Browsing by Author "Wu, RC"

Now showing 1 - 18 of 18

A novel prosodic-information synthesizer based on recurrent fuzzy neural network for the Chinese TTS system
(2004-02-01)
Lin, CT
;
Wu, RC
;
Chang, JY
;
Liang, SF
;
電控工程研究所
In this paper, a new technique for the Chinese text-to-speech (TTS) system is proposed. Our major effort focuses on the prosodic information generation. New methodologies for constructing fuzzy rules in a prosodic model simulating human's pronouncing rules are developed. The proposed Recurrent Fuzzy Neural Network (RFNN) is a multilayer recurrent neural network (RNN) which integrates a Self-constructing Neural Fuzzy Inference Network (SONFIN) into a recurrent connectionist structure. The RFNN can be functionally divided into two,parts. The first part adopts the SONFIN as a prosodic model to explore the relationship between high-level linguistic features and prosodic information based on fuzzy inference rules. As compared to conventional neural networks, the SONFIN can always construct itself with an economic network size in high learning speed. The second part employs a five-layer network to generate all prosodic parameters by directly using the prosodic fuzzy rules inferred from the first part as well as other important features of syllables. The TTS system combined with the proposed method can behave not only sandhi rules but also the other prosodic phenomena existing in the traditional TTS systems. Moreover, the proposed scheme can even find out some new rules about prosodic phrase structure. The performance of the proposed RFNN-based prosodic model is verified by imbedding it into a Chinese TTS system with a Chinese monosyllable database based on the time-domain pitch synchronous overlap add (TD-PSOLA) method. Our experimental results show that the proposed RFNN can generate proper prosodic parameters including pitch means, pitch shapes, maximum energy levels, syllable duration, and pause duration. Some synthetic sounds are on-line available for demonstration.
Assessment of driver's driving performance and alertness using EEG-based fuzzy neural networks
(2005)
Lin, CT
;
Chen, YC
;
Wu, RC
;
Liang, SF
;
Huang, TY
Traffic fatalities in recent years have become a serious concern to our society. Accidents caused by drivers' drowsiness have a high fatality rate due to the decline of drivers' abilities in perception, recognition, and vehicle control abilities while sleepy. Preventing such an accident requires a technique for detecting, estimating, and predicting the level of alertness of a driver and a mechanism to maintain the driver's maximum performance of driving. This paper proposed a system that combines electroencephalogram (EEG) power spectra estimation, independent component analysis and fuzzy neural network models to estimate drivers' cognitive state in a dynamic virtual-reality-based driving environment. Experimental results show that the quantitative driving performance can be accurately and successfully estimated through analyzing driver's EEG signals by the proposed system.
Classification of driver's cognitive responses from EEG analysis
(2005)
Liang, SF
;
Lin, CT
;
Wu, RC
;
Huang, TY
;
Chao, WH
During the past years, the growing number of traffic fatalities has become an important issue in public security. In this paper, we develop a quantitative analysis for ongoing assessment of cognitive response by investigating the neurobiological brain dynamics in traffic-light experiments. A single-trial event-related-potential (ERP)-based fuzzy neural network (FNN) is applied to recognize different brain potentials stimulated by red/green/yellow traffic-light events. The system consists of a dynamic virtual-reality (VR)-based motion simulation platform, EEG signal detection and analysis units, and FNN-based classifier. The independent component analysis (ICA) algorithms are used to obtain noise-free ERP signals from the multi-channel EEG signals. A novel temporal filter is also proposed to solve time-alignment problems of ERP features and principle component analysis (PCA) is used to reduce dimension of features, which were then fed into a FNN classifier. Experimental results demonstrate the feasibility of detecting and analyzing multiple streams of ERP signals that organize operators' cognitive responses to task events. Comparisons of three kinds of linear and nonlinear classifiers show that our proposed FNN-based classifier can achieve a satisfactory and superior recognition rate (85%). The classification results can be further transformed as the control/biofeedback signals of intelligent driving systems.
Code acquisition in a class of time-varying channels
(1998)
Su, YT
;
Wu, RC
;
電信工程研究所
;
Institute of Communications Engineering
This paper presents a model for the code acquisition in a time-varying channel and evaluates the associated acquisition time statistics. We first use a finite-state Markov chain to represent the time-varying channel. Each channel state can have either a frequency-selective or a frequency-nonselective fading characteristic. This model is an unconstrained model as it does not take into account two time-parameters. The first time-parameters the "time unit" for the Markov channel, which has to be determined by the channel Doppler spread or its fading rate. The second time-parameter has to do with the detection structure. Incorporating the constraints imposed by these two time-parameters we discuss modifications of the unconstrained model, derive related statistics (e.g., probability distribution function or characteristic function) of the acquisition time and then provide numerical examples of the acquisition time performance.
Data mining application in customer relationship management of credit card business
(2005)
Wu, RC
;
Chen, RS
;
Chang, CC
;
Chen, JY
;
資訊管理與財務金融系註：原資管所+財金所
First, we classify the selected customers into clusters using RFM model to identify high-profit, gold customers. Subsequently, we carry out data mining using association rules algorithm. We measure the similarity, difference and modified difference of mined association rules based on three rules, i.e. Emerging Patten Rule, Unexpected Change Rule, and Added/Perished Rule. In the meantime, we use rule matching threshold to derive all types of rules and explore the rules with significant change based on the degree of change measured. In this paper, we employ data mining tools and effectively discover the current spending pattern of customers and trends of behavioral change, which will allow management to detect in a large database potential changes of customer preference, and provide as early as possible products and services desired by the customers to expand the clientele base and prevent customer attrition.
Design an intelligent CIM system based on data mining technology for new manufacturing processes
(2004)
Wu, RC
;
Chen, RS
;
Fan, CR
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
The purpose of this paper is to explain a specific intelligent CIM (computer integrated manufacturing) system by integrating the following five major subject areas: computer integrated manufacturing, data warehouse, online analytical processing (OLAP), data mining and artificial intelligence. The data mining system makes use of the decision tree algorithm and classification model in exploring the meaningful information, which is useful in the process of decision making. Subsequently, the rules discovered by the data mining system are expressed through the rule based knowledge presentation method of the expert system. The intelligent CIM system is applied to semiconductor packing factories and also point at the great fluctuation of DRAM (dynamic random access memory) prices. The results of this paper are the product yield, the manufacturing cycle time and the frequency of holding lot, which have been improved. The contribution can increase business competitiveness, reduce production cost, and promote the rate of available promise for order.
EEG-based drowsiness estimation for safety driving using independent component analysis
(2005-12-01)
Lin, CT
;
Wu, RC
;
Liang, SF
;
Chao, WH
;
Chen, YJ
Preventing accidents caused by drowsiness has become a major focus of active safety driving in recent years. It requires an optimal technique to continuously detect drivers' cognitive state related to abilities in perception, recognition, and vehicle control in (near-) real-time. The major challenges in developing such a system include: 1) the lack of significant index for detecting drowsiness and 2) complicated and pervasive noise interferences in a realistic and dynamic driving environment. In this paper, we develop a drowsiness-estimation system based on electroencephalogram (EEG) by combining independent component analysis (ICA), power-spectrum analysis, correlation evaluations, and linear regression model to estimate a driver's cognitive state when he/she drives a car in a virtual reality (VR)-based dynamic simulator. The driving error is defined as deviations between the center of the vehicle and the center of the cruising lane in the lane-keeping driving task. Experimental results demonstrate the feasibility of quantitatively estimating drowsiness level using ICA-based multistream EEG spectra. The proposed ICA-based method applied to power spectrum of ICA components can successfully (1) remove most of EEG artifacts, (2) suggest an optimal montage to place EEG electrodes, and estimate the driver's drowsiness fluctuation indexed by the driving performance measure. Finally, we present a benchmark study in which the accuracy of ICA-component-based alertness estimates compares favorably to scalp-EEG based.
EEG-based fuzzy neural network estimator for driving performance
(2004)
Wu, RC
;
Lin, CT
;
Liang, SF
;
Huang, TY
;
Jung, TP
Accidents caused by drivers' drowsiness have a high fatality rate because of the marked decline in the drivers' vehicle control abilities. Preventing accidents caused by drowsiness is highly desirable but requires techniques for continuously detecting, estimating, and predicting the level. of alertness of drivers. This paper proposes a brain-machine interface that combines electroencephalographic power spectrum estimation, principal. component analysis, and fuzzy neural networks to estimate/predict drivers' drowsiness level in a virtual-reality-based driving simulator. The driving performance is defined as deviation between the center of the vehicle and the center of the cruising lane. Our results demonstrated that the proposed method is feasible to accurately estimate quantitatively driving performance in a realistic driving simulator.
Estimating driving performance based on EEG spectrum analysis
(2005)
Lin, CT
;
Wu, RC
;
Jung, TP
;
Liang, SF
;
Huang, TY
The growing number of traffic accidents in recent years has become a serious concern to society. Accidents caused by driver's drowsiness behind the steering wheel have a high fatality rate because of the marked decline in the driver's abilities of perception, recognition, and vehicle control abilities while sleepy. Preventing such accidents caused by drowsiness is highly desirable but requires techniques for continuously detecting, estimating, and predicting the level of alertness of drivers and delivering effective feedbacks to maintain their maximum performance. This paper proposes an EEG-based drowsiness estimation system that combines electroencephalogram (EEG) log subband power spectrum, correlation analysis, principal component analysis, and linear regression models to indirectly estimate driver's drowsiness level in a virtual-reality-based driving simulator. Our results demonstrated that it is feasible to accurately estimate quantitatively driving performance, expressed as deviation between the center of the vehicle and the center of the cruising lane, in a realistic driving simulator.
Estimating driving performance based on EEG spectrum and fuzzy neural network
(2004)
Wu, RC
;
Lin, CT
;
Liang, SF
;
Huang, TY
;
Chen, YC
The growing number of traffic fatalities in recent years has become a serious concern to society. Accidents caused by drivers' drowsiness behind the steering wheel have a high fatality rate because of the marked decline in the drivers' abilities of perception, recognition! and vehicle control abilities while sleepy. Preventing accidents caused by drowsiness requires a technique for detecting, estimating, and predicting the level of alertness of a driver and a mechanism for maintaining his/her maximum performance. This paper describes a system that combines electroencephalographic (EEG) power spectrum estimation, principal component analysis, and fuzzy neural network model to estimate/predict drivers' drowsiness level in a driving simulator. Our results demonstrated that, for the first time, it is feasible to accurately estimate task performance, accurately estimate quantitatively measured driving performance, expressed as deviation between the center of the vehicle and the center of the cruising lane, in a realistic driving simulation.
Frequency acquisition and tracking for mobile LEO satellite communications
(1997)
Su, YT
;
Wu, RC
;
交大名義發表
;
電信工程研究所
;
National Chiao Tung University
A class of recursive frequency acquisition and tracking algorithms for use in high dynamic mobile low earth orbit (LEO) satellite communication systems is proposed. The underlying principle of these algorithms is to apply the least-squares method to the reconstructed phase trajectories to estimate and predict the received frequency variations (Doppler frequency, Doppler rate, etc.). We consider both additive white Gaussian noise (AWGN) and Rician fading channels and analyze the corresponding mean squared errors (MSE). Numerical performance of the proposed algorithms demonstrates that the new frequency tracking algorithms not only has rapid acquisition times but also gives smaller tracking jitters.
Frequency acquisition and tracking in high dynamic environments
(2000-11-01)
Su, YT
;
Wu, RC
;
電信工程研究所
;
友訊交大聯合研發中心
;
Institute of Communications Engineering
This paper presents mean squared error (MSE) analysis of two classes of frequency acquisition and tracking algorithms. Additive white Gaussian noise as well as Rician fading channels are considered, The class of batch-processing algorithms is an extension of earlier least squares proposals used in more benign (lower dynamic) environments. These algorithms try to fit the phase trajectory of the down-converted samples of a received signal. Such a trajectory will depend on the histories of both the signal and the local frequency variations when the local frequency is updated recursively. We propose a method to solve this difficulty and present both first-order and second-order recursive algorithms. Numerical results demonstrate that the MSE performance predicted by our analysis is consistent with that estimated by computer simulation and that the proposed algorithms not only provide rapid acquisition times but also give small tracking jitters.
Frequency estimation of phase-modulated carriers
(1998-12-01)
Su, YT
;
Wu, RC
;
電信工程研究所
;
Institute of Communications Engineering
Conventional approach for frequency estimation usually assume a single tone without data modulation. In many applications such an assumption, realized by using either a separate pilot beacon or synchronization preamble is not feasible. This paper deals with frequency estimation of phase-modulated carriers in the absence of timing information and known data pattern. We introduce new frequency estimators that are based on the generalized maximum likelihood principle. The communication channels under consideration include both additive white Gaussian noise (AWGN) channels and correlated Rician fading channels. For the latter class, we distinguish between the case when the fading (amplitude) process is tracked and that when it is not tracked.
Machine learning with automatic feature selection for multi-class protein fold classification
(2005-07-01)
Huang, CD
;
Liang, SF
;
Lin, CT
;
Wu, RC
;
電控工程研究所
In machine learning, both the properly used networks and the selected features are important factors which should be considered carefully. These two factors will influence the result, whether for better or worse. In bioinformatics, the amount of features may be very large to make machine learning possible. In this study we introduce the idea of feature selection in the problem of bioinformatics. We use neural networks to complete our task where each input node is associated with a gate. At the beginning of the training, all gates are almost closed, and, at this time, no features are allowed to enter the network. During the training phase, gates are either opened or closed, depending oil the requirements. After the selection training phase has completed, gates corresponding to the helpful features are completely opened while gates Corresponding to the useless features are closed more tightly. Some gates may be partially open, depending oil the importance of the corresponding features. So, the network can not only select features in an online manner during learning, but it also does some feature extraction. We combine feature selection with our novel hierarchical machine learning architecture and apply it to multi-class protein fold classification. At the first level the network classifies the data into four major folds: all alpha, all beta, alpha + beta and alpha/beta. In the next level, we have another set of networks which further classifies the data into twenty-seven folds. This approach helps achieve the following. The gating network is found to reduce the number of features drastically. It is interesting to observe that, for the first level using just 50 features selected by the gating network, we can get a test accuracy comparable to that using 125 features in neural classifiers. The process also helps us get a better insight into the folding process. For example, tracking the evolution of different gates, we call find which characteristics (features) of the data are more important for the folding process. Eventually, it reduces the computation time. The use of the hierarchical architecture helps LIS get a better performance also.
Noisy speech segmentation/enhancement with multiband analysis and neural fuzzy networks
(2002-11-01)
Lin, CT
;
Wu, RC
;
Wu, GD
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This paper addresses the problem of speech segmentation and enhancement in the presence of noise. We first propose a new word boundary detection algorithm by using a neural fuzzy network (called ATF-based SONFIN algorithm) for identifying islands of word signals in fixed noise-level environment. We further propose a new RTF-based RSONFIN algorithm where the background noise level varies during the procedure of recording. The adaptive time-frequency (ATF) and refined time-frequency (RTF) parameters extend the TF parameter from single band to multiband spectrum analysis, and help to make the distinction of speech and noise signals clear. The ATF and RTF parameters can extract useful frequency information by adaptively choosing proper bands of the mel-scale frequency bank. Due to the self-learning ability of SONFIN and RSONFIN, the proposed algorithms avoid the need of empirically determining thresholds and ambiguous rules. The RTF-based RSONFIN algorithm can also find the variation of the background noise level and detect correct word boundaries in the condition of variable background noise level by processing the temporal relations. Our experimental results show that both in the fixed and variable noise-level environment, the algorithms that we proposed achieved higher recognition rate than several commonly used word boundary detection algorithms and reduced the recognition error rate due to endpoint detection.
Noncoherent detectors for PN code acquisition in the presence of data modulation
(2000-11-01)
Wu, RC
;
Su, YT
;
Lin, WC
;
電信工程研究所
;
Institute of Communications Engineering
Noncoherent detectors for use in acquiring data-modulated direct-sequence spread-spectrum (DS/SS) signals are considered in this paper. Taking data modulation and timing uncertainty into account and using the generalized maximum likelihood (GML) or maximum likelihood (ML) detection approaches, we derive optimal detectors in the sense of Bayes or Neyman-Pearson and propose various suboptimal detectors. A simple systematic means for their realization is suggested and the numerical performance of these detectors is presented. We also compare their performance with that of the noncoherent combining (NC1) detector that had been proposed to serve the same need. Numerical results show that even the proposed suboptimal detectors can outperform the NC1 detector in most cases of interest.
Optimal and suboptimal noncoherent detectors for PN code acquisition in the presence of data modulation
(1998)
Su, YT
;
Lin, WC
;
Wu, RC
;
電信工程研究所
;
Institute of Communications Engineering
Noncoherent detectors for use in acquiring data-modulated direct-sequence spread-spectrum (DS/SS) signals are considered in this paper. Taking data modulation into account, we examine maximum likelihood (ML) and generalized maximum likelihood (GML) detection structures and then derive suboptimal detectors. We call one of the suboptimal detector as noncoherent partially matched filter (PMF) as it matches only part of the family of legitimate data patterns, We compare the detector operating characteristic (DOC) performance of the PM filter and that of the noncoherent combining (NC) detector that had been proposed to serve the same need. Although the PM filter requires a little more computing it does give better performance.
Using data mining technology to design an intelligent CIM system for IC manufacturing
(2005)
Chen, RS
;
Wu, RC
;
Chang, CC
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
This paper aims to explain a specific intelligent computer integrated manufacturing system by integrating the following five major domains: computer integrated manufacturing, data warehouse, online analytical processing, data mining and artificial intelligence. The data mining system makes use of the decision tree algorithm and classification model in exploring the meaningful information, which is useful in the process of decision making. Subsequently, the rules discovered by the data mining system are expressed through the rule based knowledge presentation method of the expert system. The intelligent CIM system is applied to semiconductor packing factories and also point at the great fluctuation of dynamic random access memory prices. The contribution can increase business competitiveness, reduce production cost, and promote the rate Of available promise for order.