检索结果-内蒙古大学图书馆

Investigating the Contribution of Structural and Contextual Features for Spam Detection

TEHNICKI VJESNIK-TECHNICAL GAZETTE 2025年第3期32卷 958-965页

作者： Nuha, Ulin Lin, Chih-Hsueh Natl Kaohsiung Univ Sci & Technol Dept Elect Engn Kaohsiung 80778 Taiwan

One of the detrimental consequences resulting from the rapid and effortless dissemination of information is the high flow of spam messages in user's electronic devices. Various studies have attempted to conduct spam detection by proposing several approaches for spam detection based on input features. However, the effectiveness and efficiency of spam detection need improvement. Therefore, this paper investigates significant feature schemes for spam detection, including structural features and contextual representation. We propose a hybrid approach combining both features and evaluate it using various machine learning algorithms for short message service (SMS) spam classification. Experimental results show that relying solely on contextual representation outperforms structural features, achieving an accuracy of 92.56%. However, the hybrid approach, combining both structural and contextual features, achieves superior results with an accuracy of 93.22% and an F-score of 95.12%. Among the classifiers tested, random forest demonstrated the most robust performance, consistently achieving accuracy above 90% across all feature extraction schemes. The findings highlight the potential of combining structural and contextual features to enhance spam detection performance, with practical implications for telecommunication providers aiming to improve SMS filtering accuracy.

关键词： classifier algorithms contextual representation feature analysis hybrid scheme spam detection

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection IDS for Detecting DoS Attacks in IoT Networks Based on Machine Learning algorithms

引用

SENSORS 2024年第2期24卷 713页

作者： Altulaihan, Esra Almaiah, Mohammed Amin Aljughaiman, Ahmed King Faisal Univ Coll Comp Sci & Informat Technol Dept Comp Networks & Commun Al Hasa 31982 Saudi Arabia Univ Jordan King Abdullah IT Sch 2 Dept Comp Sci Amman 11942 Jordan Appl Sci Private Univ Fac Informat Technol Amman 11931 Jordan Aqaba Univ Technol Dept Comp Sci Aqaba 11191 Jordan

Widespread and ever-increasing cybersecurity attacks against Internet of Things (IoT) systems are causing a wide range of problems for individuals and organizations. The IoT is self-configuring and open, making it vulnerable to insider and outsider attacks. In the IoT, devices are designed to self-configure, enabling them to connect to networks autonomously without extensive manual configuration. By using various protocols, technologies, and automated processes, self-configuring IoT devices are able to seamlessly connect to networks, discover services, and adapt their configurations without requiring manual intervention or setup. Users' security and privacy may be compromised by attackers seeking to obtain access to their personal information, create monetary losses, and spy on them. A Denial of Service (DoS) attack is one of the most devastating attacks against IoT systems because it prevents legitimate users from accessing services. A cyberattack of this type can significantly damage IoT services and smart environment applications in an IoT network. As a result, securing IoT systems has become an increasingly significant concern. Therefore, in this study, we propose an IDS defense mechanism to improve the security of IoT networks against DoS attacks using anomaly detection and machine learning (ML). Anomaly detection is used in the proposed IDS to continuously monitor network traffic for deviations from normal profiles. For that purpose, we used four types of supervised classifier algorithms, namely, Decision Tree (DT), Random Forest (RF), K Nearest Neighbor (kNN), and Support Vector Machine (SVM). In addition, we utilized two types of feature selection algorithms, the Correlation-based Feature Selection (CFS) algorithm and the Genetic Algorithm (GA) and compared their performances. We also utilized the IoTID20 dataset, one of the most recent for detecting anomalous activity in IoT networks, to train our model. The best performances were obtained with DT and RF cl

关键词： IoT network DoS attacks feature selection classifier algorithms machine learning IDS

来源：评论

学校读者我要写书评

暂无评论

Forecasting failure-prone air pressure systems (FFAPS) in vehicles using machine learning

引用

AUTOMATIKA 2024年第1期65卷 1-13页

作者： Rahman, Mohamed Safiyur Sumathy, V. Govt Coll Engn Dharmapuri Tamilnadu India AAM India Mfg Corp Pvt Ltd Chennai Tamilnadu India Govt Coll Engn Elect & Commun Engn Dharmapuri Tamilnadu India

Vehicles become an inevitable factor in everyone's life. Sometimes it becomes a threat to human lives and society. For any real-time-based applications, everyone should focus on predicting failure-prone components. A vehicle's air pressure system (APS) is one of its most important parts. If any system failure happens against APS it leads to core-financial losses, which in turn sometimes leads to loss of human lives. Prediction of APS negligence in a real-time application requires a deep diagnosis and diligent solution. In this study, we developed a machine learning model to predict system failure against APS. A real-time dataset that includes the 170 features and the presence of high-class imbalance data and missing values has been taken and experimentally validated with existing linear and nonlinear classifiers. The performance metrics results show that the Random Forest classifier exceeds other algorithms for training and testing data with an accuracy and F1 score of 99.5 and 99.5 percent respectively.

关键词： Air pressure system (APS) machine learning classifier algorithms forecasting failure prone air pressure systems (FFAPS)

来源：评论

学校读者我要写书评

暂无评论

EOG Signal Classification with Wavelet and Supervised Learning algorithms KNN, SVM and DT

引用

SENSORS 2023年第9期23卷 4553页

作者： Perez, Sandy Nohemy Hernandez Reynoso, Francisco David Perez Gutierrez, Carlos Alberto Gonzalez Leon, Maria De los Angeles Cosio Palacios, Rocio Ortega Univ Politecn Pachuca UPP Informat & Commun Technol Zempoala 43830 Mexico Univ Valle Mexico Ctr Res Innovat & Technol Dev UVM CIIDETEC UVM Queretaro 76230 Mexico Univ Politecn Pachuca UPP Direct Res Innovat & Grad Studies Zempoala 43830 Mexico

The work carried out in this paper consists of the classification of the physiological signal generated by eye movement called Electrooculography (EOG). The human eye performs simultaneous movements, when focusing on an object, generating a potential change in origin between the retinal epithelium and the cornea and modeling the eyeball as a dipole with a positive and negative hemisphere. Supervised learning algorithms were implemented to classify five eye movements;left, right, down, up and blink. Wavelet Transform was used to obtain information in the frequency domain characterizing the EOG signal with a bandwidth of 0.5 to 50 Hz;training results were obtained with the implementation of K-Nearest Neighbor (KNN) 69.4%, a Support Vector Machine (SVM) of 76.9% and Decision Tree (DT) 60.5%, checking the accuracy through the Jaccard index and other metrics such as the confusion matrix and ROC (Receiver Operating Characteristic) curve. As a result, the best classifier for this application was the SVM with Jaccard Index.

关键词： EOG wavelet transform classifier algorithms

来源：评论

学校读者我要写书评

暂无评论

Detection of hollow heart disorder in watermelons using vibrational test and machine learning

引用

JOURNAL OF AGRICULTURE AND FOOD RESEARCH 2023年 14卷

作者： Simon-Portillo, F. J. Abellan-Lopez, D. Fabra-Rodriguez, M. Peral-Orts, R. Sanchez-Lozano, M. Miguel Hernandez Univ Elche Dept Mech & Energy Engn Avda Univ Elche 03202 Spain

The presence of internal voids in watermelons has an impact on the costs of producers and on consumer confidence. Various studies have shown that the vibrational parameters of the fruit are related to maturity, quality and the existence of internal defects. A method for the detection of internal voids in seedless watermelons based on vibrational parameters obtained in impact hammer tests and machine learning is presented. After a statistical study of the test results, the frequency of the first peak of the vibrational response and the density of the watermelon are selected as predictors to be used in the classification algorithms. The accuracy of detecting hollow watermelons increases if firmness estimator is introduced as a predictor. Probabilities of success above 89% in the detection of internal voids have been achieved using different classification algorithm.

关键词： Watermelon Non-destructive testing Vibrational method Hollow detection classifier algorithms Machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Techniques for Attack Detection Using Different Features Selection algorithms and classifiers

引用

WIRELESS PERSONAL COMMUNICATIONS 2018年第4期100卷 1689-1706页

作者： Ghazy, Rania A. El-Rabaie, El-Sayed M. Dessouky, Moawad I. El-Fishawy, Nawal A. Abd El-Samie, Fathi E. El Sadat Univ Sadat Egypt Menoufia Univ Fac Elect Engn Dept Elect & Elect Commun Menoufia 32952 Egypt Menoufia Univ Fac Elect Engn Dept Comp Sci & Engn Menoufia 32952 Egypt

With the growth and benefits of network usage, securing the networks by using anomaly intrusion detection systems (IDS) against unknown intrusions has become an important issue. The first step of protecting any network is the detection of attacks. In this paper, we concentrate on four attacks;denial of service (DoS), probing, remote-to-local, and user-to-root attacks. We depend on features extracted from (NSL-KDD) dataset for these attacks. We investigate the performance of the attack detection process for several numbers of features using various subset-based feature selection techniques aiming to find the optimum collection of features for detecting each attack with an appropriate classifier. Simulation results reveal that redundant features can be eliminated from the attack detection process, and that we can determine the most useful set of features for a certain classifier, which enhances the IDS performance.

关键词： Network intrusion detection (NID) NSL-KDD dataset Features selection classifier algorithms Denial-of service (DoS) Probing (Prob) Remote-to-local (R2L) User-to-root (U2R)

来源：评论

学校读者我要写书评

暂无评论

A multimodal biomarker for concussion identification, prognosis and management

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2018年 102卷 95-103页

作者： Jacquin, Arnaud Kanakia, Saloni Oberly, Doug Prichep, Leslie S. BrainScope Co Inc Algorithm Dev Bethesda MD USA BrainScope Co Inc Clin Affairs Bethesda MD USA NYU Sch Med Dept Psychiat New York NY USA

Background Prompt, accurate, objective assessment of concussion is crucial, particularly for children/adolescents and young adults. While there is currently no gold standard for the diagnosis of concussion, the importance of multidimensional/multimodal assessments has recently been emphasized. Methods: Concussed subjects (N = 177), matched controls (N = 187) and healthy volunteers (N = 204) represented a convenience sample of male and female subjects between the ages of 13 and 25 years, enrolled at 29 Colleges and 19 High Schools in the US. Subjects were tested at time of injury and at multiple time points during recovery. Assessments included EEG, neurocognitive tests and standard concussion assessment tools. Multimodal classifiers to maximally separate controls from concussed subjects with prolonged recovery (>= 14 days) were derived using quantitative EEG, neurocognitive and vestibular measures, informed feature reduction and a Genetic Algorithm methodology for classifier derivation. The methodology protected against overtraining using an internal cross-validation framework. An enhanced multimodal Brain Function Index (eBFI) was derived from the classifier output and mapped to a percentile scale which expressed the index relative to non-injured controls. Results: At time of injury eBFIs were significantly different between controls and concussed subjects with prolonged recovery, showing return to non-concussed levels at return-to-play plus 45 days. For the combined concussed population, and for the short recovery subjects, a more rapid recovery was seen. Conclusions: This multivariate, multimodal, objective index of brain function impairment can potentially be used, along with other tools, to aid in diagnosis, assessment, and tracking of recovery from concussion.

关键词： TBI Brain function index Enhanced BFI Concussion Sport-related concussion classifier algorithms Quantitative brain activity Electrophysiology of TBI Neurocognitive assessments Return to play

来源：评论

学校读者我要写书评

暂无评论

INSURANCE CLAIM RISK SCORING WITH MACHINE LEARNING algorithms: A CASE STUDY ON DEVELOPING A PREDICTIVE SYSTEM FOR ASSESSING CORPORATE CUSTOMERS' CLAIM RISK

INSURANCE CLAIM RISK SCORING WITH MACHINE LEARNING ALGORITHM...

引用

作者： Tuomi-Nikula, Tino LAPPEENRANTA UNIVERSITY OF TECHNOLOGY

学位级别：硕士

Predictive learning algorithms offer tools to automate and improve insurance risk management. The aim of this thesis is to study classification algorithms in risk scoring applications and to evaluate them in the creation of insurance claim risk scores from customer risk survey data. Another goal for the thesis is to quantify weights for risk survey questions using machine learning methods. This case study consists of a critical literature review and a quantitative analysis where the risk scoring systems were developed and their performance on test data evaluated. Logistic regression, Support Vector Machines, Extreme Gradient Boosted Trees (XGBT) and a Feed Forward Neural Network were used to predict claim risk from customer risk survey data. The results of the study show that with the test data, XGBT was the most accurate, predicting the risk class of a customer with 73% accuracy. Nonetheless, it is worth mentioning that all tested algorithms were suitable for the task. The results also suggest that machine learning risk prediction enables analysis of individual risk factors, and that feature importance metrics can be used to quantify weights for risk survey questions.

关键词： risk scoring machine learning insurance risk classifier algorithms predictive analytics

来源：评论

学校读者我要写书评

暂无评论

A Comparison Study of classifier algorithms for Mobile-phone's Accelerometer Based Activity Recognition

引用

Procedia Engineering 2012年 41卷 224-229页

作者： Media Anugerah Ayu Siti Aisyah Ismail Ahmad Faridi Abdul Matin Teddy Mantoro Intelligent Environment Research Group (INTEG Lab) Faculty of Information and Communication Technology International Islamic University Malaysia 53100 Kuala LumpurMalaysia Advanced Informatics School Semarak International Campus Universiti Teknologi Malaysia 53000 Kuala LumpurMalaysia

Nowadays, many mobile phones have been equipped with sensors to enable the delivery of advanced features/services to the users. Accelerometer is one of the sensors that embedded to several types of mobile phones. Our earlier research has shown that data from mobile-phone embedded accelerometer can be used for activity recognition purpose [1] . As a continuation of the research towards the search for a suitable and reliable algorithm for real-time activity recognition using mobile phone, an evaluation and comparison study of the performance of seven different categories of classifier algorithms in classifying user activities were conducted. Five basic human activities (jogging, jumping, sitting, standing, and walking) were tested. The training and testing data were done using Weka 3.6.6 data mining tool. The overall accuracy rate for classifier training managed to exceed 96% and exceeded 90% for classifier testing, which are very encouraging results.

关键词： Activity recognition Accelerometer classifier algorithms Activity-aware Accelerometer based mobile phone

来源：评论

学校读者我要写书评

暂无评论

Improve the automatic classification accuracy for Arabic tweets using ensemble methods

引用

Journal of Electrical Systems and Information Technology 2018年第3期5卷 363-370页

作者： Hammam M. Abdelaal Ahmed N. Elmahdy Ali A. Halawa Hassan A. Youness Department of Computers and Systems Engineering Faculty of Engineering Al-Azhar University Cairo Egypt Department of Computers and Systems Engineering Faculty of Engineering Minia University Egypt

Tweets classification became interest topics in recent years, especially for the Arabic language. In this paper, the Arabic tweets are classified automatically into one of some predetermined categories mainly: sport, culture, politics, technology and general, based on their linguistic characteristics and their contents, also the classification accuracy is improved for Arabic tweets, by using ensemble methods mainly: bagging, boosting and stacking on the same dataset that we used it before in the classification, to verify of the results, and identify the best classifier gives high accuracy. The experimental results showed that using ensemble methods are better than using individual classifier, to improve the accuracy of classification. Increased accuracy of classifier Naïve Bayes (NB) to 1.6%, classifier Sequential Minimal Optimization (SMO) to 2.2% and finally Decision Tree (J48) classifier reached up to 3.2%, comparing to using the J48, NB, or SMO as a single classifier.

关键词： Arabic tweets Preprocessing Classifications classifier algorithms Ensemble methods

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：