http://dspace.iimk.ac.in:80/xmlui/handle/2259/272 Theses submitted in the area of Computer Science/ Information Technology. 2026-05-12T13:18:18Z http://dspace.iimk.ac.in:80/xmlui/handle/2259/1089 User Technology Readiness in ICT for Social Development Initiatives Supriya, K K Information and Communication technology (ICT) is fuelling the growth of global economy. Intelligent use of ICT is a key to transform societies and it can contribute to the development objectives of a nation mainly through three ways: (1) serving as a tool to tackle some of the real world issues like health, education, agriculture, poverty, etc. (2) acting as a medium for efficient delivery of government services, and (3) promoting techniques to tackle the problem of information asymmetry. ICT for Development (ICT4D) is one of the dominant themes in the domain of Social Informatics studies. It encompasses socio-economic research that examines the ways in which the technological artefact and the human social context mutually constitute the ICT ensemble (Kling, 2000). ICT4D is defined in this study as the design and use of ICT and e-Services that consider social context and socio–economic development... Research Advisory Committee: Dr. M P Sebastian (Chair-person), Dr. Mohammed Shahid Abdulla (Member), Dr. Naveen Amblee (Member):: Hardcopy of the thesis is available in the library. Please contact the help desk for reference. 2016-01-01T00:00:00Z http://dspace.iimk.ac.in:80/xmlui/handle/2259/1083 The Role of ICT in improving the Quality of Healthcare Nikunj, Agarwal India is the second most populous country in the world and will cross the population of China by 20281, but the investment in healthcare technology and infrastuture in India is not growingat the same pace. This can be a threat in managing a number of diseases caused due to the lack of infrastructure. In addition, the evolution of technology in healthcare is sluggish in India as healthcare remains to be a neglected sector. The Information and Communication Technology (ICT) would help the doctors communicate effectively with the patients during or after the treatment (Carnahan, 2006), automate the manual monitoring of inpatient departments in the hospitals, reduce errors during administration of medication to patients (Chertow et al., 2001), and diagnose the patients accurately and rapidly as the accessibility to patients’ history is simplified (Miller &Sim, 2004)... Research Advisory Committee: Prof. Sebastian M P (Chair-person), Prof Mohammed Shahid Abdulla (Member), Prof. Omkumar krishnan (Member):: Hardcopy of the thesis is available in the library. Please contact the help desk for reference. 2016-01-01T00:00:00Z http://dspace.iimk.ac.in:80/xmlui/handle/2259/1082 SVDD Variants for Anomaly Detection with Implementations using Hadoop & Spark Rekha, A G Big data analytics facilitates better informed business decisions through the analysis of large data sets that remain unexploited by traditional business intelligence systems. ‘Big Data’ as input enhances the inferential power of established algorithms, but it challenges even the state-of-the-art computation and analysis methods. Though machine learning is a solution to overcome these problems, its current techniques have to be improved to deal with the Big Data. Another drawback of big data analytics is the greater focus on aggregates over outliers. However, in many situations the insights gathered from outliers could be of more significance. In light of this, the focus of this work is on developing machine learning techniques to make outlier detection practical on large business datasets. For over a decade, Support Vector Data Description (SVDD) technique has shown good predictive accuracy on a wide range of outlier detection tasks. It has been adapted to numerous business problems also. Inspired by this trend, this thesis explores the scalability problems associated with SVDD and tries to address it. Three approaches, namely, LT-SVDD, ELT-SVDD, and PELT- SVDD have been proposed. The feasibility of these methods was assessed using a set of experiments on synthetic as well as benchmark data sets; many of these with an order-of- magnitude advantage in terms of running time. The application of these methods to three real world business problems is also demonstrated. This work contributes to the support vector literature by establishing these methods as efficient for outlier detection on large data sets. Research Advisory Committee: Prof. Mohammed Shahid Abdulla (Chair-person), Prof. Asharaf S (Member), Prof. Saji Gopinath (Member):: Hardcopy of the thesis is available in the library. Please contact the help desk for reference. 2016-01-01T00:00:00Z http://dspace.iimk.ac.in:80/xmlui/handle/2259/1079 Multi-Criteria Gain Loss Method for Informed Decision Making Ram Kumar Dhurkari Decision analysis is primarily a prescriptive discipline, built upon normative and descriptive foundations. In all decision making situations, an individual decision maker (DM) arrive at any decision through some conscious and unconscious processes of their brain. In a conscious decision making situation, the DM must have complete information about the problem, the criteria, the alternatives, the methods and their consequences before arriving at any decision. This scenario is known as informed decision making situation. Since, all the discrete alternative multi-criteria decision making (MCDM) methods relies on the preferences of the DM on objective values of the alternatives, the role of the DM is very crucial. This necessitates that the MCDM methods used by the DM in an informed decision making situation to solve a multi-criteria decision (MCD) problems must conform to the cognitive capabilities and descriptive realities of the DM... Research Advisory Committee: Prof. A K Swain (Chair-person), Prof. Radhakrishna Pillai R (Member), Prof. Sridhar Guda (Member):: Hardcopy of the thesis is available in the library. Please contact the help desk for reference. 2016-01-01T00:00:00Z