Building accurate numerical models by Sharapov Dmitry

“…Numerical modeling has emerged as a crucial tool across various scientific and engineering disciplines, enabling the simulation and prediction of complex systems. This paper explores the comprehensive process of numerical model development, encompassing problem definition, mathematical formulation, discretization, implementation, and validation. …”
Get full text

Pochva: a new hydro-thermal process model in soil, snow, and vegetation for application in atmosphere numerical models by O. Drofa

“…The results of coupling Pochva to the numerical weather prediction limited-area model Bolam are presented.</p>…”
Get full text

Unsupervised detection of semantic correlations in big data by Santiago Acevedo, Alex Rodriguez, Alessandro Laio

“…This recognition enables, for instance, the prediction of missing parts of an image or text based on their context. …”
Get full text

RELIABILITY ANALYSIS OF REACTION FORCE DEVELOPED IN THE LUBRICATED REVOLUTE JOINT FOR A SLIDER-CRANK SYSTEM INCLUDING JOINT WITH CLEARANCE AND LUBRICATION by ZHAO Kuan, XUE He, CHEN JianJun, QIAO XinZhou

“…The system dynamic model was set up based on Newton-Euler method,The prediction accurary of Support Vector Machine Regression is difficult to reach the target accurary because the selection of parameters isn’t accurate. …”
Get full text

A New Distributed Type-2 Fuzzy Logic Method for Efficient Data Science Models of Medical Informatics by Fatéma Zahra Benchara, Mohamed Youssfi

“…Accordingly, the method is assigned to be implemented on big data analysis and data science prediction models for healthcare applications. The paper focuses on the proposed distributed Type-2 Fuzzy Logic (DT2FL) method and its application for MRI data analysis under a massively parallel and distributed virtual mobile agent architecture. …”
Get full text

Pruning Bayesian networks for computationally tractable multi-model calibration by Nicolas Gratius, Mario Bergés, Burcu Akinci

“…We implement this method using a Python wrapper for BayesFusion software and show that the resulting prediction accuracy outperforms existing pruning approaches which rely primarily on statistics.…”
Get full text

Are treatment plans optimized on the basis of acuros XB dose calculation robust against anatomic changes during online adaptive radiotherapy for lung cancer regarding dose homogene... by Khouya Aymane, Santiago Alina, Ringbaek Toke, Guberina Nika, Guberina Maja, Gauler Thomas, Lübcke Wolfgang, Zylka Waldemar, Pöttgen Christoph, Stuschke Martin

“…Abstract Introduction The Acuros XB dose calculation algorithm implements advanced modelling of lateral electron transport, making dose distributions sensitive to density changes between source and subsequent CT. …”
Get full text

Research on bearing fault feature transfer diagnosis based on balanced distribution adaptation under feature fusion by Lulu Wang, Yongqi Li, Chunyi Zhang, Ralph Gerard Sangalang

“…To address this issue, this paper proposes a bearing fault transfer diagnosis method that combines the Balanced Distribution Adaptation (BDA) algorithm with a Back Propagation neural network (BPNN) classification algorithm. …”
Get full text

Classification of Phishing Email Using Random Forest Machine Learning Technique by Andronicus A. Akinyelu, Aderemi O. Adewumi

“…This paper investigates and reports the use of random forest machine learning algorithm in classification of phishing attacks, with the major objective of developing an improved phishing email classifier with better prediction accuracy and fewer numbers of features. …”
Get full text

Robust time series analysis for forecasting photovoltaic energy yield by Sapundzhi Fatima, Chikalov Aleksandar, Georgiev Slavi, Georgiev Ivan, Todorov Venelin

“…The analysis proceeds with the generation of monthly predictions for the dataset, complete with their own confidence bounds, thereby showcasing the forecasting strength of the models. …”
Get full text

A New Finite-Difference Method for Nonlinear Absolute Value Equations by Peng Wang, Yujing Zhang, Detong Zhu

Get full text

Using AI in Optimizing Oral and Dental Diagnoses—A Narrative Review by Amelia Surdu, Dana Gabriela Budala, Ionut Luchian, Liliana Georgeta Foia, Gina Eosefina Botnariu, Monica Mihaela Scutariu

“…AI technologies, such as machine learning, deep learning, and computer vision, are increasingly being integrated into dental practice to analyze clinical images, identify pathological conditions, and predict disease progression. By utilizing AI algorithms, dental professionals can detect issues like caries, periodontal disease and oral cancer at an earlier stage, thus improving patient outcomes.…”
Get full text

Congestion forecast framework based on probabilistic power flow and machine learning for smart distribution grids by Alejandro Hernandez-Matheus, Kjersti Berg, Vinicius Gadelha, Mònica Aragüés-Peñalba, Eduard Bullich-Massagué, Samuel Galceran-Arellano

“…This work proposes a framework to predict grid asset congestions on a daily basis. A congestion forecast framework is proposed by combining probabilistic power flows and machine learning algorithms to support DSOs in their daily decision-making. …”
Get full text

Optimization of Quantitative Financial Data Analysis System Based on Deep Learning by Meiyi Liang

“…In order to better assist investors in the evaluation and decision-making of financial data, this paper puts forward the need to build a reliable and effective financial data prediction model and, on the basis of financial data analysis, integrates deep learning algorithm to analyze financial data and completes the financial data analysis system based on deep learning. …”
Get full text

Nove lincidence matrix differential power analysis for resisting ghost peak by Zijing JIANG, Qun DING

“…At present, differential power analysis (DPA) is one of the most important threats to the security of block ciphers in chips.When the collected power trace is insufficient, DPA is vulnerable to ghost peak caused by the difference mean value generated by the wrong key.Based on DPA, a incidence matrix differential power analysis (IMDPA) was proposed which could effectively resist ghost peak.The prediction difference mean matrix was constructed to avoid the influence of the non leaking interval on the key guessing of the leaking interval by using the weak correlation of the guessing key in the non leaking interval.The proposed IMDPA was tested in different leak intervals of AES-128 algorithm.The results show that compared with traditional DPA, IMDPA requires less (up to 85%) power trace to guess the correct key.At the same time, the key guessing efficiency of AES-128 under the implementation of protective measures by IMDPA still has obvious advantages.In order to further verify the universality of IMDPA in block ciphers, experimental verification is conducted on SM4 algorithm.Compared with traditional DPA, IMDPA requires less (up to 87.5%) power traces to guess the correct key.…”
Get full text

Low Complexity Mode Decision for 3D-HEVC by Qiuwen Zhang, Nana Li, Yong Gan

“…The basic idea of the method is to utilize the correlations between depth map and motion activity in prediction mode where variable size CU and DE are needed, and only in these regions variable size CU and DE are enabled. …”
Get full text

Performance of digital filtering and synchronization method for APD communication receiver by Hui-Jun Zhang, Peng Lin, Tong Wang, Zi-Qi Zhang, Bai-Qiu Zhao, Wen-Fang Jiao, Xiao-Nan Yu

Get full text

Efficient Resources Provisioning Based on Load Forecasting in Cloud by Rongdong Hu, Jingfei Jiang, Guangming Liu, Lixin Wang

“…It integrates an improved support vector regression algorithm and Kalman smoother. Public trace data taken from multitypes of resources were used to verify its prediction accuracy, stability, and adaptability, comparing with AR, BPNN, and standard SVR. …”
Get full text

Time-varying channel estimation in reconfigurable intelligent surface assisted communication system by Kai SHAO, Ben LU, Guangyu WANG

“…Aiming at the key problems need to be solved, such as cascade channel sparse representation, time-varying channel parameter tracking and signal reconstruction, for time-varying cascade channels estimation of reconfigurable intelligent surface (RIS) assisted communication system, a Khatri-Rao and hierarchical Bayesian Kalman filter (KR-HBKF) algorithm was proposed.Firstly, the Khatri-Rao product and Kronecker product transformations were used to obtain the sparse representation of RIS cascaded channels based on the sparse characteristics of channels, thus the RIS cascaded channel estimation problem was transformed into a low-dimensional sparse signal recovery problem.Then, according to the state evolution model of RIS cascaded channel, the time correlation parameter was introduced into the prediction model of HBKF algorithm, and the improved HBKF was applied to solve the problem of time-varying channel parameter tracking and signal reconstruction for completing the time-varying cascaded channels estimation.The sparsity and time correlation of the channel were comprehensively considered in the KR-HBKF algorithm, thus better estimation accuracy could be obtained with small pilot overhead.Compared with the traditional compressed sensing algorithm, the simulation results show that the proposed algorithm has about 5 dB estimated performance improvement, and better robustness performance under different time-varying channel conditions.…”
Get full text

Tracking maneuver target using interacting multiple model-square root cubature Kalman filter based on range rate measurement by Hongqiang Liu, Zhongliang Zhou, Haiyan Yang

“…Their approximate distribution functions are obtained by the use of the expectation maximization algorithm with Gaussian mixture model. Then the probability distribution and probability distribution of measurement prediction residual are combined into a new likelihood function to improve the efficiency of updating the model probability. …”
Get full text