A Comparison Study of Kernel Functions in the Support Vector Machine and Its Application for Termite Detection

Termites are the most destructive pests and their attacks significantly impact the quality of wooden buildings. Due to their cryptic behavior, it is rarely apparent from visual observation that a termite infestation is active and that wood damage is occurring. Based on the phenomenon of acoustic signals generated by termites when attacking wood, we proposed a practical framework to detect termites nondestructively, i.e., by using the acoustic signals extraction. This method has the pros to maintain the quality of wood products and prevent higher termite attacks. In this work, we inserted 220 subterranean termites into a pine wood for feeding activity and monitored its acoustic signal. The two acoustic features (i.e., energy and entropy) derived from the time domain were used for this study’s analysis. Furthermore, the support vector machine (SVM) algorithm with different kernel functions (i.e., linear, radial basis function, sigmoid and polynomial) were employed to recognize the termites’ acoustic signal. In addition, the area under a receiver operating characteristic curve (AUC) was also adopted to analyze and improve the performance results. Based on the numerical analysis, the SVM with polynomial kernel function achieves the best classification accuracy of 0.9188.

[1]  Ming Zhang,et al.  Artificial Higher Order Neural Networks for Economics and Business , 2008 .

[2]  Rubita Sudirman,et al.  Features extraction of electromyography signals in time domain on biceps brachii muscle , 2013 .

[3]  Mauridhi Hery Purnomo,et al.  Electronic nose based on partition column integrated with gas sensor for fruit identification and classification , 2016, Comput. Electron. Agric..

[4]  J. Goo,et al.  Receiver Operating Characteristic (ROC) Curve: Practical Review for Radiologists , 2004, Korean journal of radiology.

[5]  Krzysztof Regulski,et al.  Comparative analysis of the properties of the nodular cast iron with carbides and the austempered ductile iron with use of the machine learning and the support vector machine , 2016 .

[6]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[7]  Yudong Zhang,et al.  Classification of Fruits Using Computer Vision and a Multiclass Support Vector Machine , 2012, Sensors.

[8]  Jerzy Józwik.  IDENTIFICATION AND MONITORING OF NOISE SOURCES OF CNC MACHINE TOOLS BY ACOUSTIC HOLOGRAPHY METHODS , 2016 .

[9]  V. R. Lewis,et al.  Alternative control strategies for termites , 1997 .

[10]  Frederick Green,et al.  Remote sensing for detection of termite infestations—Proof of Concept , 2015 .

[11]  Adam Glowacz.  Recognition of acoustic signals of induction motor using fft, smofs-10 and ISVM , 2015 .

[12]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[13]  Zhixin Yang,et al.  A Hybrid EEMD-Based SampEn and SVD for Acoustic Signal Processing and Fault Diagnosis , 2016, Entropy.

[14]  Vernard R. Lewis,et al.  Surface and subsurface sensor performance in acoustically detecting the western drywood termite in naturally infested boards , 2004 .

[15]  Felix A Hager,et al.  Vibrational long-distance communication in the termites Macrotermes natalensis and Odontotermes sp. , 2013, Journal of Experimental Biology.

[16]  Zhirong Sun,et al.  Support vector machine approach for protein subcellular localization prediction , 2001, Bioinform..

[17]  Manuel P. Malumbres,et al.  On the Design of a Bioacoustic Sensor for the Early Detection of the Red Palm Weevil , 2013, Sensors.

[18]  R. Chapman.  The Insects: Structure and Function , 1969 .

[19]  Yuji Imamura,et al.  Evaluation of the temperature and relative humidity preferences of the western dry-wood termite Incisitermes minor (Hagen) using acoustic emission (AE) monitoring , 2007, Journal of Wood Science.

[20]  Gunnar Rätsch,et al.  Support Vector Machines and Kernels for Computational Biology , 2008, PLoS Comput. Biol..

[21]  Theodoros Giannakopoulos,et al.  Introduction to Audio Analysis: A MATLAB® Approach , 2014 .

[22]  Samy Bakheet,et al.  An SVM Framework for Malignant Melanoma Detection Based on Optimized HOG Features , 2017, Comput..

[23]  Muhammad Achirul Nanda,et al.  Characteristics of Acoustic Emission for Subterranean Termite Detection in Wood , 2017 .

[24]  Lei Yan,et al.  A Classification Method for Seed Viability Assessment with Infrared Thermography , 2017, Sensors.

[25]  M. Pardo,et al.  Classification of electronic nose data with support vector machines , 2005 .

[26]  Aijun Liu,et al.  Tea Category Identification using Computer Vision and Generalized Eigenvalue Proximal SVM , 2017, Fundam. Informaticae.

[27]  R. Mankin,et al.  Acoustic Detection of Termite Infestations in Urban Trees , 2002, Journal of economic entomology.

[28]  T. A. Evans,et al.  Foraging vibration signals attract foragers and identify food size in the drywood termite, Cryptotermes secundus , 2007, Insectes Sociaux.

[29]  Michael Haverty,et al.  Seasonal and Daily Patterns in Activity of the Western Drywood Termite, Incisitermes minor (Hagen) , 2011, Insects.

[30]  Adam Glowacz,et al.  Early fault diagnosis of bearing and stator faults of the single-phase induction motor using acoustic signals , 2018 .

[31]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[32]  Adam Glowacz,et al.  FAULT DIAGNOSTICS OF ACOUSTIC SIGNALS OF LOADED SYNCHRONOUS MOTOR USING SMOFS-25-EXPANDED AND SELECTED CLASSIFIERS , 2016 .

[33]  Yudong Zhang,et al.  Detection of Dendritic Spines Using Wavelet Packet Entropy and Fuzzy Support Vector Machine. , 2017, CNS & neurological disorders drug targets.

[34]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[35]  Adam Glowacz,et al.  Dijagnostika greške akustičkih signala opterećenog sinkronog motora primjenom SMOFS-25-EXPANDED i odabranih klasifikatora , 2016 .

[36]  Walid Hussein,et al.  DETECTION OF THE RED PALM WEEVIL RHYNCHOPHORUS FERRUGINEUS USING ITS BIOACOUSTICS FEATURES , 2010 .

[37]  Kurt Hornik,et al.  Support Vector Machines in R , 2006 .

[38]  Yudong Zhang,et al.  Preclinical Diagnosis of Magnetic Resonance (MR) Brain Images via Discrete Wavelet Packet Transform with Tsallis Entropy and Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM) , 2015, Entropy.

[39]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[40]  Shih-Wei Lin,et al.  Particle swarm optimization for parameter determination and feature selection of support vector machines , 2008, Expert Syst. Appl..

[41]  Adam Glowacz,et al.  Diagnostics of Rotor Damages of Three-Phase Induction Motors Using Acoustic Signals and SMOFS-20-EXPANDED , 2016 .

[42]  Young-Chan Lee,et al.  Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters , 2005, Expert Syst. Appl..

[43]  Adam Glowacz,et al.  Diagnosis of stator faults of the single-phase induction motor using acoustic signals , 2017 .

[44]  M Farkhanda.  Biosensors for termite control , 2013 .

[45]  Mohamed S. Gadala,et al.  Roller bearing acoustic signature extraction by wavelet packet transform, applications in fault detection and size estimation , 2016 .

[46]  P Sukartana,et al.  EVALUATION OF CHLORFLUAZURON IN CONTROLLING THE SUBTERRANEAN TERMITE COPTOTERMES CURVIGNATHUS (ISOPTERA: RHINOTERMITIDAE) IN INDONESIA , 2009 .

[47]  Ning Wang,et al.  1 Sensitivity , Specificity , Accuracy , Associated Confidence Interval and ROC Analysis with Practical SAS , 2010 .