Pub Date : 1900-01-01DOI: 10.1109/COMSNETS.2017.7945446
Romil Roy, Rajlakshmi Guha, S. D. Bhattacharya, J. Mukhopadhyay
College mental health is an area of significant importance. A number of stressors relating to career, relationships and life events collide during this life phase, when young adults learn to be autonomous. A major developmental task is making appropriate life choices in the face of freedom and contradictory messages from a wide range of sources. Thus identifying individuals in distress and building means to promote resilience would be relevant to any college setting. Resilience building has been a major area of concern to educators across the world. The main reason is that it is impossible to conduct face to face counselling on several occasions in a large college setting. This present study aims to build a web-based multi-step cognitive restructuring program to help young adults identify and deal with maladaptive, negative thoughts, and emotions, thereby effectively attempting to promote resilience, and improve psychological health among college students. Considering the sensitivity of the data present in the system, it has been developed following the multitier architecture with an intention to block access by unauthorized users. The system is meant to be interactive and regular feedback should be taken from the subjects. The counsellor should be given access to the full information of the subjects for evaluation. Additional tools for psychological assessment can be incorporated by the therapist into the system for an individual subject, if further evaluations are required. The system offers a generic platform for the development of other web-based interactive Computer Assisted Cognitive Behavioural Training programs addressing needs of specific populations.
{"title":"Building a web based cognitive restructuring program for promoting resilience in a college campus","authors":"Romil Roy, Rajlakshmi Guha, S. D. Bhattacharya, J. Mukhopadhyay","doi":"10.1109/COMSNETS.2017.7945446","DOIUrl":"https://doi.org/10.1109/COMSNETS.2017.7945446","url":null,"abstract":"College mental health is an area of significant importance. A number of stressors relating to career, relationships and life events collide during this life phase, when young adults learn to be autonomous. A major developmental task is making appropriate life choices in the face of freedom and contradictory messages from a wide range of sources. Thus identifying individuals in distress and building means to promote resilience would be relevant to any college setting. Resilience building has been a major area of concern to educators across the world. The main reason is that it is impossible to conduct face to face counselling on several occasions in a large college setting. This present study aims to build a web-based multi-step cognitive restructuring program to help young adults identify and deal with maladaptive, negative thoughts, and emotions, thereby effectively attempting to promote resilience, and improve psychological health among college students. Considering the sensitivity of the data present in the system, it has been developed following the multitier architecture with an intention to block access by unauthorized users. The system is meant to be interactive and regular feedback should be taken from the subjects. The counsellor should be given access to the full information of the subjects for evaluation. Additional tools for psychological assessment can be incorporated by the therapist into the system for an individual subject, if further evaluations are required. The system offers a generic platform for the development of other web-based interactive Computer Assisted Cognitive Behavioural Training programs addressing needs of specific populations.","PeriodicalId":168357,"journal":{"name":"2017 9th International Conference on Communication Systems and Networks (COMSNETS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131385400","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}
Pub Date : 1900-01-01DOI: 10.1109/COMSNETS.2017.7945352
Jayashree Mohan, Angad Vittal, K. Chandrasekaran, B. Krishnamachari
Dedicated Short Range Communication is attracting a lot of interest these days due to its utility in vehicular safety applications, intelligent transportation system and infotainment applications. Such vehicular networks are characterized by the highly dynamic changes in topology, no significant power constraints and ephemeral links. Considering an interaction between the client and server nodes that last for a random duration of time, an important question is to maximize the amount of useful content downloaded by the client, either in a single request phase, or iteratively in multiple phases. The aim of this work is to propose and investigate a multiphase request model using Markov Decision Process and compare its efficiency against a single phase version. We show that a multiphase request protocol performs better than single phase protocol.
{"title":"A reinforcement learning approach to optimize downloads over mobile networks","authors":"Jayashree Mohan, Angad Vittal, K. Chandrasekaran, B. Krishnamachari","doi":"10.1109/COMSNETS.2017.7945352","DOIUrl":"https://doi.org/10.1109/COMSNETS.2017.7945352","url":null,"abstract":"Dedicated Short Range Communication is attracting a lot of interest these days due to its utility in vehicular safety applications, intelligent transportation system and infotainment applications. Such vehicular networks are characterized by the highly dynamic changes in topology, no significant power constraints and ephemeral links. Considering an interaction between the client and server nodes that last for a random duration of time, an important question is to maximize the amount of useful content downloaded by the client, either in a single request phase, or iteratively in multiple phases. The aim of this work is to propose and investigate a multiphase request model using Markov Decision Process and compare its efficiency against a single phase version. We show that a multiphase request protocol performs better than single phase protocol.","PeriodicalId":168357,"journal":{"name":"2017 9th International Conference on Communication Systems and Networks (COMSNETS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130897172","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}
Pub Date : 1900-01-01DOI: 10.1109/COMSNETS.2017.7945414
Dr. Mahadev A. Gawas, L. Gudino, K. Anupama
Cooperative communication in VANET has become the de-facto in enabling technology to improve safety and efficiency on inter-vehicle communication (IVC). The safety related messages broadcast on emergency must have a minimum delay and high reliability. This paper proposes a cross-layer approach to efficiently broadcast the safety messages by minimizing the message redundancy and maintaining low end-to-end communication delays. We propose a scheme to select a one-hop neighbor relay as a potential forwarder for relaying the broadcast messages to improve the transmission reliability in a platoon of vehicles. The relay selection metrics compose of vehicular density, velocity, and the geographical location. The selected relay controls the broadcast messages with minimum overhead and with minimum bandwidth consumption. Similarly, a multimedia emergency message needs high priority with a shorter transmission delay. To provide the service differentiation to different traffic classes, we adopt 802.11e MAC. The cross layer is further extended to the transport layer to dynamically adapt the data transmission rate based on the physical channel state. The extensive simulation analysis conducted reveals that the proposed cross-layer scheme effectively propagates the critical broadcast messages with lesser packet latency and higher packet delivery ratio.
{"title":"Cross layer approach for effective multi hop broadcast in VANET","authors":"Dr. Mahadev A. Gawas, L. Gudino, K. Anupama","doi":"10.1109/COMSNETS.2017.7945414","DOIUrl":"https://doi.org/10.1109/COMSNETS.2017.7945414","url":null,"abstract":"Cooperative communication in VANET has become the de-facto in enabling technology to improve safety and efficiency on inter-vehicle communication (IVC). The safety related messages broadcast on emergency must have a minimum delay and high reliability. This paper proposes a cross-layer approach to efficiently broadcast the safety messages by minimizing the message redundancy and maintaining low end-to-end communication delays. We propose a scheme to select a one-hop neighbor relay as a potential forwarder for relaying the broadcast messages to improve the transmission reliability in a platoon of vehicles. The relay selection metrics compose of vehicular density, velocity, and the geographical location. The selected relay controls the broadcast messages with minimum overhead and with minimum bandwidth consumption. Similarly, a multimedia emergency message needs high priority with a shorter transmission delay. To provide the service differentiation to different traffic classes, we adopt 802.11e MAC. The cross layer is further extended to the transport layer to dynamically adapt the data transmission rate based on the physical channel state. The extensive simulation analysis conducted reveals that the proposed cross-layer scheme effectively propagates the critical broadcast messages with lesser packet latency and higher packet delivery ratio.","PeriodicalId":168357,"journal":{"name":"2017 9th International Conference on Communication Systems and Networks (COMSNETS)","volume":"17 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132546584","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}
Pub Date : 1900-01-01DOI: 10.1109/COMSNETS.2017.7945419
K. Kumar, Shibu Manuel, Deepu Benson
Identifying influential nodes in complex networks has attracted much attention because of its great theoretical significance and wide application. The m-Ranking method takes into account degree of all nodes and weight of all edges to rank nodes of the network with different weight. This ranking method can be used for unweighted networks also by fixing the value of the parameter α = 1. In addition, we demonstrate our new method on a real air traffic network and show that the ranks calculated using the new method is more meaningful compared with other methods.
{"title":"The m-Ranking of nodes in complex networks","authors":"K. Kumar, Shibu Manuel, Deepu Benson","doi":"10.1109/COMSNETS.2017.7945419","DOIUrl":"https://doi.org/10.1109/COMSNETS.2017.7945419","url":null,"abstract":"Identifying influential nodes in complex networks has attracted much attention because of its great theoretical significance and wide application. The m-Ranking method takes into account degree of all nodes and weight of all edges to rank nodes of the network with different weight. This ranking method can be used for unweighted networks also by fixing the value of the parameter α = 1. In addition, we demonstrate our new method on a real air traffic network and show that the ranks calculated using the new method is more meaningful compared with other methods.","PeriodicalId":168357,"journal":{"name":"2017 9th International Conference on Communication Systems and Networks (COMSNETS)","volume":"10 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133086661","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}
Pub Date : 1900-01-01DOI: 10.1109/COMSNETS.2017.7945425
M. Gandhi, Himashri Kour, D. Tandur, Rahul N. Gore, A. Varghese
A smart factory requires an efficient interaction between a number of physical components on the factory floor with the respective analytical and decision making components from digital domain. The flow of this information has to be continuous in order to reduce the downtime and maintain the productivity target. A smart factory should provide immediate access to the status of processes and device components to the relevant factory operators. With advancement in the concept of internet of things (IoT), many industrial devices on the factory floor now have wireless connectivity. Bluetooth technology is increasingly being used in order to provide operational and productivity status of devices to the factory floor operator. The operator typically has a smart device such as a tablet from where the respective devices can be monitored or controlled. As Bluetooth has a limited range, typically around 5–10 meters, an operator needs to come within this range of the device in order to connect with the respective industrial device and obtain its health and operational status data. Also Bluetooth mainly provides a point-to-point connectivity, thus at a time only one industrial device can be connected. For a factory floor that can have hundreds and thousands of such devices, this task of personally going and obtaining the data from every individual device could be tedious and cumbersome.
{"title":"Bluetooth IoT infrastructure network with immersive experience","authors":"M. Gandhi, Himashri Kour, D. Tandur, Rahul N. Gore, A. Varghese","doi":"10.1109/COMSNETS.2017.7945425","DOIUrl":"https://doi.org/10.1109/COMSNETS.2017.7945425","url":null,"abstract":"A smart factory requires an efficient interaction between a number of physical components on the factory floor with the respective analytical and decision making components from digital domain. The flow of this information has to be continuous in order to reduce the downtime and maintain the productivity target. A smart factory should provide immediate access to the status of processes and device components to the relevant factory operators. With advancement in the concept of internet of things (IoT), many industrial devices on the factory floor now have wireless connectivity. Bluetooth technology is increasingly being used in order to provide operational and productivity status of devices to the factory floor operator. The operator typically has a smart device such as a tablet from where the respective devices can be monitored or controlled. As Bluetooth has a limited range, typically around 5–10 meters, an operator needs to come within this range of the device in order to connect with the respective industrial device and obtain its health and operational status data. Also Bluetooth mainly provides a point-to-point connectivity, thus at a time only one industrial device can be connected. For a factory floor that can have hundreds and thousands of such devices, this task of personally going and obtaining the data from every individual device could be tedious and cumbersome.","PeriodicalId":168357,"journal":{"name":"2017 9th International Conference on Communication Systems and Networks (COMSNETS)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126932691","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}
Pub Date : 1900-01-01DOI: 10.1109/COMSNETS.2017.7945412
Surender Redhu, R. Hegde
Detection of landmarks in mobile sink environment which is generally used to improve the network lifetime is an important problem in WSN. In this paper, a method is proposed to trace the landmarks in a network leading to energy-efficient networks. The algorithm for clustering and landmarks tracing proposed herein uses the concept of random walks on graphs. The proposed method comprises of two phases namely, flow escalation and flow control and it does not require location information of the nodes. Additionally, prior information about number of optimal clusters is also not required. Experimental simulations illustrate the process of landmark detection along with clustering. Results obtained from analysis of WSN lifetime and number of data packets transmitted are motivating.
{"title":"Energy-efficient landmark tracing in WSNs using random walks on network graphs","authors":"Surender Redhu, R. Hegde","doi":"10.1109/COMSNETS.2017.7945412","DOIUrl":"https://doi.org/10.1109/COMSNETS.2017.7945412","url":null,"abstract":"Detection of landmarks in mobile sink environment which is generally used to improve the network lifetime is an important problem in WSN. In this paper, a method is proposed to trace the landmarks in a network leading to energy-efficient networks. The algorithm for clustering and landmarks tracing proposed herein uses the concept of random walks on graphs. The proposed method comprises of two phases namely, flow escalation and flow control and it does not require location information of the nodes. Additionally, prior information about number of optimal clusters is also not required. Experimental simulations illustrate the process of landmark detection along with clustering. Results obtained from analysis of WSN lifetime and number of data packets transmitted are motivating.","PeriodicalId":168357,"journal":{"name":"2017 9th International Conference on Communication Systems and Networks (COMSNETS)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116381266","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}
Pub Date : 1900-01-01DOI: 10.1109/COMSNETS.2017.7945442
Vivek B. Borse, A. S. Patil, R. Srivastava
PorFloR™ is a point-of-care portable fluorescence reader. It is a small handheld device that records the intensity of fluorescence spot and change in fluorescence intensity of the spot on the solid 2D base (e.g. paper strips) material. Nowadays, numerous fluorescence based lateral flow immunoassay (LFIA) techniques are utilized for the detection of various disease biomarkers. Most of the techniques depend on visible colorimetric detection process. Results obtained from such techniques are qualitative or semi-quantitative. Thus, we have developed the portable, easy-to-use, low cost, point-of-care strip reader that can detect the appearance as well as change in fluorescence intensity on the surface with quantitative precision. The output from device can be programmed to display the presence as well as concentration of an analyte.
{"title":"Development and testing of portable fluorescence reader (PorFloR™)","authors":"Vivek B. Borse, A. S. Patil, R. Srivastava","doi":"10.1109/COMSNETS.2017.7945442","DOIUrl":"https://doi.org/10.1109/COMSNETS.2017.7945442","url":null,"abstract":"PorFloR™ is a point-of-care portable fluorescence reader. It is a small handheld device that records the intensity of fluorescence spot and change in fluorescence intensity of the spot on the solid 2D base (e.g. paper strips) material. Nowadays, numerous fluorescence based lateral flow immunoassay (LFIA) techniques are utilized for the detection of various disease biomarkers. Most of the techniques depend on visible colorimetric detection process. Results obtained from such techniques are qualitative or semi-quantitative. Thus, we have developed the portable, easy-to-use, low cost, point-of-care strip reader that can detect the appearance as well as change in fluorescence intensity on the surface with quantitative precision. The output from device can be programmed to display the presence as well as concentration of an analyte.","PeriodicalId":168357,"journal":{"name":"2017 9th International Conference on Communication Systems and Networks (COMSNETS)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114525478","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}
Pub Date : 1900-01-01DOI: 10.1109/COMSNETS.2017.7945354
Bharadwaj Satchidanandan, P. Kumar
We address the problem of security of cyber-physical systems where some sensors may be malicious. We consider a multiple-input, multiple-output stochastic linear dynamical system controlled over a network of communication and computational nodes which contains (i) a controller that computes the inputs to be applied to the physical plant, (ii) actuators that apply these inputs to the plant, and (iii) sensors which measure the outputs of the plant. Some of these sensors, however, may be malicious. The malicious sensors do not report the true measurements to the controller. Rather, they report false measurements that they fabricate, possibly strategically, so as to achieve any objective that they may have, such as destabilizing the closed-loop system or increasing its running cost. Recently, it was shown that under certain conditions, an approach of “dynamic watermarking” can secure such a stochastic linear dynamical system in the sense that either the presence of malicious sensors in the system is detected, or the malicious sensors are constrained to adding a distortion that can only be of zero power to the noise already entering the system. The first contribution of this paper is to generalize this result to partially observed MIMO systems with both process and observation noises, a model which encompasses some of the previous models for which dynamic watermarking was established to guarantee security. This result, similar to the prior ones, is shown to hold when the controller subjects the reported sequence of measurements to two particular tests of veracity. The second contribution of this paper is in showing, via counterexamples, that both of these tests are needed in order to secure the control system in the sense that if any one of these two tests of sensor veracity is dropped, then the above guarantee does not hold. The proposed approach has several potential applications, including in smart grids, automated transportation, and process control.
{"title":"On minimal tests of sensor veracity for dynamic watermarking-based defense of cyber-physical systems","authors":"Bharadwaj Satchidanandan, P. Kumar","doi":"10.1109/COMSNETS.2017.7945354","DOIUrl":"https://doi.org/10.1109/COMSNETS.2017.7945354","url":null,"abstract":"We address the problem of security of cyber-physical systems where some sensors may be malicious. We consider a multiple-input, multiple-output stochastic linear dynamical system controlled over a network of communication and computational nodes which contains (i) a controller that computes the inputs to be applied to the physical plant, (ii) actuators that apply these inputs to the plant, and (iii) sensors which measure the outputs of the plant. Some of these sensors, however, may be malicious. The malicious sensors do not report the true measurements to the controller. Rather, they report false measurements that they fabricate, possibly strategically, so as to achieve any objective that they may have, such as destabilizing the closed-loop system or increasing its running cost. Recently, it was shown that under certain conditions, an approach of “dynamic watermarking” can secure such a stochastic linear dynamical system in the sense that either the presence of malicious sensors in the system is detected, or the malicious sensors are constrained to adding a distortion that can only be of zero power to the noise already entering the system. The first contribution of this paper is to generalize this result to partially observed MIMO systems with both process and observation noises, a model which encompasses some of the previous models for which dynamic watermarking was established to guarantee security. This result, similar to the prior ones, is shown to hold when the controller subjects the reported sequence of measurements to two particular tests of veracity. The second contribution of this paper is in showing, via counterexamples, that both of these tests are needed in order to secure the control system in the sense that if any one of these two tests of sensor veracity is dropped, then the above guarantee does not hold. The proposed approach has several potential applications, including in smart grids, automated transportation, and process control.","PeriodicalId":168357,"journal":{"name":"2017 9th International Conference on Communication Systems and Networks (COMSNETS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129819030","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}
Pub Date : 1900-01-01DOI: 10.1109/COMSNETS.2017.7945432
Munshi Yusuf Alam, S. Saurav, Ratna Mandal, Sujoy Saha, S. Nandi, Sandip Chakraborty
Rash driving is one of the primary reasons for road fatalities. However, the existing literature seldom talks about precise quantitative measures to assess behaviors like rash driving during traffic analytics. Moreover, the subjective factors like broken road patches, high peak bumps (or some time known as speed breakers in some countries), poor night illumination etc. have not been taken into consideration in the existing driver rating systems. This paper develops a methodology for fair and effective driver rating using a dynamic time warp (DTW) method, based on their behavioral observations as captured by smartphone sensors (GPS, accelerometer, light sensor etc.). The value of the correlation coefficient between the system rating and a manual rating is found to be more than 70% for our proposed system, SafeDrive, when tested extensively for bumps along a 7km city road patch. The system can be extended to provide a comprehensive driving score by including other road features like pot holes, sharp turns etc., in addition to bumps.
{"title":"A fair and effective driver rating system for developing regions","authors":"Munshi Yusuf Alam, S. Saurav, Ratna Mandal, Sujoy Saha, S. Nandi, Sandip Chakraborty","doi":"10.1109/COMSNETS.2017.7945432","DOIUrl":"https://doi.org/10.1109/COMSNETS.2017.7945432","url":null,"abstract":"Rash driving is one of the primary reasons for road fatalities. However, the existing literature seldom talks about precise quantitative measures to assess behaviors like rash driving during traffic analytics. Moreover, the subjective factors like broken road patches, high peak bumps (or some time known as speed breakers in some countries), poor night illumination etc. have not been taken into consideration in the existing driver rating systems. This paper develops a methodology for fair and effective driver rating using a dynamic time warp (DTW) method, based on their behavioral observations as captured by smartphone sensors (GPS, accelerometer, light sensor etc.). The value of the correlation coefficient between the system rating and a manual rating is found to be more than 70% for our proposed system, SafeDrive, when tested extensively for bumps along a 7km city road patch. The system can be extended to provide a comprehensive driving score by including other road features like pot holes, sharp turns etc., in addition to bumps.","PeriodicalId":168357,"journal":{"name":"2017 9th International Conference on Communication Systems and Networks (COMSNETS)","volume":"07 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129726000","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}
Pub Date : 1900-01-01DOI: 10.1109/COMSNETS.2017.7945453
Haritabh Gupta, S. Sural, Niloy Ganguly, Jaideep Vaidya
The goal of this paper is to study how friendship clusters evolve in online social networks. Results obtained from our work on Facebook data indicate that the set of friends who actively interact during a particular time interval is only a fraction of the total number of listed friends and this set of active friends tends to evolve with time. Interaction footprints on the timeline are used to cluster such active friends. Since there is a temporal variation in these clusters, it is modeled as a graph, wherein nodes represent cluster memberships and edge weights represent the number of common members between a pair of nodes. Novel methodologies for predicting the size and membership of the next active cluster based on the features extracted from past interaction of a user are introduced and their performance evaluated.
{"title":"Friends are forever? Evolution of active friendship clusters in online social networks","authors":"Haritabh Gupta, S. Sural, Niloy Ganguly, Jaideep Vaidya","doi":"10.1109/COMSNETS.2017.7945453","DOIUrl":"https://doi.org/10.1109/COMSNETS.2017.7945453","url":null,"abstract":"The goal of this paper is to study how friendship clusters evolve in online social networks. Results obtained from our work on Facebook data indicate that the set of friends who actively interact during a particular time interval is only a fraction of the total number of listed friends and this set of active friends tends to evolve with time. Interaction footprints on the timeline are used to cluster such active friends. Since there is a temporal variation in these clusters, it is modeled as a graph, wherein nodes represent cluster memberships and edge weights represent the number of common members between a pair of nodes. Novel methodologies for predicting the size and membership of the next active cluster based on the features extracted from past interaction of a user are introduced and their performance evaluated.","PeriodicalId":168357,"journal":{"name":"2017 9th International Conference on Communication Systems and Networks (COMSNETS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125627312","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：