SlideShare a Scribd company logo
1 of 6
Download to read offline
http://www.iaeme.com/IJCIET/index.asp 1745 editor@iaeme.com
International Journal of Civil Engineering and Technology (IJCIET)
Volume 10, Issue 01, January 2019, pp. 1745–1750, Article ID: IJCIET_10_01_161
Available online at http://www.iaeme.com/ijciet/issues.asp?JType=IJCIET&VType=10&IType=1
ISSN Print: 0976-6308 and ISSN Online: 0976-6316
©IAEME Publication Scopus Indexed
A WRAPPER BASED FEATURE SELECTION
APPROACH USING BEES ALGORITHM FOR
EXTREME RAINFALL PREDICTION VIA
WEATHER PATTERN RECOGNITION
THROUGH SVM CLASSIFIER
V. Karunakaran
Department of Computer Science and Engineering,
Karunya Institute of Technology and Sciences, Coimbatore, India
S. Iwin Joseph
Department of Computer Science and Engineering,
Karunya Institute of Technology and Sciences, Coimbatore, India
Ravi Teja
Department of Computer Science and Engineering,
Karunya Institute of Technology and Sciences, Coimbatore, India
M. Suganthi
Department of Electronics and Communication Engineering,
Mahendra College of Engineering, Salem, India
V. Rajasekar
Department of Computer Science and Engineering,
AMC Engineering College, Bangalore, India
ABSTRACT
Rainfall prediction is a major problem in metrological department and it is closely
associated with the economy and life of human. Accuracy of rainfall prediction is a
very important for countries like india, because Indian economy is mainly dependent
up on the agriculture. Most of the statistical methods are unsuccessful due to dynamic
nature of atmosphere. In this paper, SVM classifier is used for classification, before
SVM classifier, bees algorithm is used for feature selection. Keeping all the features
and instances in the training set is not a good approach for better classification
because all the features are not contributing more information during classification,
removing those features will not affect any classification accuracy. The experimental
result shows that the proposed method provides better detection rate, false positive
A Wrapper Based Feature Selection Approach using Bees Algorithm for Extreme Rainfall
Prediction via Weather Pattern Recognition Through SVM Classifier
http://www.iaeme.com/IJCIET/index.asp 1746 editor@iaeme.com
rate, accuracy rate and less training time of classifier what we obtained with entire
dataset.
Key words: Support Vector machine, Feature selection, Bees algorithm, Rainfall.
Cite this Article: V. Karunakaran, S. Iwin Joseph, Ravi Teja, M. Suganthi,
V. Rajasekar. A Wrapper Based Feature Selection Approach using Bees Algorithm for
Extreme Rainfall Prediction via Weather Pattern Recognition Through SVM
Classifier, International Journal of Civil Engineering and Technology (IJCIET) 10(1),
2019, pp. 1745–1750.
http://www.iaeme.com/IJCIET/issues.asp?JType=IJCIET&VType=10&IType=1
1. INTRODUCTION
Rainfall predication is very supportive to avoid flood, that will save lives of human and it also
helps to manage resources of water. Rainfall prediction also helps the farmers to manage their
crops better. Rainfall prediction is a challenging task for meteorological department due to
dynamic change of atmosphere. Most of the researchers tried with lot of machine learning
algorithms for rainfall predictions and they achieved some fair prediction result. Prashant
Goswami et al proposed artificial neural network for rainfall prediction and the experimental
shows good prediction accuracy of annual rainfall compared to the existing neural networks
[1]. Venkatesan et al used error back propagation neural network for rainfall prediction. The
experimental results compared with some existing statistical methods, error back propagation
neural network out performed in prediction accuracy [2]. A.K shai used artificial neural
network with error back propagation algorithm for rainfall prediction. The model is compared
with few statistical methods and this method provides better prediction rate and less Mean
squared value [3]. Ninan Sajeeth Philip et al used ABF neural network for rainfall prediction
and the method is compared with some statistical methods, ABF neural network is out
performed [4]. Ninan Sajeeth Philip et al used adaptive basis function network for rainfall
prediction and the method is compared with some traditional methods like principal
component analysis and spectral analysis. Adaptive basis function network provides good
prediction results [5]. Norraseth Chantasut et al used artificial neural network for rainfall
predication in the area of Chao Phraya River. The experimental result shows, 96.6% of
prediction accuracy is obtained by the model while using training dataset and 96.9% of
prediction accuracy while using testing dataset [6]. V.K.Somvanshi et al used artificial neural
network and ARIMA techniques for rainfall prediction. The experimental result shows
artificial neural network and ARIMA techniques is a promising tool for annual rainfall
predictions [7]. S. Chattopadhyay et al used multilayer perceptron for rainfall prediction. The
experimental result shows better prediction accuracy compared to the conventional methods
[8]. Smita Kulkarni et al discussed three prediction methods based on backpropagation neural
network learning rules 1. Momentum learning, 2. Conjugate gradient descent (CGD) learning,
and 3. Levenberg -- Marquardt (LM) learning. Among the three prediction methods conjugate
gradient descent methods provides better prediction accuracy compared to momentum
learning and LM learning [9]. P. Guhathakurta used deterministic artificial neural network
for rainfall prediction. This method is compared with single time series, the derivation of
smaller scale (sub-divisions) forecast model may be more useful than the all India forecast
[10]. Most of the researchers tried with different approaches for rainfall prediction, but
still need some improvement in prediction accuracy. In this paper, bees algorithm used for
feature selection, after feature selection, the obtained dataset is given to artificial neural
network for prediction. The proposed system provides better prediction rate and less mean
square value.
V. Karunakaran, S. Iwin Joseph, Ravi Teja, M. Suganthi, V. Rajasekar
http://www.iaeme.com/IJCIET/index.asp 1747 editor@iaeme.com
The rest of the paper is organized as follows: Section 2 presents introduction to wrapper
method and bees algorithm. Section 3 presents overall architecture of the proposed system.
Section 4 presents feature selection using bees algorithm. Section 5 presents experimental
results. Finally section 6 presents conclusion.
2. INTRODUCTION TO WRAPPER METHOD AND BEES
ALGORITHM
Feature selection is mostly carried out by two methods, 1. Filter method and 2. Wrapper
method. In filter method, feature selection is carried out by selection function. It is not
dependent upon the classification accuracy. In wrapper method, feature selection is carried
out by classification accuracy. Most of the wrapper method provides better classification
accuracy compared to the filter methods. Bees algorithm is a population-based search
algorithm and it was developed by Pham, Ghanbarzadeh and et al. in the year 2005 [11]. .
It
mimics the food foraging behaviour of honey bee colonies. The algorithm mainly developed
for escaping from local maxima. The basic version of the algorithm performs a kind of
neighbourhood search combined with global search, and it can be used for both combinatorial
optimization and continuous optimization. A basic version of the bees algorithm is shown
in figure 1.
Figure 1 Basic version of Bees algorithm
3. OVERALL ARCHITECTURE OF PROPOSED SYSTEM
Figure 2 Overall architecture of proposed system
A Wrapper Based Feature Selection Approach using Bees Algorithm for Extreme Rainfall
Prediction via Weather Pattern Recognition Through SVM Classifier
http://www.iaeme.com/IJCIET/index.asp 1748 editor@iaeme.com
In this paper, the first phase, bees algorithm is used for finding a best subset of features
through decision tree classifier. In the second phase, the input is obtained reduced dataset
from the first phase. The obtained reduced dataset is given to SVM classifier for rainfall
prediction. The proposed system gives detection rate, accuracy rate, less false positive rate
and less training time of classifier.
4. FEATURE SELECTION USING BEES ALGORITHM
In this paper, Bees algorithm is used for finding optimal subset of features. In our work, we
used weather forecasting dataset and the dataset consists of 60 features, all the 60 features are
not contributing equal information. In the data set few of the features contributing more
information and few of the features contributing less information. In our work, we used bees
algorithm to identify those features are contributing more information. Weather forecasting
dataset consists of 60 features. First we want to identify the best subset size. In this work, we
tried with different subset sizes like 55 features, 50 features, 45 features, 40 features, 35
features, 30 features 25 features, 20 features, 15 features and 10 features. The range of subset
size 10 to 20 gives more classification accuracy compared to remaining subset. In this work,
subset size is taken as 15.
 Initialize population with random solutions:
Initially create randomly N solutions. Weather forecasting dataset consists of 60 features.
These features are ranked according to the location. In this work the features are divided into
two subsets, one is selected subset features and the size of the subset is 15 and another one is
unselected subset of features and the size of the subset is 45. The intersection of unselected
subset of features and selected subset of features is null. Randomly, create N initial solution
and evaluate each initial solution with fitness value.
 While stopping criteria is not met
 Evaluate each initial solution with fitness value
Evaluate each initial solution with fitness value and arrange it descending order according
to the fitness value. Example p1,p2,p3…………pn. In this example, p1 is assigned as best
subset.
 Neighborhood operations.
Take first n/2 solutions. Apply exchange operator to those solutions.
Example :
P1 (Selected Subset):
F1 F4 F8 F12 F16 F20 F24 F28 F32 F38 F42 F46 F50 F54 F60
P1 (Unselected Subset)
F2 F3 F5 F6 F7 F9 F10 F11 F13 F14 F15 F17 F18 F19 F21
F22 F23 F25 F26 F27 F29 F30 F31 F33 F34 F35 F36 F37 F39 F40
F41 F43 F44 F45 F47 F48 F49 F51 F52 F53 F55 F56 F57 F58 F59
Apply exchange operator between selected subset and unselected subset. Randomly pick
ceiling of 20% of features from the selected subset and randomly pick same number of
features from the unselected sunset of features. In this example, 20% of features contain 3
features. So randomly picks 3 features from the selected subset and randomly picks 3 features
from the unselected subset and apply exchange operator to this two sets and the example
shown below.
V. Karunakaran, S. Iwin Joseph, Ravi Teja, M. Suganthi, V. Rajasekar
http://www.iaeme.com/IJCIET/index.asp 1749 editor@iaeme.com
P1 (Selected Subset)
F1 F4 F8 F12 F27 F20 F24 F28 F32 F36 F42 F46 F50 F56 F60
P1 (Unselected Subset)
F2 F3 F5 F6 F7 F9 F10 F11 F13 F14 F15 F17 F18 F19 F21
F22 F23 F25 F26 F16 F29 F30 F31 F33 F34 F35 F38 F37 F39 F40
F41 F43 F44 F45 F47 F48 F49 F51 F52 F53 F55 F54 F57 F58 F59
This process continues upto first n/2 solutions. If any of the new subset has fitness value
greater than best subset. Assign new subset as best subset.
 Take a remaining population and randomly, create n solutions and evaluate each solutions
using decision tree. If any of the new subset is better than current best subset than assign new
subset as best subset.
 End while
In this algorithm stopping criteria is defined by user. i.e., Number of iteration is given by
user and finally the algorithm returns best subset of features.
5. EXPERIMENT AND RESULTS
Take input as weather forecast dataset, it consists of 60 features and then apply bees algorithm
to find best subset of features after finding the best subset of features. Evaluate the best subset
of features by using SVM Classifier. The result obtained from SVM classifier for accuracy
and training time of classifier shown in table1 and 2 respectively.
Table 1 Detection rate, false positive rate and Accuracy belongs to feature selection and without
feature selection
Dataset Detection rate False positive rate Accuracy Rate
Weather forecasting
without feature
selection
86.28 5.93 88.98
Weather forecasting
with feature selection
87.12 5.64 89.18
Figure 1 Detection rate, false positive rate and Accuracy belongs to feature selection and without
feature selection.
A Wrapper Based Feature Selection Approach using Bees Algorithm for Extreme Rainfall
Prediction via Weather Pattern Recognition Through SVM Classifier
http://www.iaeme.com/IJCIET/index.asp 1750 editor@iaeme.com
Table 2 Training time of SVM classifier for with feature selection and without feature selection
Dateset Training time of SVM
classifier (Without feature
selection)
Training time of SVM
classifier (Without feature
selection)
Weather Forecasting 15.6 min 7.3 min
From the table 1 and 2, clearly shows proposed system gives better detection rate, false
positive rate, accuracy rate and less training time of classifier.
6. CONCLUSIONS
Accuracy of rainfall prediction is a very important for most of the countries, which are mainly
dependent up on the agriculture. Most of the statistical methods are unsuccessful due to
dynamic nature of atmosphere. In this paper, SVM classifier is used for prediction, before
SVM classifier, bees algorithm is used for feature selection. The experimental result shows
that the proposed method provides better detection rate, accuracy rate and less training time of
classifier what we obtained with entire dataset.
REFERENCES
[1] P. Goswami and Srividya, “A novel Neural Network design for long range prediction of
rainfall pattern,” Current Sci.(Bangalore), vol. 70, no. 6, pp. 447-457, 1996.
[2] C. Venkatesanet, S. D. Raskar , S. S. Tambe , B. D. Kulkarni , and R.N. Keshavamurty ,
“Prediction of all India summer monsoon rainfall using Error-Back-Propagation Neural
Networks,” Meteorology and Atmospheric Physics, pp. 225-240, 1997.
[3] A. K. Sahai, M. K. Soman, and V. Satyan, “All India summer monsoon rainfall prediction
using an Artificial Neural Network,” Climate dynamics, vol. 16, no. 4, pp. 291-302, 2000.
[4] N. S. Philip and K. B. Joseph, “On the predictability of rainfall in Kerala-An application
of ABF neural network,” Computational Science- ICCS, Springer Berlin Heidelberg, pp.
1-12, 2001.
[5] N. S. Philip and K. B. Joseph, “A Neural Network tool for analyzing trends in rainfall,”
Comput. & Geosci.,vol. 29, no. 2, pp. 215-223, 2003.
[6] N. Chantasut, C. Charoenjit, and C. Tanprasert, “Predictive mining of rainfall predictions
using artificial neural networks for Chao Phraya River,” 4th Int Conf. of the Asian
Federation of Inform. Technology in Agriculture and the 2nd World Congr. on Comput. in
Agriculture and Natural Resources, Bangkok, Thailand, pp. 117-122, 2004.
[7] V. K. Somvanshi, O. P. Pandey, P. K. Agrawal, N.V.Kalanker1, M.Ravi Prakash, and
Ramesh Chand, “Modeling and prediction of rainfall using Artificial Neural Network and
ARIMA techniques,” J. Ind. Geophys. Union, vol. 10, no. 2, pp. 141-151, 2006.
[8] S. Chattopadhyay and M. Chattopadhyay, “A Soft Computing technique in
rainfallforecasting,” Int. Conf. on IT, HIT, pp. 19-21, 2007.
[9] Smita Kulkarni, Milind Mushrif, “Comparative Study among Different Neural Net
Learning Algorithms Applied to Rainfall Predication”, ICSC’ 14 Proceedings of the 2014
International conference on electronic systems, Signal processing and Computing
Technologies pages 209-216.
[10] P.Guhathakurta, “Long lead monsoon rainfall prediction using deterministic Artificial
Neural Network model,” Meteorology and Atmospheric Physics 101, pp. 93-108, 2008.
[11] Pham DT, Ghanbarzadeh A, Koc E, Otri S, Rahim S and Zaidi M. The Bees Algorithm.
Technical Note, Manufacturing Engineering Centre, Cardiff University, UK, 2005.
[12] Osama A., Zulaiha A. O., Bees Algorithm for Feature Selection in Network Anomaly
Detection. Journal of Applied Sciences Research, 8(3) pp. 1748-1756, 2012.

More Related Content

What's hot

PREDICTIVE MODEL FOR MAIZE STEM BORERS’ CLASSIFICATION IN PRECISION FARMING
PREDICTIVE MODEL FOR MAIZE STEM BORERS’ CLASSIFICATION IN PRECISION FARMINGPREDICTIVE MODEL FOR MAIZE STEM BORERS’ CLASSIFICATION IN PRECISION FARMING
PREDICTIVE MODEL FOR MAIZE STEM BORERS’ CLASSIFICATION IN PRECISION FARMING
ijaia
 
[71]a counting algorithm for tangerine yield estimation
[71]a counting algorithm for tangerine yield estimation[71]a counting algorithm for tangerine yield estimation
[71]a counting algorithm for tangerine yield estimation
Ulzii-Orshikh Dorj
 

What's hot (9)

PREDICTIVE MODEL FOR MAIZE STEM BORERS’ CLASSIFICATION IN PRECISION FARMING
PREDICTIVE MODEL FOR MAIZE STEM BORERS’ CLASSIFICATION IN PRECISION FARMINGPREDICTIVE MODEL FOR MAIZE STEM BORERS’ CLASSIFICATION IN PRECISION FARMING
PREDICTIVE MODEL FOR MAIZE STEM BORERS’ CLASSIFICATION IN PRECISION FARMING
 
Data Analytics on Solar Energy Using Hadoop
Data Analytics on Solar Energy Using HadoopData Analytics on Solar Energy Using Hadoop
Data Analytics on Solar Energy Using Hadoop
 
[71]a counting algorithm for tangerine yield estimation
[71]a counting algorithm for tangerine yield estimation[71]a counting algorithm for tangerine yield estimation
[71]a counting algorithm for tangerine yield estimation
 
Prediction of Dengue, Diabetes and Swine Flu using Random Forest Classificati...
Prediction of Dengue, Diabetes and Swine Flu using Random Forest Classificati...Prediction of Dengue, Diabetes and Swine Flu using Random Forest Classificati...
Prediction of Dengue, Diabetes and Swine Flu using Random Forest Classificati...
 
Data Analysis and Prediction System for Meteorological Data
Data Analysis and Prediction System for Meteorological DataData Analysis and Prediction System for Meteorological Data
Data Analysis and Prediction System for Meteorological Data
 
Predict the Average Temperatures of Baghdad City by Used Artificial Neural Ne...
Predict the Average Temperatures of Baghdad City by Used Artificial Neural Ne...Predict the Average Temperatures of Baghdad City by Used Artificial Neural Ne...
Predict the Average Temperatures of Baghdad City by Used Artificial Neural Ne...
 
IRJET- IoT based Preventive Crop Disease Model using IP and CNN
IRJET-  	  IoT based Preventive Crop Disease Model using IP and CNNIRJET-  	  IoT based Preventive Crop Disease Model using IP and CNN
IRJET- IoT based Preventive Crop Disease Model using IP and CNN
 
IRJET- Plant Leaf Disease Detection using Image Processing
IRJET- Plant Leaf Disease Detection using Image ProcessingIRJET- Plant Leaf Disease Detection using Image Processing
IRJET- Plant Leaf Disease Detection using Image Processing
 
IRJET- Facial Expression Recognition System using Neural Network based on...
IRJET-  	  Facial Expression Recognition System using Neural Network based on...IRJET-  	  Facial Expression Recognition System using Neural Network based on...
IRJET- Facial Expression Recognition System using Neural Network based on...
 

Similar to Ijciet 10 01_161

Support Vector Machine for Wind Speed Prediction
Support Vector Machine for Wind Speed PredictionSupport Vector Machine for Wind Speed Prediction
Support Vector Machine for Wind Speed Prediction
IJRST Journal
 

Similar to Ijciet 10 01_161 (20)

A Review Paper on Elderly Fall Detection
A Review Paper on Elderly Fall DetectionA Review Paper on Elderly Fall Detection
A Review Paper on Elderly Fall Detection
 
IRJET- A Review on Machine Learning Algorithm Used for Crop Monitoring System...
IRJET- A Review on Machine Learning Algorithm Used for Crop Monitoring System...IRJET- A Review on Machine Learning Algorithm Used for Crop Monitoring System...
IRJET- A Review on Machine Learning Algorithm Used for Crop Monitoring System...
 
Smart Farming Using Machine Learning Algorithms
Smart Farming Using Machine Learning AlgorithmsSmart Farming Using Machine Learning Algorithms
Smart Farming Using Machine Learning Algorithms
 
Support Vector Machine for Wind Speed Prediction
Support Vector Machine for Wind Speed PredictionSupport Vector Machine for Wind Speed Prediction
Support Vector Machine for Wind Speed Prediction
 
ANALYSIS AND PREDICTION OF RAINFALL USING MACHINE LEARNING TECHNIQUES
ANALYSIS AND PREDICTION OF RAINFALL USING MACHINE LEARNING TECHNIQUESANALYSIS AND PREDICTION OF RAINFALL USING MACHINE LEARNING TECHNIQUES
ANALYSIS AND PREDICTION OF RAINFALL USING MACHINE LEARNING TECHNIQUES
 
IRJET- Smart Crop-Field Monitoring and Automation Irrigation System using...
IRJET-  	  Smart Crop-Field Monitoring and Automation Irrigation System using...IRJET-  	  Smart Crop-Field Monitoring and Automation Irrigation System using...
IRJET- Smart Crop-Field Monitoring and Automation Irrigation System using...
 
Integrated Water Resources Management Using Rainfall Forecasting With Artific...
Integrated Water Resources Management Using Rainfall Forecasting With Artific...Integrated Water Resources Management Using Rainfall Forecasting With Artific...
Integrated Water Resources Management Using Rainfall Forecasting With Artific...
 
CLOUD BURST FORECAST USING EXPERT SYSTEMS
CLOUD BURST FORECAST USING EXPERT SYSTEMSCLOUD BURST FORECAST USING EXPERT SYSTEMS
CLOUD BURST FORECAST USING EXPERT SYSTEMS
 
IRJET - Enlightening Farmers on Crop Yield
IRJET -  	  Enlightening Farmers on Crop YieldIRJET -  	  Enlightening Farmers on Crop Yield
IRJET - Enlightening Farmers on Crop Yield
 
IRJET - Intelligent Weather Forecasting using Machine Learning Techniques
IRJET -  	  Intelligent Weather Forecasting using Machine Learning TechniquesIRJET -  	  Intelligent Weather Forecasting using Machine Learning Techniques
IRJET - Intelligent Weather Forecasting using Machine Learning Techniques
 
IRJET- Agricultural Crop Yield Prediction using Deep Learning Approach
IRJET-  	  Agricultural Crop Yield Prediction using Deep Learning ApproachIRJET-  	  Agricultural Crop Yield Prediction using Deep Learning Approach
IRJET- Agricultural Crop Yield Prediction using Deep Learning Approach
 
Neural Network Model Development with Soft Computing Techniques for Membrane ...
Neural Network Model Development with Soft Computing Techniques for Membrane ...Neural Network Model Development with Soft Computing Techniques for Membrane ...
Neural Network Model Development with Soft Computing Techniques for Membrane ...
 
Prediction of Air Quality Index using Random Forest Algorithm
Prediction of Air Quality Index using Random Forest AlgorithmPrediction of Air Quality Index using Random Forest Algorithm
Prediction of Air Quality Index using Random Forest Algorithm
 
1st_Review_PPT[1].pptx
1st_Review_PPT[1].pptx1st_Review_PPT[1].pptx
1st_Review_PPT[1].pptx
 
Prediction of dementia using machine learning model and performance improvem...
Prediction of dementia using machine learning model and  performance improvem...Prediction of dementia using machine learning model and  performance improvem...
Prediction of dementia using machine learning model and performance improvem...
 
A Review of Lie Detection Techniques
A Review of Lie Detection TechniquesA Review of Lie Detection Techniques
A Review of Lie Detection Techniques
 
A Review of Lie Detection Techniques.pdf
A Review of Lie Detection Techniques.pdfA Review of Lie Detection Techniques.pdf
A Review of Lie Detection Techniques.pdf
 
IRJET- A Fruit Quality Inspection Sytem using Faster Region Convolutional...
IRJET-  	  A Fruit Quality Inspection Sytem using Faster Region Convolutional...IRJET-  	  A Fruit Quality Inspection Sytem using Faster Region Convolutional...
IRJET- A Fruit Quality Inspection Sytem using Faster Region Convolutional...
 
Sugarcane yield forecasting using
Sugarcane yield forecasting usingSugarcane yield forecasting using
Sugarcane yield forecasting using
 
Intelligent flood disaster warning on the fly: developing IoT-based managemen...
Intelligent flood disaster warning on the fly: developing IoT-based managemen...Intelligent flood disaster warning on the fly: developing IoT-based managemen...
Intelligent flood disaster warning on the fly: developing IoT-based managemen...
 

More from IAEME Publication

A STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURS
A STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURSA STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURS
A STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURS
IAEME Publication
 
BROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURS
BROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURSBROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURS
BROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURS
IAEME Publication
 
GANDHI ON NON-VIOLENT POLICE
GANDHI ON NON-VIOLENT POLICEGANDHI ON NON-VIOLENT POLICE
GANDHI ON NON-VIOLENT POLICE
IAEME Publication
 
A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...
A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...
A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...
IAEME Publication
 
ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...
ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...
ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...
IAEME Publication
 
INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...
INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...
INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...
IAEME Publication
 
A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...
A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...
A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...
IAEME Publication
 
ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...
ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...
ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...
IAEME Publication
 
OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...
OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...
OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...
IAEME Publication
 
APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...
APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...
APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...
IAEME Publication
 

More from IAEME Publication (20)

IAEME_Publication_Call_for_Paper_September_2022.pdf
IAEME_Publication_Call_for_Paper_September_2022.pdfIAEME_Publication_Call_for_Paper_September_2022.pdf
IAEME_Publication_Call_for_Paper_September_2022.pdf
 
MODELING AND ANALYSIS OF SURFACE ROUGHNESS AND WHITE LATER THICKNESS IN WIRE-...
MODELING AND ANALYSIS OF SURFACE ROUGHNESS AND WHITE LATER THICKNESS IN WIRE-...MODELING AND ANALYSIS OF SURFACE ROUGHNESS AND WHITE LATER THICKNESS IN WIRE-...
MODELING AND ANALYSIS OF SURFACE ROUGHNESS AND WHITE LATER THICKNESS IN WIRE-...
 
A STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURS
A STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURSA STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURS
A STUDY ON THE REASONS FOR TRANSGENDER TO BECOME ENTREPRENEURS
 
BROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURS
BROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURSBROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURS
BROAD UNEXPOSED SKILLS OF TRANSGENDER ENTREPRENEURS
 
DETERMINANTS AFFECTING THE USER'S INTENTION TO USE MOBILE BANKING APPLICATIONS
DETERMINANTS AFFECTING THE USER'S INTENTION TO USE MOBILE BANKING APPLICATIONSDETERMINANTS AFFECTING THE USER'S INTENTION TO USE MOBILE BANKING APPLICATIONS
DETERMINANTS AFFECTING THE USER'S INTENTION TO USE MOBILE BANKING APPLICATIONS
 
ANALYSE THE USER PREDILECTION ON GPAY AND PHONEPE FOR DIGITAL TRANSACTIONS
ANALYSE THE USER PREDILECTION ON GPAY AND PHONEPE FOR DIGITAL TRANSACTIONSANALYSE THE USER PREDILECTION ON GPAY AND PHONEPE FOR DIGITAL TRANSACTIONS
ANALYSE THE USER PREDILECTION ON GPAY AND PHONEPE FOR DIGITAL TRANSACTIONS
 
VOICE BASED ATM FOR VISUALLY IMPAIRED USING ARDUINO
VOICE BASED ATM FOR VISUALLY IMPAIRED USING ARDUINOVOICE BASED ATM FOR VISUALLY IMPAIRED USING ARDUINO
VOICE BASED ATM FOR VISUALLY IMPAIRED USING ARDUINO
 
IMPACT OF EMOTIONAL INTELLIGENCE ON HUMAN RESOURCE MANAGEMENT PRACTICES AMONG...
IMPACT OF EMOTIONAL INTELLIGENCE ON HUMAN RESOURCE MANAGEMENT PRACTICES AMONG...IMPACT OF EMOTIONAL INTELLIGENCE ON HUMAN RESOURCE MANAGEMENT PRACTICES AMONG...
IMPACT OF EMOTIONAL INTELLIGENCE ON HUMAN RESOURCE MANAGEMENT PRACTICES AMONG...
 
VISUALISING AGING PARENTS & THEIR CLOSE CARERS LIFE JOURNEY IN AGING ECONOMY
VISUALISING AGING PARENTS & THEIR CLOSE CARERS LIFE JOURNEY IN AGING ECONOMYVISUALISING AGING PARENTS & THEIR CLOSE CARERS LIFE JOURNEY IN AGING ECONOMY
VISUALISING AGING PARENTS & THEIR CLOSE CARERS LIFE JOURNEY IN AGING ECONOMY
 
A STUDY ON THE IMPACT OF ORGANIZATIONAL CULTURE ON THE EFFECTIVENESS OF PERFO...
A STUDY ON THE IMPACT OF ORGANIZATIONAL CULTURE ON THE EFFECTIVENESS OF PERFO...A STUDY ON THE IMPACT OF ORGANIZATIONAL CULTURE ON THE EFFECTIVENESS OF PERFO...
A STUDY ON THE IMPACT OF ORGANIZATIONAL CULTURE ON THE EFFECTIVENESS OF PERFO...
 
GANDHI ON NON-VIOLENT POLICE
GANDHI ON NON-VIOLENT POLICEGANDHI ON NON-VIOLENT POLICE
GANDHI ON NON-VIOLENT POLICE
 
A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...
A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...
A STUDY ON TALENT MANAGEMENT AND ITS IMPACT ON EMPLOYEE RETENTION IN SELECTED...
 
ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...
ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...
ATTRITION IN THE IT INDUSTRY DURING COVID-19 PANDEMIC: LINKING EMOTIONAL INTE...
 
INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...
INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...
INFLUENCE OF TALENT MANAGEMENT PRACTICES ON ORGANIZATIONAL PERFORMANCE A STUD...
 
A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...
A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...
A STUDY OF VARIOUS TYPES OF LOANS OF SELECTED PUBLIC AND PRIVATE SECTOR BANKS...
 
EXPERIMENTAL STUDY OF MECHANICAL AND TRIBOLOGICAL RELATION OF NYLON/BaSO4 POL...
EXPERIMENTAL STUDY OF MECHANICAL AND TRIBOLOGICAL RELATION OF NYLON/BaSO4 POL...EXPERIMENTAL STUDY OF MECHANICAL AND TRIBOLOGICAL RELATION OF NYLON/BaSO4 POL...
EXPERIMENTAL STUDY OF MECHANICAL AND TRIBOLOGICAL RELATION OF NYLON/BaSO4 POL...
 
ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...
ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...
ROLE OF SOCIAL ENTREPRENEURSHIP IN RURAL DEVELOPMENT OF INDIA - PROBLEMS AND ...
 
OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...
OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...
OPTIMAL RECONFIGURATION OF POWER DISTRIBUTION RADIAL NETWORK USING HYBRID MET...
 
APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...
APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...
APPLICATION OF FRUGAL APPROACH FOR PRODUCTIVITY IMPROVEMENT - A CASE STUDY OF...
 
A MULTIPLE – CHANNEL QUEUING MODELS ON FUZZY ENVIRONMENT
A MULTIPLE – CHANNEL QUEUING MODELS ON FUZZY ENVIRONMENTA MULTIPLE – CHANNEL QUEUING MODELS ON FUZZY ENVIRONMENT
A MULTIPLE – CHANNEL QUEUING MODELS ON FUZZY ENVIRONMENT
 

Recently uploaded

Kuwait City MTP kit ((+919101817206)) Buy Abortion Pills Kuwait
Kuwait City MTP kit ((+919101817206)) Buy Abortion Pills KuwaitKuwait City MTP kit ((+919101817206)) Buy Abortion Pills Kuwait
Kuwait City MTP kit ((+919101817206)) Buy Abortion Pills Kuwait
jaanualu31
 
scipt v1.pptxcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx...
scipt v1.pptxcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx...scipt v1.pptxcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx...
scipt v1.pptxcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx...
HenryBriggs2
 
Hospital management system project report.pdf
Hospital management system project report.pdfHospital management system project report.pdf
Hospital management system project report.pdf
Kamal Acharya
 
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Kandungan 087776558899
 

Recently uploaded (20)

8086 Microprocessor Architecture: 16-bit microprocessor
8086 Microprocessor Architecture: 16-bit microprocessor8086 Microprocessor Architecture: 16-bit microprocessor
8086 Microprocessor Architecture: 16-bit microprocessor
 
👉 Yavatmal Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl S...
👉 Yavatmal Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl S...👉 Yavatmal Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl S...
👉 Yavatmal Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top Class Call Girl S...
 
Worksharing and 3D Modeling with Revit.pptx
Worksharing and 3D Modeling with Revit.pptxWorksharing and 3D Modeling with Revit.pptx
Worksharing and 3D Modeling with Revit.pptx
 
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptxS1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx
 
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptxHOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
 
Kuwait City MTP kit ((+919101817206)) Buy Abortion Pills Kuwait
Kuwait City MTP kit ((+919101817206)) Buy Abortion Pills KuwaitKuwait City MTP kit ((+919101817206)) Buy Abortion Pills Kuwait
Kuwait City MTP kit ((+919101817206)) Buy Abortion Pills Kuwait
 
scipt v1.pptxcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx...
scipt v1.pptxcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx...scipt v1.pptxcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx...
scipt v1.pptxcxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx...
 
Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startDesign For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the start
 
Ground Improvement Technique: Earth Reinforcement
Ground Improvement Technique: Earth ReinforcementGround Improvement Technique: Earth Reinforcement
Ground Improvement Technique: Earth Reinforcement
 
Introduction to Data Visualization,Matplotlib.pdf
Introduction to Data Visualization,Matplotlib.pdfIntroduction to Data Visualization,Matplotlib.pdf
Introduction to Data Visualization,Matplotlib.pdf
 
Hospital management system project report.pdf
Hospital management system project report.pdfHospital management system project report.pdf
Hospital management system project report.pdf
 
8th International Conference on Soft Computing, Mathematics and Control (SMC ...
8th International Conference on Soft Computing, Mathematics and Control (SMC ...8th International Conference on Soft Computing, Mathematics and Control (SMC ...
8th International Conference on Soft Computing, Mathematics and Control (SMC ...
 
Convergence of Robotics and Gen AI offers excellent opportunities for Entrepr...
Convergence of Robotics and Gen AI offers excellent opportunities for Entrepr...Convergence of Robotics and Gen AI offers excellent opportunities for Entrepr...
Convergence of Robotics and Gen AI offers excellent opportunities for Entrepr...
 
Computer Networks Basics of Network Devices
Computer Networks  Basics of Network DevicesComputer Networks  Basics of Network Devices
Computer Networks Basics of Network Devices
 
Max. shear stress theory-Maximum Shear Stress Theory ​ Maximum Distortional ...
Max. shear stress theory-Maximum Shear Stress Theory ​  Maximum Distortional ...Max. shear stress theory-Maximum Shear Stress Theory ​  Maximum Distortional ...
Max. shear stress theory-Maximum Shear Stress Theory ​ Maximum Distortional ...
 
Introduction to Geographic Information Systems
Introduction to Geographic Information SystemsIntroduction to Geographic Information Systems
Introduction to Geographic Information Systems
 
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
 
Augmented Reality (AR) with Augin Software.pptx
Augmented Reality (AR) with Augin Software.pptxAugmented Reality (AR) with Augin Software.pptx
Augmented Reality (AR) with Augin Software.pptx
 
Signal Processing and Linear System Analysis
Signal Processing and Linear System AnalysisSignal Processing and Linear System Analysis
Signal Processing and Linear System Analysis
 
Hostel management system project report..pdf
Hostel management system project report..pdfHostel management system project report..pdf
Hostel management system project report..pdf
 

Ijciet 10 01_161

  • 1. http://www.iaeme.com/IJCIET/index.asp 1745 editor@iaeme.com International Journal of Civil Engineering and Technology (IJCIET) Volume 10, Issue 01, January 2019, pp. 1745–1750, Article ID: IJCIET_10_01_161 Available online at http://www.iaeme.com/ijciet/issues.asp?JType=IJCIET&VType=10&IType=1 ISSN Print: 0976-6308 and ISSN Online: 0976-6316 ©IAEME Publication Scopus Indexed A WRAPPER BASED FEATURE SELECTION APPROACH USING BEES ALGORITHM FOR EXTREME RAINFALL PREDICTION VIA WEATHER PATTERN RECOGNITION THROUGH SVM CLASSIFIER V. Karunakaran Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India S. Iwin Joseph Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India Ravi Teja Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, India M. Suganthi Department of Electronics and Communication Engineering, Mahendra College of Engineering, Salem, India V. Rajasekar Department of Computer Science and Engineering, AMC Engineering College, Bangalore, India ABSTRACT Rainfall prediction is a major problem in metrological department and it is closely associated with the economy and life of human. Accuracy of rainfall prediction is a very important for countries like india, because Indian economy is mainly dependent up on the agriculture. Most of the statistical methods are unsuccessful due to dynamic nature of atmosphere. In this paper, SVM classifier is used for classification, before SVM classifier, bees algorithm is used for feature selection. Keeping all the features and instances in the training set is not a good approach for better classification because all the features are not contributing more information during classification, removing those features will not affect any classification accuracy. The experimental result shows that the proposed method provides better detection rate, false positive
  • 2. A Wrapper Based Feature Selection Approach using Bees Algorithm for Extreme Rainfall Prediction via Weather Pattern Recognition Through SVM Classifier http://www.iaeme.com/IJCIET/index.asp 1746 editor@iaeme.com rate, accuracy rate and less training time of classifier what we obtained with entire dataset. Key words: Support Vector machine, Feature selection, Bees algorithm, Rainfall. Cite this Article: V. Karunakaran, S. Iwin Joseph, Ravi Teja, M. Suganthi, V. Rajasekar. A Wrapper Based Feature Selection Approach using Bees Algorithm for Extreme Rainfall Prediction via Weather Pattern Recognition Through SVM Classifier, International Journal of Civil Engineering and Technology (IJCIET) 10(1), 2019, pp. 1745–1750. http://www.iaeme.com/IJCIET/issues.asp?JType=IJCIET&VType=10&IType=1 1. INTRODUCTION Rainfall predication is very supportive to avoid flood, that will save lives of human and it also helps to manage resources of water. Rainfall prediction also helps the farmers to manage their crops better. Rainfall prediction is a challenging task for meteorological department due to dynamic change of atmosphere. Most of the researchers tried with lot of machine learning algorithms for rainfall predictions and they achieved some fair prediction result. Prashant Goswami et al proposed artificial neural network for rainfall prediction and the experimental shows good prediction accuracy of annual rainfall compared to the existing neural networks [1]. Venkatesan et al used error back propagation neural network for rainfall prediction. The experimental results compared with some existing statistical methods, error back propagation neural network out performed in prediction accuracy [2]. A.K shai used artificial neural network with error back propagation algorithm for rainfall prediction. The model is compared with few statistical methods and this method provides better prediction rate and less Mean squared value [3]. Ninan Sajeeth Philip et al used ABF neural network for rainfall prediction and the method is compared with some statistical methods, ABF neural network is out performed [4]. Ninan Sajeeth Philip et al used adaptive basis function network for rainfall prediction and the method is compared with some traditional methods like principal component analysis and spectral analysis. Adaptive basis function network provides good prediction results [5]. Norraseth Chantasut et al used artificial neural network for rainfall predication in the area of Chao Phraya River. The experimental result shows, 96.6% of prediction accuracy is obtained by the model while using training dataset and 96.9% of prediction accuracy while using testing dataset [6]. V.K.Somvanshi et al used artificial neural network and ARIMA techniques for rainfall prediction. The experimental result shows artificial neural network and ARIMA techniques is a promising tool for annual rainfall predictions [7]. S. Chattopadhyay et al used multilayer perceptron for rainfall prediction. The experimental result shows better prediction accuracy compared to the conventional methods [8]. Smita Kulkarni et al discussed three prediction methods based on backpropagation neural network learning rules 1. Momentum learning, 2. Conjugate gradient descent (CGD) learning, and 3. Levenberg -- Marquardt (LM) learning. Among the three prediction methods conjugate gradient descent methods provides better prediction accuracy compared to momentum learning and LM learning [9]. P. Guhathakurta used deterministic artificial neural network for rainfall prediction. This method is compared with single time series, the derivation of smaller scale (sub-divisions) forecast model may be more useful than the all India forecast [10]. Most of the researchers tried with different approaches for rainfall prediction, but still need some improvement in prediction accuracy. In this paper, bees algorithm used for feature selection, after feature selection, the obtained dataset is given to artificial neural network for prediction. The proposed system provides better prediction rate and less mean square value.
  • 3. V. Karunakaran, S. Iwin Joseph, Ravi Teja, M. Suganthi, V. Rajasekar http://www.iaeme.com/IJCIET/index.asp 1747 editor@iaeme.com The rest of the paper is organized as follows: Section 2 presents introduction to wrapper method and bees algorithm. Section 3 presents overall architecture of the proposed system. Section 4 presents feature selection using bees algorithm. Section 5 presents experimental results. Finally section 6 presents conclusion. 2. INTRODUCTION TO WRAPPER METHOD AND BEES ALGORITHM Feature selection is mostly carried out by two methods, 1. Filter method and 2. Wrapper method. In filter method, feature selection is carried out by selection function. It is not dependent upon the classification accuracy. In wrapper method, feature selection is carried out by classification accuracy. Most of the wrapper method provides better classification accuracy compared to the filter methods. Bees algorithm is a population-based search algorithm and it was developed by Pham, Ghanbarzadeh and et al. in the year 2005 [11]. . It mimics the food foraging behaviour of honey bee colonies. The algorithm mainly developed for escaping from local maxima. The basic version of the algorithm performs a kind of neighbourhood search combined with global search, and it can be used for both combinatorial optimization and continuous optimization. A basic version of the bees algorithm is shown in figure 1. Figure 1 Basic version of Bees algorithm 3. OVERALL ARCHITECTURE OF PROPOSED SYSTEM Figure 2 Overall architecture of proposed system
  • 4. A Wrapper Based Feature Selection Approach using Bees Algorithm for Extreme Rainfall Prediction via Weather Pattern Recognition Through SVM Classifier http://www.iaeme.com/IJCIET/index.asp 1748 editor@iaeme.com In this paper, the first phase, bees algorithm is used for finding a best subset of features through decision tree classifier. In the second phase, the input is obtained reduced dataset from the first phase. The obtained reduced dataset is given to SVM classifier for rainfall prediction. The proposed system gives detection rate, accuracy rate, less false positive rate and less training time of classifier. 4. FEATURE SELECTION USING BEES ALGORITHM In this paper, Bees algorithm is used for finding optimal subset of features. In our work, we used weather forecasting dataset and the dataset consists of 60 features, all the 60 features are not contributing equal information. In the data set few of the features contributing more information and few of the features contributing less information. In our work, we used bees algorithm to identify those features are contributing more information. Weather forecasting dataset consists of 60 features. First we want to identify the best subset size. In this work, we tried with different subset sizes like 55 features, 50 features, 45 features, 40 features, 35 features, 30 features 25 features, 20 features, 15 features and 10 features. The range of subset size 10 to 20 gives more classification accuracy compared to remaining subset. In this work, subset size is taken as 15.  Initialize population with random solutions: Initially create randomly N solutions. Weather forecasting dataset consists of 60 features. These features are ranked according to the location. In this work the features are divided into two subsets, one is selected subset features and the size of the subset is 15 and another one is unselected subset of features and the size of the subset is 45. The intersection of unselected subset of features and selected subset of features is null. Randomly, create N initial solution and evaluate each initial solution with fitness value.  While stopping criteria is not met  Evaluate each initial solution with fitness value Evaluate each initial solution with fitness value and arrange it descending order according to the fitness value. Example p1,p2,p3…………pn. In this example, p1 is assigned as best subset.  Neighborhood operations. Take first n/2 solutions. Apply exchange operator to those solutions. Example : P1 (Selected Subset): F1 F4 F8 F12 F16 F20 F24 F28 F32 F38 F42 F46 F50 F54 F60 P1 (Unselected Subset) F2 F3 F5 F6 F7 F9 F10 F11 F13 F14 F15 F17 F18 F19 F21 F22 F23 F25 F26 F27 F29 F30 F31 F33 F34 F35 F36 F37 F39 F40 F41 F43 F44 F45 F47 F48 F49 F51 F52 F53 F55 F56 F57 F58 F59 Apply exchange operator between selected subset and unselected subset. Randomly pick ceiling of 20% of features from the selected subset and randomly pick same number of features from the unselected sunset of features. In this example, 20% of features contain 3 features. So randomly picks 3 features from the selected subset and randomly picks 3 features from the unselected subset and apply exchange operator to this two sets and the example shown below.
  • 5. V. Karunakaran, S. Iwin Joseph, Ravi Teja, M. Suganthi, V. Rajasekar http://www.iaeme.com/IJCIET/index.asp 1749 editor@iaeme.com P1 (Selected Subset) F1 F4 F8 F12 F27 F20 F24 F28 F32 F36 F42 F46 F50 F56 F60 P1 (Unselected Subset) F2 F3 F5 F6 F7 F9 F10 F11 F13 F14 F15 F17 F18 F19 F21 F22 F23 F25 F26 F16 F29 F30 F31 F33 F34 F35 F38 F37 F39 F40 F41 F43 F44 F45 F47 F48 F49 F51 F52 F53 F55 F54 F57 F58 F59 This process continues upto first n/2 solutions. If any of the new subset has fitness value greater than best subset. Assign new subset as best subset.  Take a remaining population and randomly, create n solutions and evaluate each solutions using decision tree. If any of the new subset is better than current best subset than assign new subset as best subset.  End while In this algorithm stopping criteria is defined by user. i.e., Number of iteration is given by user and finally the algorithm returns best subset of features. 5. EXPERIMENT AND RESULTS Take input as weather forecast dataset, it consists of 60 features and then apply bees algorithm to find best subset of features after finding the best subset of features. Evaluate the best subset of features by using SVM Classifier. The result obtained from SVM classifier for accuracy and training time of classifier shown in table1 and 2 respectively. Table 1 Detection rate, false positive rate and Accuracy belongs to feature selection and without feature selection Dataset Detection rate False positive rate Accuracy Rate Weather forecasting without feature selection 86.28 5.93 88.98 Weather forecasting with feature selection 87.12 5.64 89.18 Figure 1 Detection rate, false positive rate and Accuracy belongs to feature selection and without feature selection.
  • 6. A Wrapper Based Feature Selection Approach using Bees Algorithm for Extreme Rainfall Prediction via Weather Pattern Recognition Through SVM Classifier http://www.iaeme.com/IJCIET/index.asp 1750 editor@iaeme.com Table 2 Training time of SVM classifier for with feature selection and without feature selection Dateset Training time of SVM classifier (Without feature selection) Training time of SVM classifier (Without feature selection) Weather Forecasting 15.6 min 7.3 min From the table 1 and 2, clearly shows proposed system gives better detection rate, false positive rate, accuracy rate and less training time of classifier. 6. CONCLUSIONS Accuracy of rainfall prediction is a very important for most of the countries, which are mainly dependent up on the agriculture. Most of the statistical methods are unsuccessful due to dynamic nature of atmosphere. In this paper, SVM classifier is used for prediction, before SVM classifier, bees algorithm is used for feature selection. The experimental result shows that the proposed method provides better detection rate, accuracy rate and less training time of classifier what we obtained with entire dataset. REFERENCES [1] P. Goswami and Srividya, “A novel Neural Network design for long range prediction of rainfall pattern,” Current Sci.(Bangalore), vol. 70, no. 6, pp. 447-457, 1996. [2] C. Venkatesanet, S. D. Raskar , S. S. Tambe , B. D. Kulkarni , and R.N. Keshavamurty , “Prediction of all India summer monsoon rainfall using Error-Back-Propagation Neural Networks,” Meteorology and Atmospheric Physics, pp. 225-240, 1997. [3] A. K. Sahai, M. K. Soman, and V. Satyan, “All India summer monsoon rainfall prediction using an Artificial Neural Network,” Climate dynamics, vol. 16, no. 4, pp. 291-302, 2000. [4] N. S. Philip and K. B. Joseph, “On the predictability of rainfall in Kerala-An application of ABF neural network,” Computational Science- ICCS, Springer Berlin Heidelberg, pp. 1-12, 2001. [5] N. S. Philip and K. B. Joseph, “A Neural Network tool for analyzing trends in rainfall,” Comput. & Geosci.,vol. 29, no. 2, pp. 215-223, 2003. [6] N. Chantasut, C. Charoenjit, and C. Tanprasert, “Predictive mining of rainfall predictions using artificial neural networks for Chao Phraya River,” 4th Int Conf. of the Asian Federation of Inform. Technology in Agriculture and the 2nd World Congr. on Comput. in Agriculture and Natural Resources, Bangkok, Thailand, pp. 117-122, 2004. [7] V. K. Somvanshi, O. P. Pandey, P. K. Agrawal, N.V.Kalanker1, M.Ravi Prakash, and Ramesh Chand, “Modeling and prediction of rainfall using Artificial Neural Network and ARIMA techniques,” J. Ind. Geophys. Union, vol. 10, no. 2, pp. 141-151, 2006. [8] S. Chattopadhyay and M. Chattopadhyay, “A Soft Computing technique in rainfallforecasting,” Int. Conf. on IT, HIT, pp. 19-21, 2007. [9] Smita Kulkarni, Milind Mushrif, “Comparative Study among Different Neural Net Learning Algorithms Applied to Rainfall Predication”, ICSC’ 14 Proceedings of the 2014 International conference on electronic systems, Signal processing and Computing Technologies pages 209-216. [10] P.Guhathakurta, “Long lead monsoon rainfall prediction using deterministic Artificial Neural Network model,” Meteorology and Atmospheric Physics 101, pp. 93-108, 2008. [11] Pham DT, Ghanbarzadeh A, Koc E, Otri S, Rahim S and Zaidi M. The Bees Algorithm. Technical Note, Manufacturing Engineering Centre, Cardiff University, UK, 2005. [12] Osama A., Zulaiha A. O., Bees Algorithm for Feature Selection in Network Anomaly Detection. Journal of Applied Sciences Research, 8(3) pp. 1748-1756, 2012.