Jagan Institute of Management Studies organized Tuesday Talk on 28th May,’2019 at its Rohini campus
Dr. Deepak Chahal presented a research paper titled “A contingent Exploration on Big Data Tools”. He discussed that in past few years, size of the data was grown exponentially. The size of data growth is eventually ten times faster in the growth due to various means such as the data emerging from mobile devices, remote sensing, sensing aerial devices, recording frequency of radio waves etc. Until most recently, most of the data was never analysed and most of the time it was discarded. This data is stored after spending much cost whereas later it is ignored or deleted because there is no desired space to process the data. Even if organizations succeed to store data it will contribute nothing until analysed to get some new insights. So, the first challenge big data faces is the lack of storage mediums and secondly a suitable software to analyse this data. In this paper, he has discussed about the evolution of 4Vs of big data, levels of big data tools, various data tools along with a comparative analysis of those tools on the basis of distinguished features like Mode of software, Data Processing, Language Support, Data Flow Security, Latency and Fault tolerance.
Ms. Nainika Kaushik presented a paper titled “Information Retrieval from search engine using praticle swarm optimization.” She discussed about the World Wide Web creating an abundance of information to the users, which makes the identification of relevant content difficult. Web mining tries to address this problem. It consists of the application of machine learning and data mining techniques, which allow the automatic extraction of meaningful patterns and relationships from large collections of web data. Web mining can be divided into three main subareas: (i) web content mining, which infers knowledge from the content (i.e. text and graphics) of web pages, (ii) web structure mining, which extracts information from data describing the organization of web content, and (iii) web usage mining, which captures usage patterns by analysing data generated from the interactions of the users with the Web. There is not a clear-cut distinction among these categories, and all three mining tasks can be combined. So the research focuses on a different type of technique for searching the web content , where mining of the web content is done efficiently resulting in insightful results for the users. She applied the support vector machine technique and the Particle Swarm Optimization (PSO) algorithm for searching the web content generating the efficient and best results.