Anew Chinese chestnut cultivar Yanli 3 by ZHANG Xinfang, FAN Liying, ZHANG Shuhang, LI Ying, GUO Yan, LIU Jinyu, WANG Guangpeng

“…According to “Descriptors and Data Standard for Chestnut”, the resistance of Yanli 3 to red mites is stronger than that of the control variety Yanshanduanzhi. …”
Get full text

Conditional Generation of Building Bubble Diagrams Based on Stochastic Differential Equations by Zhiwen Wei, Joonki Lee, Hyeongmo Gu, Seungyeon Choo, Jaeil Kim

“…The forward SDE progressively injects noise into the data, transforming it into a tractable prior distribution, while the reverse SDE removes the noise to reconstruct the original data distribution. …”
Get full text

FedNDA: Enhancing Federated Learning with Noisy Client Detection and Robust Aggregation by Tuan Dung Kieu, Charles Fonbonne, Trung-Kien Tran, Thi-Lan Le, Hai Vu, Huu-Thanh Nguyen, Thanh-Hai Tran

“… Federated Learning is a novel decentralized methodology that enables multiple clients to collaboratively train a global model while preserving the privacy of their local data. …”
Get full text

A New Collaborative Filtering Recommendation Method Based on Transductive SVM and Active Learning by Xibin Wang, Zhenyu Dai, Hui Li, Jianfeng Yang

“…Firstly, a “maximum-minimum segmentation” of version space-based AL strategy is developed to choose the most informative unlabeled samples for human annotation; it aims to choose the least data which is enough to train a high-quality model. …”
Get full text

Multimodal multi-instance evidence fusion neural networks for cancer survival prediction by Hui Luo, Jiashuang Huang, Hengrong Ju, Tianyi Zhou, Weiping Ding

“…We then dynamically adjust the weights of the class probability distribution after multimodal fusion based on the estimated evidence from the fused multimodal data to achieve trusted survival prediction. …”
Get full text

DKA Prediction in Children Using Artificial Intelligence: Improved Emergency Care by Arifa Parveen, Mohsina Riffat, Sarang Shaikh

“…Additionally, we also split the above dataset into two sets (i.e., train, and test) with an overall distribution of 70%, and 30% for the train (3500 data points), and test (1500 data points); respectively. …”
Get full text

SPEMix: a lightweight method via superclass pseudo-label and efficient mixup for echocardiogram view classification by Shizhou Ma, Yifeng Zhang, Delong Li, Yixin Sun, Zhaowen Qiu, Lei Wei, Suyu Dong

“…The supervised echocardiogram view classification methods have worse generalization performance due to the difficulty of labeling echocardiographic images, while the semi-supervised echocardiogram view classification can achieve acceptable results via a little labeled data. However, the current semi-supervised echocardiogram view classification faces challenges of declining accuracy due to out-of-distribution data and is constrained by complex model structures in clinical application.MethodsTo deal with the above challenges, we proposed a novel open-set semi-supervised method for echocardiogram view classification, SPEMix, which can improve performance and generalization by leveraging out-of-distribution unlabeled data. …”
Get full text

FORCINN: First‐Order Reversal Curve Inversion of Magnetite Using Neural Networks by Zhaowen Pei, Wyn Williams, Lesleis Nagy, Greig A. Paterson, Roberto Moreno, Adrian R. Muxworthy, Liao Chang

“…Here, we propose a neural network algorithm (FORCINN) to invert the size and aspect ratio distribution from measured FORC data. We trained and tested the FORCINN model using a data set of synthetic numerical FORCs for single magnetite grains with various grain‐sizes (45–400 nm) and aspect ratios (oblate and prolate grains). …”
Get full text

JEWS OF THE TEREK REGION ACCORDING TO THE ALL-RUSSIA CENSUS OF POPULATION OF THE RUSSIAN EMPIRE OF 1897 by M. I. BARAZBIEV, Yu. I. MURZAKHANOV

“…However, a cross-analysis of data on the distribution of the population by mother tongue and religion allows obtaining fairly reliable data on the number of different ethnic groups. …”
Get full text

Building a Gender-Bias-Resistant Super Corpus as a Deep Learning Baseline for Speech Emotion Recognition by Babak Abbaschian, Adel Elmaghraby

“…While deep learning techniques have significantly advanced SER systems, their robustness concerning speaker gender and out-of-distribution data has not been thoroughly examined. Furthermore, standards for SER remain rooted in landmark papers from the 2000s, even though modern deep learning architectures can achieve comparable or superior results to the state of the art of that era. …”
Get full text

Predicting the remaining useful life of metro pantograph sliding strips using gamma processes and its implications for maintenance scheduling. by Jie Liu, Chuang Wu

“…This study proposes an adaptive, data-driven framework for predicting the remaining useful life (RUL) of these components, leveraging operational data from Chongqing Metro Line 6. …”
Get full text

Deep Learning-Based Ground-Penetrating Radar Inversion for Tree Roots in Heterogeneous Soil by Xibei Li, Xi Cheng, Yunjie Zhao, Binbin Xiang, Taihong Zhang

“…Additionally, a GPR simulation data set and a measured data set are built in this study, which were used to train inversion models and validate the effectiveness of GPR inversion methods.The introduced GPR inversion model is a pyramid convolutional network with vision transformer and edge inversion auxiliary task (PyViTENet), which combines pyramidal convolution and vision transformer to improve the diversity and accuracy of data feature extraction. …”
Get full text

Integrating vulnerability and hazard in malaria risk mapping: the elimination context of Senegal by Camille Morlighem, Chibuzor Christopher Nnanatu, Justice Moses K. Aheto, Catherine Linard

“…Furthermore, models including only vulnerability factors outperformed those including only hazard factors. However, the models trained on the 2020-21 MIS data performed poorly, achieving a median R² of 0.13 at best for the model based on hazard factors, likely due to data collection during the dry season. …”
Get full text

Quantitative Inversion of Martian Hydrous Minerals Based on LSTM-1DCNN Model by Xinbao Liu, Ming Jin, Xiangnan Liu, Zhiming Yang, Zengqian Hou, Xiaozhong Ding

“…Hydrous minerals are significant indicators of the ancient aqueous environment on Mars, and orbital hyperspectral data are one of the most effective tools for obtaining information about the distribution of hydrous minerals on the Martian surface. …”
Get full text

Estimating Rainfall Erosivity in North Korea Using Automated Machine Learning: Insights into Regional Soil Erosion Risks by Jeongho Han, Seoro Lee

“…The GradientBoostingRegressor (GBR) model, optimized using the Tree-based Pipeline Optimization Tool (TPOT), was trained on South Korean data. The model’s performance was evaluated using metrics such as the root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R²), achieving high predictive accuracy across eight stations in South Korea. …”
Get full text

Simulation modelling of single nucleotide genetic polymorphisms by Николай Николаевич Яцков, Владимир Владимирович Апанасович, Василий Викторович Гринев

“…We propose an approach for the identification of single nucleotide polymorphisms (SNPs) in DNA sequences, based on the simulation modelling of sites of single nucleotides using the generation of random events according to the beta or normal distributions, the parameters of which are estimated from the available experimental data. …”
Get full text

Deep Self-Supervised Disturbance Mapping With the OPERA Sentinel-1 Radiometric Terrain Corrected SAR Backscatter Product by Harris Hardiman-Mostow, Charles Marshak, Alexander L. Handwerger

“…In this work, we utilize this new dataset to systematically analyze land surface disturbances. As labeling SAR data is often prohibitively time-consuming, we train a self-supervised vision transformer—which requires no labels to train—on OPERA RTC-S1 data to estimate a per-pixel distribution from the set of baseline imagery and assess disturbances when there is significant deviation from the modeled distribution. …”
Get full text

Petrophysical evaluation of clastic formations in boreholes with incomplete well log dataset by using joint inversion technique and machine learning algorithms by Felipe Santana-Román, Ambrosio Aquino López, Manuel Romero Salcedo (+), Raúl del Valle García, Oscar Campos Enriquez

“…To determine petrophysical parameters (i.e., volumes of laminar, structural and disperse shale) in clastic rocks from incomplete well log data we followed three approaches which are based on a hierarchical model, and on a joint inversion technique: 1) Available well log data (excluding the incomplete well log) are used to train machine learning algorithms to generate a predictive model; 2) the first step of the second approach machine learning algorithms are used to generate the missing data which are subsequently included a joint inversion; 3) in the third approach, machine learning process is used to estimate the missing data which are subsequently included in the prediction of the petrophysical properties. …”
Get full text

Multi-Scale Feature Fusion GANomaly with Dilated Neighborhood Attention for Oil and Gas Pipeline Sound Anomaly Detection by Yizhuo Zhang, Zhengfeng Sun, Shen Shi, Huiling Yu

“…Anomaly detection in oil and gas pipelines based on acoustic signals currently faces challenges, including limited anomalous samples, varying audio data distributions across different operating conditions, and interference from background noise. …”
Get full text

A personalized federated learning approach to enhance joint modeling for heterogeneous medical institutions by Hong Ye, Xiangzhou Zhang, Kang Liu, Ziyuan Liu, Weiqi Chen, Bo Liu, Eric WT Ngai, Yong Hu

“…Current clustering-based FL methods struggle to adapt to complex and diverse data distributions, negatively impacting model performance. …”
Get full text