S
Shuicai Shi
Researcher at Beijing Information Science & Technology University
Publications - 29
Citations - 183
Shuicai Shi is an academic researcher from Beijing Information Science & Technology University. The author has contributed to research in topics: Vector space model & Feature extraction. The author has an hindex of 7, co-authored 29 publications receiving 153 citations.
Papers
More filters
Proceedings ArticleDOI
Study on SVM Compared with the other Text Classification Methods
TL;DR: Experimental data show that F1 value of SVM classifier has reached more than 86.26%, and the classification results comparing to other classification methods have greatly improved, and it proves that SVM is an effective machine learning method.
Proceedings ArticleDOI
The key technology of topic detection based on K-means
TL;DR: A topic detection prototype system is developed to study how K in K-means affects topic detection, and TDT evaluation methods prove that the validity of the value of K in the algorithm is 83.33% in the topic Detection prototype system based on K-Means.
Proceedings ArticleDOI
Study on Efficiency of Full-Text Retrieval Based on Lucene
TL;DR: After mastering index structure and principle, the size of index buffer in memory is increased and the frequency of writing index to disk by a specific algorithm is decreased and index is optimized by merging it in memory and on disk.
Journal ArticleDOI
Study on Feature Selection Algorithm in Topic Tracking
TL;DR: T evaluation methods prove that optimal topic tracking performance based on weight of evidence for text increases by 8.762% more than mutual information.
Proceedings ArticleDOI
A Smart Approach for Text Detection, Localization and Extraction in Video Frames
TL;DR: A smart approach for text detection, localization and extraction in video frames is presented in this paper, where block change rate (BCR) is imported to realize text detection and localization, and element image division in Lab color space is implied in binary text extraction.