Application of support vector machine system introducing multiple submodels in data mining by Weinan Tang

“…Finally, combined with the designed parallel support vector machine algorithm, video facial and expression recognition is carried out. …”
Get full text

Co-Optimization of Vibration Suppression and Data Efficiency in Robotic Manipulator Dynamic Modeling by Xiaowei Han, Kunru Wu, Nanmu Hui

“…Then, a linear regression formulation of the manipulator’s structural dynamics is established, and the BLS network is employed to model the unstructured residuals—primarily arising from nonlinear friction—with high precision. Finally, the PSO algorithm is applied to optimize the hyperparameters of the BLS network, achieving global model optimality. …”
Get full text

Design and Optimization of a Piezoelectric Stick-Slip Actuator with Distributed Compliance by Tingting Ye, Zhao Feng, Yangmin Li

“…Then, its dominant performances are predicted through finite element analysis, including the step size and the first natural frequency. …”
Get full text

STUDY ON ENERGY ABSORPTION CHARACTERISTIC OF SINUSOIDAL BELLOWS FILLED EMULSION ABSORBER by ZHANG JianZhuo, ZHANG WanJiu, PAN YiShan, GUO Hao, WANG ShuWen

“…The pre⁃folded energy absorber is the only energy absorber structure used in rock burst mine at present.It has excellent energy absorption characteristics,but there are some problems in the buckling deformation process such as large load fluctuation and spark due to friction.In view of the above situation,a sinusoidal bellows(reduced diameter round pipe)filled with emulsion was designed to form a solid⁃liquid coupling body energy absorption component(composite component).The effects of three factors,namely wall thickness of the bellows,amplitude of the busbar and diameter of the liquid outlet,on the energy absorption characteristics of the energy absorption component were studied.The prediction model of average load,load fluctuation coefficient and specific energy absorption was established.The smoothed partiole hydrodynamics(SPH)particle algorithm of Abaqus finite element software was used for fluid⁃structure coupling analysis of the model.The structural parameters of energy absorption components were optimized by response surface method and the optimization results were obtained.The results show that when the wall thickness of corrugated pipe is 3.959 mm,the amplitude of busbar is 3.721 mm,and the diameter of outlet is 22.161 mm,the energy absorption characteristics of the member are the best.The average load is 438.684 kN,the load fluctuation coefficient is 1.178,and the specific energy absorption is 12.123 kJ/kg.Through comparison and verification,the results have high reliability,which provides a superior energy absorption component for the energy absorption link of anti⁃impact support equipment.…”
Get full text

Bathymetry Inversion Using a Deep‐Learning‐Based Surrogate for Shallow Water Equations Solvers by Xiaofeng Liu, Yalan Song, Chaopeng Shen

“…The inversion loss due to flow prediction error and the two regularizations play dominant roles in the initial and final stages, respectively. …”
Get full text

Determination of disintegration time using formulation data for solid dosage oral formulations via advanced machine learning integrated optimizer models by Mohammed Ghazwani, Umme Hani

“…Data preprocessing involved Min-Max normalization, outlier detection via Elliptic Envelope, and feature selection using Conditional Mutual Information, with hyperparameters optimized through the Water Cycle Algorithm. Performance was assessed using R², RMSE, and MAE across train, validation, and test sets, with 95% confidence intervals confirming robust predictions. …”
Get full text

Research on Sugar Concentration Sensing Based on Real-Time Polarization and Interaction Effects by Qiong Gong, Tongxiao Lyu, Song Ye, Xinqiang Wang

“…The addition of the interaction effect model significantly improves the prediction accuracy, with an RMSE of 0.36934 and a relative error within ±5%. …”
Get full text

The Face and number plate recognition for car anti-theft by Quoc Bao Truong, Tan-Loc Tran, Thanh Tan-Kiet Nguyen, Huu Cuong Nguyen

“…The system automatically predicts whether the driver is valid with the registration number plate. …”
Get full text

In Silico identification and modelling of FDA-approved drugs targeting T-type calcium channels. by Pedro Fong, Susana Roman Garcia, Melanie I Stefan, David C Sterratt

“…We used the automated docking suite GOLD v5.5 with the genetic algorithm to simulate molecular docking and predict the protein-ligand binding modes, and the ChemPLP empirical scoring function to estimate the binding affinities of 2,115 FDA-approved drugs to the human Cav3.1 channel. …”
Get full text

Machine Learning Classification of 3D Intracellular Trafficking Using Custom and Imaris-Derived Motion Features by Oleg Kovtun

“…<b>Methods:</b> This study extends a previously established two-dimensional, machine learning-based diffusional fingerprinting approach into a three-dimensional framework to overcome this limitation. It presents an algorithm that predicts intracellular motion types based on a comprehensive feature set, including custom statistical descriptors and standard Imaris-derived trajectory features, which capture subtle variations in individual trajectories. …”
Get full text

Evaluation of inflammatory bowel disease-related sleep disorders based on an interpretable machine learning approach: a multicenter study in China by Jiayi Sun, Junhai Zhen, Chuan Liu, Changqing Jiang, Jie Shi, Kaichun Wu, Weiguo Dong

“…Finally, the Local Interpretable Model–Agnostic Explanations algorithm (Lime) was utilized to interpret the results of the best ML model. …”
Get full text

Migrative armadillo optimization enabled a one-dimensional quantum convolutional neural network for supply chain demand forecasting. by Mohamed Irhuma, Ahmad Alzubi, Tolga Öz, Kolawole Iyiola

“…The Migrative Armadillo Optimization (MAO) algorithm effectively optimizes the hyperparameters of the model. …”
Get full text

YOLO Model-Based Eye Movement Detection During Closed-Eye State by Shigui Zhang, Junhui He, Yuanwen Zou

“…Our tracker achieved a mean distance error of 0.77 mm, with 90% of predicted eye position distances having an error of less than 1.67 mm, enabling real-time tracking at 30 frames per second. …”
Get full text

The Impact of Road Functions on Road Congestions Based on POI Clustering: An Empirical Analysis in Xi’an, China by Hui Zhu, Kaiqi Zhang, Changjun Wang, Lujin Jia, Siyu Song

“…We adopted the DBSCAN algorithm to cluster POIs and use the mixed POI clusters to label the socio-economic functions of roads. …”
Get full text

Optimization of a Heavy-Duty Hydrogen-Fueled Internal Combustion Engine Injector for Optimum Performance and Emission Level by Murat Ozkara, Mehmet Zafer Gul

“…This study presents a high-fidelity optimization framework that couples a validated computational fluid dynamics (CFD) combustion model with a surrogate-assisted multi-objective genetic algorithm (MOGA). The CFD model was validated using particle image velocimetry (PIV) data from non-reacting flow experiments conducted in an optically accessible research engine developed by Sandia National Laboratories, ensuring accurate prediction of in-cylinder flow structures. …”
Get full text

A 37 years [1984–2021] Landsat/Sentinel-2 derived snow cover time-series for Switzerland by Charlotte Poussin, Pascal Peduzzi, Bruno Chatenoux, Gregory Giuliani

“…Hereafter, we present a 37-year monthly time-series of snow cover derived from Landsat and Sentinel-2 data using the Snow Observations from Space algorithm and processed in the Swiss Data Cube that facilitates the analysis, production and reuse of this Essential Climate Variable, enhancing environmental monitoring efforts at national scale.…”
Get full text

The Face and number plate recognition for car anti-theft by Quoc Bao Truong, Tan-Loc Tran, Thanh Tan-Kiet Nguyen, Huu Cuong Nguyen

“…The system automatically predicts whether the driver is valid with the registration number plate. …”
Get full text

A Novel Hybrid Model for Short-Term Forecasting in PV Power Generation by Yuan-Kang Wu, Chao-Rong Chen, Hasimah Abdul Rahman

“…Moreover, five types of forecasting modules were developed and utilized to predict the one-hour-ahead PV output. They include the ARIMA, SVM, ANN, ANFIS, and the combination models using GA algorithm. …”
Get full text

Construction of Industrial Economic Management Decision Model Based on Three Parameter Interval Grey Numbers by Pao-Ching Lin, Tzu-Jung Wu, Jui-Chan Huang

“…This model characterizes the uncertainty of decision information by introducing three parameter interval grey numbers, and innovatively adopts grey relational clustering decision-making method, combined with genetic algorithm to dynamically optimize key parameters. The results demonstrated that the model exhibited excellent performance on multiple datasets, with an accuracy stable between 95 and 96%. …”
Get full text

The Fault-Tolerant Control Strategy for the Steering System Failure of Four-Wheel Independent By-Wire Steering Electric Vehicles by Qianlong Han, Chengye Liu, Jingbo Zhao, Haimei Liu

“…The front wheel controller predicts the necessary steering angle in accordance with a linear model and addresses the requirements of the front wheels and additional torque. …”
Get full text