{"title":"Non-parametric Bayesian Learning for Newcomer Detection using Footstep-Induced Floor Vibration: Poster Abstract","authors":"Yiwen Dong, Jonathon Fagert, Pei Zhang, H. Noh","doi":"10.1145/3412382.3458785","DOIUrl":"https://doi.org/10.1145/3412382.3458785","url":null,"abstract":"Detecting a previously unknown person (newcomer detection) is critical for visitor management, intruder prevention, and access control in smart buildings. Biometrics have been used to detect newcomers, including face, fingerprint, voice, iris, etc. These approaches often require active participation of the users or require dense instrumentation. Prior work using footstep-induced floor vibration to identify people removes these requirements, but only functions for known people due to the high variability in footstep-induced vibrations and the limited number of predicted classes in supervised learning. To overcome the limitations, we introduce a newcomer detection system based on non-parametric Bayesian learning, which models the variability and distribution of consecutive footstep-induced floor vibration for newcomer walking patterns. Preliminary results from real-world experiments with 6 people show up to 92% accuracy in newcomer detection with an average of 4 consecutive footsteps.","PeriodicalId":414542,"journal":{"name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129522212","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":"Towards Reducing Labeling Efforts in IoT-based Machine Learning Systems: PhD Forum Abstract","authors":"Tahiya Chowdhury","doi":"10.1145/3412382.3459211","DOIUrl":"https://doi.org/10.1145/3412382.3459211","url":null,"abstract":"The number of Internet-of-Things (IoT) and edge devices has exploded in recent years. Coupled with recent advances in learning methodologies, these can make the vision of smart building a reality and transform how people interact with their environment. Deep learning-driven systems have been already successful in many IoT application areas of pervasive sensing and ubiquitous computing including human activity monitoring and occupancy detection. However, the robustness of such systems at scale is dependent on the availability of a large amount of data labeled by a human expert. Acquiring human annotation involves high effort, high cost, and is often error-prone. Therefore, learning to execute tasks in a machine learning system without manual inspection is of prime interest as it can open up opportunities for continual learning in the long-term deployment of IoT systems. In this work, we propose deep neural network-based approaches for segmentation and classification tasks in sensor streams with no or limited labels. We focus on reducing human labeling efforts in machine learning systems by 1) leveraging temporal features learned through deep neural networks for downstream tasks and 2) learning robust features in dynamic environments by utilizing multiple sensing sources and semi-supervised learning (e.g. small amount of labeled data).","PeriodicalId":414542,"journal":{"name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116885182","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":"Hands-On IoT Education with Mobile Devices: Demo Abstract","authors":"Devin C. Jean, Gordon Stein, Á. Lédeczi","doi":"10.1145/3412382.3458778","DOIUrl":"https://doi.org/10.1145/3412382.3458778","url":null,"abstract":"Distributed computing, computer networking, cyber-physical systems and the Internet of Things (IoT) are all around us, yet very little of the underlying concepts are being taught in introductory computer science courses in K12. Teaching IoT is especially problematic since it requires hardware with its own cost and maintenance requirements that many under-resourced schools cannot afford. However, smartphones are commonplace networked devices that boast a wide range of sensors. With the right approach, they can be used to introduce many advanced computing concepts even to novices. We have created a mobile app, PhoneIoT, which makes all available sensors accessible to the user's computer through NetsBlox, a block-based educational programming environment specializing in networking and distributed computing. Accessing PhoneIoT uses the same simple networking primitives as other NetsBlox services, so no additional knowledge is required. PhoneIoT makes it possible to collect sensor data, build a custom graphical interface on the device and receive corresponding events, all without leaving your browser running NetsBlox. This demonstration will showcase a few simple projects such as an exercise tracking app and how to turn your phone into a game controller.","PeriodicalId":414542,"journal":{"name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124489245","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}
Jiayao Gao, Weitao Xu, S. Kanhere, Sanjay Jha, J. Kim, Walter Huang, Wen Hu
{"title":"A Novel Model-Based Security Scheme for LoRa Key Generation","authors":"Jiayao Gao, Weitao Xu, S. Kanhere, Sanjay Jha, J. Kim, Walter Huang, Wen Hu","doi":"10.1145/3412382.3458256","DOIUrl":"https://doi.org/10.1145/3412382.3458256","url":null,"abstract":"Physical layer key generation has attracted considerable attention in the past decade since it provides an alternative solution for the key establishment in wireless networks using channel reciprocity. In this paper we explore the possibility of physical layer key generation for emerging Low Power Wide Area Networks (LPWAN) such as LoRa (Long Range). However, due to the lower transmission rates of LPWANs compared to Wi-Fi and Zigbee, the channel reciprocity is relatively low, which makes timely key generation challenging. To address this problem, we propose a novel information-theoretic key generation scheme that can operate at all data rate settings, featuring a model-based key generation method. Furthermore, we derive an optimal window size to calculate the parameters of the channel model based on a random waypoint model to balance the channel reciprocity and entropy. Extensive evaluations on a campus testbed show that our method can achieve up to 13.8 bps key generation rate. Compared to state-of-the-art methods, the proposed method improves key generation rate by 3x to 5x. We also analyzed the security of the proposed approach and demonstrated it to be resilient to eavesdropping attacks.","PeriodicalId":414542,"journal":{"name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114925438","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":"BLE Can See: A Reinforcement Learning Approach for RF-based Indoor Occupancy Detection","authors":"Md Fazlay Rabbi Masum Billah, Nurani Saoda, Jiechao Gao, Bradford Campbell","doi":"10.1145/3412382.3458262","DOIUrl":"https://doi.org/10.1145/3412382.3458262","url":null,"abstract":"The emergence of radio frequency (RF) dependent device-free indoor occupancy detection has seen slow acceptance due to its high fragility. Experimentation shows that an RF-dependent occupancy detector initially performs well in the room to be sensed. However, once the physical arrangement of objects changes in the room, the performance of the classifier degrades significantly. To address this issue, we propose BLECS, a Bluetooth-dependent indoor occupancy detection system which can adapt itself in the dynamic environment. BLECS uses a reinforcement learning approach to predict the occupancy of an indoor environment and updates its decision policy by interacting with existing IoT devices and sensors in the room. We tested this system in five different rooms for 520 hours in total, involving four occupants. Results show that, BLECS achieves 21.4% performance improvement in a dynamic environment compared to the state-of-the-art supervised learning algorithm with an average F1 score of 86.52%. This system can also predict occupancy with a maximum 89.23% F1 score in a completely unknown environment with no initial trained model.","PeriodicalId":414542,"journal":{"name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","volume":"168 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115413834","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":"A Multi-source Unsupervised Domain Adaptation Method for Wearable Sensor based Human Activity Recognition: Poster Abstract","authors":"Baiqiang Zhang, Rong Zheng, Jie Liu","doi":"10.1145/3412382.3458788","DOIUrl":"https://doi.org/10.1145/3412382.3458788","url":null,"abstract":"Human Activity Recognition (HAR) refers to recognizing a human's ongoing actions through sensor data. At present, one of the main problems faced by Human Activity Recognition is that different subjects, devices and wearing positions can cause inconsistent sensor data distribution. When a classification model trained using some labeled dataset is used to classify a new unlabeled data with different distributions, there will be a significant performance loss. However, it is difficult to annotate manually sensor data for new subjects. Prior works applying unsupervised domain adaptation methods to solve this problem only used a single source domain. However, in practice, it is common to have multiple labeled source domains. Inspired by a work in the field of computer vision, we propose an unsupervised domain adaptation method for human activity recognition using multiple source domains. Experimental results on a commonly used public HAR dataset show that our model can effectively alleviate the performance loss caused by inconsistent distributions. Moreover, compared with the single-source domain adaptation, the multi-source domain adaptation method can improve the accuracy further.","PeriodicalId":414542,"journal":{"name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130840627","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":"Detecting Human-Induced Changes in Powerline Signals: A Human Sensing System Design: Poster Abstract","authors":"Tian Zhou, Lin Zhang","doi":"10.1145/3412382.3458786","DOIUrl":"https://doi.org/10.1145/3412382.3458786","url":null,"abstract":"Human activity in the room causes signal changes on the power-lines. Therefore, the state of a person can be inferred by measuring the signal changes on the powerlines. Previous powerline-based indoor human sensing systems suffer from expensive hardware costs and thus cannot be deployed on a large scale. In this work, we propose a more cost-effective version of the sensing system and achieve sufficiently good results in a real deployment.","PeriodicalId":414542,"journal":{"name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121175223","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":"Low-Cost, Perspective Invariant and Personalized Thermal Comfort Estimation: Poster Abstract","authors":"Peter Wei, Yanchen Liu, Xiaofan Jiang","doi":"10.1145/3412382.3458781","DOIUrl":"https://doi.org/10.1145/3412382.3458781","url":null,"abstract":"In this poster abstract, we present a thermal comfort estimation system using low-cost thermal camera based sensor nodes. This system extracts perspective invariant, non-intrusive thermal measurements, is easily deployable and low-cost, and can incorporate individual thermal feedback for more personalized thermal comfort estimates. In comparison with baseline methods, our system is able to improve thermal comfort estimates on the ASHRAE 7-point thermal sensation scale by up to 64% over baseline methods.","PeriodicalId":414542,"journal":{"name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127409762","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}
Amanda Watson, Andrew Lyubovsky, Kenneth Koltermann, Gang Zhou
{"title":"Magneto: Joint Angle Analysis Using an Electromagnet-Based Sensing Method","authors":"Amanda Watson, Andrew Lyubovsky, Kenneth Koltermann, Gang Zhou","doi":"10.1145/3412382.3458253","DOIUrl":"https://doi.org/10.1145/3412382.3458253","url":null,"abstract":"Joint angle analysis facilitates research into injury prevention, rehabilitation, and activity monitoring. Sensors used in such analysis must be unobtrusive, accurate, and if used for motion, capable of monitoring fast-paced, dynamic motions. To effectively contribute to these applications, we created a body-mounted electromagnet-based sensing system for joint angle analysis called Magneto. Our system is wireless, features a high sampling rate, is not subject to drift, and is unaffected by outside magnetic noise. Magnetic field readings are influenced by noise due to magnetic interference from the Earth's magnetic field, the environment, and nearby ferrous objects. Magneto uses the combination of an electromagnet and magnetometer to remove environmental interference from a magnetic field reading. We evaluated this sensing method to show its performance when removing the interference in three-movement dimensions, in six environments, and with six different cycling rates. Then, we localized the electromagnet with respect to the magnetic field reader in any direction within a 13.8 cm range with a relative error of 2.3% for the distance and an average error of 3.43° for the orientation angle. We applied Magneto in a pilot study: calculating elbow flexion angles. In this study, we calculated elbow flexion angles to the nearest 15° with 93.8% accuracy.","PeriodicalId":414542,"journal":{"name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","volume":"254 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122727682","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":"Efficient Execution of Deep Neural Networks on Mobile Devices with NPU","authors":"Tianxiang Tan, G. Cao","doi":"10.1145/3412382.3458272","DOIUrl":"https://doi.org/10.1145/3412382.3458272","url":null,"abstract":"Many Deep Neural Network (DNN) based applications have been developed and run on mobile devices. Although these advanced DNN models can provide better results, they also suffer from high computational overhead which means long delay and more energy consumption when running on mobile devices. To address these problems, many companies have developed dedicated Neural Processing Units (NPUs) for mobile devices, which can process AI features. Compared to CPU, NPU can run DNN models much faster, but with lower accuracy. To address this issue, we leverage model partition techniques to improve the performance of DNN models on mobile devices with NPU. The challenge is to determine which part of the DNN model should be run on CPU and which part to be run on NPU. Based on the delay and the accuracy requirements of the applications, we study two problems: Max-Accuracy where the goal is to maximize the accuracy under some time constraint, and Min-Time where the goal is to minimize the processing time while ensuring the accuracy is above a certain threshold. To solve these problems, we propose heuristic based algorithms which are simple but only search a small number of layer combinations (i.e., where to run which DNN model layers). To further improve the performance, we propose a Machine Learning based Model Partition (MLMP) algorithm. MLMP searches more layer combinations and considers both accuracy loss and processing time simultaneously. We also address many implementation issues to support model partition techniques on mobile devices with NPU. Experimental results show that MLMP outperforms the heuristic based algorithms and it can significantly improve the accuracy or reduce the processing time based on the application requirements.","PeriodicalId":414542,"journal":{"name":"Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125698913","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}