A risk prediction model for neovascular glaucoma secondary to proliferative diabetic retinopathy based on Boruta feature selection and random forest by Zihan Huang, Di Gong, Cuicui Tang, Jinghui Wang, Chenchen Zhang, Kuanrong Dang, Kuanrong Dang, Xiaoyan Chai, Xiaoyan Chai, Jiantao Wang, Zhichao Yan

“…All data analyses and modeling were performed in R (version 4.2.3).ResultsThe Boruta algorithm selected 12 significant predictive features. …”
Get full text

IT: An interpretable transformer model for Alzheimer's disease prediction based on PET/MR images by Zhaomin Yao, Weiming Xie, Jiaming Chen, Ying Zhan, Xiaodan Wu, Yingxin Dai, Yusong Pei, Zhiguo Wang, Guoxu Zhang

“…The efficiency of our model is underscored by robust experimental validation, wherein it delivers superior performance on a host of evaluative benchmarks, all while maintaining low demands on computational resources. …”
Get full text

Fine Resolution Mapping of Forest Soil Organic Carbon Based on Feature Selection and Machine Learning Algorithm by Yanan Li, Jing Li, Jun Tan, Tianyue Ma, Xingguang Yan, Zongyang Chen, Kunheng Li

“…This study utilized 32 environmental variables from multispectral, topographic, and soil data, along with 142 soil samples and six machine learning methods to construct a forest SOC model for the Huodong mining district. The performance of Boruta and SHAP (SHapley Additive exPlanations) in optimizing feature selection was evaluated. …”
Get full text

MRI Delta-Radiomics and Morphological Feature-Driven TabPFN Model for Preoperative Prediction of Lymphovascular Invasion in Invasive Breast Cancer by Yunhua Li BS, Jianfeng Yang MS, Pan Xiao MS, Haibo Liu BS, Yingjun Zhou BS, Xiuqi Yang MS, Gangwen Chen BS, Zhichao Zuo PhD

“…Among the evaluated machine learning models, the TabPFN algorithm demonstrated superior performance by effectively integrating the Radscore along with clinical and MR morphological features, resulting in an AUC of 0.899. …”
Get full text

MLG: a mixed local and global model for brain tumor classification by Wenna Chen, Xinghua Tan, Jincan Zhang, Ganqin Du, Qizhi Fu, Hongwei Jiang

“…Conversely, the Biformer Block is responsible for extracting global features, adaptively focusing on relevant sets of key tokens based on query positions, thereby minimizing attention to irrelevant information and further boosting model performance. …”
Get full text

VSG-FC: A Combined Virtual Sample Generation and Feature Construction Model for Effective Prediction of Surface Roughness in Polishing Processes by Dapeng Yang, Shenggao Ding, Lifang Pan, Yong Xu

“…This approach optimizes the feature space through sample augmentation and feature reconstruction, thereby enhancing model performance. …”
Get full text

A model of feature extraction for well logging data based on graph regularized non-negative matrix factorization with optimal estimation by Kehong Yuan, Youlin Shang, Haixiang Guo, Yongsheng Dong, Zhonghua Liu

“…Firstly, the low dimensional embedding dimension of high-dimensional well logging data is modeled and estimated, which enables the method to obtain the appropriate number of features that reflect the data structure. …”
Get full text

Hybrid CNN-Transformer-WOA model with XGBoost-SHAP feature selection for arrhythmia risk prediction in acute myocardial infarction patients by Li Li, Wenjun Ren, Yuying Lei, Lixia Xu, Xiaohui Ning

“…Ablation studies showed that combining CNN and Transformer improved predictive power and that WOA-based hyperparameter tuning further enhanced robustness. The model maintained stable performance across subgroups and demonstrated low inference latency (<8 ms per case). …”
Get full text

A Robust Hybrid CNN+ViT Framework for Breast Cancer Classification Using Mammogram Images by Vasudha Rani Patheda, Gunda Laxmisai, B. V. Gokulnath, S. P. Siddique Ibrahim, S. Selva Kumar

“…The CNN+ViT model gave us an accuracy of 90.1% showing robust performance. …”
Get full text

MDA-MIM: a radar echo map prediction model integrating multi-scale feature fusion and dual attention mechanism by HU Qiang, GAO Yating, YIN Binli, QU Lianen

“…To obtain high-quality spatiotemporal features from radar echo maps, an improved MIM (memory in memory) model, MDA-MIM (multi-scale feature fusion and dual attention mechanism MIM) was proposed. …”
Get full text

OM-VST: A video action recognition model based on optimized downsampling module combined with multi-scale feature fusion. by Xiaozhong Geng, Cheng Chen, Ping Yu, Baijin Liu, Weixin Hu, Qipeng Liang, Xintong Zhang

“…To solve these problems, we propose the OM-Video Swin Transformer (OM-VST) model. This model adds a multi-scale feature fusion module with an optimized downsampling module based on a Video Swin Transformer (VST) to improve the model's ability to perceive and characterize feature information. …”
Get full text

Fine-grained ship image classification and detection based on a vision transformer and multi-grain feature vector FPN model by Fengxiang Wang, Deying Yu, Liang Huang, Yalun Zhang, Yongbing Chen, Zhiguo Wang

Get full text

Enhancing the Transformer Model with a Convolutional Feature Extractor Block and Vector-Based Relative Position Embedding for Human Activity Recognition by Xin Guo, Young Kim, Xueli Ning, Se Dong Min

“…Therefore, we proposed using multi-layer convolutional layers as a Convolutional Feature Extractor Block (CFEB). CFEB enables the Transformer model to leverage both local and global time series features for activity classification. …”
Get full text

MF-ShipNet: a multi-feature weighted fusion and PCA-SVM model for ship detection in remote sensing images by Jianfeng Li, Yibing Yang, Liutong Yang, Yang Zhao, Qinghua Luo, Chenxu Wang

“…To solve this problem, this paper proposes a multi-feature weighted fusion and PCA-SVM model for ship detection in remote sensing images. …”
Get full text

HCT-Det: A High-Accuracy End-to-End Model for Steel Defect Detection Based on Hierarchical CNN–Transformer Features by Xiyin Chen, Xiaohu Zhang, Yonghua Shi, Junjie Pang

“…This structure combines window-based self-attention (WSA) blocks to reduce computational overhead and parallel residual convolutional (Res) blocks to enhance local feature continuity. The model’s backbone generates three cross-scale features as encoder inputs, which undergo Intra-Scale Feature Interaction (ISFI) and Cross-Scale Feature Interaction (CSFI) to improve detection accuracy for targets of various sizes. …”
Get full text

Probabilistic prediction intervals of short-term wind speed using selected features and time shift dependent machine learning models by Rami Al-Hajj, Gholamreza Oskrochi, Mohamad M. Fouad, Ali Assi

“…Models for estimating prediction intervals of wind speed do not differentiate between daytime and nighttime shifts, which can affect the performance of probabilistic wind speed forecasting. …”
Get full text

Performance Evaluation of Hybrid Bio-Inspired and Deep Learning Algorithms in Gene Selection and Cancer Classification by Shahad S. Alkamli, Hala M. Alshamlan

“…Meanwhile, deep learning models excel in pattern recognition and automated feature extraction, offering a complementary approach to traditional gene selection techniques. …”
Get full text

A Three-Dimensional Feature Space Model for Soil Salinity Inversion in Arid Oases: Polarimetric SAR and Multispectral Data Synergy by Ilyas Nurmemet, Yilizhati Aili, Yang Xiang, Aihepa Aihaiti, Yu Qin, Bilali Aizezi

“…Based on the interactions of these three optimal features within the 3D feature space, we constructed the Optical-Radar Salinity Inversion Model (ORSIM). …”
Get full text

Integration of Nuclear, Clinical, and Genetic Features for Lung Cancer Subtype Classification and Survival Prediction Based on Machine- and Deep-Learning Models by Bin Xie, Mingda Mo, Haidong Cui, Yijie Dong, Hongping Yin, Zhe Lu

“…The performance of the models was comprehensively evaluated. …”
Get full text

Integrated feature selection-based stacking ensemble model using optimized hyperparameters to predict breast cancer with smart web application by Rajib Kumar Halder, Marzana Akter Lima, Mohammed Nasir Uddin, Md.Aminul Islam, Adri Saha

“…These features are then used to train the model, ensuring that our approach focuses on the most relevant data points for breast cancer classification. …”
Get full text