Young-Ro Yoon

A New Specimen Management System Using RFID Technology

The specimen management system with barcode needs to be improved in order to solve inherent problems in work performance. This study describes the application of Radio Frequency Identification (RFID) which is the solution for the problems associated with specimen labeling and management. A new specimen management system and architecture with RFID technology for clinical laboratory was designed. The suggested system was tested in various conditions such as durability to temperature and aspect of effective utilization of new work flow under a virtual hospital clinical laboratory environment. This system demonstrates its potential application in clinical laboratories for improving work flow and specimen management. The suggested specimen management system with RFID technology has advantages in comparison to the traditional specimen management system with barcode in the aspect of mass specimen processing, robust durability of temperature, humidity changes, and effective specimen tracking.

Development of Heart Rate Monitoring for Mobile Telemedicine using Smartphone

The point of this study is on the development of wireless patient monitoring system that can monitor heart rates in real time environments. The entire system consists of a portable photoplethysmography device, a healthcare server and a Smartphone for healthcare information reports. The portable device collects heart rate information from the patients and sends the data to home healthcare server. This device is designed to be easily worn and have low power consumption. The role of the healthcare server is to analyze the collected biomedical signals. The result of the analysis is displayed on the Smartphone through the CDMA networks. The application program on Smartphone gives the healthcare information to patients and doctors. This system would be useful for patients who have chronic heart disease.

Evaluation of Performance of Several Established Pitch Detection Algorithms in Pathological Voices

Robust pitch estimation is important in many areas of speech processing. In voice pathology, diverse statistics extracted form pitch estimation were commonly used to test voice quality. In this study, we compared several established pitch detection algorithms (PDAs) for verification of adequacy of the PDAs. In the database of total pathological voices of 99 and normal voices of 30, an analysis of errors related with pitch detection was evaluated between pathological and normal voices, or among the types of pathological voices. Pitch errors of all PDAs used in this study more or less showed some changes between pathological and normal voices. According to the results of pitch errors, gross pitch error showed some increases in cases of pathological voices; especially excessive increase in PDA based on nonlinear time-series. In an analysis of types of pathological voices classified by aperiodicity and the degree of chaos, the more voice has aperiodic and chaotic, the more growth of pitch errors increased. Consequently, it is required to survey the severity of tested voice in order to obtain accurate pitch estimates.

Detection of suspicious pain regions on a digital infrared thermal image using the multimodal function optimization

Automatic detection of suspicious pain regions is very useful in the medical digital infrared thermal imaging research area. To detect those regions, we use the SOFES (Survival Of the Fitness kind of the Evolution Strategy) algorithm which is one of the multimodal function optimization methods. We apply this algorithm to famous diseases, such as a foot of the glycosuria, the degenerative arthritis and the varicose vein. The SOFES algorithm is available to detect some hot spots or warm lines as veins. And according to a hundred of trials, the algorithm is very fast to converge.

ECG data compression using fractal interpolation

Presents a fractal interpolation compression method for ECGs. The method represents any range of ECG signal by fractal interpolation parameters. The variable range size technique is employed in order to reduce the reconstruction error. Small ranges are used for encoding rapidly varying parts of ECG to preserve the signal quality. The suggested algorithm was evaluated using MIT/BIH database. A high compression ratio is achieved with a relatively low percent rms difference.<<ETX>>

Classification of Ventricular arrhythmia using a support vector machine based on morphological features

This paper proposes a method for the classification of ventricular arrhythmia using support vector machines (SVM). The features used in the SVMs were extracted automatically based on morphological information. Three different features were extracted: RR interval, QRS slope, and QRS shape similarity. Then, the SVM was used to classify five different electrocardiogram (ECG) heartbeat episodes. The Gaussian Radial Basis Function was utilized for the kernel function because the ECG beat episodes were treated as a non-linear pattern. The sensitivity of the classification used for the five beat episodes was 93.16%.

Personalized healthcare comment service for hypertension patients using mobile device

Hypotension and hypertension are chronic diseases, which can be effectively prevented and controlled by constantly monitoring. In this study, personalized healthcare comment service for hypertension patients is proposed and implemented. We have developed algorithms of health state code generation and doctors comments for patients on case-by-case basis. This prototype service shows how such personalized comments can manage patients with hypertension using blood pressure monitor and mobile device.

Target Source Detection using an Improved Sensing Model in Wireless Sensor Networks (ISMWSNs)

We applied the inverse problem approach to locate the known source in a uniformly distributed sensor network from a simultaneous RSSI measurement between sensors and sources. We also proposed a new sensing model to calculate RSSI between sensors and a specific source and carefully considered the orientation vector of the source. We detected the original source by means of a linear inverse problem using the calculated RSSI at the target source from the improved sensing model. Finally, we simulated the proposed sensing model to verify its ability to detect the original source. Changes in the initial source and calculated results remained quite in place. Moreover, the norm of the detected source was significantly larger than the norm of any other sources.

Multimodal Function Optimization Based on the Survival of the Fitness kind of the Evolution Strategy

In this paper, a new algorithm for the multimodal function optimization is proposed, base on the concept of the survival of the fitness rule of evolution. The proposed algorithm has common criteria not to be invaded by each other. Thus, there is only one survivor in a partial solution space in which one optimal point locates. To verify the proposed algorithm, three multimodal functions - Alex function 5, six-hump camel back function, and Rastrigins function - are tested.

A Study of Significant data Classification between EDR extracted and frequency analysis of Heart Rate Variability from ECG using Conductive textile

The aim of this study is classification of correlative data through comparison between ECG-Derived Respiration (EDR) and High Frequency (HF) component obtained frequency analysis of heart rate variability (HRV) from ECG using two of conductive textiles. Generally, individual frequency range of the HF component has been determined only by means of distinctive parameters of respiration such as respiratory rate, range and median value of respiratory rate, etc. However, in many cases Low Frequency (LF) components and High Frequency (HF) components may be superimposed on each other totally or particularly and can not be diagnostically estimated because respiratory rhythms are individually much remarkably differentiated. This study, in consequence, analyze frequency component of EDR derived from ECG and then compare with high frequency components of HRV and finally find out valuable data for further analysis. Hardware constitution is used to bed type ECG measurement equipment based on U-Healthcare, can identify user using Radio Frequency (RF) module as well as manage data each of user. We used Frequency Modulation (FM) method based on Respiration Sinus Arrhythmia (RSA) in order to extract EDR from ECG signal. ECG data and EDR data were processed with Lab-VIEW, then classified through each of frequency analysis.