VISION TRANSFORMER USING FRACTIONAL GRADIENT ATTENTION TOOLS FOR ROBUST IMAGE CLASSIFICATION
Vision Transformers (ViTs) have attained very promising results in the field of computer vision, but those models continue to face several critical issues such as gradient saturation and poor generalization on smaller datasets. The current attention mechanisms are inefficient to resolve issues by the leading to ineffective feature extraction and an...
By S. Shalini, P.S. Eliahim Jeevaraj
GRAPH-BASED METHODS FOR EXTRACTIVE ARABIC NEWS TEXT SUMMARIZATION
The speed of the increasing digital content requires the creation of successful Automatic Text Summarization (ATS) systems. Although major improvements have been made in the summarization of high-resource languages, the summarization of Arabic texts has not been effectively studied, especially in terms of comparative studies of preprocessing method...
By Rasha Almutairi, Sahar Jambi, Tawfiq Hasanin
OPTIMIZED GIS-BASED RISK MAPPING OF WATER WALLS IN KIRKUK CITY
In Kirkuk City, Iraq, groundwater pollution is increasingly a problem due to intense urbanization, population growth, and unregulated water well drilling. Although the systematic assessment of groundwater pollution is essential to domestic and agricultural applications, the systematic analysis of its contamination has not been conducted, and the cu...
By Amel Nashat Shakir, Omar Falah Mirdan, Arjan Sharfuldeen Omar
MLA: INTELLECTUAL DUAL KEY-BASED NODE AUTHENTICATION WITH MASTER LINKED AUDITOR NODE BEHAVIOUR-BASED MALICIOUS NODE DETECTION FOR SECURE DATA TRANSMISSION IN 6G ENABLED WSN
This study focuses on the ever-increasing challenge of ensuring the integrity of Sixth Generation (6G) enabled Wireless Sensor Networks (WSNs), which are highly vulnerable to malicious node attacks, thereby compromising network data integrity and efficiency. Conventional methods of cryptography do not necessarily resist advanced attacks like select...
By Pavan Vamsi Mohan Movva, Radhika Rani Chintala
NEURO ADAPTIVE METACOGNITIVE PROMPTING STRATEGIES FOR IMPROVING SELF REGULATED LEARNING AND CRITICAL THINKING IN PSYCHOLOGICAL SCIENCE EDUCATION
The growing recognition of Psychological Science education as a domain that demands higher-level thinking has revealed that students still exhibit chronic shortcomings in self-regulated learning (SRL) and critical thinking. Reports indicate that about 42% of undergraduate psychology students have low metacognitive monitoring accuracy, and more than...
By Nodira Fazilova, Khurshida Komilova, Olmos Avezov, Fatima Nazarova, Salima Akhmedova, Muzaffar Xaydarov, Rano Alimardanova
TRACING THE ROLE OF PRESS COVERAGE IN SHAPING SOCIETAL UNDERSTANDING OF 2D NANOMATERIALS AND PHOTOCATALYTIC APPLICATIONS
In this study, the authors examine how journalism affects the societal awareness regarding 2D nanomaterials and their use in photocatalysis, using the content of the press from 2000 to 2025. The analytical approach and historical approach of the study help them to comprehensively examine a variety of sources, such as newspapers, archival repositori...
By Ala'a A. Al-Majdi, Safaa M. Almudhafar
EFFECT OF SAND SHELL IMPROVEMENT USING POLYPROPYLENE FIBER AND CEMENT ON THE SEISMIC RESPONSE OF SMALL-SCALE ZONED EARTH DAM MODELS
The application of sand as shell materials in zoned earth dams is common due to its availability and economic factors. Nevertheless, it is necessary to analyze the performance of such materials under the simultaneous effect of seepage and earthquake loads, especially when the core of the structure is formed from low permeable materials. The present...
By Hussein Jassim Abdulsameea, Saleh Issa Khassaf
AN ADAPTIVE BUTTERFLY OPTIMIZATION-DRIVEN EXPLAINABLE CNN–TRANSFORMER FRAMEWORK FOR ACCURATE AND TRUSTWORTHY CLINICAL DIAGNOSIS
Clinically-oriented AI-based diagnostic systems have exhibited impressive predictive accuracies; however, their poor interpretability capabilities and incapability to optimize their learning parameters in eal-time pose a major challenge towards implementing such solutions in the actual healthcare settings. To overcome such limitations, in thi...
By A Vaideghy, V Sridevi, D Saraswathi, L. S Sindhuja
MODIFIED ATTENTION U-DENSENET FOR 13-CLASS LUMBAR SPINE MRI SEGMENTATION
Low back pain can be caused by lumbar disc disorders; however, correct segmentation of the structures of the vertebrae and the disc disorders using MRI is crucial for clinical evaluation. In this case, previous deep-learning segmentation approaches have mainly concentrated on the segmentation of anatomical structures and lacked pathology-aware disc...
By Rana Riyadh Saeed, Muhammad Amir As’ari, Ahmad Zahran Md Khudzari, Ahmed Sabeeh Yousif, Hadeel Mohamed Farook Alhialy, Mohamed Muyaser Naif
LATENT URBAN HERITAGE ASSESSMENT IN SAIGON HO CHI MINH CITY THROUGH HISTORICAL CARTOGRAPHY AND URBAN MORPHOLOGY
Ho Chi Minh City, historically known as Saigon, is being redeveloped at a pace that places pressure on heritage values located beyond protected monuments and colonial-era buildings. This study examines how earlier hydrological, settlement, commercial, defensive, administrative, and metropolitan structures remain visible or latent in the present urb...
By Minh Hieu Nguyen, Ngoc Quynh Giao Pham, Thi Minh Dieu Nguyen