A problem that pervades throughout students’ careers is their poor performance in high school. Predicting students’ academic performance helps educational institutions in many ways. Knowing and identifying the factors that can affect the academic performance of students at the beginning of the thread can help educational institutions achieve their educational goals by providing support to students earlier. The aim of this study was to predict the achievement of early secondary students. Two sets of data were used for high school students who graduated from the Al-Baha region in the Kingdom of Saudi Arabia. In this study, three models were constructed using different algorithms: Naïve Bayes (NB), Random Forest (RF), and J48. Moreover, the Synthetic Minority Oversampling Technique (SMOTE) technique was applied to balance the data and extract features using the correlation coefficient. The performance of the prediction models has also been validated using 10-fold cross-validation and direct partition in addition to various performance evaluation metrics: accuracy curve, true positive (TP) rate, false positive (FP) rate, accuracy, recall, F-Measurement, and receiver operating characteristic (ROC) curve. The NB model achieved a prediction accuracy of 99.34%, followed by the RF model with 98.7%.

/pdf/data-mining-approach-to-predict-success-of-secondary-school-4jtnmr6y.pdf

Data Mining Approach to Predict Success of Secondary School Students: A Saudi Arabian Case Study

Over the decades, a tremendous increase has been witnessed in the production of documents available in digital form. The increased production of documents has gained so much momentum that their rate of production jumps two-fold every five years. These articles are searched over the internet via search engines, digital libraries, and citation indexes. However, the retrieval of relevant research papers for user queries is still a pipedream. This is because scientific documents are not indexed based on some subject classification hierarchies. Hence, the classification of these documents becomes a challenging task for the researchers. Classification of the documents can be two-fold: one way is to assign a single label to each document and the other is to assign multi-labels to each document based on its belonging domains. Classification of the documents can be performed by using either the available metadata or the whole content of the documents. While performing classification, there are many challenges which may belong to the dataset, feature selection technique, preprocessing methodology, and which classification model is suitable for the classification of the documents. This paper highlights the issues for single-label and multi-label classification by using either metadata or content of the documents and why metadata-based approaches are better than content-based approaches in terms of feasibility.

/pdf/single-vs-multi-label-the-issues-challenges-and-insights-of-25cdpgyg.pdf

Single vs. Multi-Label: The Issues, Challenges and Insights of Contemporary Classification Schemes

With the continuous increase in Internet of Things (IoT) device usage, more interest has been shown in internet security, specifically focusing on protecting these vulnerable devices from malicious traffic. Such threats are difficult to distinguish, so an advanced intrusion detection system (IDS) is becoming necessary. Machine learning (ML) is one of the promising techniques as a smart IDS in different areas, including IoT. However, the input to ML models should be extracted from the IoT environment by feature extraction models, which play a significant role in the detection rate and accuracy. Therefore, this research aims to introduce a study on ML-based IDS in IoT, considering different feature extraction algorithms with several ML models. This study evaluated several feature extractors, including image filters and transfer learning models, such as VGG-16 and DenseNet. Additionally, several machine learning algorithms, including random forest, K-nearest neighbors, SVM, and different stacked models were assessed considering all the explored feature extraction algorithms. The study presented a detailed evaluation of all combined models using the IEEE Dataport dataset. Results showed that VGG-16 combined with stacking resulted in the highest accuracy of 98.3%.

/pdf/intrusion-detection-system-using-feature-extraction-with-1iu9jsbr.pdf

Intrusion Detection System Using Feature Extraction with Machine Learning Algorithms in IoT

With the rapid advances in Information Technology (IT), the focus on engaging computing students to gain practical experience in the IT industry before graduation is becoming increasingly complex without incorporating pedagogical strategies of success in curricula. The goal is to enable computing major students to gain in-depth knowledge and practical understanding of the IT working environment before graduating through essential industry-driven practical skills based on international standards and best practices. Unfortunately, tracking and analyzing students’ practical skills performance during their IT field training programs, which are conducted primarily off-campus at various public and private organizations, before, during, and after the training period, is a daunting task for both the college instructors and the industry trainers. To overcome these challenges, this paper introduces a Sustainable University Field Training (SUNFIT) framework, which is a pedagogical approach towards mining the educational data using machine learning to integrate and measure the field training programs against the internationally recognized accreditation standards such as Accreditation Board for Engineering and Technology (ABET). The study employs machine learning models aimed at continuously measuring and monitoring international ABET accreditation requirements on computing major courses’ academic data, elucidating student performance across various semesters, integrating best practices, and producing an evidence-based rationale approach for evaluating weak learning outcomes (LOs) with minimal manual intervention, as well as preventing faculty-specific portfolio errors. The proposed approach could be easily developed by academics, researchers, or even students, and for a variety of purposes, including enhancing poor student outcomes (SOs). In addition, various data mining and machine learning approaches have been investigated over field training assessment data for successful prediction in subsequent cycles. The results are promising, with Naïve Bayes obtaining the highest accuracy of 90.54% followed by J48 and PART algorithms at 87.83%.

/pdf/sunfit-a-machine-learning-based-sustainable-university-field-3ifu4wna.pdf

SUNFIT: A Machine Learning-Based Sustainable University Field Training Framework for Higher Education

Plant taxonomy is the scientific study of the classification and naming of various plant species. It is a branch of biology that aims to categorize and organize the diverse variety of plant life on earth. Traditionally, plant taxonomy has been performed using morphological and anatomical characteristics, such as leaf shape, flower structure, and seed and fruit characters. Artificial intelligence (AI), machine learning, and especially deep learning can also play an instrumental role in plant taxonomy by automating the process of categorizing plant species based on the available features. This study investigated transfer learning techniques to analyze images of plants and extract features that can be used to cluster the species hierarchically using the k-means clustering algorithm. Several pretrained deep learning models were employed and evaluated. In this regard, two separate datasets were used in the study comprising of seed images of wild plants collected from Egypt. Extensive experiments using the transfer learning method (DenseNet201) demonstrated that the proposed methods achieved superior accuracy compared to traditional methods with the highest accuracy of 93% and F1-score and area under the curve (AUC) of 95%, respectively. That is considerable in contrast to the state-of-the-art approaches in the literature.

/pdf/transfer-learning-approach-to-seed-taxonomy-a-wild-plant-24nzfov9.pdf

Transfer Learning Approach to Seed Taxonomy: A Wild Plant Case Study

The World Health Organization (WHO) declared the outbreak of Coronavirus disease 2019 (COVID-19) a pandemic on 11 March 2020. The evolution of this pandemic has raised global health concerns, making people worry about how to protect themselves and their families. This has greatly impacted people’s sentiments. There was a dire need to investigate a large amount of social data such as tweets and others that emerged during the post-pandemic era for the assessment of people’s sentiments. As a result, this study aims at Arabic tweet-based sentiment analysis considering the COVID-19 pandemic in Saudi Arabia. The datasets have been collected in two different periods in three major regions in Saudi Arabia, which are: Riyadh, Dammam, and Jeddah. Tweets were annotated with three sentiments: positive, negative, and neutral after due pre-processing. Convolutional neural networks (CNN) and bi-directional long short memory (BiLSTM) deep learning algorithms were applied for classifying the sentiment of Arabic tweets. This experiment showed that the performance of CNN achieved 92.80% accuracy. The performance of BiLSTM was scored at 91.99% in terms of accuracy. Moreover, as an outcome of this study, an overwhelming upsurge in negative sentiments were observed in the dataset during COVID-19 compared to the negative sentiments of the dataset before COVID-19. The technique has been compared with the state-of-the-art techniques in the literature and it was observed that the proposed technique is promising in terms of various performance parameters.

/pdf/arabic-tweets-based-sentiment-analysis-to-investigate-the-2ym6x7sk.pdf

Arabic Tweets-Based Sentiment Analysis to Investigate the Impact of COVID-19 in KSA: A Deep Learning Approach

To constructively ameliorate and enhance traffic safety measures in Saudi Arabia, a prolific number of AI (Artificial Intelligence) traffic surveillance technologies have emerged, including Saher, throughout the past years. However, rapidly detecting a vehicle incident can play a cardinal role in ameliorating the response speed of incident management, which in turn minimizes road injuries that have been induced by the accident’s occurrence. To attain a permeating effect in increasing the entailed demand for road traffic security and safety, this paper presents a real-time traffic incident detection and alert system that is based on a computer vision approach. The proposed framework consists of three models, each of which is integrated within a prototype interface to fully visualize the system’s overall architecture. To begin, the vehicle detection and tracking model utilized the YOLOv5 object detector with the DeepSORT tracker to detect and track the vehicles’ movements by allocating a unique identification number (ID) to each vehicle. This model attained a mean average precision (mAP) of 99.2%. Second, a traffic accident and severity classification model attained a mAP of 83.3% while utilizing the YOLOv5 algorithm to accurately detect and classify an accident’s severity level, sending an immediate alert message to the nearest hospital if a severe accident has taken place. Finally, the ResNet152 algorithm was utilized to detect the ignition of a fire following the accident’s occurrence; this model achieved an accuracy rate of 98.9%, with an automated alert being sent to the fire station if this perilous event occurred. This study employed an innovative parallel computing technique for reducing the overall complexity and inference time of the AI-based system to run the proposed system in a concurrent and parallel manner.

https://www.mdpi.com/2504-2289/7/1/22/pdf?version=1674982920

Atta Rahman

Papers

Arabic Tweets-Based Sentiment Analysis to Investigate the Impact of COVID-19 in KSA: A Deep Learning Approach

A Real-Time Computer Vision Based Approach to Detection and Classification of Traffic Incidents

Data Mining Approach to Predict Success of Secondary School Students: A Saudi Arabian Case Study

Single vs. Multi-Label: The Issues, Challenges and Insights of Contemporary Classification Schemes

SUNFIT: A Machine Learning-Based Sustainable University Field Training Framework for Higher Education