Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8651
Browse
24 results
Search Results
Conference Object Arabic Sign Language Paradigm Enhancement(American Institute of Physics, 2026) Aljuboori, Mohammed Khaleel Naser; Tasel, Faris SerdarConference Object Transformative Technologies in Neurosurgery: A Systematic Literature Review(Institute of Electrical and Electronics Engineers Inc., 2026) Serpil, Mete; Atas, Sezer; Ozcan, Muhammed Yusuf; Çetinkaya, Alperen BerkeConference Object Optimizing Lis-Assisted Wireless Communication Systems Using Deep Learning(Institute of Electrical and Electronics Engineers Inc., 2025) Sever, Hayri; Al-Janabi, Mustafa Muayad HasanConference Object Multi-Attribute Clothing Classification Using Modular Deep Learning Models: A ResNet-Centric Architecture(Institute of Electrical and Electronics Engineers Inc., 2025) Kuzukiran, Boran; Horkar, Emrah; Tunç, Sevgi Koyuncu; Akşit, EsraConference Object Fundus Image-Based Diabetic Retinopathy Detection Using EfficientNetB3 with Web Integration(Institute of Electrical and Electronics Engineers Inc., 2025) Girgec, Ceyda; Tunç, Sevgi Koyuncu; Kiliç, Ömer Faruk; Ünsal, CemConference Object Enhancing File Security with an Optimized Auto-Classification Framework Based on Learning Models(Institute of Electrical and Electronics Engineers Inc., 2025) Açikgöz, Zeliha; Arslan, Recep Sinan; Arslan, SerdarConference 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: 2Damage Detection in Aircraft Engine Borescope Inspection Using Deep Learning(Springer Science and Business Media Deutschland GmbH, 2025) Uzun, I.; Tolun, M.R.; Sari, F.; Alpaslan, F.N.Aircraft engine inspection is a key pillar of aviation safety as it helps to maintain adequate performance standards to ensure engine airworthiness. In addition, it is also vital for asset value retention. Borescope inspection is currently the most widely used visual inspection method for aircraft engines. However, borescope inspection is a time-consuming, subjective, and complex process that heavily depends on the experience and attention level of the inspector. Moreover, the cost savings of airlines and the maintenance, repair, and overhaul (MRO) centers expose pressure and workload on inspectors. These factors make an automated system to support damage detection during borescope inspection necessary in order to mitigate potential risks. In this paper, we propose a deep learning-based automated damage detection framework that employs aircraft engine borescope inspection images. Faster R-CNN-based deep learning model with Inception v2 feature extractor is utilized for the present architecture. Due to the limited number of images, data augmentation and other overfitting methods are also employed. The framework supports crack, burn, nick, and dent damage types across all modules of turbofan engines. It is trained and validated with moderate to complex borescope images obtained from the field. The framework achieves 92.64% accuracy for crack, 92.05% for nick or dent, and 81.14% for burn damage classes, with an overall 88.61% average accuracy. © The Author(s) 2025.Article Citation - WoS: 1Citation - Scopus: 1Ordered Clustering-Based Semantic Music Recommender System Using Deep Learning Selection(Tech Science Press, 2025) Ha, Weitao; Gang, Sheng; Navaei, Yahya D.; Gezawa, Abubakar S.; Nanehkaran, Yaser A.Music recommendation systems are essential due to the vast amount of music available on streaming platforms, which can overwhelm users trying to find new tracks that match their preferences. These systems analyze users' emotional responses, listening habits, and personal preferences to provide personalized suggestions. A significant challenge they face is the "cold start" problem, where new users have no past interactions to guide recommendations. To improve user experience, these systems aim to effectively recommend music even to such users by considering their listening behavior and music popularity. This paper introduces a novel music recommendation system that combines order clustering and a convolutional neural network, utilizing user comments and rankings as input. Initially, the system organizes users into clusters based on semantic similarity, followed by the utilization of their rating similarities as input for the convolutional neural network. This network then predicts ratings for unreviewed music by users. Additionally, the system analyses user music listening behaviour and music popularity. Music popularity can help to address cold start users as well. Finally, the proposed method recommends unreviewed music based on predicted high rankings and popularity, taking into account each user's music listening habits. The proposed method combines predicted high rankings and popularity by first selecting popular unreviewed music that the model predicts to have the highest ratings for each user. Among these, the most popular tracks are prioritized, defined by metrics such as frequency of listening across users. The number of recommended tracks is aligned with each user's typical listening rate. The experimental findings demonstrate that the new method outperformed other classification techniques and prior recommendation systems, yielding a mean absolute error (MAE) rate and root mean square error (RMSE) rate of approximately 0.0017, a hit rate of 82.45%, an average normalized discounted cumulative gain (nDCG) of 82.3%, and a prediction accuracy of new ratings at 99.388%.Article Citation - WoS: 11Citation - Scopus: 17Convolutional Neural Network-Based Deep Learning for Landslide Susceptibility Mapping in the Bakhtegan Watershed(Nature Portfolio, 2025) Feng, Li; Zhang, Maosheng; Mao, Yimin; Liu, Hao; Yang, Chuanbo; Dong, Ying; Nanehkaran, Yaser A.Landslides pose a significant threat to infrastructure, ecosystems, and human safety, necessitating accurate and efficient susceptibility assessment methods. Traditional models often struggle to capture the complex spatial dependencies and interactions between geological and environmental factors. To address this gap, this study employs a deep learning approach, utilizing a convolutional neural network (CNN) for high-precision landslide susceptibility mapping in the Bakhtegan watershed, southwestern Iran. A comprehensive landslide inventory was compiled using 235 documented landslide locations, validated through remote sensing and field surveys. An equal number of non-landslide locations were systematically selected to ensure balanced model training. Fifteen key conditioning factors-including topographical, geological, hydrological, and climatological variables-were incorporated into the model. While traditional statistical methods often fail to extract spatial hierarchies, the CNN model effectively processes multi-dimensional geospatial data, learning intricate patterns influencing slope instability. The CNN model outperformed other classification approaches, achieving an accuracy of 95.76% and a precision of 95.11%. Additionally, error metrics confirmed its reliability, with a mean absolute error (MAE) of 0.11864, mean squared error (MSE) of 0.18796, and root mean squared error (RMSE) of 0.18632. The results indicate that the northern and northeastern regions of the Bakhtegan watershed are highly susceptible to landslides, highlighting areas where proactive mitigation strategies are crucial. This study demonstrates that deep learning, particularly CNNs, offers a powerful and scalable solution for landslide susceptibility assessment. The findings provide valuable insights for urban planners, engineers, and policymakers to implement effective risk reduction strategies and enhance resilience in landslide-prone regions.
- «
- 1 (current)
- 2
- 3
- »