The impact of fractional cover distribution in training samples on the accuracy of fractional cover estimation: a model-based evaluation by Rujia Wang, Chen Shi

“…In machine learning-based fractional cover estimation, the fractional cover distribution in training samples critically influences model construction and, consequently the accuracy of the estimations. …”
Get full text

Estimating Train Choices of Rail Transit Passengers with Real Timetable and Automatic Fare Collection Data by Wei Zhu, Wei Wang, Zhaodong Huang

“…Then, an integrated framework for estimating individual passenger’s train choices is developed through a data-driven approach. …”
Get full text

Technical, legal, and ethical challenges of generative artificial intelligence: an analysis of the governance of training data and copyrights by Marcelo Pasetti, James William Santos, Nicholas Kluge Corrêa, Nythamar de Oliveira, Camila Palhares Barbosa

“…Abstract This article examines the legal, technical, and ethical challenges of generative AI, focusing on the governance of training data and copyright compliance. It addresses the growing tension between AI development and the rights of content creators, particularly regarding the unauthorized use of copyrighted material for model training. …”
Get full text

Constraint Learning-based Optimal Power Dispatch for Active Distribution Networks with Extremely Imbalanced Data by Yonghua Song, Ge Chen, Hongcai Zhang

Get full text

Synthetic fibrosis distributions for data augmentation in predicting atrial fibrillation ablation outcomes: an in silico study by Alexander M. Zolotarev, Alexander M. Zolotarev, Kiane Johnson, Kiane Johnson, Yusuf Mohammad, Omnia Alwazzan, Omnia Alwazzan, Gregory Slabaugh, Gregory Slabaugh, Caroline H. Roney, Caroline H. Roney

“…IntroductionCardiac fibrosis influences atrial fibrillation (AF) progression and ablation outcomes, with late gadolinium enhancement (LGE) MRI providing a non-invasive tool to measure fibrosis distributions. While deep learning (DL) has shown promise in predicting ablation success, training such pipelines is limited by the availability of real patient data.MethodsIn this study, we generated synthetic fibrosis distributions using a denoising diffusion probabilistic model trained on a collection of 100 real LGE-MRI distributions. …”
Get full text

Anomaly Detection in Spatiotemporal Data from Fiber Optic Distributed Temperature Sensing for Outdoor Fire Monitoring by Haitao Bian, Xiaohan Luo, Zhichao Zhu, Xiaowei Zang, Yu Tian

“…Results showed that, compared to AE and VAE models handling spatial or temporal data, the CNN-AE demonstrated superior anomaly detection performance and strong robustness when applied to spatiotemporal data. …”
Get full text

Large-Scale Model Meets Federated Learning: A Hierarchical Hybrid Distributed Training Mechanism for Intelligent Intersection Large-Scale Model by Chang Liu, Shaoyong Guo, Fangfang Dang, Xuesong Qiu, Sujie Shao

“…The traditional cloud-based training method incurs a significant amount of computational and storage overhead, and there is a risk of data leakage. …”
Get full text

Personalized Federated Learning with Progressive Local Training Strategy and Lightweight Classifier by Jianhao Liu, Wenjuan Gong, Ziyi Fang, Jordi Gonzàlez, Joel Rodrigues

“…Personalized federated learning (pFL), a specialized branch of FL, seeks to address this issue by tailoring models to the unique data distributions of individual clients. Despite its potential, current pFL frameworks face critical limitations, particularly in handling client training discontinuity. …”
Get full text

The snow must go on: how German cross-country skiers maintained training and performance in the face of COVID-19 lockdowns by H. Kock, H. Kock, A. Schürer, C. A. Staunton, C. A. Staunton, Helen G. Hanstock

“…BackgroundThe Covid-19 pandemic in 2020 led to disruption of sporting events, with athletes obliged to comply with national lockdown restrictions.PurposeTo investigate the effect of the Covid-19 pandemic restrictions on national-team XC skiers' annual and weekly training distribution from training diaries, results from submaximal and maximal physiological roller ski tests, and competition results from the International Ski and Snowboard Federation (FIS) world cup.MethodsAnnual and weekly training type (specific, non-specific, strength, other) and intensity distribution (TID) data were collected for 12 German XC-skiers (Tier 4/5; BM: 67 ± 7 kg; age 26 ± 3 years; 6♀: V̇O2max 61.3 ± 3.4 ml · kg · min−1; 6♂: V̇O2max 72.5 ± 6.2 ml · kg · min−1). …”
Get full text

A Data-Driven State Estimation Based on Sample Migration for Low-Observable Distribution Networks by Hao Jiao, Chen Wu, Lei Wei, Jinming Chen, Yang Xu, Manyun Huang

“…The state estimation model is trained using historical measurement data from distribution networks with high observability. …”
Get full text

Leveraging Gradient Noise for Detection and Filtering of Byzantine Clients by Latifa Errami, Vyacheslav Kungurtsev, El Houcine Bergou

“…Distributed Learning enables multiple clients to collaboratively train large models on private, decentralized data. …”
Get full text

Spatial distribution prediction of pore pressure based on Mamba model by Xingye Liu, Xingye Liu, Bing Liu, Wenyue Wu, Qian Wang, Yuwei Liu

“…Initially, the deep learning model is trained and optimized by collecting and analyzing well-logging data, including key parameters such as acoustic time difference and density. …”
Get full text

Prediction Model for the Environmental Noise Distribution of High-Speed Maglev Trains Using a Segmented Line Source Approach by Shiquan Cheng, Jianmin Ge, Longhua Ju, Yuhao Chen

Get full text

Revolutionizing healthcare data analytics with federated learning: A comprehensive survey of applications, systems, and future directions by Nisha Thorakkattu Madathil, Fida K. Dankar, Marton Gergely, Abdelkader Nasreddine Belkacem, Saed Alrabaee

“…Federated learning (FL)–a distributed machine learning that offers collaborative training of global models across multiple clients. …”
Get full text

Voltage Control for Distribution Networks Based on Large Language Model-Assisted Deep Reinforcement Learning by Limei Yan, Chongyang Cheng

“…Furthermore, existing deep reinforcement learning (DRL) methods often rely on extensive real-world operational data for agent training. Yet, the lack of diversity in the collected data can significantly limit the generalization ability of agents under varying operating conditions. …”
Get full text

STPam: Software for Intelligently Analyzing and Mining Spatiotemporal Processes Based on Multi-Source Big Data by Rongjun Xiong, Zeqiang Chen, Huiwen Pan, Dongyang Liu, Aiguo Sun, Nengcheng Chen

“…It finds applications in various fields such as natural disaster evolution, environmental pollution, and human behavior prediction. However, training spatiotemporal models based on big data is time-consuming, and the traditional physical models and static objects used in existing geographic data analysis software have limitations in mining efficiency and simulation accuracy for dynamic spatiotemporal processes. …”
Get full text

Random Matrix Theory Predictions of Dominant Mode Rejection SINR Loss due to Signal in the Training Data by Christopher C. Hulbert, Kathleen E. Wage

“…This work leverages recent random matrix theory (RMT) results to develop DMR performance predictions under the assumption that the desired signal is contained in the training data. Using white noise gain and interference suppression predictions, the paper derives a lower bound on DMR’s average SINR loss and confirms its accuracy using Monte Carlo simulations. …”
Get full text

Fusing Multisource A-Train Satellites and Reanalysis Data for a Comprehensive Deep Convective System Dataset by Xiaoyu Hu, Lang Zhang, Jinming Ge, Qingyu Mu, Meihua Wang, Bochun Liu, Jiajing Du, Zihang Han, Leyi Wang, Hui Wang, Ruilin Zhou

“…Deep convective systems (DCSs) play a crucial role in global water cycles, energy distribution, and extreme weather events. This study aims to enhance the understanding of DCSs by creating a comprehensive dataset through the fusion of multisource A-Train satellite observations and reanalysis data. …”
Get full text

Improved Distributed Backdoor Attacks in Federated Learning by Density-Adaptive Data Poisoning and Projection-Based Gradient Updating by Jian Wang, Hong Shen, Wei Ke, Xue Hua Liu

“…While federated learning enables collaborative model training with preserved data locality, it remains vulnerable to evolving backdoor attacks that exploit its distributed architecture. …”
Get full text

Drivers of the Integration of Virtual Reality into Construction Safety Training in Ghana by Hutton Addy, Clinton Aigbavboa, Simon Ofori Ametepey, Rexford Henaku Aboagye, Wellington Didibhuku Thwala

Get full text