Stacking-Based Ensemble Learning Method for the Recognition of the Pedestrian Crossing Intention by Hongjia Zhang, Song Gao, Pengwei Wang

“…Secondly, the pedestrian crossing intention characterization parameter set was determined through statistical analysis. …”
Get full text

Translating microbial kinetics into quantitative responses and testable hypotheses using Kinbiont by Fabrizio Angaroni, Alberto Peruzzi, Edgar Z. Alvarenga, Fernanda Pinheiro

“…Kinbiont consists of three sequential yet independent modules: (1) data preprocessing, (2) model-based parameter inference with both user-defined differential equation systems and hard-coded growth models, and (3) explainable machine learning analyses to map experimental conditions directly to inferred biological parameters. …”
Get full text

Development of Automatic Welding System for Offshore Platform Pile Pipe by XU Jia-zhong, ZHANG Yu, YOU Bo, LI Dong-jie, FU Wei

“…We elaborate the control requirement of the system，hardware configuration，software design and human-machine interface design，and complete the pile pipe girth welding test and technological parameter selection. …”
Get full text

Design and analysis of a rope-driven elbow-wrist rehabilitation mechanism with joint dislocation compensation by HOU Yulei, CAI Qingming, GAO Zhiqiang, LI Yue, LIU Fei, DENG Yunjiao, ZENG Daxing

“…However, the existing rehabilitation robots have insufficient human-machine compatibility due to configuration limitations, and the rehabilitation effect is not ideal. …”
Get full text

Survey on vertical federated learning: algorithm, privacy and security by Jinyin CHEN, Rongchang LI, Guohan HUANG, Tao LIU, Haibin ZHENG, Yao CHENG

“…Federated learning （FL） is a distributed machine learning technology that enables joint construction of machine learning models by transmitting intermediate results （e.g., model parameters, parameter gradients, embedding representation, etc.） applied to data distributed across various institutions.FL reduces the risk of privacy leakage, since raw data is not allowed to leave the institution.According to the difference in data distribution between institutions, FL is usually divided into horizontal federated learning （HFL）, vertical federated learning （VFL）, and federal transfer learning （TFL）.VFL is suitable for scenarios where institutions have the same sample space but different feature spaces and is widely used in fields such as medical diagnosis, financial and security of VFL.Although VFL performs well in real-world applications, it still faces many privacy and security challenges.To the best of our knowledge, no comprehensive survey has been conducted on privacy and security methods.The existing VFL was analyzed from four perspectives: the basic framework, communication mechanism, alignment mechanism, and label processing mechanism.Then the privacy and security risks faced by VFL and the related defense methods were introduced and analyzed.Additionally, the common data sets and indicators suitable for VFL and platform framework were presented.Considering the existing challenges and problems, the future direction and development trend of VFL were outlined, to provide a reference for the theoretical research of building an efficient, robust and safe VFL.…”
Get full text

Conditional universal differential equations capture population dynamics and interindividual variation in c-peptide production by Max de Rooij, Natal A. W. van Riel, Shauna D. O’Donovan

“…Furthermore, we show that the conditional parameter captures relevant inter-individual variation. …”
Get full text

Accident Detection and Flow Prediction for Connected and Automated Transport Systems by Yi Zhang, Fang Liu, Sheng Yue, Yuxuan Li, Qianwei Dong

“…This paper proposes a traffic accident detection method for connected and automated transport systems by conducting a grid-based parameter extracting and SVC-based traffic state classification. …”
Get full text

STUDY OF TORQUE NONUNIFORMITY IN DOUBLE-ACTION HYDRAULIC ROTARY VANE MO-TORS by V. Yu. Savin, V. Yu. Ilyichev

“…In this case, the most important parameter of the torque is its nonuniformity. The problem of determining nonuniform torque in hydraulic motors having ten and twelve vanes is investigated with the aim of ensuring the maximum stability of this parameter.Method. …”
Get full text

Performance optimization for mMTC in 5G network with multiple random access schemes by Wen ZHAN, Yiwen LIANG, Xinghua SUN, Xuesong TAN

“…To optimize the support for massive machine type communication (mMTC) services with different traffic characteristics, packet-based random access (PBRA) scheme coexists with the connection-based random access (CBRA) scheme in 5G networks.Yet, given the traffic characteristic of mMTC, which random access scheme should be chosen is still an open issue.To address this issue, the network throughput and signaling overhead analysis of mMTC with PBRA and CBRA were presented, and the problem of throughput maximization while maintaining the signaling-to-throughput ratio below a certain level was solved.Based on this, the optimal access scheme selection strategy and the corresponding optimal network parameter configuration were obtained and verified via simulations.…”
Get full text

Research and apply of the quality of star image for star tracker by SHEN Yuteng, ZHANG Chi

“…In this paper,“Seven Parameter Image Quantitative Evaluation Standard”is developed, which makes use of the massive star image data accumulated in the production of star tracker and through data modeling theory research. …”
Get full text

Numerical model of the pneumatic diaphragm actuator by Aleksandr Kovalenko

“…The key point of the investigation was development of the diaphragm model and its key parameter - effective area. It has been found that the accurate enough diaphragm effective area can be determined as a function of readily available and easily measurable parameters such as the rigid center displacement, pressures in the chambers, diaphragm dimensions, and its material physical properties. …”
Get full text

Multitask deep learning for the emulation and calibration of an agent-based malaria transmission model. by Agastya Mondal, Rushil Anirudh, Prashanth Selvaraj

“…We then use the trained emulator in conjunction with parameter estimation techniques to calibrate the underlying model to reference data. …”
Get full text

基于工作空间的航空发动机柔性工装尺度优化及刚度分析 by 石宏, 李伟楠, 陈亮, 朱宁, 金印

“…Based on the study of flexible assembly tooling configuration on aero-engine,he workspace of aero-engine flexible assembly tooling is calculated,and a mathematic model is set up by Monte Carlo method,the design parameter dimensional optimization for workspace is carried out,then the global condition number for construction of different sizes is solved,the result is used for the optimization of machine kinematic.At last the conservative congruence transformation（CCT）stiffness matrix is derived,and stiffness mapping in the direction of X,Y,Zis simulated.These results are applied for the analysis and discuss of stiffness.This work has outstanding theoretical significance for assembly accuracy improvement,optimizing assembly performance,pose and position reasonable selection during the assembly and dimensional optimization.…”
Get full text

基于SVM与GA参数优化的齿轮箱断齿故障诊断方法研究 by 张星辉, 康建设, 曹端超, 孙磊, 滕红智

“…A new method of gearbox fault diagnosis based on SVM（Support vector machine） and GA（Genetic algorithm）which is used to optimize parameters is presented.Firstly,the raw vibration signal is preprocessed by Time Synchronous Average algorithm.Then,the signal wavelet packet decomposition is carried out,standard deviation of wavelet packet coefficients of the signals is considered as the fault feature vector,and the normalization process of the fault feature vector is carried out.In the end,the fault feature vector is used as the input of SVM.In this process,the Daubechies order,wavelet packet decomposition level,c and g of SVM are optimized by GA.After that,the optimized parameter is used in training model which will be used for fault diagnosis.The experimental result shows that SVM and GA can be used to effectively diagnose faults of gearbox.…”
Get full text

Performance optimization for mMTC in 5G network with multiple random access schemes by Wen ZHAN, Yiwen LIANG, Xinghua SUN, Xuesong TAN

“…To optimize the support for massive machine type communication (mMTC) services with different traffic characteristics, packet-based random access (PBRA) scheme coexists with the connection-based random access (CBRA) scheme in 5G networks.Yet, given the traffic characteristic of mMTC, which random access scheme should be chosen is still an open issue.To address this issue, the network throughput and signaling overhead analysis of mMTC with PBRA and CBRA were presented, and the problem of throughput maximization while maintaining the signaling-to-throughput ratio below a certain level was solved.Based on this, the optimal access scheme selection strategy and the corresponding optimal network parameter configuration were obtained and verified via simulations.…”
Get full text

Composite Motion Design Procedure for Vibration Assisted Small-Hole EDM Using One Voice Coil Motor by Jing Cui, Zhongyi Chu

“…To address the problem of debris accumulation in small-hole electrical discharge machine (EDM) and simplify the design of the spindle head, the paper proposes a novel composite motion design procedure integrated high frequency vibration and large stroke feed using one voice coil motor (VCM). …”
Get full text

Approximating non-Gaussian Bayesian partitions with normalising flows: statistics, inference and application to cosmology by Tobias Röspel, Adrian Schlosser, Björn Malte Schäfer

“…Subject of this paper is the simplification of Markov chain Monte Carlo sampling as used in Bayesian statistical inference by means of normalising flows, a machine learning method which is able to construct an invertible and differentiable transformation between Gaussian and non-Gaussian random distributions. …”
Get full text

Deep learning multilayer architecture for analysis of three-dimensional Eyring-Powell nanofluid flow subject to viscous dissipation and joule heating by Zahoor Shah, Muflih Alhazmi, Maryam Jawaid, Nafisa A. Albasheir, Mohammed M.A. Alma Zah, Nashwan Adnan Othman, Waqar Azeem Khan

“…With an increase in the Eyring-Powell fluid parameter, the velocity profile is likely to increase. present study utilized an advanced machine learning framework that has been proven to outperform the state-of-the-art models in predicting complex dynamics of EPNF-3D-VJ. …”
Get full text

Construction Mechanical Response Analysis of City Railway Machinary Method Link Passage under Eccentric Opening Conditions by LI Yitao, SUN Shuangchi, YU Jing, ZHOU Meng, WANG Wenzhong

“…Under varying conditions of burial depth, soil parameter, and shield machine thrust, the impact of link passage construction on the main tunnel structure is analyzed from three aspects: deformation, axial force, and bending moment of special segments under different operating conditions. …”
Get full text

Ecological and Ergonomic Aspects of Operating Hybrid Sunflower Cultivation Technologies by M. A. Kerimov, V. V. Vetushko

“…The technology for cultivating hybrid sunflower seeds is formalized as a biotechnical dynamic system structured around the «operator–machine–environment» triad. The efficiency of this system depends on multiple factors, primarily the qualification level of machine operators, the technical advancement of the machinery, and the conditions of both the production and external environments. …”
Get full text