Improve performance of extreme learning machine in classification of patchouli varieties with imbalanced class

Patchouli has various varieties with almost the same physical characteristics. This often makes it difficult to recognize varieties with a high PA (Patchouli Alcohol) content. In this study an improvisation was introduced in the identification of patchouli varieties using leaf images using Extreme Learning Machine (ELM). However, problems occur in ELM if the data used is not balanced where the training process can not able to recognize data in the minority class well. Therefore, this study conducted a process to balance the composition of the data using the Synthetic Minority Over-sampling Technique (SMOTE) method. The test results of 93 data on the imbalanced composition with a comparison of 70% of training data and 30% of test data obtained an average accuracy of 93.57%. After implementing SMOTE in the Tetraploid, Patchoulina and Sidikalang classes where the amount of data in each class becomes 58 data, an average accuracy of 96.00% is achieved. This shows the existence of an increase in the process of identification with ELM when new data generation with SMOTE is carried out to balance the composition of the data.

[1]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[2]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[3]  A. Samal,et al.  Plant species identification using Elliptic Fourier leaf shape analysis , 2006 .

[4]  Yuxuan Wang,et al.  A Leaf Recognition Algorithm for Plant Classification Using Probabilistic Neural Network , 2007, 2007 IEEE International Symposium on Signal Processing and Information Technology.

[5]  Lei Cai,et al.  Comparison of Extreme Learning Machine with Support Vector Regression for Reservoir Permeability Prediction , 2009, 2009 International Conference on Computational Intelligence and Security.

[6]  Lance Chun Che Fung,et al.  Classification of Imbalanced Data by Combining the Complementary Neural Network and SMOTE Algorithm , 2010, ICONIP.

[7]  Asadollah Shahbahrami.  Algorithms and architectures for 2D discrete wavelet transform , 2012, The Journal of Supercomputing.

[8]  Ali Miri,et al.  Privacy-preserving back-propagation and extreme learning machine algorithms , 2012, Data Knowl. Eng..

[9]  Arnab Bhattacharya,et al.  A Plant Identification System using Shape and Morphological Features on Segmented Leaflets: Team IITK, CLEF 2012 , 2012, CLEF.

[10]  J. S. Murguía,et al.  Two-dimensional wavelet transform feature extraction for porous silicon chemical sensors. , 2013, Analytica chimica acta.

[11]  Ervizal A. M. Zuhud,et al.  A Computer Aided System for Tropical Leaf Medicinal Plant Identification , 2013 .

[12]  Han Zhao,et al.  Extreme learning machine: algorithm, theory and applications , 2013, Artificial Intelligence Review.

[13]  Seong-Ran Lee.  The Application Effect of a Medical Information Management System for the Prevention of Depression in Mastectomy Patients , 2013, BSBT 2013.

[14]  Kwang-seok Hong,et al.  An Implementation of Leaf Recognition System using Leaf Vein and Shape , 2013 .

[15]  Kun-Huang Chen,et al.  A hybrid classifier combining SMOTE with PSO to estimate 5-year survivability of breast cancer patients , 2014, Appl. Soft Comput..

[16]  Anuj Srivastava,et al.  Landmark-free statistical analysis of the shape of plant leaves. , 2014, Journal of Theoretical Biology.

[17]  Lina Yang,et al.  Implementation of 2D Discrete Wavelet Transform by Number Theoretic Transform and 2D Overlap-Save Method , 2014 .

[18]  P. Bhandarkar,et al.  Leaf identification using morphology and structural decomposition , 2014, 2014 International Conference on Signal Processing and Integrated Networks (SPIN).

[19]  Ashish Khare,et al.  Fusion of multimodal medical images using Daubechies complex wavelet transform - A multiresolution approach , 2014, Inf. Fusion.

[20]  Tapio Pahikkala,et al.  Classification of plant species from images of overlapping leaves , 2015, Comput. Electron. Agric..

[21]  Cesar Beltran-Castanon,et al.  Leaf-Based Plant Identification Through Morphological Characterization in Digital Images , 2015, CAIP.

[22]  Yuan Yan Tang,et al.  ApLeaf: An efficient android-based plant leaf identification system , 2015, Neurocomputing.

[23]  Jun Wang,et al.  Comparison of ELM, RF, and SVM on E-nose and E-tongue to trace the quality status of mandarin (Citrus unshiu Marc.) , 2015 .

[24]  Radu Dogaru,et al.  A comparison of Extreme Learning Machine and Support Vector Machine classifiers , 2015, 2015 IEEE International Conference on Intelligent Computer Communication and Processing (ICCP).

[25]  Nursuriati Jamil,et al.  Automatic Plant Identification: Is Shape the Key Feature?☆ , 2015 .

[26]  Anushikha Singh,et al.  Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image , 2016, Comput. Methods Programs Biomed..

[27]  Guang-Bin Huang,et al.  Extreme Learning Machine for Multilayer Perceptron , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[28]  Chengjin Zhang,et al.  Using the SMOTE technique and hybrid features to predict the types of ion channel-targeted conotoxins. , 2016, Journal of theoretical biology.

[29]  Ning Wang,et al.  Individual leaf identification from horticultural crop images based on the leaf skeleton , 2016, Comput. Electron. Agric..

[30]  Pinar Yildirim.  Pattern Classification with Imbalanced and Multiclass Data for the Prediction of Albendazole Adverse Event Outcomes , 2016, ANT/SEIT.

[31]  Nian Liu,et al.  Improved deep belief networks and multi-feature fusion for leaf identification , 2016, Neurocomputing.

[32]  Pablo M. Granitto,et al.  Deep learning for plant identification using vein morphological patterns , 2016, Comput. Electron. Agric..

[33]  Nader Fathianpour,et al.  Selecting optimum base wavelet for extracting spectral alteration features associated with porphyry copper mineralization using hyperspectral images , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[34]  Adel Bakhshipour,et al.  Weed segmentation using texture features extracted from wavelet sub-images , 2017 .

[35]  Sanyam Shukla,et al.  Class-specific kernelized extreme learning machine for binary class imbalance learning , 2018, Appl. Soft Comput..

[36]  Charnon Chupong,et al.  Comparison Study on Artificial Neural Network and Online Sequential Extreme Learning Machine in Regression Problem , 2019, 2019 7th International Electrical Engineering Congress (iEECON).

[37]  Amir F. Atiya,et al.  A Comprehensive Analysis of Synthetic Minority Oversampling Technique (SMOTE) for handling class imbalance , 2019, Inf. Sci..

[38]  Junhong Zhao,et al.  Learning imbalanced datasets based on SMOTE and Gaussian distribution , 2020, Inf. Sci..