My Research and Projects

Unified semantic model for IoT data and its applications.
Used in: Fiesta-IoT Platform

This research activity is along the lines of building semantic models for storage of data produced by devices. Here, the focus of study is to: (a) study how data generated by sensor (static, mobile, social, and participatory) can be federated and semantically stored with the use of ontology (b) build a large scale crowdsensing experiment that could utilize the semantically annotated data from the sensor, provide useful information to citizens about the environment and be of societal value.
A Plethora of data is being generated and made available via sensing technologies. Attaching semantics to this data provides meaning to the data and helps in (a) achieving common understanding and (b) performing analysis and reasoning. A lot of ontologies such as SSN, iot-lite, and SAO, etc. have been developed to provide semantics to this data. However, there is no comprehensive ontology to deal with data produced by various sensors. Semantics not only can be applied to the generated data, but it can also be applied to the data obtained from the analysis or reasoning of the generated data. Thus, via this contribution, the key questions answered are:
  • what properties should be considered in the ontology (also called as a semantic model) that covers aspects like, metadata, measurements from a sensor, and streaming nature and mobile nature of measurements, and covers relatively all domains related to IoT so as to show interoperability and federation?
  • data once semantically stored, how large scale crowdsensing experiment can utilize it and produce meaningful results?
Further, this study also includes the study of mobility model. As a partner in the project, my involvement extends from June 2015 until December 2017 as a Technical expert. An alpha version of the working link about the software demo can be accessed via This contribution finds its implementation in the EU H2020 FIESTA-IoT project.
FIESTA-IoT (Feb 2015 - Jan 2018) "is acronym for Federated Interoperable Semantic IoT/cloud Testbeds and Applications. Fiesta-IoT is a Horizon 2020 project and lies in Future Internet Research and Experimentation (FIRE) domain. The FIESTA-IoT project works on integrating IoT platforms, testbeds and associated silo applications. FIESTA-IoT opens up new opportunities for the development and deployment of experiments that exploit data and capabilities from multiple testbeds. The FIESTA-IoT infrastructure enables experimenters to use a single EaaS API (i.e. the FIESTA-IoT EaaS API) for executing experiments over multiple IoT federated testbeds in a testbed agnostic way i.e. like accessing a single large scale virtualized testbed".
FIESTA-IoT consortium consists of European partners like Inria, NUIG, EGM, Com4innov, IT Innovation, University of Cantabria, Sodercan, Ayuntamienta de Santander, Fraunhofer FOKUS, Unparallel Innovation, NEC, University of Surrey, Athens Institute of Technology and a South Korean partner KETI.

Large scale data acquisition and its application in transit domain.
Used in: Sarathi Middleware

This research activity is along the lines of simulating large-scale dataset based on representative data and generating recommendations by studying mobility and travel characteristics in a multi-modal network to enable personalized multi-modal mobility such as those based on preferences of travelers. This contribution finds its applicability in the Inria DRI/DST-CEFIPRA Associate Team Sarathi (March 2014 - Feb 2017) of which I am the PI since October 2015. Sarathi team aims to develop a personalized mobility service platform for urban travelers in emerging markets. Sarathi team consists of members from I.I.I.T. Delhi. The project relies on mobile participatory sensing.
Public transportation is essential for the sustainable and economic development of cities. In order to understand the transportation needs that could sustain, it is also essential to understand the transit behavior of the commuters and then recommend personalizations based on the needs. This understanding can be achieved by analyzing either data acquired via Mobile CrowdSensing (MCS) applications or via getting the transit data from transport service providers. Nevertheless, acquiring data via such methods is a time-consuming activity, and further, the deployment of MCS applications lack large-scale participation of users. This makes it hard to collect the transit needs and thus limits the database required to make correct recommendations. This is referred to as cold start problem in the recommendation systems. To overcome such issues, my this research activity is focused on how large-scale data can be generated using data from the representative set and once this data is available how it can be used to generate recommendations for commuters. Further, as this data might come from different sources, how semantically this data be federated and stored to achieve efficiency. Thus, in this contribution, the key questions addressed are:
  • what are the properties that need to be addressed in order to generate representative data?
  • what are the suitable recommendation techniques that are applicable to the gathered data to provide better recommendations to the commuters?
  • what semantic properties are to be used to store such data?
As a use case, this activity is supported by the development of a website application - "MetroCognition" that aims to integrate the results obtained from the activity. Via this application, the data about the convenience of the commuter is collected. This convenience is based on comfort, seat availability and waiting time.

Understanding human behavior for personalization of city wide data.
Used in: 3cixty Platform

This research activity is along the lines of modeling and implementation of algorithms for personalizing city data based on mobility traces of the users and their preferences. Due to personalization, my research activity was also focused on the user data reconciliation and investigation of privacy issues related to the reconciliation of user data. This study includes the study of the state of the art algorithms. This contribution finds it applicability in EIT Digital 3cixty activity. Here, the research activity also included software development activity where my responsibility also extended towards the implementation of various other features within 3cixty backend like authentication, extraction of mobility profile from partner's server, and 3cixty backend APIs. Specifically, my contributions include: the development of the core user profile, implementation of web crawlers (social profile crawlers), implementation of query augmentation and the analysis of call logs. The implementation includes programming in Java using SPARQL, Google API calls, and Virtuoso. As a partner in the project, my involvement extends from Jan 2014 until December 2015 under the capacity of the Task Contributor in 2014 and Task Leader in 2015.
3cixty (Jan 2014 - Dec 2015) "is a platform that aims to integrate city data. It offers a service platform that developers can use to create applications that enable people to instantaneously access reconciled information (including crowdsourced information) about a city with a personalized view. 3cixty platform is jointly under development by European partners including Inria, DFKI, Telecom Italia, Eurecom, Cefriel, Fondazione Politecnico di Milano and SMEs like Ambientic, Mobidot and Localidata. 3cixty platform provides services via REST-based APIs calls and is selected as EIT digital labs showcase platform for Milan 2015 Expo. 3cixty also hosted an App challenge that enabled developers to develop their own Apps using 3cixty features".
Find More chevron_right

Enhancing Information Dissemination in Wireless Networks.
Used in: Thesis

This contribution is along the lines of developing models and algorithms to enable faster diffusion of information by achieving small world characteristics within a network constituent of either static or mobile or both kinds of devices. This contribution paved the way to my Ph.D. dissertation. Information dissemination across the network is a critical aspect. Dissemination of information should be context dependent and, if needed, should reach as many devices in the network in a short time. In communication networks, those based on the device to device interactions, dissemination of the information has lately picked up a lot of interest and the need for self-organization of the network has been brought up. Self-organization leads to local behaviors and interactions that have global effects and helps in addressing scaling issues. The use of self-organized features allows autonomous behavior with low memory usage. In order to provide self-organized features to communication networks, insights from such naturally occurring phenomena are used.
Nonetheless, achieving small world properties is an attractive way to enhance information dissemination across the network. To achieve small world properties, rewiring of links in the network is performed by altering the length and the direction of the existing links. In an autonomous wireless environment, such re-organization can be achieved using self-organized phenomenon like Lateral Inhibition and Flocking, and beamforming (a concept in communication). Further, due to slow and evolutionary nature of Lateral inhibition and Flocking, it is not feasible to apply the algorithm in a mobile scenario. This leads to study of other algorithms that perform best and utilizes no extra energy and had low computational cost. Thus, in this contribution, the key questions addressed were:
  • how can information dissemination be enhanced across the network, either static or mobile?
  • how can insights from nature be utilized?
  • how using local properties global properties can be addressed in the network?
  • by utilizing real mobility data, how can the study of dissemination using mean field approach in a very large population be done?
The main outcomes of this contribution were: i) study of nature-inspired algorithms to increase connectivity and achieve Small World properties, ii) a distributed algorithm for nodes to decide on their beamforming behavior, iii) a simulation based analysis of the achievable performance benefits of randomized beamforming and identify the challenges involved, iv) a distributed algorithm for nodes to decide on their beamforming behavior, v) a new measure of betweenness centrality WFB (Wireless Flow Betweenness), which is used to identify beamforming nodes, vi) significant performance benefits can be achieved over randomized beamforming using algorithm developed in the contribution, vii) the introduction of latent states to account for variable density, viii) study of how mobility in a network with community structure could be applied to achieve large-scale dissemination in a dynamic device to device based communication network, and ix), study of information dissemination in the context of Ivory Coast.

Towards Transport Information Managemenent

Development of an application platform for citywide and countrywide transport information management relying on mobile social crowd-sensing while taking into account the particular context and constraints in a region.

Design of parallel processor for Natural Language Processing applications

The Project was funded by Ministry of Communications and Information Technology, India. The PI for the project was Prof. Ajai Jain of IIT Kanpur. My research includes studying the NLP Applications such as Machine Translation, Question Answering System, Text Summarizer and Information Retrieval. The project had three phases: Research on the NLP Applications and Development of desktop application for them, development of web service and development of the processor. In the first phase, the implementation of the project was done using SystemC, C, and Java. The web service, the second phase, was implemented using Java and the front-end was developed using C sharp. The third phase used VHDL.

Specific components for Red Bull Racing Team

Developing software components essential for communication with the race car and team members during the race. Languages used include C sharp, MATLAB and SQL. The components developed became part of already existing software such as Event Request, Race Car, Fuchsia Bovine and Driver Feedback.

New Publications

List of new publications.

New Class Notifications

New Class Notifications.

New Interesting Material

Lsit of new Interesting Material.