Ming-Yuan Cho

Optimization and Implementation of a Load Control Scheduler Using Relaxed Dynamic Programming for Large Air Conditioner Loads

This paper presents the optimization and implementation of a relaxed dynamic programming (RDP) algorithm to generate a daily control scheduling for optimal or near-optimal air conditioner loads (ACLs). The conventional control mode for ACL includes demand control, cycling control, and timer control, to assist customers for saving electricity costs. The proposed load control scheduler (LCS) scheme supports any combination of these three control types to save costs optimally during the dispatch period. Microprocessor hardware techniques were applied to carry out the proposed strategy for realistic application. The Visual C++ language was adopted as the developing tool to carry out the proposed work. Field tests of controlling air conditioners located in the campus of National Kaohsiung University of Applied Sciences, Kaohsiung, Taiwan, were tested on-site to demonstrate the effectiveness of the proposed load control strategy. The results show that interruptible load scheduling can reduce the system load effectively, and the load capacity reduced by the proposed load control strategy follows closely the trajectory of the peak load.

Power transformer fault diagnosis using support vector machines and artificial neural networks with clonal selection algorithms optimization

This paper presents an innovative method based on Artificial Neural Network (ANN) and multi-layer Support Vector Machine (SVM) for the purpose of fault diagnosis of power transformers. A clonal selection algorithm (CSA) based encoding technique is applied to improve the accuracy of classification, which demonstrated in the literature for the first time. With features and RBF kernel parameters selection to predict incipient fault of power transformer improve the accuracy of classification systems and the generalization performance. The proposed approach is distinguished by removing redundant input features that may be confusing the classifier and optimizing the selection of kernel parameters. Simulation results of practice data demonstrate the effectiveness and high efficiency of the proposed approach, which makes operation faster and also increases the accuracy of the classification.

Fault Diagnosis of Power Transformers Using SVM/ANN with Clonal Selection Algorithm for Features and Kernel Parameters Selection

For the purpose of fault diagnosis of power transformers, a novel approach based on artificial neural network (ANN) and multi-layer support vector machine (SVM) is presented in the paper. The proposed approach is distinguished by features and kernel parameters selection using clonal selection algorithms (CSA). It is capable of filtering out irrelevant input features, leading to improve prediction accuracy. As revealed in the experimental results, the proposed approach outperforms previous ones in both classification accuracy and computational efficiency

Dosimetric advantages of generalised equivalent uniform dose-based optimisation on dose–volume objectives in intensity-modulated radiotherapy planning for bilateral breast cancer

OBJECTIVE We compared and evaluated the differences between two models for treating bilateral breast cancer (BBC): (i) dose-volume-based intensity-modulated radiation treatment (DV plan), and (ii) dose-volume-based intensity-modulated radiotherapy with generalised equivalent uniform dose-based optimisation (DV-gEUD plan). METHODS The quality and performance of the DV plan and DV-gEUD plan using the Pinnacle(3) system (Philips, Fitchburg, WI) were evaluated and compared in 10 patients with stage T2-T4 BBC. The plans were delivered on a Varian 21EX linear accelerator (Varian Medical Systems, Milpitas, CA) equipped with a Millennium 120 leaf multileaf collimator (Varian Medical Systems). The parameters analysed included the conformity index, homogeneity index, tumour control probability of the planning target volume (PTV), the volumes V(20 Gy) and V(30 Gy) of the organs at risk (OAR, including the heart and lungs), mean dose and the normal tissue complication probability. RESULTS Both plans met the requirements for the coverage of PTV with similar conformity and homogeneity indices. However, the DV-gEUD plan had the advantage of dose sparing for OAR: the mean doses of the heart and lungs, lung V(20) (Gy), and heart V(30) (Gy) in the DV-gEUD plan were lower than those in the DV plan (p<0.05). CONCLUSIONS A better result can be obtained by starting with a DV-generated plan and then improving it by adding gEUD-based improvements to reduce the number of iterations and to improve the optimum dose distribution. Advances to knowledge The DV-gEUD plan provided superior dosimetric results for treating BBC in terms of PTV coverage and OAR sparing than the DV plan, without sacrificing the homogeneity of dose distribution in the PTV.

Particle swarm optimization-based SVM for incipient fault classification of power transformers

A successful adoption and adaptation of the particle swarm optimization (PSO) algorithm is presented in this paper. It improves the performance of Support Vector Machine (SVM) in the classification of incipient faults of power transformers. A PSO-based encoding technique is developed to improve the accuracy of classification. The proposed scheme is capable of removing misleading input features and, optimizing the kernel parameters at the same time. Experiments on real operational data had demonstrated the effectiveness and efficiency of the proposed approach. The power system industry can benefit from our system in both the accelerated operational speed and the improved accuracy in the classification of incipient faults.

Relaxed Dynamic Programming for Constrained Economic Direct Loads Control Scheduling

We study the problem of dynamically scheduling a set of period stage control tasks controlling a set of large air conditioner loads (ACLs). To be able to solve the scheduling problem for realistic on-line cases, we utilize the technique of relaxed dynamic programming (RDP) algorithm to generate an optimal or near optimal daily control scheduling for ACLs with relaxing bounds. Field tests of controlling the ACLs located in the campus are tested on-site to demonstrate the effectiveness of the proposed load control strategy.

Precise segmentation rendering for medical images based on maximum entropy processing

Precision is definitely required in medical treatments, however, most three-dimensional (3-D) renderings of medical images lack for required precision. This study aimed at the development of a precise 3-D image processing method to discriminate clearly the edges. Since conventional Computed Tomography (CT), Positron Emission Tomography (PET), or Magnetic Resonance Imaging (MRI) medical images are all slice-based stacked 3-D images, one effective way to obtain precision 3-D rendering is to process the sliced data with high precision first then to stack them together carefully to reconstruct a desired 3-D image. A recent two-dimensional (2-D) image processing method known as the entropy maximization procedure proposed to combine both the gradient and the region segmentation approaches to achieve a much better result than either alone seemed to be our best choice to extend it into 3-D processing. Three examples of CT scan data of medical images were used to test the validity of our method. We found our 3-D renderings not only achieved the precision we sought but also has many interesting characteristics that shall be of significant influence to the medical practice.

Particle Swarm Optimization-Based SVM Application: Power Transformers Incipient Fault Syndrome Diagnosis

Based on statistical learning theory, support vector machine (SVM) has been well recognized as a powerful computational tool for problems with nonlinearity had high dimensionalities. In this paper, we present a successful adoption of the particle swarm optimization (PSO) algorithm to improve the performances of SVM classifier for the purpose of incipient faults syndrome diagnosis of power transformers. A PSO-based encoding technique is applied to improve the accuracy of classification. The proposed scheme removes irreverent input features that may be confusing the classifier and optimizes the kernel parameters simultaneously. Experiments on real operational data demonstrated the effectiveness and high efficiency of the proposed approach which make operation faster and also increase the accuracy of the classification

Boundary Finding Combining Wavelet and Markov Random Field Segmentation Based on Maximum Entropy Theory

Boundary finding is one of the most important aspects in medical image processing. Wavelet edge detector becomes popular in recent years but is known to degrade in noisy situations. This study aimed to develop an advance precision image segmentation algorithm to enhance the blurred edges clearly for medical target definition. A new method of combining wavelet analysis with Markov Random Field (RBF) segmentations has been developed to improve the performance of boundary finding. We found that the resulting boundary is indeed much superior than using the wavelets or RBF segmentations performed alone. Experimental results of a magnetic resonance of imaging (MRI) proved the method shall have important practical values.

Diagnosis of incipient fault of power transformers using SVM with clonal selection algorithms optimization

In this study we explore the feasibility of applying Artificial Neural Networks (ANN) and Support Vector Machines (SVM) to the prediction of incipient power transformer faults. A clonal selection algorithm (CSA) is introduced for the first time in the literature to select optimal input features and RBF kernel parameters. CSA is shown to be capable of improving the speed and accuracy of classification systems by removing redundant and potentially confusing input features, and of optimizing the kernel parameters simultaneously. Simulation results on practice data demonstrate the effectiveness and high efficiency of the proposed approach.