Horng-Lin Shieh

Modified particle swarm optimization algorithm with simulated annealing behavior and its numerical verification

The hybrid algorithm that combined particle swarm optimization with simulated annealing behavior (SA-PSO) is proposed in this paper. The SA-PSO algorithm takes both of the advantages of good solution quality in simulated annealing and fast searching ability in particle swarm optimization. As stochastic optimization algorithms are sensitive to their parameters, proper procedure for parameters selection is introduced in this paper to improve solution quality. To verify the usability and effectiveness of the proposed algorithm, simulations are performed using 20 different mathematical optimization functions with different dimensions. The comparative works have also been conducted among different algorithms under the criteria of quality of the solution, the efficiency of searching for the solution and the convergence characteristics. According to the results, the SA-PSO could have higher efficiency, better quality and faster convergence speed than compared algorithms.

Robust neural-fuzzy method for function approximation

The back propagation (BP) algorithm for function approximation is multi-layer feed-forward perceptions to learn parameters from sampling data. The BP algorithm uses the least squares method to obtain a set of weights minimizing the object function. One of main issues on the BP algorithm is to deal with data sets having variety of data distributions and bound with noises and outliers. In this paper, in order to overcome the problems of function approximation for a nonlinear system with noise and outliers, a robust fuzzy clustering method is proposed to greatly mitigate the influence of noise and outliers and then a fuzzy-based data sifter (FDS) is used to partition the nonlinear systempsilas domain into several piecewise linear subspaces to be represented by neural networks. Two experiments are illustrated and these results have shown that the proposed approach has good performance in various kinds of data domains with data noise and outliers.

Robust validity index for a modified subtractive clustering algorithm

A novel robust validity index is proposed for subtractive clustering (SC) algorithm. Although the SC algorithm is a simple and fast data clustering method with robust properties against outliers and noise; it has two limitations. First, the cluster number generated by the SC algorithm is influenced by a given threshold. Second, the cluster centers obtained by SC are based on data that have the highest potential values but may not be the actual cluster centers. The validity index is a function as a measure of the fitness of a partition for a given data set. To solve the first problem, this study proposes a novel robust validity index that evaluates the fitness of a partition generated by SC algorithm in terms of three properties: compactness, separation and partition index. To solve the second problem, a modified algorithm based on distance relations between data and cluster centers is designed to ascertain the actual centers generated by the SC algorithm. Experiments confirm that the preferences of the proposed index outperform all others.

A Robust Fuzzy Clustering Approach And Its Application To Principal Component Analysis

Abstract A robust fuzzy clustering approach is proposed to simplify the task of principal component analysis (PCA) by reducing the data complexity of an image. This approach performs well on function curves and character images that not only have loops, shazp corners and intersections but also include data with noise and outliers. The proposed approach is composed of two phases: fustly, input data are clustered using the proposed distance analysis to get good and reasonable number of clusters; secondly, the input data are further re-clustered by the proposed robust fuzzy c-means (RFCM) to mitigate the influence of noise and outlier data so that a good result of principal components can be found. Experimental results have shown the approach works well on PCA for both curves and images despite their input data sets include loops, corners, intersections, noise and outliers.

Artificial classification system of aging period based on insulation status of transformers

The classification system to identify the aging period of insulation status for cast-resin transformer through current impulse method of partial discharge is proposed in this paper. An effectively insulating classification technology plays an important role to enhance the system operating reliability. Since PD is a well know evidence of insulation degrading, a series of high voltage test with acceleration aging process to collect PD signals for classification system are conducted in the lab. Some selected statistical PD features instead of waveform are then extracted from these experimental PD signals as input data of the classification system. Also, an artificial neural network that combined particle swarm optimization is presented as the effectively classification tool. To demonstrate the effectiveness and feasibility of the proposed approach, the artificial classification system is applied on both noisy and noiseless circumstance with promising results.

RFID medicine management system

This study proposes a framework of medicine management system based on the Radio Frequency Identification (RFID). The heavy workloads of the hospital often result in that the nurses give patients the wrong medicine. This situation leads to the patient injury, and even death. In order to improve the quality of health care, this paper integrates the RFID, network and database techniques to develop a graphical medicine management system. In the proposed system, each patient has a RFID tag and each kind of medicine also is encoded to a RFID number. The digital patient information forms contain the medicinal information of each patient. When a nurse gives medicine to a patient, he or she must check the patients RFID tag and the medicinal number to avoid the situation of taking wrong medicines.

A robust fuzzy CMAC for function approximation

This paper proposes a new robust fuzzy CMAC algorithm for function approximation. The advantages of CMAC neural network are fast learning convergence, capable of mapping nonlinear functions quickly due to its local generalization of weight updating. In this paper, in order to overcome the problems of function approximation for a nonlinear system with noise and outliers, a robust fuzzy clustering method is proposed to greatly mitigate the influence of noise and outliers and then a new CMAC learning process used to learn the nonlinear systems features for function approximation.

An Emergency Care System Using RFID and Zigbee Techniques

In this study a RFID technology to assist medical care personnel with ward round and nursing is proposed to increase the management efficiency and reduce the human caused careless mistakes. We use the RFID tag, ZigBee technology, and long-range wireless communication to build an emergency care system. The designed model consists of an active RFID tag, an active RFID-ZigBee positioning reader (including Router) and wireless network module. Because using wireless transmission, this architecture does not require any communication cable. When the router is placed in the corresponding position, the patient can be located, making this construction relatively simple.

RFID restaurant POS system

In order to reduce the labor cost, improve the service quality, and achieve energy saving and carbon reduction for restaurants, this paper integrated a RFID, server and graphical man-machine interface to develop an ordering system for restaurants. The system can improve the service efficiency, lower the operating cost, and reduce environmental burden.

A new framework of fuzzy clustering algorithm

In this paper, a novel data clustering algorithm based on the subtractive clustering (SC) algorithm and a new validity index are proposed. The SC algorithm is a simple method for data clustering; however, it has two problems which must be overcome. The first problem is such that the cluster centers found by SC are taken from data with the highest potential values, but that this data may not be the real cluster centers. The second problem is such that the cluster number generated by the SC algorithm is influenced by a predefined parameter. The proposed algorithm is based on distance relations between data and centers and is designed to ascertain the real centers generated by the SC algorithm. In addition, a novel robust cluster index is proposed to identify the real cluster number generated by SC algorithm.