Leauhatong, Thurdsak

Preferred name

Main Affiliation

School of Engineering

thurdsak.le@kmitl.ac.th

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
ECG analysis for person identification
(2013-12-01)
Pathoumvanh, Somsanouk
;
Airphaiboon, Surapan
;
Prapochanung, Benjawan
;
Leauhatong, Thurdsak
Electrocardiogram (ECG) has been actively proposed as aliveness biometric. In this paper, the study which concern to a realistic application is proposed. Firstly, a single lead normal ECG signal is acquired from individuals of 10 subjects. Then, each single beat ECG is segmented and analyzed in Continuous Wavelet Transform (CWT) domain. Total energy of wavelet coefficients for each P, QRS, and T segment is calculated. Next, the Fisher Linear Discriminant Analysis (FLDA) is applied. Finally, normalized Euclidean distance is implemented as a classifier. In experimental results, 97% of classification accuracy is achieved in case of a normal ECG (with non-variation of heart rate). © 2013 IEEE.
Some of the metrics are blocked by your
consent settings
Optimal selection of mother wavelet for classifying human activities from acceleration signals
(2016-02-04)
Leauhatong, Thurdsak
;
Nuttaitanakul, Nitipat
;
Prapochanang, Benjawan
Falls are major problems that could have happened to elderly, and could cause paralysis, hip fractures, disabilities or accidental deaths. A human activity classification from acceleration signals may be an important process in fall prevention or detection. An algorithm which combines the wavelet transform and the multilayer perceptron neural network is an effective tool for classifying complicate signals. In order to optimize the classification, this paper aims to compare the performances of the algorithm which uses different mother wavelets. In our experiments, 5 volunteers who were healthy with the ages between 21 to 25 year old were asked to attach a tri-axial accelerometer at the right side of their waists. Next, the volunteers were asked to perform 5 daily-life activities: 1) walking, 2) standing up from a chair, 3) sitting down on a chair, 4) lying down on a bed, and 5) getting up from a bed; and 5 falling events: 1) forward falling, 2) backward falling, 3) falling to the right side, 4) falling to the left side, and 5) falling when standing up. In this paper, there are 2 experiments. In the first experiment, the algorithm was used to classify the real activity of the acceleration signals. Then the output of the algorithm can be any activity from ten activities. In the second experiment, the algorithm was used to detect the falling events. Then the output of the algorithm has 2 values; the falling event or the daily-life activity. The mother wavelets which an; used to evaluate the performances of the classification were Daubechies, Coiflet, Symlet, and Biorthogonal. From the experiments of the both of the human activity classification and the falling detection, the algorithm which used the Biorthogonal mother wavelet showed the best performances.
Some of the metrics are blocked by your
consent settings
Image coding using vector quantization based on wavelet transform fuzzy C-means and principle component analysis
(2009-12-01)
Phanprasit, Tanasak
;
Leauhatong, Thurdsak
;
Pintavirooj, Chuchart
;
Sangworasil, Manas
Image coding requires a small bit rate for high-speed data transmission and a small space for data storage. Simultaneously, the peak signal to noise ratio (PSNR) has to be maintained. In this paper, we proposed a method of image coding design using wavelet transform (WT). By applying the WT for defining groups of pixels with the same intensity in spatial domain, the groups of pixels are allocated in a low frequency range. Hence, locations of pixels are the key factor to determine the size of each block and we use wavelet transform to decompose each block into subband components, which are represented by 3D vectors. The 3D vectors are then classified into 8 groups corresponding to quadrants of spatial coordinates. In addition, we apply Fuzzy C-Means algorithm to classify the member in the magnitudes value of 3D vectors into code vector. Due to the lossy coding process, we propose a method of system error compensation on Vector Quantization (VQ) by using principle component analysis and discrete wavelet transform to performed on the system error and keeping the high-energy coefficient for further inverse wavelet transform to yield system error compensation. The reconstructed image and system error compensate will be combined in order to construct an output image (X<inf>o</inf>). By applying the proposed method, performance of the method is evaluated as 26.19% of bit rate and 1.50% of PSNR improved. ©2009 IEEE.
Some of the metrics are blocked by your
consent settings
Human falling detection algorithm using back propagation neural network
(2012-12-01)
Sengto, Adna
;
Leauhatong, Thurdsak
A fall monitor system is necessary to reduce the rate of fall fatalities in elderly people. As an accelerometer has been smaller and inexpensive, it has been becoming widely used in motion detection fields. This paper proposes the falling detection algorithm based on back propagation neural network to detect the fall of elderly people. In the experiment, a tri-axial accelerometer was attached to waists of five healthy and young people. In order to evaluate the performance of the fall detection, five young people were asked to simulate four daily-life activities and four falls; walking, jumping, flopping on bed, rising from bed, front fall, back fall, left fall and right fall. The experimental results show that the proposed algorithm can potentially distinguish the falling activities from the other daily-life activities. ©2012 IEEE.
Some of the metrics are blocked by your
consent settings
A new content-based medical image retrieval system based on wavelet transform and multidimensional wald-wolfowitz runs test
(2012-12-01)
Nakaram, Phatsarun
;
Leauhatong, Thurdsak
Recently, one of the authors proposed a new similarity measure, called weighted multidimensional Wald and Wolfowitz (MWW) runs test, for the content-based color image retrieval system. The algorithm outperforms conventional similarity measures for comparing two color images. In this paper, we propose a new content-based medical image retrieval system based on discrete wavelet transform (DWT) symlet and the weighted MWW runs test. The DWT is used to extracted texture features of the medical images. The weighted MWW runs test is used to compare distributions of texture features of two medical images. Our experiments were performed on 1,000 medical images from image retrieval in medical applications (IRMA). The experimental results show promisingly efficient to retrieve the medical images. ©2012 IEEE.
Some of the metrics are blocked by your
consent settings
A novel algorithm for detection human falling from accelerometer signal using wavelet transform and neural network
(2015-01-01)
Nuttaitanakul, Nitipat
;
Leauhatong, Thurdsak
Falls are major problems that could have happened to elderly, and could cause paralysis, hip fractures, or could lead to disabilities or accidental deaths. An algorithm for accurately detecting the falls is necessary in order to decrease the rate of disabilities or accidental deaths. In this paper, a new algorithm to detect the falls from the acceleration signal using the wavelet transform and multilayer perceptron neural network is proposed. In our experiments, 5 volunteers who were healthy with the ages between 21 to 25 year old were asked to attach a tri-axial accelerometer at the right side of their waists. The orientation of the accelerometer was vertical direction. Next, the volunteers were asked to perform 5 daily-life activities: 1) walking 2) standing up from a chair 3) sitting down on a chair 4) lying down on a bed and 5) getting up from a bed; and 5 falling activities: 1) falling forward 2) falling backward 3) falling to the right side 4) falling to the left side and 5) falling while standing up. The experimental results of the human activity classification that the proposed algorithm gave the maximum precision value (0.856). Moreover, it can be seen from the experiments of the falling detection that the proposed algorithm gave the maximum precision value (1.000)

Leauhatong, Thurdsak

Filters

Settings

Sort By

Results per page