Scopus İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8651

Browse

Filters

2020 - 20263

Settings

Subject: search.filters.subject.Deep LearningWoS Q: search.filters.wosQuartile.N/A

Search Results

Now showing 1 - 3 of 3
  • Conference Object
    Sentiment Analysis for Arabic Using Deep Learning
    (Springer Science and Business Media Deutschland GmbH, 2026) al-Hamadani, S.A.S.; Sever, H.
    With the explosive growth of digital communication, understanding sentiment in online content has become increasingly critical for a wide range of applications, from customer feedback analysis to social media monitoring. However, sentiment analysis for Arabic presents unique challenges due to the language's rich morphology, diverse dialects, and complex syntactic structures. These challenges are further amplified in multimodal settings, where the fusion of textual, visual, and auditory cues is required to capture the full spectrum of human emotion. To address these issues, this paper introduces a new framework for Arabic Multimodal Sentiment Analysis (AMSA), combining multi-level deep learning approaches across text, audio, and visual modalities. Our approach utilizes state-of-the-art transformer-based architecturees, including Multimodal Transformer (MulT) and Early Fusion models, to tackle both linguistic complexity and multimodal alignment. Specifically, we leverage DeBERTa for extracting rich textual features, ViT (Vision Transformer) for visual cues, and Whisper for capturing nuanced audio signals, creating robust and contextualized representations. Experimental results on a curated Arabic multimodal dataset demonstrate the effectiveness of this approach, with our proposed MulT model achieving an F1 score of 72.73%, reflecting a substantial improvement of 13.98% in F1 score and 14.6% in accuracy over existing baselines. These findings highlight the power of cross-modal attention mechanisms and early fusion strategies in accurately capturing subtle sentiments across multiple modalities. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
  • Article
    Citation - Scopus: 7
    COVID-19 Classification Using Hybrid Deep Learning and Standard Feature Extraction Techniques
    (Institute of Advanced Engineering and Science, 2023) El Shenbary, H. A.; Ebeid, Ebeid Ali; Baleanu, Dumitru I.
    There is no doubt that COVID-19 disease rapidly spread all over the world, and effected the daily lives of all of the people. Nowadays, the reverse transcription polymerase chain reaction is the most way used to detect COVID-19 infection. Due to time consumed in this method and material limitation in the hospitals, there is a need for developing a robust decision support system depending on artificial intelligence (AI) techniques to recognize the infection at an early stage from a medical images. The main contribution in this research is to develop a robust hybrid feature extraction method for recognizing the COVID-19 infection. Firstly, we train the Alexnet on the images database and extract the first feature matrix. Then we used discrete wavelet transform (DWT) and principal component analysis (PCA) to extract the second feature matrix from the same images. After that, the desired feature matrices were merged. Finally, support vector machine (SVM) was used to classify the images. Training, validating, and testing of the proposed method were performed. Experimental results gave (97.6%, 98.5%) average accuracy rate on both chest X-ray and computed tomography (CT) images databases. The proposed hybrid method outperform a lot of standard methods and deep learning neural networks like Alexnet, Googlenet and other related methods. © 2022 Elsevier B.V., All rights reserved.
  • Conference Object
    Citation - WoS: 10
    Citation - Scopus: 21
    Multi-Label Classification of Text Documents Using Deep Learning
    (Ieee, 2020) Mohammed, Hamza Haruna; Dogdu, Erdogan; Gorur, Abdul Kadir; Choupani, Roya
    Recently, studies in the field of Natural Language Processing and its related applications continue to mount up. Machine learning is proven to be predominantly data-driven in the sense that generic model building methods are used and then tailored to specific application domains. Needless to say, this has proven to be a very effective approach in modeling the complicated data dependencies we frequently experience in practice, making very few assumptions, and allowing the information to talk for themselves. Examples of these applications can be found in chemical process engineering, climate science, healthcare, and linguistic processing systems for natural languages, to name a few. Text classification is one of the important machine learning tasks that is used in many digital applications today; such as in document filtering, search engines, document management systems, and many more. Text classification is the process of categorizing of text documents into a given set of labels. Furthermore, multi-label text classification is the task of categorization of text documents into one or more labels simultaneously. Over the years, many methods for classifying text documents have been proposed, including the popularly known bag of words (BoW) method, support vector machine (SVM), tree induction, and label-vector embedding, to mention a few. These kinds of tools can be used in many digital applications, such as document filtering, search engines, document management systems, etc. Lately, deep learning-based approaches are getting more attention, especially in extreme multi-label text classification case. Deep learning has proven to be one of the major solutions to many machine learning applications, especially those involving high-dimensional and unstructured data. However, it is of paramount importance in many applications to be able to reason accurately about the uncertainties associated with the predictions of the models. In this paper, we explore and compare the recent deep learning-based methods for multi-label text classification. We investigate two scenarios. First, multi-label classification model with ordinary embedding layer, and second with Glove, word2vec, and FastText as pre-trained embedding corpus for the given models. We evaluated these different neural network model performances in terms of multi-label evaluation metrics for the two approaches, and compare the results with the previous studies.