... International Conference on Distributed Computing in Sensor Systems and workshops. DCOSS (Conference)最新文献

{"title":"Robustness of ML-Based Seizure Prediction Using Noisy EEG Data From Limited Channels.","authors":"Umair Mohammad, Fahad Saeed","doi":"10.1109/dcoss-iot61029.2024.00097","DOIUrl":"10.1109/dcoss-iot61029.2024.00097","url":null,"abstract":"<p><p>Seizures pose a significant health hazard for over 50 million individuals with epilepsy worldwide, with approximately 56% experiencing uncontrollable seizures according to the CDC. Predicting seizures is challenging even with the availability of various sensors (gyroscopes, pulse rate sensors, heart rate monitors, etc). Electroencephalography (EEG) data can directly measure the activity of the brain and has been the choice of leveraging deep learning (DL) models for seizure prediction. Despite DL models achieving over 95% accuracy on retroactive clinical-grade EEG data, this performance fails to translate in real-world settings where the accuracy goes down to 66% - which warrants further investigation. Moreover, consumer-grade wearable EEG headsets, characterized by lower data quality and a varying number of channels across brands, present additional challenges. In this paper, we estimate the robustness of DL models which are trained on clinical-grade EEG data but tested on the type of data expected from consumer-grade wearable EEG headsets. We select the previously published model SPERTL to estimate its robustness when: (1) predicting with data from less leads/channels, (2) predicting when faced with streaming data, (3) evaluating performance on imbalanced data with more interictal segments. Our results are compared against baseline results from the SPERTL model which we have re-configured to operate independently of the number of channels with an average baseline area under the curve (AUC) score of 98.56%. Our results demonstrate that though the model is surprisingly resilient to streaming and noisy data, reducing the number of channels and a higher class imbalance have a more severe degradation. The AUC across all cross-validation sets degrades only by 2% and 3% on average for noisy and streaming data, respectively. However, a performance reduction, on average, is observed by 32% when imbalance is increased with higher percentage of interictal samples, and up to 16% when using lower number of channels.</p>","PeriodicalId":93158,"journal":{"name":"... International Conference on Distributed Computing in Sensor Systems and workshops. DCOSS (Conference)","volume":"2024 ","pages":"620-626"},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11935532/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143712613","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EyeFi: Fast Human Identification Through Vision and WiFi-based Trajectory Matching.","authors":"Shiwei Fang,&nbsp;Tamzeed Islam,&nbsp;Sirajum Munir,&nbsp;Shahriar Nirjon","doi":"10.1109/dcoss49796.2020.00022","DOIUrl":"https://doi.org/10.1109/dcoss49796.2020.00022","url":null,"abstract":"<p><p>Human sensing, motion trajectory estimation, and identification are central to a wide range of applications in many domains such as retail stores, surveillance, public safety, public address, smart homes and cities, and access control. Existing solutions either require facial recognition or installation and maintenance of multiple units, or they lack long-term re-identification capability. In this paper, we propose a novel system - called EyeFi- that combines WiFi and camera on a standalone device to overcome these limitations. EyeFi integrates a WiFi chipset to an overhead camera and fuses motion trajectories obtained from both vision and RF modalities to identify individuals. In order to do that, EyeFi uses a student-teacher model to train a neural network to estimate the Angle of Arrival (AoA) of WiFi packets from the CSI values. Based on extensive evaluation using real-world data, we observe that EyeFi improves WiFi CSI based AoA estimation accuracy by more than 30% and offers 3,800 times computational speed over the state-of-the-art solution. In a real-world environment, EyeFi's accuracy of person identification averages 75% when the number of people varies from 2 to 10.</p>","PeriodicalId":93158,"journal":{"name":"... International Conference on Distributed Computing in Sensor Systems and workshops. DCOSS (Conference)","volume":"2020 ","pages":"59-68"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/dcoss49796.2020.00022","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38869150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Wi-Fringe: Leveraging Text Semantics in WiFi CSI-Based Device-Free Named Gesture Recognition.","authors":"Md Tamzeed Islam,&nbsp;Shahriar Nirjon","doi":"10.1109/dcoss49796.2020.00019","DOIUrl":"https://doi.org/10.1109/dcoss49796.2020.00019","url":null,"abstract":"<p><p>The lack of adequate training data is one of the major hurdles in WiFi-based activity recognition systems. In this paper, we propose Wi-Fringe, which is a WiFi CSI-based device-free human gesture recognition system that recognizes <i>named</i> gestures, i.e., activities and gestures that have a semantically meaningful name in English language, as opposed to arbitrary free-form gestures. Given a list of activities (only their names in English text), along with zero or more training examples (WiFi CSI values) per activity, Wi-Fringe is able to detect all activities at runtime. We show for the first time that by utilizing the state-of-the-art semantic representation of English words, which is learned from datasets like the Wikipedia (e.g., Google's word-to-vector [1]) and verb attributes learned from how a word is defined (e.g, American Heritage Dictionary), we can enhance the capability of WiFi-based named gesture recognition systems that lack adequate training examples per class. We propose a novel cross-domain knowledge transfer algorithm between radio frequency (RF) and text to lessen the burden on developers and end-users from the tedious task of data collection for all possible activities. To evaluate Wi-Fringe, we collect data from four volunteers in a multi-person apartment and an office building for a total of 20 activities. We empirically quantify the trade-off between the accuracy and the number of unseen activities.</p>","PeriodicalId":93158,"journal":{"name":"... International Conference on Distributed Computing in Sensor Systems and workshops. DCOSS (Conference)","volume":"2020 ","pages":"35-42"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/dcoss49796.2020.00019","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39499040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SEnTINEL - INtELligent Transport SystEm for Urban Mobility Management in Smart Cities","authors":"M. S. Quessada, A. L. Cristiani, Pedro Luis Ranzani Junior, Matheus Leal, R. Meneguette","doi":"10.1109/DCOSS.2019.00102","DOIUrl":"https://doi.org/10.1109/DCOSS.2019.00102","url":null,"abstract":"Applications for intelligent transportation systems are springing up to bring many benefits to users during their journey through the use of vehicle traffic monitoring. However, testing and experimenting with real-world environments still poses a challenge for these applications since a realistic scenario of mobility is required. Typically, simulation tools use mobility trails to construct the network topology based on the mathematical formulation of a city mobility model, which attempts to emulate the real mobility of a given city. Another strategy is to use the real route of vehicles traveling to generate the model of mobility of a certain city; however, many studies available in the literature do not use the entire flow of vehicles that circulate in the city, acquiring data only of a small group of vehicles. Thus, in this work we intend to develop an infrastructure that would allow the extraction of the information of mobility from the vehicles of the countryside cities, in real time. This enables not only real-time vehicle monitoring but also the generation of traceability of real-time mobility. The results showed low battery consumption, as well as a low amount of mobile data usage.","PeriodicalId":93158,"journal":{"name":"... International Conference on Distributed Computing in Sensor Systems and workshops. DCOSS (Conference)","volume":"134 1","pages":"538-545"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77377561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Message from the General Chair and Program Chair","authors":"H. Ammari, S. Olariu","doi":"10.1109/DCOSS.2016.4","DOIUrl":"https://doi.org/10.1109/DCOSS.2016.4","url":null,"abstract":"The Twelfth Annual International Conference on Distributed Computing in Sensor Systems (DCOSS) will be held in Washington DC, USA on May 26-28, 2016. This conference broadly focuses on the design, development, and optimization of large scale networked sensor systems. In addition to the established tracks in the previous editions of DCOSS, such as Algorithms and Performance Analysis, Applications, Systems, Real Deployments and Tools, Signal Processing and Information Theory, this twelfth edition includes a new Track of the Year, called \"Cloud Computing and Applications to Sensing Systems.\" DCOSS 2016 includes a high-quality technical program consisting of keynotes, research papers, Poster and Demo session, and Ph.D. Forum. This year we received 65 submissions in response to the call for papers. Each paper was reviewed by at least three experts in the field. After detailed on-line discussions with the Track Chairs, 24 papers were finally accepted, leading to an acceptance ratio of 37%. Specifically, the program covers important aspects of distributed computing in sensor systems, such as mobile crowdsourcing, energy efficiency and communication, routing, tracking and localization, security, and applications and outdoor testbed, to name a few. Additionally, there is one workshop that addresses challenging research topics in sensor networking. We believe the technical program will provide an exciting forum for researchers and practitioners to exchange cutting-edge ideas in distributed sensor systems.","PeriodicalId":93158,"journal":{"name":"... International Conference on Distributed Computing in Sensor Systems and workshops. DCOSS (Conference)","volume":"125 1","pages":"viii"},"PeriodicalIF":0.0,"publicationDate":"2016-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85277733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Smart Shadow - An Autonomous Availability Computation Resource Allocation Platform for Internet of Things in the Fog Computing Environment","authors":"D. R. Vasconcelos, R. Andrade, J. Souza","doi":"10.1109/DCOSS.2015.25","DOIUrl":"https://doi.org/10.1109/DCOSS.2015.25","url":null,"abstract":"In the ecosystem of Internet of Things, many applications require external computational resources with quick response. In this context, a possible solution is to use computational resources from other devices that are located nearby the host device. This new environment is named Fog computing and creates several opportunities and challenges. One these challenges, which is the focus of this work, is how to allocate available resources in a simple and effective way for a client device that you want to use these features. The proposal \"Smart Shadow\" is an autonomous platform availability allocation of computer resources in a Fog computing infrastructure based on learning from previous event to support mobile hosts devices.","PeriodicalId":93158,"journal":{"name":"... International Conference on Distributed Computing in Sensor Systems and workshops. DCOSS (Conference)","volume":"161 1","pages":"216-217"},"PeriodicalIF":0.0,"publicationDate":"2015-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80160822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predictive Filtering for Adjacency-Based Localization in MANET","authors":"A. Alshehri, S. Shah-Heydari","doi":"10.1109/DCOSS.2013.27","DOIUrl":"https://doi.org/10.1109/DCOSS.2013.27","url":null,"abstract":"","PeriodicalId":93158,"journal":{"name":"... International Conference on Distributed Computing in Sensor Systems and workshops. DCOSS (Conference)","volume":"76 1","pages":"448-453"},"PeriodicalIF":0.0,"publicationDate":"2013-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80720224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ubiquitous Widgets: Designing Interactions Architecture for Adaptive Mobile Applications","authors":"Pierre Dibon, Marc Dalmau, P. Roose","doi":"10.1109/DCOSS.2013.32","DOIUrl":"https://doi.org/10.1109/DCOSS.2013.32","url":null,"abstract":"","PeriodicalId":93158,"journal":{"name":"... International Conference on Distributed Computing in Sensor Systems and workshops. DCOSS (Conference)","volume":"94 1","pages":"331-336"},"PeriodicalIF":0.0,"publicationDate":"2013-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78942471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DCOSS 2012 Foreword","authors":"Dongming Lu, Wenyuan Xu, Zhi Wang, M. Rabbat","doi":"10.1109/DCOSS.2012.4","DOIUrl":"https://doi.org/10.1109/DCOSS.2012.4","url":null,"abstract":"The 8th IEEE International Conference on Distributed Computing in Sensor Systems (DCOSS 2012) is taking place in Hangzhou, China, from Wednesday, May 16, to Friday, May 18, 2012. Previous editions have taken place in Barcelona, Spain (2011), Santa Barbara, USA (2010), Los Angeles, USA (2009), Santorini Island, Greece (2008), Santa Fe, USA (2007), San Francisco, USA (2006), and Marina del Rey, USA (2005). We are pleased to present the conference program to you. This year, the DCOSS program features high-quality research presentations, two keynotes, and a poster and work-inprogress session. The conference program covers several aspects of distributed computing in sensor systems aligned with the three main tracks: algorithms and analysis, signal processing and information theory, and systems and applications. This year we received 100 submissions. Each submitted paper was reviewed by at least three Technical Program Committee experts, and ultimately a total of 34 papers were accepted. We will also feature three interesting workshops and one poster/demonstration/work-in-progress session. We are proud to feature two excellent keynotes from leading experts on issues currently driving the distributed computing and sensor systems community. We hope that the technical program will provide a stimulating forum for researchers and practitioners throughout all three days.","PeriodicalId":93158,"journal":{"name":"... International Conference on Distributed Computing in Sensor Systems and workshops. DCOSS (Conference)","volume":"1967 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91397099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Passive target tracking: Application with mobile devices using an indoors WSN Future Internet testbed","authors":"M. Karagiannis, K. Chantzis, S. Nikoletseas, J. Rolim","doi":"10.1109/DCOSS.2011.5982182","DOIUrl":"https://doi.org/10.1109/DCOSS.2011.5982182","url":null,"abstract":"","PeriodicalId":93158,"journal":{"name":"... International Conference on Distributed Computing in Sensor Systems and workshops. DCOSS (Conference)","volume":"132 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75873171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}