Chenn-Jung Huang

Application of wrapper approach and composite classifier to the stock trend prediction

The research on the stock market prediction has been more popular in recent years. Numerous researchers tried to predict the immediate future stock prices or indices based on technical indices with various mathematical models and machine learning techniques such as artificial neural networks (ANN), support vector machines (SVM) and ARIMA models. Although some researches in the literature exhibit satisfactory prediction achievement when the average percentage error and root mean square error are used as the performance metrics, the prediction accuracy of whether stock market goes or down is seldom analyzed. This paper employs wrapper approach to select the optimal feature subset from original feature set composed of 23 technical indices and then uses voting scheme that combines different classification algorithms to predict the trend in Korea and Taiwan stock markets. Experimental result shows that wrapper approach can achieve better performance than the commonly used feature filters, such as @g^2-Statistic, Information gain, ReliefF, Symmetrical uncertainty and CFS. Moreover, the proposed voting scheme outperforms single classifier such as SVM, kth nearest neighbor, back-propagation neural network, decision tree, and logistic regression.

Frog classification using machine learning techniques

An automatic frog sound identification system is developed in this work to provide the public to easily consult online. The sound samples are first properly segmented into syllables. Then three features, spectral centroid, signal bandwidth and threshold-crossing rate, are extracted to serve as the parameters for the frog sound classification. Two well-known classifiers, kNN and SVM, are adopted to recognize the frog species based on the three extracted features. The experimental results show that the average classification accuracy rate can be up to 89.05% and 90.30% for kNN and SVM classifiers, respectively. The effectiveness of the proposed on-line recognition system is thus verified.

Clustered defect detection of high quality chips using self-supervised multilayer perceptron

During electrical testing, each die on a wafer must be tested to determine whether it functions as originally designed. When defects, including scratches, stains or localized failed patterns, are clustered on the wafer, the tester may not detect all of the defective dies in the flawed area. A testing factory must assign a few workers to check the wafers and hand-mark the defective dies in the flawed region or close to the flawed region, to ensure that no defective die is present in the final assembly. This work presents an automatic wafer-scale defect cluster identifier that uses a multilayer perceptron to detect the defect cluster and mark all of the defective dies. The proposed identifier is compared with an existing tool used in industry. The experimental results confirm that the proposed algorithm is more effective at identifying defects and outperforms the present approach.

Implementation of call admission control scheme in next generation mobile communication networks using particle swarm optimization and fuzzy logic systems

In the present and next generation wireless networks, cellular system remains the major method of telecommunication infrastructure. Since the characteristic of the resource constraint, call admission control is required to address the limited resource problem in wireless network. The call dropping probability and call blocking probability are the major performance metrics for quality of service (QoS) in wireless network. Many call admission control mechanisms have been proposed in the literature to decrease connection dropping probability for handoffs and new call blocking probability in cellular communications. In this paper, we proposed an adaptive call admission control and bandwidth reservation scheme using fuzzy logic control concept to reduce the forced termination probability of multimedia handoffs. Meanwhile, we adopt particle swarm optimization (PSO) technique to adjust the parameters of the membership functions in the proposed fuzzy logic systems. The simulation results show that the proposed scheme can achieve satisfactory performance when performance metrics are measured in terms of the forced termination probability for the handoffs, the call blocking probability for the new connections and bandwidth utilization.

Admission control schemes for proportional differentiated services enabled internet servers using machine learning techniques

Abstract A widely existing problem in contemporary web servers is the unpredictability of response time. Owing to long response delay, revenues of the enterprises are substantially reduced due to many aborted e-commerce transactions. Recently, researchers have been addressing different admission control schemes of differentiated service for web servers to complement the Internet differentiated services model and thereby provide QoS support to the users of the World Wide Web. However, most of these admission control mechanisms do not guarantee the QoS requirements of all admitted clients under bursty workload. Although an Internet service model called proportional differentiated service is enabled in web servers to improve the QoS guarantee predicament in the literature, it still exists some impracticable assumptions and incompatible problems with the current Internet protocols. In this paper, we propose two algorithms for admission control and traffic scheduler schemes of the web server under proportional differentiated service, wherein a time series predictor is embedded to estimate the traffic load of the client in the next measurement time period. Support vector regression and particle swarm optimization techniques are used to implement the time series predictor based on the reports of successful prediction in the literature. The experimental results reveal that the proposed schemes can realize proportional delay differentiation service in multiclass Web server effectively. Meanwhile, the small computation overhead of particle swarm optimization verifies the feasibility of this machine learning technique in the real-time applications such as the admission control of the Internet server as illustrated in this work.

A mobility-aware link enhancement mechanism for vehicular ad hoc networks

With the growth up of internet in mobile commerce, researchers have reproduced various mobile applications that vary from entertainment and commercial services to diagnostic and safety tools. Mobility management has widely been recognized as one of the most challenging problems for seamless access to wireless networks. In this paper, a novel link enhancement mechanism is proposed to deal with mobility management problem in vehicular ad hoc networks. Two machine learning techniques, namely, particle swarm optimization and fuzzy logic systems, are incorporated into the proposed schemes to enhance the accuracy of prediction of link break and congestion occurrence. The experimental results verify the effectiveness and feasibility of the proposed schemes.

QoS-aware roadside base station assisted routing in vehicular networks

The transmission technology for intelligent transportation systems can be typically classified into two categories, namely, road-to-vehicle communication (RVC) and inter-vehicle communication (IVC). RVCs perform the information communication service offer from road to vehicle whereas the IVCs perform the information communication through vehicles. This work proposes quality of service (QoS)-aware roadside base station assisted routing mechanisms to establish a routing path in IVC with the assistance of roadside base station. A link failure prevention mechanism is employed to effectively construct alternative routing path required by the volatile network topology in vehicular Ad hoc networks. Besides, a bandwidth consumption predictor is presented to avoid dropping packets owing to inadequate bandwidth during handoffs. A neural network with fast learning algorithm is adopted as the core module for estimating the parameters used in the proposed schemes. Simulation results demonstrate the effectiveness and feasibility of the proposed work.

APPLICATIONS OF DATA MINING TECHNIQUES TO AUTOMATIC FROG IDENTIFICATION

An intelligent frog call identifier is developed in this work to provide the public with easy online consultation. The raw frog call samples are first filtered by noise removal, high frequency compensation, and discrete wavelet transform techniques in that order. An adaptive end-point detection segmentation algorithm is proposed to effectively separate the individual syllables from the noise. Eight features, including spectral centroid, signal bandwidth, spectral roll-off, threshold-crossing rate, delta spectrum magnitude, spectral flatness, average energy, and mel-frequency cepstral coefficients are extracted and serve as the input parameters of the classifier. Three well-known classifiers, the kth nearest neighboring, a backpropagation neural network, and a naive Bayes classifier, are employed in this work for comparison. A series of experiments were conducted to measure the outcome performance of the proposed work. Experimental results show that the recognition rate of the k-nearest neighbor classifier with the parameters of mel-frequency cepstral coefficients can achieve up to 93.81%. The effectiveness of the proposed frog call identifier is thus verified.