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

Nanda, Muhammad Achirul; Seminar, Kudang Boro; Nandika, Dodi; Maddu, Akhiruddin

doi:10.3390/info9010005

Cited by 126 publications

(43 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although the training precision is reduced to some extent, it is conductive to avoiding over learning and achieving the accuracy of detection results for botnets. We also present our results with Support Vector Machines (SVM) that is a supervised learning approach and it is one of the three major learning types in machine learning [32][33][34][35][36][37][38]. SVMs are known to be "large margin classifiers" and we expect them to perform well in situations which require good generalization.…”

Section: Classification Calculationmentioning

confidence: 98%

A Feature Extraction Method for P2P Botnet Detection Using Graphic Symmetry Concept

Yang

Wang

2019

Symmetry

View full text Add to dashboard Cite

A DDoS (Distributed Denial of Service) attack makes use of a botnet to launch attacks and cause node congestion of wireless sensor networks, which is a common and serious threat. Due to the various kinds of features required in a Peer-to-Peer (P2P) botnet for DDoS attack detection via current machine learning methods and the failure to effectively detect encrypted botnets, this paper extracts the data packet size and the symmetric intervals in flow according to the concept of graphic symmetry. Combined with flow information entropy and session features, the frequency domain features can be sorted so as to obtain features with better correlations, which solves the problem of multiple types of features required for detection. Information entropy corresponding to the flow size can distinguish an encrypted botnet. This method is implemented through machine learning techniques. Experimental results show that the proposed method can detect the P2P botnet for DDoS attack and the detection accuracy is higher than that of traditional feature detection.

show abstract

Section: Classification Calculationmentioning

confidence: 98%

A Feature Extraction Method for P2P Botnet Detection Using Graphic Symmetry Concept

Yang

Wang

2019

Symmetry

View full text Add to dashboard Cite

show abstract

“…Considering that the seismic signal discrimination problem is a linear non-separable case, the kernel functions K(x i , x j ) = ψ(x i ) · ψ(x j ) are used to map the original input vector space to a high dimensional feature space where an optimal hyperplane can be found [27].…”

Section: Seismic Signal Discrimination Using Svmmentioning

confidence: 99%

Seismic Discrimination between Earthquakes and Explosions Using Support Vector Machine

Kim

Lee

You

2020

Sensors

View full text Add to dashboard Cite

The discrimination between earthquakes and explosions is a serious issue in seismic signal analysis. This paper proposes a seismic discrimination method using support vector machine (SVM), wherein the amplitudes of the P-wave and the S-wave of the seismic signals are selected as feature vectors. Furthermore, to improve the seismic discrimination performance using a heterodyne laser interferometer for seismic wave detection, the Hough transform is applied as a compensation method for the periodic nonlinearity error caused by the frequency-mixing in the laser interferometric seismometer. In the testing procedure, different kernel functions of SVM are used to discriminate between earthquakes and explosions. The outstanding performance of a laser interferometer and Hough transform method for precision seismic measurement and nonlinearity error compensation is confirmed through some experiments using a linear vibration stage. In addition, the effectiveness of the proposed discrimination method using a heterodyne laser interferometer is verified through a receiver operating characteristic curve and other performance indices obtained from practical experiments.

show abstract

“…We aim to obtain the transformed data in a higher dimension with easy separability. Nanda et al [22] presents the numerical results with the highest classification accuracy using the SVM algorithm with the polynomial kernel, so the polynomial kernel is chosen in our paper.…”

Section: Introductionmentioning

confidence: 99%

A 3D Shape Recognition Method Using Hybrid Deep Learning Network CNN–SVM

2020

View full text Add to dashboard Cite

3D shape recognition becomes necessary due to the popularity of 3D data resources. This paper aims to introduce the new method, hybrid deep learning network convolution neural network-support vector machine (CNN-SVM), for 3D recognition. The vertices of the 3D mesh are interpolated to be converted into Point Clouds; those Point Clouds are rotated for 3D data augmentation. We obtain and store the 2D projection of this 3D augmentation data in a 32 × 32 × 12 matrix, the input data of CNN-SVM. An eight-layer CNN is used as the algorithm for feature extraction, then SVM is applied for classifying feature extraction. Two big datasets, ModelNet40 and ModelNet10, of the 3D model are used for model validation. Based on our numerical experimental results, CNN-SVM is more accurate and efficient than other methods. The proposed method is 13.48% more accurate than the PointNet method in ModelNet10 and 8.5% more precise than 3D ShapeNets for ModelNet40. The proposed method works with both the 3D model in the augmented/virtual reality system and in the 3D Point Clouds, an output of the LIDAR sensor in autonomously driving cars.Electronics 2020, 9, 649 2 of 14 connected information [4]. Hence, the right choice for the classification task is directly generating 3D Point Clouds for the original 3D shape.3D shape recognition is a base step that widely uses other tasks in intelligent electronic systems, such as 3D object tracking in intelligent robots or 3D object detection in autonomously driving cars. This paper will present the hybrid deep learning method, a combination of CNN and a Polynomial Kernel-based support vector machine (SVM) classifier, with a high accuracy in 3D shape recognition. CNN is used as the algorithm for feature extraction. The related studies are presented in section two before describing the method in section three. Then, we will compare other methods based on the numerical results. Finally, the conclusion is given. Related StudiesThere are two approaches: hand-crafted shape descriptors and the CNN-based method in some existing related methods for the recognition of 3D shapes. Descriptors of Hand-Crafted ShapeFeatures of a hand-crafted shape consist of local and global features [5]. Global shape features, for example, viewpoint histogram [6] and shape distributions [7], proceed with the whole shape but are inappropriate for the occluded shapes recognition of messy scenes. In contrast, 3D local shape features, for example, spin image [8], rotational projection statistics (RoPS) [9], heat kernel signatures (HKS) [10], and fast point feature histogram (FPFH) [11], or 2D image features extensions, 3D SURF [12] and 2.5D SIFT [13], outperform the global features in messy scenes. Various areas, including 3D shape matching, shape recognition, and 3D shape retrieval, have applied these methods successfully with heavy dependence on human design and field experience. As a result, working on the massive 3D repositories with various objects from a variety of domains is challenging for those shape features. CNN-Based Method

show abstract

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

Cited by 126 publications

References 39 publications

A Feature Extraction Method for P2P Botnet Detection Using Graphic Symmetry Concept

A Feature Extraction Method for P2P Botnet Detection Using Graphic Symmetry Concept

Seismic Discrimination between Earthquakes and Explosions Using Support Vector Machine

A 3D Shape Recognition Method Using Hybrid Deep Learning Network CNN–SVM

Contact Info

Product

Resources

About