Generalizing location-centric variations to enhance contactless human activity recognition by Fawad Khan, Syed Yaseen Shah, Jawad Ahmad, Alanoud Al Mazroa, Adnan Zahid, Muhammed Ilyas, Qammer Hussain Abbasi, Syed Aziz Shah

“…The proposed Federated Weighted Averaging for HAR (Fed-WAHAR) algorithm mitigates location-induced disparities, including heterogeneity and non-Independent and Identically Distributed (non-IID) data distributions. Fed-WAHAR employs a dynamic weighting approach based on local models' accuracy to improve global model classification accuracy and reduce convergence time effectively. …”
Get full text

Research on optimization of storage system in intelligent computing center by CAO Yuanming, LEI Ming, LIU Qin, NIU Yingxia, WU Zhenyu, PAN Jie

“…The intelligent computing center uses distributed file storage for data preprocessing and model training, distributed object storage for the acquisition of raw data and model release, and distributed block storage to provide storage for the resource management platform. …”
Get full text

Early Failure Statistics Analysis of the Line Contactor of CR400BF EMU by Miao SHA, Donghui YUAN, Yang LIU, Hesheng ZHANG, Xuyuan SI, Junyi YANG

Get full text

Fine Observation Characteristics and Causes of "9·7" Extreme Heavy Rainstorm over Pearl River Delta, China by Chen Xunlai, Xu Ting, Wang Rui, Li Yuan, Zhang Shuting, Wang Shuxin, Wang Mingjie, Chen Yuanzhao

“…On 7-8 September 2023, the Pearl River Delta experiences an extremely heavy rainstorm, known as "9·7" extreme rainstorm. Multi-source data are comprehensively utilized, including high-density automatic weather station data, sounding data, wind profiler data, Doppler radar data, high-resolution measurements from FY-4B satellite, and the fifth-generation European Centre for Medium-Range Weather Forecasts (ECMWF) atmospheric reanalysis (ERA5), to analyze the fine precipitation characteristics and causes of this case. …”
Get full text

An Improved U-Net-Based Framework for Estimating River Surface Flow Velocity by 周继威, 安国成, 王根一

“…Cross-dataset validation under natural turbulence (CDJJB) maintained MAE=0.073, demonstrating adaptability to environmental heterogeneity.The integration of adaptive label generation (bell-shaped/stepped distributions) and spatiotemporal training addressed data scarcity by leveraging sequential video dynamics. …”
Get full text

Quantifying the impact of workshops promoting microbiome data standards and data stewardship by Julia M. Kelliher, Francisca E. Rodriguez, Leah Y. D. Johnson, Simon Roux, Montana Smith, Alicia Clum, Wendi Lynch, Candace Hope Bias, Sarai S. Finks, Ishi Keenum, E. Anders Kiledal, Heng-An Lin, Reid Longley, Ryan McDonald, Thomas M. Pitot, Josué Rodríguez-Ramos, Jiaxian Shen, Daniel D. Sprockett, Joel Swift, Archana Yadav, Emiley A. Eloe-Fadrosh

“…In 2021, the National Microbiome Data Collaborative launched its Ambassador Program, which utilizes a community-learning model to annually train a cohort of early-career researchers in microbiome data stewardship best practices. …”
Get full text

Exploring feature sparsity for out-of-distribution detection by Qichao Chen, Kuan Li, Zhiyuan Chen, Tomas Maul, Jianping Yin

“…Previous work has used free energy as a score function and proposed a fine-tuning method that utilized OOD data in the training phase of the classification model, which achieves a higher performance on the OOD detection task compared with traditional methods. …”
Get full text

Robust screening of atrial fibrillation with distribution classification by Pierre-François Massiani, Lukas Haverbeck, Claas Thesing, Friedrich Solowjow, Marlo Verket, Matthias Daniel Zink, Katharina Schütt, Dirk Müller-Wieland, Nikolaus Marx, Sebastian Trimpe

“…It achieves state-of-the-art performance and unprecedented robustness on the screening problem while only leveraging one interpretable feature and little training data. We illustrate these advantages by evaluating on other data sources (cross-data-set) and through sensitivity studies. …”
Get full text

Snow Distribution Patterns Revisited: A Physics‐Based and Machine Learning Hybrid Approach to Snow Distribution Mapping in the Sub‐Arctic by R. L. Crumley, C. L. Bachand, K. E. Bennett

“…Previous studies have suggested that with years of observational data, these snow distribution patterns can be statistically integrated into a snow process modeling workflow. …”
Get full text

Reducing Head Pose Estimation Data Set Bias With Synthetic Data by Roberto Valle, Jose M. Buenaposada, Luis Baumela

“…Data set bias not only compromises the fairness, accuracy and effectiveness of trained models, but also leads to a lower performance in real-world scenarios compared to the evaluation results obtained with a specific data set. …”
Get full text

MLCRP: ML-Based GPU Cache Performance Modeling Featured With Reuse Profiles by Minjung Cho, Eui-Young Chung

“…MLCRP consists of three main stages: data preparation, training, and inference. In the data preparation stage, synthetic RP-based traces are generated from parameterized distributions to simulate diverse and non-stationary memory patterns. …”
Get full text

Method of accelerating deep learning with optimized distributed cache in containers by Kai ZHANG, Yang CHE

“…When using GPU to train deep learning models with large-scale dataset, the data loading and preprocessing stages often decrease overall performance notably.Lots of GPU computing resources are wasted on waiting for loading data from remote storage.Firstly, the methods of accelerating deep learning training with container and distributed cache were introduced.The architecture and initial optimization of such training system, which was implemented with Alluxio and Kubernetes, were introduced as well.Secondly, the task and data co-located scheduling (TDCS) and the colocated scheduling policy were elaborated.Thirdly, TDCS was implemented in Kubernetes cluster, which made the acceleration result more extensible.Finally, the result of training ResNet50 image classification model on 128 NVIDIAV100 GPU devices demonstrates that the proposed methods can bring 2 to 3 times speed up comparing with load data from remote storage directly.…”
Get full text

Environment Semantic Communication: Enabling Distributed Sensing Aided Networks by Shoaib Imran, Gouranga Charan, Ahmed Alkhateeb

“…This strategy significantly alleviates the overhead associated with the data storage and transmission of the raw images. …”
Get full text

Energy Cooperatives as an Instrument for Stimulating Distributed Renewable Energy in Poland by Katarzyna Brodzińska, Małgorzata Błażejowska, Zbigniew Brodziński, Irena Łącka, Alicja Stolarska

“…They also suggest reviewing restrictions on the area and power capacity for renewable energy distribution. Proper training for cooperative managers and network operator staff is essential. …”
Get full text

Delta-Adjust: Minimum Distance Interpolation by Ziad F. Doughan, Sari S. Itani

“…Delta-Adjust achieves this independently of the underlying data distribution, without any training steps, and without requiring explicit assumptions about global model structure.…”
Get full text

Comprehensive Dataset for Event Classification Using Distributed Acoustic Sensing (DAS) Systems by Adrian Tomasov, Pavel Zaviska, Petr Dejdar, Ondrej Klicnik, Tomas Horvath, Petr Munster

“…Abstract Distributed Acoustic Sensing (DAS) technology leverages optical fibers to detect acoustic signals over long distances, offering high-resolution data critical for applications such as seismic monitoring, structural health monitoring, and security. …”
Get full text

Optimal intrusion detection for imbalanced data using Bagging method with deep neural network optimized by flower pollination algorithm by Hussein Ridha Sayegh, Wang Dong, Bahaa Hussein Taher, Muhanad Mohammed Kadum, Ali Mansour Al-madani

Get full text

A Methodology of Real-Time Data Fusion for Localized Big Data Analytics by Sohail Jabbar, Kaleem R. Malik, Mudassar Ahmad, Omar Aldabbas, Muhammad Asif, Shehzad Khalid, Kijun Han, Syed Hassan Ahmed

“…The traditional big-data analytical approaches use data clustering as small buckets while providing distributed computation among different child nodes. …”
Get full text

SpectralEarth: Training Hyperspectral Foundation Models at Scale by Nassim Ait Ali Braham, Conrad M. Albrecht, Julien Mairal, Jocelyn Chanussot, Yi Wang, Xiao Xiang Zhu

Get full text

Canopy height and biomass distribution across the forests of Iberian Peninsula by Yang Su, Martin Schwartz, Ibrahim Fayad, Mariano García, Miguel A. Zavala, Julián Tijerín-Triviño, Julen Astigarraga, Verónica Cruz-Alonso, Siyu Liu, Xianglin Zhang, Songchao Chen, François Ritter, Nikola Besic, Alexandre d’Aspremont, Philippe Ciais

“…Here we present high-resolution remote sensing-based canopy height (10 m resolution) and above ground biomass (AGB, 50 m resolution) maps for the forests of the Iberian Peninsula from 2017 to 2021, using a deep learning framework that integrates Sentinel-1, Sentinel-2, and LiDAR data. Two UNET models were developed: one trained on Airborne Laser Scanning (ALS) data (MAE: 1.22 m), while another using Global Ecosystem Dynamics Investigation (GEDI) footprints (MAE: 3.24 m). …”
Get full text