Classification of Structural and Functional Development Stage of Cardiomyocytes Using Machine Learning Techniques by V. R. Bondarev, K. O. Ivanko, N. G. Ivanushkina

“…Final accuracy of the model for defining the cardiomyocytes maturation stage achieved 77%. …”
Get full text

Intrusion Detection System Framework for SDN-Based IoT Networks Using Deep Learning Approaches With XAI-Based Feature Selection Techniques and Domain-Constrained Features by Manlaibaatar Tserenkhuu, Md Delwar Hossain, Yuzo Taenaka, Youki Kadobayashi

“…Randomly selecting hyperparameters and using datasets with irrelevant features can negatively affect model performance and computational complexity. This study proposes an IDS framework to detect various cyberattacks in SDN-based IoT networks utilizing three deep learning algorithms that incorporate hyperparameter tuning and the feature selection process based on explainable artificial intelligence (XAI), which uses domain-constrained features to improve performance and reduce computational complexity. …”
Get full text

Partitioning variability in animal behavioral videos using semi-supervised variational autoencoders. by Matthew R Whiteway, Dan Biderman, Yoni Friedman, Mario Dipoppa, E Kelly Buchanan, Anqi Wu, John Zhou, Niccolò Bonacchi, Nathaniel J Miska, Jean-Paul Noel, Erica Rodriguez, Michael Schartner, Karolina Socha, Anne E Urai, C Daniel Salzman, International Brain Laboratory, John P Cunningham, Liam Paninski

“…We also show how the behavioral features produced by our model improve the precision and interpretation of these downstream analyses compared to using the outputs of either fully supervised or fully unsupervised methods alone.…”
Get full text

Machine learning-based prediction of carotid intima–media thickness progression: a three-year prospective cohort study by An Zhou, Kui Chen, Kui Chen, Yonghui Wei, Qu Ye, Qu Ye, Yuanming Xiao, Rong Shi, Jiangang Wang, Wei-Dong Li

“…After Platt scaling, the calibration improved significantly across all the models. Decision curve analysis revealed a positive net benefit across a wide threshold range (0.01–0.5). …”
Get full text

Efficient structure learning of gene regulatory networks with Bayesian active learning by Dániel Sándor, Péter Antal

“…Our results demonstrate that integrating active learning into structure learning algorithms can significantly improve performance, offering a scalable and effective approach for gene regulatory network discovery.…”
Get full text

Identification of Gingival Inflammation Surface Image Features Using Intraoral Scanning and Deep Learning by Wei Li, Linlin Li, Wenchong Xu, Yuting Guo, Min Xu, Shengyuan Huang, Dong Dai, Chang Lu, Shuai Li, Jiang Lin

“…Results: The GC-U-Net model showed high recognition accuracy, with a Dice of 77.8%, an IoU of 65.4%, and a PA of 93.7%. …”
Get full text

Spatial Semantic Expression of Terrain Viewshed: A Data Mining Method by Cheng Zhang, Yiwen Wang, Haozhe Cheng, Wanfeng Dou

“…This paper proposes a model to express topographical viewshed spatial relationships. …”
Get full text

Approximate Synthesis of Н_∞ – Controllers in Nonlinear Dynamic Systems over a Semi-Infinite Time Period by A. V. Panteleev, A. A. Yakovleva

“…Current research is aimed at improving approaches to the synthesis of controllers covering both linear and nonlinear dynamic systems. …”
Get full text

Research on short-term power load forecasting based on deep reinforcement learning with multiple intelligences by Tianyun Luo, Dunlin Zhu, Jinming Liu, Sheng Yang, Jinglong He, Yuan Fu

“…In this paper, we analyze the multi-intelligence application architecture in power load forecasting, and analyze the function of each intelligent unit applied to short-term power load forecasting; based on clarifying the interaction relationship of each intelligent unit in short-term power load forecasting, we model short-term power load forecasting as a distributed and partially observable Markov decision-making process, which is suitable for multi-intelligence deep reinforcement learning; based on the MATD3 algorithm, a centralized training-distributed execution framework is used to train multiple intelligences within the model to achieve short-term power load forecasting. …”
Get full text

An Analysis of the Vocational-Educational Problematics for Substantiating Production Specialist Competencies by V. E. Steinberg, L. V. Vakhidova, E. M. Gabitova

“…We present a recommendation for the organisational and content-based improvement of specialist education in terms of key SVE tasks and factors. …”
Get full text

Geoinformation monitoring of the educational risk in educational institutions of higher education by Aleksandr N. Kolesenkov, Dmitry S. Zhuravlyov

“…The use of geoinformation technologies will ensure the integration of attributive and space-time data, taking into account geographical reference to the cartographic basis from the divisions of educational institutions, will allow quickly modeling the processes and evaluating the implementation of the educational programs.A mathematical model, a method and an algorithm for assessing the effectiveness of the implementation of educational programs in educational institutions have been developed. …”
Get full text

Attention-Based Hypergraph Neural Network: A Personalized Recommendation by Peihua Xu, Maoyuan Zhang

“…To address the limitations of existing studies in multimodal heterogeneous data fusion and high-order relationship modeling, this research proposes a Heterogeneous Hypergraph and Attention-based Online Course Recommendation (HHAOCR) algorithm. …”
Get full text

ADAPTIVE VISION AI by V. Vodyanitskyi, V. Yuskovych-Zhukovska

“…Therefore, the algorithm must be trained. The paper considers models that are trained on a high-performance computing cluster with GPU support. …”
Get full text

Recent Developments to the ANSWERS® Monte Carlo Codes MONK® and MCBEND® by Fildes Jessica, Richards Simon, Bird Adam, Cox Andrew, Fry Timothy, Hanlon David, Jones Brian, Long David, Tantillo Francesco, Wright George, Hiles Richard

“…The geometry capabilities have been enhanced by the addition of novel stochastic geometry algorithms for modelling highly disordered heterogeneous mixtures and random distributions of shapes. …”
Get full text

Coral reef detection using ICESat-2 and machine learning by Gabrielle A. Trudeau, Kim Lowell, Jennifer A. Dijkstra

“…Future work should refine algorithms and incorporate additional environmental variables to improve model performance across various reef types.…”
Get full text

Optimizing blood glucose predictions in type 1 diabetes patients using a stacking ensemble approach by Vincent B. Liu, Laura Y. Sue, Oscar Madrid Padilla, Yingnian Wu

“…Results: This study looked at three baseline algorithms for predicting blood glucose levels. Machine learning models Random Forest, LSTM, and GRU served as baselines, with MAE, RMSE, and MARD values. …”
Get full text

Unveiling nature's secrets: Deep learning for enhanced biogenic emission resolution by Antonio Giganti

“…Consequently, many existing BVOC emission maps may not be fully suitable for reliable atmospheric, climate, and forecasting model simulations.My research aims to explore and assess the use of novel AI-based algorithms to improve the spatiotemporal modeling of BVOC emissions. …”
Get full text

Research on Security Enhancement for Abnormal Content Release in Unified Audio Video Information service Systems by FENG Junhao

“…Method The content audit system using decision tree algorithms is combined with a unified audio video information service system, to construct an integrated data and multi-dimensional information security model, thereby improving the existing audio video information security management system. …”
Get full text

Grid structure optimization using slow coherency theory and holomorphic embedding method by Fei Tang, Mo Chen, Yuhan Guo, Jinzhou Sun, Xiaoqing Wei, Jiaquan Yang, Xuehao He

“…Simulation results show that the proposed optimization method effectively improves the synchrony clustering performance and voltage stability of the test systems, offering faster optimization speed and better results compared to other classical algorithms.…”
Get full text

Research on global ship cargo capacity prediction based on multi-source heterogeneous data by Shuhang Chen, Zhihuan Wang, Zhihuan Wang, Tianye Lu, Jiayang Zhu, Chunchang Zhang, Chunchang Zhang, Xiangming Zeng, Xiangming Zeng, Jiayi Wang, Zandi Shang, Zandi Shang

“…Results demonstrate that the K-nearest neighbors (KNN) algorithm achieves 88% predictive accuracy on validation data—a 19-percentage-point improvement over conventional methods (69%). …”
Get full text