Seung-Won Shin

Removal of baseline wandering in ECG signal by improved detrending method

The very first step to process electrocardiogram (ECG) signal is to eliminate baseline wandering interference that is usually caused by electrode-skin impedance mismatch, motion artifacts due to a patients body moment or respiratory breathing. A new method is thus suggested to remove baseline wandering in ECG by improving the detrending method that was originally proposed for eliminating slow non-stationary trends from heart rate variability (HRV). In our proposed method, a global trend is estimated in terms of baseline wandering by merging the local trend based on an ECG segment that represents a part of the ECG signal. The experimental results show that the improved detrending method can efficiently resolve baseline wandering without distorting any morphological characteristic embedded in the ECG signal in no time delay manner.

Suppression of Noisy Characteristics of Biosignals by Implementing Digital Filters with an Android Smartphone Platform

In this study, the novel digital filtering algorithms are implemented to suppress the noisy characteristics embedded in ambulatory electrocardiogram signals by an android smartphone platform. With this aim, Graphical User Interface (GUI) is designed and implemented by utilizing multithread-Java programming to realize Finite Impulse Response and Infinite Impulse Response filter. With simulating our implemented digital filters built in an android smartphone, we can find the fact that we can efficiently suppresses the noisy characteristics due to baseline wandering and 60 Hz powerline source fluctuations especially in electrocardiograms.

Estimation of Heart Rate Variability with an Android Smart Phone Platform

In this study, ambulatory electrocardiogram(ECG) signal and the rhythms of heart beats are visualized in terms of R-R intervals and Heart Rate Variability(HRV) in the environment of an android plaform. With this aim, Graphical User Interface(GUI) is implemented by executing multi-thread Java programming modules including ECG, heart-beats, tachogram and visualization unit. ECG signals are acquired in an android device by receiving the data from ambulatory ECG sensory system. Finite Impulse Response(FIR) filters are implemented to eliminate the baseline wandering noises contained in the ambulatory signals and DC-offset level in R-R interval data. With simulating the normal or stress emotional state of a subject, we can find the fact that HRV can be successfully estimated and visualized in an android smart phone platform.

Infrared Thermography in Human Hand

It is important to estimate the hand skin temperature because it reveals not only physiological properties of a certain diseases but also it can estimate even human mental-stress conditions. In this study, we try to estimate the temporal skin temperature distribution of human hand by applying stress-cold test to possibly apply to estimate a subject’s blood circulation condition in his or her hand in terms of normal or abnormal state.

Implementing Graphic User Interface System for Microwave Radiometry Data to Utilize Breast Cancer Diagnosis

In this study, a novel Graphic User Interface (GUI) software development system is suggested so that it can be applied to diagnose breast cancer with utilizing 3~4.2 GHz microwave radiometric data. The estimated inner and surface temperature values on the patient`s right and left breast in terms of microwave radiometry are visualized in HSV color mapping space and their relevant contour regions and lines are depicted by Marching Square graphic algorithm. Also the database system is implemented in terms of patient and diagnostic module to support the medical decisions concerning the breast cancer diagnosis.

Image Enhancement with Rotating Kernel Transformation Filter Generated by Bresenham's Algorithm

It is quite important to improve the visual acuity of a medical image by suppressing noisy parts and simultaneously keeping the details of signal components to draw the accurate diagnostics. With this aim, we suggest a novel method to generate Rotational Kernel Transformation (RKT) filter mask with applying Bresenham`s algorithm and implement an nonlinear filtering algorithm to eliminate noises. As a result, we can find the fact that RKT filter mask can be automatically created and the visual acuity of a corrupted image can be elevated in terms of the signal-to-noise ratio (SNR) with applying the RKT filter.

Real-time photoacoustic tomograpghy using linear array probe and detection of line structure using Hough transform

A real-time photoacoustic tomography (PAT) system is developed using a linear array probe and phantom images are acquired with a pattern of line structure. Moreover, it is attempted to detect line structures from the acquired images by Hough transform. This effort leads to the measurement of a process of magenta passing through a tube and acquisition of images at a speed of about 2 frame/sec. Besides, it is confirmed that the Hough transform applied on the acquired PAT images has the detection rate of about 50% for delineating a line structure.

Encryptions of ECG Signals by Using Fiducial Features

With the advent of ubiquitous healthcare technology to provide a patient with the necessary medical services in anywhere and anytime scheme, the importance of securing safe communication without tampering the medical data by the unauthorized users is getting more emphasized. With this aim, a novel method for constructing encryption keys on the basis of biometrical measurement of electrocardiogram (ECG) is suggested in this study. The experiments on MIT/BIH database show that our proposed method can achieve safe communication by successfully ciphering and deciphering ECG data including premature ventricular contraction arrhythmia signal with compromising its fiducial features as biometric key to transmit the data via the internet network.

Color Image Segmentation for Extracting Dental Plaque

In this study, we propose the unsupervised image segmentation algorithm to estimate dental plaque accumulations on digital imaging with methylene blue disclosed plaque. With this aim, RGB color plane is mapped into HSI coordinates and the circular histogram of Hue is reconstructed by applying Otsus threshold level. The histogram distribution on Saturation features is also analyzed by maximizing the variance between a plaque candidate and non-plaque one. The dental plaque regions are resolved by applying the composite decision logics based on the threshold level of Hue and Saturation.

Detecting facial features by heteroassociative memory neural network utilizing facial statistics

In this paper, we present an efficient algorithm of extracting the multiple facial features such as eyes, nose, and mouth. The face candidates are first obtained based on skin-color filtering inYCbCr color domain and skin-temperature values and then the elliptic measures are applied to extract a true face candidate and its boundary. A Sobel edge mask is performed and consequently horizontal projection operation is applied to locate the eyes referring to the maximum horizontal projection value in Y component. Once two eyes are located, the distance that crosses the center of eyes and extends to the face boundary, D1 is determined. A heteroassociative memory neural network model is utilized to find the facial features. An input neuron vector X accepts D1 and the output neurons vector Y maps it to the facial features such as eyes, nose and mouth.