Page 153 - My FlipBook
P. 153
Associate Research Fellow 王建民 研
究
Chien-Min Wang 人
員
Ph.D., Electrical Engineering, National Taiwan University, Taiwan Faculty
T +886-2-2788-3799 ext. 1703 E cmwang@iis.sinica.edu.tw
F +886-2-2782-4814 W wcmwwwa.inisg.sinica.edu.tw/pages/pages/
・ Assistant Research Fellow, Institute of Information Science, Academia Sinica (1991-1995)
・ Associate Research Fellow, Institute of Information Science, Academia Sinica
(1996-present)
Research Description
My current research interests include cloud computing, services computing, and human-centered computing. For cloud computing, we aim
at e cient and scalable processing of huge datasets. We proposed the design pattern called two-phase data processing to allow dependence
within a set of input key-value pairs and enable MapReduce to exploit coarse-grained parallelism. We also proposed a solution for large-scale
generalized su x array (GSA) construction with MapReduce and an in-memory data store. It can construct GSA with a 4-fold larger input on
the same hardware system, indicating better scalability than the original method.
For services computing, we focus on the modeling and forecasting of QoS and workload of cloud services. Currently, several research works
are ongoing, including (1) a comprehensive survey of current time-aware QoS forecasting research; (2) a long-term collection and profound
analysis of a large-scale time-aware dynamic QoS dataset; (3) an empirical study to cloud workload forecasting problem; and (4) an improved
genetic programming (GP)-based QoS time series forecasting approach.
For human-centered computing, we focus on intelligent context-aware services with wearable devices. A human centered computing system
should have three abilities: understanding the context about the user, providing the service that makes the lives better, and interacting with
human naturally through perception. We studied activity recognition technology and presented a personalized and real-time prototyping
solution on smart glasses. We also studied gesture recognition technology and introduced a novel TV control simulation system that
recognizes hand gestures and track hand joints. Based on the result of context recognition, context-aware services can then perform
appropriate actions and provide the desired information to the users.
1. Yang Syu, Chien-Min Wang, and Yong-Yi Fanjiang, "Modeling Publications Brochure 2020
and Forecasting of Time-aware Dynamic QoS Attributes for
Cloud Services," IEEE Transactions on Network and Service 6. Jan-Jan Wu, Shu-Fan Shih, Hsiangkai Wang, Pangfeng Liu,
Management, Vol. 16, No. 1, pp. 56-71, March 2019. and Chien-Min Wang, "QoS-aware Replica Placement for Grid
Computing," Concurrency and Computation: Practice and
2. Yang Syu and Chien-Min Wang, "An Empirical Investigation Experience, pp. 193-213, Vol. 24, No. 3, March 2012.
of Real-World QoS of Web Services," Proceeding of the 16th
International Conference on Services Computing, Lecture Notes 7. Chien-Min Wang, Hsi-Min Chen, Chun-Chen Hsu, and Jonathan
in Computer Science, pages 48-65, June 2019. Lee, "Dynamic Resource Selection Heuristics for a Non-reserved
Bidding-based Grid Environment," Future Generation Computer
3. Yueh Wu and Chien-Ming Wang, "Applying Hand Gestures Systems, Vol. 26, No. 2, pp. 183-197, February 2010.
Recognition and Joints Tracking to TV Controller with CNN
and Convolutional Pose Machine," Proceeding of the 24th 8. Jan-Jan Wu, Yi-Fang Lin, Da-Wei Wang, and Chien-Min Wang,
International Conference on Pattern Recognition," Beijing, China, "Optimizing Server Placement for Parallel I/O in Switch-based
August 2018. Clusters," Journal of Parallel and Distributed Computing, Vol. 69,
No. 3, pp. 266-281, March 2009.
4. Hsiang-Huang Wu and Chien-Min Wang, "Generalization
of Large-Scale Data Processing in one MapReduce job for 9. Chien-Min Wang, Chun-Chen Hsu, Pangfeng Liu, Hsi-Min Chen,
Coarse-Grained Parallelism," International Journal of Parallel and Jan-Jan Wu, "Optimizing Server Placement in Hierarchical
Programming, Vol. 45, No. 4, pp. 797-826, August 2017. Grid Environments," The Journal of Supercomputing, pp. 267-
282, Vol. 42, No. 3, December 2007.
5. Ding-Yong Hong, Jan-Jan Wu, Pen-Chung Yew, Wei-Chung Hsu,
Chun-Chen Hsu, Pangfeng Liu, Chien-Min Wang, and Yeh-Ching 10. Yi-Fang Lin, Chien-Min Wang, and Jan-Jan Wu, "Optimizing I/
Chung, "Efficient and Retargetable Dynamic Binary Translation O Server Placement for Parallel I/O on Switch-Based Irregular
on Multicores," IEEE Transactions on Parallel and Distributed Networks," The Journal of Supercomputing, pp. 201-217, Vol. 36,
Systems, Vol. 25, No. 3, pp. 622-632, February 2014. No. 3, June 2006.
151
究
Chien-Min Wang 人
員
Ph.D., Electrical Engineering, National Taiwan University, Taiwan Faculty
T +886-2-2788-3799 ext. 1703 E cmwang@iis.sinica.edu.tw
F +886-2-2782-4814 W wcmwwwa.inisg.sinica.edu.tw/pages/pages/
・ Assistant Research Fellow, Institute of Information Science, Academia Sinica (1991-1995)
・ Associate Research Fellow, Institute of Information Science, Academia Sinica
(1996-present)
Research Description
My current research interests include cloud computing, services computing, and human-centered computing. For cloud computing, we aim
at e cient and scalable processing of huge datasets. We proposed the design pattern called two-phase data processing to allow dependence
within a set of input key-value pairs and enable MapReduce to exploit coarse-grained parallelism. We also proposed a solution for large-scale
generalized su x array (GSA) construction with MapReduce and an in-memory data store. It can construct GSA with a 4-fold larger input on
the same hardware system, indicating better scalability than the original method.
For services computing, we focus on the modeling and forecasting of QoS and workload of cloud services. Currently, several research works
are ongoing, including (1) a comprehensive survey of current time-aware QoS forecasting research; (2) a long-term collection and profound
analysis of a large-scale time-aware dynamic QoS dataset; (3) an empirical study to cloud workload forecasting problem; and (4) an improved
genetic programming (GP)-based QoS time series forecasting approach.
For human-centered computing, we focus on intelligent context-aware services with wearable devices. A human centered computing system
should have three abilities: understanding the context about the user, providing the service that makes the lives better, and interacting with
human naturally through perception. We studied activity recognition technology and presented a personalized and real-time prototyping
solution on smart glasses. We also studied gesture recognition technology and introduced a novel TV control simulation system that
recognizes hand gestures and track hand joints. Based on the result of context recognition, context-aware services can then perform
appropriate actions and provide the desired information to the users.
1. Yang Syu, Chien-Min Wang, and Yong-Yi Fanjiang, "Modeling Publications Brochure 2020
and Forecasting of Time-aware Dynamic QoS Attributes for
Cloud Services," IEEE Transactions on Network and Service 6. Jan-Jan Wu, Shu-Fan Shih, Hsiangkai Wang, Pangfeng Liu,
Management, Vol. 16, No. 1, pp. 56-71, March 2019. and Chien-Min Wang, "QoS-aware Replica Placement for Grid
Computing," Concurrency and Computation: Practice and
2. Yang Syu and Chien-Min Wang, "An Empirical Investigation Experience, pp. 193-213, Vol. 24, No. 3, March 2012.
of Real-World QoS of Web Services," Proceeding of the 16th
International Conference on Services Computing, Lecture Notes 7. Chien-Min Wang, Hsi-Min Chen, Chun-Chen Hsu, and Jonathan
in Computer Science, pages 48-65, June 2019. Lee, "Dynamic Resource Selection Heuristics for a Non-reserved
Bidding-based Grid Environment," Future Generation Computer
3. Yueh Wu and Chien-Ming Wang, "Applying Hand Gestures Systems, Vol. 26, No. 2, pp. 183-197, February 2010.
Recognition and Joints Tracking to TV Controller with CNN
and Convolutional Pose Machine," Proceeding of the 24th 8. Jan-Jan Wu, Yi-Fang Lin, Da-Wei Wang, and Chien-Min Wang,
International Conference on Pattern Recognition," Beijing, China, "Optimizing Server Placement for Parallel I/O in Switch-based
August 2018. Clusters," Journal of Parallel and Distributed Computing, Vol. 69,
No. 3, pp. 266-281, March 2009.
4. Hsiang-Huang Wu and Chien-Min Wang, "Generalization
of Large-Scale Data Processing in one MapReduce job for 9. Chien-Min Wang, Chun-Chen Hsu, Pangfeng Liu, Hsi-Min Chen,
Coarse-Grained Parallelism," International Journal of Parallel and Jan-Jan Wu, "Optimizing Server Placement in Hierarchical
Programming, Vol. 45, No. 4, pp. 797-826, August 2017. Grid Environments," The Journal of Supercomputing, pp. 267-
282, Vol. 42, No. 3, December 2007.
5. Ding-Yong Hong, Jan-Jan Wu, Pen-Chung Yew, Wei-Chung Hsu,
Chun-Chen Hsu, Pangfeng Liu, Chien-Min Wang, and Yeh-Ching 10. Yi-Fang Lin, Chien-Min Wang, and Jan-Jan Wu, "Optimizing I/
Chung, "Efficient and Retargetable Dynamic Binary Translation O Server Placement for Parallel I/O on Switch-Based Irregular
on Multicores," IEEE Transactions on Parallel and Distributed Networks," The Journal of Supercomputing, pp. 201-217, Vol. 36,
Systems, Vol. 25, No. 3, pp. 622-632, February 2014. No. 3, June 2006.
151
