Publications
For an updated list of publications please visit my Google Scholar link
Mobi-IoST: mobility-aware cloud-fog-edge-iot collaborative framework for time-critical applications,
Shreya Ghosh, Anwesha Mukherjee, Soumya K Ghosh, Rajkumar Buyya, IEEE Transactions on Network Science and Engineering, 2020
The design of mobility-aware framework for edge/fog computing for IoT systems with back-end cloud is gaining research interest. In this paper, a mobility-driven cloud-fog-edge collaborative real-time framework, Mobi-IoST, has been proposed, which has IoT, Edge, Fog and Cloud layers and exploits the mobility dynamics of the moving agent. The IoT and edge devices are considered to be the moving agents in a 2-D space, typically over the road-network. The framework analyses the spatio-temporal mobility data (GPS logs) along with the other contextual information and employs machine learning algorithm to predict the location of the moving agents (IoT and Edge devices) in real-time. The accumulated spatio-temporal traces from the moving agents are modelled using probabilistic graphical model. The major features of the proposed framework are: (i) hierarchical processing of the information using IoT-Edge-Fog-Cloud architecture to provide better QoS in real-time applications, (ii) uses mobility information for predicting next location of the agents to deliver processed information, and (iii) efficiently handles delay and power consumption. The performance evaluations yield that the proposed Mobi-IoST framework has approximately 93% accuracy and reduced the delay and power by approximately 23-26% and 37-41% respectively than the existing mobility-aware task delegation system.
MARIO: A spatio-temporal data mining framework on Google Cloud to explore mobility dynamics from taxi trajectories,
Shreya Ghosh, Soumya K Ghosh, Rajkumar Buyya, Journal of Network and Computer Applications, Elsvier, 2020
With the major advances in location acquisition techniques, deployment of GPS enabled devices and increasing number of mobile users, substantial amount of location traces are generated from different geographical regions. It provides unprecedented opportunities to analyze and derive valuable insights of urban dynamics, specifically, time-dependent mobility patterns and region-specific travel demands. This work proposes an end-to-end mobility association rule mining framework called MARIO, conducive to extract urban mobility dynamics through analysing large taxi trip traces of a city. The MARIO framework consists of (i) generating mobility-dynamics network by spatio-temporal analysis of taxi-trips, (ii) finding travel demand variations in different functional regions of the urban area, (iii) extracting mobility association rules and (iv) predicting travel demands and traffic dynamics using extracted associative rules. The proposed MARIO framework is implemented in Google Cloud Platform and an extensive set of experiments using real GPS trace dataset of NYC Green and Yellow Taxi trace, Roma Taxi Dataset and San Francisco Taxi Dataset have been carried out to demonstrate the effectiveness of the framework. The performance of the proposed approach is significantly better than the baseline methods in predicting travel demands (with the reduction of average MAPE value and execution time by 50%).
Exploring Mobility Behaviours of Moving Agents from Trajectory traces in Cloud-Fog-Edge Collaborative Framework,
Shreya Ghosh, Soumya K Ghosh, CCGrid 2020
Both analyzing mobility traces and understanding a user's movement semantics from mobile sensor data are challenging issues in ubiquitous computing systems. With the pervasiveness of sensor technologies, wireless networks and GPS-equipped devices, a huge volume of location information is being accumulated. Several techniques have been proposed to analyze the mobility traces and extract informative knowledge for varied location-aware applications. However, all of these applications necessitate an effective mobility-analysis framework to capture the movement behavior of individuals in minimum delay. This paper aims to develop a cloud-based mobility analytics framework to model peoples' mobility behaviour in varied granular scale and extract usable knowledge to provision location-aware services. The preliminary experimental results on real-life dataset depict the effectiveness of our proposed framework.
THUMP: Semantic Analysis on Trajectory Traces to Explore Human Movement Pattern,
Shreya Ghosh, Soumya K Ghosh, Poster Paper, WWW 2016
Exploring human movement pattern from raw GPS traces is an interesting and challenging task. This paper aims at analysing a large volume of GPS data in spatio- temporal context, clustering trajectories using geographic and semantic location information and identifying different categories of people. It tries to exploit the fact that human moves with an intent. The proposed framework yields encouraging results using a large scale GPS dataset of Microsoft GeoLife.
Modeling of Human Movement Behavioral Knowledge from GPS Traces for Categorizing Mobile Users
Shreya Ghosh, Soumya K Ghosh, Cognitive Computing Track, WWW 2017
Human movement analysis and categorization of mobile users based on their movement semantics are challenging tasks. Further, due to security and privacy issues, insufficient labelled or user-annotated data (or, ground-truth data) makes the user-classification from GPS traces more complex. In this work, we present a framework which models user movement patterns containing both spatio-temporal and semantic information, generates semantic stay-point taxonomy by analysing GPS traces of all users, summarizes individuals’ GPS traces and clusters users based on the semantics of their movement patterns. To alleviate labelled data scarcity problem while user categorization in a particular region of interest (ROI), we propose a method to transfer knowledge derived from a set of GPS traces of a geographically distanced but similar type of ROI. An extensive set of experiments using real GPS trace dataset of Kharagpur, India and Dartmouth, Hanover, USA have been carried out to demonstrate the effectiveness of our proposed framework.
Activity-Based Mobility Profiling: A Purely Temporal Modeling
Approach
Shreya Ghosh, Soumya K Ghosh, Rahul Deb Das and Stephan Winter, Cognitive Computing Track, WWW 2018
Several studies have shown that the spatio-temporal mobility traces of human movements can be used to identify an individual. However, this work presents a novel framework for activity-based mobility profiling of individuals using only the temporal information. The proposed framework is conducive to model individuals’ activity patterns in temporal scale, and quantifies the uniqueness measures based on certain temporal features of the activity sequence.
Exploring Human Movement Behaviour
Based on Mobility Association Rule
Mining of Trajectory Traces
Shreya Ghosh, Soumya K Ghosh, ISDA 2017
With the emergence of location sensing technologies AQ1 there is a growing interest to explore spatio-temporal GPS (Global Positioning System) traces collected from various moving agents (ex: mobile-users, GPS-equipped vehicles etc.) to facilitate location-aware applications. This paper, therefore focuses on finding meaningful patterns from spatio-temporal data (GPS log) of human movement history and measures the interestingness of the extracted patterns. An experimental evaluation on GPS data-set of an academic campus demonstrates the efficacy of the system and its potential to extract meaningful rules from real-life dataset.
A Machine Learning Approach to Find the
Optimal Routes through Analysis of GPS Traces of Mobile City Traffic
Shreya Ghosh, Abhisek Chowdhury and Soumya K Ghosh, ICACNI 2017
The rapid urbanization in developing countries has modernized people’s lives in various aspects but also triggered many challenges, namely increasing carbon footprints/pollution, traffic congestion, high energy consumption etc. Traffic congestion is one of the major issues in any big city which has huge negative impacts, like wastage of productive time, longer travel-time, more fuel consumption etc. In this paper, we aim to analyse GPS trajectories and analyse it to summarize the traffic flow patterns and detect probable traffic congestion. To have a feasible solution of the traffic congestion issue, we partition the complete region-of-interest(ROI) based on both traffic flow data and underlying structure of the road network. Our proposed framework combines various road-features and GPS footprints and analyzes the density of the traffic at each region, generates the road-segment graph along with the edge-weights and computes congestion-ranks of the routes which in turn helps to identify optimal routes of a given source and destination point. Experimentation has been carried out using the GPS trajectories (Tdrive dataset of Microsoft) generated by 10,357 taxis covering 9 million kilometers and underlying road network extracted from OSM to show the effectiveness of the framework.