{"title":"Proceedings of the 20th International Conference on Distributed Computing and Networking","authors":"","doi":"10.1145/3288599","DOIUrl":"https://doi.org/10.1145/3288599","url":null,"abstract":"","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122726005","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}
A cryptographic access control scheme enforces access control policy of the data owner on his encrypted data. Most widely used cryptographic access control mechanism is hierarchical access control. Set of users for which access of data is to be managed/controlled, is divided into disjoint partitions called "security classes" or simply "classes". A hierarchical key assignment scheme (HKAS) assigns encryption keys of the data items in such a way that a class can only access data intended for class(es) lower down in the hierarchy [1]. So, we say each class has "designated access" to data intended for class(es) lower in the hierarchy. Suppose a class Ci, not having designated access to another class Cj, wishes to temporarily have access to data intended for Cj for a finite duration of time and Cj agrees for the same. However, consider that Cj does not wish to share its designated access with Ci. That is, Cj wishes to allow Ci to access data intended directly for Cj but not the one intended for any of the classes to which Cj has designated access and Ci does not. This flexibility requirement has various practical applications. In health-care services for instance, it may be desired that patient's data accessible directly to a doctor is securely delegated to another doctor in another service center for a finite period of time for expert consultation. However, it may be desired that the two doctors do not share information of any other patient.
{"title":"Flexible cryptographic access control through proxy re-encryption between groups","authors":"Gaurav Pareek, B. Purushothama","doi":"10.1145/3288599.3299722","DOIUrl":"https://doi.org/10.1145/3288599.3299722","url":null,"abstract":"A cryptographic access control scheme enforces access control policy of the data owner on his encrypted data. Most widely used cryptographic access control mechanism is hierarchical access control. Set of users for which access of data is to be managed/controlled, is divided into disjoint partitions called \"security classes\" or simply \"classes\". A hierarchical key assignment scheme (HKAS) assigns encryption keys of the data items in such a way that a class can only access data intended for class(es) lower down in the hierarchy [1]. So, we say each class has \"designated access\" to data intended for class(es) lower in the hierarchy. Suppose a class Ci, not having designated access to another class Cj, wishes to temporarily have access to data intended for Cj for a finite duration of time and Cj agrees for the same. However, consider that Cj does not wish to share its designated access with Ci. That is, Cj wishes to allow Ci to access data intended directly for Cj but not the one intended for any of the classes to which Cj has designated access and Ci does not. This flexibility requirement has various practical applications. In health-care services for instance, it may be desired that patient's data accessible directly to a doctor is securely delegated to another doctor in another service center for a finite period of time for expert consultation. However, it may be desired that the two doctors do not share information of any other patient.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128311759","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}
Samaikya Valluripally, M. Raju, P. Calyam, M. Chisholm, Sai Swathi Sivarathri, A. Mosa, T. Joshi
The adoption of big data analytics in healthcare applications is overwhelming not only because of the huge volume of data being analyzed, but also because of the heterogeneity and sensitivity of the data. Effective and efficient analysis and visualization of secure patient health records are needed to e.g., find new trends in disease management, determining risk factors for diseases, and personalized medicine. In this paper, we propose a novel community cloud architecture to help clinicians and researchers to have easy/increased accessibility to data sets from multiple sources, while also ensuring security compliance of data providers is not compromised. Our cloud-based system design configuration with cloudlet principles ensures application performance has high-speed processing, and data analytics is sufficiently scalable while adhering to security standards (e.g., HIPAA, NIST). Through a case study, we show how our community cloud architecture can be implemented along with best practices in an ophthalmology case study which includes health big data (i.e., Health Facts database, I2B2, Millennium) hosted in a campus cloud infrastructure featuring virtual desktop thin-clients and relevant Data Classification Levels in storage.
{"title":"Community cloud architecture to improve use accessibility with security compliance in health big data applications","authors":"Samaikya Valluripally, M. Raju, P. Calyam, M. Chisholm, Sai Swathi Sivarathri, A. Mosa, T. Joshi","doi":"10.1145/3288599.3295594","DOIUrl":"https://doi.org/10.1145/3288599.3295594","url":null,"abstract":"The adoption of big data analytics in healthcare applications is overwhelming not only because of the huge volume of data being analyzed, but also because of the heterogeneity and sensitivity of the data. Effective and efficient analysis and visualization of secure patient health records are needed to e.g., find new trends in disease management, determining risk factors for diseases, and personalized medicine. In this paper, we propose a novel community cloud architecture to help clinicians and researchers to have easy/increased accessibility to data sets from multiple sources, while also ensuring security compliance of data providers is not compromised. Our cloud-based system design configuration with cloudlet principles ensures application performance has high-speed processing, and data analytics is sufficiently scalable while adhering to security standards (e.g., HIPAA, NIST). Through a case study, we show how our community cloud architecture can be implemented along with best practices in an ophthalmology case study which includes health big data (i.e., Health Facts database, I2B2, Millennium) hosted in a campus cloud infrastructure featuring virtual desktop thin-clients and relevant Data Classification Levels in storage.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"193 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116531730","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}
Major problem of IEEE 802.11 based Vehicular Ad-hoc Network (VANET) is traffic congestion. The traffic congestion occurs due to unnecessary bandwidth usages, high vehicle density, excess increase in transmission power and immediate topology changes in a vehicular ad-hoc network which leads to excessive packet loss and lowers the safety of the applications. Under such conditions, all the transmitted packets from the source may not be delivered to the destination. Vehicles unaware of the traffic congestion increase the difficulty of it by eventually joining it. Many congestion control techniques have been proposed, but still, the problem arises. In this paper, we propose Distributed α-Fair Transmit Power Adaptation Based Congestion Control in Vehicular Ad-hoc Network to discover and reduce traffic congestion using the transmit power control and optimum node selection for cooperative VANET in the framework of the utility function optimization. The proposed system has better performance as compared to DFAV, DV-CAST, and UV-CAST regarding packet reception probability, average packet delivery ratio, and average end-to-end packet delivery delay in Vehicular Ad-hoc Network (VANET).
{"title":"Distributed α-fair transmit power adaptation based congestion control in VANET","authors":"Chandrakant Navdeti, C. Giri, I. Banerjee","doi":"10.1145/3288599.3288606","DOIUrl":"https://doi.org/10.1145/3288599.3288606","url":null,"abstract":"Major problem of IEEE 802.11 based Vehicular Ad-hoc Network (VANET) is traffic congestion. The traffic congestion occurs due to unnecessary bandwidth usages, high vehicle density, excess increase in transmission power and immediate topology changes in a vehicular ad-hoc network which leads to excessive packet loss and lowers the safety of the applications. Under such conditions, all the transmitted packets from the source may not be delivered to the destination. Vehicles unaware of the traffic congestion increase the difficulty of it by eventually joining it. Many congestion control techniques have been proposed, but still, the problem arises. In this paper, we propose Distributed α-Fair Transmit Power Adaptation Based Congestion Control in Vehicular Ad-hoc Network to discover and reduce traffic congestion using the transmit power control and optimum node selection for cooperative VANET in the framework of the utility function optimization. The proposed system has better performance as compared to DFAV, DV-CAST, and UV-CAST regarding packet reception probability, average packet delivery ratio, and average end-to-end packet delivery delay in Vehicular Ad-hoc Network (VANET).","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122216130","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) paradigm integrates smart devices and sensors to build systems such as smart homes, healthcare etc. However, sensors are prone to several attacks from malicious insiders as well as outsiders. Thus to secure IoT based applications, providing anonymous communication and end to end data secrecy while preventing impersonation and preserving privacy of nodes are important concerns. The existing solutions on achieving anonymous communication or data secrecy, either cannot achieve complete anonymity or have large storage or communication overhead which is difficult to implement in resource-constrained sensor based IoT. So, in this work we propose an Improved Secure Directed Diffusion (ISDD) protocol targeting a low-overhead solution for all the said security goals. The ISDD uses pseudonyms to conceal the node's real identity thereby ensuring anonymous communication. It also uses bilinear pairing to derive shared keys which are then used to generate multiple encryption layers over the plaintext message. Thus ISDD achieves end to end data secrecy, privacy of nodes and also effectively prevents malicious adversaries from impersonating a legitimate node. Finally, through security analysis we establish the aforementioned claims while achieving additional features compared to other state-of-the-art competing schemes. We also compute different overheads which are compared with two existing schemes. Results show significant improvement of ISDD in communication and storage overhead over both the competing schemes at the cost of marginal higher computation while keeping energy consumption within an acceptable limit.
{"title":"End to end secure anonymous communication for secure directed diffusion in IoT","authors":"Jayasree Sengupta, S. Ruj, S. Bit","doi":"10.1145/3288599.3295577","DOIUrl":"https://doi.org/10.1145/3288599.3295577","url":null,"abstract":"The Internet of Things (IoT) paradigm integrates smart devices and sensors to build systems such as smart homes, healthcare etc. However, sensors are prone to several attacks from malicious insiders as well as outsiders. Thus to secure IoT based applications, providing anonymous communication and end to end data secrecy while preventing impersonation and preserving privacy of nodes are important concerns. The existing solutions on achieving anonymous communication or data secrecy, either cannot achieve complete anonymity or have large storage or communication overhead which is difficult to implement in resource-constrained sensor based IoT. So, in this work we propose an Improved Secure Directed Diffusion (ISDD) protocol targeting a low-overhead solution for all the said security goals. The ISDD uses pseudonyms to conceal the node's real identity thereby ensuring anonymous communication. It also uses bilinear pairing to derive shared keys which are then used to generate multiple encryption layers over the plaintext message. Thus ISDD achieves end to end data secrecy, privacy of nodes and also effectively prevents malicious adversaries from impersonating a legitimate node. Finally, through security analysis we establish the aforementioned claims while achieving additional features compared to other state-of-the-art competing schemes. We also compute different overheads which are compared with two existing schemes. Results show significant improvement of ISDD in communication and storage overhead over both the competing schemes at the cost of marginal higher computation while keeping energy consumption within an acceptable limit.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129496184","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}
Swapnoneel Roy, Faustina J. Anto Morais, Mehrdad Salimitari, M. Chatterjee
Protecting and securing data that reside at various hosts in the Internet has become more important than ever before because of the growing number of cyber attacks. Though there have been several studies related to denial of service and cache attacks, those studies are primarily based on simulations and investigations of attacks on real networks are still lacking. In this paper, we experimentally investigated the effects of cache attacks on blockchain based information-centric networks. We used the hyperledger fabric to implement the blockchains for small and medium-sized networks. We implemented cache attacks where the attacker target the cache with unpopular content, forcing the user to fetch the data from the web servers. We experimented with two different topologies (linear and mesh) and also considered two cache sizes at the nodes. Three cache replacement policies were used: Least Recently Used, Random, and First In First Out. The cache hit, time taken to get the data, and the number of hops to serve the request were obtained with real network traffic. On the hyperledger fabric framework, we implemented two types of requests and showed how the query delay, invoke delay, and update delay vary with time. Based on our results, we find that most of the information centric networks, including the ones based on blockchains, are vulnerable to cache attacks.
{"title":"Cache attacks on blockchain based information centric networks: an experimental evaluation","authors":"Swapnoneel Roy, Faustina J. Anto Morais, Mehrdad Salimitari, M. Chatterjee","doi":"10.1145/3288599.3288640","DOIUrl":"https://doi.org/10.1145/3288599.3288640","url":null,"abstract":"Protecting and securing data that reside at various hosts in the Internet has become more important than ever before because of the growing number of cyber attacks. Though there have been several studies related to denial of service and cache attacks, those studies are primarily based on simulations and investigations of attacks on real networks are still lacking. In this paper, we experimentally investigated the effects of cache attacks on blockchain based information-centric networks. We used the hyperledger fabric to implement the blockchains for small and medium-sized networks. We implemented cache attacks where the attacker target the cache with unpopular content, forcing the user to fetch the data from the web servers. We experimented with two different topologies (linear and mesh) and also considered two cache sizes at the nodes. Three cache replacement policies were used: Least Recently Used, Random, and First In First Out. The cache hit, time taken to get the data, and the number of hops to serve the request were obtained with real network traffic. On the hyperledger fabric framework, we implemented two types of requests and showed how the query delay, invoke delay, and update delay vary with time. Based on our results, we find that most of the information centric networks, including the ones based on blockchains, are vulnerable to cache attacks.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133858691","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}
Karthi Balasubramanian, B. Yamuna, P. Salija, K. Lingasubramanian, D. Mishra
In complex systems like 'Internet of Things' and 'Cyber Physical Systems', reliable communication is made possible by the use of error control codes like turbo codes. Such systems are vulnerable to attack by Trojans during the design or fabrication phases of IC manufacturing. This leads to a severe performance degradation of the entire system. This paper aims at analyzing the effect of a sign-bit-flipping Trojan on a turbo coded communication system. Simulations were carried out on a conventional iterative turbo decoder and the results point out that the Trojan affects the performance of the decoder at SNRs greater than -2 dB. This performance degradation is seen even with minimal activation of the Trojan and a finite error persists even at very high SNRs.
{"title":"Effect of sign-bit-flipping trojan on turbo coded communication systems","authors":"Karthi Balasubramanian, B. Yamuna, P. Salija, K. Lingasubramanian, D. Mishra","doi":"10.1145/3288599.3295586","DOIUrl":"https://doi.org/10.1145/3288599.3295586","url":null,"abstract":"In complex systems like 'Internet of Things' and 'Cyber Physical Systems', reliable communication is made possible by the use of error control codes like turbo codes. Such systems are vulnerable to attack by Trojans during the design or fabrication phases of IC manufacturing. This leads to a severe performance degradation of the entire system. This paper aims at analyzing the effect of a sign-bit-flipping Trojan on a turbo coded communication system. Simulations were carried out on a conventional iterative turbo decoder and the results point out that the Trojan affects the performance of the decoder at SNRs greater than -2 dB. This performance degradation is seen even with minimal activation of the Trojan and a finite error persists even at very high SNRs.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132567924","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 paper, we propose a general scheme, called Algorithm STIC, to compute spanning-tree-like data structures on arbitrary networks. STIC is self-stabilizing and silent and, despite its generality, is also efficient. It is written in the locally shared memory model with composite atomicity assuming the distributed unfair daemon, the weakest scheduling assumption of the model. Its stabilization time is in O(nmaxCC) rounds, where nmaxCC is the maximum number of processes in a connected component. We also exhibit polynomial upper bounds on its stabilization time in steps and process moves holding for large classes of instantiations of Algorithm STIC. We illustrate the versatility of our approach by proposing several such instantiations that efficiently solve classical problems such as leader election, as well as, unconstrained and shortest-path spanning tree constructions.
{"title":"Silent self-stabilizing scheme for spanning-tree-like constructions","authors":"Stéphane Devismes, D. Ilcinkas, C. Johnen","doi":"10.1145/3288599.3288607","DOIUrl":"https://doi.org/10.1145/3288599.3288607","url":null,"abstract":"In this paper, we propose a general scheme, called Algorithm STIC, to compute spanning-tree-like data structures on arbitrary networks. STIC is self-stabilizing and silent and, despite its generality, is also efficient. It is written in the locally shared memory model with composite atomicity assuming the distributed unfair daemon, the weakest scheduling assumption of the model. Its stabilization time is in O(nmaxCC) rounds, where nmaxCC is the maximum number of processes in a connected component. We also exhibit polynomial upper bounds on its stabilization time in steps and process moves holding for large classes of instantiations of Algorithm STIC. We illustrate the versatility of our approach by proposing several such instantiations that efficiently solve classical problems such as leader election, as well as, unconstrained and shortest-path spanning tree constructions.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123765321","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}
Krishna Vijay Kumar Singh, Sakshi Gupta, Saurabh Verma, M. Pandey
This paper addresses the problem of non-optimal performance of Transmission Control Protocol (TCP) over Wi-Fi networks. TCP considers packet loss as a signal for congestion leading to reduced sending rate. This idea works well for the wired networks where majority of the packet losses are due to congestion. However, in wireless networks, packets are mostly lost because of transmission errors and mobility of the end hosts. Also, when packets are lost due to disassociation of the receiver from the network during mobility, sender remains idle for a significant period even after the receiver is re-associated. In this paper, we present the design and implementation of Software Defined Network (SDN) assisted TCP for wireless networks. In our approach, mobility induced packet losses are tackled smartly to avoid reduction in sending rate. Further, the data transfer starts immediately as soon as the receiver is re-associated to the network during mobility. Unlike existing solutions, our SDN assisted TCP does not violate the end-to-end semantics and no modification is required in the TCP protocol running at the end hosts. We have implemented and evaluated our approach using Mininet Wi-fi emulation platform. The results establish the applicability of our approach.
{"title":"Improving performance of TCP for wireless network using SDN","authors":"Krishna Vijay Kumar Singh, Sakshi Gupta, Saurabh Verma, M. Pandey","doi":"10.1145/3288599.3288626","DOIUrl":"https://doi.org/10.1145/3288599.3288626","url":null,"abstract":"This paper addresses the problem of non-optimal performance of Transmission Control Protocol (TCP) over Wi-Fi networks. TCP considers packet loss as a signal for congestion leading to reduced sending rate. This idea works well for the wired networks where majority of the packet losses are due to congestion. However, in wireless networks, packets are mostly lost because of transmission errors and mobility of the end hosts. Also, when packets are lost due to disassociation of the receiver from the network during mobility, sender remains idle for a significant period even after the receiver is re-associated. In this paper, we present the design and implementation of Software Defined Network (SDN) assisted TCP for wireless networks. In our approach, mobility induced packet losses are tackled smartly to avoid reduction in sending rate. Further, the data transfer starts immediately as soon as the receiver is re-associated to the network during mobility. Unlike existing solutions, our SDN assisted TCP does not violate the end-to-end semantics and no modification is required in the TCP protocol running at the end hosts. We have implemented and evaluated our approach using Mininet Wi-fi emulation platform. The results establish the applicability of our approach.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122219185","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}
Bowen Du, Chris Xiaoxuan Lu, Xuan Kan, Kai Wu, Man Luo, Jian Hou, K. Li, S. Kanhere, Yiran Shen, Hongkai Wen
Water has been widely acknowledged as an essential part of all living things. It is the fundamental necessity for all life's activities and most biochemical reactions in human body are executed in water. Therefore, the type and quantity of liquid intake everyday have a critical impact on individuals' health. In this paper, we demonstrate HydraDoctor, a real-time liquids intake monitoring system which is able to detect drinking activities, classify the categories of liquids and estimate the amount of intake. The system runs on multiple platforms including a smartwatch to detect the motion of hands and a smartglass to capture the images of mugs. A smartphone is also used as an edge computing platform and a remote server is designed for computationally intensive image processing. In HydraDoctor, multiple state-of-the-art machine learning techniques are applied: a Support Vector Machine (SVM)-based classifier is proposed to achieve accurate and efficient liquids intake monitoring, which is trained to detect the hand raising action. Both of them are well optimized to enable in-situ processing on smartwatch. To provide more robust and detailed monitoring, the smartglass is also incorporated and trigged to capture a short video clip in the front of the user when potential drinking activity is detected. The smartglass will send the video clip to the remote server via its companion smartphone and a Faster-RCNN is performed on the server to confirm the detected drinking activity and identify the type of intake liquid. According to our evaluation on the real-world experiments, HydraDoctor achieves very high accuracy both in drinking activity detection and types of liquids classification, whose accuracy is 85.64% and 84% respectively.
{"title":"HydraDoctor: real-time liquids intake monitoring by collaborative sensing","authors":"Bowen Du, Chris Xiaoxuan Lu, Xuan Kan, Kai Wu, Man Luo, Jian Hou, K. Li, S. Kanhere, Yiran Shen, Hongkai Wen","doi":"10.1145/3288599.3288635","DOIUrl":"https://doi.org/10.1145/3288599.3288635","url":null,"abstract":"Water has been widely acknowledged as an essential part of all living things. It is the fundamental necessity for all life's activities and most biochemical reactions in human body are executed in water. Therefore, the type and quantity of liquid intake everyday have a critical impact on individuals' health. In this paper, we demonstrate HydraDoctor, a real-time liquids intake monitoring system which is able to detect drinking activities, classify the categories of liquids and estimate the amount of intake. The system runs on multiple platforms including a smartwatch to detect the motion of hands and a smartglass to capture the images of mugs. A smartphone is also used as an edge computing platform and a remote server is designed for computationally intensive image processing. In HydraDoctor, multiple state-of-the-art machine learning techniques are applied: a Support Vector Machine (SVM)-based classifier is proposed to achieve accurate and efficient liquids intake monitoring, which is trained to detect the hand raising action. Both of them are well optimized to enable in-situ processing on smartwatch. To provide more robust and detailed monitoring, the smartglass is also incorporated and trigged to capture a short video clip in the front of the user when potential drinking activity is detected. The smartglass will send the video clip to the remote server via its companion smartphone and a Faster-RCNN is performed on the server to confirm the detected drinking activity and identify the type of intake liquid. According to our evaluation on the real-world experiments, HydraDoctor achieves very high accuracy both in drinking activity detection and types of liquids classification, whose accuracy is 85.64% and 84% respectively.","PeriodicalId":346177,"journal":{"name":"Proceedings of the 20th International Conference on Distributed Computing and Networking","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124066959","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：