Dynamics-Guided Support Vector Machines for Response Analysis of Steel Frame Under Sine Wave Excitation by Yao Wang, Huaiman Li

“…To address this issue, a novel dynamics-guided support vector machine (DG-SVM) method is proposed, which embeds an optimization process to reduce dependence on the time step size. …”
Get full text

Attention is All Large Language Model Need by Liu Yuxin

“…Single-modal large models can be broadly categorized into three types based on their application domains: Text LLM for Natural Language Processing (NLP), Image LLM for Computer Vision (CV), and Audio LLM for speech interaction. …”
Get full text

Performance of Finite Precision on Discrete Chaotic Map Based on a Feedback Shift Register by Chunguang Huang, Qun Ding

“…The scintillating technological improvements have changed the process of communication in all parts of the world. …”
Get full text

HIL Automatic Test System Design for the Host Software of LKJ-15C System by HE Xiezhen, ZHOU Zhifei, JIANG Jian

“…To overcome the problems of high workload, low efficiency and difficult recurrence of the manual test process for LKJ-15C host software, a novel automatic test system is proposed based on HIL simulation technology and test script technology. …”
Get full text

Type-2 Neutrosophic Sets (T2NSs) for Quality Evaluation of Project-Based Art and Design Courses: Evaluation Seven Projects by Ruijuan Zhang

“…Conflicting objectives for alternatives must be valued in a decision-making process, and the optimal option must be chosen based on the decision-makers requirements. …”
Get full text

Deriving structure from evolution: metazoan segmentation by Paul François, Vincent Hakim, Eric D Siggia

“…We evolved in silico regulatory networks by a mutation/selection process that just rewards the number of segment boundaries. …”
Get full text

Research on Trajectory Planning of Fermented Grains Grasping Mechanical Arms by Xuan Liu, Zhaomin Wu, Chang Wang, Jianhua Zhang

“…The discharging work of fermented grains is a necessary process in the production of wine， the difficulties in automating the work with mechanical arms include the long and narrow working space and the loose form of fermented wine which tends to fall. …”
Get full text

A Three-Stage Optimization Algorithm for the Stochastic Parallel Machine Scheduling Problem with Adjustable Production Rates by Rui Zhang

“…We consider a parallel machine scheduling problem with random processing/setup times and adjustable production rates. …”
Get full text

Unsupervised feature selection algorithm based on L 2,p-norm feature reconstruction. by Wei Liu, Qian Ning, Guangwei Liu, Haonan Wang, Yixin Zhu, Miao Zhong

“…Traditional subspace feature selection methods typically rely on a fixed distance to compute residuals between the original and feature reconstruction spaces. …”
Get full text

Review of image classification based on deep learning by Fu SU, Qin LV, Renze LUO

“…In recent years,deep learning performed superior in the field of computer vision to traditional machine learning technology.Indeed,image classification issue drew great attention as a prominent research topic.For traditional image classification method,huge volume of image data was of difficulty to process and the requirements for the operation accuracy and speed of image classification could not be met.However,deep learning-based image classification method broke through the bottleneck and became the mainstream method to finish these classification tasks.The research significance and current development status of image classification was introduced in detail.Also,besides the structure,advantages and limitations of the convolutional neural networks,the most important deep learning methods,such as auto-encoders,deep belief networks and deep Boltzmann machines image classification were concretely analyzed.Furthermore,the differences and performance on common datasets of these methods were compared and analyzed.In the end,the shortcomings of deep learning methods in the field of image classification and the possible future research directions were discussed.…”
Get full text

Application of Revit Secondary Development in Sluice Seepage Calculation by NIU Lijun, LI Yihao

“…Based on the concept of forward design,this paper uses C# language to abstract and package the traditional seepage calculation method (improved resistance coefficient method) and redevelops AutoRevit through Revit API interface programming.As a result,the visual interactive analysis process of sluice seepage calculation is achieved so that the design of sluice anti-seepage measures can realize forward design based on a three-dimensional model.In this paper,a regulating sluice is taken as an example for verification,and the results are compared with those calculated by AutoBank software.The results show that the plug-in has high accuracy and efficiency and realizes the highly visual sluice seepage calculation and low-difficulty human-computer interaction.At the same time,it has the function of instantly judging the results according to the specification.The plug-in not only expands the function of BIM technology but also facilitates designers in the water conservancy industry.In addition,it provides certain technical references for further expanding the deep application of BIM technology in water conservancy design.…”
Get full text

High-speed hardware architecture design and implementation of Ed25519 signature verification algorithm by Yiming XUE, Shurong LIU, Shuheng GUO, Yan LI, Cai’e HU

“…Aiming at the high performance requirements of signature verification for specific scenarios such as blockchain, a high-speed hardware architecture of Ed25519 was proposed.To reduce the number of calculations for point addition and point double, a multiple point multiplication algorithm based on interleaving NAF was conducted by using pre-computation and lookup tables.The modular multiplication operation was realized by using the Karatsuba multiplication and fast reduction method, and the point addition and point double operation was designed without modular addition and subtraction, which could effectively improve the performance of point addition and point double.Given that modular exponentiation was the most time-consuming operation in the decompression process, a new modular exponentiation approach was developed by parallelizing modular inverse and modular multiplication, and therefore the performance of the de-compression operation could be improved.The proposed architecture fully considers the use of resources and is implemented on the Zynq-7020 FPGA platform with 13 695 slices, achieving 8 347 verifications per second at 81.6 MHz.…”
Get full text

Development of a transdisciplinary education concept to prepare textile technology students for dealing with AI by Lennart Hellweg, Johanna Bulthaupt, Alen Tabakovic, Mathias Beer

“…The goal in the Faculty of Textile and Clothing Technology is to train specialists in the use of AI in the textile process chain. Students will learn how to classify image data of fibers based on a practical example. …”
Get full text

Theory of Electron-Phonon Interactions in Extended Correlated Systems Probed by Resonant Inelastic X-Ray Scattering by Jinu Thomas, Debshikha Banerjee, Alberto Nocera, Steven Johnston

“…Despite the growing importance of this area of research, the community lacks a complete understanding of how the RIXS process excites the lattice and how these excitations encode information about the e-ph interactions. …”
Get full text

Formal Verification of Multi-Thread Minimax Behavior Using mCRL2 in the Connect 4 by Diego Escobar, Jesus Insuasti

“…The parallel version of minimax distributes computations across multiple threads, with each thread evaluating different successor states concurrently. …”
Get full text

Sinkhole attack detection based on fusion of ACO and P2P trust model in WSN by Wumaier HENIGULI

“…Finally，P2P trust model was used to compute trust value of each suspicious node，and the node with trust value was lower than the preset threshold as invasion of node. …”
Get full text

Occlusion‐robust markerless surgical instrument pose estimation by Haozheng Xu, Stamatia Giannarou

“…To deal with partial instrument visibility, a keypoint object representation is used and stable and accurate instrument poses are computed using a PnP solver. To boost the learning process of the model under occlusion, a new mask‐based data augmentation approach has been proposed. …”
Get full text

Modern Adaptive and Intelligent Digital Learning Systems: Mechanisms and Potential by Konstantin A. Skvorchevsky, Olga V. Dyatlova

“…In particular, it explores human-computer interaction in both individual and group formats, involving both students and teachers. …”
Get full text

Knowledge reasoning with multiple relational paths by Hang Su, Huangcan Li, Dun Li

“…Secondly, the loss function and training process of NSPN are introduced. Finally, comparative experiments are carried out on the public dataset, and the results show that our model is superior to other models in relation prediction tasks and link prediction tasks, improves the computational efficiency and data sparsity, and provides a new idea for knowledge reasoning methods.…”
Get full text

Protein Folding: Search for Basic Physical Models by Ivan Y. Torshin, Robert W. Harrison

“…Moreover, the present-day models rarely take into account that the protein folding is, essentially, a rapid process that produces a highly specific architecture. …”
Get full text