{"title":"Context Sensing and Feature Discovery for Improving Classifications","authors":"Md. Sumon Shahriar, M. S. Rahman","doi":"10.1145/2820716.2820720","DOIUrl":"https://doi.org/10.1145/2820716.2820720","url":null,"abstract":"We propose context sensing as features for improved accuracy in classifications in our ongoing research. In many applications, features extracted from purposed sensors may not be enough for classification tasks accurately. Context features can help to discriminate classes in such cases. To address the problem, we first present how context can be used as features in classifications. Further, we present a case study on energy appliance identification from aggregated power usage for a household using context sensing and features.","PeriodicalId":218586,"journal":{"name":"Proceedings of the 1st Workshop on Context Sensing and Activity Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130412101","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":"An Efficient Variable Dimension PSO Algorithm for Mobile Node Tour Planning in WSN","authors":"Wei Wang, Haoshan Shi, Pengyu Huang, Fuping Wu, Dingyi Fang, Xiaojiang Chen, Xiaoyan Yin","doi":"10.1145/2820716.2820723","DOIUrl":"https://doi.org/10.1145/2820716.2820723","url":null,"abstract":"Recent advances in unmanned aerial vehicle (UAV) and wireless charging technologies have made it practical to introduce a mobile node into Wireless Sensor Networks (WSN). This mobile node with sink ability or charging equipment on it can travel around the entire network to gather data from isolate sensor nodes or charge the nodes wirelessly. This can help with the large scale WSN to be connected or keep working for a long time without replacing batteries. For the mobile node, routing design is an important problem. We can regard this problem as a special case of traveling salesman problem with neighborhoods (TSPN), which is NP-hard. In this paper, we propose a novel routing design algorithm base on Variable Dimensions Particle Swarm Optimization (VD-PSO). In this algorithm, every particle is a feasible solution of TSPN. Every dimension of the particle is the coordinates of a rendezvous point (the point where mobile node stay to gather data or charge the nodes). And the dimensionality is right the number of the rendezvous point. With the evolutionary method of the particles, we can derive the best route of the mobile node. Simulation results show that our scheme has fast convergence speed, and the result is quite approximate to the optimal solution.","PeriodicalId":218586,"journal":{"name":"Proceedings of the 1st Workshop on Context Sensing and Activity Recognition","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121297428","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":"Session details: Session 1: Security and Localization","authors":"Jinsong Han","doi":"10.1145/3254002","DOIUrl":"https://doi.org/10.1145/3254002","url":null,"abstract":"","PeriodicalId":218586,"journal":{"name":"Proceedings of the 1st Workshop on Context Sensing and Activity Recognition","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121063581","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":"Session details: Session 3: Sensors and Sensing","authors":"Chen Qian","doi":"10.1145/3254004","DOIUrl":"https://doi.org/10.1145/3254004","url":null,"abstract":"","PeriodicalId":218586,"journal":{"name":"Proceedings of the 1st Workshop on Context Sensing and Activity Recognition","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121376080","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}
Jiaqing Luo, Shijie Zhou, Hongrong Cheng, Yongjian Liao, Bin Guo
{"title":"The Design and Implementation of A Cost-effective RFID Indoor Localization System","authors":"Jiaqing Luo, Shijie Zhou, Hongrong Cheng, Yongjian Liao, Bin Guo","doi":"10.1145/2820716.2820718","DOIUrl":"https://doi.org/10.1145/2820716.2820718","url":null,"abstract":"Recently, there has been growing interest in indoor localization, because numerous applications depend on the rapid and accurate position estimation of tagged objects. While RFID-based indoor localization is attractive, the need for a large-scale and high-density deployment of readers and reference tags is costly. By using mobile readers mounted on guide rails, we design and implement a cost-effective RFID indoor localization system, which requires neither reference tags nor RSSI functions, for stock-taking and searching in warehouse operations. In particular, we install two guide rails, which can allow a reader to move horizontally or vertically, on the ceiling of a warehouse or workshop. We then propose a continuous scanning algorithm to improve the accuracy for locating a single tagged object, and a category-based scheduling algorithm to shorten the time for locating multiple tagged objects. Our primary experimental results show that the system can achieve high time efficiency and localization accuracy in the indoor localization.","PeriodicalId":218586,"journal":{"name":"Proceedings of the 1st Workshop on Context Sensing and Activity Recognition","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129281653","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":"Prevent CSI Spoofing in Uplink MU-MIMO Transmission","authors":"Wei Xi, Rong Ma, Yuanhang Cai, K. Zhao","doi":"10.1145/2820716.2820726","DOIUrl":"https://doi.org/10.1145/2820716.2820726","url":null,"abstract":"A Multi-User MIMO (MU-MIMO) Access Point (AP) can obtain a capacity gain by simultaneously transmitting for multiple clients. In order to select concurrent uplink (UL) users with strong channel orthogonality and thus high total capacity, channel state information (CSI) feedback from users is required. However, the inaccurate CSI feedback can seriously influence the efficiency of data transmission. Moreover, due to spontaneous uplink traffic, uplink user s- election cannot rely on the access point central assignment and needs a distributed realization instead, which makes the problem even more challenging. In this paper, we propose a CSI validation algorithm, called CVU, to detect the CSI spoofing of uplink users. CVU requires CSI at transmitting AP to set antenna gains and phases to enable simultaneous verification code distribution through beamforming. Only accurate CSI feedback can user accurately obtains its verification code. AP selects the users with accurate verification codes to obtain their data using a nonlinear equalizer. Our simulation results show that CVU significantly outperforms state-of-the-art user selection methods under CSI spoofing attack.","PeriodicalId":218586,"journal":{"name":"Proceedings of the 1st Workshop on Context Sensing and Activity Recognition","volume":"19 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128902072","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":"Doppler Effect based Moving Target Detection Adaptive to Speed","authors":"Tianzhang Xing, Dingyi Fang, Xiaojiang Chen, Meng Jin, Xin Zheng, K. Zhao","doi":"10.1145/2820716.2820722","DOIUrl":"https://doi.org/10.1145/2820716.2820722","url":null,"abstract":"Moving target detection serves as a key enabler for various applications such as campus security, military battlefield, and wildlife protection. Conventional detection systems usually adopt the multimedia or RF based technology (e.g. the Doppler shift). The performance of the detection system based on multimedia is usually limited by light and monitoring perspective. In the detection system based on RF, the detection rate is affected by false noise, because the signal mutation (maybe caused by fast motion) and weak change (maybe caused by slow motion) are deemed to the false noise which is easy ignored. In this paper, we present the moving target detection system MovLoc based on Doppler detecting, that is robust to velocity different motion velocity. In order to the minute Doppler shifts extracted accurately, MovLoc uses the Sliding Cumulative Difference Window (SCDW) under the Filtered Multi-tone (FMT) modulation. Then, the arrival angle estimated by the Accumulated Ring (AR) algorithm, can used to localize the target. Our experimental results show that MovLoc achieves an average false positive of 9% and an average false negative of 6% in detecting target with 3 different velocities.","PeriodicalId":218586,"journal":{"name":"Proceedings of the 1st Workshop on Context Sensing and Activity Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130309556","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}
Fu Xiao, Xiaohui Xie, Hai Zhu, Lijuan Sun, Ruchuan Wang
{"title":"Invisible Cloak Fails: CSI-based Passive Human Detection","authors":"Fu Xiao, Xiaohui Xie, Hai Zhu, Lijuan Sun, Ruchuan Wang","doi":"10.1145/2820716.2820719","DOIUrl":"https://doi.org/10.1145/2820716.2820719","url":null,"abstract":"WiFi signals have attracted extensive attention for context-aware due to its ubiquity. Traditional WiFi sensing methods mainly adopt Received Signal Strength Indication (RSSI), however the coarse features hamper its expansion. To achieve more finger-grained information, Channel State Information (CSI) is introduced for sensing, based on which, we design a directional human detection scheme via data prediction, which aims to visualize the variations of CSI when human appears. However, this scheme suffers from the limitations caused by the link-centric architecture of WiFi. Considering the demands for omni-directional coverage of some scenarios (e.g. museum exhibition), we propose a omni-directional detection scheme based on fingerprinting utilizing the relationship between the CSI signal features and locations. Experiments are processed in actual scenarios and experimental results verify the feasibility of our two schemes.","PeriodicalId":218586,"journal":{"name":"Proceedings of the 1st Workshop on Context Sensing and Activity Recognition","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127443916","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":"Session details: Session 2: Wi-Fi based Context Recognition","authors":"Panlong Yang","doi":"10.1145/3254003","DOIUrl":"https://doi.org/10.1145/3254003","url":null,"abstract":"","PeriodicalId":218586,"journal":{"name":"Proceedings of the 1st Workshop on Context Sensing and Activity Recognition","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133443234","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":"SenSys: A Sensor Data Sharing System for Smart Devices using Bluetooth Low Energy","authors":"H. Gupta, Shivakumar S. Bagi, Avinash Uttav","doi":"10.1145/2820716.2820728","DOIUrl":"https://doi.org/10.1145/2820716.2820728","url":null,"abstract":"In this work, we present SenSys, a Sensor data sharing System for smart devices. The SenSys opportunistically shares the sensor data of a smart device to other nearby smart devices using Bluetooth Low Energy. The SenSys has been evaluated by well-designed practical experiments to share the sensor data. The prototype results show that the SenSys requires very limited time for sharing the sensor data, reduces the power consumption, and increases the accuracy.","PeriodicalId":218586,"journal":{"name":"Proceedings of the 1st Workshop on Context Sensing and Activity Recognition","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130234143","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}