KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 15

Some of the metrics are blocked by your
consent settings
Water Level Monitoring and Evacuation Guideline Using Ant Colony Optimization on Mobile Application
(2020-08-01)
Kimpan, Warangkhana
;
Kasetvetin, Sirawich
;
Kimpan, Chom
The most natural disasters that have happened in Thailand are storm and flood problems. The people who live near water sources have no warning about the overflowing of water nearby, so they cannot evacuate or get help in time. Thus, there is always a high risk of losing properties or lives. In order to alleviate the losses, this paper proposes water level monitoring on Android application from Internet of Things devices and the guideline for evacuation by applying Ant Colony Optimization which is inspired by the real ant colony. Internet of Things devices are used to monitor the water levels in community for the user who lives near the water sources or near the places which have high risk of flooding. The Hydrostatic level sensors are placed in the water basin near the community to measure the height of the water which can also be observed in real time from mobile application. When the height of the water reaches the critical value that was set in the application, it sends notifications to the user. Moreover, Line bot is used to let the user knows the potential risks from rising water levels. At the critical level, the user needs to evacuate to a safe place located nearby. The application will guide the user to follow the direction to the most safety destination. In case of many people are already evacuated in one place and it reached the maximum amount of limitation, the application will change the recommendation direction to other places nearby using Ant Colony Optimization algorithm for making decisions.
Some of the metrics are blocked by your
consent settings
Detection of hard exudate for diabetic retinopathy using unsupervised classification method
(2020-07-01)
Maneerat, Noppadol
;
Thongpasri, Teerapon
;
Narkthewan, Athasart
;
Kimpan, Chom
Diabetic retinopathy (DR) causes retinal disorders such as blood vessel blockage, the leaks of blood, and the proteins in water bleeding into the tissues of retina. All of the symptoms lead to the destruction of retina resulting in reduced visibility or finally lose vision. Therefore, this study presents an image processing method to extract hard exudates in the retinal image, which is a serious symptom of diabetic retinopathy using an unsupervised classification method. The proposed hard exudates extraction method composes of 3 steps. Firstly, the optic disc similar to hard exudate is eliminated from the retinal image. Subsequently, the green channel of the RGB color model is selected for data analysis because it represents all hard exudates better than the red and blue channels. The features of hard exudates in the retinal image are then extracted by various methods such as dilation, erosion, entropy analysis, and standard deviation analysis and it also appeared in many dimensions. Finally, the proposed method uses k-mean, which is an unsupervised classification technique for hard exudates clustering. The determination of hard exudates from the retinal image is achieved using two datasets (DIARETDB0 and DIARETDB1). These datasets are usually used for algorithm efficiency analysis to retinal image evaluation. The results show that the maximum specificity is approximate 97%. It indicates that the proposed method can be applied for the automatic detection of diabetic retinopathy.
Some of the metrics are blocked by your
consent settings
Diabetic retinopathy image analysis using radial inverse force histograms
(2017-07-02)
Kimpan, Somchok
;
Maneerat, Noppadol
;
Kimpan, Chom
This research article discusses the process of increasing the efficiency of image retrieval based on details from the database of the retinal image of diabetic retinopathy patients. The image retrieval uses Radial Inverse Force Histograms which can improve the performance of the image retrieval process in using the details of the retinal image. The value of Radial Inverse Force Histograms can be used to retrieve the similar image. The experimental results indicated that using Radial Inverse Force Histograms can detect the diabetic eyes. Moreover, the image retrieval system is useful in diagnosis the retinal disorders for effectively screen or separate the diabetic retinopathy patients.
Some of the metrics are blocked by your
consent settings
Invariant range image multi-pose face recognition using gradient face, membership matching score and 3-layer matching search
(2005-01-01)
Pansang, Seri
;
Attachoo, Boonwat
;
Kimpan, Chom
;
Sato, Makoto
The purpose of this paper is to present the novel technique to solve the recognition errors in invariant range image multi-pose face recognition. The scale, center and pose error problems were solved by using the geometric transform [13]. Range image face data (RIFD) was obtained from a laser range finder and was used in the model to generate multi-poses. Each pose data size was reduced by linear reduction. The reduced RIFD was transformed to the gradient face model for facial feature image extraction and also for matching using the Membership Matching Score model. Using this method, the results from the experiment are acceptable although the size of gradient face image data is quite small (659 elements). Three-Layer Matching Search was the algorithm designed to reduce the access timing to the most accurate and similar pose position. The proposed algorithm was tested using facial range images from 130 people with normal facial expressions and without eyeglasses. The results achieved the mean success rate of 95.67 percent of ±12 degrees up/down and left/right (UDLR) and 88.35 percent of ±24 degrees UDLR. Copyright © 2005 The Institute of Electronics, Information and Communication Engineers.
Some of the metrics are blocked by your
consent settings
Adaptive watermarking in spatial domain for still image
(2004-12-01)
Kimpan, Somchok
;
Lasakul, Attasit
;
Kimpan, Chom
In this paper, watermarking for still image is proposed Image watermarking is performed in spatial domain that not only easy but also good result. A watermark image as binary image is embedded onto a original image by using method that gray levels of pixels in original image blocks is modified to appropriate an intensity of block. A variation of watermark image bits in order to embed the original image block selected affects to embedded block intensity and also it depends on original image block intensity. The block size is adapted as intensity of original image and capacity of watermark image in order to embed. As method of varying block size proposed, the effect of block size adaptation is good and also watermark image is robust to a number types of degradation. As the proposed method, qualify of the original image is at least affected.
Some of the metrics are blocked by your
consent settings
Outage probability and BER statistics of the reverse link CDMA system with imperfect power control over multipath fading channel
(2002-12-01)
Kumpairee, Chalermpon
;
Kimpan, Chom
;
Pin-ngern, Ouen
;
Noppakeepong, Suthichai
The capacity of the reverse link CDMA system is presented. Gaussian and Lognormal approximation are the methods for determination of system capacity. The average probability of bit error (BER) is also investigated. An analysis in this paper, the parameter in the number of resolvable paths of multipath signal over Rayleigh fading and Frequency-Selective channel is expressed. In addition, we also show the effect of power control errors.
Some of the metrics are blocked by your
consent settings
The effect of fading on the erlang capacity of imperfect power control CDMA cellular system
(2002-12-01)
Omsin, Somchai
;
Kimpan, Chom
;
Pin-Ngern, Ouen
;
Noppakeepong, Suthichai
This paper presents an approach to the evaluation of the reverse link capacity of a CDMA cellular system, which based on using Gaussian and Lognormal approximation are methods for approximate the capacity of system. We include the fading channel multipath intensity profile (MIP) shape factor in the capacity formula. The system condition is an imperfect power control and Rayleigh multipath fading channel.
Some of the metrics are blocked by your
consent settings
Reduction of the gradient noise in adaptive algorithm for adaptive noise canceller with parallel block structure
(2002-12-01)
Kidakorn, Pongjai
;
Rattanakoch, Wiren
;
Kimpan, Chom
;
Pin-ngern, Ouen
;
Noppanakeepong, Suthichai
An adaptive algorithm for detecting single sinusoid of unknown frequency corrupted by Gaussian noise was proposed in 1989 by Nishimura et al. using IIR band pass filter with a variable center frequency and parallel block structure for fast processing [1]. In 1996 the adaptive algorithm was investigated and solved the problem of several input frequency being impossible to converge using the new algorithm proposed by Takahashi et al. [2]. However, the control signal generated by the new algorithm used for adjusting the center frequency of band pass filter is still rattled in spite of its converge. In this paper, in addition to using output in adaptive algorithm as proposed, the input signal is used as auxiliary or reference signal. By mean of this way the rattle on the control signal can be reduced significantly with the same convergence rate and a few computation complexity added to it.
Some of the metrics are blocked by your
consent settings
Handwritten Thai character recognition using Fourier descriptors and genetic neural networks
(2002-01-01)
Phokharatkul, Pisit
;
Kimpan, Chom
This article presents a method to solve the rotated and scaling character recognition problem using Fourier descriptors and genetic neural networks. The contours of character image are extracted and separated between the outer contour and inner or loop contours. The loop contours are a special characteristic of Thai characters, called the head of the character. The special features of Thai characters (loop contours) are used at the rough classification stage, and Fourier descriptors with genetic neural networks are used at the fine classification stage. The Fourier descriptors detect the outer contour of a character and it is fed to network. These features are recognized by a multilayer neural network. Genetic algorithms (GAs) are utilized to help compute the weights of the neural network optimally and reduce uncertain states in the neural networks output. Experimental results have shown that the combination of the Fourier descriptors with genetic neural networks, loop features, and local curvature charateristics of similar characters are powerful tools for successfully classifying Thai characters. The recognition rate by this method is 99.12% for 1200 examples of handwritten Thai words (a total of 13,500 characters) written by 60 persons.
Some of the metrics are blocked by your
consent settings
Printed thai character recognition using Fuzzy-Rough Sets
(2001-12-01)
Kasemsiri, Watjanapong
;
Kimpan, Chom
This paper proposes the method of using the Fuzzy-Rough Sets for the recognition of Thai Characters. In our work we divide the classification process into 2 levels, coarse and fine classification. Both levels of classification have the same processes, applying Rough Set's lower approximation and then using Fuzzy-Rough sets. The different point between those two levels is the features of inputted data used for classifying. There are 40 coarse groups and some of them need not to pass through the second level of classification. We trained this system with 2816 training samples, which composed of 4 fonts and 4 sizes characters. The system is tested with unknown sample, which composed of 7 fonts and 7 sizes characters, 4 fonts and 4 sizes of the training sample are inclusive. The accuracy of this proposed system is as high as 89%.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results