IRJET- Smart Crop-Field Monitoring and Automation Irrigation System using IoT
0 likes•182 views
This document describes a proposed smart crop field monitoring and automated irrigation system using IoT technologies. The system uses sensors to monitor soil moisture levels and temperature in crop fields. A Raspberry Pi device collects data from the sensors via an IoT network. The system aims to automate irrigation by turning pumps on and off based on the sensor data, allowing for more precise watering that reduces water usage while maximizing crop yields. It also aims to allow remote monitoring of crop fields using the sensor data collected on the cloud. The system is meant to help modernize agriculture and make it more efficient through precision farming techniques enabled by IoT.
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 7976
SMART CROP-FIELD MONITORING AND AUTOMATION IRRIGATION
SYSTEM USING IoT
Dr. N. RAJESHKUMAR1, B. VAISHNAVI2, K. SARANYA3, C. SURABHI4
1Associate Professor, Department of ECE, KPR Institute of Engineering and Technology
2,3,4Student, Department of ECE, KPR Institute of Engineering and Technology
---------------------------------------------------------------------***----------------------------------------------------------------------
Abstract –Agriculture playsvitalroleinthedevelopmentof
agricultural country like India. Issues concerning agriculture
have been hindering the development of the country. The only
solution to this problem is smart agriculture by modernizing
the current traditional methods of agriculture. Hence the
proposed method aims at making agriculture smart using
automation and IoT technologies. Internet of things enables
various applications like crop growth monitoring and
selection, irrigation decision support, etc. A Raspberry-Pi
based automatic irrigation system is proposed to
modernization and improves productivity of the crop. The
main aim of this work is crop development at low quantity
water consumption and automatic pest identification. The
major advantage of this system is implementationofprecision
agriculture with cloud computing, thatwilloptimizetheusage
of water, pesticides while maximizing the yield of the crops.
Key Words: Precision Agriculture,IrrigationSystem,IoT,
Raspberry-Pi, Cloud Computing.
INTRODUCTION
India’s major source of income is from agriculture
sector and 70% of farmers and general people depend on
agriculture. In Indian irrigation system, the farmers have
chosen most of the methods manually such as grip, terraced,
ditch irrigation system etc. In order to improve the crop
productivity there is an urgent need to change manual
method to automation. Also, considering the water
availability throughout India, it is one of the valuable
resources to protect and save for future needs. Embedded
based automatic irrigation system is suitable for farmers
since it is available at low cost and can easily be installed.
This system helps the farmer by providing water to crops at
stringent time and quantity. Automation irrigation system
observes the moisture sensors and temperature variations
around the crop area that takes the precise time to turn the
motor ON or OFF. This automation avoids human errorsand
also it checks the soil moisture level. Internet of things
allows as to control the systems from remote area over the
internet. It can control the sensors which are usedatvarious
areas at blinding roads, railway grids and water control
systems. So it can avoid the human errors and errors
appearing during system operation. IoTisthe emergingarea
that penetrates over other area and made them efficient.Itis
developing now-a-days by inclusion of new sensors, sensor
network, RF based communications. It can exhibits smart
intelligence, precise sensing along with good identification.
The principle objective of this work is to present an
approach which minimize the unmerited usage of water and
automate the process of pest detection and rectification in
agricultural fields. It also involves developing a smart
irrigation method adoptable for water scarce location by
efficient usage of water resources thereby increasing the
overall productivity.
The paper aims a high precision monitoringthedata
and control agriculture with IoT technologies. The
Raspberry-Pi andcloud based IoT system to monitorthereal
time data from crop field. The system mainly focuses
moisturevariations correlatewithtemperaturechangesdata
by smart sensors and controls irrigation systems. Inorderto
provide cloud based computing to system the precision level
has increased as suitable to use the system by farmer.
LITERATURE SURVEY
A proliferation of literature is available in plant leaf
disease detection. We will highlight some of the key
configuration. A methodology for detecting plan diseases
early and accurately using diverse image processing
techniques has been proposed by Anand H. Kulkarni et al.
[1], in which Gabor filter has beenusedforfeature extraction
and ANN based classifier has been used for classification
with recognition rate up to 91%. Homogenize techniques
like canny and sobel filter has been used to identify the
edges by P. Revathi et al [2]. Then these extracted edge
features have been used in classification to identify disease
spots. Proposed homogeneous pixel counting technique for
cotton disease detection (HPCCDD) algorithmhasbeenused
for categorizing the diseases. They claim the accuracy of
98.1% over existing algorithm.
Asem Khmag [3], proposed a recognitionsystemfor
leaf images based on its leaf contourinwhichtherecognition
of plants is directly associated to society’s life. Leaves from
plants is proved to be a feasible source of information used
to identify plant species. The recognition system of leaves is
accomplished automatically using the experts of experts of
human being. The leaf contours of the same plants are
computed using support victor machine (SVM) where the
similar sequences of the same contours usually carry the
same features while different plant sequences havedifferent](https://image.slidesharecdn.com/irjet-v6i3977-190923051118/85/IRJET-Smart-Crop-Field-Monitoring-and-Automation-Irrigation-System-using-IoT-1-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 7977
contours. Tushare H Jaware et al. [4] proposed a novel, in
which improved K-means clustering technique is used to
solve the low-level image segmentation. Spatial gray-level
dependence matrices (SGDM) method has been used for
extracting statistical texture features by Sanjay B. Dhaygude
et al. [5] also RGB images has been converted into Hue
Saturation Value (HSV) color space representation.Mokhled
S. A. Tarawneh. [6] presented empirical investigation of
olive leaf spot disease by using auto-cropping segmentation
and fuzzy c-means classification .A new techniquehavebeen
proposed by S.M.Ramesh et al. [7] for enhancement of color
images by scaling the discrete cosine transform coefficients
which provides better enchancement compared to image
capture by digital camera.
In order to classify the grape and wheat diseases black
propagation networks have been used by Haiguang Wang et
al. [8] A. Menukaewjinda et al. [9] tried back propagation
neutral network (BPNN) for efficient grape leaf color
extraction and they also explore modified self-organizing
feature map (MSOFM) and genetic algorithm(GA)andfound
that these techniques were providing automatic adjustment
in parameters for grape leaf disease color extraction.
Support vector machine (SVM) have been found a very
promising technique to achieve efficient classificationofleaf
diseases.
EXISTING SYSTEM
In the present era one of the greatest problemfaced
by the world is water scarcity and agriculture being a
demanding occupation consumes plenty ofwater.Therefore
a system is required that uses water judiciously. Smart
irrigation systems estimate and measure diminution of
existing plant moisture in order to operate an irrigation
system, restoring water as needed while minimizing excess
water use.
The soil moisture based irrigation control uses
volumetric techniques which are relatively simple but these
quantities are related thr0ugh soil water characteristics
curve that is specific to a soil type. Also the sensors used
require routine maintenance for proper performance.
Intelligent automatic plant irrigation system concentrates
water in plants regularly without human monitoring usinga
moisture sensor. The circuitisbuiltarounda comparator op-
amp (M324) and a timer which drives a relay to switch on a
motor.
Fig 1 describes the smart irrigation system. The
system uses a hardware component, which is subjected to
variations with the environmental conditions. A real-time
wireless smart sensor array for scheduling irrigation
prototyped a real-time, smart sensor array for measuring
soil moisture and soil temperature that uses of-the-shelf
components are developed and evaluated for scheduling
irrigation in cotton. This system is specific for a crop and
hence its usage is limited. Proper scheduling of irrigation is
critical for efficient water management in crop production,
particularly under conditionsofwaterscarcity. Theeffectsof
the applied amount of irrigation water, irrigation frequency
and water use are particularly important. To improve water
efficiency there must be a proper irrigation scheduling
strategy. So our project devices a simple system, using a
microcontroller to automate the irrigation and watering of
small potted plants or crops with minimal manual
interventions.
Fig 1 SMART IRRIGATION SYSTEM
PROPOSED SYSTEM
The traditional approach of monitoring the
agricultural environment requires individuals manually
taking measurements and checking them at various times.
This system helps the farmer byproviding watertothecrops
at stringent time and quantity. It also avoids the human
errors and check soil moisture. It can exhibit smart
intelligence, precise sensing along with good identification.
There are five main steps used for the detection of
plant leaf diseases. The processing scheme consist of image
acquisition through digital camera or scanner, image pre-
processing includes image enchancement, image
segmentation where the affected and useful area are
segmented, feature extraction and classification. Lastly, the
presence of diseases on the plant leaf will be identified.Here
we present step by step approach for segmenting the
diseased image and to extract itsfeatures. Fig2describesthe
steps involved in identification of diseased leaf.
Raspberry pi
Plant
Sensors
Relay
Motor
Information
to farmer](https://image.slidesharecdn.com/irjet-v6i3977-190923051118/85/IRJET-Smart-Crop-Field-Monitoring-and-Automation-Irrigation-System-using-IoT-2-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 7979
REFERENCES
[1] Anand H. Kulkarni, Ashwin Patil R. K., “Applying image
processing technique to detect plant diseases”,
International Journal of Modern Engineering Research,
vol.2, Issue.5, pp: 3661-3664, 2012.
[2] P. Revathi, M. Hemalatha, “Classification of Cotton Leaf
Spot Diseases Using Image Processing Edge Detection
Techniques”, IEEE International conferenceof emerging
trends in Science, Engineering and Technology,pp-169-
173, No. 6, December 1990.
[3] Asem Khmag, “Recognition Systemfor LeafImageBased
on its leaf contour and centroid”, IEEE 15th Student
Conference on Research, AZ zawia, Libya.
[4] Tushar H. Taware, Ravindra. D. Badgujar and Prashant
G. Patil, “Crop disease detection using image
segmentation” ,National Conference on Advances in
Communication and Computing, World Journal of
Science and Technology, pp-190-194, Dhule,
Maharashtra, India, 2012.
[5] Prof. Sanjay B. Dhaygude, Mr. Nitin P. Khumbar,
“Agricultural plant leaf disease detection using image
processing “, International Joural of Advanced Research
in Electrical, Electronics and Instrumentation
Engineering, S & S Publication vol. 2, Issue 1, pp:599-
602, 2013.
[6] Mokhled S. Tarawneh “An empirical investigation of
olive leaf spotdiseaseusingauto-croppingsegmentation
and Fuzzy c-means classification”, World Applied
Sciences Journal, vol. 23,no. 9,andpp:1207-1211,2013.
[7] S. M. Ramesh, Dr. A. Shanmugan, “A new technique for
enhancement of color images by scaling the discrete
cosine transform coefficients”, International Journal of
Electronics and CommunicationTechnology,IJECTvol 2,
Issue 1, March 2011.
[8] Haiguang Wang, Guanlin Li, Zhanhong Ma, XIalong Li,
“Image recognition of plant diseases based on back
propagation networks, 5th International Conference on
Image and Signal Processing, pp: 894-900, Chongqing,
China, 2012.
[9] A. Menukaewjinda, P. Kumsawat, K. Attakitmongcol, A.
Srikaew, “ grape leaf disease detection from colorimage
using hybrid intelligent system”, Proceedings of
Electrical Engineering/Electronics, Computer,
Telecommunication and Information Technology, vol 1,
pp: 513-516,Krabi, Thailand, 2008.](https://image.slidesharecdn.com/irjet-v6i3977-190923051118/85/IRJET-Smart-Crop-Field-Monitoring-and-Automation-Irrigation-System-using-IoT-4-320.jpg)
IRJET- Smart Crop-Field Monitoring and Automation Irrigation System using IoT
- 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 7976 SMART CROP-FIELD MONITORING AND AUTOMATION IRRIGATION SYSTEM USING IoT Dr. N. RAJESHKUMAR1, B. VAISHNAVI2, K. SARANYA3, C. SURABHI4 1Associate Professor, Department of ECE, KPR Institute of Engineering and Technology 2,3,4Student, Department of ECE, KPR Institute of Engineering and Technology ---------------------------------------------------------------------***---------------------------------------------------------------------- Abstract –Agriculture playsvitalroleinthedevelopmentof agricultural country like India. Issues concerning agriculture have been hindering the development of the country. The only solution to this problem is smart agriculture by modernizing the current traditional methods of agriculture. Hence the proposed method aims at making agriculture smart using automation and IoT technologies. Internet of things enables various applications like crop growth monitoring and selection, irrigation decision support, etc. A Raspberry-Pi based automatic irrigation system is proposed to modernization and improves productivity of the crop. The main aim of this work is crop development at low quantity water consumption and automatic pest identification. The major advantage of this system is implementationofprecision agriculture with cloud computing, thatwilloptimizetheusage of water, pesticides while maximizing the yield of the crops. Key Words: Precision Agriculture,IrrigationSystem,IoT, Raspberry-Pi, Cloud Computing. INTRODUCTION India’s major source of income is from agriculture sector and 70% of farmers and general people depend on agriculture. In Indian irrigation system, the farmers have chosen most of the methods manually such as grip, terraced, ditch irrigation system etc. In order to improve the crop productivity there is an urgent need to change manual method to automation. Also, considering the water availability throughout India, it is one of the valuable resources to protect and save for future needs. Embedded based automatic irrigation system is suitable for farmers since it is available at low cost and can easily be installed. This system helps the farmer by providing water to crops at stringent time and quantity. Automation irrigation system observes the moisture sensors and temperature variations around the crop area that takes the precise time to turn the motor ON or OFF. This automation avoids human errorsand also it checks the soil moisture level. Internet of things allows as to control the systems from remote area over the internet. It can control the sensors which are usedatvarious areas at blinding roads, railway grids and water control systems. So it can avoid the human errors and errors appearing during system operation. IoTisthe emergingarea that penetrates over other area and made them efficient.Itis developing now-a-days by inclusion of new sensors, sensor network, RF based communications. It can exhibits smart intelligence, precise sensing along with good identification. The principle objective of this work is to present an approach which minimize the unmerited usage of water and automate the process of pest detection and rectification in agricultural fields. It also involves developing a smart irrigation method adoptable for water scarce location by efficient usage of water resources thereby increasing the overall productivity. The paper aims a high precision monitoringthedata and control agriculture with IoT technologies. The Raspberry-Pi andcloud based IoT system to monitorthereal time data from crop field. The system mainly focuses moisturevariations correlatewithtemperaturechangesdata by smart sensors and controls irrigation systems. Inorderto provide cloud based computing to system the precision level has increased as suitable to use the system by farmer. LITERATURE SURVEY A proliferation of literature is available in plant leaf disease detection. We will highlight some of the key configuration. A methodology for detecting plan diseases early and accurately using diverse image processing techniques has been proposed by Anand H. Kulkarni et al. [1], in which Gabor filter has beenusedforfeature extraction and ANN based classifier has been used for classification with recognition rate up to 91%. Homogenize techniques like canny and sobel filter has been used to identify the edges by P. Revathi et al [2]. Then these extracted edge features have been used in classification to identify disease spots. Proposed homogeneous pixel counting technique for cotton disease detection (HPCCDD) algorithmhasbeenused for categorizing the diseases. They claim the accuracy of 98.1% over existing algorithm. Asem Khmag [3], proposed a recognitionsystemfor leaf images based on its leaf contourinwhichtherecognition of plants is directly associated to society’s life. Leaves from plants is proved to be a feasible source of information used to identify plant species. The recognition system of leaves is accomplished automatically using the experts of experts of human being. The leaf contours of the same plants are computed using support victor machine (SVM) where the similar sequences of the same contours usually carry the same features while different plant sequences havedifferent
- 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 7977 contours. Tushare H Jaware et al. [4] proposed a novel, in which improved K-means clustering technique is used to solve the low-level image segmentation. Spatial gray-level dependence matrices (SGDM) method has been used for extracting statistical texture features by Sanjay B. Dhaygude et al. [5] also RGB images has been converted into Hue Saturation Value (HSV) color space representation.Mokhled S. A. Tarawneh. [6] presented empirical investigation of olive leaf spot disease by using auto-cropping segmentation and fuzzy c-means classification .A new techniquehavebeen proposed by S.M.Ramesh et al. [7] for enhancement of color images by scaling the discrete cosine transform coefficients which provides better enchancement compared to image capture by digital camera. In order to classify the grape and wheat diseases black propagation networks have been used by Haiguang Wang et al. [8] A. Menukaewjinda et al. [9] tried back propagation neutral network (BPNN) for efficient grape leaf color extraction and they also explore modified self-organizing feature map (MSOFM) and genetic algorithm(GA)andfound that these techniques were providing automatic adjustment in parameters for grape leaf disease color extraction. Support vector machine (SVM) have been found a very promising technique to achieve efficient classificationofleaf diseases. EXISTING SYSTEM In the present era one of the greatest problemfaced by the world is water scarcity and agriculture being a demanding occupation consumes plenty ofwater.Therefore a system is required that uses water judiciously. Smart irrigation systems estimate and measure diminution of existing plant moisture in order to operate an irrigation system, restoring water as needed while minimizing excess water use. The soil moisture based irrigation control uses volumetric techniques which are relatively simple but these quantities are related thr0ugh soil water characteristics curve that is specific to a soil type. Also the sensors used require routine maintenance for proper performance. Intelligent automatic plant irrigation system concentrates water in plants regularly without human monitoring usinga moisture sensor. The circuitisbuiltarounda comparator op- amp (M324) and a timer which drives a relay to switch on a motor. Fig 1 describes the smart irrigation system. The system uses a hardware component, which is subjected to variations with the environmental conditions. A real-time wireless smart sensor array for scheduling irrigation prototyped a real-time, smart sensor array for measuring soil moisture and soil temperature that uses of-the-shelf components are developed and evaluated for scheduling irrigation in cotton. This system is specific for a crop and hence its usage is limited. Proper scheduling of irrigation is critical for efficient water management in crop production, particularly under conditionsofwaterscarcity. Theeffectsof the applied amount of irrigation water, irrigation frequency and water use are particularly important. To improve water efficiency there must be a proper irrigation scheduling strategy. So our project devices a simple system, using a microcontroller to automate the irrigation and watering of small potted plants or crops with minimal manual interventions. Fig 1 SMART IRRIGATION SYSTEM PROPOSED SYSTEM The traditional approach of monitoring the agricultural environment requires individuals manually taking measurements and checking them at various times. This system helps the farmer byproviding watertothecrops at stringent time and quantity. It also avoids the human errors and check soil moisture. It can exhibit smart intelligence, precise sensing along with good identification. There are five main steps used for the detection of plant leaf diseases. The processing scheme consist of image acquisition through digital camera or scanner, image pre- processing includes image enchancement, image segmentation where the affected and useful area are segmented, feature extraction and classification. Lastly, the presence of diseases on the plant leaf will be identified.Here we present step by step approach for segmenting the diseased image and to extract itsfeatures. Fig2describesthe steps involved in identification of diseased leaf. Raspberry pi Plant Sensors Relay Motor Information to farmer
- 3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 7978 Fig 2 DISEASED LEAF DETECTION The scale invariant feature transform (SIFT) is a feature detection algorithm in computer visiontodetectand describe local features and images. SIFTkeypointsofobjects are first extracted from a set of reference images and stored in a database. An object is recognized in a new image by individually comprising each feature from the new image to this database and finding candidate matchingfeatures based on Euclidean distance of their feature vectors from the full set of matches, subsets of key points that agree on the objects and its location, scale and its orientation in the new image are identified to filter out good matches. The determination of consistent clusters is performed rapidly by using an efficient hash table implementations of the generalized Hough transform. Each clustersofthreeor more features that agree on an object and its pores is then subject to future. Detailed model verification and subsequently out lairs are discarded. Finally the probability that a particular set of features indicate the presence of an object is computed, given the accuracy of fit and number of probable false matches. Object matches that pass all tests can be identified as correct with high confidence. RESULT AND DISCUSSION The real time results and the status of the system were taken on 4G mobile phones. The system displays the temperature and humidity level of the crop field based on the input from the temperature and humidity sensors respectively. The status of crop health canalsobemonitored from remote places by using image recognitionsystem.Here two sensors are used to control the irrigation system so that trouble shooting can easily bedonewheneveritisnecessary. Threshold voltages are chosen for calibration of the sensors by considering the past month temperature and soil moisture values. Threshold values vary depending on the crop and plantation. Graphical output is shown in Fig 3. Fig 3 OUTPUT CONCLUSION A precision agriculture irrigation system is developed with low complex circuitry. Two sensors and raspberry pi microcontrollers are successfullyinterfacedAll observations and experimental tests proves that proposed system is a complete solution to field activities, irrigation problems etc. Implementation of such a system in a fieldwill definitely help to improve the field of crops and the overall production. With the help of this system irrigation system can be completely automated and also provides real time information about the land and crops that will help farmers to increase the production rate. Image Acquisition Image pre- processing Image Segmentation using SIFT algorithm Feature Extraction Classification
- 4. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 03 | Mar 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 7979 REFERENCES [1] Anand H. Kulkarni, Ashwin Patil R. K., “Applying image processing technique to detect plant diseases”, International Journal of Modern Engineering Research, vol.2, Issue.5, pp: 3661-3664, 2012. [2] P. Revathi, M. Hemalatha, “Classification of Cotton Leaf Spot Diseases Using Image Processing Edge Detection Techniques”, IEEE International conferenceof emerging trends in Science, Engineering and Technology,pp-169- 173, No. 6, December 1990. [3] Asem Khmag, “Recognition Systemfor LeafImageBased on its leaf contour and centroid”, IEEE 15th Student Conference on Research, AZ zawia, Libya. [4] Tushar H. Taware, Ravindra. D. Badgujar and Prashant G. Patil, “Crop disease detection using image segmentation” ,National Conference on Advances in Communication and Computing, World Journal of Science and Technology, pp-190-194, Dhule, Maharashtra, India, 2012. [5] Prof. Sanjay B. Dhaygude, Mr. Nitin P. Khumbar, “Agricultural plant leaf disease detection using image processing “, International Joural of Advanced Research in Electrical, Electronics and Instrumentation Engineering, S & S Publication vol. 2, Issue 1, pp:599- 602, 2013. [6] Mokhled S. Tarawneh “An empirical investigation of olive leaf spotdiseaseusingauto-croppingsegmentation and Fuzzy c-means classification”, World Applied Sciences Journal, vol. 23,no. 9,andpp:1207-1211,2013. [7] S. M. Ramesh, Dr. A. Shanmugan, “A new technique for enhancement of color images by scaling the discrete cosine transform coefficients”, International Journal of Electronics and CommunicationTechnology,IJECTvol 2, Issue 1, March 2011. [8] Haiguang Wang, Guanlin Li, Zhanhong Ma, XIalong Li, “Image recognition of plant diseases based on back propagation networks, 5th International Conference on Image and Signal Processing, pp: 894-900, Chongqing, China, 2012. [9] A. Menukaewjinda, P. Kumsawat, K. Attakitmongcol, A. Srikaew, “ grape leaf disease detection from colorimage using hybrid intelligent system”, Proceedings of Electrical Engineering/Electronics, Computer, Telecommunication and Information Technology, vol 1, pp: 513-516,Krabi, Thailand, 2008.