Analysis of Outlier Detection on Structured Data
Abstract— Outlier detection has played an important role in all research areas for data analysis in various domains. Outlier is involved according to human error, sensors or mechanical faults and environment. It is detected to get data quality for all applications. On the other hand the good outliers can occur by chance in new contributions in research .The aim of this study is to discover new trend with outlier in dataset. The problem statement is how to detect the outlier analysis based on different datasets between before and after removing outlier. In this system, a box and whisker plot and the robust J48 algorithm are applied for outlier detection and classification.
Index Terms— a box and whisker plot, classification, data Mining, J48, outlier detection
Khin Myo Myat, Si Si Mar Win
University of Computer Studies–Mandalay, MYANMAR
Cite: Khin Myo Myat, Si Si Mar Win, "Analysis of Outlier Detection on Structured Data," Proceedings of 2020 the 10th International Workshop on Computer Science and Engineering (WCSE 2020), pp. 16-21, Yangon (Rangoon), Myanmar (Burma), February 26-28, 2020.