MESM: integrating multi-source data for high-accuracy protein-protein interactions prediction through multimodal language models by Feng Wang, Jinming Chu, Liyan Shen, Shan Chang

“…This limits the model’s ability to learn richer and more effective interaction information, thereby affecting prediction performance. …”
Get full text

Unlocking The Potential of Hybrid Models for Prognostic Biomarker Discovery in Oral Cancer Survival Analysis: A Retrospective Cohort Study by Leila Nezamabadi Farahani, Anoshirvan Kazemnejad, Mahlagha Afrasiabi, Leili Tapak

“…Then, the particle swarm optimization (PSO) and genetic algorithm (GA) were used in combination with SVR for selecting features related to pseudo-survival outcome. Concordance index (C-index), mean absolute error (MAE), mean squared error (MSE) and R-squares, were used to evaluate the performance of the models using selected features. …”
Get full text

A Machine Learning Model Integrating Tongue Image Features and Myocardial Injury Markers Predicts Major Adverse Cardiovascular Events in Patients with Coronary Heart Disease by Zhou M, Li J, Lim J, Xiao X, Xia Y, Wang Q, Xu Z

“…All the patients were classified into two different groups according to follow-up results showed whether there was MACE, and the tongue image of each patient was performed using SMX System 2.0 to normalised acquisition was performed using SMX System 2.0, and tongue body (TC_) and tongue coating (CC_) data were converted to RGB and HSV model parameters. …”
Get full text

Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study by Xin Guan, Bo Zhang, Ming Fu, Mengying Li, Xu Yuan, Yaowu Zhu, Jing Peng, Huan Guo, Yanjun Lu

“…Performances of models were evaluated by AUC, prediction accuracy, precision, and F1 scores.Results Six features, including disease severity, age, levels of high-sensitivity C-reactive protein (hs-CRP), lactate dehydrogenase (LDH), ferritin, and interleukin-10 (IL-10), were selected as predictors for COVID-19 mortality. …”
Get full text

Leveraging Personalized Customer Experiences in Mobile Edge Computing Through Split Learning Using Smart Data-Driven Modeling by V. Vinoth Kumar, K. M. Karthick Raghunath, Iyappan Perumal, K. Manikandan

Get full text

An End-to-End General Language Model (GLM)-4-Based Milling Cutter Fault Diagnosis Framework for Intelligent Manufacturing by Jigang He, Xuan Liu, Yuncong Lei, Ao Cao, Jie Xiong

“…The rise in large language models (LLMs) has brought changes to tool life diagnosis. …”
Get full text

Universal Modeling for Non-Destructive Testing of Soluble Solids Content in Multi-Variety Blueberries Based on Hyperspectral Imaging Technology by Lingqi Meng, Guoliang Chen, Dayang Liu, Ning Tian

Get full text

SD-YOLOv8: SAM-Assisted Dual-Branch YOLOv8 Model for Tea Bud Detection on Optical Images by Xintong Zhang, Dasheng Wu, Fengya Xu

“…The SD-YOLOv8 model mainly consists of two key components: (1) the SAM-based foreground segmenter (SFS) to generate foreground masks of tea bud images without any training, and (2) the heterogeneous feature extractor to parallelly capture both color features in optical images and edge features in foreground masks. …”
Get full text

Explainability enhanced liver disease diagnosis technique using tree selection and stacking ensemble-based random forest model by Mohammad Mamun, Safiul Haque Chowdhury, Muhammad Minoar Hossain, M.R. Khatun, Sadiq Iqbal

“…Finally, the ultimate model is selected based on incorporating cross-validation and evaluation through performance metrics like accuracy, precision, specificity, etc., and efficient XAI methods express the ultimate model's interoperability. …”
Get full text

Pedestrian trajectory prediction model based on self-supervised spatiotemporal graph network by Shiji Yang, Xuezhong Xiao

“…Firstly, in the process of spatiotemporal graph modeling, this model introduces hop interaction instead of node interaction to update node features, which greatly reduces the times of graph convolution operations, alleviates the problem of feature smoothing, and greatly improves the accuracy of prediction. …”
Get full text

Hypergraph Self-Supervised Learning-Based Joint Spectral-Spatial-Temporal Feature Representation for Hyperspectral Image Change Detection by Ping Jian, Yimin Ou, Keming Chen

“…Second, two SSL strategies namely contrastive spectral-spatial features learning and generative temporal features learning are skillfully designed to exploit the inherent characteristics of hypergraph models and extract discriminative latent feature representations for downstream tasks. …”
Get full text

CT feature-based nomogram for predicting tumor spread through air spaces in stage IA lung adenocarcinoma by Bin Luo, Han Yang, Ningbo Fan, Pengfei Duan, Zhesheng Wen, Peng Lin

Get full text

Dual-Scale Complementary Spatial-Spectral Joint Model for Hyperspectral Image Classification by Huayue Chen, Yue Sun, Xiang Li, Bochuan Zheng, Tao Chen

“…DTFE preserves edge information while smoothing details, effectively removing noise and retaining the dual-scale feature information. In the postprocessing stage, a sub-Markov random walk-based spatial probability optimization method is proposed, which models the spatial association of neighboring pixels, retaining complex textures as well as weak edge information to optimize the classification probability. …”
Get full text

Weighting Variables for Transportation Assets Condition Indices Using Subjective Data Framework by Abdallah B. Al-Hamdan, Yazan Ibrahim Alatoom, Inya Nlenanya, Omar Smadi

“…Random forest models performed effectively in modeling the relationship between the overall condition index (OCI) and the objective measures and provided feature importance scores that were converted into weights. …”
Get full text

A Comprehensive Comparative Analysis of Deep Learning Models for Student Performance Prediction in Virtual Learning Environments: Leveraging the OULA Dataset and Advanced Resamplin... by Bayan A. Alnasyan, Mohammed Basheri, Madini O. Alassafi

“…The SAINT model achieved the highest performance in binary classification (94.33% accuracy), leveraging its ability to capture meaningful yet straightforward feature interactions. …”
Get full text

DiffusionAAE: Enhancing hyperspectral image classification with conditional diffusion model and Adversarial Autoencoder by Zeyu Cao, Jinhui Li, Xiangrui Xu

“…Our framework’s key innovation lies in its two-stage architecture: first, an AAE extracts robust latent features capturing intricate spectral–spatial relationships; second, a conditional diffusion model refines these features through progressive denoising, enabling class-specific feature generation while maintaining physical constraints inherent to hyperspectral data. …”
Get full text

Application of Improved YOLOv8 Image Model in Urban Manhole Cover Defect Management and Detection: Case Study by Yanqiong Ding, Baojiang Han, Hua Jiang, Hao Hu, Lei Xue, Jiasen Weng, Zhili Tang, Yuzhang Liu

“…By introducing the fused MBConv structure, the computational complexity is significantly reduced, while the efficiency of feature extraction is improved. An innovative foreground attention module is introduced to adaptively enhance the features of manhole cover defects, improving the model’s ability to identify defects of various scales. …”
Get full text

ANFIS-based modeling of packed bed thermal energy storage with phase change material: A novel geometric design for enhanced performance by Somayeh Davoodabadi Farahani, Reza Rahmani, As'ad Alizadeh, Aliakbar Karimipour

“…For the numerical analysis, ANSYS Fluent software was employed in two scenarios: one involving a complete concrete sample and the other featuring concrete mixed with PCM in various geometries. …”
Get full text

AYOLO: Development of a Real-Time Object Detection Model for the Detection of Secretly Cultivated Plants by Ali Yılmaz, Yüksel Yurtay, Nilüfer Yurtay

“…On a custom dataset comprising 80 images of poppy plants, AYOLO achieved a remarkable Average Precision (AP) of 38.7% while maintaining a high rendering speed of 239 FPS (Frames Per Second) on a Tesla K80 GPU. Real-time performance is demonstrated by achieving 239 FPS, and feature fusion optimally combines spatial and semantic information across scales. …”
Get full text

LGWheatNet: A Lightweight Wheat Spike Detection Model Based on Multi-Scale Information Fusion by Zhaomei Qiu, Fei Wang, Tingting Li, Chongjun Liu, Xin Jin, Shunhao Qing, Yi Shi, Yuntao Wu, Congbin Liu

Get full text