Toward Inclusive Smart Cities: Sound-Based Vehicle Diagnostics, Emergency Signal Recognition, and Beyond by Amr Rashed, Yousry Abdulazeem, Tamer Ahmed Farrag, Amna Bamaqa, Malik Almaliki, Mahmoud Badawy, Mostafa A. Elhosseini

“…A comprehensive framework is proposed, combining audio preprocessing, feature extraction (via Mel Spectrograms, MFCCs, and Chromatograms), and classification using 11 models. …”
Get full text

Human action recognition based on low- and high-level data from wearable inertial sensors by Irvin Hussein Lopez-Nava, Angélica Muñoz-Meléndez

“…The proposed features in this work are the number of movements and the average duration of consecutive movements. …”
Get full text

Digital mapping of soil organic carbon in the hilly and mountainous landscape of Indian Himalayan region employing machine-learning techniques by Justin George Kalambukattu, Suresh Kumar, Bappa Das, Trisha Roy

“…A feature ranking and variable selection protocol was used for the selection of optimal set of covariates prior to model development. …”
Get full text

Disaster Resilience Evaluation of Mountainous Rural Communities: A Case Study of Representative Villages in the Anning River Basin, Liangshan Prefecture by Wu Yuanfei, Liu Mengying, Tian Bingwei, Tian Renjie, Hu Yifan

“…The key findings revealed the following: (1) The comprehensive resilience scores ranked Taoyuan > Niulang > Qunying > Caogu. Taoyuan's top performance stemmed from its designation as a national disaster prevention demonstration community featuring robust infrastructure and frequent emergency drills, whereas Caogu's lowest resilience resulted from its high-altitude topography, aging population, and inadequate infrastructure. (2) State resilience contributed most significantly to overall resilience (51.43%), with the building quality (C9) being the pivotal driver. …”
Get full text

Normalization Strategies in Multi-Center Radiomics Abdominal MRI: Systematic Review and Meta-Analyses by Jovana Panic, Arianna Defeudis, Gabriella Balestra, Valentina Giannini, Samanta Rosati

“…The main challenge is represented by the great and unavoidable image variability which is usually addressed using different pre-processing techniques including spatial, intensity and feature normalization. The purpose of this study is to systematically summarize normalization methods and to evaluate their correlation with the radiomics model performances through meta-analyses. …”
Get full text

Analysis of peel and shear strains in cracked lap shear specimens subjected to fatigue loading using digital image correlation by Alessandra Panerai, Gianmarco Piccoli, Luca Michele Martulli, Andrea Bernasconi, Michele Carboni

“…In this work, Cracked Lap Shear specimens, which feature mixed I+II mode loading conditions, were tested under fatigue loading. …”
Get full text

A Survey on Machine Learning Approaches for Personalized Coaching with Human Digital Twins by Harald H. Rietdijk, Patricia Conde-Cespedes, Talko B. Dijkhuis, Hilbrand K. E. Oldenhuis, Maria Trocan

“…As a conclusion, we provide direction for further research, formulated in the following research question: how can the optimization of human data feature engineering and personalized model selection be achieved in Human Digital Twins and can techniques such as meta-learning be of use in this context?…”
Get full text

GH-UNet: group-wise hybrid convolution-VIT for robust medical image segmentation by Shengxiang Wang, Ge Li, Min Gao, Linlin Zhuo, Mingzhe Liu, Zhizhong Ma, Wei Zhao, Xiangzheng Fu

“…GH-UNet integrates a hybrid convolution-Transformer encoder for both local detail and global context modeling, a Group-wise Dynamic Gating (GDG) module for adaptive feature weighting, and a cascaded decoder for multi-scale integration. …”
Get full text

LMGDoc: Light Multigranular GNN for Efficient Document Understanding by Abdellatif Sassioui, Yasser Elouargui, Mohamed El Kamili, Rachid Benouini, El Mehdi Benyoussef, Meriyem Chergui, Mohammed Ouzzif

“…While recent transformer-based models have achieved strong performance, they typically rely on large-scale pretraining and have high computational demands, limiting their usability in real-time or resource-constrained settings. …”
Get full text

Artificial saliva effect on toxic substances release from acrylic resins by Kostić Milena, Krunić Nebojša, Najman Stevo, Nikolić Ljubiša, Nikolić Vesna, Rajković Jelena, Petrović Milica, Igić Marko, Ignjatović Aleksandra

“…Storage of acrylic samples in two models of artificial saliva were performed in a water bath at the temperature of 37 ± 1°C. …”
Get full text

Optimized Tile Quality Selection in Multi-User 360° Video Streaming by Moatasim Mahmoud, Stamatia Rizou, Andreas S. Panayides, Nikolaos V. Kantartzis, George K. Karagiannidis, Pavlos I. Lazaridis, Zaharias D. Zaharis

“…To simulate our solution in practical settings, we employ a long short-term memory (LSTM) model to perform viewport prediction and make the assessment based on real-life viewing data. …”
Get full text

American Visceral Leishmaniasis: Factors Associated with Lethality in the State of São Paulo, Brazil by Geraldine Madalosso, Carlos Magno Fortaleza, Ana Freitas Ribeiro, Lisete Lage Cruz, Péricles Alves Nogueira, José Angelo Lauletta Lindoso

“…A comparison between VL fatal cases and survivors was performed for clinical, laboratory, and biological features. …”
Get full text

Alphabet Handwriting Recognition: From Wood‐Framed Hydrogel Arrays Design to Machine Learning Decoding by Guihua Yan, Xichen Hu, Ziyue Miao, Yongde Liu, Xianhai Zeng, Lu Lin, Olli Ikkala, Bo Peng

“…Efficient handwritten recognition is then achieved through appropriate manual feature extraction and algorithms with low complexity within a computing network, as demonstrated in this work, the strategic choice of expertise‐based feature engineering and simplified algorithms effectively boost the overall model performance on handwriting recognition. …”
Get full text

Predicting female football outcomes by machine learning: behavioural analysis of goals as high stress events by Aratz Olaizola, Ibai Errekagorri, Elsa Fernández, Julen Castellano, John Suckling, Karmele Lopez-de-Ipina

“…Several well-established ML models and feature extraction techniques were deployed with overall good performance of greater than 70% accuracy, with some specific methodology combinations have superior performance. …”
Get full text

Quantum generative learning for high-resolution medical image generation by Amena Khatun, Kübra Yeter Aydeniz, Yaakov S Weinstein, Muhammad Usman

“…Integration of quantum computing in generative machine learning models has the potential to offer benefits such as training speed-up and superior feature extraction. …”
Get full text

Predicting patient risk of leaving without being seen using machine learning: a retrospective study in a single overcrowded emergency department by Arianna Scala, Teresa Angela Trunfio, Massimo Majolo, Michelangelo Chiacchio, Giuseppe Russo, Paolo Montuori, Giovanni Improta

“…These findings suggest that predictive modeling may support hospital resource planning and patient flow management strategies to reduce LWBS rates.…”
Get full text

Efficacy of Magnetic Sphincter Augmentation versus Nissen Fundoplication for Gastroesophageal Reflux Disease in Short Term: A Meta-Analysis by Ming-yu Chen, Di-yu Huang, Angela Wu, Yi-bin Zhu, He-pan Zhu, Liu-mei Lin, Xiu-jun Cai

“…The meta-analysis search was performed, using four databases. All studies from 2005 to 2016 were included. …”
Get full text

A vision transformer based CNN for underwater image enhancement ViTClarityNet by Mohamed E. Fathy, Samer A. Mohamed, Mohammed I. Awad, Hossam E. Abd El Munim

“…Given the limited availability of paired underwater image datasets (clear and degraded), BlueStyleGAN is proposed as a generative model to create synthetic underwater images from clear in-air images by simulating realistic attenuation effects. …”
Get full text

Trajectory Prediction and Intention Recognition Based on CNN-GRU by Jinghao Du, Dongdong Lu, Fei Li, Ke Liu, Xiaolan Qiu

“…This model achieved a notable performance, with a Mean Absolute Error (MAE) not exceeding 6.877. …”
Get full text

Lightweight multiscale information aggregation network for land cover land use semantic segmentation from remote sensing images by Yahia Said, Oumaima Saidani, Ali Delham Algarni, Mohammad H. Algarni, Ayman Flah

“…The model’s performance was rigorously evaluated using the NITRDrone and UDD6 datasets, demonstrating a segmentation accuracy of 94.8%, with a significantly reduced parameter count compared to state-of-the-art methods. …”
Get full text