Clinical prediction of intravenous immunoglobulin-resistant Kawasaki disease based on interpretable Transformer model. by Gahao Chen, Ziwei Yang

“…Six machine learning algorithms - Random Forest (RF), AdaBoost, Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Tabular Prior-data Fitted Network version 2.0 (TabPFN-V2) - were implemented with five-fold cross-validation to optimize model hyperparameters. …”
Get full text

Mechanistic role of the KRTAP5-AS1/miR-199b-5p/CYP19A1 axis in polycystic ovary syndrome pathogenesis by Ping Tao, Xiaohong Yan, Zhanxiang Wang

“…Bioinformatics analyses including ceRNA network construction predicted the KRTAP5-AS1/miR-199b-5p/CYP19A1 regulatory axis, which was experimentally validated through dual-luciferase reporter assays. qRT-PCR confirmed the expression patterns of these molecules in expanded clinical cohorts (38 PCOS vs. 30 controls), with Pearson correlation analysis examining relationships between gene expression and clinical parameters. …”
Get full text

A Comparative Study of Lesion-Centered and Severity-Based Approaches to Diabetic Retinopathy Classification: Improving Interpretability and Performance by Gang-Min Park, Ji-Hoon Moon, Ho-Gil Jung

“…Transfer learning from NMC to APTOS notably improved severity classification, achieving performance gains of 15.2% in mild cases and 66.3% in severe cases through feature fusion using Bidirectional Feature Pyramid Network (BiFPN) and Feature Pyramid Network (FPN). …”
Get full text

Screening and regulatory mechanism exploration of M1 macrophage polarization and efferocytosis-related biomarkers in coronary heart disease by Hong Gao, Junhua Li, Jianxin Huang, Xiaojie Jiang

“…These biomarkers were subsequently leveraged to explore immune infiltration patterns and to construct a molecular regulatory network. …”
Get full text

Research on Data Repair of Pile-Type Adjustable Wind Turbine Foundation Monitoring Based on FST-ATTNet by WEI Huanwei, ZHAO Jizhang, ZHENG Xiao, TAN Fang, LIU Cong

“…In the time domain, Bidirectional Gated Recurrent Units (BiGRU) capture both forward and backward dependencies within the time series, ensuring a comprehensive understanding of local sequence patterns. The Kolmogorov-Arnold Network (KAN) incorporates a B-spline activation function, further enhancing the model's ability to capture complex nonlinear temporal changes. …”
Get full text

On the added value of sequential deep learning for the upscaling of evapotranspiration by B. Kraft, B. Kraft, B. Kraft, J. A. Nelson, S. Walther, F. Gans, U. Weber, G. Duveiller, M. Reichstein, W. Zhang, M. Rußwurm, D. Tuia, M. Körner, Z. Hamdi, M. Jung

“…</p> <p>In this study, we compared instantaneous (i.e., non-sequential) models (extreme gradient boosting (XGBoost) and a fully connected neural network (FCN)) with sequential models (a long short-term memory (LSTM) model and a temporal convolutional network (TCN)) for the modeling and upscaling of ET. …”
Get full text

Object representations drive emotion schemas across a large and diverse set of daily-life scenes by Chuanji Gao, Susan Ajith, Marius V. Peelen

“…To explore this, we collected emotion ratings for 4913 daily-life scenes from 300 participants, and predicted these ratings from representations in deep neural networks and functional magnetic resonance imaging (fMRI) activity patterns in visual cortex. …”
Get full text

Deep learning-driven medical image analysis for computational material science applications by Li Lu, Mingpei Liang

“…IntroductionDeep learning has significantly advanced medical image analysis, enabling precise feature extraction and pattern recognition. However, its application in computational material science remains underexplored, despite the increasing need for automated microstructure analysis and defect detection. …”
Get full text

Activation-Guided Low-Rank Parameter Adaptation for Efficient Model Fine-Tuning by Qingchen Wang, Shengyu Shen

Get full text

Identify suitable artificial groundwater recharge zones using hybrid deep learning models by Navaz Khalillollahi, Mohsen Isari, Hamed Faroqi, Kaywan Othman Ahmed, Kamran Nobakht Vakili, Miklas Scholz, Saad Sh. Sammeng

“…Identifying groundwater recharge zones is crucial for sustainable water resource management in water-scarce environments, such as Kurdistan, Iran. This study evaluated four deep learning models for delineating groundwater recharge zones: Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU), and hybrid deep learning Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU). …”
Get full text

Deep learning helps discriminate between autoimmune hepatitis and primary biliary cholangitis by Alessio Gerussi, Oliver Lester Saldanha, Giorgio Cazzaniga, Damiano Verda, Zunamys I. Carrero, Bastian Engel, Richard Taubert, Francesca Bolis, Laura Cristoferi, Federica Malinverno, Francesca Colapietro, Reha Akpinar, Luca Di Tommaso, Luigi Terracciano, Ana Lleo, Mauro Viganó, Cristina Rigamonti, Daniela Cabibi, Vincenza Calvaruso, Fabio Gibilisco, Nicoló Caldonazzi, Alessandro Valentino, Stefano Ceola, Valentina Canini, Eugenia Nofit, Marco Muselli, Julien Calderaro, Dina Tiniakos, Vincenzo L’Imperio, Fabio Pagni, Nicola Zucchini, Pietro Invernizzi, Marco Carbone, Jakob Nikolas Kather

Get full text

Advanced Hybrid Transformer-CNN Deep Learning Model for Effective Intrusion Detection Systems with Class Imbalance Mitigation Using Resampling Techniques by Hesham Kamal, Maggie Mashaly

“…The Transformer-CNN model focuses on three primary objectives to enhance detection accuracy and performance: (1) reducing false positives and false negatives, (2) enabling real-time intrusion detection in high-speed networks, and (3) detecting zero-day attacks. We evaluate our proposed model, Transformer-CNN, using the NF-UNSW-NB15-v2 and CICIDS2017 benchmark datasets, and assess its performance with metrics such as accuracy, precision, recall, and F1-score. …”
Get full text

Criminal Law Challenged by Crossing into Virtual Reality by Mahdi Karimi

“…These latter criminal behaviors are either committed through the use of social networks such as Facebook, Twitter, and Instagram or are facilitated by using them. 2. …”
Get full text

Length Scales, Rates, and Variability of Mixing Downstream of River Confluences by Tasneem Haq Meem, Bruce L. Rhoads, Quinn W. Lewis, Muhammad Umar, Alexander Sukhodolov

“…The findings confirm that confluences are important locations of accelerated mixing in river networks.…”
Get full text

Socioeconomic status and lifestyle as factors of multimorbidity among older adults in China: results from the China Health and Retirement Longitudinal Survey by Wei Gong, Wei Gong, Wei Gong, Xiaoxiao Hu, Huimin Cui, Huimin Cui, Yuxin Zhao, Yuxin Zhao, Hong Lin, Hong Lin, Hong Lin, Peng Sun, Peng Sun, Jianjun Yang, Jianjun Yang

“…Model performance was evaluated using AUC, accuracy, precision, recall, F1-score, RMSE, and decision curve analysis (DCA). …”
Get full text

Enhanced Deep Autoencoder-Based Reinforcement Learning Model with Improved Flamingo Search Policy Selection for Attack Classification by Dharani Kanta Roy, Hemanta Kumar Kalita

“…Intrusion detection has been a vast-surveyed topic for many decades as network attacks are tremendously growing. This has heightened the need for security in networks as web-based communication systems are advanced nowadays. …”
Get full text

The impact of immune-related adverse events on the outcome of advanced gastric cancer patients with immune checkpoint inhibitor treatment by Tianhang Zhang, Haitao Lv, Jiasong Li, Shasha Zhang, Jingjing Zhang, Siqi Wang, Yingnan Wang, Yingnan Wang, Zhanjun Guo

“…In this study, we investigated individually the impact of the different irAEs on AGC survival as well as the co-occurrence patterns of multi-irAEs.MethodsThe uni-irAE, multi-irAEs, and non-irAE were identified based on National Comprehensive Cancer Network (NCCN) guidelines. …”
Get full text

Methods and reliability study of moral education assessment in universities: A machine learning-based approach by Ting Jin

“…This analysis utilizes Principal Component Analysis (PCA) alongside the k-Nearest Neighbor (k-NN) method, Support Vector Regression (SVR), and Artificial Neural Networks (ANN) to study student performance indices, enabling the prediction of ethical reasoning capabilities for standardized evaluation. …”
Get full text

Integrating single-cell RNA-Seq and bulk RNA-Seq data to explore the key role of fatty acid metabolism in hepatocellular carcinoma by Hua Dai, Xin Tao, Yuansen Shu, Fanrong Liu, Xiaoping Cheng, Xiushen Li, Bairui Shu, Hongcheng Luo, XuXiang Chen, Zhaorui Cheng

“…Subsequent to this, consensus clustering analysis was implemented to stratify patients into distinct subgroups, contingent upon the expression patterns of lipid metabolism genes. Further analytical procedures involved functional enrichment analysis, evaluation of immune infiltration, and examination of the mutation landscape.PTGES3 was identified as a pivotal gene associated with lipid metabolism. …”
Get full text

Design of open systems for meniscus splitting demonstrated using an aqueous polymer solution by Reina Hagiwara, Kosuke Okeyoshi

“…To understand it as a universal phenomenon independent of the polymer species, the distinct evolutionary pathways to pattern formation were evaluated, focusing on the interface deformation and directional deposition of the polymer. …”
Get full text