Dynamic risk prediction in financial-production systems using temporal self-attention and adaptive autoregressive models by Xuduo Lin, Ziang Qi 

“…In financial production systems, accurate risk prediction is crucial for decision- makers. Traditional forecasting methods face certain limitations when dealing with complex time-series data and nonlinear dependencies between systems, especially under extreme market fluctuations. …”
Get full text

Predicting Rolling Element Bearings’ Deterioration Vibration Trend based on Limited Historical Data for a Desired Confidence Level using Machine Learning Algorithms by Mohammad Reza Seif, Somaye Mohammadi, Parham Rahimi, Mehdi Behzad

“…This study proceeds in three distinct phases: selecting the key characteristic for predicting its deterioration trend, identifying the feature to pinpoint the failure onset, and determining the most suitable model for forecasting future bearing vibration states. RMS has emerged as the optimal characteristic for trend prediction, while Peak and Kurtosis have been identified as effective indicators for failure onset detection. …”
Get full text

Desensitized Financial Data Generation Based on Generative Adversarial Network and Differential Privacy by Fan Zhang, Luyao Wang, Xinhong Zhang

“…NVF-DPGAN model is feasible and practical in terms of financial data enhancement and privacy protection. This method can also be generalized to other fields, such as the privacy protection of medical data.…”
Get full text

Trustworthiness of Deep Learning Under Adversarial Attacks in Power Systems by Dowens Nicolas, Kevin Orozco, Steve Mathew, Yi Wang, Wafa Elmannai, George C. Giakos

“…In power grids, DL models such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks are commonly utilized for tasks like state estimation, load forecasting, and fault detection, depending on their ability to learn complex, non-linear patterns in high-dimensional data such as voltage, current, and frequency measurements. …”
Get full text

Spatiotemporal prevalence of COVID-19 and SARS-CoV-2 variants in Africa by Li-Ping Gao, Can-Jun Zheng, Ting-Ting Tian, Alie Brima Tia, Michael K. Abdulai, Kang Xiao, Cao Chen, Dong-Lin Liang, Qi Shi, Zhi-Guo Liu, Xiao-Ping Dong, Xiao-Ping Dong

Get full text

Gut microbiota and plasma metabolites in pregnant mothers and infant atopic dermatitis: A multi-omics studyKey Message by Bingqian Du, MA.Sc, Aga Shama, BA.Sc, Yi Zhang, BA.Sc, Baolan Chen, MA.Sc, Yongqi Bu, BA.Sc, Pei-an Chen, MA.Sc, Chuzhi Lin, BA.Sc, Jie Liu, MA.Sc, Juan Zheng, MA.Sc, Zhenjun Li, MD, PhD, Qingsong Chen, PhD, Yu Sun, PhD, Xi Fu, PhD

Get full text

MobileNetV3: an efficient deep learning-based feature selection and classification technique for cardiovascular disease by B. Dhanalaxmi, B. Naveen Kumar, Yeligeti Raju, Rama Seshagiri Rao Channapragada

“…Missing data handling, outlier detection, normalization using min–max normalization methods, categorical data encoding, and transformation are all done during the pre-processing phase. …”
Get full text

The differences in microbial communities and Tick-Borne pathogens between Dermacentor marginatus and Hyalomma asiaticum collected from the Northwestern Xinjiang Uygur Autonomous Re... by Like Duan, Xiaona Yang, Lin Zhang, Xuexia Hou, Lijuan He, Jingwen Li, Qin Hao

Get full text

Analysis of satellite big data requirements in numerical weather prediction by Hequn YANG, Xiaofeng WANG, Yanqing GAO, Yiwen LU, Bingxin MA, Xinyao WANG

“…Multi cooperative satellites can provide multi spectral, multi temporal, multi factor, multi scale and multi-level remote sensing data, which is rich in valuable information for numerical weather prediction (NWP).In order to support earth system seamless fine gridded forecasting service in the future, the application status of satellite observation big data was discussed for numerical weather prediction from the aspects of detection variables, time density, spatial coverage, horizontal and vertical resolution, as well as accuracy and timeliness.At the same time, in order to make satellite big data be highly tolerant with NWP, the challenges and prospects were summarized, such as multi-satellite integrated and consistent processing, all-weather, coupled data assimilation methods, deep integration with artificial intelligence, and interaction between satellite observation and prediction.…”
Get full text

Predicting the heat capacity of strontium-praseodymium oxysilicate SrPr4(SiO4)3O using machine learning, deep learning, and hybrid models by Amir Hossein Sheikhshoaei, Ali Khoshsima, Davood Zabihzadeh

“…Machine learning (ML) offers a potent solution for forecasting diverse processes using both data-driven and knowledge-based methods. …”
Get full text

Road safety improvement in road traffic participant – vehicle – road – external environment system by E. V. Kurakina, V. A. Sklyarova

“…The use of an integrated approach instead of disparate single actions will allow achieving the tasks set for the state to reduce the accident rate on the country’s roads.Materials and methods. Analytical methods based on analysis of links, flows, temporary analysis of events, methods of road traffic safety assessment based on detection of safety and accident factors, detection of accident concentration places, methods of probability theory and processing of research results, software-computing methods of information technologies.Results. …”
Get full text

A Comparative Analysis of the Effectiveness of Multiple Models for Predicting Heart Failure using Data Mining by Ahmed Sami Jaddoa, Juliet Kadum, Amaal Kadum

“…In order to preserve lives, early detection regarding such disease is essential. One of the quickest, practical, and affordable methods of disease detection is Data Mining DM, an artificial intelligence AI technology. …”
Get full text

A crosslinked eutectogel for ultrasensitive pressure and temperature monitoring from nostril airflow by Tao Liu, Qinan Wu, Huansheng Liu, Xiyang Zhao, Xin Yi, Jing Liu, Zhenzhen Nong, Bingpu Zhou, Qingwen Wang, Zhenzhen Liu

“…However, the developed methods only rely on single stimulus sensing for nostril airflow, which is extremely susceptible to interference in the complex environment, and severely affects the accuracy of detection results. …”
Get full text

Comparison of the quality of logistic regression models and a classification tree in predicting hospital mortality in elderly patients with non-ST-elevation myocardial infarction by K. G. Pereverzeva, S. S. Yakushin, N. N. Peregudova, M. V. Mishutina

“…Using the CHAID (Chi Squared Automatic Interaction Detection) method to develop a classification tree for predicting hospital mortality in patients with non-ST-elevation myocardial infarction (non-STEMI) aged 75 years and older and compare the quality of the constructed model with the logistic regression model.Material and methods. …”
Get full text

Evaluation of innovative technology market potential on the basis of technology audit by Oleksandra Kosenko, Victoriia Cherepanova, Iryna Dolyna, Viktoriia Matrosova, Olena Kolotiuk

“…This mechanism is built on structure evaluation table of technology market potential level detection as an object of commercialization. To ensure the efficiency of practical effect of the mechanism proposed, the authors systematized and completed methods of functional analysis and scanning of market environment for the purpose of qualitative comprehensive evaluation and innovative technology market potential forecasting.Introduction of the proposed evaluation method for technology market potential will result in the improvement of efficiency of enterprise innovation activity due to more rational distribution of available resources and immediate financing of developments with greater market potential.…”
Get full text

Automated Eddy Identification and Tracking in the Northwest Pacific Based on Conventional Altimeter and SWOT Data by Lan Zhang, Cheinway Hwang, Han-Yang Liu, Emmy T. Y. Chang, Daocheng Yu

Get full text

Application of capsule networks based on reparameterized heterogeneous convolution in multi-scale heterogeneous environment matrix in predictive modeling of interdisciplinary compl... by Shuya Liu, Xiaoli Zhang

“…Abstract Predictive modeling of complex systems frequently encounters inadequate processing capabilities for multi-scale heterogeneous data, as conventional methods grapple with the effective integration of such data. …”
Get full text

Chemometric and computational modeling of polysaccharide coated drugs for colonic drug delivery by Ahmad Khaleel AlOmari, Khaled Almansour

“…For ML modeling, we examined the predictive accuracy of three machine learning models—Elastic Net (EN), Group Ridge Regression (GRR), and Multilayer Perceptron (MLP)—for forecasting the release behavior of samples. The dataset, consisting of 155 data points with over 1500 spectral features, underwent preprocessing involving normalization, Principal Component Analysis (PCA) for dimensionality reduction, and outlier detection using Cook’s Distance. …”
Get full text

The implications of mutations in multiple genes associated with ethambutol resistance among multidrug-resistant tuberculosis isolates from China by Ma-chao Li, Wei Wang, Tong-yang Xiao, Hai-can Liu, Shi-qiang Lin, Hao Hang, Xiang-long Bo, Xiao-tian Nan, Cheng Qian, Xue-ting Fan, Xiu-qin Zhao, Gui-lian Li, Kang-Lin Wan, Li-li Zhao

Get full text

Artificial intelligence model predicts M2 macrophage levels and HCC prognosis with only globally labeled pathological images by Huiyuan Tian, Yongshao Tian, Dujuan Li, Minfan Zhao, Qiankun Luo, Lingfei Kong, Tao Qin

“…Background and aimsThe levels of M2 macrophages are significantly associated with the prognosis of hepatocellular carcinoma (HCC), however, current detection methods in clinical settings remain challenging. …”
Get full text