This paper outlines the research to develop a vehicular visible light communication system with the use of a new type of CMOS sensor: a dynamic vision sensor. Rather than reporting still frames and absolute intensity values, a DVS camera only outputs events when it observes a change in luminance. This unique property greatly reduces the possibility of wasting the valuable bandwidth in capturing fix image backgrounds. To understand the behavior of a DVS camera, preliminary experiments are carried out. Based on the experimental results, we propose to design a LED array which is able to achieve a long communication range even with low average luminance level, when using a DVS camera as the receiver. On the other hand, algorithms are also developed for addressing the system mobility issue. We believe that this proposed system can offer several advantages over the existing systems. First, long communication range is achieved with a much lower luminance level. Second, the system is able to perform simultaneous transmission without additional multiplexing overheads. Finally, with the use of a DVS camera, the bandwidth is preserved for data carrying and hence the chance for boosting the system throughput.
{"title":"Vehicular Visible Light Communication with Dynamic Vision Sensor","authors":"Wen-Hsuan Shen","doi":"10.1145/3325425.3329941","DOIUrl":"https://doi.org/10.1145/3325425.3329941","url":null,"abstract":"This paper outlines the research to develop a vehicular visible light communication system with the use of a new type of CMOS sensor: a dynamic vision sensor. Rather than reporting still frames and absolute intensity values, a DVS camera only outputs events when it observes a change in luminance. This unique property greatly reduces the possibility of wasting the valuable bandwidth in capturing fix image backgrounds. To understand the behavior of a DVS camera, preliminary experiments are carried out. Based on the experimental results, we propose to design a LED array which is able to achieve a long communication range even with low average luminance level, when using a DVS camera as the receiver. On the other hand, algorithms are also developed for addressing the system mobility issue. We believe that this proposed system can offer several advantages over the existing systems. First, long communication range is achieved with a much lower luminance level. Second, the system is able to perform simultaneous transmission without additional multiplexing overheads. Finally, with the use of a DVS camera, the bandwidth is preserved for data carrying and hence the chance for boosting the system throughput.","PeriodicalId":315182,"journal":{"name":"The ACM MobiSys 2019 on Rising Stars Forum","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134373147","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}
Tiny IoT devices have shown their utilities in many fields. However, due to the low cost, small form factor, and inherently restricted computation resources, these IoT devices are facing many fundamental challenges such as the power issue, the communication issue, and the security issue when deployed in scale or operated in long-term period. In this paper, we discuss the feasibility of using distributed antenna systems to facilitate the deployment of IoT devices. Specifically, by coherently combining the phase of each antenna in a 3D distributed antenna system, we form an energy ball at the target location where the energy density level is significantly higher than the energy density level at any other locations. We highlight the properties of energy ball and deploy a testbed with over 20 software defined radios. Our preliminary results demonstrate that this energy ball has a great potential to be leveraged to solve many fundamental problems in IoT and enable exciting IoT applications.
{"title":"Facilitating the Deployment of Next Billion IoT Devices with Distributed Antenna Systems","authors":"Xiaoran Fan","doi":"10.1145/3325425.3329943","DOIUrl":"https://doi.org/10.1145/3325425.3329943","url":null,"abstract":"Tiny IoT devices have shown their utilities in many fields. However, due to the low cost, small form factor, and inherently restricted computation resources, these IoT devices are facing many fundamental challenges such as the power issue, the communication issue, and the security issue when deployed in scale or operated in long-term period. In this paper, we discuss the feasibility of using distributed antenna systems to facilitate the deployment of IoT devices. Specifically, by coherently combining the phase of each antenna in a 3D distributed antenna system, we form an energy ball at the target location where the energy density level is significantly higher than the energy density level at any other locations. We highlight the properties of energy ball and deploy a testbed with over 20 software defined radios. Our preliminary results demonstrate that this energy ball has a great potential to be leveraged to solve many fundamental problems in IoT and enable exciting IoT applications.","PeriodicalId":315182,"journal":{"name":"The ACM MobiSys 2019 on Rising Stars Forum","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127922912","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}
In this work, we propose to develop an intelligent parking management system utilizing Radio Frequency Identification (RFID). The system can detect empty parking spaces by the reader mounted on the drone, and guide vehicles looking for a parking space to the nearest one. Our design can also calculate the parking fee based on time duration between the arrival and the departure of the parking vehicle, and charge to the owner automatically. We believe that the proposed system has numerous unique advantages over other solutions, such as camera-based system and those that requires sensors installed for each parking space. We hope that the idea can be quickly realized through this project and put into real use in the near future.
{"title":"Intelligent Parking Management System Utilizing RFID","authors":"Hao-Ping Wu","doi":"10.1145/3325425.3329942","DOIUrl":"https://doi.org/10.1145/3325425.3329942","url":null,"abstract":"In this work, we propose to develop an intelligent parking management system utilizing Radio Frequency Identification (RFID). The system can detect empty parking spaces by the reader mounted on the drone, and guide vehicles looking for a parking space to the nearest one. Our design can also calculate the parking fee based on time duration between the arrival and the departure of the parking vehicle, and charge to the owner automatically. We believe that the proposed system has numerous unique advantages over other solutions, such as camera-based system and those that requires sensors installed for each parking space. We hope that the idea can be quickly realized through this project and put into real use in the near future.","PeriodicalId":315182,"journal":{"name":"The ACM MobiSys 2019 on Rising Stars Forum","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124542905","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}
Information sharing in connected vehicle systems helps each participating vehicle to have a more complete and expanded sensing range beyond its own sensing capability. When sharing visual traffic information among vehicle nodes, it is of great significance to identify overlapping components and associate objects in common to create an accurate and complete surrounding scene. This paper Extends FusionEye, a study of perception sharing, by exploring deep learning approaches for real time vehicle verification tasks. We propose two deep neural network architectures inspired by ResNet and train the neural networks using FusionEye's dataset. Preliminary results show that when learning from vehicle's appearances and kinematic information, the verification accuracy reaches $92%$, which provides possible solution for real time system.
{"title":"Vehicle Verification Using Deep Learning for Connected Vehicle Sharing Systems","authors":"Hansi Liu","doi":"10.1145/3325425.3329944","DOIUrl":"https://doi.org/10.1145/3325425.3329944","url":null,"abstract":"Information sharing in connected vehicle systems helps each participating vehicle to have a more complete and expanded sensing range beyond its own sensing capability. When sharing visual traffic information among vehicle nodes, it is of great significance to identify overlapping components and associate objects in common to create an accurate and complete surrounding scene. This paper Extends FusionEye, a study of perception sharing, by exploring deep learning approaches for real time vehicle verification tasks. We propose two deep neural network architectures inspired by ResNet and train the neural networks using FusionEye's dataset. Preliminary results show that when learning from vehicle's appearances and kinematic information, the verification accuracy reaches $92%$, which provides possible solution for real time system.","PeriodicalId":315182,"journal":{"name":"The ACM MobiSys 2019 on Rising Stars Forum","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116201212","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}
The demand for a ubiquitous and accurate indoor localization service is continuously growing. Cellular-based systems, by definition, have been shown to be a perfect selection to provide a ubiquitous localization service. The main barrier towards achieving this goal is the heterogeneity of the many different types and models of cell phones which result in variations of the measured received signal strength (RSS) even from the same location at the same time. This is particular to fingerprinting-based localization where different types of phones may be used between the system training and tracking times. The performance of the current cellular-based solutions drops significantly. In this paper, we propose a deep learning-based system that leverages cellular measurements from training devices to provide consistent, fine-grained performance across unseen tracking phones with milliwatts of power consumption. The proposed system incorporates different components to extract the device-invariant features and improve the deep model's generalization and robustness, achieving device-transparent operation. Evaluation of the proposed system in a realistic testbed using three different Android phones with different form factors and sensing capability shows that it can achieve a consistent localization accuracy. This is better than the state-of-the-art indoor cellularbased systems by at least 65%. Our experiments show the promise of this method, yielding maximum median error typically within only 0.39 meter of training and testing with the same phone.
{"title":"Device-Invariant Cellular-Based Indoor Localization System Using Deep Learning","authors":"Hamada Rizk","doi":"10.1145/3325425.3329940","DOIUrl":"https://doi.org/10.1145/3325425.3329940","url":null,"abstract":"The demand for a ubiquitous and accurate indoor localization service is continuously growing. Cellular-based systems, by definition, have been shown to be a perfect selection to provide a ubiquitous localization service. The main barrier towards achieving this goal is the heterogeneity of the many different types and models of cell phones which result in variations of the measured received signal strength (RSS) even from the same location at the same time. This is particular to fingerprinting-based localization where different types of phones may be used between the system training and tracking times. The performance of the current cellular-based solutions drops significantly. In this paper, we propose a deep learning-based system that leverages cellular measurements from training devices to provide consistent, fine-grained performance across unseen tracking phones with milliwatts of power consumption. The proposed system incorporates different components to extract the device-invariant features and improve the deep model's generalization and robustness, achieving device-transparent operation. Evaluation of the proposed system in a realistic testbed using three different Android phones with different form factors and sensing capability shows that it can achieve a consistent localization accuracy. This is better than the state-of-the-art indoor cellularbased systems by at least 65%. Our experiments show the promise of this method, yielding maximum median error typically within only 0.39 meter of training and testing with the same phone.","PeriodicalId":315182,"journal":{"name":"The ACM MobiSys 2019 on Rising Stars Forum","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122063929","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}
In this early-stage work, we propose various solutions to enable the next generation of wireless sensors. Our vision is to introduce battery-free wireless sensors that can be deployed ubiquitously. Such sensors would have the ability to both infer the physical environment, and communicate the sensed information wirelessly. In particular, we explore the emerging research directions of ambient and analog RF backscatter for communication, and visible light for sensing. We combine these concepts with energy harvesting to achieve self-powered operation. Furthermore, we introduce novel mechanisms that eliminate sensor-local computational blocks, and instead couple sensors directly to ultra-low power communication modules to transmit sensor information. Our initial results show that we are able to achieve operation of both sensing and communication at a few microwatts of power. Moreover, we can maintain a sufficiently high sensing resolution to enable novel battery-free applications such as hand gesture sensing and intrusion detection.
{"title":"Enabling the Next Generation of Wireless Sensors","authors":"Andreas Soleiman","doi":"10.1145/3325425.3329939","DOIUrl":"https://doi.org/10.1145/3325425.3329939","url":null,"abstract":"In this early-stage work, we propose various solutions to enable the next generation of wireless sensors. Our vision is to introduce battery-free wireless sensors that can be deployed ubiquitously. Such sensors would have the ability to both infer the physical environment, and communicate the sensed information wirelessly. In particular, we explore the emerging research directions of ambient and analog RF backscatter for communication, and visible light for sensing. We combine these concepts with energy harvesting to achieve self-powered operation. Furthermore, we introduce novel mechanisms that eliminate sensor-local computational blocks, and instead couple sensors directly to ultra-low power communication modules to transmit sensor information. Our initial results show that we are able to achieve operation of both sensing and communication at a few microwatts of power. Moreover, we can maintain a sufficiently high sensing resolution to enable novel battery-free applications such as hand gesture sensing and intrusion detection.","PeriodicalId":315182,"journal":{"name":"The ACM MobiSys 2019 on Rising Stars Forum","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125234417","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：