Browsing by Author "Chen, Wei-Hsin"

Now showing 1 - 11 of 11

A new vehicle detection with distance estimation for lane change warning systems
(2007)
Wu, Bing-Fei
;
Chen, Wei-Hsin
;
Chang, Chai-Wei
;
Chen, Chao-Jung
;
Chung, Ming-Wei
In this paper, the vehicle detection with distance estimation algorithm is proposed by using two CCD cameras mounted on the both side mirrors of our experimental car, TAIWAN iTS-1. The Sobel edge pixels and gray intensity are applied for the lane marking and vehicle detection in our work. A new detection which utilizes a lane prediction technique to reduce the size of the ROI is developed for real-time embedded system applications. The side vehicles can be easily detected by comparing the gray intensity with the road surface. Then, the image coordinate model is utilized for the distance estimation with the detected approaching vehicles. The verified effective distance is 30m behind the host vehicle. This approach has been successfully implemented on the DSP board for the real-time detection and this system will be extended to the lane change warning system to give drivers alerts to avoid collision.
Bio-signal Analysis System Design with Support Vector Machines based on Cloud Computing Service Architecture
(2010-01-01)
Shen, Chia-Ping
;
Chen, Wei-Hsin
;
Chen, Jia-Ming
;
Hsu, Kai-Ping
;
Lin, Jeng-Wei
Today, many bio-signals such as Electroencephalography (EEG) are recorded in digital format. It is an emerging research area of analyzing these digital bio-signals to extract useful health information in biomedical engineering. In this paper, a bio-signal analyzing cloud computing architecture, called BACCA, is proposed. The system has been designed with the purpose of seamless integration into the National Taiwan University Health Information System. Based on the concept of. NET Service Oriented Architecture, the system integrates heterogeneous platforms, protocols, as well as applications. In this system, we add modern analytic functions such as approximated entropy and adaptive support vector machine (SVM). It is shown that the overall accuracy of EEG bio-signal analysis has increased to nearly 98% for different data sets, including open-source and clinical data sets.
Bioethanol production from acid pretreated microalgal hydrolysate using microwave-assisted heating wet torrefaction
(2020-11-01)
Yu, Kai Ling
;
Chen, Wei-Hsin
;
Sheen, Herng-Kuang
;
Chang, Jo-Shu
;
Lin, Chih-Sheng
This study focused on the bioethanol production from the co-production of solid biochar and liquid hydrolysate under microwave-assisted heating wet torrefaction towards a sustainable green technology. The two indigenous microalgal biomass undergone dilute acid pretreatment using wet torrefaction to produce microalgal hydrolysates and biochar at operating conditions of 160-170 degrees C with holding times of 5-10 min. The hydrolysates were utilized for fermentation with the yeast Saccharomyces cerevisiae at 29 degrees C in a dark condition at a non-agitation state for 120 h. The concentrations of total reducing sugar, reducing sugar by-product, and bioethanol in the hydrolysates were determined. The carbohydrate-rich microalga C. vulgaris ESP-31 showed a good performance in bioethanol production. Microalgal hydrolysate obtained after the pretreatment consisted of a total reducing sugar with the highest concentration of 98.11 g/L. The formation of by-product 5-hydroxymethyl-2-furaldehyde (5 HMF), which might act as the fermentation inhibitor that led to the low ethanol yield, was also analyzed. The highest ethanol yield achieved was 7.61% with a maximum experimental conversion probability of 95.22%. This study has demonstrated the feasible bioethanol production from microalgal hydrolysate through microwave-assisted heating wet torrefaction using dilute acids and the optimization of bioethanol production can be carried out for better performance in the future study.
Dynamic CCD camera calibration tor traffic monitoring and vehicle applications
(2007)
Wu, Bing-Fei
;
Chen, Wei-Hsin
;
Chang, Chai-Wei
;
Liu, Chih-Chun
;
Chen, Chao-Jung
In this paper, the camera calibration approach based on the perspective model for the tilt angle, pan angle and the height of installation is proposed. Before starting the calibration, the lane information is acquired by applying the Sobel horizontal and vertical edged pixels. The calibration method only utilizes a pair of parallel lane markings without manually selecting special features. The tilt angle, pan angle and camera height are calibrated sequentially in our method. This algorithm can be widely applied in vehicle collision avoidance applications and traffic monitoring systems.
High-Performance Seizure Detection System Using a Wavelet-Approximate Entropy-fSVM Cascade With Clinical Validation
(2013-10-01)
Shen, Chia-Ping
;
Chen, Chih-Chuan
;
Hsieh, Sheau -Ling
;
Chen, Wei-Hsin
;
Chen, Jia-Ming
The classification of electroencephalography (EEG) signals is one of the most important methods for seizure detection. However, verification of an atypical epileptic seizure often can only be done through long-term EEG monitoring for 24 hours or longer. Hence, automatic EEG signal analysis for clinical screening is necessary for the diagnosis of epilepsy. We propose an EEG analysis system of seizure detection, based on a cascade of wavelet-approximate entropy for feature selection, Fisher scores for adaptive feature selection, and support vector machine for feature classification. Performance of the system was tested on open source data, and the overall accuracy reached 99.97%. We further tested the performance of the system on clinical EEG obtained from a clinical EEG laboratory and bedside EEG recordings. The results showed an overall accuracy of 98.73% for routine EEG, and 94.32% for bedside EEG, which verified the high performance and usefulness of such a cascade system for seizure detection. Also, the prediction model, trained by routine EEG, can be successfully generalized to bedside EEG of independent patients.
Newborn Screening for Phenylketonuria: Machine Learning vs Clinicians
(2012)
Chen, Wei-Hsin
;
Chen, Han-Ping
;
Tseng, Yi-Ju
;
Hsu, Kai-Ping
;
Hsieh, Sheau-Ling
The metabolic disorders may hinder an infant\'s normal physical or mental development during the neonatal period. The metabolic diseases can be treated by effective therapies if the diseases are discovered in the early stages. Therefore, newborn screening program is essential to prevent neonatal from these damages. In the paper, a support vector machine (SVM) based algorithm is introduced in place of cut-off value decision to evaluate the analyte elevation raw data associated with Phenylketonuria. The data were obtained from tandem mass spectrometry (MS/MS) for newborns. In addition, a combined feature selection mechanism is proposed to compare with the cut-off scheme. By adapting the mechanism, the number of suspected cases is reduced substantially; it also handles the medical resources effectively and efficiently.
Newborn Screening System Based on Adaptive Feature Selection and Support Vector Machines
(2009-01-01)
Hsieh, Sung-Huai
;
Chien, Yin-Hsiu
;
Shen, Chia-Ping
;
Chen, Wei-Hsin
;
Chen, Po-Hao
The clinical symptoms of metabolic disorders during neonatal period are often not apparent, if not treated early irreversible damages such as mental retardation may occur, even death. Therefore, practicing newborn screening is very important to prevent neonatal from these damages. In this paper, the newborn screening system used support vector machines (SVM) classification technique is proposed in place of cut-off value decision to evaluate the metabolic substances concentration raw data obtained from tandem mass spectrometry (MS/MS) and determine whether the newborn has some kinds of metabolic disorder diseases. On the basis of the proposed features, new analytic combinations are identified with superior discriminatory performance compared with the best published combinations. Classifiers built with the feature selection to find C3/C2, C3 and C16 of three key point features achieved diagnostic sensitivities, specificities and accuracy approaching 100%.
Numerical simulation of electrical characteristics in nanoscale Si/GaAs MOSFETs
(2006-07-01)
Li, Yiming
;
Chen, Wei-Hsin
;
電子物理學系
;
電信工程研究所
;
Department of Electrophysics
In this paper, electrical characteristics of metaloxide-semiconductor field effect transistor (MOSFET) with silicon/gallium-arsenic (Si/GaAs) stacked film are numerically studied. By calculating several important device characteristics, such as the on-state current, the subthreshold swing, the drain induced barrier lowering, the threshold voltage, the threshold voltage roll-off, and the output resistance, a 50 nm Si/GaAs MOSFET is simulated with respect to different thicknesses of Si/GaAs film. Compared with the results of pure Si MOSFET, Si/GaAs MOSFET shows promising characteristics after properly selecting the thickness of Si/GaAs film. Among Si, germanium (Ge), and Si/Ge MOSFETs, Si/GaAs MOSFET relatively exhibits a higher driving capability due to higher carrier mobility within the Si/GaAs film. However, quantitatively accurate estimation of device characteristics will depend upon more precise calculation of band structure of the stacked film.
Production of microalgal biochar and reducing sugar using wet torrefaction with microwave-assisted heating and acid hydrolysis pretreatment
(2020-08-01)
Yu, Kai Ling
;
Chen, Wei-Hsin
;
Sheen, Herng-Kuang
;
Chang, Jo-Shu
;
Lin, Chih-Sheng
This study employed the microwave-assisted acid hydrolysis pretreatment using wet torrefaction on two indigenous microalgae, Chlorella vulgaris ESP-31 and Chlorella sp. GD with different biomass composition to investigate the yields of solid biochar and total reducing sugar in the liquid hydrolysate. Operating conditions at low temperatures (160, 170 degrees C) with short holding time (5, 10 min) under several concentrations of diluted acid medium (0, 0.1 and 0.2 M) were carried out to investigate the torrefaction severity effects towards the properties of the solid and liquid products. The highest biochar yields of 54.5% and 74.6% are obtained from C. vulgaris ESP-31 and Chlorella sp. GD, respectively under the wet torrefaction conditions with an improvement in the properties for fuel and value-added environmental application. The highest total reducing sugar concentration of 98.11 g/L and 12.08 g/L are obtained in C. vulgaris ESP-31 and Chlorella sp. GD liquid hydrolysates, respectively after acid hydrolysis pretreatment. With the co-production of high total reducing sugar in the liquid hydrolysate that can be utilized for bioethanol production and solid biochar as another value-added product, the acid hydrolysis pretreatment using wet torrefaction can be one of the conversion technologies towards the application of renewable energy production. (C) 2020 Elsevier Ltd. All rights reserved.
Web Services Based Bio-signal System Leveraging Support Vector Machines
(2009)
Hsieh, Sung-Huai
;
Hsieh, Sheau-Ling
;
Shen, Chia-Ping
;
Chen, Wei-Hsin
;
Cheng, Po-Hsun
Bio-signal analysis is one of the most important approaches to biomedical engineering. The health information such as ECG, PCG, EMG and EEG are often recorded in digital format to be analyzed. In this paper, a bio-signal analyzing web service system using Support Vector Machines (SVM) classifier technique is proposed. The bio-signals are recorded in digital format as the input of the system. In addition, based on the concept of Service-Oriented Architecture (SOA), the system under web services .NET is designed. The system provides features including heterogeneous platform, protocols, as well as applications. The system has been designed with the purpose of seamless integration into the Health Information System.
Web-Based Newborn Screening System for Metabolic Diseases: Machine Learning Versus Clinicians
(2013-05-01)
Chen, Wei-Hsin
;
Hsieh, Sheau-Ling
;
Hsu, Kai-Ping
;
Chen, Han-Ping
;
Su, Xing-Yu
Background: A hospital information system (HIS) that integrates screening data and interpretation of the data is routinely requested by hospitals and parents. However, the accuracy of disease classification may be low because of the disease characteristics and the analytes used for classification. Objective: The objective of this study is to describe a system that enhanced the neonatal screening system of the Newborn Screening Center at the National Taiwan University Hospital. The system was designed and deployed according to a service-oriented architecture (SOA) framework under the Web services. NET environment. The system consists of sample collection, testing, diagnosis, evaluation, treatment, and follow-up services among collaborating hospitals. To improve the accuracy of newborn screening, machine learning and optimal feature selection mechanisms were investigated for screening newborns for inborn errors of metabolism. Methods: The framework of the Newborn Screening Hospital Information System (NSHIS) used the embedded Health Level Seven (HL7) standards for data exchanges among heterogeneous platforms integrated by Web services in the C# language. In this study, machine learning classification was used to predict phenylketonuria (PKU), hypermethioninemia, and 3-methylcrotonyl-CoA-carboxylase (3-MCC) deficiency. The classification methods used 347,312 newborn dried blood samples collected at the Center between 2006 and 2011. Of these, 220 newborns had values over the diagnostic cutoffs (positive cases) and 1557 had values that were over the screening cutoffs but did not meet the diagnostic cutoffs (suspected cases). The original 35 analytes and the manifested features were ranked based on F score, then combinations of the top 20 ranked features were selected as input features to support vector machine (SVM) classifiers to obtain optimal feature sets. These feature sets were tested using 5-fold cross-validation and optimal models were generated. The datasets collected in year 2011 were used as predicting cases. Results: The feature selection strategies were implemented and the optimal markers for PKU, hypermethioninemia, and 3-MCC deficiency were obtained. The results of the machine learning approach were compared with the cutoff scheme. The number of the false positive cases were reduced from 21 to 2 for PKU, from 30 to 10 for hypermethioninemia, and 209 to 46 for 3-MCC deficiency. Conclusions: This SOA Web service-based newborn screening system can accelerate screening procedures effectively and efficiently. An SVM learning methodology for PKU, hypermethioninemia, and 3-MCC deficiency metabolic diseases classification, including optimal feature selection strategies, is presented. By adopting the results of this study, the number of suspected cases could be reduced dramatically.