Search

Intracranial haemorrhage (ICH) detection is a critical task in radiology and neurology, as timely recognition of haemorrhages in the brain can assist in rapid intervention and treatment. Several imaging modalities, including computed tomography (CT) and magnetic resonance imaging (MRI), are widely utilized to detect and classify ICH. Traditional methods for intracranial haemorrhage detection relied on manual inspection of CT images by radiologists. However, with advancements in machine learning (ML) and deep learning (DL) techniques, automated and computer-aided systems have been developed to assist radiologists in detecting and diagnosing ICH efficiently. DL models, particularly convolutional neural network (CNN), has shown promising results in ICH detection on CT images. With this motivation, this study focuses on the development of a Political Optimizer with Deep Learning based Intracranial Haemorrhage Diagnosis on Healthcare Management (PODL-ICHDHM) technique. The presented PODL-ICHDHM technique majorly concentrates on the recognition and classification of ICH on CT images. In this study, bilateral filtering (BF) is initially applied to pre-process the CT images. For feature extraction purposes, the Faster SqueezeNet approach is utilized in this study. At last, the PO algorithm with denoising autoencoder (DAE) model is utilized for the classification of ICH accurately. The experimental result analysis of the PODL-ICHDHM approach was validated on a benchmark dataset. The outcomes emphasized the improved performance of the PODL-ICHDHM algorithm over other recent approaches with a maximum detection accuracy of 98.43%.

Aspect-based sentiment analysis (ABSA) is a fine-grained type of sentiment analysis; it works on an aspect level. It mainly focuses on extracting aspect terms from text or reviews, categorizing the aspect terms, and classifying the sentiment polarities toward each aspect term and aspect category. Aspect term extraction (ATE) and aspect category detection (ACD) are interdependent and closely associated tasks. However, the majority of the current literature on Arabic aspect-based sentiment analysis (ABSA) deals with these tasks individually, assumes that aspect terms are already identified, or employs a pipeline model. Pipeline solutions employ single models for each task, where the output of the ATE model is utilized as the input for the ACD model. This sequential process can lead to the propagation of errors across different stages, as the performance of the ACD model is influenced by any errors produced by the ATE model. Therefore, the primary objective of this study was to investigate a multi-task learning approach based on transfer learning and transformers. We propose a multi-task learning model (MTL) that utilizes the pre-trained language model (AraBERT), namely, the MTL-AraBERT model, for extracting Arabic aspect terms and aspect categories simultaneously. Specifically, we focused on training a single model that simultaneously and jointly addressed both subtasks. Moreover, this paper also proposes a model integrating AraBERT, single pair classification, and BiLSTM/BiGRU that can be applied to aspect term polarity classification (APC) and aspect category polarity classification (ACPC). All proposed models were evaluated using the SemEval-2016 annotated dataset for the Arabic hotel dataset. The experiment results of the MTL model demonstrate that the proposed models achieved comparable or better performance than state-of-the-art works (F1-scores of 80.32% for the ATE and 68.21% for the ACD). The proposed SPC-BERT model demonstrated high accuracy, reaching 89.02% and 89.36 for APC and ACPC, respectively. These improvements hold significant potential for future research in Arabic ABSA.

Modern vehicles equipped with various smart sensors have become a means of transportation and have become a means of collecting, creating, computing, processing, and transferring data while traveling through modern and rural cities. A traditional vehicular ad hoc network (VANET) cannot handle the enormous and complex data that are collected by modern vehicle sensors (e.g., cameras, lidar, and global positioning systems (GPS)) because they require rapid processing, analysis, management, storage, and uploading to trusted national authorities. Furthermore, the integrated VANET with cloud computing presents a new concept, vehicular cloud computing (VCC), which overcomes the limitations of VANET, brings new services and applications to vehicular networks, and generates a massive amount of data compared to the data collected by individual vehicles alone. Therefore, this study explored the importance of big data in VCC. First, we provide an overview of traditional vehicular networks and their limitations. Then we investigate the relationship between VCC and big data, fundamentally focusing on how VCC can generate, transmit, store, upload, and process big data to share it among vehicles on the road. Subsequently, a new taxonomy of big data in VCC was presented. Finally, the security challenges in big data-based VCCs are discussed.

Vehicular ad hoc networks (VANETs) have received a great amount of interest, especially in wireless communications technology. In VANETs, vehicles are equipped with various intelligent sensors that can collect real-time data from inside and from surrounding vehicles. These real-time data require powerful computation, processing, and storage. However, VANETs cannot manage these real-time data because of the limited storage capacity in on board unit (OBU). To address this limitation, a new concept is proposed in which a VANET is integrated with cloud computing to form vehicular cloud computing (VCC) technology. VCC can manage real-time services, such as real-time video surveillance data that are used for monitoring critical events on the road. These real-time video surveillance data include highly sensitive data that should be protected against intruders in the networks because any manipulation, alteration, or sniffing of data will affect a driver’s life by causing improper decision-making. The security and privacy of real-time video surveillance data are major challenges in VCC. Therefore, this study reviewed the importance of the security and privacy of real-time video data in VCC. First, we provide an overview of VANETs and their limitations. Second, we provide a state-of-the-art taxonomy for real-time video data in VCC. Then, the importance of real-time video surveillance data in both fifth generation (5G), and sixth generation (6G) networks is presented. Finally, the challenges and open issues of real-time video data in VCC are discussed.

BACKGROUND AND OBJECTIVE: Eosinophilic lung diseases are a diverse group of disorders characterized by pulmonary opacities associated with tissue or peripheral eosinophilia. DESIGN AND SETTING: A retrospective study conducted at two tertiary care hospitals from January 1999 to December 2009. METHODS: All cases with the diagnosis of pulmonary eosinophilia were reviewed over a period of 10 years. Data on demographic, clinical, and radiologic characteristics were collected. RESULTS: Thirty-five patients with a mean age of 33.9 (16.2) years, of which 20 (57.1%) were male and meeting the criteria of eosinophilic lung disease were identified. Cough and dyspnea were the most frequent symptoms at presentation in 29 (82.9%) and 27 (77.1%) patients, respectively. Reticulonodular and airspace patterns were the most common radiographic findings in 17 (48.6%) and 15 (42.9%) patients, respectively. Peripheral eosinophilia was present in 33 (94.3%) patients. Twenty-four patients (68.6%) were labeled as having idiopathic pulmonary infiltrate with eosinophilia. Complete remission was achieved in 13 (54.2%) of 24 patients, while 10 (41.7%) patients relapsed within a few months of discontinuation of therapy. Specific therapy for a specific disease was administered in 8 patients: 2 patients for pulmonary tuberculosis, 2 for Churg–Strauss syndrome, 1 for lymphoma, 1 for schistosomiasis, 1 for acute eosinophilic pneumonia, and 1 for Wegener granuloma; 3 patients were treated as allergic bronchopulmonary aspergillosis. CONCLUSIONS: Pulmonary eosinophilia remains rare but challenging, and it can have the same diverse clinical and radiographic presentations seen with other common pulmonary conditions. Clinicians should be alert to these syndromes and must think of them in any lung disease differential diagnoses.