Flight delays are a major concern for both travelers and airlines, with significant financial and reputational consequences. Accurately predicting flight delays is crucial for enhancing customer satisfaction and airline revenues. In this paper, we leverage the power of artificial intelligence and machine learning techniques to build a framework for accurately predicting flight delays. To achieve this, we collected flight information from September 2017 to April 2023, along with weather data, and performed extensive feature engineering to extract informative features to train our model. We conduct a comparative analysis of various popular machine learning architectures with distinctive characteristics, aiming to determine their efficacy in achieving optimal accuracy on our newly proposed dataset. Based on our evaluation of various architectures, our findings demonstrate that CatBoost outperformed the others by achieving the highest test accuracy and the lowest error rate in the challenging use case of Saudi Arabia. Moreover, to simulate real-world scenarios, our framework evaluates the best-performing model that has been selected for deployment in a web application, which provides users with the ability to accurately forecast flight delays and offers a user-friendly dashboard with valuable insights and analysis capabilities.

Matrix Factorization (MF) method is widely popular for personalized recommendations. However, the natural data sparsity problem limits its performance, where users generally only interact with a small fraction of available items. Accordingly, several hybrid models have been proposed recently to optimize MF performance by incorporating additional contextual information in the MF’s learning process. Although these models improved recommendation quality, there are two primary aspects for further enhancements: (1) multiple models focus only on some portion of the available contextual information and neglect other portions, and (2) learning the feature space of the contextual information needs to be further improved. Therefore, we introduce a Collaborative Dual Attentive Autoencoder (CATA++) method that utilizes an item’s content and learns its latent space via two parallel autoencoders. We employ the attention mechanism in the middle of our autoencoders to capture the most significant segments of contextual information, which leads to a better representation of the items in the latent space. Extensive experiments on three scientific-article datasets have shown that our dual-process learning strategy has significantly improved MF performance in comparison with other state-of-the-art MF-based models using various experimental evaluations. The source code of our method is available at: https://github.com/jianlin-cheng/CATA.

Efficient classification of Arabic news items has become more crucial for efficient information management and analysis due to the fast growth of online news material. This paper proposes a hybrid Attention-Based Transformer Model (ABTM) for Arabic news categorization that uses deep learning and classical text representations to improve classification accuracy and interpretability. Given the increasing amount of Arabic news materials, robust categorization systems are crucial for properly managing and analyzing this information. To deal with the complexities of the Arabic language and enrich the dataset, we used a thorough preparation pipeline that includes text cleaning, tokenization, lemmatization, and data augmentation approaches. We combined a bespoke attention embedder with classic TF-IDF and Bag-of-Words features to provide a comprehensive feature set that includes both the text’s contextual and statistical aspects. We benchmarked our technique using cutting-edge Arabic language models, such as AraBERTv1-base and asafaya/bert-base-arabic. We use (local interpretable model agnostic explanation) text explainer to offer insights into model predictions, improving our findings’ interpretability. Our results show that the ABTM strategy considerably enhances classification performance, with high accuracy and reasonable explanations for model decisions. This classification includes a wide range of news categories, including politics, sports, culture, the economy, and a variety of themes, representing the diversity of Arabic news. This study contributes to the field of Arabic natural language processing by offering a novel method that combines deep learning with traditional techniques, thereby advancing the state of Arabic news classification. Enhanced classification accuracy and interpretability facilitate better management and understanding of the rich and growing Arabic news content, supporting informed decision-making and knowledge discovery.

Image-based Arabian camel breed classification is an important task for various practical applications, such as breeding management, genetic improvement, conservation, and traceability. However, it is a challenging task due to the lack of standardized criteria and methods, the high similarity among breeds, and the limited availability of data and resources. In this paper, we propose an approach to tackle this challenge by using convolutional neural networks (CNNs) and transfer learning to classify images of six different Arabian camel breeds: Waddeh, Majaheem, Homor, Sofor, Shaele, and Shageh. To achieve this, we created, preprocessed, and annotated a novel dataset of 1073 camel images. We then pre-trained CNNs as feature extractors and fine-tuned them on our new dataset. We evaluated several popular CNN architectures with diverse characteristics such as InceptionV3, NASNetLarge, PNASNet-5-Large, MobileNetV3-Large, and EfficientNetV2 (small, medium, and large variants), and we found that NASNetLarge achieves the best test accuracy of 85.80% on our proposed dataset. Finally, we integrated the best-performing CNN architecture, NASNetLarge, into a mobile application for further validation and actual use in a real-world scenarios.

There are many applications controlled by the brain signals to bridge the gap in the digital divide between the disabled and the non-disabled people. The deployment of novel assistive technologies using brain-computer interface (BCI) will go a long way toward achieving this lofty goal, especially after the successes demonstrated by these technologies in the daily life of people with severe disabilities. This paper contributes in this direction by proposing an integrated framework to control the operating system functionalities using Electroencephalography signals. Different signal processing algorithms were applied to remove artifacts, extract features, and classify trials. The proposed approach includes different classification algorithms dedicated to detecting the P300 responses efficiently. The predicted commands passed through a socket to the API system, permitting the control of the operating system functionalities. The proposed system outperformed those obtained by the winners of the BCI competition and reached an accuracy average of 94.5% according to the offline approach. The framework was evaluated according to the online process and achieved an excellent accuracy attaining 97% for some users but not less than 90% for others. The suggested framework enhances the information accessibility for people with severe disabilities and helps them perform their daily tasks efficiently. It permits the interaction between the user and personal computers through the brain signals without any muscular efforts.

The data sparsity is a significant challenge for collaborative filtering methods in recommendation systems for making accurate recommendations. Several approaches have been published to address this issue. Most of them usually use only one source of data to train their model, and other approaches still have lower performance especially when the sparsity of data is very high. In this paper, we use a deep learning based model, DeepHCF, to tackle this problem. DeepHCF uses two sources of data, ratings matrix and item reviews, to train two deep models via joint training. The user-item ratings matrix data is trained using a Multi-Layer Perceptron (MLP), while other side information is trained using a Convolutional Neural Network (CNN). The users and items' latent features learned by each model are utilized by factorization machines for our model prediction. Extensive experimental results on four different realworld datasets show that DeepHCF achieves on average a 7.42% improvement over the second most accurate method, when the dataset has over 99.9% of sparsity.