Explainable quality assessment of effective aligned skeletal representations for martial arts movements by multi-machine learning decisions by Yiqun Pang, Kaiqi Zhang, Fengmei Li

“…Firstly, the key features are extracted by the feature alignment technique, which eliminates the influence of athletes’ movement speed, rhythm and duration on the scoring, thus reflecting the athletes’ skill level more realistically. Second, to further improve the objectivity and accuracy, an adaptive weighted multi-model decision-making strategy is proposed. …”
Get full text

DEVELOPMENT OF A SOFTWARE MODULE FOR OPERATIONAL DISPATCH CONTROL OF PRODUCTION BASED ON CYBER-PHYSICAL CONTROL SYSTEMS by Igor Nevliudov, Vladyslav Yevsieiev, Nataliia Demska, Sergiy Novoselov

“…Conclusions: the proposed models and methods will not only automate the process of managing the development of CPPS from scratch, but will also make it possible to automate the process of managing the development of the cybernetic component for the modernization and improvement of existing CPPS.…”
Get full text

Activity cliff-aware reinforcement learning for de novo drug design by Xiuyuan Hu, Guoqing Liu, Yang Zhao, Hao Zhang

“…This RL framework is designed to focus model optimization on high-impact regions within the SAR landscape, improving the generation of molecules with targeted properties. …”
Get full text

Rethinking Technological Investment and Cost-Benefit: A Software Requirements Dependency Extraction Case Study by Gouri Ginde, Guenther Ruhe, Chad Saunders

“…As such, our results showed that, 1) chasing model accuracy improvisation through increased annotated data does not generate expected returns in traditional ML methods. 2) For complex ML algorithms, the need for larger annotated dataset investment cost is justified by the higher returns, however, the trade-offs between accuracy and ROI become evident.…”
Get full text

Incorporating Contextual Factors into a Comprehensive Analysis of Operational Efficiency and Service Quality in Healthcare Sector by Utsav Pandey, Sanjeet Singh

“…The proposed model is empirically tested using healthcare data of 31 provinces of China for a period from 2013 to 2018. …”
Get full text

Multi-View Collaborative Training and Self-Supervised Learning for Group Recommendation by Feng Wei, Shuyu Chen

“…This paper addresses the data sparsity issue to improve group recommendation performance, overcoming the limitations of overlooking individual user recommendation tasks and depending on single-view modeling. …”
Get full text

A PSO weighted ensemble framework with SMOTE balancing for student dropout prediction in smart education systems by Achin Jain, Arun Kumar Dubey, Shakir Khan, Arvind Panwar, Mohammad Alkhatib, Abdulaziz M Alshahrani

“…This methodology balances the dataset using SMOTE, optimizes model hyperparameters, and fine-tunes ensemble weights through PSO to improve predictive performance. …”
Get full text

Inflammation-related 5-hydroxymethylation signatures as markers for clinical presentations of coronary artery disease by Jing Xu, Hangyu Chen, Jingang Yang, Yanmin Yang, Yuan Wu, Jun Zhang, Jiansong Yuan, Tianjie Wang, Tao Tian, Jia Li, Xueyan Zhao, Xiaojin Gao, Jie Lu, Lin Li, Lei Zhang, Xuehui Li, Long Chen, Chuan He, Chaoran Dong, Jian Lin, Weixian Yang, Yuejin Yang

“…Using machine learning algorithms, we identified inflammation-related 5hmC modifications associated with disease severity and constructed a classification model based on key hydroxymethylated markers. …”
Get full text

An autonomous navigation method for field phenotyping robot based on ground-air collaboration by Zikang Zhang, Zhengda Li, Meng Yang, Jiale Cui, Yang Shao, Youchun Ding, Wanneng Yang, Wen Qiao, Peng Song

Get full text

Domain adaptation of deep neural networks for tree part segmentation using synthetic forest trees by Mitch Bryson, Ahalya Ravendran, Celine Mercier, Tancred Frickey, Sadeepa Jayathunga, Grant Pearse, Robin J.L. Hartley

“…Results of our work indicated that models trained on our synthetic data pipeline were competitive with models trained on real data, in particular when real data came from non-target sites, and our unsupervised domain adaptation method further improved performance. …”
Get full text

Machine Learning-Powered Smart Healthcare Systems in the Era of Big Data: Applications, Diagnostic Insights, Challenges, and Ethical Implications by Sita Rani, Raman Kumar, B. S. Panda, Rajender Kumar, Nafaa Farhan Muften, Mayada Ahmed Abass, Jasmina Lozanović

“…It bridges the gap between ML algorithms and smart diagnostics, offering critical perspectives for clinicians, data scientists, and policymakers.…”
Get full text

Advancements in deep learning for early diagnosis of Alzheimer’s disease using multimodal neuroimaging: challenges and future directions by Muhammad Liaquat Raza, Muhammad Liaquat Raza, Muhammad Liaquat Raza, Syed Tawassul Hassan, Subia Jamil, Noorulain Hyder, Kinza Batool, Sajidah Walji, Muhammad Khizar Abbas

“…Recent advancements in deep learning algorithms applied to multimodal brain imaging offer promising solutions for improving diagnostic accuracy and predicting disease progression.MethodThis narrative review synthesizes current literature on deep learning applications in Alzheimer’s disease diagnosis using multimodal neuroimaging. …”
Get full text

Association of emergency department nurse and physician work environment agreement on clinician job and patient outcomes by K. Jane Muir, Anish K. Agarwal, Daniela Golinelli, Karen B. Lasater, James Ballinghoff, Colleen Mattioni, Matthew D. McHugh, Linda H. Aiken, United States Clinician Wellbeing Study Consortium

“…Hospital-level linear regression models determined the relationship between hospital profiles and clinician job and patient outcomes. …”
Get full text

Intellectual or developmental disabilities and curative female breast cancer treatment: A population-based retrospective cohort studyLay summary by Rebecca L. Hansford, Brooke Wilson, Rebecca Griffiths, Alyson L. Mahar

“…IDD status was identified using an established algorithm. We estimated associations between IDD and surgical resection, adjuvant chemotherapy, and radiation using cause-specific hazards models in four distinct cohorts determined by stage and treatment eligibility. …”
Get full text

Diagnosis of Benign and Malignant Newly Developed Nodules on the Surgical Side After Breast Cancer Surgery Based on Machine Learning by Zhixiang Wang, Qingqing Li, Yiran Wang, Linxue Qian, Xiangdong Hu, Dong Liu

“…It can assist doctors in developing more effective treatment plans, improving patient outcomes. Future studies should expand sample sizes, include multicenter data, and explore advanced algorithms to further enhance diagnostic performance.…”
Get full text

Carbon Sequestration Strategies in Regenerative Agricultural Systems by Leveraging Wireless Sensor Networks for Precision Carbon Management by Al-Jawahry Hassan M., AI_Sadi Hafidh l., Rajasekhar Boddu

“…In this study, a total approach towards optimizing carbon sequestration strategies using advanced technologies like Wireless Sensor Network (WSN), Digital Twin model, and predictive algorithms like Random Forest Regression and gradient boosting are presented. …”
Get full text

Research on new energy power plant network traffic anomaly detection method based on EMD by Danni Liu, Shengda Wang, YutongLi, Ji Du, Jia Li

“…Abstract Overview As Photovoltaic (PV) systems connect into the grid and depend on digital technology, risks develop from obsolete components, insufficient security measures, and insecure access points. Objectives Improve the safety and dependability of the main data communication network by conducting research on Proactive Coordinated Fault-Tolerant Federation (PCFT) security structure, building an early warning simulation to handle power data interactions network abnormalities, studying algorithms and technologies for abnormal traffic control, and effectively managing abnormal network traffic like DDoS, network scanning, along with surge traffic; Improve the capability of the SLA hierarchical service, enhance the service quality of the core services executed through the backbone network, as well as strengthen the security capability of the access system for the new energy power plant’s communication network by combing and analyzing the traffic of the main network of the current information communication network. …”
Get full text

DMSA-Net: a deformable multiscale adaptive classroom behavior recognition network by Chunyu Dong, Jing Liu, Shenglong Xie

“…To improve the network’s capacity to model minute behavioral phenomena, the backbone section introduces a deformable self-attention dattention module, dynamically modifying the receptive field’s geometry to enhance the model’s concentration on the region of interest. …”
Get full text

Coral reef detection using ICESat-2 and machine learning by Gabrielle A. Trudeau, Kim Lowell, Jennifer A. Dijkstra

“…Future work should refine algorithms and incorporate additional environmental variables to improve model performance across various reef types.…”
Get full text

PCES-YOLO: High-Precision PCB Detection via Pre-Convolution Receptive Field Enhancement and Geometry-Perception Feature Fusion by Heqi Yang, Junming Dong, Cancan Wang, Zhida Lian, Hui Chang

“…When compared to YOLOv11s, it increases mAP50 by 1.0% and mAP50–95 by 5.6% while also significantly reducing the model parameters. The performance of PCES-YOLO is also evaluated against mainstream object detection algorithms, including Faster R-CNN, SSD, YOLOv8n, etc. …”
Get full text