Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems最新文献

{"title":"Pseudo Random Binary Sequence Excitation for Electrical Impedance Tomography","authors":"O. Hyka, A. Véjar, T. Rymarczyk","doi":"10.1145/3485730.3492889","DOIUrl":"https://doi.org/10.1145/3485730.3492889","url":null,"abstract":"Minimal hardware requirements for electrical impedance tomography can enhance the method's applicability for medical tracking and diagnostic tasks in e-health. The principle of electrical tomography is that the response to electrical excitation of biological tissues provides information about the material structure. In order to reduce the required hardware, we study pseudo random binary sequence excitation patterns, instead of the standard sinusoidal excitation. We implement the measurement system in reconfigurable hardware with a mixed signal SoC. The measurements are validated using system identification in the resulting data to estimate the discrete transfer function of the system under measurement.","PeriodicalId":356322,"journal":{"name":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127920206","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":"Dynamic application mapping on CTH network: a performance-centric approach","authors":"Avik Bose, P. Ghosal","doi":"10.1145/3485730.3494036","DOIUrl":"https://doi.org/10.1145/3485730.3494036","url":null,"abstract":"Communication cost in terms of energy consumption and network latency, along with the dynamic allocation time of the tasks and their execution time, is the primary design concern of a run-time mapping and scheduling strategy that may significantly affect the overall performance of an application. The present work proposes a dynamic mapping and scheduling algorithm based on the Cube-Tree-Hybrid (CTH) topology. The CTH network can integrate a large number of IP cores under significantly low network diameter, as opposed to mesh. Moreover, the design of CTH comes with considerable path diversity. For the above properties, mapping on CTH becomes simpler than mesh, which successfully minimizes the communication hop distance amongst various tasks of an application. Extensive experimentation has been done across several synthetic and real application workloads. Compared to the prevalent mesh-based mapping techniques, the proposed algorithm achieves a minimum gain of 56% on communication latency, whereas it is 36% in total power consumption. Minimum 14% improvement on applications' deadline satisfaction is achieved.","PeriodicalId":356322,"journal":{"name":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134435652","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":"3D Human Pose Estimation Using WiFi Signals","authors":"Yili Ren, Zi Wang, Yichao Wang, Sheng Tan, Yingying Chen, Jie Yang","doi":"10.1145/3485730.3492871","DOIUrl":"https://doi.org/10.1145/3485730.3492871","url":null,"abstract":"This paper presents GoPose, a 3D skeleton-based human pose estimation system that uses commodity WiFi devices at home. Our system leverages the WiFi signals reflected off the human body for 3D pose estimation. In contrast to prior systems that need dedicated sensors, our system does not require a user to wear any sensors and can reuse the WiFi devices that already exist in a home environment for mass adoption. To realize such a system, we leverage the 2D AoA estimation of the signals reflected from the human body and the deep learning techniques. Preliminary results show GoPose achieves a high accuracy of 4.5cm in various scenarios.","PeriodicalId":356322,"journal":{"name":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","volume":"132 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130891652","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":"SpiderWeb: Enabling Through-Screen Visible Light Communication","authors":"Hanting Ye, Qing Wang","doi":"10.1145/3485730.3485948","DOIUrl":"https://doi.org/10.1145/3485730.3485948","url":null,"abstract":"We are now witnessing a trend of realizing full-screen on electronic devices such as smartphones to maximize their screen-to-body ratio for a better user experience. Thus the bezel/narrow-bezel on today's devices to host various line-of-sight sensors would disappear. This trend not only is forcing sensors like the front cameras to be placed under the screen of devices, but also will challenge the deployment of the emerging Visible Light Communication (VLC) technology, a paradigm for the next-generation wireless communication. In this work, we propose the concept of through-screen VLC with photosensors placed under Organic Light-Emitting Diode (OLED) screen. Though being transparent, an OLED screen greatly attenuates the intensity of passing-through light, degrading the efficiency of intensity-based VLC systems. In this paper, we instead exploit the color domain to build SpiderWeb, a through-screen VLC system. For the first time, we observe that an OLED screen introduces a color-pulling effect at photosensors, affecting the decoding of color-based VLC signals. Motivated by this observation and by the structure of spider's web, we design the SWebCSK Color-Shift Keying modulation scheme and a slope-based demodulation method, which can eliminate the color-pulling effect. We prototype SpiderWeb with off-the-shelf hardware and evaluate its performance thoroughly under various scenarios. The results show that compared to existing solutions, our solutions can reduce the bit error rate by two orders of magnitude and can achieve a 3.4x data rate.","PeriodicalId":356322,"journal":{"name":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115363001","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":"Decentralized Federated Learning Framework for the Neighborhood: A Case Study on Residential Building Load Forecasting","authors":"Jiechao Gao, Wenpeng Wang, Zetian Liu, Md Fazlay Rabbi Masum Billah, Bradford Campbell","doi":"10.1145/3485730.3493450","DOIUrl":"https://doi.org/10.1145/3485730.3493450","url":null,"abstract":"The fast-growing trend of Internet of Things (IoT) has provided its users with opportunities to improve user experience such as voice assistants, smart cameras, and home energy management systems. Such smart home applications often require large numbers of diverse training data to accomplish a robust model. As single user may not have enough data to train such a model, users intent to collaboratively train their collected data in order to achieve better performance in such applications, which raise the concern of data privacy protection. Existing approaches for collaborative training need to aggregate data or intermediate model training updates in the cloud to perform load forecasting, which could directly or indirectly cause personal data leakage, alongside with significant communication bandwidth and extra cloud service monetary cost. In this paper, to ensure the performance of smart home applications as well as the protection of user data privacy, we introduce the decentralized federated learning framework for the neighborhood and show the study on residential building load forecasting application as an example. We present PriResi, a privacy-preserved, communication-efficient and cloud-service-free load forecasting system to solve the above problems in a residential building. We first introduce a decentralized federated learning framework, which allows the residents to process all collected data locally on the edge by broadcasting the model updates between the smart home agent in each residence. Second, we propose a gradient selection mechanism to reduce the number of aggregated gradients and the frequency of gradient broadcasting to achieve communication-efficient and high prediction results. The real-word dataset experiments show that our method can achieve 97% of load forecasting accuracy while preserving residences' privacy. We believe that our proposed decentralized federated learning framework can be widely used in other smart home applications as well.","PeriodicalId":356322,"journal":{"name":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115569726","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":"FedDL","authors":"Linlin Tu, Xiaomin Ouyang, Jiayu Zhou, Yuze He, Guoliang Xing","doi":"10.1145/3485730.3485946","DOIUrl":"https://doi.org/10.1145/3485730.3485946","url":null,"abstract":"Deep learning has been increasingly applied to improve human activity recognition (HAR) accuracy and reduce the human efforts of handcrafted feature extractions. Federated Learning (FL) is an emerging learning paradigm that enables the collaborative learning of a global model without exposing users' raw data. However, existing FL approaches yield unsatisfactory HAR performance as they fail to dynamically aggregate models according to the statistical diversity of users' data. In this paper, we propose FedDL, a novel federated learning system for HAR that can capture the underlying user relationships and apply them to learn personalized models for different users dynamically. Specifically, we design a dynamic layer sharing scheme that learns the similarity among users' model weights to form the sharing structure and merges models accordingly in an iterative, bottom-up layer-wise manner. FedDL merges local models based on the dynamic sharing scheme, significantly speeding up the convergence while maintaining high accuracy. We have implemented FedDL and evaluated using a new data set we collected using LiDAR and four public real-world datasets involving 178 users in total. The results show that FedDL outperforms several state-of-the-art FL paradigms in terms of model accuracy (by more than 15%), converging rate (by more than 70%), and communication overhead (about 30% reduction). Moreover, the testing results on the datasets of different scales show that FedDL has high scalability and hence can be deployed for large-scale real-world applications.","PeriodicalId":356322,"journal":{"name":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124262940","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":"Sense Me on the Ride: Accurate Mobile Sensing over a LoRa Backscatter Channel","authors":"Haotian Jiang, Jiacheng Zhang, Xiuzhen Guo, Yuan He","doi":"10.1145/3485730.3485933","DOIUrl":"https://doi.org/10.1145/3485730.3485933","url":null,"abstract":"Wireless sensing has great significance in Internet of Things (IoT) applications and has attracted substantial research interests in academia. In this study, we propose Palantir, a first-of-its-kind long-range sensing system based on the LoRa backscatter technology. By utilizing the ON-OFF-Keying modulated backscatter signals, Palantir can perform fine-grained long-range cyclist sensing. Our findings show that sensing is more susceptible to channel quality than communication. Hence, the design of Palantir particularly addresses the critical challenges of signal processing, such as amplitude instability, frequency offset, clock drift, spectrum leakage, and multiplicative noise. We implement Palantir and evaluate its performance by conducting comprehensive benchmark experiments. A prototype is also built and a case study of respiration monitoring in the real world is implemented. Results demonstrate that Palantir can perform accurate sensing at a range up to 100 m, which is twice that of state-of-the-art approaches. The median deviation of the detected motion period is as low as 0.2%.","PeriodicalId":356322,"journal":{"name":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121908447","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":"Modulated Molecular Channel Coding Scheme for Multi-Bacterial Transmitters","authors":"D. P. Martins, J. Drohan, S. Foley, L. Coffey, S. Balasubramaniam","doi":"10.1145/3485730.3494039","DOIUrl":"https://doi.org/10.1145/3485730.3494039","url":null,"abstract":"Synthetic biology has utilised engineering concepts for the rational design of biocompatible systems. Here we utilise two bacterial populations to create a modulated molecular channel coding scheme for molecular communications systems. We believe this approach can drive the development of more reliable biocompatible molecular communications systems to apply in the dairy industry.","PeriodicalId":356322,"journal":{"name":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122005023","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":"Social Distancing Compliance Monitoring for COVID-19 Recovery Through Footstep-Induced Floor Vibrations","authors":"Yiwen Dong, Yuyan Wu, H. Noh","doi":"10.1145/3485730.3492893","DOIUrl":"https://doi.org/10.1145/3485730.3492893","url":null,"abstract":"Monitoring the compliance of social distancing is critical for schools and offices to recover in-person operations in indoor spaces from the COVID-19 pandemic. Existing systems focus on vision- and wearable-based sensing approaches, which require direct line-of-sight or device-carrying and may also raise privacy concerns. To overcome these limitations, we introduce a new monitoring system for social distancing compliance based on footstep-induced floor vibration sensing. This system is device-free, non-intrusive, and perceived as more privacy-friendly. Our system leverages the insight that footsteps closer to the sensors generate vibration signals with larger amplitudes. The system first estimates the location of each person relative to the sensors based on signal energy and then infers the distance between two people. We evaluated the system through a real-world experiment with 8 people, and the system achieves an average accuracy of 97.8% for walking scenario classification and 80.4% in social distancing violation detection.","PeriodicalId":356322,"journal":{"name":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124825329","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 Battery-Free Long-Range Wireless Smart Camera for Face Recognition","authors":"Marco Giordano, M. Magno","doi":"10.1145/3485730.3493367","DOIUrl":"https://doi.org/10.1145/3485730.3493367","url":null,"abstract":"In this demo we present a battery-free smart camera that exploits aggressive power management and energy harvesting to achieve face recognition in an energy-neutral fashion. A novel hardware accelerator for Convolution Neural Networks is employed to speed up the inference of the Tiny Machine Learning algorithm. The recognized face, and not the entire image, is sent via LoRa in a sensor network-like scenario. Experimental results demonstrated the capability of the developed sensor node to start and work perpetually with only a small photovoltaic panel array.","PeriodicalId":356322,"journal":{"name":"Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127390081","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}