A multiobjective continuation method to compute the regularization path of deep neural networks by Augustina Chidinma Amakor, Konstantin Sonntag, Sebastian Peitz

“…To overcome this limitation, we present an algorithm that allows for the approximation of the entire Pareto front for the above-mentioned objectives in a very efficient manner for high-dimensional DNNs with millions of parameters. …”
Get full text

An Improved Control Strategy for Managing Reactive Power and Reducing Capacity of Interlinking Converters by Participating of Electric Vehicles in Hybrid AC/DC Microgrids by Abbas Safari, Hesam Rahbarimagham

“…Moreover, a reactive power control algorithm is presented which can compensate the reactive power of the AC subgrid based on the interface converter’s maximum rated capacity. …”
Get full text

Methodology for Using Multi-Temporal Landsat Images to Monitor Urban Growth of Kirkuk Governorate by Tabark Y. Gehad, Nejat Q. Omer, Nada S. Abdulmajeed

“…The Supervised Maximum Likelihood algorithm was utilized to categorize images into urban and non-urban areas, with accuracy rates ranging from 91.25% to 96.66% between 1990 and 2020. …”
Get full text

Geometry optimization on the cross section of adhesively bonded thin-walled composite beam subjected to axial crushing load by Xiao Han, Jingru Ye, Shaoqiang Hou, Wenbin Hou

“…The non-dominated sorting genetic algorithm II (NSGA-II) was introduced to search for global optimum solution, and radial basis function (RBF) approximations for the objective functions were applied to reduce the computational cost. …”
Get full text

Client-oriented approach for assessing the quality of website of freight forwarding company when servicing private clients by O. A. Yusupova

“…The results of the survey of respondents outlined the areas of work to improve the section of the website of the Russian Railways Logistics company in terms of website content, transparency of the algorithm for calculating the cost of services, the possibility of choosing a class of service and getting answers to typical questions of interest to the client. …”
Get full text

Perspectives on Soft Actor–Critic (SAC)-Aided Operational Control Strategies for Modern Power Systems with Growing Stochastics and Dynamics by Jinbo Liu, Qinglai Guo, Jing Zhang, Ruisheng Diao, Guangjun Xu

“…To tackle the limitations of existing control approaches that require full-system models with accurate parameters and conduct real-time extensive sensitivity-based analyses in handling the growing uncertainties, this paper presents a novel data-driven control framework using reinforcement learning (RL) algorithms to train robust RL agents from high-fidelity grid simulations for providing immediate and effective controls in a real-time environment. …”
Get full text

Ranking Analysis for Online Customer Reviews of Products Using Opinion Mining with Clustering by S. K. Lakshmanaprabu, K. Shankar, Deepak Gupta, Ashish Khanna, Joel J. P. C. Rodrigues, Plácido R. Pinheiro, Victor Hugo C. de Albuquerque

“…Also, the novelty of this work—the Dragonfly Algorithm (DA)—recognizes ideal features of the items in sites, and an advanced ideal feature-based positioning procedure will be directed to discover, at long last, which web-based business webpage is best and easy to understand. …”
Get full text

A Vibration Model of Ball Bearings with a Localized Defect Based on the Hertzian Contact Stress Distribution by Fanzhao Kong, Wentao Huang, Yunchuan Jiang, Weijie Wang, Xuezeng Zhao

“…The relative motion between the inner ring, the outer ring, and the balls is considered in the proposed model, and the Runge-Kutta algorithm is used to solve the vibration equations. …”
Get full text

Towards a New Taxonomy of Pattern-Making in the Visuo-Spatial Domain in Early Childhood Based on Zygonic Theory and the Sounds of Intent Framework of Musical Development by Adam Ockelford, Sarah McCarthy, Sue Gifford, Helen Thouless, Sharon Kirk, Michael Thorpe

“…Drawing on the principles set out in zygonic theory and using the structure laid out in the Sounds of Intent framework, the researchers propose how to map the development of pattern understanding from the auditory domain onto the visuo-spatial domain. An algorithm is used to demonstrate the structural processing load for different pattern types, which allows the putative developmental stages of pattern-processing capacity to be plotted sequentially. …”
Get full text

Neural Network-Based Lower Limb Prostheses Control Using Super Twisting Sliding Mode Control by Adisu Tadese Demora, Chala Merga Abdissa

“…The neural network structure is built using Feed-forward Neural Network (FFNN) architecture and Levenberg-Marquardt (LM) back-propagation training algorithm for accuracy, fast convergence, and reliable optimization of nonlinear relationships. …”
Get full text

A Two-Layer Network Dynamic Congestion Pricing Based on Macroscopic Fundamental Diagram by Bangyang Wei, Daniel(Jian) Sun

“…The upper level model aims at minimizing the total travel time, while the lower level focuses on the MFD-based traffic assignment, which extends the link-based traffic assignment to network wide level. Genetic algorithm (GA) and the method of successive average were adopted for solving the proposed model, on which an online experimental platform was established using VISSIM, MATLAB, and Visual Studio software packages. …”
Get full text

Internal communication as a mediator in the relationship between transformational leadership and academic staff’s readiness for change in higher education by Saharudin Saharudin, Ekawarna Ekawarna, Urip Sulistiyo, Mohd. Odha Meditamar, Santo Kristiyono

“…Partial Least Squares Structural Equation Modeling (PLS-SEM) was used to test the hypotheses, with the PLS Algorithm assessing the measurement model and PLS Bootstrapping testing the structural model for mediation effects. …”
Get full text

Robust adaptive optimization for sustainable water demand prediction in water distribution systems by Ke Wang, Jiayang Meng, Zhangquan Wang, Kehua Zhao, Banteng Liu

“…To further enhance the model’s robustness, an innovative optimization algorithm is incorporated within the CEEMD process to minimize the variance in multi-scale arrangement entropy among the decomposed components, thereby improving the model’s generalization capabilities. …”
Get full text

Design optimization of the podded propulsor considering pod housing drag and propulsion motor performance by Yuhang Zhou, Chengjiang Liu, Yao Yan, Quan Chen, Wenliang Ke

“…Sensitivity analysis revealed that the stator outer diameter and fore taper angle are key factors influencing motor performance and drag, respectively. A genetic algorithm was used to optimize the POD with bi-objective and tri-objective focuses on minimizing drag, maximizing motor efficiency and power density. …”
Get full text

Change of Parameters of the Koiwa–Hasiguti Dynamic Dislocation Relaxation in Nanostructured and Polycrystalline Zirconium after Severe Plastic Deformation and Annealing by P. P. Pal-Val, L. N. Pal-Val, A. P. Rybalko, E. N. Vatazhuk

“…It is shown that the parameter β of the lognormal distribution determines the width, height, and asymmetry of the peak and also allows estimating the relaxation strength from the peak height. An algorithm for retrieving the parameter β from experimental data is presented.…”
Get full text

Relationship Between the 2019 Ridgecrest, California, <i>M</i>_W7.1 Earthquake and Its <i>M</i>_W6.4 Foreshock Sequence by Jianchang Zheng, Zhengshuai Zhang, Xiaohan Li

“…Based on the relocated catalogue, we adopt the nearest neighbour algorithm to analyze its foreshock and aftershock sequences. …”
Get full text

Alterations of the Gut Microbiome in Chinese Zhuang Ethnic Patients with Sepsis by Jieyang Yu, Hongping Li, Jingjie Zhao, Yanhua Huang, Chunlei Liu, Pengfei Yang, Dinggui Lu, Jian Song, Lingzhang Meng

“…Moreover, patients with sepsis could be effectively classified based on the abundance of these bacteria using a support vector machine algorithm. Conclusion. This study demonstrated significant differences in the gut microbiome between Zhuang ethnic patients with sepsis and healthy individuals. …”
Get full text

Outbreak prediction of covid-19 in most susceptible countries by D. Yadav, H. Maheshwari, U. Chandra

“…It spread on humans as well as animals and infected more than 183 countries with 2959927 confirm cases and 202733 deaths till 28 April 2020. 84 days data is used to predict confirmed and death cases for the next 10 days by using prophet and daily average based algorithm. Predicted confirmed cases are 2886183 and death cases 190540 till 25 April 2020. …”
Get full text

Analysis and Dynamic Prediction of Bus Dwell Time Under Rainfall Conditions by Baoyun SUN, Yaping YANG, Lei DONG, Honglin LU, Zimin WANG

“…Support vector machine, k-nearest neighbour and backpropagation (BP) prediction models were established, and the BP neural network model, having the best prediction effect, was optimised using a genetic algorithm (GA). The constructed GA-BP prediction model was more realistic than the BP prediction model and can be used to predict bus dwell times under rainfall conditions. …”
Get full text

Parameter Optimization on the Three-Parameter Whitenization Grey Model and Its Application in Simulation and Prediction of Gross Enrollment Rate of Higher Education in China by Jihong Sun, Hui Li, Bo Zeng, Xiaoyun Zhao, Chuanhui Wang

“…This study combines the Three-parameter Whitenization Grey Model (TWGM(1,1)), which fits the inhomogeneous exponential law sequence, and the Particle Swarm Algorithm (PSA) to optimize the order and background value coefficients under the condition of the minimum sum of squares of simulation errors, and hence, to solve the problem that the cumulative order is fixed to “1” and the background value coefficient value is fixed to “0.5.” …”
Get full text