An approach towards enhancement of classification accuracy rate using efficient pruning methods with associative classifiers

2021 ◽  
Author(s):  
Kavita Mittal
Keyword(s):  
Classification Accuracy ◽  
Accuracy Rate ◽  
Associative Classifiers ◽  
Pruning Methods

scholarly journals MalDeep: A Deep Learning Classification Framework against Malware Variants Based on Texture Visualization

2019 ◽  
Vol 2019 ◽  
pp. 1-11
Author(s):  
Yuntao Zhao ◽  
Chunyu Xu ◽  
Bo Bo ◽  
Yongxin Feng
Keyword(s):  
Deep Learning ◽  
Classification Accuracy ◽  
Feature Space ◽  
Image Texture ◽  
Accuracy Rate ◽  
Texture Representation ◽  
Malware Classification ◽  
Classification Framework ◽  
Average Accuracy ◽  
New Feature

The increasing sophistication of malware variants such as encryption, polymorphism, and obfuscation calls for the new detection and classification technology. In this paper, MalDeep, a novel malware classification framework of deep learning based on texture visualization, is proposed against malicious variants. Through code mapping, texture partitioning, and texture extracting, we can study malware classification in a new feature space of image texture representation without decryption and disassembly. Furthermore, we built a malware classifier on convolutional neural network with two convolutional layers, two downsampling layers, and many full connection layers. We adopt the dataset, from Microsoft Malware Classification Challenge including 9 categories of malware families and 10868 variant samples, to train the model. The experiment results show that the established MalDeep has a higher accuracy rate for malware classification. In particular, for some backdoor families, the classification accuracy of the model reaches over 99%. Moreover, compared with other main antivirus software, MalDeep also outperforms others in the average accuracy for the variants from different families.

scholarly journals Sex determination in Northern Thai from crania by using computer-aided design software and conventional caliper methods

2019 ◽  
Vol 12 (3) ◽  
pp. 103-110
Author(s):  
Toonlanat Thuanthong ◽  
Paiwan Sudwan
Keyword(s):  
Sex Determination ◽  
Classification Accuracy ◽  
Computer Aided Design ◽  
High Accuracy ◽  
Accuracy Rate ◽  
Essential Step ◽  
Computer Aided ◽  
Design Software ◽  
Aided Design ◽  
Digital Caliper

AbstractBackgroundIdentification of sex from skeletal remains is an essential step in forensic anthropology. The skull is the second choice, after the pelvis, to estimate sex by osteometric methods.ObjectiveTo evaluate the process of identification of sex in Northern Thai from crania by using computer-aided design (AutoCAD) software and conventional caliper methods.MethodsDry skulls of 86 men and 74 women were examined. AutoCAD software and digital calipers were used to measure dimensions. Eleven of the 15 parameters were created for this study.ResultsMen are significantly larger than women in all parameters, except in the nasospinale–prosthion measurement. There were no significant differences in the intraobserver error test and between the AutoCAD and digital caliper measurements. The logistic regression analysis yielded a sex classification accuracy rate of 92.9% in men, 93.4% in women, and 93.1% of overall accuracy for AutoCAD software. When using digital calipers, there was an accuracy rate of 89.3% in men, 94.7% in women, and 91.9% for overall accuracy.ConclusionsAutoCAD software is a reliable method to predict the sex and provide high accuracy in sex determination from crania.

scholarly journals Empirical Study on Theories and Techniques of Adolescent Physical Health Promotion under the Background of Big Data

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Haolun Xu
Keyword(s):  
Health Promotion ◽  
Big Data ◽  
Physical Health ◽  
Classification Accuracy ◽  
Health Data ◽  
Training Set ◽  
Accuracy Rate ◽  
Standing Long Jump ◽  
Long Jump ◽  
Accuracy Rates

In order to make my country’s youth health management more scientific, more standardized, and more effective, it is necessary to conduct in-depth research on the management of youth physical health promotion. Through the investigation and analysis of the physical health data of adolescents in my country, this paper proposes that the results of health intervention training as part of the empirical research on the construction of adolescent health big data management service system can effectively improve the relationship hypothesis of the physical health of adolescents and by selecting the example of our country’s “Adolescent Physical Health Data Analysis in 2020” for regression analysis. The research results show that the theory of adolescent physical health promotion can improve the physical health of adolescents by interfering with students’ physical exercise. In the processing of data, GBDT is suitable when the training set is relatively large, and as the sample size increases, the accuracy rate can reach 79.79%. In terms of the classification accuracy of male sitting forward bending promotion, the accuracy of the RF method is higher than that of GBDT. In terms of the promotion classification effect of boys’ 1000 m running, the RF method achieved the highest promotion accuracy rate of 77.62%. In the male pull-ups to promote the classification effect, when the proportion of the training set is 60%, the RF method gets the highest accuracy rate, which is 92.04%. The results of the classification effect for girls standing long jump promotion show that the classification accuracy rate for girls standing long jump promotion is between 51% and 56%. When the training set is less than 60%, the RF method is the best, the highest is 53.93%, and the rest is the GBDT method, the highest is 55.46%; in Macro-F1, the RF and GBDT indicators have their own advantages. In the promotion of the classification effect on the final fitness level of girls, the accuracy rates of RF and GBDT methods range from 90% to 96%, and the accuracy rates of the NN method range from 80% to 87%; when the practice rate reaches 80%, the GBDT method achieves the highest accuracy rate of 95.06%; on the Macro-F1 index, the GBDT method is obviously the best.

scholarly journals Study on Potential of Meridian Acupoints of Traditional Chinese Medicine

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Qiuping Li ◽  
Tianxia Zhao ◽  
Xin’an Wang ◽  
Changpei Qiu ◽  
Bing Zhou ◽  
...  
Keyword(s):  
Chinese Medicine ◽  
Traditional Chinese Medicine ◽  
Electric Potential ◽  
Classification Accuracy ◽  
Low Cost ◽  
Principal Component ◽  
Accuracy Rate ◽  
Good Therapeutic Effect ◽  
Acquisition Scheme ◽  
Potential Signal

In recent years, Traditional Chinese Medicine (TCM) has attracted more and more attention due to its good therapeutic effect, low cost, and convenience. This research is also a part of the goal of the modernization of TCM. Based on the meridian electric potential acquisition system independently developed by our project team, in this paper, we designed the human body's meridian electric potential acquisition scheme. We use principal component analysis (PCA) to prove that the meridional potential signal is derived from the ECG signal. Then, Inception ResNet V2 was used to classify acupoints and nonacupoints. Finally, the classification accuracy rate reached 86.59045265, and the F1 score = 0.72161642. This shows that acupoints and nonacupoints can be distinguished by their surface potential.

Learning Advanced Brain Computer Interface Technology

2019 ◽  
Vol 15 (3) ◽  
pp. 14-27
Author(s):  
Wang Tao ◽  
Wu Linyan ◽  
Li Yanping ◽  
Gao Nuo ◽  
Zhang Weiran
Keyword(s):  
Feature Extraction ◽  
Classification Accuracy ◽  
Wavelet Packet ◽  
Extraction Methods ◽  
Support Vector ◽  
Wavelet Packet Analysis ◽  
Accuracy Rate ◽  
Desirable Outcome ◽  
Eeg Data ◽  
System Data

Feature extraction is an important step in electroencephalogram (EEG) processing of motor imagery, and the feature extraction of EEG directly affects the final classification results. Through the analysis of various feature extraction methods, this article finally selects Common Spatial Patterns (CSP) and wavelet packet analysis (WPA) to extract the feature and uses Support Vector Machine (SVM) to classify and compare these extracted features. For the EEG data provided by GRAZ University, the accuracy rate of feature extraction using CSP algorithm is 85.5%, and the accuracy rate of feature extraction using wavelet packet analysis is 92%. Then this paper analyzes the EEG data collected by Emotiv epoc+ system. The classification accuracy of wavelet packet extracted features can still be maintained at more than 80%, while the classification accuracy of CSP extracted feature is decreased obviously. Experimental results show that the method of wavelet packet analysis towards competition data and Emotiv epoc+ system data can both get a desirable outcome.

scholarly journals Identifying the Optimal Features in Multimodal Deception Detection

2020 ◽  
Vol 4 (2) ◽  
pp. 25
Author(s):  
Amin Derakhshan ◽  
Mohammad Mikaeili ◽  
Tom Gedeon ◽  
Ali Motie Nasrabadi
Keyword(s):  
Thermal Imaging ◽  
Classification Accuracy ◽  
Deception Detection ◽  
Feature Selection Method ◽  
Feature Reduction ◽  
Accuracy Rate ◽  
Reduction Techniques ◽  
The Face ◽  
Thermal Features ◽  
Mock Crime

Facial thermal imaging is a non-contact technology which can be useful for ubiquitous deceptive anxiety recognition. To date, studies investigating this technology have produced equivocal results in classification accuracy and finding the most correlated regions on the face. This study was conducted using our dataset with 41 subjects using two different protocols and three modalities (thermal, GSR and PPG). We selected and tracked five regions of interest (ROI) on each facial thermal imprint including periorbital, forehead, cheek, perinasal and chin that were mostly used in previous papers. By employing six statistical features, four feature reduction techniques and three classifiers, we attempted to identify the ROIs which are mostly associated with activation of the sympathetic nervous system to increase the final classification accuracy rate. The results of linear classification models show significant improvement of classification accuracy by using ROC feature selection method. We achieved 90.1% and 74.7% accuracy rate for thermal features in mock crime and best friend scenarios, respectively. Our experimental results show that perinasal and cheek areas have greater discriminatory power in comparison with other ROIs on the face.

scholarly journals Decimation-Free Directional Filter Banks for Classification and Numbering on Posterior Dental Radiography Using Mesiodistal Neck Detection

2014 ◽  
Vol 18 (4) ◽  
pp. 649-657
Author(s):  
Agus Zainal Arifin ◽  
◽  
Anny Yuniarti ◽  
Wijayanti Nurul Khotimah ◽  
Arya Yudhi Wijaya ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Biomedical Applications ◽  
Filter Bank ◽  
Dental Radiography ◽  
Support Vector ◽  
Segmentation Method ◽  
Accuracy Rate ◽  
Directional Filter ◽  
Novel Method

Dental classification and numbering on posterior dental radiography are important tasks for forensic and biomedical applications. This paper proposed a novel method of classification and numbering on posterior dental radiography using Decimation-Free Directional Filter Bank (DDFB) and mesiodistal neck detection. The method was started by a segmentation method for decomposing dental image into directional images using DDFB. Detection of mesiodistal neck tooth separated the crown and the root of teeth. Finally we used support vector machine for classification and numbering. The experimental results achieved a classification accuracy rate of 91%. It approved the robustness of the proposed method for solving the problem of dental classification and numbering.

Research of Orange Quality Classification Technology Based on BP Neural Network Algorithm

2015 ◽  
Vol 713-715 ◽  
pp. 1821-1824
Author(s):  
Chun Hua Qian ◽  
He Qun Qiang ◽  
Sheng Rong Gong
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Classification Accuracy ◽  
Bp Algorithm ◽  
Shape Features ◽  
Accuracy Rate ◽  
Network Algorithm ◽  
Quality Classification ◽  
Neural Network Algorithm

BP algorithm is a classical neural network algorithm. We analyzed the deficiency of traditional BP neural network algorithm, designed new S function and momentum method strategy, optimized the algorithm parameters. We use the new algorithm in the classification of orange images, take color and shape features as input value, the experimental results proved that our algorithm is faster and the classification accuracy rate reaches to 90%

Sign in / Sign up

Export Citation Format

Share Document