The role of artificial intelligence in promoting health and developing preventive strategies for diabetes by Ameneh Marzban

“…For instance, machine learning models can evaluate patient records, lifestyle factors, and genetic information to deliver precise risk assessments and personalized recommendations. …”
Get full text

A deep neural network framework for estimating coastal salinity from SMAP brightness temperature data by Yidi Wei, Qing Xu, Qing Xu, Xiaobin Yin, Xiaobin Yin, Yan Li, Yan Li, Kaiguo Fan

“…The framework leverages machine learning interpretability tools (Shapley Additive Explanations, SHAP) to optimize input feature selection and employs a grid search strategy for hyperparameter tuning.Results and discussionSystematic validation against independent in-situ measurements demonstrates that the baseline DNN model constructed for the entire region and time period outperforms conventional algorithms including K-Nearest Neighbors, Random Forest, and XGBoost and the standard SMAP SSS product, achieving a reduction of 36.0%, 33.4%, 40.1%, and 23.2%, respectively in root mean square error (RMSE). …”
Get full text

A Framework for Segmentation and Classification of Cervical Cells Under Long-tailed Distribution by YANG Xiao na, LI Chao wei, SHAO Hui li, HE Yong jun

“…This framework first performs cell nucleus segmentation, uses U-Net as the base model for layer reduction, adds AG module, and uses ACBlock module instead of traditional standard convolutional blocks; then uses ResNeSt for coarse classification of segmented data, fuses manual features extracted based on physicians ′ experience and machine features extracted by ResNeSt network for fine classification , and uses active learning iteratively to expand the cervical cell categories and fuse the ACBlock module in the BBN model to process the long-tail data; finally, the diagnostic indexes of abnormal cells are refined and abnormal cells are screened according to the TBS diagnostic criteria and the physician ′s diagnostic experience. …”
Get full text

Evaluating Feasibility of Pose Detection with Image Rotation for Monitoring Elderly People at Home by Sinan Chen, Masahide Nakamura

“…In this study, abnormal behaviors in in-home elderly individuals were detected using high-precision pose detection technologies, such as the MoveNet model, based on machine learning. However, there was a discrepancy in pose detection accuracy between the standing and lying positions. …”
Get full text

An upgraded high-precision gridded precipitation dataset for the Chinese mainland considering spatial autocorrelation and covariates by J. Hu, C. Miao, J. Su, Q. Zhang, J. Gou, J. Gou, Q. Sun, Q. Sun

Get full text

Soft-Computing Analysis and Prediction of the Mechanical Properties of High-Volume Fly-Ash Concrete Containing Plastic Waste and Graphene Nanoplatelets by Musa Adamu, Yasser E. Ibrahim, Mahmud M. Jibril

“…Hence, this study employed two machine-learning (ML) models, namely Gaussian Process Regression (GPR) and Elman Neural Network (ELNN), to forecast the mechanical properties of HVFAC. …”
Get full text

Automotive DNN-Based Object Detection in the Presence of Lens Obstruction and Video Compression by Gabriele Baris, Boda Li, Pak Hung Chan, Carlo Alberto Avizzano, Valentina Donzella

“…Recent advances in sensing, processing, machine learning, and communication technologies are accelerating assisted and automated functions development for commercial vehicles. …”
Get full text

A comprehensive review of bibliometric and methodological approaches in flood mitigation studies: Current trends and future directions by Funmilayo Ebun Rotimi, Roohollah Kalatehjari, Taofeeq Durojaye Moshood, George Dokyi

“…Furthermore, it highlights the growing diversity of approaches, with increasing interest in machine learning algorithms and combined methods. …”
Get full text

Revolutionizing Clear-Sky Humidity Profile Retrieval with Multi-Angle-Aware Networks for Ground-Based Microwave Radiometers by Yinshan Yang, Zhanqing Li, Jianping Guo, Yuying Wang, Hao Wu, Yi Shang, Ye Wang, Langfeng Zhu, Xing Yan

“…Based on the 7-year (2018–2024) in situ measurements from Beijing, Nanjing, and Shanghai, validation results reveal that AngleNet achieves substantial improvements, with an average R2 of 0.71 and a root mean square error (RMSE) of 10.39%, surpassing conventional models such as LGBM (light gradient boosting machine) and RF (random forest) by over 10% in both metrics, and demonstrating a remarkable 41% increase in R2 and a 10% reduction in RMSE compared to the previous BRNN method (batch normalization and robust neural network). …”
Get full text

The Relationship Between Surface Meteorological Variables and Air Pollutants in Simulated Temperature Increase Scenarios in a Medium-Sized Industrial City by Ronan Adler Tavella, Daniele Feijó das Neves, Gustavo de Oliveira Silveira, Gabriella Mello Gomes Vieira de Azevedo, Rodrigo de Lima Brum, Alicia da Silva Bonifácio, Ricardo Arend Machado, Letícia Willrich Brum, Romina Buffarini, Diana Francisca Adamatti, Flavio Manoel Rodrigues da Silva Júnior

“…This study utilized five years of daily meteorological data (from 1 January 2019 to 31 December 2023) to model atmospheric conditions and two years of daily air pollutant data (from 21 December 2021 to 20 December 2023) to simulate how pollutant levels would respond to annual temperature increases of 1 °C and 2 °C, employing a Support Vector Machine, a supervised machine learning algorithm. …”
Get full text

Research on Partial Least Squares Method Based on Deep Confidence Network in Traditional Chinese Medicine by Wang-ping Xiong, Tian-ci Li, Qing-xia Zeng, Jian-qiang Du, Bin Nie, Chih-Cheng Chen, Xian Zhou

“…This method mainly uses the deep learning model to extract the upper-level features of the original data, putting the extracted features into the partial least squares model for multiple linear regression and evading the problem that selects the number of principal components, continuously adjusting the model parameters until satisfied well-pleased accuracy condition. …”
Get full text

Pretrained E(3)-equivariant message-passing neural networks with multi-level representations for organic molecule spectra prediction by Yuzhi Xu, Daqian Bian, Cheng-Wei Ju, Fanyu Zhao, Pujun Xie, Yuanqing Wang, Wei Hu, Zhenrong Sun, John Z. H. Zhang, Tong Zhu

“…Compared to state-of-the-art machine learning models, EnviroDetaNet excels in various predictive tasks and maintains high accuracy even with a 50% reduction in training data, demonstrating strong generalization capabilities. …”
Get full text

Research on the Maximum Regenerative Energy Commutation Control Strategy of a Dual-Mode Synergistic Energy Recovery Pump-Controlled Grinder by Bo Yu, Gexin Chen, Keyi Liu, Guishan Yan, Yaou Zhang, Yinping Liu

“…Machine learning models were compared for predicting the peak time of total recovered energy, with a neural network (NN) demonstrating superior accuracy (R² ≈ 0.99997). …”
Get full text

Genome-wide DNA methylation patterns in Daphnia magna are not significantly associated with age by Ruoshui Liu, Marco Morselli, Lev Y. Yampolsky, Leonid Peshkin, Matteo Pellegrini

“…Our results showed no significant global differences in DNA methylation levels between young, mature, and old individuals, nor any age-related clustering in dimensionality reduction analyses. Attempts to construct an epigenetic clock using machine learning models did not yield accurate age predictions, likely due to the overall low DNA methylation levels and lack of robust age-associated methylation changes. …”
Get full text

Review on atomistic and quantum mechanical simulation approaches in chemical mechanical planarization by Seokgyu Ryu, Murali Ramu, Patrick Joohyun Kim, Junghyun Choi, Kangchun Lee, Jihoon Seo

“…Future research directions include development of machine learning-accelerated simulations, integration of multiphysics models connecting molecular-scale phenomena to wafer-scale uniformity, and predictive frameworks for novel slurry chemistries. …”
Get full text

Characteristics and mechanisms of soil salinization in humid climate areas by Chunrui Wu, Xinqiang Du, Bo Meng, Hui Guo

“…Study region: The Sanjiang Plain, China Study focus: Using 509 field-collected soil samples and multi-source remote sensing data (Landsat and Sentinel-2) as model inputs, among several machine learning methods tested, the XGBoost model was identified as the most effective and was used to construct a soil salinization inversion model, revealing the spatiotemporal evolution of soil salinization from 1992 to 2022. …”
Get full text

Human-Centric IoT-Driven Digital Twins in Predictive Maintenance for Optimizing Industry 5.0 by Özlem Sabuncu, Bülent Bilgehan

“…The model was further compared with the PSO algorithm, demonstrating its superiority with a 7.5% reduction in total maintenance cost and a 6.3% decrease in total downtime. …”
Get full text

Application of artificial intelligence techniques for the profiling of visitors to tourist destinations by Juan Schrader, Lloy Pinedo, Franz Vargas, Karla Martell, José Seijas-Díaz, Roger Rengifo-Amasifen, Rosa Cueto-Orbe, Cinthya Torres-Silva

“…The aim of this study was to characterize tourists using machine learning techniques in order to identify distinct segments that can inform planning and promotional strategies for the Alto Amazonas destination. …”
Get full text

Prediction of long-term recurrence-free and overall survival in early-onset colorectal cancer: the ENCORE multi-centre study by Alessandro Mannucci, Goretti Hernández, Hiroyuki Uetake, Yasuhide Yamada, Francesc Balaguer, Hideo Baba, Tianhui Chen, Jinfei Chen, C. Richard Boland, Giulia Martina Cavestro, Enrique Quintero, Ajay Goel

“…We then trained and independently validated a machine learning model (XGBoost) to predict 5-year recurrence-free and overall survival (RFS and OS) of patients with stage I-III EOCRC. …”
Get full text

Potato leaves disease classification based on generalized Jones polynomials image features by Ala’a R. Al-Shamasneh

“…In order to diagnose potato diseases more accurately and quickly using a machine learning model, this study uses a new feature extraction method based on GJPs image features. …”
Get full text