Garvita Bajaj

Garvita Bajaj

Auto-generated profile, based on publicly available information

Garvita Bajaj

Mélange Laboratory, Indraprastha Institute of Information Technology, New Delhi 110020, India

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 October 2018 in IEEE Access
Verified
Journal Article
Open access
GBGarvita Bajaj
Garvita Bajaj
RARachit Agarwal
Rachit Agarwal
PSPuspendra P Singh
Puspendra P Singh
NGNikolaos Georgantas
Nikolaos Georgantas
VIValerie Issarny
Valerie Issarny
IoT systems are now being deployed worldwide to sense phenomena of interest. The existing IoT systems are often independent which limits the use of sensor data to only one application. Semantic solutions have been proposed to support reuse of sensor data across IoT systems and applications. This allows integration of IoT systems for increased productivity by solving challenges associated with their interoperability and heterogeneity. Several ontologies have been proposed to handle different aspects of sensor data collection in IoT systems, ranging from sensor discovery to applying reasoning on collected sensor data for drawing inferences. In this paper, we study and categorize the existing ontologies based on the fundamental ontological concepts (e.g., sensors, context, location, and more) required for annotating different aspects of data collection and data access in an IoT application. We identify these fundamental concepts by answering the 4Ws (What, When, Who, Where) and 1H (How) identified using the 4W1H methodology.

23 December 2019 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
GBGarvita Bajaj
Garvita Bajaj
PSPuspendra P Singh
Puspendra P Singh
Metro trains have emerged as a sustainable and cost-effective solution against environmental concerns and productivity losses caused by road traffic congestion. Understanding commuters' needs and preferences are essential for promoting and providing metro services. In this work, we survey a group of Delhi metro commuters to study their metro convenience preferences. Using mixed-method analysis, we identify the factors that contribute to commuters' convenience through stated preference valuations obtained from a survey (368 valid responses). These factors are a combination of metro route attributes (boarding/de-boarding stations and line interchanges) shaped by commuter experiences associated with safety concerns, last-mile connectivity, and their perceptions of travel time, crowdedness, and getting a seat. Based on our findings, we discuss the implications these preferences and perceptions have on user experience with the Delhi metro. We then propose design guidelines to enhance the existing Delhi metro app to improve user experience with metro train service.

3 October 2016
Verified
Conference Paper
Open access
GBGarvita Bajaj
Garvita Bajaj
RARachit Agarwal
Rachit Agarwal
Georgios BouloukakisGeorgios Bouloukakis
Georgios Bouloukakis
PSPuspendra P Singh
Puspendra P Singh
NGNikolaos Georgantas
Nikolaos Georgantas
VIValérie Issarny
Valérie Issarny
Public transportation is essential for sustainable and economical development of cities. Several transport organizations aim to provide service information to commuters through web and mobile apps. This information includes possible routes between two stations, estimated travel and arrival times, and real-time updates about traffic conditions. However, this information is currently not personalized according to commuter preferences. In this work, we emphasize the need for personalized transit service information to commuters and present a vision of our work in this direction. Our final goal is to develop a fully-functional personalized route recommendation system for public transit commuters. This involves identifying commuter preferences and suitable recommendation techniques, and developing a platform to communicate this information to the commuters. We identify the requirements for the development of this platform, and propose an architecture for our system. As a proof of concept, we present an Android participatory sensing application - MetroCognition, which acquires feedback on convenience experienced by commuters in public transit.

1 June 2018
Verified
Conference Paper
Closed access
GBGarvita Bajaj
Garvita Bajaj
PSPuspendra P Singh
Puspendra P Singh
Mobile CrowdSensing (MCS) applications rely on sensor data collected from a number of mobile participant devices; the participant devices need to sustain in the system for longer duration in order to services multiple requests. In this work, we propose two online load-balanced algorithms, that use available resources on mobile devices, to efficiently allocate tasks to a subset of participants. We have conducted extensive simulations to compare our algorithms with three baseline approaches and observed significant improvements in the system lifetime and the total number of tasks serviced. To further validate our results, we also conduct real-world experiments on 8 smartphones. We achieve 29.3% increase in the number of tasks serviced, with drastic improvements in system lifetime (in resource constrained cases) over the state-of-the-art approaches.