informationArticleA Comparison Study of Kernel Functions in theSupport Vector Machine and Its Application forTermite DetectionMuhammad Achirul Nanda1ID, Kudang Boro Seminar1,*ID, Dodi Nandika2and Akhiruddin Maddu31Faculty of Agricultural Technology, Bogor Agricultural University, Bogor 16680, West Java, Indonesia;[email protected]2Faculty of Forestry, Bogor Agricultural University, Bogor 16680, West Java, Indonesia;[email protected]3Faculty of Mathematics and Natural Sciences, Bogor Agricultural University, Bogor 16680, West Java,Indonesia; [email protected]*Correspondence: [email protected]; Tel.: +62-8164834625Received: 10 December 2017; Accepted: 28 December 2017; Published: 2 January 2018Abstract:Termites are the most destructive pests and their attacks significantly impact the quality ofwooden buildings. Due to their cryptic behavior, it is rarely apparent from visual observation that atermite infestation is active and that wood damage is occurring. Based on the phenomenon of acousticsignals generated by termites when attacking wood, we proposed a practical framework to detecttermites nondestructively, i.e., by using the acoustic signals extraction. This method has the pros tomaintain the quality of wood products and prevent higher termite attacks. In this work, we inserted220 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 thisstudy’s analysis. Furthermore, the support vector machine (SVM) algorithm with different kernelfunctions (i.e., linear, radial basis function, sigmoid and polynomial) were employed to recognize thetermites’ 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.Keywords:acoustic signal; kernel function; support vector machine; termite detection1. IntroductionLiving in large underground colonies, termites can attack any wood that has a direct contact to theground and can even lead to the death of a healthy tree. Termites are harmful pests that economicallyimpact the quality of the wood in wooden buildings, forest trees and crops. As can be seen in Figure1,it shows the initial attack of subterranean termites onAcacia crassicarpaplantation, Riau Province,Indonesia. In addition, the damage of wooden buildings by termites is also easy to find in Bogorcity and surrounding areas . In fact, some areas of the important buildings in Indonesia have beenseriously attacked e.g., Presidential Palace, Istana Merdeka, Jakarta, etc. . Nandika et al.  reportedthat the cost, due to termite attacks to wooden buildings, was estimated to reach about Rp 8.7 trillionin 2015 not including treatment costs, repairs of the damaged buildings and loss of property value.