Article
Education & Educational Research
Muhammad Shoaib, Nasir Sayed, Nedra Amara, Abdul Latif, Sikandar Azam, Sajjad Muhammad
Summary: Technology and data analysis play a crucial role in education, and educational data mining has emerged as an important trend in understanding student behavior and factors influencing academic achievement.
EDUCATION AND INFORMATION TECHNOLOGIES
(2022)
Article
Education & Educational Research
Ruangsak Trakunphutthirak, Vincent C. S. Lee
Summary: This study uses machine learning techniques to analyze student academic performance in higher education institutions, filling gaps in existing literature and providing better understanding for educators by incorporating data on Internet usage behavior, among other factors.
JOURNAL OF EDUCATIONAL COMPUTING RESEARCH
(2022)
Article
Computer Science, Information Systems
Siti Dianah Abdul Bujang, Ali Selamat, Roliana Ibrahim, Ondrej Krejcar, Enrique Herrera-Viedma, Hamido Fujita, Nor Azura Md. Ghani
Summary: This study conducted a comprehensive analysis of machine learning techniques, compared the accuracy performance of different techniques for predicting student grades in the first semester, and proposed a multi-class prediction model. The results showed that the model achieved significant performance improvement when dealing with imbalanced datasets, providing a more reliable model for student grade prediction.
Review
Education & Educational Research
Anupam Khan, Soumya K. Ghosh
Summary: Student performance modelling is a challenging and popular research topic in educational data mining, with multiple factors influencing performance in non-linear ways. Limited specific surveys on student performance analysis and prediction are available, primarily focusing on identifying possible predictors or modeling student performance, but lacking consideration of temporal aspects. This paper presents a systematic review of EDM studies on student performance in classroom learning, focusing on predictors, identification methods, time, and aim of prediction, being the first survey to specifically consider only classroom learning and address temporal aspects.
EDUCATION AND INFORMATION TECHNOLOGIES
(2021)
Review
Computer Science, Information Systems
Siti Dianah Abdul Bujang, Ali Selamat, Ondrej Krejcar, Farhan Mohamed, Lim Kok Cheng, Po Chan Chiu, Hamido Fujita
Summary: This study aims to review existing research and provide a state-of-the-art approach for handling imbalanced classification in higher education, focusing on student grade prediction. The survey results reveal that the widely applied method for addressing imbalanced problems in student grade prediction is the data-level approach using SMOTE oversampling. However, there is a lack of application of hybrid and feature selection methods to improve the generalization of predictive models. The outcomes of this review will guide professionals and academic researchers in dealing with imbalanced classification, especially in higher education.
Article
Computer Science, Information Systems
Ziling Chen, Gang Cen, Ying Wei, Zifei Li
Summary: Predicting student performance is crucial for improving academic achievements. This paper proposes a student performance prediction approach that combines a relationship matrix-based bipartite network method and Louvain clustering. It also introduces a hybrid neural network model based on a relationship matrix. The results show that the proposed approach effectively predicts student performance, allowing educators to provide individualized support and assistance.
Review
Computer Science, Information Systems
Dalia Abdulkareem Shafiq, Mohsen Marjani, Riyaz Ahamed Ariyaluran Habeeb, David Asirvatham
Summary: Student retention is a crucial metric in education, and various techniques such as educational data mining and learning analytics are employed to improve teaching practices and identify at-risk students. However, there are challenges in applying predictive models and incorporating important factors like heterogeneous and homogeneous student groups.
Article
Chemistry, Multidisciplinary
Chuang Liu, Haojie Wang, Yingkui Du, Zhonghu Yuan
Summary: Student achievement prediction is a crucial research direction in educational data mining, which directly reflects students' mastery of courses and teachers' teaching level. This paper proposes a student achievement prediction model based on evolutionary spiking neural network and demonstrates its accuracy through experimental results.
APPLIED SCIENCES-BASEL
(2022)
Review
Psychology, Multidisciplinary
Yupei Zhang, Yue Yun, Rui An, Jiaqi Cui, Huan Dai, Xunqun Shang
Summary: This paper systematically reviews the study of student performance prediction (SPP) from the perspective of machine learning and data mining. It divides SPP into five stages and conducts experiments on data sets to discuss current shortcomings and future work, ultimately advancing the progress of personalized education.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Education & Educational Research
Yawen Chen, Linbo Zhai
Summary: Accompanied by the advancement of technology, educational data has significantly increased. Educational data mining techniques play a crucial role in extracting valuable information from this vast amount of data. Machine learning has shown promising performance in educational applications, particularly in student performance prediction. However, there is a lack of comprehensive studies comparing different machine learning methods in educational data, and most studies focus on single types of data. This paper investigates the performance of machine learning methods in different application scenarios using three types of task-oriented educational data.
EDUCATION AND INFORMATION TECHNOLOGIES
(2023)
Article
Education & Educational Research
Neila Chettaoui, Ayman Atia, Med Salim Bouhlel
Summary: This paper explores the integration of eye-gaze features to predict students' learning performance during an embodied learning activity. By collecting students' eye-tracking data, learning profiles, academic performances, and time to complete the activity, the research finds that combining eye-gaze features with learning traces and behavior attributes can accurately predict students' learning performance.
EDUCATION AND INFORMATION TECHNOLOGIES
(2023)
Article
Chemistry, Multidisciplinary
Aurora Esteban, Cristobal Romero, Amelia Zafra
Summary: This paper examines the significance of assignment information in predicting student success in distance learning, showcasing how algorithms using Multiple Instance Learning outperform those using single instance learning by more than 20%.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Theory & Methods
Tai Tan Mai, Marija Bezbradica, Martin Crane
Summary: With the shift of higher education programmes to online channels due to the COVID19 pandemic, issues in monitoring students' learning progress have arisen. However, a novel approach has been proposed to analyze students' learning behavior and its relationship with learning assessment results, improving the analysis and prediction based on learning behavioral datasets.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Chemistry, Multidisciplinary
Han Xue, Yanmin Niu
Summary: In higher education, student learning relies increasingly on autonomy. With the rise in blended learning, both online and offline, students need to further improve their online learning effectiveness. Therefore, predicting students' performance and identifying students who are struggling in real time to intervene is an important way to improve learning outcomes.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Multidisciplinary
Yi Luo, Saientan Bag, Orysia Zaremba, Adrian Cierpka, Jacopo Andreo, Stefan Wuttke, Pascal Friederich, Manuel Tsotsalas
Summary: This study demonstrates the potential of machine learning in predicting the synthesis parameters of metal-organic frameworks (MOFs). By establishing a MOF synthesis database and training machine learning models, the researchers achieved good prediction performance in synthesizing new MOF structures, surpassing human expert predictions.
ANGEWANDTE CHEMIE-INTERNATIONAL EDITION
(2022)
Article
Computer Science, Information Systems
Abeer S. Desuky, Yomna M. Elbarawy, Samina Kausar, Asmaa Hekal Omar, Sadiq Hussain
Summary: This study focuses on the classification of imbalanced datasets. It rebalances the datasets through resampling and uses Jellyfish Search (JS) to find the optimal subset. Experimental results show that the proposed method performs better in terms of performance.
Article
Multidisciplinary Sciences
Fahime Khozeimeh, Danial Sharifrazi, Navid Hoseini Izadi, Javad Hassannataj Joloudari, Afshin Shoeibi, Roohallah Alizadehsani, Mehrzad Tartibi, Sadiq Hussain, Zahra Alizadeh Sani, Marjane Khodatars, Delaram Sadeghi, Abbas Khosravi, Saeid Nahavandi, Ru-San Tan, U. Rajendra Acharya, Sheikh Mohammed Shariful Islam
Summary: This study proposes a novel CAD detection method based on CMR images, utilizing the feature extraction ability of deep neural networks and combining the features with the aid of a random forest. By converting image data to numeric features and using the predictions of multiple CNNs as input features for decision trees, our method can be applied to any image dataset. Experiments on a large CMR dataset show that our method achieves higher accuracy compared to a stand-alone CNN trained using fivefold cross validation.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Cybernetics
Paraskevi Theodorou, Apostolos Meliones
Summary: The autonomy, independence, productivity, and quality of life of people with visual impairments greatly rely on their ability to use assistive technologies. This paper presents a detailed analysis of user needs and requirements for designing and developing assistive navigation systems for blind and visually impaired people. The findings offer insight into the design, development, deployment, and distribution of such systems.
UNIVERSAL ACCESS IN THE INFORMATION SOCIETY
(2023)
Article
Ophthalmology
Paraskevi Theodorou, Apostolos Meliones, Costas Filios
Summary: In an effort to improve the quality of life for visually impaired individuals, cities have implemented sound-emitting devices in traffic lights and sidewalks to aid navigation. The concept of smart cities has also led to the installation of synchronized, real-time traffic lights worldwide. Factors such as cost-efficient planning, maintenance, power efficiency, and device coordination are important considerations. This article provides an overview of existing navigation solutions, along with a new implementation proposal based on feedback from interviews with members of the Lighthouse for the Blind of Greece.
BRITISH JOURNAL OF VISUAL IMPAIRMENT
(2023)
Article
Green & Sustainable Science & Technology
Sheikh Safiullah, Asadur Rahman, Shameem Ahmad Lone, S. M. Suhail Hussain, Taha Selim Ustun
Summary: The ongoing COVID-19 pandemic has disrupted the health sector, and the use of masks, social distancing, and antibody growth rate are critical in reducing the spread of the virus. This study proposes a nature-inspired meta-heuristic algorithm called C-19BOA, which mimics the behavior of coronavirus disease and focuses on three containment factors: social distancing, mask usage, and antibody rate. The algorithm is tested on benchmark functions and applied to optimize power system parameters, demonstrating its effectiveness.
Article
Computer Science, Information Systems
Rositsa Doneva, Silvia Gaftandzhieva
Summary: The success of a business organization in digital transformation depends on identifying and monitoring critical success factors (CSFs). This paper presents a comprehensive framework for managing CSFs, helping organizations conceptualize CSFs for different stages and providing practical guidance for maximum benefit.
Article
Computer Science, Artificial Intelligence
Moloud Abdar, Soorena Salari, Sina Qahremani, Hak-Keung Lam, Fakhri Karray, Sadiq Hussain, Abbas Khosravi, U. Rajendra Acharya, Vladimir Makarenkov, Saeid Nahavandi
Summary: The COVID-19 pandemic poses a major threat to human health, making the development of computer-aided detection systems a priority. This study introduces a new deep learning feature fusion model called UncertaintyFuseNet, which accurately classifies CT scan and X-ray images. The results demonstrate the efficiency and robustness of the model.
INFORMATION FUSION
(2023)
Review
Chemistry, Analytical
Paraskevi Theodorou, Kleomenis Tsiligkos, Apostolos Meliones
Summary: Several assistive technology solutions for the Blind and Visually Impaired (BVI) have been proposed in literature, utilizing multi-sensor data fusion techniques. However, review studies quickly become outdated due to the rapid publication rate, and there is no comparative study between research literature and commercial applications trusted by BVI individuals. This study aims to classify and compare multi-sensor data fusion solutions from literature and commercial applications, and evaluate the usability and user experience through field testing.
Article
Chemistry, Multidisciplinary
Javad Hassannataj Joloudari, Abdolreza Marefat, Mohammad Ali Nematollahi, Solomon Sunday Oyelere, Sadiq Hussain
Summary: Imbalanced Data (ID) is a problem in machine learning where one class has significantly more samples than the other, leading to biased learning. This paper investigates the effectiveness of deep neural networks and convolutional neural networks mixed with oversampling and undersampling methods to handle imbalanced data. The proposed CNN-based model with SMOTE achieves 99.08% accuracy on 24 imbalanced datasets.
APPLIED SCIENCES-BASEL
(2023)
Article
Medicine, General & Internal
Mehmet Akif Cifci, Sadiq Hussain, Peren Jerfi Canatalay
Summary: With the widespread use of electronic health records, the automated extraction of critical information from electronic medical records, such as oncological medical events, has become increasingly important. However, extracting tumor-related medical events can be challenging due to their unique characteristics. To address this difficulty, we propose a novel approach that utilizes Generative Adversarial Networks (GANs) for data augmentation and pseudo-data generation algorithms to improve the model's transfer learning skills. Our approach shows promising results in extracting vital tumor-related information from electronic medical records.
Article
Computer Science, Information Systems
Abeer S. Desuky, Mehmet Akif Cifci, Samina Kausar, Sadiq Hussain, Lamiaa M. El Bakrawy
Summary: This paper introduces a new optimization algorithm called Mud Ring Algorithm (MRA), which mimics the mud ring feeding behavior of bottlenose dolphins in the Atlantic coast of Florida. By mathematically simulating this feeding strategy, MRA demonstrates its superiority in solving optimization problems.
Article
Mathematics, Applied
Lamiaa M. El Bakrawy, Mehmet Akif Cifci, Samina Kausar, Sadiq Hussain, Md Akhtarul Islam, Bilal Alatas, Abeer S. Desuky
Summary: This study proposes a modified antlion optimization (MALO) algorithm to improve the primary antlion optimization algorithm (ALO) for the task of instance reduction. The results show that the MALO algorithm outperforms the basic ALO algorithm and other comparative algorithms in terms of convergence rate and performance measures like Accuracy, Balanced Accuracy (BACC), Geometric mean (G-mean), and Area Under the Curve (AUC). The MALO algorithm offers a potential solution to the problem of local optima stagnation and slow convergence speed.
Article
Mathematical & Computational Biology
Danial Sharifrazi, Roohallah Alizadehsani, Javad Hassannataj Joloudari, Shahab S. Band, Sadiq Hussain, Zahra Alizadeh Sani, Fereshteh Hasanzadeh, Afshin Shoeibi, Abdollah Dehzangi, Mehdi Sookhak, Hamid Alinejad-Rokny
Summary: Myocarditis is an inflammation of the heart wall caused by viral infection, and it can lead to damage of the heart muscle and its electrical system. This paper presents a new deep learning-based model that accurately diagnoses myocarditis.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2022)
Article
Public, Environmental & Occupational Health
Iqramul Haq, Mahabub Alam, Aminul Islam, Mofasser Rahman, Abdul Latif, Md Injamul Haq Methun, Ashis Talukder
Summary: This study assessed the impact of sociodemographic factors on child mortality in urban and rural areas of Bangladesh. The findings showed that poverty, women's age, age at first marriage, birth interval, and number of children ever born had significant effects on child mortality. Additionally, women's education and wealth status were also associated with child mortality.
JOURNAL OF PUBLIC HEALTH-HEIDELBERG
(2022)
