Postsurgery Classification of Best-Corrected Visual Acuity Changes Based on Pterygium Characteristics Using the Machine Learning Technique by Fatin Nabihah Jais, Mohd Zulfaezal Che Azemin, Mohd Radzi Hilmi, Mohd Izzuddin Mohd Tamrin, Khairidzan Mohd Kamal

“…Conclusion. Machine learning algorithms can produce a highly accurate postsurgery classification model of BCVA changes using pterygium characteristics.…”
Get full text

Topology optimization of a cargo gripper design using the minimum effort principle by Gnezdilov S.G.

“…The study emphasizes accounting for varied load scenarios (e.g., sheet tilting) for future refinement. It confirms the algorithm’s effectiveness in simplifying models and highlights iterative refinement for rational topology. …”
Get full text

Precision Weed Management for Straw-Mulched Maize Field: Advanced Weed Detection and Targeted Spraying Based on Enhanced YOLO v5s by Xiuhong Wang, Qingjie Wang, Yichen Qiao, Xinyue Zhang, Caiyun Lu, Chao Wang

“…Thirdly, we designed a targeted spraying system by combining the proposed model with the targeted spraying device. Through model test and spraying experiments, the results demonstrated that while the model exhibited a 0.9% decrease in average detection accuracy for weeds, it achieved an 8.46% increase in detection speed, with model memory and computational load reduced by 50.36% and 53.16%, respectively. …”
Get full text

Simulation of Land Use and Land Cover Using the MOLUSCE Plugin Integrated with QGIS for the Western Himalayan Region of India by S. Kumari, S. Kumari, A. Roy

“…This calibration accounts for historical trends and transitions, thereby improving the model's predictive accuracy for future scenarios. …”
Get full text

Reducing bias in coronary heart disease prediction using Smote-ENN and PCA. by Xinyi Wei, Boyu Shi

“…This indicates that combining data balancing and feature dimensionality reduction techniques significantly improves model accuracy and makes the random forest model the best model. …”
Get full text

Using machine learning to predict the risk of developing hypertensive disorders of pregnancy using a contemporary nulliparous cohortAJOG Global Reports at a Glance by Jonathan S. Schor, PhD, Adesh Kadambi, BEng, Isabel Fulcher, PhD, Kartik K. Venkatesh, MD, PhD, Mark A. Clapp, MD, MPH, Senan Ebrahim, MD, PhD, Ali Ebrahim, PhD, Timothy Wen, MD, MPH

“…Sensitivity analyses were conducted to compare the sensitivity and specificity of the reduced model compared to existing risk factor-based algorithms. …”
Get full text

Intelligent Prediction Platform for Sepsis Risk Based on Real-Time Dynamic Temporal Features: Design Study by Mingwei Zhang, Ming Zhong, Yunzhang Cheng, Tianyi Zhang

“…Three linear parameters (mean, SD, and endpoint value) were calculated to construct the prediction model using multiple ML algorithms. The interpretability module uses the TreeSHAP (Tree-Based Shapley Additive Explanations) method to enhance model transparency through both individual prediction and global explanations. …”
Get full text

Prediction of Flexural Ultimate Capacity for Reinforced UHPC Beams Using Ensemble Learning and SHAP Method by Zhe Zhang, Xuemei Zhou, Ping Zhu, Zhaochao Li, Yichuan Wang

“…Furthermore, multiple machine learning (ML) algorithms, including both traditional and EL models, are employed to develop optimized predictive models for the flexural ultimate capacity of reinforced UHPC specimens derived from the established database. …”
Get full text

Interrelationships Between Inflammatory Score, Delayed Cerebral Ischemia and Unfavorable Outcome in Patients with aSAH: A Four-Way Decomposition by Zhang P, Zhu H, Li X, Qian Y, Zhu Y, Zhang W, Yan Z, Ni H, Lin Z, Lin X, Li Z, Zhuge Q, Zeng B

“…Adding the inflammatory score to the predictive model improved the AUC from 0.772 to 0.822, with an NRI of 5.3% and IDI of 6.9%.Conclusion: The inflammatory score was significantly associated with DCI and poor outcome in patients with aSAH. …”
Get full text

Deep learning-based novel ensemble method with best score transferred-adaptive neuro fuzzy inference system for energy consumption prediction by Birce Dağkurs, İsmail Atacak

“…In order to build a robust and dynamic prediction model, the interaction between the base predictors and the ANFIS architecture is achieved using a best score transfer approach. …”
Get full text

Developing a Multisensor-Based Machine Learning Technology (Aidar Decompensation Index) for Real-Time Automated Detection of Post–COVID-19 Condition: Protocol for an Observational... by Jenny Mathew, Jaclyn A Pagliaro, Sathyanarayanan Elumalai, Lauren K Wash, Ka Ly, Alison J Leibowitz, Varsha G Vimalananda

“…Using appropriate algorithmic techniques, the study expects the model to have a sensitivity of >80% and a positive predicted value of >70%. …”
Get full text

Early Diagnosis of Knee Osteoarthritis With a Natural Language Processing–Driven Approach Based on Clinician Notes: Development and Validation Study by Narathip Thanyakunsajja, Kulsawasd Jitkajornwanich, Shan Xu, Donghee Shin, Pattama Charoenporn

“…Lastly, a disease-specific standard questionnaire called WOMAC (Western Ontario and McMaster Universities Arthritis Index) was taken into account to improve the overall performance of the models. …”
Get full text

Exploration of biomarkers for predicting the prognosis of patients with diffuse large B-cell lymphoma by machine-learning analysis by Shifen Wang, Hong Tao, Xingyun Zhao, Siwen Wu, Chunwei Yang, Yuanfei Shi, Zhenshu Xu, Dawei Cui

“…However, the molecular mechanisms that underlie this association have not been clearly elucidated. To improve this situation, it is urgent to explore disease-specific diagnostic biomarkers and mechanisms. …”
Get full text

Residual Film–Cotton Stubble–Nail Tooth Interaction Study Based on SPH-FEM Coupling in Residual Film Recycling by Xuejun Zhang, Yangyang Shi, Jinshan Yan, Shuo Yang, Zhaoquan Hou, Huazhi Li

“…The effect of cotton straw–root stubble on residual film recovery can only be better determined by appropriate machine operating parameters, which are essential to improving residual film recovery. Through analyses of the pickup device, key parameters were identified, and a model was built by combining the FEM and SPH algorithms to simulate the interaction of nail teeth, residual film, soil and root stubble. …”
Get full text

Research on Hybrid Architecture Neural Networks for Time Series Prediction by Fujin Zhuang, Xiao Chen, Punyaphol Horata, Khamron Sunat

“…Although MAE was slightly higher, the overall error control remained within an acceptable range, validating the model’s stability and effectiveness. The importance of the attention mechanism was further verified through ablation experiments, with the complete model’s R2 value improving by 87.04% and MSE decreasing by 87.18% compared to using TCN alone, confirming the effectiveness of the multi-module collaborative design. …”
Get full text

Detection of communities with Naming Game-based methods. by Thais Gobet Uzun, Carlos Henrique Costa Ribeiro

“…Also, our model has shown a degree of accuracy both for non-overlapping and overlapping communities that are comparable with most algorithms specifically designed for topological community detection.…”
Get full text

Decoding Depression from Different Brain Regions Using Hybrid Machine Learning Methods by Qi Sang, Chen Chen, Zeguo Shao

“…Compared with traditional single methods, the hybrid approach significantly improved detection accuracy by leveraging the strengths of different algorithms. …”
Get full text

The Use of General Inverse Problem Platform (GRIPP) as a Robust Backtracking Solution by Nikolas Gomes Silveira de Souza, Jader Lugon, Alexandre Macedo Fernandes, Ramiro Joaquim de Jesus Neves, Antônio José da Silva Neto

“…This study addresses the challenge of identifying pollutant sources in aquatic coastal environments using inverse problem techniques hampered by particularities in hydrodynamic and Lagrangian models. An approach is presented employing the General Inverse Problem Platform (GRIPP) coupled with a General Simulated Annealing (GenSA) algorithm for robust backtracking. …”
Get full text

Edge Computing Oriented Certificateless Sorting Ciphertext Retrieval Scheme by DUAN Jie, GU Wei, ZHANG Shujuan, GONG Xin

“…Second, by referencing the certificateless public key cryptosystem, the user’s public and private keys were generated and managed by themselves, which solved the problems of key escrow and certificate management in traditional schemes and improved the security of the system. Finally, by blocking the index and trapdoor to filter out keywords unrelated to the query, the secure KNN(k-nearest neighbor) algorithm was used to calculate document similarity, which improved retrieval efficiency and accuracy. …”
Get full text

Polymer electrolyte membrane fuel cell performance Revolutionized: Artificial intelligence-validated asymmetric flow channels enhance mass transport via hybrid analytical-numerical... by Nima Ahmadi, Ghader Rezazadeh

“…Experimental validation confirms a current density improvement of up to 5.6 % over conventional designs, while Artificial Intelligence (AI)-driven optimization via a hybrid Convolutional Neural Network and Genetic Algorithm independently identifies the same optimal configuration. …”
Get full text