BiLSTM-Based Parallel CNN Models With Attention and Ensemble Mechanism for Twitter Sentiment Analysis by Anas W. Abulfaraj

“…When used together, models like the Convolutional Neural Networks (CNN) and LSTM networks have significant high-performance results for text feature extraction and semantic relationship of the word. …”
Get full text

On the effectiveness of neural operators at zero-shot weather downscaling by Saumya Sinha, Brandon Benton, Patrick Emami

“…We find that this Swin-Transformer-based approach mostly outperforms models with neural operator layers in terms of average error metrics, whereas an Enhanced Super-Resolution Generative Adversarial Network-based approach is better than most models in terms of capturing the physics of the ground truth data. …”
Get full text

PaleAle 6.0: Prediction of Protein Relative Solvent Accessibility by Leveraging Pre-Trained Language Models (PLMs) by Wafa Alanazi, Di Meng, Gianluca Pollastri

“…Today, deep learning is arguably the most powerful method for predicting RSA and other structural features of proteins. …”
Get full text

YOLO-SegNet: A Method for Individual Street Tree Segmentation Based on the Improved YOLOv8 and the SegFormer Network by Tingting Yang, Suyin Zhou, Aijun Xu, Junhua Ye, Jianxin Yin

“…In urban forest management, individual street tree segmentation is a fundamental method to obtain tree phenotypes, which is especially critical. Most existing tree image segmentation models have been evaluated on smaller datasets and lack experimental verification on larger, publicly available datasets. …”
Get full text

Reliable Event Detection via Multiple Edge Computing on Streaming Traffic Social Data by Yipeng Ji, Jingyi Wang, Yan Niu, Hongyuan Ma

“…The results indicate that our model can better implement streaming social traffic event detection, and is superior to most text classification methods.…”
Get full text

TCBGY net for enhanced wear particle detection in ferrography using self attention and multi scale fusion by Lei He, Haijun Wei, Cunxun Sun

“…Secondly, we introduce the convolutional block attention module (CBAM) into the neck network to enhance salience for detecting wear particles while suppressing irrelevant information interference. …”
Get full text

Synergizing vision transformer with ensemble of deep learning model for accurate kidney stone detection using CT imaging by Arwa Alzughaibi, Adwan A. Alanazi, Mohammed Alshahrani, Ines Hilali Jaghdam, Abaker A. Hassaballa

“…CT scans are one of the most extensively accessible imaging models, and they are employed for effective diagnosis. …”
Get full text

An Efficient Encoding Spectral Information in Hyperspectral Images for Transfer Learning of Mask R-CNN for Instance Segmentation of Tomato Sepals by Zeljana Grbovic, Marko Panic, Vladan Filipovic, Sanja Brdar, Hendrik de Villiers, Manon Mensink, Aneesh Chauhan

“…The most vulnerable parts of tomatoes are the tips of the sepals, which are the primary entry points for fungal spores. …”
Get full text

PREDICTION BACKUP TESTICULAR FUNCTION IN PATIENTS WITH NONOBSTRUCTIVE AZOOSPERMIA by N. G. Kul’chenko, A. A. Kostin, Yu. V. Samsonov, G. A. Demyashkin, D. V. Moskvichev

“…Modern authors believe that male infertility accounts for 40–50%. The most severe form of male infertility is azoospermia, which is observed in 10–15% of cases. …”
Get full text

A role for the thalamus in danger evoked awakening during sleep by Ida Luisa Boccalaro, Mattia Aime, Florence Marcelle Aellen, Thomas Rusterholz, Micaela Borsa, Ivan Bozic, Andrea Sattin, Tommaso Fellin, Carolina Gutierrez Herrera, Athina Tzovara, Antoine Adamantidis

“…Here, we showed that neutral auditory stimuli evoked responses across parallel auditory and non-auditory pathways, including the auditory cortex and thalamus, the hippocampus and centro-medial thalamus (CMT). Using a convolutional neural network, we identified CMT activity as the most discriminant hub for auditory-evoked sleep-to-wake transitions among all recorded structures. …”
Get full text

Efficient Robot Localization Through Deep Learning-Based Natural Fiduciary Pattern Recognition by Ramón Alberto Mena-Almonte, Ekaitz Zulueta, Ismael Etxeberria-Agiriano, Unai Fernandez-Gamiz

“…These images are processed by a convolutional neural network (CNN), designed to detect the most distinctive features of the environment. …”
Get full text

SIG-ShapeFormer: A Multi-Scale Spatiotemporal Feature Fusion Network for Satellite Cloud Image Classification by Xuan Liu, Zhenyu Lu, Bingjian Lu, Zhuang Li, Zhongfeng Chen, Yongjie Ma

“…The temporal evolution of cloud systems plays a crucial role in accurate classification, particularly under the coexistence of multiple weather systems. However, most existing models—such as those based on convolutional neural networks (CNNs), Transformer architectures, and their variants like Swin Transformer—primarily focus on spatial modeling of static images and do not explicitly incorporate temporal information, thereby limiting their ability to effectively integrate spatiotemporal features. …”
Get full text

A Deep Learning Approach to Assist in Pottery Reconstruction from Its Sherds by Matheus Ferreira Coelho Pinho, Guilherme Lucio Abelha Mota, Gilson Alexandre Ostwald Pedro da Costa

“…Pottery is one of the most common and abundant types of human remains found in archaeological contexts. …”
Get full text

Automated detection of diabetic retinopathy lesions in ultra-widefield fundus images using an attention-augmented YOLOv8 framework by Lei-Si Hu, Jie Wang, Heng-Ming Zhang, Hai-Yu Huang

“…ObjectiveTo enhance the automatic detection precision of diabetic retinopathy (DR) lesions, this study introduces an improved YOLOv8 model specifically designed for the precise identification of DR lesions.MethodThis study integrated two attention mechanisms, convolutional exponential moving average (convEMA) and convolutional simple attention module (convSimAM), into the backbone of the YOLOv8 model. …”
Get full text

Assessment of a Hyperspectral Remote Sensing Model Performance for Particulate Phosphorus in Optically Shallow Lake Water by Banglong Pan, Wuyiming Liu, Zhuo Diao, Qianfeng Gao, Lanlan Huang, Shaoru Feng, Juan Du, Qi Wang, Jiayi Li, Jiamei Cheng

“…It also serves as one of the most significant sources of phosphorus for primary productivity, serving as a possible source of soluble reactive phosphorus, and contributing a sizable amount of the total phosphorus (TP), so monitoring the spatial and temporal variability of PP is crucial for understanding eutrophication in water bodies. …”
Get full text

Benchmarking CNN Architectures for Tool Classification: Evaluating CNN Performance on a Unique Dataset Generated by Novel Image Acquisition System by Muhenad Bilal, Ranadheer Podishetti, Daniel Grossmann, Markus Bregulla

“…Among the evaluated training strategies, fine-tuning proved the most efficient training method for developing CNN models for tool classification.…”
Get full text

Modeling the Relationship between Financial Stability and Banking Risks: Artificial Intelligence Approach by Hakeem Faraj Gumar, Parviz Piri, Mehdi Heydari

“…The variables of capital adequacy ratio, cash flow, bank size, and Z score were identified as the most important factors affecting financial stability. …”
Get full text

KOC_Net: Impact of the Synthetic Minority Over-Sampling Technique with Deep Learning Models for Classification of Knee Osteoarthritis Using Kellgren–Lawrence X-Ray Grade by Syeda Nida Hassan, Mudassir Khalil, Humayun Salahuddin, Rizwan Ali Naqvi, Daesik Jeong, Seung-Won Lee

“…One of the most common diseases afflicting humans is knee osteoarthritis (KOA). …”
Get full text

Enhanced Pneumonia Detection from Chest X-rays Using Machine Learning and Deep Neural Architectures by Kamal Upreti, Anju Singh, Divakar Singh, Preety Shoran, Uma Shankar, Meenakshi Yadav, Rituraj Jain

“…The study aims to improve diagnostic precision, reduce interpretation discrepancies, and facilitate faster clinical decision-making by identifying the most effective machine learning approaches for real-world applications in healthcare settings. …”
Get full text

Machine Learning-Based Analysis of Travel Mode Preferences: Neural and Boosting Model Comparison Using Stated Preference Data from Thailand’s Emerging High-Speed Rail Network by Chinnakrit Banyong, Natthaporn Hantanong, Supanida Nanthawong, Chamroeun Se, Panuwat Wisutwattanasak, Thanapong Champahom, Vatanavongs Ratanavaraha, Sajjakaj Jomnonkwao

“…CatBoost emerges as the top-performing model (area under the curve = 0.9113; accuracy = 0.7557), highlighting travel cost, service frequency, and waiting time as the most influential determinants. These findings underscore the effectiveness of machine learning approaches in capturing complex behavioral patterns, providing empirical evidence to guide high-speed rail policy development in low- and middle-income countries. …”
Get full text