Yen-Chieh Ouyang

Prof. Dr. Yen-Chieh Ouyang

orcid

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 August 2014 in IEEE Transactions on Cloud Computing
Verified
Journal Article
Closed access
YCYi-Ju Chiang
Yi-Ju Chiang
YOYen-Chieh Ouyang
Yen-Chieh Ouyang
CHChing-Hsien (Robert) Hsu
Ching-Hsien (Robert) Hsu
Cloud computing is a new paradigm for delivering remote computing resources through a network. However, achieving an energy-efficiency control and simultaneously satisfying a performance guarantee have become critical issues for cloud providers. In this paper, three power-saving policies are implemented in cloud systems to mitigate server idle power. The challenges of controlling service rates and applying the N-policy to optimize operational cost within a performance guarantee are first studied. A cost function has been developed in which the costs of power consumption, system congestion and server startup are all taken into consideration. The effect of energy-efficiency controls on response times, operating modes and incurred costs are all demonstrated. Our objectives are to find the optimal service rate and mode-switching restriction, so as to minimize cost within a response time guarantee under varying arrival rates. An efficient green control (EGC) algorithm is first proposed for solving constrained optimization problems and making costs/performances tradeoffs in systems with different power-saving policies. Simulation results show that the benefits of reducing operational costs and improving response times can be verified by applying the power-saving policies combined with the proposed algorithm as compared to a typical system under a same performance guarantee.

16 May 2008 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
YOYen-Chieh Ouyang
Yen-Chieh Ouyang
HCHsian-Min Chen
Hsian-Min Chen
JCJyh-Wen Chai
Jyh-Wen Chai
CCClayton Chi-Chang Chen
Clayton Chi-Chang Chen
SPSek-Kwong Poon
Sek-Kwong Poon
CCChein-I Chang
Chein-I Chang
Independent component analysis (ICA) has found great promise in magnetic resonance (MR) image analysis. Unfortunately, two key issues have been overlooked and not investigated. One is the lack of MR images to be used to unmix signal sources of interest. Another is the use of random initial projection vectors by ICA, which causes inconsistent results. In order to address the first issue, this paper introduces a band-expansion process (BEP) to generate an additional new set of images from the original MR images via nonlinear functions. These newly generated images are then combined with the original MR images to provide sufficient MR images for ICA analysis. In order to resolve the second issue, a prioritized ICA (PICA) is designed to rank the ICA-generated independent components (ICs) so that MR brain tissue substances can be unmixed and separated by different ICs in a prioritized order. Finally, BEP and PICA are combined to further develop a new ICA-based approach, referred to as PICA-BEP to perform MR image analysis.

30 October 2014 in IEEE Transactions on Services Computing
Verified
Journal Article
Closed access
YCYi-Ju Chiang
Yi-Ju Chiang
YOYen-Chieh Ouyang
Yen-Chieh Ouyang
CHChing-Hsien Hsu
Ching-Hsien Hsu
Cloud computing is an innovative service platform to offer diverse resources such as infrastructure, platform and software as services. However, one challenging aspect of such a service is the impatient user threat, which directly leads to numerous negative impacts such as poor throughput, unpredictable workload and waste of resources. In this paper, the problems of conducting system controls in a cost-effective way and simultaneously satisfying performance guarantees are first studied. System losses are analyzed according to the related performance factors and waiting buffer sizes. A cost model is developed to address a performances/cost tradeoff issue in which the user balking, reneging, system blocking and resources provisioning are all taken into account. The relationship between system controls and throughput variations in a multi-servers system with a finite buffer is demonstrated. A proposed policy combined with a heuristic algorithm allows cloud providers to control the service rate and buffer size within a system loss guarantee by solving constrained optimization problems. Simulation results show that more cost-saving and system throughput enhancement can be verified as compared to a system without applying our policy.

1 January 2014 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
PDF file
YCYiju Chiang
Yiju Chiang
YOYen-Chieh Ouyang
Yen-Chieh Ouyang
Cloud computing realizes a utility computing paradigm by offering shared resources through an Internet‐based computing. However, how a system control can enhance profit and simultaneously satisfy the service level agreements (SLAs) has become one of the major interests for cloud providers. In this paper, a cloud server farm provided with finite capacity is modeled as an M/M/R/K queuing system. Revenue losses are estimated according to the system controls and impatient customer behaviors. Three important issues are solved in this paper. First, a profit function is developed in which both the system blocking loss and the user abandonment loss are evaluated in total revenue. A tradeoff between meeting system performances and reducing operating costs is conducted. Second, the effects of system capacity control and utilization on various performances of waiting time, loss probability, and final arrival rate are demonstrated. Finally, the proposed optimal profit control (OPC) policy allows a cloud provider to make the optimal decision in the number of servers and system capacity, so as to maximize profit. As compared to a system without applying the OPC policy, enhancing providers’ profit and improving system performances can be obtained.

3 May 2010 in EURASIP Journal on Advances in Signal Processing
Verified
Journal Article
Open access
PDF file
CYCheng-Yi Yu
Cheng-Yi Yu
YOYen-Chieh Ouyang
Yen-Chieh Ouyang
CWChuin-Mu Wang
Chuin-Mu Wang
CCChein-I Chang
Chein-I Chang
Contrast has a great influence on the quality of an image in human visual perception. A poorly illuminated environment can significantly affect the contrast ratio, producing an unexpected image. This paper proposes an Adaptive Inverse Hyperbolic Tangent (AIHT) algorithm to improve the display quality and contrast of a scene. Because digital cameras must maintain the shadow in a middle range of luminance that includes a main object such as a face, a gamma function is generally used for this purpose. However, this function has a severe weakness in that it decreases highlight contrast. To mitigate this problem, contrast enhancement algorithms have been designed to adjust contrast to tune human visual perception. The proposed AIHT determines the contrast levels of an original image as well as parameter space for different contrast types so that not only the original histogram shape features can be preserved, but also the contrast can be enhanced effectively. Experimental results show that the proposed algorithm is capable of enhancing the global contrast of the original image adaptively while extruding the details of objects simultaneously.

15 November 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
GLGui Chou Liang
Gui Chou Liang
YOYen-Chieh Ouyang
Yen-Chieh Ouyang
SDShu-Mei Dai
Shu-Mei Dai
The detection of rice leaf folder (RLF) infestation usually depends on manual monitoring, and early infestations cannot be detected visually. To improve detection accuracy and reduce human error, we use push-broom hyperspectral sensors to scan rice images and use machine learning and deep neural learning methods to detect RLF-infested rice leaves. Different from traditional image processing methods, hyperspectral imaging data analysis is based on pixel-based classification and target recognition. Since the spectral information itself is a feature and can be considered a vector, deep learning neural networks do not need to use convolutional neural networks to extract features. To correctly detect the spectral image of rice leaves infested by RLF, we use the constrained energy minimization (CEM) method to suppress the background noise of the spectral image. A band selection method was utilized to reduce the computational energy consumption of using the full-band process, and six bands were selected as candidate bands. The following method is the band expansion process (BEP) method, which is utilized to expand the vector length to improve the problem of compressed spectral information for band selection. We use CEM and deep neural networks to detect defects in the spectral images of infected rice leaves and compare the performance of each in the full frequency band, frequency band selection, and frequency BEP. A total of 339 hyperspectral images were collected in this study; the results showed that six bands were sufficient for detecting early infestations of RLF, with a detection accuracy of 98% and a Dice similarity coefficient of 0.8, which provides advantages of commercialization of this field.