Search

This paper proposes a technique for frequency-partitioned spectrum estimation (FPSE), which is used in the National Taiwan University Wireless Health Advanced Monitoring Bio-Diagnosis System for electrocardiogram analysis. A process for analyzing the RR interval (which is a time series formed by the heat-beat duration that represents heart-rate variations) in conjunction with the fuzzy clustering technique is proposed for arrhythmia recognition. FPSE helps reduce data transmission errors and allows the computational load to be moved to a remote server; however, it suffers from waveform deterioration during reconstruction of the signal power spectrum. To compensate for this problem, this paper proposes a modified FPSE approach that imposes an additional boundary constraint to ensure that the estimated spectrum is smooth. The simulation results show that the proposed algorithm is more effective at recovering the original frequency information and achieves a globally asymptotic trend. The proposed arrhythmia recognition procedure was applied to the Massachusetts Institute of Technology-Boston's Beth Israel Hospital (MIT-BIH) database (developed by MIT and Boston's Beth Israel Deaconess Medical Center), which demonstrated that it is both very convenient and efficient. [ABSTRACT FROM AUTHOR]

In this paper, we present a new method to forecast the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) using fuzzy time series and automatically generated weights of multiple factors. The proposed method uses the variation magnitudes of adjacent historical data to generate fuzzy variation groups of the main factor (i.e., the TAIEX) and the elementary secondary factors (i.e., the Dow Jones, the NASDAQ and the M1B), respectively. Based on the variation magnitudes of the main factor TAIEX and the elementary secondary factors of a particular trading day, it constructs the occurrence vector of the main factor and the occurrence vectors of the elementary secondary factors on the trading day, respectively. By calculating the correlation coefficients between the numerical data series of the main factor and the numerical data series of each elementary secondary factor, respectively, it calculates the relevance degree between the forecasted variation of the main factor and the forecasted variation of each elementary secondary factor. Based on the correlation coefficients between the numerical data series of the main factor and the numerical data series of each elementary secondary factor on a trading day, it automatically generates the weights of the occurrence vector of the main factor and the occurrence vector of each elementary secondary factor on the trading day, respectively. Then, it calculates the forecasted variation of the main factor and the forecasted variation of each elementary secondary factor on the trading day, respectively, to obtain the final forecasted variation on the trading day. Finally, based on the closing index of the TAIEX on the trading day and the final forecasted variation on the trading day, it generates the forecasted value of the next trading day. The experimental results show that the proposed method outperforms the existing methods. [ABSTRACT FROM PUBLISHER]

Temporary gate shortages and stochastic flight delays (including late departures or arrivals and early arrivals) are common problems that often occur simultaneously in real-time airport operations. The aim of this paper is to design a gate reassignment model to deal with temporary gate shortages and stochastic flight delays. This is done by allowing the violation of gate reassignment constraints in the model. A numerical test was carried out, based on data from the operations of the Taiwan Taoyuan Airport (a major international airport in Taiwan), to demonstrate the performance of the proposed model. A comparison of the proposed model and a traditional reassignment model, as well as major findings related to the test results, are also discussed and presented. [ABSTRACT FROM AUTHOR]

In this paper, we develop an intercity bus scheduling model for a variable market share. The proposed model, unlike the past intercity bus scheduling models, does not assume a fixed market share. Instead, passenger choice behaviors in competitive markets are considered. The model is formulated as a nonlinear mixed integer program that is characterized as nondeterministic polynomial-time hard. We develop a solution algorithm to efficiently solve the model. The test results, which are based on a major Taiwan intercity bus carrier, show the good performance of the model and the solution algorithm. [ABSTRACT FROM AUTHOR]

Drug-related problems, particularly those that result from sub- or overtherapeutic doses of high-alert medications, have become a growing concern in clinical medicine. In this paper, we use a model-tree-based regression technique (namely, M5) and support vector machine (SVM) for regression to develop learning-based systems for predicting the adequacy of a vancomycin regimen. We empirically evaluate each system's accuracy in predicting patients' peak and trough concentrations in different clinical scenarios characterized by renal functions and regimen types. Our data consist of 1099 clinical cases that were collected from a major tertiary medical center in southern Taiwan. We also examine the use of Bagging for enhancing the prediction power of the respective systems and include in our evaluation a salient one-compartment model for performance benchmark purposes. Overall, our evaluation results suggest that both M5 and SVM are significantly more accurate than the benchmark one-compartment model in predicting patients' peak and trough concentrations across all investigated clinical scenarios. MS appears to benefit considerably from Bagging, which has a positive but seemingly smaller effect on SVM. Taken together, our findings indicate supervised learning techniques that are capable of effectively supporting clinicians' use of vancomycin or similar high-alert drugs in their patient care and management. [ABSTRACT FROM AUTHOR]