Accepted Papers

  • Player Valuation in Indian Premier League Auction using Data Mining Techniques
    Aditya Methaila1, Prince Kansal 2,Himanshu Arya 2 and Pankaj Kumar2 ,1NSIT, India and 2MSIT, India.
    ABSTRACT
    The Indian Premier League is a new T20 League which completed its inaugural season in 2008. . Players' auctions are not new phenomena in the world of sports. However, in the game of cricket auctioning of players was first time used in Indian Premier League (IPL). No fixed method was used before to evaluate the performance of a player and determining its base price. In this study, we build several predictive models for predicting the selection of a player in the Indian Premier League, a cricket league, based on each player's past performance. Using One-Day International (ODI) variables and T-20 variables of both batting and bowling, we have found a number of interpretable variables that have explanatory power over auction values. The models that are developed can help decision makers during the auction to set salaries for the players.
  • Hiding Sensitive Association Rule Using Hybrid Algorithm
    Sanjay Keer and Samant Verma,SATI,India
    ABSTRACT
    Privacy preserving in data mining is a novel research direction to preserve privacy for sensitive knowledge from disclosure. Many of the researchers in this area have recently made effort to preserve privacy for sensitive association rules in statistical database. The objective of the proposed hybrid algorithm for privacy preserving data mining is to hide certain sensitive information so that they cannot be discovered through association rule mining techniques. The sensitive items whether in Left Hand Side (LHS) or Right Hand Side (RHS) of the rule cannot be inferred through association rule mining algorithms.Combining the concept of two algorithms, Increase Support of Left Hand Side (ISL) and Decrease Support of Right Hand Side (DSR) algorithms, sensitive rules are hidden. In this approach initially prepared the clusters of sensitive association rules, and then apply the ISL and DSR algorithm for hiding the sensitive association rules. The proposed hybrid algorithm compares with ISL, DSR and hybrid of ISL and DSR algorithm on the base of hidden sensitive association rules.
  • Multi-user service platform design for Smart TV & NScreen services in Open Cloud environment
    Jubyoung Oh1 and Ohseok Kwon2,1Koino inc,Korea and 2Chungnam National University, Korea.
    ABSTRACT

    Smart TV has been discussed as a promising device of Post PC category to handle various user needs by adding computing power to general TV. Smart TV is already commercialized and used in web-surfing, on-demand requests on multimedia contents like movies combined with internet enabled set-top box devices. There has been specific approach to increase its effectiveness by adding TV apps for specific Smart TV hardware. However, in the point of view in Post PC concept, current Smart TV platform and architecture need new paradigm. The architecture should provide office-work friendly environment, cover various OS-dependent users and apps based on Android OS & iOS together, and support legacy IT resources. Thus, we design new platform and architecture platform to achieve the goal to make Smart TV as a Post PC device.

  • Phonetic Classification By Adaptive Network Based Fuzzy Inference System And Subtractive Clustering
    Samiya Silarbi,university of science and technology of oran mohamed boudiaf USTO-MB,Algeria.
    ABSTRACT

    This paper presents the application of Adaptive Network Based Fuzzy Inference System ANFIS on speech recognition. The primary tasks of fuzzy modeling are structure identification and parameter optimization, the former determines the numbers of membership functions and fuzzy if-then rules while the latter identifies a feasible set of parameters under the given structure. However, the increase of input dimension, rule numbers will have an exponential growth and there will cause problem of "rule disaster". Thus, determination of an appropriate structure becomes an important issue where subtractive clustering is applied to define an optimal initial structure and obtain small number of rules. The appropriate learning algorithm is performed on TIMIT speech database supervised type, a pre-processing of the acoustic signal and extracting the coefficients MFCCs parameters relevant to the recognition system. Finally, hybrid learning combines the gradient decent and least square estimation LSE of parameters network. The results obtained show the effectiveness of the method in terms of recognition rate and number of fuzzy rules generated.