Optimal features assisted multi-attention fusion for robust fire recognition in adverse conditions by Inam Ullah, Nada Alzaben, Yousef Ibrahim Daradkeh, Mi Young Lee

“…Abstract Deep neural networks have significantly enhanced visual data-based fire detection systems. However, high false alarm rates, shallow-layered networks, and poor recognition in challenging environments continue to hinder their practical deployment. …”
Get full text

Indigenous early warning indicators for improving natural hazard predictions by Masego M. Motsumi, Livhuwani D. Nemakonde

“…A phenomenological approach, which is a form of qualitative research design, was employed, with data collected through focus group discussions and virtual interviews with key informants, involving 109 participants. …”
Get full text

Fostering Place Attachment Through Activity: Insights from Qaisaria Buildings in the Kurdistan Region of Iraq –Koya and Kifri as Case Studies by Mohammad Ahmed Shehab, Asst. Prof. Dr. Raz Saeed Faraj

“…These findings emphasize the importance of integrating dynamic activities in heritage preservation policies to strengthen historic marketplaces' social and functional continuity.…”
Get full text

A survey of multimodal composite editing and retrieval by Suyan Li, Fuxiang Huang, Lei Zhang

“…Multimodal composite retrieval integrates diverse modalities such as text, image and audio to provide more accurate, personalized, and contextually relevant results. …”
Get full text

Models of user experience quality in computer information systems by П. Р. Пелех, В. М. Юзевич

“…Unlike traditional Quality of Service (QoS) or subjective Quality of Experience (QoE) models alone, EPQuE integrates technical and perceptual factors through an adaptive algorithmic pipeline. …”
Get full text

Applying machine learning to decode built environment thresholds for public and active transport distances in the global south by Ali Shkera, Domokos Esztergár-Kiss

“…By integrating advanced ML methods with transportation policy analysis, this research bridges critical methodological and contextual gaps thus offering actionable insights for urban planners in high-density, transit-dependent cities worldwide.…”
Get full text

The self-perceived role of tech champions in municipal healthcare services—a descriptive qualitative study by Sissel Pettersen, Hilde Eide, Anita Berg

“…Braun and Clarke’s [2022] description of reflexive thematic analysis guided the data analysis. Results We found that tech champions hold an undefined role, holding neither predefined job descriptions nor assigned clear-cut dedicated tasks. …”
Get full text

Artificial intelligence in urban science: why does it matter? by Xinyue Ye, Tan Yigitcanlar, Michael Goodchild, Xiao Huang, Wenwen Li, Shih-Lung Shaw, Yanjie Fu, Wenjing Gong, Galen Newman

“…Urban science aims to explain, discover, understand, and generalize (EDUG) complex, human-centric systems, emphasizing societal context and sustainability. However, integrating artificial intelligence (AI) into urban science presents challenges, including data availability, ethical considerations, and the ‘black-box’ nature of many AI models. …”
Get full text

AuxTransUNet: Enhancing Remote Sensing Image Segmentation of Open-Pit Mining Areas in Qinghai–Tibet Plateau by Fangzhou Hong, Guojin He, Guizhou Wang, Zhaoming Zhang, Yan Peng

“…To address these challenges, we propose AuxTransUNet, a hybrid deep learning framework that integrates CNNs with transformers to enhance both local detail extraction and global contextual understanding. …”
Get full text

SCRED-Distillation: Improving Low-Dose CT Image Quality via Feature Fusion and Mutual Learning by Yanqing Wang, Xinru Zhan, Wanquan Liu, Yingying Li, Kexin Guo, Huafeng Wang

“…This approach synergistically integrates the global contextual awareness of Transformer architectures with the efficiency and regularization benefits of Knowledge Distillation. …”
Get full text

A hybrid deep learning model for sentiment analysis of COVID-19 tweets with class balancing by Md. Alamin Talukder, Md. Ashraf Uddin, Suman Roy, Partho Ghose, Smita Sarker, Ansam Khraisat, Mohsin Kazi, Md Momtazur Rahman, Musawer Hakimi

“…This study proposes a hybrid deep learning (DL) model that integrates Bidirectional Encoder Representations from Transformers (BERT) for contextual feature extraction with Long Short-Term Memory (LSTM) networks for sequential learning to classify COVID-19-related sentiments. …”
Get full text

Board effectiveness and carbon emission disclosure: evidence from ASEAN countries by Marwan Mansour, Almothanna Jamil Abu-Allan, Sajead Mowafaq Alshdaifat, Dheif Allah E’leimat, Mohammed W. A. Saleh

“…Notably, board independence has a negative impact on disclosure, highlighting contextual governance challenges in the ASEAN region. …”
Get full text

Insights into the relationship between emotional intelligence and critical thinking among nursing students by Ahmad Ayed, Ibrahim Aqtam, Malakeh Z. Malak, Dalia Toqan, Bahaaeddin M. Hammad, Jamal Qaddumi, Mustafa Shouli

“…Validated scales, the Schutte Self-Reported Emotional Intelligence Test (SSEIT) and Critical Thinking Disposition Scale (CTDS), were utilized. Data were analyzed using Pearson’s correlation and multiple linear regression analysis (F = 89.47, p < 0.001). …”
Get full text

HiEE: Hierarchical feature fusion for Chinese event extraction by Shuxiang Hou, Yurong Qian, Jiaying Chen, Jigui Zhao, Huiyong Lv, Hongyong Leng

“…To overcome these difficulties, we have organized and annotated a fine-grained event dataset related to governance texts from real-world Chinese event data, covering flat, overlapped, and nested events. …”
Get full text

Illocutionary indicators of sarcasm in the genre of sports analytical articles by Ksenia A. Pavlova

“…The main research methods include theoretical analysis and synthesis, corpus analysis together with discourse, contextual and interpretive analyses. The integrated application of the methods enumerated has given an opportunity to obtain reliable data on the most frequent illocutionary indicators of sarcasm and their linguistic representation. …”
Get full text

Novel dual gland GAN architecture improves human protein localization classification using salivary and pituitary gland inspired loss functions by Hanaa Salem Marie, Moatasem M. Draz, Waleed Abd Elkhalik, Mostafa Elbaz

“…The SG-Loss specifically targets discontinuities in protein expression patterns, while PG-Loss maintains biological plausibility by enforcing organelle-specific constraints learned from annotated training data. Our proposed Dual-Gland GAN demonstrates superior performance with an Inception Score of 9.83 (± 0.31) and MS-SSIM Diversity of 0.187 (± 0.021). …”
Get full text

Cloud Removal in the Tibetan Plateau Region Based on Self-Attention and Local-Attention Models by Guoqiang Zheng, Tianle Zhao, Yaohui Liu

“…This paper proposes a novel Multi-Scale Attention-based Cloud Removal Model (MATT). The model integrates global and local information by incorporating multi-scale attention mechanisms and local interaction modules, enhancing the contextual semantic relationships and improving the robustness of feature representation. …”
Get full text

A novel attention-based deep learning model for improving sentiment classification after the case of the 2023 Kahramanmaras/Turkey earthquake on Twitter by Serpil Aslan, Muhammed Yildirim

“…As users freely express their thoughts and emotions, a vast amount of data is generated, particularly in the aftermath of disasters, which can be collected quickly and directly from individuals. …”
Get full text

Enhancing English Language Teaching and User Experience in Virtual Environments: A Systematic Review on Gamification and Personalised Learning by Myriam Tatiana Velarde Orozco, Bárbara Luisa De Benito Crosetti

“…Two extraction matrices captured bibliographic, contextual and analytical data; methodological quality was appraised with MMAT-2018. …”
Get full text

A novel reconstruction-based video anomaly detection with idempotent generative network by Wenmin Dong, Lifeng Zhang, Wenjuan Shi, Xiangwei Zheng, Yuang Zhang

“…Reconstruction-based VAD has received increasing research attention, but faces challenges such as missing anomalies for the reconstruction error as a criterion, and information loss when suppressing anomalous data, existing methods also struggle to detect unseen anomalies. …”
Get full text