Neeraj Alavala, Haige Chen, Rishabh Singhal, Ashutosh Dhekne
{"title":"PetTrack","authors":"Neeraj Alavala, Haige Chen, Rishabh Singhal, Ashutosh Dhekne","doi":"10.1145/3539489.3539587","DOIUrl":"https://doi.org/10.1145/3539489.3539587","url":null,"abstract":"Tracking a pet’s location and activity indoors is of acute interest to pet owners who want to feel connected to their pet as well as of interest to pet owners who feel concerned about their pet’s well-being. Today, such tracking is performed using pet cameras. However, cameras need to be installed in every room accessible to the pet, do not work well in the dark, and generate a tremendous amount of data. In this paper we develop an indoor localization and pose detection system for pets using ultra-wideband (UWB) radios and an accelerometer affixed to the pet’s collar. We also develop a new message format for UWB packets to carry accelerometer data in addition to localization data to estimate the pet’s pose. Our pose-estimation logic detects the pet’s pose using accelerometer data via a K-nearest neighbor classifier. The pet’s location and pose is shown to the pet-owner via a functional mobile application. We believe this cost-effective and efficient new way of tracking a pet indoors will inspire others to extend this research further.","PeriodicalId":278175,"journal":{"name":"Proceedings of the 2022 Workshop on Body-centric Computing Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114633957","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":"Plantar Biometrics for Edge Computing","authors":"Mads Stege, Charalampos Orfanidis, Xenofon Fafoutis","doi":"10.1145/3539489.3539589","DOIUrl":"https://doi.org/10.1145/3539489.3539589","url":null,"abstract":"Biometric systems are getting integrated into our daily life as the needs for authentication are increased rapidly. In smartphones fingerprint and face identification are used already widely as a method for user authentication. A relatively novel area of biometrics is the usage of plantar biometrics, foot sole features, to verify human identities. There are several approaches to utilise plantar biometrics but most of the proposed approaches require bulky, obtrusive or an immobile design. In this paper, we introduce a unobtrusive biometric system based on a shoe wearable, which is able to authenticate individuals with the assistance of Neural Network Classifier. The implemented system is evaluated on $10$ individuals achieving $94.3%$ accuracy with a loss of $1.87$. Furthermore, the learning and authentication part takes place on the edge which has numerous benefits towards the performance but also the security aspects of the system.","PeriodicalId":278175,"journal":{"name":"Proceedings of the 2022 Workshop on Body-centric Computing Systems","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123923530","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":"FinePose","authors":"Shubham Rohal, S. Shriram, Vp Nguyen, Shijia Pan","doi":"10.1145/3539489.3539590","DOIUrl":"https://doi.org/10.1145/3539489.3539590","url":null,"abstract":"As people’s lifestyles becomes more sedentary, neck and back pain among young adults have increased. Those who spend a significant amount of time looking at digital screens (e.g., computers, tablets, smartphones) tend to assume forward head postures (FHP), which increases the load on their postural muscles and stress on the cervical spine. As a result, FHP often leads to neck and upper back muscle pains and interferes with normal functioning and quality of life. It may also result in degenerative spine issues, such as cervical degenerative disc disease and cervical osteoarthritis. We present FinePose, a system that measures the postural muscle (upper and middle trapezius muscle) stiffness levels. FinePose repurposes the haptic vibration input on the existing smart posture brace, generated by the lightweight and low-power coin vibration motor, and conducts active vibration sensing to measure the muscle elasticity. It uses an array of accelerometers at different distances from the motor to capture vibration response. Next, FinePose extracts features that describe vibration propagation properties and establishes a regression model to predict the muscle stiffness level. We conduct real world experiments with four subjects on multiple days, and demonstrate preliminary results that validate FinePose's feasibility.","PeriodicalId":278175,"journal":{"name":"Proceedings of the 2022 Workshop on Body-centric Computing Systems","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116303809","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":"Enabling Body-Centric Computing Applications with LED-to-Camera Communication","authors":"Omer Dalgic, D. Puccinelli, Marco Zúñiga","doi":"10.1145/3539489.3539588","DOIUrl":"https://doi.org/10.1145/3539489.3539588","url":null,"abstract":"Advances in Visible Light Communication are enabling novel Internet of Things applications. Going forward, we expect that LED-to-Camera links will enable a wide range of body-centric computing applications. Up until now, most LED-to-Camera studies have been following a deploy-and-test approach instead of a principled methodology. This ad-hoc design raises up two problems. First, we cannot compare fairly the various methods proposed in the literature because they use different types of LEDs and cameras. Second, and perhaps more importantly, we cannot identify the fundamental opportunities and limits of these novel links. To overcome these challenges, we propose a simple analytical model that estimates the range and data rate of LED-to-camera links prior to deployment. The model is built from first principles and requires only a limited set of parameters. To validate the accuracy of our model, we consider the two main transmission modes used in the literature: binary transmission and communication based on the rolling shutter effect. Our experimental evaluation confirms the predictions of the analytical model.","PeriodicalId":278175,"journal":{"name":"Proceedings of the 2022 Workshop on Body-centric Computing Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132386421","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}