Sangsu Lee, Xi Zheng, Jie Hua, H. Vikalo, C. Julien
{"title":"Opportunistic Federated Learning: An Exploration of Egocentric Collaboration for Pervasive Computing Applications","authors":"Sangsu Lee, Xi Zheng, Jie Hua, H. Vikalo, C. Julien","doi":"10.1109/PERCOM50583.2021.9439130","DOIUrl":"https://doi.org/10.1109/PERCOM50583.2021.9439130","url":null,"abstract":"Pervasive computing applications commonly involve user’s personal smartphones collecting data to influence application behavior. Applications are often backed by models that learn from the user’s experiences to provide personalized and responsive behavior. While models are often pre-trained on massive datasets, federated learning has gained attention for its ability to train globally shared models on users’ private data without requiring the users to share their data directly. However, federated learning requires devices to collaborate via a central server, under the assumption that all users desire to learn the same model. We define a new approach, opportunistic federated learning, in which individual devices belonging to different users seek to learn robust models that are personalized to their user’s own experiences. However, instead of learning in isolation, these models opportunistically incorporate the learned experiences of other devices they encounter opportunistically. In this paper, we explore the feasibility and limits of such an approach, culminating in a framework that supports encounter-based pairwise collaborative learning. The use of our opportunistic encounter-based learning amplifies the performance of personalized learning while resisting overfitting to encountered data.","PeriodicalId":413351,"journal":{"name":"2021 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128662961","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":"Lan: Learning to Augment Noise Tolerance for Self-report Survey Labels","authors":"Suwen Lin, Louis Faust, N. Chawla","doi":"10.1109/PERCOM50583.2021.9439109","DOIUrl":"https://doi.org/10.1109/PERCOM50583.2021.9439109","url":null,"abstract":"The prevalence of mobile sensors makes it possible for researchers to collect and analyze the pervasive sensed human activity data with machine learning tools. These analyses and applications heavily rely on the self-report survey data that reflect human physical and psychological behaviors. However, many factors can affect the reliability of such self-report surveys, such as participants’ trusty and ambiguous descriptions in questionnaires. These inaccurate survey labels challenge the development of the models, especially when it comes to the case where deep learning approaches tend to memorize the noisy information from training data. In this paper, we set out to deal with the noisy self-report survey labels. We aim to address the following challenges: 1)the limited access to clean labeled data in real-world scenarios; 2)different noise ratio of the data from different participants; 3)various types of noise that appear in the data; 4)how to evaluate the reliability of participants. As such, we propose a generalizable model, Lan, for learning from multi-modal sensory data and noisy labels. The proposed model incorporates the temporal information from sensory data to guide the model training and thus to augment noise tolerance. Extensive experiments on a real-world dataset were conducted to show our model outperforms state-of-the-art benchmarks.","PeriodicalId":413351,"journal":{"name":"2021 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116015233","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":"Embracing Self-Powered Wireless Wearables for Smart Healthcare","authors":"Longzhi Yuan, Can Xiong, Si Chen, Wei Gong","doi":"10.1109/PERCOM50583.2021.9439117","DOIUrl":"https://doi.org/10.1109/PERCOM50583.2021.9439117","url":null,"abstract":"We present Apollo, a self-powered wireless biochemical system that is wearable and can continuously monitor personal health states. It has three key enablers. First, we design an ultra-low-power Bluetooth backscatter module, which can effectively take BLE signals as excitations and transmit sensor data at high data rates to smartphones. Further, at the core of self-power management is a novel multi-source harvester that can transform RF, light, and thermal energies into electrical energy. Moreover, we introduce a biochemical sensor array that can accurately measure sweat metabolites and electrolytes.We prototype Apollo on a compactly integrated flexible PCB using all commercial off-the-shelf components. Through extensive experiments and field studies, we show that it is able to measure the glucose level in sweat within 5% error rate while consuming 5.8 mW for sensing and 720 pJ/bit for wireless transmissions. This translates to over 1700x lower power than standard electrochemical workstations, and 26x lower power than existing commercial BLE chipsets. We believe Apollo marks an important step towards the dream of ubiquitous healthcare for everyone as it provides a highly convenient, self-managed, and fully integrated way for health monitoring.","PeriodicalId":413351,"journal":{"name":"2021 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"219 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121955848","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":"GAZEL: Runtime Gaze Tracking for Smartphones","authors":"Joonbeom Park, Seonghoon Park, H. Cha","doi":"10.1109/PERCOM50583.2021.9439113","DOIUrl":"https://doi.org/10.1109/PERCOM50583.2021.9439113","url":null,"abstract":"Although work has been conducted on smartphone gaze tracking, the existing techniques are not pervasively used because of their heavy weight and low accuracy. Our preliminary analysis shows that these techniques would work better if their models were trained with data from tablets which have large screens. In this paper, we propose GAZEL, a runtime smartphone gaze-tracking scheme that achieves high accuracy on real devices. The key idea of GAZEL, a tablet-to-smartphone transfer learning, is to train a CNN model with data collected from tablets and then transplant the model to a smartphone. To achieve the goal, we designed a new CNN-based model architecture that is head pose resilient and light enough to operate at runtime. We also exploit implicit calibration to alleviate errors caused by differences in users’ visual and device characteristics. The experiment results with commercial smartphones show that GAZEL achieves 27.5% better accuracy on smartphones compared to the state-of-the-art techniques and provides gaze tracking at up to 18 fps which is practically usable at runtime.","PeriodicalId":413351,"journal":{"name":"2021 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132850179","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":"Mobility Improves Accuracy: Precise Robot Manipulation with COTS RFID Systems","authors":"Haoyu Wang, Si Chen, Wei Gong","doi":"10.1109/PERCOM50583.2021.9439133","DOIUrl":"https://doi.org/10.1109/PERCOM50583.2021.9439133","url":null,"abstract":"This paper presents GLAC, the first 3D localization system that enables millimeter-level object manipulation for robotics using only COTS RFID devices. The key insight of GLAC is that mobility reduces ambiguity and thus improves accuracy. Unlike state-of-the-art systems that require extra time or hardware to boost performance, it draws the power of modeling mobility in a delicate way. In particular, we build a novel framework for real-time tracking using the Hidden Markov Model (HMM). In our framework, multiple Kalman filters are designed to take a single phase observation for updating mobility states, and a fast inference algorithm is proposed to efficiently process an exponentially large number of candidate trajectories. We prototype GLAC with only UHF tags and a commercial reader of four antennas. Comprehensive experiments show that the median position accuracies of x/y/z dimensions are within 1 cm for both LoS and NLoS cases. The median position accuracy for slow-moving targets is 0.41 cm, which is 2.2×, 17.3×, and 14.9× better than TurboTrack, Tagoram, and RF-IDraw, respectively. Also, its median velocity accuracy is at least 20 better than all three competitors for fast-moving targets. Besides accuracy, it achieves more than 4× localization time gains over state-of-the-art systems.","PeriodicalId":413351,"journal":{"name":"2021 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125614238","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":"MousePath: Enhancing PC Web Pages through Smartphone and Optical Mouse","authors":"Zhiwei Wang, Qianyi Huang, Yihui Yan, Haitian Ren, Yizhou Zhang, Zhice Yang","doi":"10.1109/PERCOM50583.2021.9439139","DOIUrl":"https://doi.org/10.1109/PERCOM50583.2021.9439139","url":null,"abstract":"This paper proposes MousePath, a novel lightweight communication system between PC web pages and smartphones. MousePath works by putting the optical mouse on top of the smartphone’s screen, then its transmission starts and is instantly finished without association and pairing friction. It encodes data into the movement of smartphone’s display content and leverages the optical mouse of the computer to sense the movement for decoding the data. We prototype and evaluate the system with commercial computers and smartphones. A key benefit of MousePath is that it can be seamlessly integrated into web pages. Two representative web applications, i.e., sensor sharing and message sharing, have been developed to demonstrate MousePath’s potential in enhancing PC web page functionalities.","PeriodicalId":413351,"journal":{"name":"2021 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133641420","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}
Jascha Grübel, Tyler Thrash, D. Hélal, R. Sumner, C. Hölscher, Victor R. Schinazi
{"title":"The Feasibility of Dense Indoor LoRaWAN Towards Passively Sensing Human Presence","authors":"Jascha Grübel, Tyler Thrash, D. Hélal, R. Sumner, C. Hölscher, Victor R. Schinazi","doi":"10.1109/PERCOM50583.2021.9439137","DOIUrl":"https://doi.org/10.1109/PERCOM50583.2021.9439137","url":null,"abstract":"Long Range Wide Area Network (LoRaWAN) has been advanced as an alternative for creating indoor sensor networks that extends beyond its original long-distance communication purpose. For the present paper, we developed a Dense Indoor Sensor Network (DISN) with 390 sensor nodes and three gateways and empirically evaluated its performance for half a year. Our analysis of more than 14 million transmissions revealed that DISNs achieve a much lower distance coverage compared to previous research. In addition, the deployment of multiple gateways decreased the loss of transmissions due to environmental and network factors such as concurrently received messages. Given the complexity of our system, we received few colliding concurrent messages, which demonstrates a gap between the projected requirements of LoRaWAN systems and the actual requirements of real-world applications. Our attenuation model indicates that robust coverage in an indoor environment can be maintained by placing a gateway every 30 m and every 5 floors. We discuss the application of DISNs for the passive sensing and visualization of human presence using a Digital Twin (DT).","PeriodicalId":413351,"journal":{"name":"2021 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"212 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126097035","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":"Data Collection Utility Maximization in Wireless Sensor Networks via Efficient Determination of UAV Hovering Locations","authors":"Mengyu Chen, W. Liang, Sajal K. Das","doi":"10.1109/PERCOM50583.2021.9439126","DOIUrl":"https://doi.org/10.1109/PERCOM50583.2021.9439126","url":null,"abstract":"Data collection in Wireless Sensor Networks (WSNs) has been a hot research topic owing to the accelerated development in the Internet of Things (IoT). With high agility, mobility and flexibility, the Unmanned Aerial Vehicle (UAV) is widely considered as a promising technology for data collection in WSNs. Under the one-to-many data collection scheme, where a UAV is able to collect data from multiple sensors simultaneously within its reception range, the identification of hovering locations of the UAV impacts the efficiency of data collection significantly. Most existing studies either neglect this critical issue or discretize the UAV serving area into small regions with a given size, which results in the inevitable utility loss of data collection. In this paper, we jointly consider the hovering location positioning of the UAV and the utility maximization of data collection. Specifically, we first formulate a novel data collection utility maximization problem (UMP) and show that it is an NP-hard problem. We then devise an efficient algorithm for precisely positioning (potential) UAV hovering locations, which improves the data collection utility significantly. We also propose an approximation algorithm for UMP with approximation ratio $left( {1 - frac{1}{e}} right)$, where e is the base of the natural logarithm. We finally evaluate the performance of the proposed algorithms through simulation experiments, and demonstrate that the proposed algorithms significantly outperform four heuristics.","PeriodicalId":413351,"journal":{"name":"2021 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129028823","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}
Hochul Lee, Seyul Lee, Young Choon Lee, Hyuck Han, Sooyong Kang
{"title":"iEdge: An IoT-assisted Edge Computing Framework","authors":"Hochul Lee, Seyul Lee, Young Choon Lee, Hyuck Han, Sooyong Kang","doi":"10.1109/PERCOM50583.2021.9439122","DOIUrl":"https://doi.org/10.1109/PERCOM50583.2021.9439122","url":null,"abstract":"Edge computing has emerged as a viable solution to bridge the gap between distributed Internet of Things (IoT) devices and centralized distant clouds. In particular, small-scale servers are deployed at the edge of network (i.e., edge servers) to ‘help’ cloud servers process data IoT devices constantly generate. However, these edge servers often struggle to deal with emerging applications that require real-time data processing in situ, such as real-time facial recognition. In this paper, we present iEdge as an IoT-assisted edge computing framework that enables the seamless execution of applications across an edge server and nearby IoT devices. The seamless execution in essence has been realized by transforming platform-dependent monolithic applications to cross-platform composite applications and offloading some tasks/functions of these composite applications to IoT devices considering device context. We have evaluated iEdge using a prototype implementation with a real-time facial recognition application. Experimental results show that iEdge effectively harnesses smart IoT devices as a consolidated edge computing execution environment and enables such an application to process more video streams than typical ‘edge-only’ computing.","PeriodicalId":413351,"journal":{"name":"2021 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117094489","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":"Deep Triplet Networks with Attention for Sensor-based Human Activity Recognition","authors":"Bulat Khaertdinov, E. Ghaleb, S. Asteriadis","doi":"10.1109/PERCOM50583.2021.9439116","DOIUrl":"https://doi.org/10.1109/PERCOM50583.2021.9439116","url":null,"abstract":"One of the most significant challenges in Human Activity Recognition using wearable devices is inter-class similarities and subject heterogeneity. These problems lead to the difficulties in constructing robust feature representations that might negatively affect the quality of recognition. This study, for the first time, applies deep triplet networks with various triplet loss functions and mining methods to the Human Activity Recognition task. Moreover, we introduce a novel method for constructing hard triplets by exploiting similarities between subjects performing the same activities using the concept of Hierarchical Triplet Loss. Our deep triplet models are based on the recent state-of-the-art LSTM networks with two attention mechanisms. The extensive experiments conducted in this paper identify important hyperparameters and settings for training deep metric learning models on widely-used open-source Human Activity Recognition datasets. The comparison of the proposed models against the recent benchmark models shows that deep metric learning approach has the potential to improve the quality of recognition. Specifically, at least one of the implemented triplet networks shows the state-of-the-art results for each dataset used in this study, namely PAMAP2, USC-HAD and MHEALTH. Another positive effect of applying deep triplet networks and especially the proposed sampling algorithm is that feature representations are less affected by inter-class similarities and subject heterogeneity issues.","PeriodicalId":413351,"journal":{"name":"2021 IEEE International Conference on Pervasive Computing and Communications (PerCom)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131644105","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}