myriad deployments across industries like aerospace, healthcare and industrial automation. However, many IoT scenarios require real-time capabilities for deployments with rigid timing, reliability and resource constraints, while publish–subscribe mechanisms currently rely on components that are not strictly real-time capable, such as the Linux networking stack, making it hard to provide robust performance guarantees without large safety margins.</div><div>In order to make publish–subscribe approaches viable and efficient also in such real-time scenarios, we introduce user-space DDS networking transport extensions, allowing us to fast-track the communication hot path by bypassing the Linux kernel. For this purpose, we extend the best-performing vendor implementation from a previous study, CycloneDDS, to include modules for two widespread user-space networking technologies, the Data Plane Development Kit (DPDK) and the eXpress Data Path (XDP). Building on this, we additionally offer two more extensions to the second most performant implementation FastDDS, also based on DPDK and XDP, and realize novel optimizations not present in the original extension implementations. We evaluate each extension’s performance benefits against four existing DDS implementations (OpenDDS, RTI Connext, FastDDS and CycloneDDS). The DPDK-based and XDP-based extensions offer a performance benefit of 31%–38% and 18%–22% reduced mean latency, respectively, as well as an increase in bandwidth and sample rate throughput of at least 160%, while reducing the latency bound by at least 93%, demonstrating the performance and dependability advantages of circumventing the kernel for real-time communications.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102013"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143356384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sunho Lim , Ingyu Lee , Gyu Sang Choi , Jinseok Chae , Ellora Ashish , Eric Ward , Cong Pu
{"title":"FastPlan: A three-step framework for accelerating drone-centric search operations in post-disaster relief","authors":"Sunho Lim , Ingyu Lee , Gyu Sang Choi , Jinseok Chae , Ellora Ashish , Eric Ward , Cong Pu","doi":"10.1016/j.pmcj.2025.102017","DOIUrl":"10.1016/j.pmcj.2025.102017","url":null,"abstract":"<div><div>Commercially well-known drones are increasingly popular and have been deployed in post-disaster relief to support traditional search and rescue operations. However, there are still barriers to conducting a drone-centric search operation, including but not limited to operational difficulty for non-professional drone pilots, inefficient pre-planned path, and more importantly initial setup delay. In this paper, we propose a small-scale prototype of a mobile framework, called <em>FastPlan</em>, to facilitate the development for expediting drone-centric search decisions and operations. The basic idea is to automate the required search operations with no or minimized user intervention. The framework consists of three major operations: map extraction, clustering, and path planning. We extract a set of target POIs and metadata from a public map (i.e., Google Maps) integrated with a customized local database to decide where and what to search. Then we deploy simple density-based clustering and search priority-based path planning strategies to efficiently group and cover the POIs. The framework can be extended flexibly by replacing individual operations with an alternative depending on the search priority, like a Lego block. We implement the framework as an Android-based mobile software (App) for a proof-of-the-concept and conduct extensive simulation experiments for performance evaluation. We analyze the different performance behavior and their implication and applicability. The results indicate that the proposed framework can be a viable approach to post-disaster relief.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102017"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143155593","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}
Acquila Santos Rocha , Billy Anderson Pinheiro , Weverton Cordeiro , Vinicius C.M. Borges
{"title":"TrustMD — A multi-layer framework for domain, edge and D2D caching based on trust dissemination and blockchain","authors":"Acquila Santos Rocha , Billy Anderson Pinheiro , Weverton Cordeiro , Vinicius C.M. Borges","doi":"10.1016/j.pmcj.2025.102015","DOIUrl":"10.1016/j.pmcj.2025.102015","url":null,"abstract":"<div><div>Device-to-Device communication (D2D), combined with edge caching and distinct domains, is a promising approach for offloading data from wireless mobile networks. However, user security is still an open issue in D2D communication. Security vulnerabilities remain possible as a side effect of enabling straightforward, direct, and spontaneous interactions between untrustworthy users. To address this issue, this work involves designing TrustMD (Trust Multiple Domain), a multi-layer framework combining diverse technologies inspired by blockchain and trust management to develop a secure and scalable framework for multi-domain, edge, and D2D caching layers. Specifically, TrustMD combines edge trust storage with blockchain for distributed storage management in a multi-layer architecture designed to store trust control data in edge efficiently and D2D networks across different domains. Our experiments with TrustMD showed a significant improvement in data goodput, reaching as high as 95% of the total network throughput. In contrast, state-of-the-art approaches without trust control dissemination achieved at most 80%. Even though we observed a 7% increase in D2D overhead, TrustMD can effectively control latency levels. TrustMD managed security effectively without compromising network performance, reducing false negative rates up to 31% in the best-case scenario. TrustMD offers a scalable and effective security solution that boosts network performance and ensures robust protection.</div></div>","PeriodicalId":49005,"journal":{"name":"Pervasive and Mobile Computing","volume":"107 ","pages":"Article 102015"},"PeriodicalIF":3.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143376981","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}