Hokeun Kim, Eunsuk Kang, David Broman, Edward A. Lee
An emerging type of network architecture called edge computing has the potential to improve the availability and resilience of IoT services under anomalous situations such as network failures or denial-of-service (DoS) attacks. However, relatively little has been explored on the problem of ensuring availability even when edge computers that provide key security services (e.g., authentication and authorization) become unavailable themselves. This article proposes a resilient authentication and authorization framework to enhance the availability of IoT services under DoS attacks or failures. The proposed approach leverages a technique called secure migration, which allows an IoT device to migrate to another trusted edge computer when its own local authorization service becomes unavailable. Specifically, we describe the design of a secure migration framework and its supporting mechanisms, including (1) automated migration policy construction and (2) protocols for preparing and executing the secure migration. We formalize secure migration policy construction as an integer linear programming (ILP) problem and show its effectiveness using a case study on smart buildings, where the proposed solution achieves significantly higher availability under simulated attacks on authorization services.
{"title":"Resilient Authentication and Authorization for the Internet of Things (IoT) Using Edge Computing","authors":"Hokeun Kim, Eunsuk Kang, David Broman, Edward A. Lee","doi":"10.1145/3375837","DOIUrl":"https://doi.org/10.1145/3375837","url":null,"abstract":"An emerging type of network architecture called edge computing has the potential to improve the availability and resilience of IoT services under anomalous situations such as network failures or denial-of-service (DoS) attacks. However, relatively little has been explored on the problem of ensuring availability even when edge computers that provide key security services (e.g., authentication and authorization) become unavailable themselves. This article proposes a resilient authentication and authorization framework to enhance the availability of IoT services under DoS attacks or failures. The proposed approach leverages a technique called secure migration, which allows an IoT device to migrate to another trusted edge computer when its own local authorization service becomes unavailable. Specifically, we describe the design of a secure migration framework and its supporting mechanisms, including (1) automated migration policy construction and (2) protocols for preparing and executing the secure migration. We formalize secure migration policy construction as an integer linear programming (ILP) problem and show its effectiveness using a case study on smart buildings, where the proposed solution achieves significantly higher availability under simulated attacks on authorization services.","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":"62 1","pages":"1 - 27"},"PeriodicalIF":2.7,"publicationDate":"2020-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73605942","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 Internet of Things (IoT) demands synergy among several research domains and incorporates a broad range of multidisciplinary topics, including low-power wireless networking, embedded systems, data streaming architectures, data analytics and machine learning, cloud and edge computing, service computing and middleware, and security and privacy, as well as social computing. ACM Transactions on Internet of Things (TIOT) publishes novel research contributions and experience reports broadly related to these topics and their interrelations in the context of IoT, with a focus on system designs, end-to-end architectures, and enabling technologies, covering in principle the entire spectrum from hardware devices up to the application layer. Along with this large breadth of scope, another defining element of TIOT is that the results and insights reported in it must be corroborated by a strong experimental component. This is expected to offer evidence of the proposed techniques in realistic scenarios (e.g., based on field deployments or user studies) or public datasets, with the intent to facilitate adoption and exploitation in the real world of the novel ideas published in TIOT. In the same light, experience reports about the use or adaptation of known systems and techniques in real-world applications are equally welcome, as these studies elicit valuable insights for researchers and practitioners alike. This first, inaugural issue bears witness to the aforementioned breadth of topics and emphasis on experimental validation, as it begins with articles proposing novel system-level techniques concerned with wearable computing and light-based positioning, continues with contributions concerned with security at the edge and IoT services in the cloud, and then ends with the definition of ontologies for IoT applications. Many other interesting papers have already been accepted and will appear in the upcoming issues. All of these high-quality contributions have been selected from an outstanding number of submissions from all over the world. We are very excited to see that the research field of IoT is increasingly gaining momentum. In this respect, we are fortunate to have an outstanding editorial board helping us with the process of reviewing and selecting from these many and diverse submissions. The associate editors on the board reflect the scientific mission and values of TIOT and comprise top-notch researchers from academia and industry, with a balanced mix of seniority, gender, and geography. We sincerely thank all of them for accepting to help us in the delicate task of bringing the first issues of TIOT to reality. Indeed, ACM TIOT is the result of the work of many people, some of whom we want to publicly thank in this inaugural editorial. We are very grateful to Steve Welch and the ACM Publications Board for kickstarting the process by contacting us and planting the seed of a new transaction on IoT in our heads. Lothar Thiele and Tarek Abdelzaher drafted t
{"title":"ACM Transactions on Internet of Things","authors":"S. Dustdar, G. Picco","doi":"10.1145/3379599","DOIUrl":"https://doi.org/10.1145/3379599","url":null,"abstract":"The Internet of Things (IoT) demands synergy among several research domains and incorporates a broad range of multidisciplinary topics, including low-power wireless networking, embedded systems, data streaming architectures, data analytics and machine learning, cloud and edge computing, service computing and middleware, and security and privacy, as well as social computing. ACM Transactions on Internet of Things (TIOT) publishes novel research contributions and experience reports broadly related to these topics and their interrelations in the context of IoT, with a focus on system designs, end-to-end architectures, and enabling technologies, covering in principle the entire spectrum from hardware devices up to the application layer. Along with this large breadth of scope, another defining element of TIOT is that the results and insights reported in it must be corroborated by a strong experimental component. This is expected to offer evidence of the proposed techniques in realistic scenarios (e.g., based on field deployments or user studies) or public datasets, with the intent to facilitate adoption and exploitation in the real world of the novel ideas published in TIOT. In the same light, experience reports about the use or adaptation of known systems and techniques in real-world applications are equally welcome, as these studies elicit valuable insights for researchers and practitioners alike. This first, inaugural issue bears witness to the aforementioned breadth of topics and emphasis on experimental validation, as it begins with articles proposing novel system-level techniques concerned with wearable computing and light-based positioning, continues with contributions concerned with security at the edge and IoT services in the cloud, and then ends with the definition of ontologies for IoT applications. Many other interesting papers have already been accepted and will appear in the upcoming issues. All of these high-quality contributions have been selected from an outstanding number of submissions from all over the world. We are very excited to see that the research field of IoT is increasingly gaining momentum. In this respect, we are fortunate to have an outstanding editorial board helping us with the process of reviewing and selecting from these many and diverse submissions. The associate editors on the board reflect the scientific mission and values of TIOT and comprise top-notch researchers from academia and industry, with a balanced mix of seniority, gender, and geography. We sincerely thank all of them for accepting to help us in the delicate task of bringing the first issues of TIOT to reality. Indeed, ACM TIOT is the result of the work of many people, some of whom we want to publicly thank in this inaugural editorial. We are very grateful to Steve Welch and the ACM Publications Board for kickstarting the process by contacting us and planting the seed of a new transaction on IoT in our heads. Lothar Thiele and Tarek Abdelzaher drafted t","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":"16 1","pages":"1 - 2"},"PeriodicalIF":2.7,"publicationDate":"2020-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73818823","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 adoption of the Internet of Things is gradually increasing. However, there remains a significant obstacle that hinders its adoption as a truly ubiquitous technology: the ability of constrained devices to unambiguously exchange data with shared meaning. In this respect, the World Wide Web Consortium has developed the Web of Things architecture to provide semantic data exchange. However, such an architecture does not cover all possible use cases and still has important limitations. This article specifically addresses these issues. In particular, it discusses the design and implementation of a solution that extends the Web of Things architecture to achieve a higher level of semantic interoperability for the Internet of Things. The proposed solution relies on a human-assisted translation process and defines an architecture that enhances the semantic compatibility between components in the World Wide Web Consortium and the Internet Engineering Task Force. The effectiveness of the proposed solution is demonstrated through both a quantitative and a qualitative evaluation, in terms of performance and key properties in comparison with the state of the art.
{"title":"Semantic Interoperability in the IoT","authors":"Oscar Novo, M. D. Francesco","doi":"10.1145/3375838","DOIUrl":"https://doi.org/10.1145/3375838","url":null,"abstract":"The adoption of the Internet of Things is gradually increasing. However, there remains a significant obstacle that hinders its adoption as a truly ubiquitous technology: the ability of constrained devices to unambiguously exchange data with shared meaning. In this respect, the World Wide Web Consortium has developed the Web of Things architecture to provide semantic data exchange. However, such an architecture does not cover all possible use cases and still has important limitations. This article specifically addresses these issues. In particular, it discusses the design and implementation of a solution that extends the Web of Things architecture to achieve a higher level of semantic interoperability for the Internet of Things. The proposed solution relies on a human-assisted translation process and defines an architecture that enhances the semantic compatibility between components in the World Wide Web Consortium and the Internet Engineering Task Force. The effectiveness of the proposed solution is demonstrated through both a quantitative and a qualitative evaluation, in terms of performance and key properties in comparison with the state of the art.","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":"27 1","pages":"1 - 25"},"PeriodicalIF":2.7,"publicationDate":"2020-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81151330","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}
Chengwen Luo, Jiawei Wu, Jian-qiang Li, Jia Wang, Weitao Xu, Zhong Ming, Bo Wei, Wei Li, Albert Y. Zomaya
Recently, Internet of Things (IoT) has raised as an important research area that combines the environmental sensing and machine learning capabilities to flourish the concept of smart spaces, in which intelligent and customized services can be provided to users in a smart manner. In smart spaces, one fundamental service that needs to be provided is accurate and unobtrusive user identification. In this work, to address this challenge, we propose a Gait Recognition as a Service (GRaaS) model, which is an instantiation of the traditional Sensing as a Service (S2aaS) model, and is specially deigned for user identification using gait in smart spaces. To illustrate the idea, a Radio Frequency Identification (RFID)-based gait recognition service is designed and implemented following the GRaaS concept. Novel tag selection algorithms and attention-based Long Short-term Memory (At-LSTM) models are designed to realize the device layer and edge layer, achieving a robust recognition with 96.3% accuracy. Extensive evaluations are provided, which show that the proposed service has accurate and robust performance and has great potential to support future smart space applications.
{"title":"Gait Recognition as a Service for Unobtrusive User Identification in Smart Spaces","authors":"Chengwen Luo, Jiawei Wu, Jian-qiang Li, Jia Wang, Weitao Xu, Zhong Ming, Bo Wei, Wei Li, Albert Y. Zomaya","doi":"10.1145/3375799","DOIUrl":"https://doi.org/10.1145/3375799","url":null,"abstract":"Recently, Internet of Things (IoT) has raised as an important research area that combines the environmental sensing and machine learning capabilities to flourish the concept of smart spaces, in which intelligent and customized services can be provided to users in a smart manner. In smart spaces, one fundamental service that needs to be provided is accurate and unobtrusive user identification. In this work, to address this challenge, we propose a Gait Recognition as a Service (GRaaS) model, which is an instantiation of the traditional Sensing as a Service (S2aaS) model, and is specially deigned for user identification using gait in smart spaces. To illustrate the idea, a Radio Frequency Identification (RFID)-based gait recognition service is designed and implemented following the GRaaS concept. Novel tag selection algorithms and attention-based Long Short-term Memory (At-LSTM) models are designed to realize the device layer and edge layer, achieving a robust recognition with 96.3% accuracy. Extensive evaluations are provided, which show that the proposed service has accurate and robust performance and has great potential to support future smart space applications.","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":"5 1","pages":"1 - 21"},"PeriodicalIF":2.7,"publicationDate":"2020-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78639817","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}
Zheng Dong, Yan Lu, G. Tong, Yuanchao Shu, Shuai Wang, Weisong Shi
Vehicle tracking, a core application to smart city video analytics, is becoming more widely deployed than ever before thanks to the increasing number of traffic cameras and recent advances in computer vision and machine-learning. Due to the constraints of bandwidth, latency, and privacy concerns, tracking tasks are more preferable to run on edge devices sitting close to the cameras. However, edge devices are provisioned with a fixed amount of computing budget, making them incompetent to adapt to time-varying and imbalanced tracking workloads caused by traffic dynamics. In coping with this challenge, we propose WatchDog, a real-time vehicle tracking system that fully utilizes edge nodes across the road network. WatchDog leverages computer vision tasks with different resource-accuracy tradeoffs, and decomposes and schedules tracking tasks judiciously across edge devices based on the current workload to maximize the number of tasks while ensuring a provable response time-bound at each edge device. Extensive evaluations have been conducted using real-world city-wide vehicle trajectory datasets, achieving exceptional tracking performance with a real-time guarantee.
{"title":"WatchDog: Real-time Vehicle Tracking on Geo-distributed Edge Nodes","authors":"Zheng Dong, Yan Lu, G. Tong, Yuanchao Shu, Shuai Wang, Weisong Shi","doi":"10.1145/3549551","DOIUrl":"https://doi.org/10.1145/3549551","url":null,"abstract":"Vehicle tracking, a core application to smart city video analytics, is becoming more widely deployed than ever before thanks to the increasing number of traffic cameras and recent advances in computer vision and machine-learning. Due to the constraints of bandwidth, latency, and privacy concerns, tracking tasks are more preferable to run on edge devices sitting close to the cameras. However, edge devices are provisioned with a fixed amount of computing budget, making them incompetent to adapt to time-varying and imbalanced tracking workloads caused by traffic dynamics. In coping with this challenge, we propose WatchDog, a real-time vehicle tracking system that fully utilizes edge nodes across the road network. WatchDog leverages computer vision tasks with different resource-accuracy tradeoffs, and decomposes and schedules tracking tasks judiciously across edge devices based on the current workload to maximize the number of tasks while ensuring a provable response time-bound at each edge device. Extensive evaluations have been conducted using real-world city-wide vehicle trajectory datasets, achieving exceptional tracking performance with a real-time guarantee.","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":"21 1","pages":"1 - 23"},"PeriodicalIF":2.7,"publicationDate":"2020-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85192654","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}
Noah J. Apthorpe, Pardis Emami-Naeini, Arunesh Mathur, M. Chetty, N. Feamster
Internet-connected consumer devices have rapidly increased in popularity; however, relatively little is known about how these technologies are affecting interpersonal relationships in multi-occupant households. In this study, we conduct 13 semi-structured interviews and survey 508 individuals from a variety of backgrounds to discover and categorize how consumer IoT devices are affecting interpersonal relationships in the United States. We highlight several themes, providing exploratory data about the pervasiveness of interpersonal costs and benefits of consumer IoT devices. These results inform follow-up studies and design priorities for future IoT technologies to amplify positive and reduce negative interpersonal effects.
{"title":"You, Me, and IoT: How Internet-connected Consumer Devices Affect Interpersonal Relationships","authors":"Noah J. Apthorpe, Pardis Emami-Naeini, Arunesh Mathur, M. Chetty, N. Feamster","doi":"10.1145/3539737","DOIUrl":"https://doi.org/10.1145/3539737","url":null,"abstract":"Internet-connected consumer devices have rapidly increased in popularity; however, relatively little is known about how these technologies are affecting interpersonal relationships in multi-occupant households. In this study, we conduct 13 semi-structured interviews and survey 508 individuals from a variety of backgrounds to discover and categorize how consumer IoT devices are affecting interpersonal relationships in the United States. We highlight several themes, providing exploratory data about the pervasiveness of interpersonal costs and benefits of consumer IoT devices. These results inform follow-up studies and design priorities for future IoT technologies to amplify positive and reduce negative interpersonal effects.","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":"68 1","pages":"1 - 29"},"PeriodicalIF":2.7,"publicationDate":"2020-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81316251","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}
Fog computing is a promising computing paradigm in which IoT data can be processed near the edge to support time-sensitive applications. However, the availability of resources in computation devices is not stable, since they may not be exclusively dedicated to the Fog application processing in the Fog environment. This, combined with dynamic user behaviour, can affect the execution of applications. To address dynamic changes in user behaviour in resource-limited Fog devices, this article proposes a multi-criteria–based resource allocation policy with resource reservation to minimise overall delay, processing time, and SLA violations. This process considers Fog computing–related characteristics, such as device heterogeneity, resource constraints, and mobility, as well as dynamic changes in user requirements. We employ multiple objective functions to find appropriate resources for executing time-sensitive tasks in the Fog environment. Experimental results show that our proposed policy performs better than the existing one, reducing the total delay by 51%. The proposed algorithm also reduces processing time and SLA violations, which is beneficial for running time-sensitive applications in the Fog environment.
{"title":"Multi-criteria--based Dynamic User Behaviour--aware Resource Allocation in Fog Computing","authors":"R. Naha, S. Garg","doi":"10.1145/3423332","DOIUrl":"https://doi.org/10.1145/3423332","url":null,"abstract":"Fog computing is a promising computing paradigm in which IoT data can be processed near the edge to support time-sensitive applications. However, the availability of resources in computation devices is not stable, since they may not be exclusively dedicated to the Fog application processing in the Fog environment. This, combined with dynamic user behaviour, can affect the execution of applications. To address dynamic changes in user behaviour in resource-limited Fog devices, this article proposes a multi-criteria–based resource allocation policy with resource reservation to minimise overall delay, processing time, and SLA violations. This process considers Fog computing–related characteristics, such as device heterogeneity, resource constraints, and mobility, as well as dynamic changes in user requirements. We employ multiple objective functions to find appropriate resources for executing time-sensitive tasks in the Fog environment. Experimental results show that our proposed policy performs better than the existing one, reducing the total delay by 51%. The proposed algorithm also reduces processing time and SLA violations, which is beneficial for running time-sensitive applications in the Fog environment.","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":"53 1","pages":"1 - 31"},"PeriodicalIF":2.7,"publicationDate":"2019-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85455267","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}
Jie Jiang, Riccardo Pozza, Nigel Gilbert, K. Moessner
There has been increasing interest in deploying Internet of Things (IoT) devices to study human behavior in locations such as homes and offices. Such devices can be deployed in a laboratory or “in the wild” in natural environments. The latter allows one to collect behavioral data that is not contaminated by the artificiality of a laboratory experiment. Using IoT devices in ordinary environments also brings the benefits of reduced cost, as compared with lab experiments, and less disturbance to the participants’ daily routines, which in turn helps with recruiting them into the research. However, in this case, it is essential to have an IoT infrastructure that can be easily and swiftly installed and from which real-time data can be securely and straightforwardly collected. In this article, we present MakeSense, an IoT testbed that enables real-world experimentation for large-scale social research on indoor activities through real-time monitoring and/or situation-aware applications. The testbed features quick setup, flexibility in deployment, the integration of a range of IoT devices, resilience, and scalability. We also present two case studies to demonstrate the use of the testbed: one in homes and one in offices.
{"title":"MakeSense","authors":"Jie Jiang, Riccardo Pozza, Nigel Gilbert, K. Moessner","doi":"10.1145/3381914","DOIUrl":"https://doi.org/10.1145/3381914","url":null,"abstract":"There has been increasing interest in deploying Internet of Things (IoT) devices to study human behavior in locations such as homes and offices. Such devices can be deployed in a laboratory or “in the wild” in natural environments. The latter allows one to collect behavioral data that is not contaminated by the artificiality of a laboratory experiment. Using IoT devices in ordinary environments also brings the benefits of reduced cost, as compared with lab experiments, and less disturbance to the participants’ daily routines, which in turn helps with recruiting them into the research. However, in this case, it is essential to have an IoT infrastructure that can be easily and swiftly installed and from which real-time data can be securely and straightforwardly collected. In this article, we present MakeSense, an IoT testbed that enables real-world experimentation for large-scale social research on indoor activities through real-time monitoring and/or situation-aware applications. The testbed features quick setup, flexibility in deployment, the integration of a range of IoT devices, resilience, and scalability. We also present two case studies to demonstrate the use of the testbed: one in homes and one in offices.","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":"24 1","pages":"1 - 25"},"PeriodicalIF":2.7,"publicationDate":"2019-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86926536","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}
Device-free context awareness is important to many applications. There are two broadly used approaches for device-free context awareness, i.e., video-based and radio-based. Video-based approaches can deliver good performance, but privacy is a serious concern. Radio-based context awareness applications have drawn researchers' attention instead, because it does not violate privacy and radio signal can penetrate obstacles. The existing works design explicit methods for each radio-based application. Furthermore, they use one additional step to extract features before conducting classification and exploit deep learning as a classification tool. Although this feature extraction step helps explore patterns of raw signals, it generates unnecessary noise and information loss. The use of raw CSI signal without initial data processing was, however, considered as no usable patterns. In this article, we are the first to propose an innovative deep learning–based general framework for both signal processing and classification. The key novelty of this article is that the framework can be generalised for all the radio-based context awareness applications with the use of raw CSI. We also eliminate the extra work to extract features from raw radio signals. We conduct extensive evaluations to show the superior performance of our proposed method and its generalisation.
{"title":"No Need of Data Pre-processing","authors":"Bo Wei, K. Li, Chengwen Luo, Weitao Xu, Jin Zhang","doi":"10.1145/3467980","DOIUrl":"https://doi.org/10.1145/3467980","url":null,"abstract":"Device-free context awareness is important to many applications. There are two broadly used approaches for device-free context awareness, i.e., video-based and radio-based. Video-based approaches can deliver good performance, but privacy is a serious concern. Radio-based context awareness applications have drawn researchers' attention instead, because it does not violate privacy and radio signal can penetrate obstacles. The existing works design explicit methods for each radio-based application. Furthermore, they use one additional step to extract features before conducting classification and exploit deep learning as a classification tool. Although this feature extraction step helps explore patterns of raw signals, it generates unnecessary noise and information loss. The use of raw CSI signal without initial data processing was, however, considered as no usable patterns. In this article, we are the first to propose an innovative deep learning–based general framework for both signal processing and classification. The key novelty of this article is that the framework can be generalised for all the radio-based context awareness applications with the use of raw CSI. We also eliminate the extra work to extract features from raw radio signals. We conduct extensive evaluations to show the superior performance of our proposed method and its generalisation.","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":"16 1","pages":"1 - 26"},"PeriodicalIF":2.7,"publicationDate":"2019-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72908806","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}
Miguel de Prado, Jing Su, Rabia Saeed, Lorenzo Keller, Noelia Vállez, Andrew Anderson, David Gregg, L. Benini, Tim Llewellynn, N. Ouerhani, Rozenn Dahyot, Nuria Pazos
Next generation of embedded Information and Communication Technology (ICT) systems are interconnected and collaborative systems able to perform autonomous tasks. The remarkable expansion of the embedded ICT market, together with the rise and breakthroughs of Artificial Intelligence (AI), have put the focus on the Edge as it stands as one of the keys for the next technological revolution: the seamless integration of AI in our daily life. However, training and deployment of custom AI solutions on embedded devices require a fine-grained integration of data, algorithms, and tools to achieve high accuracy and overcome functional and non-functional requirements. Such integration requires a high level of expertise that becomes a real bottleneck for small and medium enterprises wanting to deploy AI solutions on the Edge, which, ultimately, slows down the adoption of AI on applications in our daily life. In this work, we present a modular AI pipeline as an integrating framework to bring data, algorithms, and deployment tools together. By removing the integration barriers and lowering the required expertise, we can interconnect the different stages of particular tools and provide a modular end-to-end development of AI products for embedded devices. Our AI pipeline consists of four modular main steps: (i) data ingestion, (ii) model training, (iii) deployment optimization, and (iv) the IoT hub integration. To show the effectiveness of our pipeline, we provide examples of different AI applications during each of the steps. Besides, we integrate our deployment framework, Low-Power Deep Neural Network (LPDNN), into the AI pipeline and present its lightweight architecture and deployment capabilities for embedded devices. Finally, we demonstrate the results of the AI pipeline by showing the deployment of several AI applications such as keyword spotting, image classification, and object detection on a set of well-known embedded platforms, where LPDNN consistently outperforms all other popular deployment frameworks.
{"title":"Bonseyes AI Pipeline—Bringing AI to You","authors":"Miguel de Prado, Jing Su, Rabia Saeed, Lorenzo Keller, Noelia Vállez, Andrew Anderson, David Gregg, L. Benini, Tim Llewellynn, N. Ouerhani, Rozenn Dahyot, Nuria Pazos","doi":"10.1145/3403572","DOIUrl":"https://doi.org/10.1145/3403572","url":null,"abstract":"Next generation of embedded Information and Communication Technology (ICT) systems are interconnected and collaborative systems able to perform autonomous tasks. The remarkable expansion of the embedded ICT market, together with the rise and breakthroughs of Artificial Intelligence (AI), have put the focus on the Edge as it stands as one of the keys for the next technological revolution: the seamless integration of AI in our daily life. However, training and deployment of custom AI solutions on embedded devices require a fine-grained integration of data, algorithms, and tools to achieve high accuracy and overcome functional and non-functional requirements. Such integration requires a high level of expertise that becomes a real bottleneck for small and medium enterprises wanting to deploy AI solutions on the Edge, which, ultimately, slows down the adoption of AI on applications in our daily life. In this work, we present a modular AI pipeline as an integrating framework to bring data, algorithms, and deployment tools together. By removing the integration barriers and lowering the required expertise, we can interconnect the different stages of particular tools and provide a modular end-to-end development of AI products for embedded devices. Our AI pipeline consists of four modular main steps: (i) data ingestion, (ii) model training, (iii) deployment optimization, and (iv) the IoT hub integration. To show the effectiveness of our pipeline, we provide examples of different AI applications during each of the steps. Besides, we integrate our deployment framework, Low-Power Deep Neural Network (LPDNN), into the AI pipeline and present its lightweight architecture and deployment capabilities for embedded devices. Finally, we demonstrate the results of the AI pipeline by showing the deployment of several AI applications such as keyword spotting, image classification, and object detection on a set of well-known embedded platforms, where LPDNN consistently outperforms all other popular deployment frameworks.","PeriodicalId":29764,"journal":{"name":"ACM Transactions on Internet of Things","volume":"23 1","pages":"1 - 25"},"PeriodicalIF":2.7,"publicationDate":"2019-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76689781","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：