KMITL

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

Browse

Search Results

Now showing 1 - 10 of 10

Some of the metrics are blocked by your
consent settings
New upper and lower bounds line of sight path loss model for mobile propagation in buildings
(2008-03-03)
Phaiboon, Supachai
;
Phokharatkul, Pisit
;
Somkuarnpanit, Suripon
This paper proposes a method to predict line-of-sight (LOS) path loss in buildings. We performed measurements in two different types of buildings at a frequency of 1.8 GHz and propose a new path loss model with its upper and lower bounds. The upper and lower bounds depend on max and min values of sampled path loss data. This makes our model limit path loss within the boundary lines. The model includes time-variant effects from the object movement from people in the building and cars in parking areas. These influence reasonably on wave propagation. The results have shown that the proposed model will be useful for the design of the indoor wireless communication systems. © 2007 Elsevier GmbH. All rights reserved.
Some of the metrics are blocked by your
consent settings
Mobile path loss prediction with image segmentation and classification
(2007-10-01)
Phaiboon, Supachai
;
Phokharatkul, Pisit
;
Kittithamavongs, Piti
This paper presents an intelligent radio wave propagation prediction model by using the 2-dimension aerial image which is taken from the actual area. An suburban area is used as examples. The prediction procedure is done in three steps. First, the image segmentation is employed to divide the area image into subgroups by using Maximum Likelihood algorithm. The second step uses the subgroup images from step 1 to determine the parameters for the fuzzy model that we use to classify the propagation areas. The final step is to plot the path loss contour on the image so the cellular cell site can be chosen. The research results show that the proposed segmentation provides an accuracy of 80-90% compared with the actual area. Therefore, cell site selection can be designed on the 2-dimension aerial map with the error less than 8 dB.
Some of the metrics are blocked by your
consent settings
Muti-layer fuzzy logic sets for mobile path loss in forests
(2007-08-08)
Phaiboon, Supachai
;
Phokharatkul, Pisit
;
Somkuarnpanit, Suripon
Mobile path loss prediction in forests using Multi-Layer fuzzy logic system (MLFS) is presented in this paper. The MLFS consists of a tree density decision layer which is a supervisory layer in order to select the next layers using fuzzy decision. The sub-predictions use a set of rule base that provide path loss prediction in each case of an environment. These crisp inputs are classified by the fuzzifier to fuzzy sets and then inferenced using fuzzy linguistic rule base into multi - output path loss slopes via de-fuzzifier. For this study, we classified the terrains into high-, medium-, low- density and grass area and used the simple linguistic rules for prediction of the path loss slopes. We performed measurements in different forest densities at a frequency of 1.8 GHz with base station antenna height in a range of 3, 4, and 5 m above ground while the receiving antenna height was fixed at 1.8 m above ground. The results have shown that fuzzy logic approach provides more accurate prediction of path loss slopes than that of conventional empirical mathematic models. The proposed models will be useful for the local wireless network and micro-cell design of mobile communication systems in forests. ©2006 IEEE.
Some of the metrics are blocked by your
consent settings
Mobile path loss prediction model for forest areas using MIMO fuzzy logic system
(2006-09-01)
Phaiboon, Supachai
;
Phokharatkul, Pisit
;
Kittitummawong, Piti
;
Somkuarnpanit, Suripon
This paper proposes a method to predic mobile path loss in forests using MIMO fuzzy logic system. The multi-input was classified into seven input parameters defined as, X1 is number of trees/m<sup>2</sup> and X2 to X7 are tree structure parameters. These crisp inputs are classified by fuzzifier to fuzzy sets and then inferenced using fuzzy linguistic rule base into multi - output path loss slopes via de-fuzzifier. For this study, we classified the terrains into high-, medium-, low- density and grass area and used the simple linguistic rules for prediction the path loss slopes. We performed measurements in different forest densities at a frequency of 1.8 GHz with base station antenna height in a range of 3, 4, and 5 m above ground while the receiving antenna height was fixed at 1.8 m above ground. The results have shown that fuzzy logic approach provides more accurate prediction of path loss slopes than that of conventional empirical mathematic model. The proposed models will be useful for the local wireless network and micro-cell design of mobile communication systems in forests.
Some of the metrics are blocked by your
consent settings
Microwave line-of-sight path loss prediction on urban street by fuzzy logic model
(2005-12-01)
Phaiboon, Supachai
;
Phokharatkul, Pisit
;
Somkuarnpanit, Suripon
;
Boonpiyathud, Sitchai
This paper proposes a method to model the path loss characteristics on urban streets in the microwave band. We applied the concept of fuzzy logic to predict path losses. The input fuzzy sets were classified into five sets, namely 1) Distance between transmitter and receiver, 2) Frequency, 3) Time of day, 4) Transmitting antenna height and 5) Receiving antenna height. These inputs are then inferenced into output path loss via linguistic rules which were trained by measurement. To check the proposed model, we compared the fuzzy prediction with the same and an another measurement. The results show that the fuzzy logic models provided a better prediction. © 2005 IEEE.
Some of the metrics are blocked by your
consent settings
Breakpoint distance los path loss model for indoor communication using anfis
(2005-12-01)
Phaiboon, Supachai
;
Phokharatkul, Pisit
;
Somkurnpanich, Suripon
Breakpoint distance LOS model for indoor wireless communication is presented in this paper. The model is based on the determination of the breakpoint distance and % of wall area between the transmitter and the receiver. The propagation path losses are predicted with adaptive neuro - fuzzy inference systems (ANFIS), trained with measurements at the frequency of 1.8 GHz. The advantage of the ANFIS with hybrid least squares and gradient descent algorithms is fast convergence compared with original neural network. Comparison of our predicted results to measurements indicate that improvements in accuracy over conventional empirical models are achieved.
Some of the metrics are blocked by your
consent settings
Upper-and lower-bound path-loss modeling for indoor line-of-sight environments
(2005-01-01)
Phaiboon, Supachai
;
Phokharatkul, Pisit
;
Somkuarnpanit, Suripon
;
Boonpiyathud, Sitchai
This paper proposes a method to predict line-of-sight (LOS) path loss in buildings. We performed measurements in two different type of buildings at a frequency of 1.8 GHz and propose upper-and-lower bounds path loss models which depend on max and min values of sample path loss data. This makes our models limit path loss within the boundary lines. The models include time-variant effects such as people moving and cars in parking areas with their influence on wave propagation that is very high. The results have shown that the proposed models will be useful for the system and cell design of indoor wireless communication systems. © 2005 IEEE.
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
Object recognition using characteristic component and genetic algorithms
(2001-12-01)
Phokharatkul, Pisit
;
Foitong, Sombut
;
Kimpan, Chom
Object recognition is an essential part of the computer vision system. This paper uses a genetic algorithm to select a model shape that has the best match with invariant input images. The contour shape of an image is described in term of shape features such as the straight lines, curves, and angles. In the first step of the method, the shape feature is identified by analyzing the contour, and measuring the invariant properties of the normalized features. The second step obtains coding of the shape features as attributed strings and stores this in the database of system. Finally, the procedure in the first and second step is used to obtain the input model and uses a genetic algorithm to find the best-matched model with an input model by searching the best-matched model from the database. From this method we can recognize an unknown object. The algorithm is tested with 20 objects rotated in different orientations. The results are encouraging, since we achieved 95.9% correct recognition.
Some of the metrics are blocked by your
consent settings
Recognition of handprinted Thai characters using the cavity features of character based on neural network
(1998-12-01)
Phokharatkul, Pisit
;
Kimpan, Chom
This paper describes a method of cavity features and neural network for recognizing handprinted Thai characters. The recognition process is implemented using mathematical morphology to detect the cavity features of patterns, and learning to classify by neural network. The stage of recognition divided into three stages. First, the handprinted Thai characters are segmented from the sentence into three different level groups. Then, the cavity features of each handprinted Thai character are detected, and counted the numbers by the Euler number method. Finally, uses the majority area of the cavity features for computed the feature codes of the characters in each class. These codes are trained by neural network for learning in the classification characters.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results