Research

Visit  BIG DATA @ Vestlandsforsking  to know about our research and innovation activities.


Research Interests:                                                         

Knowledge Representation and Reasoning, Semantic Web and Semantic Applications, Machine Learning, Knowledge Based Systems, Natural Language Interface, Big Data Analytics and Data Science.


Key Application Areas:  Emergency Management, Mobility and Transport, Tourism, Information Security, Social Computing, Healthcare, etc.


Current Research Activities
Projects


Current Research Activities:
Recent technology allows for the collection of massive volumes of data. These datasets are not only huge, but complex, including unstructured, heterogeneous data, image, video, and human language. Hence, entirely innovative approaches are needed to handle them.

Big data in Urban Mobility, Emergency Response and Healthcare:
Our research focus is on identifying value that big data can provide from the discovery of strategic information up to its analysis and exploitation. We delve into different ways of representing and analysing big data to make it amenable to valuable insight discovery. We also use data science to build predictive models to help with decision support tasks.

Some of the sub areas on which we focus are:

  • Harnessing insights from unstructured data
  • Big data and emerging technologies
  • Data quality, security and privacy
  • Role of big data for financial, media, energy, healthcare, tourism and mobility sectors

Social informatics:
Our research focus is at the crossroads of human computer interaction, sociology and communication, mainly focusing on the topics of privacy, big data, interpersonal communication, social networks.

Some of the sub areas on which we focus are:

  • Analysis of user engagement in large-scale unstructured data from social networks
  • Privacy and social big data
  • Emergency response and crisis informatics
  • Best practices, methods and results in requirements analysis and in human centred evaluation

Knowledge engineering and semantic technologies:
Our research focus is on interdisciplinary research within the broad areas of software engineering, semantic web, linked open data, and knowledge engineering.

Some of the sub areas on which we focus are:

  • Knowledge engineering techniques and applications for organization, analysis, management, and reuse of information
  • Formalisms for the representation of knowledge
  • Applications that employ knowledge in the forms of ontologies and semantic data Information extraction and content analysis
  • Cognitive aspects of semantic technologies

Major Funding Agencies:                                                                       
European Commission (FP7),
Third World Academy of Sciences (TWAS),
UNESCO,
Research Council of Norway,
NCE Norway,
Department of Science & Tech., Government of India,
NBHM, Department of Atomic Energy, Government of India,
Industrial Funding.


Projects:

Major R&D Project Completed: 14 International and 19 National.

Project Title: Ubiquitous Data-Driven Urban Mobility (UBIMOB)
Type: Research Project, The Research Council of Norway (2017 - )
Mobility describes the ability of people and goods to move around an area and in doing so to access the essential facilities, communities and destinations that are required to support a decent quality of life and a buoyant economy. Mobility incorporates the transport infrastructure and services that facilitate these interactions. Mobility generates huge amounts of data through sensors, traffic cameras, as well as asynchronous user-generated information, synchronous user-generated data, historic databases and data from mobility companies in real-time. If properly analysed and interlinked, these ubiquitous data can be utilized to understand, optimise and manage mobility and make it more efficient, sustainable and
smart. Ubiquitous Data-Driven Urban Mobility (UBIMOB) project will address this challenge by developing and delivering an adaptive and context sensitive mobility dashboard, which on one hand helps citizens to make smart decisions taking their personal need into account and on the other hand helping service providers and operators to reach equilibrium of mobility services, supply and demand, by smarter resource planning and matchmaking. UBIMOB will help to add, create and increase the value of existing and new data sources as well as providing a means for more timely and efficient decision making. The project has the potential to impact the everyday lives of citizens, their health and the environment with huge financial and social impact. UBIMOB solution will be evaluated rigorously by residents, business and decision makers in 3 cities in Norway. In first phase, UBIMOB partners will explore and assess the technical feasibility, needs of cities and commercial potential of an innovation that the consortium wants to exploit and commercialize.
The UBIMOB consortium consists of 5 national partners and 2 international partners with complementary expertise covering all aspects of the project.

Project Title: Transnational Partnership for Excellent Research and Education in Big Data and Emergency Management (BDEM)
Type: INTPART Project, The Research Council of Norway (2017 - 2020)
Emergency management has become a problem for authorities across the world.  Because the frequency of disasters such as floods, landslides, earthquakes, and even riots have considerably increased over past decades.  As with natural disasters, such health, infrastructure and security incidents can critically impact people and jeopardize public safety. With a current focus on moving from reacting to these events as they happen towards preventing and minimizing them, big data play a critical role in societal ability to plan, prepare and recover from emergency events. The project aims through cooperation between Vestlandsforsking, University of Bergen and six world class departments from the USA, Hong Kong and Japan, to establish a long term partnership where excellent education is to be embedded in excellent research in big data and emergency management.  The project has multiple partner institutions in three countries, and thus has the potential to be an extensive network that connects many researchers, faculties and students. The BDEM research and education network will be coordinated by Vestlandsforsking and will run for a term of three years.

Project Title: Emergency Management in Social Media Generation (EmerGent)
Type: Research Project, FP7 European Commission (2014 - 2017)
EmerGent aims at understanding the positive and the negative impact of social media in emergencies in order to enhance objective and perceived safety and security of citizens before, during and after emergencies. Furthermore, EmerGent aims at strengthening the role of European companies dealing with services and products related to the aimed research and development results. The understanding of critical situations, the reactions expressed through social media and the general importance and preferred types of social media will be considered.
For this research new methods and tools will be developed to reinforce the communication between weakly connected (via social media) crisis-communities (citizens) and the emergency management services, supported by European associations. To handle the vast amount of valuable and distributed data new methods for Information Mining and Information Quality will be developed to classify and rate publicy available and provided data from users. With developed methodologies and software tools for the routing of mined and classified emergency relevant information from social networks, EmerGent will create a comprehensive concept for Novel Emergency Management.


Project Title: Big data roadmap and cross-disciplinarY community for addressing socieTal Externalities (BYTE)
Type: CSA Project, FP7 European Commission (2014 - 2017)
The BYTE project will assist European science and industry in capturing the positive externalities and diminishing the negative externalities associated with big data in order to gain a greater share of the big data market by 2020. BYTE moves beyond current practices to consider how big data will develop to the year 2020 using foresight tools to identify future practices, applications and positive and negative externalities. This will allow BYTE to develop, in collaboration with expert stakeholders, a vision for big data in 2020 that includes meeting the relevant goals of the Digital Agenda for Europe. In collaboration with expert stakeholders, the consortium will then devise a research and policy roadmap that will provide incremental steps necessary to achieve the BYTE vision and guidelines to assist industry and scientists to address externalities in order to improve innovation and competitiveness. BYTE will culminate in the launch of the big data community, a sustainable, cross-disciplinary platform that will implement the roadmap and assist stakeholders in identifying and meeting big data challenges. Furthermore, BYTE will disseminate project findings and recommendations and publicise the big data community to a large population of stakeholders to encourage further innovation and economic competitiveness in Europe’s engagement with big data.

Project Title: High-Performance Modelling and Simulation for Big Data Applications
Member, Management Committee: Rajendra Akerkar
Type: COST Action IC1406 (2015 - 2019)
This Action will provide the integration to foster a novel, coordinated Big Data endeavour supported by High Performance Computing. It will strongly support information exchange, synergy and coordination of activities among leading European research groups and top global partner institutions, and will promote European software industry competitiveness.

Project Title: Uncertainty Reasoning for Linked Data
Coordinator: Rajendra Akerkar
Type: Research Project (2011 - 2013)
The necessity for reasoning over uncertain information within the Semantic Web occurs in many different situations. The Semantic Web must handle information from applications that have special knowledge representation needs (for example, multimedia-processing, geospatial, and situation awareness applications) and that face uncertain, imprecise knowledge. This project deals with important uncertainty representation issues which apply to linked data and develop methods to tackling them.

Project Title: Nature-inspired and Socio-COgnitive Information Search and Retrieval for Complex Information Environments  (NiCOS)
Coordinator: Rajendra Akerkar
Type: R&D Project (2012 - 2014)
The project NiCOS aims at the development of collaborative artificial socio-cognitive agents that reside on the Internet. NiCOS represents an emergent class of cooperative agents that do not have a physical existence, however are equipped with key constituents of cognition to become adaptive, collaborative, robust and self improving in a certain environment given specific tasks. With NiCOS we focus on artificial agents that are able to blend human and computer abilities for the benefit of the user. NiCOS enhances social awareness and cognitive abilities by linking and processing users information, activities and relationships with social circles and gain access to the most relevant information and intuitively understand, collaborate and process the information in users’ own context.
We develop a framework that integrates a socio-cognitive model and architecture with modules such as digital memory, knowledge representation and special purpose components as realized in natural language systems and search engines. In the human-computer interface, NiCOS will also assist the agent learning about conversations with interactions and social feedback to make better recommendations. The feasibility of the innovative approach is demonstrated via two application scenarios: a scenario where users train their NiCOS to more efficient search within large organisations, and a scenario where NiCOS assists the human user in information access related to climate change
.

Project Title: Intelligent Support for Real-time Decision Making
Coordinator: Rajendra Akerkar
Type: Research Project (2010 - 2013)
This project aims to increase situation awareness and support decision making for enterprises to proactively engage online people with their product advertisements. The project will advance the state of the art in social media by investigating approaches and techniques from text mining, information extraction, machine learning, semantic technologies and social network analysis that combine to allow the analysis of big data scale streams of heterogeneous multilingual content in real-time. The project results will be evaluated within two distinct case studies, namely, tourism and health.

Project Title: Intelligent Agri-Information Framework
Team: Akerkar R. (Advisor), Manoj G., Dineshkumar P., Punyashree P.B., Shruthi N.
Type: R&D Project (2011-12)
The biggest challenge faced by Indian Planners is how to reach the rural people effectively to make them take advantage of the benefits. There is some miss-match or inequality between the farmers and government & other organization. In this project, we investigate solution for the problem and correct the gap by making effective use of Information Communication Technology (ICT), which might be the starting point for other researchers in order to improve agricultural practices in India and which will be a good contribution to this society.
Task:1: Building a comprehensive ontology for agriculture,
Task:2: Developing an intelligent system on top of the ontology,
Task:3: Creating Query based interface,
Task:4: Extending that interface in various regional languages
.

Project Title: Technology Approach to Cultural Reasoning
Team: R. Akerkar, J. Calmet, P. Maret
Type: Research Pre-Project (2010 - 11)
While solutions to leveraging culture for innovation and dissolving conflicts arising from cultural misunderstandings exist in a variety of forms, as yet one aspect remains absent in our IT society. This missing link is a framework for automated cultural reasoning - one that would enable new computer-based solutions to overcome issues in cross-cultural communications and collaborations. The purpose of the project is to establish such a solution, especially a trust-building framework for the automated handling of cultural issues in controlled application domains. The main idea of the proposal consists in designing trust-building IT tools to rationalize intercultural differences arising in virtual enterprises. These tools are founded on a new abstraction of cultural items, which is valid across all fields of knowledge from humanities to technology, and theories from insurance economics, sociology, and knowledge management.

Project Title: Linked Data Tourism 
Team: R. Akerkar and T. Aaberge
Type: R&D Pre-Project (2011 - 12)
This pre-project aims at developing our understanding of how the Linked Data ecosystem is evolving, the infrastructure required to support that ecosystem, and where we can best provide support to help promote shared innovation around the emerging linked data web. Important innovative elements are:
•    The importance of information control and metadata strategies for tourism –sector services
•    A methodology and a technology for publication and reuse of open tourism service information


Project Title: Networks for Societal Transformation (NeST)
Coordinator: Rajendra Akerkar
Type: R&D Industrial Pre-Project (2010 - 2012)
This Project aims at exploring novel way of communication among people not only for sharing experiences, but are also for helping people connect to resources that are required by them to solve actual problems. Ultimate goal is at providing a generic design of a NeST and it will present a proof of concept showing the broad effect of the project on very different application areas, namely climate and health care.

Project Title: Collaborative Information Access (CoInA)
Coordinator: Rajendra Akerkar
Type: Research Project (2011- 12)
In CoInA we will construct a socio-cognitive agent that goes beyond the state-of-the-art of  current intelligent web based agents in four respects, it will possess a semantically enhanced memory
have the capacity to dialog with a group of people that collaborates on making a search of information have augmented Socio-Cognition  ability, i.e., innovative enhancement to interleave remembering with thinking and doing, therefore making the context of thought and action available to guide remembering participate in a collaborative information seeking interaction. The semantic modelling of the socio-cognitive agent will take into account hybrid reasoning and results from socio-cognitive research. The project will apply best practice semantic modelling and hybrid reasoning techniques and in many ways present a new approach in this domain. 


Project Title: ICT based Semantic Interoperability 
Coordinator: Rajendra Akerkar
Type: Research Project (2009 - 2010)
To develop and evaluate new methods for development and evolution of the Semantic Web methodologies and tools for sustainable tourism. To investigate Knowledge technologies that can be used to improve the accuracy of searches and obtain a superior matching between customer expectations and tourism products. Also to examine how to accomplish semantic interoperability between web sources and services.

Project Title: Knowledge Discovery to explore correlations between Mind Conditions and Physical Elements of Human beings.
Team: Rajendra Akerkar & Manish Joshi
Type: Research Project  (2007 - 2009)
Human is not simply a machine,as Descartes suggested more than 300 years ago. It seems we have come full circle in our beliefs about the mind - body relationship. Body and mind clearly interact and in complex ways that we do not yet fully understand. This project aims at establishing correlation between patient symptoms and probable disturbances in patient’s mind using models of  knowledge discovery in databases.


Project Title: Adaptive HTML Analysis to Automatically Wrapper Generation.
Team: Rajendra Akerkar, David Camacho and  María Dolores Rodríguez-Moreno
Type: Research Project (2008-2009)
In this project, we propose an approach, based on Artificial Intelligence techniques, to extract information from HTML pages and to add automatically semantic tags to them (extracted from a given ontology). Our project will use both, an adaptive interaction with the user, and several machine learning algorithms to adapt the wrapper generation process to the necessities of the users. The integration of both, Information Extraction and Software Agents technologies, to automatically generate adaptive wrappers could be an important issue in the evolution of new algorithms (and their related applications). These algorithms could be able to aid manage the current complexity of the Web (designed for humans not for software programs), and to alleviate the problem of extract (and manage) semantic data from the current Web systems. To study how these techniques can be adapted to the current Semantic Web-based technologies.

Project Title: Instructional Designs for Distance Education: Neural Net Enabled Distance Learning Model.
Project Coordinators: Prof. Rajendra Akerkar and A. Bagal
Type: Industrial (2007 - 2009)
The unique “one-to-one” nature of distance learning offers a unique opportunity to tailor the instructional process for the benefit of the student as well as the organization. Neural Net Technology offers an “add-on” possibility for the computer/teacher to learn about the student, and adjust the course content as well as the pace to best suit the student. This will result in educating the student rather than issuing a pass/fail grade based on a process designed to fit all. Knowledge represented in the human brain as the strength of a very large number of interconnections between a very large number of nodes called neurons. Based on actual experience, the human brain adjusts the interconnection strength to adapt to new environments. In case of distance learning, this would entail the administrative software program adjusting the course content, through an on-going comparison of the student’s performance against a set of established “thresholds”.

Project Title: Machine Learning for Data Mining in Medicine.
Coordinators: Rajendra Akerkar
Type: R&D Project (2003 - 2007)
The central idea of this research work was: Can useful and new knowledge be discovered from large collection of medical data by means of Data Mining, in particular by the method of machine learning from examples with artificial neural nets and case based reasoning? In this research phase, we have tested machine learning approaches used in mining of medical data, distinguishing between symbolic and sub-symbolic data mining methods and applications of these methods in medicine have been considered.

Project Title: Intelligent Natural Language Interface.
Coordinators: Rajendra Akerkar and Manish Joshi
Type: Research Project (Completed in July 2007)
Natural Language Interface helps user to interact with computer in non-formal manner by answering various questions posed by user. Key-word matching based paradigm generate answers, however these answers often affected by problems caused by some language Dependant phenomena like semantic symmetry and ambiguous modification. Current methods described in literature tackles these problems using in depth parsing whereas we have formulated rules to tackle linguistic phenomena using shallow parsing.  We have developed an Intelligent Natural Language Interface (ENLIGHT) comprising of newly formulated shallow parsing based algorithms in conjunction with some AI techniques to train the system. We have then tested results obtained from the ENLIGHT system. As compare to other systems which requires in depth parsing for extracting correct answer ENLIGHT system is more effective and efficient. Results are compared using different metrics like precision, mean reciprocal rank, response time and ENLIGHT system show better performance. Our algorithms  implemented for search engine technology in the next phase.

Project Title: A Knowledge Representation and Reasoning System
Coordinators: Rajendra Akerkar,  D. Rajesh Duthie
Type: Research Project (Completed in December 2005)
The general task of work in knowledge representation and reasoning (KRR) is, trivially, the representation of knowledge. The kind of knowledge for which the representation task has been undertaken is secondary to the description of the overall task as an exercise in knowledge representation. Thus, the task of representing and using mathematical, commonsense, visual language based, and logic knowledge is "lumped" together under the KRR. We would like to argue that, in the task of natural language processing and understanding, language syntax, semantics, and pragmatics imposes constraints on any computational formalism. In this project, we present KRR system for the representation of knowledge associated with natural language dialog. We say that this may done with minimal loss of inferential power and will result in and enriched representation language capable of supporting complex natural language description, some discourse phenomena, standard first-order inference, inheritance and terminological sub-assumptions. The aim of the new logic and its implementation in a KRR system are as follows: A study of some characteristics of natural language that a KRR system should support, a KRR system to present a formalization of a propositional semantic network based knowledge representation and reasoning system that addressed our goals for NLP, a KRR system in which mapping from natural language sentences into logical form sentences be as direct as possible. The work also include other related aspects of the above mentioned problems.

Project Title: A Computational Model for Knowledge Intensive Learning
Coordinators: Rajendra Akerkar,  Rajeshree Belekar
Type: Research Project (Completed in December 2007)
The  framework  represents  a  perspective  on  knowledge,  reasoning  and  learning  that  aims  at satisfying   three   fundamental   system   requirements. All   requirements   are   based   on   the assumption  that  competent  and  robust  systems  need  a  thorough,  relatively  deep  knowledge model as a fundament for understanding, i.e. as a background pool of knowledge from which plausible   explanations   are   generated   to   support   reasoning   steps   and learning   decisions concerning the more shallow, associational knowledge in past cases and heuristic rules. The system developed under this project  works for majority type of adult diabetic patients.

Mini-Projects:
Semantic Markup for Fjord Norway's Websites  (2011)
Scheduling system for managing information for tourism (2012-13)
Mechanized Cultural Reasoning (2010)
Semantic models for cross-sector portals (2009-10)

Previous major projects in mathematics:
1. Project Title: Computational Combinatorial Structures on Hilbert Scheme.
    Funding agency: NBHM, Dept. of Atomic Energy, Government of India. (1997-99)
2. Project Title: Symbolic/Numeric Algebraic Constraints Solving (SNACS).
    Partial Support: Third World Academy of Sciences, Italy. (1999-2001)
3. Project Title: Computer Algebra Applications in Industry
    Funding Agency: Dept. of Science & Technology, Government of India. (1997-98)