PSO Algorithm for Text Clustering Based on Latent Semantic Indexing
محل انتشار: چهارمین کنفرانس داده کاوی ایران
سال انتشار: 1389
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 2,165
فایل این مقاله در 7 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
IDMC04_093
تاریخ نمایه سازی: 15 دی 1389
چکیده مقاله:
In this paper we develop a PSO algorithm based on latent semantic indexing (PSO+LSI) for text clustering. Main problem of text clustering algorithm is very high dimension because in vector space model (VSM) each term represent one dimension. Latent semantic indexing (LSI) is a technique that can reduce high dimension textual data. PSO family of bio-inspired algorithms has recently successfully been applied to a number of real word clustering problems. We use a adaptive inertia weight (AIW) that do proper exploration and exploitation in search space. PSO can merge with LSI to achieve best clustering accuracy and efficiency. the superiority of PSO+LSI over PSO+Kmeans clustering algorithm is demonstrated in two dataset (Hamshahri & Reuters).
کلیدواژه ها:
نویسندگان
Eisa Hasanzadeh
Qazvin Islamic Azad University, Electrical & computer engineering faculty, Qazvin, Iran
Hamid Hasanpour
Faculty of Computer & IT Engineering, Shahrood University of Technology, Iran