Accepted Papers


  • Mining Big Data: Challenges and Opportunities in the UAE
    Zaher Al Aghbari,Computer Science,United Arab Emirates.
    Nowadays, the daily amount of generated data is measured in exabytes. Such huge data is now referred to as Big Data. Big data mining leads to the discovery of the useful information from huge data repositories. However, this huge amount of data hinders existing data mining tools and thus creates new research challenges that open the door for new research opportunities. In this paper, we provide an overview of the research challenges and opportunities of big data mining. We present the technologies and platforms that are required for mining big data. A number of applications that can benefit from big data mining are also discussed. We discuss the status of big data mining, current efforts and future research directions.
  • Performance Analysis of Classification And Clustering Algorithms Using Hadoop Mahout
    Srinivasulu Asadi 1, Ch D V Subba Rao 2,1JNTUA College of Engineering,India 2 S.V University College of Engineering,India.
    High dimensional data concerns large-volume, complex, growing data sets with multiple, and autonomous sources. As the data increasing very drastically day by day, it is a major issue to manage and organize the data efficiently. This emerged the necessity of machine learning techniques. With the availability of high speed networks, data storage and the data collection capacity, Machine learning cluster algorithms are now rapidly expanding in all science and engineering domains such as Pattern recognition, data mining, bioinformatics, and recommendation systems. To support the scalable machine learning framework with Map Reduce and Hadoop support, Apache Mahout is used to manage the huge voluminous data. Various cluster problems such as cluster tendency, partitioning, cluster validity, and cluster performance can be easily overcome by Mahout clustering algorithms. Mahout manages data in four steps i.e., fetching data, text mining, clustering, classification and collaborative filtering. In the proposed approach, various data types such as numeric, characters and image datasets are classified into several categories i.e., collaborative filtering, clustering, classification or frequent item set mining. A non-hadoop cluster named taste recommendation frame work is also implemented.


Copyright ® DMDB 2015