Seung Hong

Comparison between short time Fourier and wavelet transform for feature extraction of heart sound

Presents the application of the wavelet transform analysis method to the phonocardiogram (PCG) signal. Heart sound is a highly nonstationary signal. So in the analysis of heart sound it is important to study the frequency and time information. To investigate the exact features of heart sound we adopt Short-Time Fourier Transform (STFT) and Wavelet Transform (WT) as a time-frequency representation. As a result, it is found that the first sound in the PCG signal and the two components of the second sound are inaccurately detected. On the other hand, it is found that the wavelet transform is capable of detecting the two components, the aortic valve component A2 and pulmonary valve component P2, of the second sound S2 in a normal PCG signal. Furthermore, the wavelet transform provides more features and characteristics of the PCG signals that will help the physician to obtain qualitative and quantitative measurements of the heart sound.

A speckle reduction filter using wavelet-based methods for medical imaging application

One of the most significant features of diagnostic echocardiographic images is to reduce speckle noise and make better image quality. In this paper we proposed a simple and effective filter design for image denoising and contrast enhancement based on multiscale wavelet denoising method. Wavelet threshold algorithms replace wavelet coefficients with small magnitude by zero and keep or shrink the other coefficients. This is basically a local procedure, since wavelet coefficients characterize the local regularity of a function. After we estimate distribution of noise within echocardiographic image, then apply to the fitness wavelet threshold algorithm. A common way of the estimating the speckle noise level in coherent imaging is to calculate the mean-to-standard-deviation ratio of the pixel intensity, often termed the Equivalent Number of Looks (ENL), over a uniform image area. Unfortunately, we found this measure not very robust mainly because of the difficulty to identify a uniform area in a real image. For this reason, we will only use here the S/MSE ratio and which corresponds to the standard SNR in case of additive noise. We have simulated some echocardiographic images by specialized hardware for real-time application; processing of a 512*512 images takes about 1 min. Our experiments show that the optimal threshold level depends on the spectral content of the image. High spectral content tends to over-estimate the noise standard deviation estimation performed at the finest level of the DWT. As a result, a lower threshold parameter is required to get the optimal S/MSE. The standard WCS theory predicts a threshold that depends on the number of signal samples only.

A Study in the Implementation of Environment of Behavior Monitoring System Based on Image Processing

According as society looks graying trend gradually, more shaped system that can achieve measuring health-state of old people more harmoniously construction required in field of old people’s welfare and medical treatment. This study suggests the system that can monitor the user, especially old people’s outward aging and health-state using CCD camera loaded fish-eye lens. Measurement of outward aging is achieved by two steps. The first is based on structure of human musculoskeletal system. This process is achieved by image processing, for example edge detecting, thresholding, skeletonization, etc. Through this process, we get the angles of arm and shoulder and curve of vertebra. The second is image acquisition about behavior pattern. For the second step, CCD camera loaded fish-eye lens is installed from the ceiling. The data-base that is acquired by the methods that this study suggests will be applied to Ubiquitous Home Automation System. So it will be in effective use for the welfare and the monitoring system for old people.

EMG signals recognition for continuous prosthetic arm control purpose

To be functional in a practical sense for real-time control of assistive devices, a myoprocessor must successfully integrate both detection and estimation systems. This paper describes an approach for classifying electromyographic (EMG) signals using a multilayer perceptrons (MLPs) and hidden Markov models (HMMs) hybrid classifier and force estimation. Instead of using MLPs as probability generators for HMMs the authors propose to use MLPs as the second classifiers to increase discrimination rates of myoelectric patterns. This strategy is proposed to overcome weak discrimination and to consider dynamic properties of EMG signals. Two discrimination strategies (HMM, and HMM with three subnet MLPs) for discriminating signals representative of 6 primitive class of motions are described and compared. The proposed strategy increase the discrimination results considerably. Results are presented to support this approach.

Noise reduction of echocardiographic images using wavelet filtering

In this paper we proposed a new wavelet filtering technique to reduce the speckle noise in ultrasound images. The advantages of this approach are demonstrated in echocardiographic image enhancement and in comparison with other techniques. Wavelet signal processing provides a multiresolution decomposition. The fact that wavelet approaches tend to concentrate energy near edge features makes the result rather different than that found in standard Fourier based approaches. For speckle noise, the time and frequency localization capabilities of wavelets provide better noise reduction and less signal distortion than direct filtering of data. A technical method of noise filtering for reducing speckle noise in ultrasound images is presented. Experimental results are presented to illustrate the application of these techniques to echocardiographic images. Application of the proposed method to echocardiographic images has demonstrated that the results produced have high potential for use as inputs for a further automated interpretation stage.

Development of the Walking Assistant Robot for the Elderly

In this paper, we propose an architecture of walking assistant robot for the elderly which is usable at outdoor environment. It equips PXA255 embedded board, motors, laser range finder and GPS receiver. User operates it using smart handle bar. It is useful to the elderly for more comfortable walking and path guidance.

Study of ZMP Measurement for Bipedrobot Using FSR Sensor

This paper discuss a method measuring ZMP for biped robot. We obtained feet-bottom pressure distribution using FSR sensors attaching feet-bottom. We calculate value of ZMP coordinates that is the center of gravity for biped robot using their pressure distribution. Value of Biped Robot ZMP coordinates always exists in feet-bottom. When walking limbs of biped robot are controlled, inverse kinematics use method supposed by author. We introduce it in this paper.

A Study on Path Guidance System of Guide Robot for Visually Impaired

In this paper, earth coordinate of the guidance robot for the visually impaired is detected by using GPS (Global Position System), and the system which leads the visually impaired to position information (TM coordinate) in Korea is achieved through map-matching with electronic map. The visually impaired need more information about the walking path than ordinary people when walking outdoor. Therefore, we studied implementation which can guide the visually impaired more safely through map-matching with GPS signal by making electronic map for the visually impaired.

Design of nonlinear filter for echocardiographic images on wavelet-based method

One of the most significant features of diagnostic echocardiographic images is to reduce speckle noise and make better image quality. In this paper we proposed a simple and effective filter design for image denoising and contrast enhancement based on multiscale wavelet denoising method. Wavelet threshold algorithms replace wavelet coefficients with small magnitude by zero and keep or shrink the other coefficients. This is basically a local procedure, since wavelet coefficients characterize the local regularity of a function. After we estimate distribution of noise within echocardiographic image, then apply to fitness Wavelet threshold algorithm. A common way of the estimating the speckle noise level in coherent imaging is to calculate the mean-to-standard-deviation ratio of the pixel intensity, often termed the Equivalent Number of Looks(ENL), over a uniform image area. Unfortunately, we found this measure not very robust mainly because of the difficulty to identify a uniform area in a real image. For this reason, we will only use here the S/MSE ratio and which corresponds to the standard SNR in case of additivie noise. We have simulated some echocardiographic images by specialized hardware for real-time applicati on;processing of a 512*512 images takes about 1 mm. Our experiments show that the optimal threshold level depends on the spectral content of the image. High spectral content tends to over-estimate the noise standard deviation estimation performed at the fmest level ofthe DWT. As a result, a lower threshold parameter is required to get the optimal S/MSE. The standard WCS theory predicts a threshold that depends on the number of signal samples only.

Local obstacle avoidance for synchro-drive mobile robot

The authors consider the problem faced by an indoor mobile robot that has to reach a given target by traveling through an unmapped region in a plane which contains obstacles. The robot must avoid static and dynamic obstacles of which the robot has no prior knowledge about the positions or size of them. The robot can acquires knowledge of obstacles only when obstacles are encountered and detected by ultrasonic sensors. Also, an indoor robot needs to be equipped with fast detection of obstacles and selection of steering commands algorithms to maximize the progress towards the goal location. The dynamics of the robot must be considered to make the generated commands more reliable.