PROJECT TITLE :

T2FS-Based Adaptive Linguistic Assessment System for Semantic Analysis and Human Performance Evaluation on Game of Go

ABSTRACT:

The game of Go may be a board game with a protracted history that's much additional complex than chess. The uncertainties of this game will be higher when the board size gets bigger. For evaluating the human performance on Go games, one human could be advanced to the next rank based mostly on the quantity of winning games via a proper human against human competition. However, an individual's Go player's performance may be influenced by factors like the on-the-spot atmosphere, and physical and mental situations of the day, which causes problem and uncertainty in certificating the human's rank. Thanks to a sample of 1 player's games, evaluating his/her strength by classical models like the Bradley-Terry model is attainable. But, thanks to inhomogeneous game conditions and restricted access to archives of games, such estimates can be imprecise. Furthermore, classical rankings (one Dan, a pair of Dan, ...) are integers, which cause a rather imprecise estimate of the opponent's strengths. Thus, we propose to use a sample of games played against a laptop to estimate the human's strength. In order to increase the precision, the strength of the pc is customized from one move to the next by increasing or decreasing the computational power based mostly on the current situation and the result of games. The human will decide some specific conditions, such as komi and board size. During this paper, we use sort-2 fuzzy sets (T2FSs) with parameters optimized by a genetic algorithm for estimating the rank in an exceedingly stable manner, independently of board size. Additional exactly, an adaptive Monte Carlo tree search (MCTS) estimates the number of simulations, like the strength of its opponents. Next, the T2FS-primarily based adaptive linguistic assessment system infers the human performance and presents the results using the linguistic description. The experimental results show that the proposed approach is feasible for application to the adaptive linguistic assessment on somebody's Go player's performance.