Utilizing graphics processing unit to accelerate drug-symptom association mining. (September 2020)

• Record Type: Journal Article
• Authors: Tian, Yun; Scholer, Jesse; Ji, Yanqing; Rogers, Uri; Shen, Fangyang
• Is Part Of: Computers & electrical engineering. Volume 86(2020)
• Publication Date: 2020-09
• Subjects: Frequent Itemset Mining -- Association Rule Mining -- Graphical Processing Unit -- and Drug-symptom Association Mining; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2020.106704
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: A limited number of graphics processing unit algorithms exist for frequent itemset and association rule mining. This paper attempts to address that gap by introducing algorithms that lend themselves to massively parallel processing in a tool we call GPUMiner. The performance of GPUMiner will be contrasted against classic algorithms developed for a central processing unit type architecture. Multiple optimizations are adopted to improve efficiency in our design, including separate bitmaps for drugs and symptoms, parallel reduction for sum operation and a thread combination matrix that enables multiple-drug combinations to explored. Experiments, using the popular test dataset T40I10D100K.data, show that our GPUMiner is able to achieve a speedup of 13.7 in comparison to the existing implementation. In addition, we apply GPUMiner in discovering drug-symptom associations and report on some well-known symptoms associated with a single drug or a combination of multiple drugs.