Intelligent prediction for face straightness based on sensor data and human operation information by SUN Yan, FU Xiang, WANG Ranfeng, JIA Yifan, ZHANG Zhixing

“…A face straightness analysis matrix was constructed, consisting of the normal advancing stroke control distance matrix and the accumulated advancing stroke control distance matrix. Through feature engineering, feature extraction was carried out on the straightness analysis matrix of the working face, and the feature matrix was generated as a sample, with the working condition type corresponding to the manual control distance to serve as sample labels. …”
Get full text

Enhancing Digital Twin Fidelity Through Low-Discrepancy Sequence and Hilbert Curve-Driven Point Cloud Down-Sampling by Yuening Ma, Liang Guo, Min Li

“…This paper addresses the critical challenge of point cloud down-sampling for digital twin creation, where reducing data volume while preserving geometric fidelity remains an ongoing research problem. We propose a novel down-sampling approach that combines Low-Discrepancy Sequences (LDS) with Hilbert curve ordering to create a method that preserves both global distribution characteristics and local geometric features. …”
Get full text

Research on Fault Diagnosis Method of High-Speed EMU Air Compressor Based on ICEEMDAN and Wavelet Threshold Combined Noise Reduction by Liqiang Peng, Akang Guo, Shuzhao Zhang

“…Finally, vibration and pressure signals from the air compressor are subjected to feature extraction, constructing high-dimensional feature vectors. …”
Get full text

Mental health in children with and without disabilities in a register-based Swedish sample supports the two-continua model: a latent class analysis by Lina Homman, Lilly Augustine, Mats Granlund

“…Abstract Background Mental health is a term frequently used to describe mental health problems. However, mental health includes both mental health problems and well-being. …”
Get full text

Error Analysis and Compensation of 3‒PTT Parallel Robot by CHEN Mingfang, LIANG Hongjian, WEI Songpo, HE Chaoyin

“…The most effective method with the lowest cost is to calibrate the robot's kinematics. However, problems exist in traditional calibration methods, such as excessive error parameters, error accumulation, and difficulty in obtaining the optimal solution of statically indeterminate equations. …”
Get full text

Fault Diagnosis Method of Bearing based on LCD Cross Approximate Entropy and Relevance Vector Machine by Tan Jingjing, Gao Feng, Zhang Qiantu

“…Finally,the fault feature are put into RVM to identify different faults. …”
Get full text

AN INCIPIENT FAULT DIAGNOSIS METHOD FOR ROLLING BEARING BASED ON MCKD AND LMD by SUN Wei, LI XinMin, JIN XiaoQiang, HUANG JianPing, ZHANG XianHui

“…Aiming at the problem that the Local mean decomposition（LMD） method is difficult to draw early weak fault,a fault diagnosis method for the roller bearing based on maximum correlated kurtosis deconvolution（MCKD） and LMD was proposed.Firstly,the fault signal was de-noised and meantime periodic impact components were enhanced by MCKD method,Then,that result is decomposed by LMD to get PF,the correlation coefficient between the PF and the signal is used as the standard of judgment,so that the redundant low-frequency PF can be rejected.Finally,the effective PF is selected to analyze the spectrum and extract the fault feature.The experiment of the simulation data and the actual roller bearing fault diagnosis data show that the method can effectively extract the feature frequency information of incipient fault and has a certain reliability.…”
Get full text

Customer Attrition Detection Using the LGBM Model by Huang Jie

“…To select the most suitable model for accurately detecting customer churn, this study performs preprocessing, including data cleaning, feature engineering, and feature selection. The dataset is then split into training, testing, and validation sets. …”
Get full text

Engineering Vibration Recognition Using CWT-VGG19 by Wei Huang, Jian Xu

“…The continuous wavelet transform converts the original one-dimensional vibration signals into two-dimensional time-frequency representations with richer feature information, which are then input into the convolutional layers for automatic feature extraction, culminating in vibration recognition through the SoftMax layer. …”
Get full text

Human action recognition method based on multi-view semi-supervised ensemble learning by Shengnan CHEN, Xinmin FAN

“…Mass labeled data are hard to get in mobile devices.Inadequate training leads to bad performance of classifiers in human action recognition.To tackle this problem, a multi-view semi-supervised ensemble learning method was proposed.First, data of two different inertial sensors was used to construct two feature views.Two feature views and two base classifiers were combined to construct co-training framework.Then, the confidence degree was redefined in multi-class task and was combined with active learning method to control predict pseudo-label result in each iteration.Finally, extended training data was used as input to train LightGBM.Experiments show that the method has good performance in precision rate, recall rate and F1 value, which can effectively detect different human action.…”
Get full text

Research and prospect of standard for biometric multi-modal fusion used with mobile devices by Guanchen LIN, Zhifei WANG

“…Aiming at the problem of inconsistent biometric multi-modal fusion technology framework for mobile devices and lack of standards, a unified technical framework of multi-modal fusion standards was proposed.Firstly, the current status of standardization related to biometric used with mobile device was analyzed.Secondly, the local recognition and remote recognition application modes of mobile device biometrics standards were studied, and then four sub-multimodal fusion classification methods of multi-feature, multi-algorithm, multi-instance, and multi-sensor were analyzed and proposed.Then, four levels of multi-modal fusion were researched and proposed: sample-level fusion, feature-level fusion, score-level fusion, and decision-level fusion, and a standard technical framework for biometric multi-modal fusion for mobile devices was proposed.Finally, prospects for the application of biometric multi-modal fusion technology were given.…”
Get full text

Multi-class fault diagnosis of BF based on global optimization LS-SVM by ZHANG Hai-gang, ZHANG Sen, YIN Yi-xin

“…Aiming at the requirement of high speed and precision in blast furnace fault diagnosis systems, a new strategy based on global optimization least-squares support vector machines (LS-SVM) was proposed to solve this problem. Firstly, the variable metric discrete particle swarm optimization algorithm was employed to optimize the feature selection and LS-SVM parameters. …”
Get full text

Wavelet transform and cyclic cumulant based modulation classification in wireless network by Wenwen Li, Zheng Dou, Lin Qi

“…It leads to the low-modulation classification probability in multipath channel. To resolve this problem, we propose a novel modulation classification algorithm. …”
Get full text

Explainable machine learning models for mortality prediction in patients with sepsis in tertiary care hospital ICU in low- to middle-income countries by Saumya Diwan, Vinay Gandhi, Esha Baidya Kayal, Puneet Khanna, Amit Mehndiratta

“…It is an even more prevalent health problem in low- and middle-income countries demanding costly treatment and management. …”
Get full text

Recognition method based on hesitant fuzzy set for unequal length sequences and its application by Shuangming LI, Xin GUAN, Guidong SUN

“…Aiming at the problem that unequal length sequences were difficult to recognize, a recognition method based on hesitant fuzzy distance measure was proposed.Firstly, the problem was described from the perspective of fuzzy value, and the hesitant fuzzy information recognition model of unequal length sequence was established by lattice closeness degree.Secondly, the mean value, variance, relative range and hesitancy degree of hesitant fuzzy values were defined.Combined with membership difference of the shorter part, the generalized integrated feature distance measure and the generalized weighted integrated feature distance measure were defined to meet relevant properties of metric space, and the strict mathematical proof process was given.Finally, entropy measure and support measure were proposed to determine the weight, and the VIKOR recognition method based on hesitant distance measure was given.The simulation results verify the effectiveness and feasibility of proposed method from numerical examples, energy strategy selection and target recognition respectively.…”
Get full text

Research on transformer operation state prediction based on comprehensive weights and BO-CNN-GRU by Ying Liu, Wenbin Cao, Xiaoming Zhang, Yuhang Sun, Xu Sun

“…Firstly, 11 kinds of monitoring data in three categories including oil chromatography gas content, temperature, and electrical quantity are selected as feature parameters; Then, the game theory method is used to integrate the weight values of the three methods of G1 method, entropy weight method and CRITIC method to get the comprehensive weight value of each feature parameter, and the transformer operation state index is constructed based on the comprehensive weight; Finally, the BO-CNN-GRU combination prediction model is built, which solves the problem of difficulty in determining the hyperparameters of the model. …”
Get full text

Generalized Intuitionistic Fuzzy Normalized Weighted Optimized Geometric Bonferroni Mean and Their Application to MADM by Jin-Bo Zhang, Tian-Le Sun, Ming-Hua Shi

“…Long-term research has proved that information aggregation operator is an effective tool to solve this kind of problem. Bonferroni mean (BM) is an important information aggregation tool which has the main feature of capturing the interrelationships among aggregated arguments. …”
Get full text

Comparison of algorithms for multi-objective optimization of radio technical device characteristics by A. V. Smirnov

“…The selection of a method for solving multi-objective optimization problems has many practical applications in diverse fields. …”
Get full text

CR-CLCD: A cross-regional cropland change detection framework with multi-view domain adaptation for high-resolution satellite imagery by Zhendong Sun, Xinyu Wang, Yanfei Zhong

“…Recently, numerous advanced CD methods have been proposed to address the CNA problem. However, applying these methods to cross-regional or large-scale CNA detection presents several challenges: (1) Radiance-feature differences of croplands across regions i.e., crop type and phenology differences arising from variations in planting structures and seasonality; (2) Change-pattern differences of croplands across regions, i.e., differences in predominant change types resulting from distinct regional economic development characteristics. …”
Get full text

MAGICAL REALISM IN THE CONTEXT OF POSTMODERN AESTHETICS: HERMANN KASACK’S “THE CITY BEYOND THE RIVER” AND MAX KIDRUK’S “DON’T LOOK BACK AND STAY QUIET” INTER- TEXTUAL CONNECTIONS... by Tetiana V. Bykova, Nina D. Osmak

“…The article is devoted to revealing the main characteristics of Magical Realism as a central feature of postmodern text in the novels by Hermann Kasack “The City Beyond the River” and Max Kidruk “Don’t Look Back and Stay Quiet”. …”
Get full text