Sanjay Madria - Academia.edu (original) (raw)

Papers by Sanjay Madria

Research paper thumbnail of Demo-Abstract: A DTN System for Tracking Miners using GAE-LSTM and Contact Graph Routing in an Underground Mine

Proceedings of the Int'l ACM Symposium on Mobility Management and Wireless Access

Research paper thumbnail of Information fusion architecture for secure cyber physical systems

Computers & Security, Aug 1, 2019

Research paper thumbnail of Resource Management in Cloud-Assisted Cyber-Physical Systems

Cambridge University Press eBooks, Oct 15, 2020

Research paper thumbnail of QoS guaranteeing robust scheduling in attack resilient cloud integrated cyber physical system

Future Generation Computer Systems, Oct 1, 2017

Research paper thumbnail of Information Fusion Architecture for Variable-Load Scheduling in a Cloud-Assisted CPS

This paper addresses the problem of devising an effective information fusion architecture for a t... more This paper addresses the problem of devising an effective information fusion architecture for a task scheduling algorithm which facilitates data processing of a Cyber Physical System (CPS) under bounded latency for bursty or lossy traffic. Task scheduling traditionally caters to real-time systems where a feedback loop does not exist allowing the serviced application to be independent of the inputs from the server. However, owing to the nature of a near real-time CPS, such liberties cannot be entertained. Additionally, the advent of big data in CPS has necessitated the use of Cloud Computing as a scalable and cost effective alternative. Task scheduling in such CPSs, where inputs from the Cloud complete the feedback loop is a major research issue. Therefore, in this paper, we propose a multi-layered information fusion architecture which integrates such a task scheduling mechanism by accommodating both traffic bursts and packet losses. Our scheduling algorithm ensures that the overall latency always remains under an acceptable upper bound as required by the CPS application.

Research paper thumbnail of Proceedings of the Third international conference on Distributed Computing and Internet Technology

Research paper thumbnail of BLAME: A Blockchain-assisted Misbehavior Detection and Event Validation in VANETs

2021 22nd IEEE International Conference on Mobile Data Management (MDM), 2021

The vehicular ad-hoc networks (VANETs) are considered a key mechanism for the collection and diss... more The vehicular ad-hoc networks (VANETs) are considered a key mechanism for the collection and dissemination of basic safety messages (BSM) in the modern transportation system. However, the presence of compromised or malicious vehicles within the network can disrupt the security of the information and the safety of the passengers. The emergence of a blockchain-based distributed framework in VANETs ensures transparency and security within the network without the assist of a trusted centralized entity. Nonetheless, the presence of the majority of malicious vehicles within the region of interest (ROI) can still bypass the security provided by the state-of-the-art blockchain-based frameworks. In this paper, we propose a Blockchain-assisted Misbehavior Detection and Event Validation (BLAME) framework that can effectively detect the valid traffic events and the malicious vehicles from the ROI by leveraging the neighbor information and the event recorded by the individual vehicles even if they are in majority. The efficacy of BLAME has been validated through simulations in VENTOS simulators and a simulated blockchain environment by extensively addressing different use case scenarios.

Research paper thumbnail of Distributed Computing and Internet Technology: Third International Conference, ICDCIT 2006, Bhubaneswar, India, December 20-23, 2006 (Lecture Notes in Computer Science)

The Role of Programming Languages in Future Data-Centric and Net-Centric Applications.- The Role ... more The Role of Programming Languages in Future Data-Centric and Net-Centric Applications.- The Role of Programming Languages in Future Data-Centric and Net-Centric Applications.- Wireless Sensor Network I - Routing and Power Control.- Net-Centric Computing: The Future of Computers and Networking.- Optimisation Problems Based on the Maximal Breach Path Measure for Wireless Sensor Network Coverage.- Energy-Aware Improved Directed Diffusion Algorithm for Area Event Monitoring in Wireless Sensor Network.- Distributed Node-Based Transmission Power Control for Wireless Ad Hoc Networks.- Wireless Sensor Network II - Localization and Coverage.- Ticket-Based Binding Update Protocol for Mobile IPv6.- Data Rate Adaptive Route Optimization for Sink Mobility Support in Wireless Sensor Networks.- Localization Control to Locate Mobile Sensors.- Static and Dynamic Allocation Algorithms in Mesh Structured Networks.- Mobile AdHoc Networks - Security and Reliability.- A Key Management Scheme with Encoding and Improved Security for Wireless Sensor Networks.- Key Inheritance-Based False Data Filtering Scheme in Wireless Sensor Networks.- Anonymous Agreed Order Multicast: Performance and Free Riding.- On Reliability Analysis of Forward Loop Forward Hop Networks.- Quality of Service I.- A Dynamic Paging Scheme for Minimizing Signaling Costs in Hierarchical Mobile IPv6 Networks.- QoS-Aware Routing Based on Local Information for Mobile Ad Hoc Networks.- Kalman Filter Based H.264 Motion Vector Recovery for Error Resilient Video Service over Mobile GRID.- Quality of Service II.- Throughput and Delay Analysis Considering Packet Arrival in IEEE 802.11.- A Routing Optimization Algorithm for BGP Egress Selection.- Enhanced OTIS k-Ary n-Cube Networks.- Multimedia Traffic Distribution Using Capacitated Multicast Tree.- Grid and Distributed Computing.- Application-Level Checkpointing Techniques for Parallel Programs.- A Generalized Linear Programming Based Approach to Optimal Divisible Load Scheduling.- Improving the Deployability of Existing Windows-Based Client/Server Business Information Systems Using ActiveX.- Web Services and E-Commerce.- An Automatic Approach to Displaying Web Applications as Portlets.- Allocating QOS-Constrained Applications in a Web Service-Oriented Grid.- Multicontext-Aware Recommendation for Ubiquitous Commerce.- An Improved E-Commerce Protocol for Fair Exchange.- Requirements-Driven Modeling of the Web Service Execution and Adaptation Lifecycle.- Modified Raymond's Algorithm for Priority (MRA-P) Based Mutual Exclusion in Distributed Systems.- Efficient Remote User Authentication and Key Establishment for Multi-server Environment.- Web Databases.- Materialized View Tuning Mechanism and Usability Enhancement.- Research into Verifying Semistructured Data.- An Empirical Study on a Web Server Queueing System and Traffic Generation by Simulation.- Dynamic Primary Copy with Piggy-Backing Mechanism for Replicated UDDI Registry.- Data Mining.- Mining Images of Material Nanostructure Data.- Mining Sequential Support Affinity Patterns with Weight Constraints.- Lossless Data Hiding for High Embedding Capacity.- Spatio-temporal Databases.- Extension of R-Tree for Spatio-temporal OLAP Operations.- Multimedia Data Hiding in Spatial and Transformed Domain.- Indexing and Retrieval of Document Images by Spatial Reasoning.

Research paper thumbnail of Efficient Data Collection in IoT Networks Using Trajectory Encoded With Geometric Shapes

IEEE Transactions on Sustainable Computing, 2021

The Mobile Edge Computing (MEC) mitigates the bandwidth limitation between the edge server and th... more The Mobile Edge Computing (MEC) mitigates the bandwidth limitation between the edge server and the remote cloud by directly processing the large amount of data locally generated by the network of the internet of things (IoT) at the edge. To reduce redundant data transmission, this paper proposes a data collection scheme that only gathers the necessary data from IoT devices along a trajectory. Instead of using and transmitting location information (to preserve location anonymity), a virtual coordinate system called distance vector of hops to anchors (DV-Hop) is used. The proposed trajectory encoding algorithm uses ellipse and hyperbola constraints to encode the position of interest (POI) and the trajectory route to the POI. Sensors make routing decisions only based on the geometric constraints and the DV-Hop information, both of which are stored in their memory. The proposed DV-Hop updating algorithm enables the users to collect data in an IoT network with mobile nodes. The experiments show that in heterogeneous IoT networks, the proposed data collection scheme outperforms two other state-of-the-art topology-based routing protocols, called ring routing, and nested ring. The results also show that the proposed scheme has better latency, reliability, coverage, energy usage, and provide location privacy compared to state-of-the-art-schemes

Research paper thumbnail of STIMULATE: A System for Real-time Information Acquisition and Learning for Disaster Management

2020 21st IEEE International Conference on Mobile Data Management (MDM), 2020

Real-time information sharing and propagation using social media such as Twitter has proven itsel... more Real-time information sharing and propagation using social media such as Twitter has proven itself as a potential resource to improve situational awareness in a timely manner for disaster management. Traditional disaster management systems work well for analyzing static and historical information. However, they cannot process dynamic streams of data that are being generated in real-time. This paper presents STIMULATE - a System for Real-time Information Acquisition and Learning for Disaster Management that can (1) fetch and process tweets in real-time, (2) classify those tweets into FEMA defined categories for rescue priorities using pre-trained deep learning models and generate useful insights, (3) find FEMA defined stranded people for rescue missions of varying priorities, and (4) provide an interactive web interface for rescue management given the available resources. The STIMULATE prototype is primarily built using the Python Flask framework for web interaction. Additionally, it is deployed in the cloud environment using Hadoop and MongoDB for scalable storage, and on-demand computing for processing extensive social media data. The deep learning models in the STIMULATE prototype use Python Keras and the TensorFlow library. We use Bi-directional Long Short-Term Memory (BLSTM) and Convolutional Neural Network (CNN) for developing the tweet classifier. Further, we use the Python PyWSGI WebSocket server for rescue scheduling operations. We present a deep learning system trained on hurricane Harvey and Irma datasets only. The tweet classifier is evaluated using 15 different disaster datasets. Finally, we present the results of multiple simulations using synthetic data with different sizes to measure the performance and effectiveness of the tweets processor and rescue scheduling algorithm.

Research paper thumbnail of Distributed Incentive-Based Secured Traffic Monitoring in VANETs

2020 21st IEEE International Conference on Mobile Data Management (MDM), 2020

Vehicular Ad-hoc Networks (VANETs) allow vehicles to share traffic-related events such as congest... more Vehicular Ad-hoc Networks (VANETs) allow vehicles to share traffic-related events such as congestion to improve the driver’s safety and comfort. However, due to the untrusted vehicular network environment, determining the credibility of broadcast messages becomes crucial and challenging. In this paper, we propose an incentive-based distributed trust management system with a secure event detection model employing the Byzantine fault-tolerant Paxos algorithm and game theory. The novelty of the proposed model lies in its ability to validate the accuracy of the broadcast information when the malicious vehicles form the majority compared to non-malicious vehicles within the ROI, unlike the state-of-the-art models. The proposed system’s feasibility and effectiveness have been validated using the VENTOS, SUMO, and Omnet++ simulators by comprehensively addressing all possible use-case scenarios, and under the influence of at least one non-malicious vehicle at each RSU.

Research paper thumbnail of Security Frameworks in Mobile Cloud Computing

Handbook of Computer Networks and Cyber Security, 2020

The concept of mobile cloud computing (MCC) combines mobile computing with cloud resources, and t... more The concept of mobile cloud computing (MCC) combines mobile computing with cloud resources, and therefore, has opened up new directions in the field of mobile computing. Cloud resources can help in overcoming the memory, energy, and other computing resource limitations of mobile devices. Thus, the mobile cloud computing applications can address some of the resource constraint issues by offloading tasks to cloud servers. Despite these advantages, mobile cloud computing is still not widely adopted due to various challenges associated with security in mobile cloud computing framework including issues of privacy, access control, service level agreements, interoperability, charging model, etc. In this chapter, we focus on the challenges associated with security in mobile cloud computing, and key features required in a security framework for MCC. Initially, we describe key architectures pertaining to various applications of mobile cloud computing, and later, we discuss few security frameworks proposed for MCC in terms of handling privacy, security, and attacks.

Research paper thumbnail of EMOCOV: Machine learning for emotion detection, analysis and visualization using COVID-19 tweets

Online Social Networks and Media, 2021

Research paper thumbnail of DistributedHART: A Distributed Real-Time Scheduling System for WirelessHART Networks

2019 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), 2019

Research paper thumbnail of Sensor Cloud: A Cloud of Sensor Networks

2016 IEEE International Conference on Cloud Engineering Workshop (IC2EW), 2016

Summary form only given. Traditional models of computing with wireless sensors imposes restrictio... more Summary form only given. Traditional models of computing with wireless sensors imposes restrictions on how efficiently wireless sensors can be used due to resource constraints. Newer models for interacting with wireless sensors such as the Internet of Things and Sensor Cloud aim to overcome these restrictions. This tutorial will discuss a sensor cloud architecture that enables different wireless sensor networks, spread in a huge geographical area to connect together and be used by multiple users at the same time in an 'on demand' basis. Virtual sensors will be shown to assist in creating a multi-user environment on top of resource constrained physical wireless sensors, and can help in supporting multiple applications in an on-demand basis. Security issues will be presented, along with an overview of some potential solutions to these problems such as: energy efficient privacy and data integrity preserving data aggregation algorithms, risk assessment in sensor clouds, and attribute-based access control for sensor cloud applications.

Research paper thumbnail of Structure and content semantic similarity detection of eXtensible markup language documents using keys

Research paper thumbnail of XML Similarity Detection and Measurements

Research paper thumbnail of Dynamic data replication schemes for mobile ad-hoc network based on aperiodic updates

Research paper thumbnail of Reputation and Credit Based Incentive Mechanism for Data-Centric Message Delivery in DTNs

2018 19th IEEE International Conference on Mobile Data Management (MDM)

In Delay Tolerant Networks (DTNs), to ensure successful message delivery, contribution of mobile ... more In Delay Tolerant Networks (DTNs), to ensure successful message delivery, contribution of mobile nodes in relaying in an opportunistic fashion is essential. In our proposed data-centric dissemination protocol here, messages (images) are annotated with keywords by the source, and then intermediate nodes are presented with an option of adding keyword-based annotations to create higher content strength messages enroute toward the destination. Therefore, the message contents like images get enriched as the ground situation evolves and learned by these intermediate nodes, such as in a disaster situation, or in a battlefield. Due to limited battery and storage capacity in mobile devices, nodes might turn selfish and do not participate in relaying or improving the quality of messages. Thus, additionally, an incentive mechanism is proposed in this paper which considers factors like message quality, level of interests, battery usage, etc for the calculation of incentives. At the same time, in order to prevent the nodes from turning malicious by adding inappropriate message tags in pursuit of acquiring more incentive, a distributed reputation model (DRM) is developed and integrated with the proposed incentive scheme. DRM takes into account inputs from the intermediate users like ratings of the message quality, relevance of annotations in the message, etc. The proposed scheme thus ensures avoidance of congestion due to uncooperative or selfish nodes in the system. The performance evaluations show that our approach delivers more high priority and quality messages with reduced traffic with a slightly lower message delivery ratio compared to a more recent DTN routing like ChitChat, where a source forwards a message to intermediate nodes, which meet or exceed the matching strength of keyword-based interests.

Research paper thumbnail of A Parallel Algorithm For Anonymizing Large-scale Trajectory Data

ACM/IMS Transactions on Data Science, 2020

With the proliferation of location-based services enabled by a large number of mobile devices and... more With the proliferation of location-based services enabled by a large number of mobile devices and applications, the quantity of location data, such as trajectories collected by service providers, is gigantic. If these datasets could be published, then they would be valuable assets to various service providers to explore business opportunities, to study commuter behavior for better transport management, which in turn benefits the general public for day-to-day commuting. However, there are two major concerns that considerably limit the availability and the usage of these trajectory datasets. The first is the threat to individual privacy, as users’ trajectories may be misused to discover sensitive information, such as home locations, their children’s school locations, or social information like habits or relationships. The other concern is the ability to analyze the exabytes of location data in a timely manner. Although there have been trajectory anonymization approaches proposed in th...

Research paper thumbnail of Demo-Abstract: A DTN System for Tracking Miners using GAE-LSTM and Contact Graph Routing in an Underground Mine

Proceedings of the Int'l ACM Symposium on Mobility Management and Wireless Access

Research paper thumbnail of Information fusion architecture for secure cyber physical systems

Computers & Security, Aug 1, 2019

Research paper thumbnail of Resource Management in Cloud-Assisted Cyber-Physical Systems

Cambridge University Press eBooks, Oct 15, 2020

Research paper thumbnail of QoS guaranteeing robust scheduling in attack resilient cloud integrated cyber physical system

Future Generation Computer Systems, Oct 1, 2017

Research paper thumbnail of Information Fusion Architecture for Variable-Load Scheduling in a Cloud-Assisted CPS

This paper addresses the problem of devising an effective information fusion architecture for a t... more This paper addresses the problem of devising an effective information fusion architecture for a task scheduling algorithm which facilitates data processing of a Cyber Physical System (CPS) under bounded latency for bursty or lossy traffic. Task scheduling traditionally caters to real-time systems where a feedback loop does not exist allowing the serviced application to be independent of the inputs from the server. However, owing to the nature of a near real-time CPS, such liberties cannot be entertained. Additionally, the advent of big data in CPS has necessitated the use of Cloud Computing as a scalable and cost effective alternative. Task scheduling in such CPSs, where inputs from the Cloud complete the feedback loop is a major research issue. Therefore, in this paper, we propose a multi-layered information fusion architecture which integrates such a task scheduling mechanism by accommodating both traffic bursts and packet losses. Our scheduling algorithm ensures that the overall latency always remains under an acceptable upper bound as required by the CPS application.

Research paper thumbnail of Proceedings of the Third international conference on Distributed Computing and Internet Technology

Research paper thumbnail of BLAME: A Blockchain-assisted Misbehavior Detection and Event Validation in VANETs

2021 22nd IEEE International Conference on Mobile Data Management (MDM), 2021

The vehicular ad-hoc networks (VANETs) are considered a key mechanism for the collection and diss... more The vehicular ad-hoc networks (VANETs) are considered a key mechanism for the collection and dissemination of basic safety messages (BSM) in the modern transportation system. However, the presence of compromised or malicious vehicles within the network can disrupt the security of the information and the safety of the passengers. The emergence of a blockchain-based distributed framework in VANETs ensures transparency and security within the network without the assist of a trusted centralized entity. Nonetheless, the presence of the majority of malicious vehicles within the region of interest (ROI) can still bypass the security provided by the state-of-the-art blockchain-based frameworks. In this paper, we propose a Blockchain-assisted Misbehavior Detection and Event Validation (BLAME) framework that can effectively detect the valid traffic events and the malicious vehicles from the ROI by leveraging the neighbor information and the event recorded by the individual vehicles even if they are in majority. The efficacy of BLAME has been validated through simulations in VENTOS simulators and a simulated blockchain environment by extensively addressing different use case scenarios.

Research paper thumbnail of Distributed Computing and Internet Technology: Third International Conference, ICDCIT 2006, Bhubaneswar, India, December 20-23, 2006 (Lecture Notes in Computer Science)

The Role of Programming Languages in Future Data-Centric and Net-Centric Applications.- The Role ... more The Role of Programming Languages in Future Data-Centric and Net-Centric Applications.- The Role of Programming Languages in Future Data-Centric and Net-Centric Applications.- Wireless Sensor Network I - Routing and Power Control.- Net-Centric Computing: The Future of Computers and Networking.- Optimisation Problems Based on the Maximal Breach Path Measure for Wireless Sensor Network Coverage.- Energy-Aware Improved Directed Diffusion Algorithm for Area Event Monitoring in Wireless Sensor Network.- Distributed Node-Based Transmission Power Control for Wireless Ad Hoc Networks.- Wireless Sensor Network II - Localization and Coverage.- Ticket-Based Binding Update Protocol for Mobile IPv6.- Data Rate Adaptive Route Optimization for Sink Mobility Support in Wireless Sensor Networks.- Localization Control to Locate Mobile Sensors.- Static and Dynamic Allocation Algorithms in Mesh Structured Networks.- Mobile AdHoc Networks - Security and Reliability.- A Key Management Scheme with Encoding and Improved Security for Wireless Sensor Networks.- Key Inheritance-Based False Data Filtering Scheme in Wireless Sensor Networks.- Anonymous Agreed Order Multicast: Performance and Free Riding.- On Reliability Analysis of Forward Loop Forward Hop Networks.- Quality of Service I.- A Dynamic Paging Scheme for Minimizing Signaling Costs in Hierarchical Mobile IPv6 Networks.- QoS-Aware Routing Based on Local Information for Mobile Ad Hoc Networks.- Kalman Filter Based H.264 Motion Vector Recovery for Error Resilient Video Service over Mobile GRID.- Quality of Service II.- Throughput and Delay Analysis Considering Packet Arrival in IEEE 802.11.- A Routing Optimization Algorithm for BGP Egress Selection.- Enhanced OTIS k-Ary n-Cube Networks.- Multimedia Traffic Distribution Using Capacitated Multicast Tree.- Grid and Distributed Computing.- Application-Level Checkpointing Techniques for Parallel Programs.- A Generalized Linear Programming Based Approach to Optimal Divisible Load Scheduling.- Improving the Deployability of Existing Windows-Based Client/Server Business Information Systems Using ActiveX.- Web Services and E-Commerce.- An Automatic Approach to Displaying Web Applications as Portlets.- Allocating QOS-Constrained Applications in a Web Service-Oriented Grid.- Multicontext-Aware Recommendation for Ubiquitous Commerce.- An Improved E-Commerce Protocol for Fair Exchange.- Requirements-Driven Modeling of the Web Service Execution and Adaptation Lifecycle.- Modified Raymond's Algorithm for Priority (MRA-P) Based Mutual Exclusion in Distributed Systems.- Efficient Remote User Authentication and Key Establishment for Multi-server Environment.- Web Databases.- Materialized View Tuning Mechanism and Usability Enhancement.- Research into Verifying Semistructured Data.- An Empirical Study on a Web Server Queueing System and Traffic Generation by Simulation.- Dynamic Primary Copy with Piggy-Backing Mechanism for Replicated UDDI Registry.- Data Mining.- Mining Images of Material Nanostructure Data.- Mining Sequential Support Affinity Patterns with Weight Constraints.- Lossless Data Hiding for High Embedding Capacity.- Spatio-temporal Databases.- Extension of R-Tree for Spatio-temporal OLAP Operations.- Multimedia Data Hiding in Spatial and Transformed Domain.- Indexing and Retrieval of Document Images by Spatial Reasoning.

Research paper thumbnail of Efficient Data Collection in IoT Networks Using Trajectory Encoded With Geometric Shapes

IEEE Transactions on Sustainable Computing, 2021

The Mobile Edge Computing (MEC) mitigates the bandwidth limitation between the edge server and th... more The Mobile Edge Computing (MEC) mitigates the bandwidth limitation between the edge server and the remote cloud by directly processing the large amount of data locally generated by the network of the internet of things (IoT) at the edge. To reduce redundant data transmission, this paper proposes a data collection scheme that only gathers the necessary data from IoT devices along a trajectory. Instead of using and transmitting location information (to preserve location anonymity), a virtual coordinate system called distance vector of hops to anchors (DV-Hop) is used. The proposed trajectory encoding algorithm uses ellipse and hyperbola constraints to encode the position of interest (POI) and the trajectory route to the POI. Sensors make routing decisions only based on the geometric constraints and the DV-Hop information, both of which are stored in their memory. The proposed DV-Hop updating algorithm enables the users to collect data in an IoT network with mobile nodes. The experiments show that in heterogeneous IoT networks, the proposed data collection scheme outperforms two other state-of-the-art topology-based routing protocols, called ring routing, and nested ring. The results also show that the proposed scheme has better latency, reliability, coverage, energy usage, and provide location privacy compared to state-of-the-art-schemes

Research paper thumbnail of STIMULATE: A System for Real-time Information Acquisition and Learning for Disaster Management

2020 21st IEEE International Conference on Mobile Data Management (MDM), 2020

Real-time information sharing and propagation using social media such as Twitter has proven itsel... more Real-time information sharing and propagation using social media such as Twitter has proven itself as a potential resource to improve situational awareness in a timely manner for disaster management. Traditional disaster management systems work well for analyzing static and historical information. However, they cannot process dynamic streams of data that are being generated in real-time. This paper presents STIMULATE - a System for Real-time Information Acquisition and Learning for Disaster Management that can (1) fetch and process tweets in real-time, (2) classify those tweets into FEMA defined categories for rescue priorities using pre-trained deep learning models and generate useful insights, (3) find FEMA defined stranded people for rescue missions of varying priorities, and (4) provide an interactive web interface for rescue management given the available resources. The STIMULATE prototype is primarily built using the Python Flask framework for web interaction. Additionally, it is deployed in the cloud environment using Hadoop and MongoDB for scalable storage, and on-demand computing for processing extensive social media data. The deep learning models in the STIMULATE prototype use Python Keras and the TensorFlow library. We use Bi-directional Long Short-Term Memory (BLSTM) and Convolutional Neural Network (CNN) for developing the tweet classifier. Further, we use the Python PyWSGI WebSocket server for rescue scheduling operations. We present a deep learning system trained on hurricane Harvey and Irma datasets only. The tweet classifier is evaluated using 15 different disaster datasets. Finally, we present the results of multiple simulations using synthetic data with different sizes to measure the performance and effectiveness of the tweets processor and rescue scheduling algorithm.

Research paper thumbnail of Distributed Incentive-Based Secured Traffic Monitoring in VANETs

2020 21st IEEE International Conference on Mobile Data Management (MDM), 2020

Vehicular Ad-hoc Networks (VANETs) allow vehicles to share traffic-related events such as congest... more Vehicular Ad-hoc Networks (VANETs) allow vehicles to share traffic-related events such as congestion to improve the driver’s safety and comfort. However, due to the untrusted vehicular network environment, determining the credibility of broadcast messages becomes crucial and challenging. In this paper, we propose an incentive-based distributed trust management system with a secure event detection model employing the Byzantine fault-tolerant Paxos algorithm and game theory. The novelty of the proposed model lies in its ability to validate the accuracy of the broadcast information when the malicious vehicles form the majority compared to non-malicious vehicles within the ROI, unlike the state-of-the-art models. The proposed system’s feasibility and effectiveness have been validated using the VENTOS, SUMO, and Omnet++ simulators by comprehensively addressing all possible use-case scenarios, and under the influence of at least one non-malicious vehicle at each RSU.

Research paper thumbnail of Security Frameworks in Mobile Cloud Computing

Handbook of Computer Networks and Cyber Security, 2020

The concept of mobile cloud computing (MCC) combines mobile computing with cloud resources, and t... more The concept of mobile cloud computing (MCC) combines mobile computing with cloud resources, and therefore, has opened up new directions in the field of mobile computing. Cloud resources can help in overcoming the memory, energy, and other computing resource limitations of mobile devices. Thus, the mobile cloud computing applications can address some of the resource constraint issues by offloading tasks to cloud servers. Despite these advantages, mobile cloud computing is still not widely adopted due to various challenges associated with security in mobile cloud computing framework including issues of privacy, access control, service level agreements, interoperability, charging model, etc. In this chapter, we focus on the challenges associated with security in mobile cloud computing, and key features required in a security framework for MCC. Initially, we describe key architectures pertaining to various applications of mobile cloud computing, and later, we discuss few security frameworks proposed for MCC in terms of handling privacy, security, and attacks.

Research paper thumbnail of EMOCOV: Machine learning for emotion detection, analysis and visualization using COVID-19 tweets

Online Social Networks and Media, 2021

Research paper thumbnail of DistributedHART: A Distributed Real-Time Scheduling System for WirelessHART Networks

2019 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), 2019

Research paper thumbnail of Sensor Cloud: A Cloud of Sensor Networks

2016 IEEE International Conference on Cloud Engineering Workshop (IC2EW), 2016

Summary form only given. Traditional models of computing with wireless sensors imposes restrictio... more Summary form only given. Traditional models of computing with wireless sensors imposes restrictions on how efficiently wireless sensors can be used due to resource constraints. Newer models for interacting with wireless sensors such as the Internet of Things and Sensor Cloud aim to overcome these restrictions. This tutorial will discuss a sensor cloud architecture that enables different wireless sensor networks, spread in a huge geographical area to connect together and be used by multiple users at the same time in an 'on demand' basis. Virtual sensors will be shown to assist in creating a multi-user environment on top of resource constrained physical wireless sensors, and can help in supporting multiple applications in an on-demand basis. Security issues will be presented, along with an overview of some potential solutions to these problems such as: energy efficient privacy and data integrity preserving data aggregation algorithms, risk assessment in sensor clouds, and attribute-based access control for sensor cloud applications.

Research paper thumbnail of Structure and content semantic similarity detection of eXtensible markup language documents using keys

Research paper thumbnail of XML Similarity Detection and Measurements

Research paper thumbnail of Dynamic data replication schemes for mobile ad-hoc network based on aperiodic updates

Research paper thumbnail of Reputation and Credit Based Incentive Mechanism for Data-Centric Message Delivery in DTNs

2018 19th IEEE International Conference on Mobile Data Management (MDM)

In Delay Tolerant Networks (DTNs), to ensure successful message delivery, contribution of mobile ... more In Delay Tolerant Networks (DTNs), to ensure successful message delivery, contribution of mobile nodes in relaying in an opportunistic fashion is essential. In our proposed data-centric dissemination protocol here, messages (images) are annotated with keywords by the source, and then intermediate nodes are presented with an option of adding keyword-based annotations to create higher content strength messages enroute toward the destination. Therefore, the message contents like images get enriched as the ground situation evolves and learned by these intermediate nodes, such as in a disaster situation, or in a battlefield. Due to limited battery and storage capacity in mobile devices, nodes might turn selfish and do not participate in relaying or improving the quality of messages. Thus, additionally, an incentive mechanism is proposed in this paper which considers factors like message quality, level of interests, battery usage, etc for the calculation of incentives. At the same time, in order to prevent the nodes from turning malicious by adding inappropriate message tags in pursuit of acquiring more incentive, a distributed reputation model (DRM) is developed and integrated with the proposed incentive scheme. DRM takes into account inputs from the intermediate users like ratings of the message quality, relevance of annotations in the message, etc. The proposed scheme thus ensures avoidance of congestion due to uncooperative or selfish nodes in the system. The performance evaluations show that our approach delivers more high priority and quality messages with reduced traffic with a slightly lower message delivery ratio compared to a more recent DTN routing like ChitChat, where a source forwards a message to intermediate nodes, which meet or exceed the matching strength of keyword-based interests.

Research paper thumbnail of A Parallel Algorithm For Anonymizing Large-scale Trajectory Data

ACM/IMS Transactions on Data Science, 2020

With the proliferation of location-based services enabled by a large number of mobile devices and... more With the proliferation of location-based services enabled by a large number of mobile devices and applications, the quantity of location data, such as trajectories collected by service providers, is gigantic. If these datasets could be published, then they would be valuable assets to various service providers to explore business opportunities, to study commuter behavior for better transport management, which in turn benefits the general public for day-to-day commuting. However, there are two major concerns that considerably limit the availability and the usage of these trajectory datasets. The first is the threat to individual privacy, as users’ trajectories may be misused to discover sensitive information, such as home locations, their children’s school locations, or social information like habits or relationships. The other concern is the ability to analyze the exabytes of location data in a timely manner. Although there have been trajectory anonymization approaches proposed in th...