- Intelligent Data Analytics Lab.
- Web site
- Courses - Undergraduate
- - Java Programming 2- Software Engineering Exercise- SCCP - Factory - Big Data and Situation Awareness
- Courses - Graduate
- - Advanced Internet Technology- Semantic Web Technologies- Introduction To Big Data Science
- - Semantic Web Services and Composition - Web Data Mining - Awareness Computing - Big Data Science and Infrastructure- Web Security and e-Business
- Educational Background, Biography
- - Diploma Taejeon High School, Taejeon. - Bachelor Department of Electronics, Korea University - Master Dept. of Electronics (Computer), Graduate School, Korea University - Ph.D Dept. of Electronics, Graduate School, Korea University
- Current Research Theme
- Semantic Web Services & Service Composition<br>Deep Learning Applications in Semantic Web Services, Natural Language Processing<br>Web Data Mining<br>Big Data Infrastructure and Analysis
- Key Topic
- - Automatic Service Composition Framework- Global Social Service Network and Its Application- Big Data Mining and Analysis- Geo-Aware Optimal Big Data Infrastructure- Service Composition Framework on Big Data Science
- Affiliated Academic Society
- ACM, IEEE, IEICE, ISPJ, IEIE
- Jogging, Basketball
Reading Books (Bible) and Prayer
Talking with Sincere Topics
- School days' Dream
- Current Dream
- To have a personality as like Jesus
- - Love God with all heart and Love others as like you.
- Favorite Books
- - Bible
- Messages for Students
- - Your life is unique and more important than any others. - Set the highest and most valuable goal that you can decide, try with Your all heart and NEVER give up until it can be realized.
- Publications other than one's areas of specialization
- Big Data Science using Machine Learning with Service Computing (Entire Summary)
The data explosion in recent years has led to a great rising demand for Big Data processing, and new intelligent approaches as a science are strongly required for discovering more competitive knowledge from the large data. Machine learning is a core technology for analyzing data and its technique is being developed very fast. Deep Learning (DL) is one of important technique and has applied many areas. Service Computing is a cross-disciplinary science that encompasses the science and technology of bridging the gap between business and IT services. The service computing enables to use the machine learning more intelligently. Core technologies and applications for Big Data analysis using intelligent services and machine learning are being studied as below.
- Machine Learning (Deep Learning) Applications - Other Applications on Service Computing, Medical Applications
Several applications are being studied such as discovering knowledge on service invocation using Transformer and BERT, Medical applications (Pneumonia analysis using DL, EEG signal analysis for depression patients using DL), Document classification, and Other data analysis.
- Machine Learning (Deep Learning) Applications - Automatic Ontology Generation
Extracting taxonomy such as super or sub relationship of terms from documents is studied using several DL architectures, RNN, VAE, and BERT.
- Automatic Deep Learning Service Generation
This research aims at dissemination of AI technologies to Non-AI domain people. Because there are many people who want to use AI technique such as deep learning for their business domain. A system to generate machine learning or deep learning architecture based on AI expert’s knowledge automatically and flexibly is being studied using automatic service composition technique.
- Machine Learning (Deep Learning) Applications - Neural Language Translation with Context
One of brilliant contribution of DL is language translator. We have studied on the Sequence to Sequence model and Transformer model for translation between Japanese and English. They have shown very good result. Now, a new architecture to reduce lexical ambiguity on Transformer using BERT.
- Service Computing on Big Data
The data explosion in recent years has led to a great rising demand for Big Data processing, and new intelligent approaches as a science are strongly required for discovering more competitive knowledge from the large data. Service Computing is a cross-disciplinary science that encompasses the science and technology of bridging the gap between business and IT services. In my research, key issues for intelligent services based on Big Data Science are studied.
- Big Data Processing and Infrastructure
Processing of big data requires a large amount of computation resource, big data infrastructure such as Hadoop and Spark of Apache support distributed processing for the big data. One important topic for parallel processing on the Big Data infrastructure is to develop faster algorithm to process the data efficiently. A new architecture for intelligent big data analytics using automatic service composition have studied during several years.
Dissertation and Published Works
1. T. H. Akila S. Siriweera, Incheon Paik, QoS-aware Rule-based Traffic-efficient Multi-objective Service Selection in Big Data Space, IEEE Access, Accepted on Aug. 24, 2018.
2. WuhuiChen, IncheonPaik, Zhenni Li, Neil Y.Yen, A cost minimization data allocation algorithm for dynamic data center resizing, Journal of Parallel and Distributed Computing Volume 118, Part 2, August 2018, pp. 280-295.
3. Wuhui Chen, Incheon Paik, Zhenni Li, "Cost-Aware Streaming Workflow Allocation on Geo-Distributed Data Centers", IEEE Transactions on Computers, doi:10.1109/TC.2016.2595579, Vol. 66, No. 2, Feb. 2017. pp. 256-271
4. Wuhui Chen, Incheon Paik, Patrick C.K. Hung, Transformation-based Streaming Workflow Allocation on Geo-Distributed Data centers for Streaming Big Data Processing, IEEE Transactions on Service Computing, Accepted on September 2016.
5. Wuhui Chen, Incheon Paik, Zhenni Li, Topology-Aware Optimal Data Placement Algorithm for Network Traffic Optimization, IEEE Transactions on Computers, Pre-Printed Version (DOI: 10.1109/TC.2015.24852), http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7286787, Vol. 65, No. 8, Aug. 2016. Ppp. 2603-2617.
6. T. H. Akila S. Siriweera, Incheon Paik, Banage T. G. S. Kumara, C. K. Koswatta, "Architecture for Intelligent Big Data Analysis based on Automatic Service Composition", International Journal of Big Data (IJBD), 2(2), 2015, pp. 1-14.
7. W. Chen, I. Paik, Toward Better Quality of Service Composition Based on Global Social Service Network, IEEE Transactions on Parallel and Distributed Systems, Vol. 26, Issue 5, April, 2014. pp. 1466-1476.
8. W. Chen, I. Paik, P. C.K Hung, Constructing a Global Social Service Network for Better Quality of Web Service Discovery, IEEE Transactions on Service Computing, Volume:8 , Issue: 2, March-April, 2015, pp284 - 298.
9. Banage Thenna Gedara Samantha Kumara,Incheon Paik,Hiroki Ohashi,Yuichi Yaguchi,Wuhui Chen, Context-Aware Web Service Clustering and Visualization, International Journal of Web Services Research (JWSR), Accepted on December, 2014.
10. Incheon Paik, Wuhui Chen, Michael M. Huhns, Scalable Architecture for Automatic Service Composition, IEEE Transactions on Service Computing, VOL. 7, NO. 1, JANUARY-MARCH, 2014, pp. 82-95.
II. Refereed International Conference Papers (Selected 10 Papers)
1. Incheon Paik, Ryo Ataka, Adaptable Deep Learning Generation by Automatic Service Composition, IEEE International Conference on Web Service 2019, Milan, Italy, July, 2019.
2. Kazuki Omine, Incheon Paik, Atsushi Oba, Incheon Paik, Extraction of Taxonomic Relation of Complex Terms by Recurrent Neural Network, IEEE International Conference on Cognitive Computing 2018, Milan, Italy, July, 2019.
3. Takeyuki Miyagi, Incheon Paik and Rupasingha Arachchilage Hiruni Madhusha Rupasingha,Analysis of Web Service Using Word Embedding by Deep Learning, Proceedings of IEEE International Conference on Awareness Science and Technology 2018 (iCAST 2018), Kyushu, Japan, September 2018.
4. Yuji Ishizuka , Quang-Minh Do , Wuhui Chen , Incheon Paik, On-line Cost-aware Workflow Allocation in Heterogeneous Computing Environments, Proceedings of IEEE 12th International Symposium on Embedded Multicore/Many-core Systems-on-Chip (MCSOC 2018), Hanoi, Vietnam, Sep. 2018.
5. Rupasingha A. H. M. Rupasingha, Incheon Paik, Improving Service Recommendation by Alleviating the Sparsity with a Novel Ontology-based Clustering, Proceedings on IEEE International Conference on Web Service 2018, San Francisco, USA, July, 2018.
6. Kazuki Omine, Incheon Paik, Classification of Taxonomical Relationship by Word Embedding and Wedge Product, Proceedings on IEEE International Conference on Cognitive Computing 2018, San Francisco, USA, July, 2018.
7. T. H. Akila S. Siriweera, Incheon Paik, ConstraintDriven Dynamic Workflow for Automation of Big Data Analytics based on Graph Plan,Proceedings on IEEE International Conference on Web Service 2017,Hawaii, U.S.A, June-July, 2017.
8. T. H. Akila S. Siriweera, Incheon Paik, QoS and Customizable Transactionaware Selection for Big Data Analytics, Proceedings on IEEE International Conference on Service Computing 2017,Hawaii, U.S.A, June-July, 2017.
9. Yutaka Koshiba, Incheon Paik, Wuhui Chen, Fast Social Service Network Construction using Map-Reduce for Efficient Service Discovery, Proceedings on IEEE International Conference on Service Computing 2016, San Francisco, U.S.A, June-July, 2016.
10. Yuji Ishizuka, Wuhui Chen, Incheon Paik, Workflow Transformation for Real-Time Big Data Processing, Proceedings on IEEE International Conference on Big Data Congress 2016, San Francisco, U.S.A, June-July, 2016.