Article
Computer Science, Information Systems
Hina Tufail, M. Usman Ashraf, Khalid Alsubhi, Hani Moaiteq Aljahdali
Summary: The outbreak of Covid-19 has led to an increase in global online shopping, highlighting the significant impact of online reviews on businesses. In our research, we proposed a fake review detection model using text classification and machine learning techniques, which outperformed other state-of-the-art techniques with high accuracy.
Article
Computer Science, Artificial Intelligence
Behrooz Noori
Summary: This article introduces a new framework for categorizing and predicting customer sentiments, and the decision tree algorithm was found to provide the best results among various machine learning algorithms used. The most important factors influencing the great customer experience were extracted using the decision tree algorithm. An interesting observation was made on the effect of the number of features on the performance of machine learning algorithms.
APPLIED ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Yinan Guo, Zirui Zhang, Fengzhen Tang
Summary: Feature selection is important in machine learning to reduce complexity and simplify interpretation. A novel non-linear method proposed in this paper uses kernelized multi-class support vector machines and fast recursive feature elimination to select features that work well for all classes, resulting in lower computational time complexity.
PATTERN RECOGNITION
(2021)
Article
Engineering, Multidisciplinary
Bilal Chandio, Asadullah Shaikh, Maheen Bakhtyar, Mesfer Alrizq, Junaid Baber, Adel Sulaiman, Adel Rajab, Waheed Noor
Summary: The study investigates machine learning methods for sentiment analysis in Roman Urdu, proposes a fine-tuned SVM with a Roman Urdu Stemmer, and introduces the largest dataset in Roman Urdu. The experiments demonstrate the challenging nature of Roman Urdu sentiment analysis and the need for further research attention.
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES
(2022)
Article
Computer Science, Hardware & Architecture
Yosef Masoudi-Sobhanzadeh, Shabnam Emami-Moghaddam
Summary: This study proposes a machine learning-based method to predict botnets, addressing the limitations of existing methods in real-time application, functionality, and consideration of attack types. The results show that the proposed method accurately classifies data streams into relevant groups and achieves a trade-off between feature selection and prediction model performance.
Article
Computer Science, Artificial Intelligence
L. D. C. S. Subhashini, Yuefeng Li, Jinglan Zhang, Ajantha S. Atukorale, Yutong Wu
Summary: With the increasing number of customer reviews on the Web, there is a growing demand for effective methods to retrieve valuable information from reviews. Researchers have proposed many automatic mining and classification methods, but choosing a trusted method remains a challenge for companies. This article surveys recent opinion mining literature, focusing on text feature extraction, knowledge representation, and classification methods.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Article
Computer Science, Artificial Intelligence
Reyhaneh Yaghobzadeh, Seyed Reza Kamel, Mojtaba Asgari
Summary: Various methods have been proposed to diagnose renal failure using data mining and artificial intelligence techniques. The present study aimed to increase the accuracy and efficiency of renal failure diagnosis by introducing a feature selection method based on the dragonfly algorithm and optimizing data classification using the optimal parameters of the support vector machine algorithm. The proposed method showed a significant improvement of 34.12% in accuracy compared to the latest available methods, with 3.37% and 9.17% higher accuracy ratings.
Article
Automation & Control Systems
Yaonan Cheng, Xiaoyu Gai, Yingbo Jin, Rui Guan, Mengda Lu, Ya Ding
Summary: Tool wear has a significant impact on machining quality and efficiency. Accurate and effective monitoring of tool wear is crucial for timely tool replacement and intelligent development of the manufacturing industry. This article proposes a new method using the WOA-optimized SVM to predict tool wear, which shows improved accuracy and performance based on milling experiments.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Javier Alcaraz, Martine Labbe, Mercedes Landete
Summary: This paper introduces a Support Vector Machine with feature selection and proposes a bi-objective evolutionary algorithm to approximate the Pareto optimal frontier. Extensive computational experiments are conducted to compare the results obtained by different methods, and the properties of points in the Pareto frontier are discussed.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Chemistry, Analytical
Erik Kepes, Jakub Vrabel, Ondrej Adamovsky, Sara Stritezska, Pavlina Modlitbova, Pavel Porizka, Jozef Kaiser
Summary: This article presents four approaches to interpret support vector machines (SVMs) and investigates the classification task of 19 algal and cyanobacterial species. The study finds that different feature importance metrics provide complementary information, and identifies the SVM model's bias towards features with a large variance.
ANALYTICA CHIMICA ACTA
(2022)
Article
Computer Science, Information Systems
Ruba Obiedat, Raneem Qaddoura, Ala' M. Al-Zoubi, Laila Al-Qaisi, Osama Harfoushi, Mo'ath Alrefai, Hossam Faris
Summary: With the increasing presence of online media and customers' reviews, decision-makers and customers in the restaurant industry are paying more attention to the impact of customer reviews. To meet customer expectations and improve service quality, decision-makers need to analyze the sentiments underlying customer reviews. This study proposes a PSO-SVM approach to analyze and predict the sentiments of customer reviews, achieving better classification accuracy by optimizing the dataset and addressing the issue of imbalanced data.
Article
Engineering, Electrical & Electronic
Younes Mohammadi, Amir Salarpour, Roberto Chouhy Leborgne
Summary: This paper introduces two classifiers, Support Vector Machine (SVM) and Ensemble, using genetic algorithm and 10-fold cross-validation to classify voltage sag sources, achieving high accuracy rates of 96.28% and 99.11% respectively. A comprehensive strategy to enhance SVM accuracy and maintain Ensemble performance by selecting appropriate features is presented, resulting in improved classification performance.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Raymond Chiong, Zongwen Fan, Zhongyi Hu, Fabian Chiong
Summary: This study introduces an improved support vector machine method for predicting body fat percentage. The method incorporates bias error control and feature selection to enhance prediction accuracy, outperforming other prediction models in experimental results.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Multidisciplinary Sciences
Abdullah Al-Saleh
Summary: The Internet of Things field has posed challenges for network architectures, with cybersecurity being the primary goal for intrusion detection systems (IDSs). To improve IDS performance, researchers have focused on efficiently protecting connected data and devices due to the increasing number and types of attacks. This paper presents a novel IDS model that offers accurate detection in less processing time by reducing computational complexity. The model uses the Gini index method to determine security feature impurity and improve selection processes. It also employs a balanced communication-avoiding support vector machine decision tree method for enhanced intrusion detection accuracy. Evaluation using the UNSW-NB 15 dataset shows that the proposed model achieves a high attack detection performance of approximately 98.5%.
SCIENTIFIC REPORTS
(2023)
Article
Biochemical Research Methods
Chun Qiu, Sai Li, Shenghui Yang, Lin Wang, Aihui Zeng, Xufeng Zhang
Summary: The study identified key genes related to the mechanisms of glioblastoma occurrence and established a classification model using the CFS method. The accuracy of the model was 76.25% and 70.3% in different tests. PPP2R2B and CYBB may serve as potential biomarkers for the diagnosis of glioblastomas.
CURRENT BIOINFORMATICS
(2021)
