检索结果-内蒙古大学图书馆

International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Su-Mei Li Zi-Xi Zhu Xiao-Ning Li Xin-Guang Li Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies Guangzhou Guangdong China Experimental teaching center Guangdong University of Foreign Studies Guangzhou Guangdong China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou Guangdong China School of Computer Science and Technology South China Business College (SCBC) of Guangdong University of Foreign Studies Guangzhou Guangdong China

ISBN: (数字)9798331507398

ISBN: (纸本)9798331507404

In order to address the issue of incomplete feature extraction in traditional oral fluency scoring methods, a method based on feature fusion is proposed in the paper, which integrates traditional acoustic features and deep features of audio to complete the scoring of oral fluency. For the audio to be tested, IS10_paraling features are extracted as traditional acoustic features, and a fine-tuned wav2vec2.0 pre-trained model is used to extract deep features of the audio. These two types of features are concatenated to form fusion features, which are then input into a multilayer perceptron scoring model to obtain the oral fluency score. experimental results on the speechocean762 dataset show that compared to scoring methods based on single types of audio features, the fusion feature-based method improves scoring performance. The multilayer perceptron scoring model based on fusion features achieves a Pearson correlation coefficient of 0.744 with human scoring, demonstrating the effectiveness of the proposed method.

关键词： Correlation coefficient Training Human-machine systems Data visualization Multilayer perceptrons Feature extraction Acoustics User experience Informatics Spectrogram

来源：评论

学校读者我要写书评

暂无评论

Significant Wave Height Prediction Based on VMD-SA-MLP-BP

Significant Wave Height Prediction Based on VMD-SA-MLP-BP

引用

Chinese Automation Congress (CAC)

作者： Yining Wu Runfeng Zhang Fang Liu Zhenzhong Liu Jianguo Wu Haonan Dong Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Yichang Research Institute of Testing Technology Yichang China Tianjin Hanhailanfan Marine Technology Co. Ltd. Tianjin China School of Computer Science and Engineering Tianjin University of Technology Tianjin China

Waves seriously impact port construction, worldwide route planning, military activities, and wave power generation. To improve the accuracy of significant wave height prediction, we proposed a novel prediction method, a multi-layer perceptron combined with a backpropagation adjustment (MLP-BP) prediction model that combines mutation mode decomposition (VMD) and a simulated annealing optimization algorithm (SA). Firstly, we use the variable modulus method to decompose the significant wave height sequence data and transform the wave height sequence into multiple different sub-modes (IMF) to reduce the complexity and non-stationarity of the data. Secondly, the simulated annealing algorithm (SA) is used to optimize the weight and bias of the MLP-BP neural network to find the optimal parameter configuration and improve the performance and generalization ability of the prediction model. Finally, the decomposed sub-modal components of each significant wave height sequence are inserted into the MLP-BP neural network and the predicted values of each element are summed to obtain the final significant wave height prediction. The prediction results of the SSA-MLP-BP, PSO-MLP-BP, SA-MLP-BP, and VMD-SA-MLP-BP were compared and demonstrated that the VMD-SA-MLP-BP model performed best. The MAE, MAPE, MSE, RMSE, and R2 of the prediction evaluation indexes were 0.036 m, 11.7%, 0.004 m 2 , 0.067 m, and 0.983, respectively, which performed well in predicting significant wave height.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Structural strength analysis of loess based on genetic algorithm and the prediction and optimization of coal mine gas emission

引用

Arabian Journal of Geosciences 2021年第15期14卷 1-9页

作者： Xie, Xiumei Du, Xuedong Wang, Binguo College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Provincial Computer Experimental Teaching Demonstrating Center of Shandong Province Qingdao China Key Laboratory of Information Technology for Intelligence Mines in Shandong Province Qingdao China

Loess is a special kind of broken granular material, and its structure is closely related to its physical and mechanical properties. From the macroscopic and microscopic study of loess to the multi-step comprehensive study of the development process of loess, in the study of the effect of medium on the structural strength characteristics of loess, many scholars have deeply discussed. At present, the main research direction of loess deformation and fracture is to clarify the nature and mechanism of macro-deformation of loess, especially from the change of microstructure. Therefore, it is of great scientific significance to study and explore the relationship between structure and soil shear strength, which can also provide guidance for specific engineering practice theory. In this paper, the deformation and microstructure characteristics of loess are analyzed according to the water content, and the Q3 loess in Y City is mainly studied. Based on genetic algorithm, the relationship between soil structure and deformation and failure characteristics is studied. However, JRBF network has many uncertain parameters, so it is difficult to determine the optimal value. Therefore, using RBF neural network to predict mine gas emission has certain limitations. In this paper, we use genetic algorithm to optimize and simplify the structure and parameters of RBF network and establish a GA-RBF prediction model to predict the amount of gas emission. The model keeps the best value of network parameters based on the principle of advantages and disadvantages and uses transformation and other operations to select escape algorithm. The simulation results show that the prediction accuracy of ca-rbf is better than that of traditional RBF, and the training speed is also greatly improved. According to the research of genetic algorithm, it is applied to loess structure and mine gas emission, which can effectively improve the loess structure and mine gas emission.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Double Transformed Tubal Nuclear Norm Minimization for Tensor Completion

引用

Transactions of Nanjing University of Aeronautics and Astronautics 2022年第S01期39卷 166-174页

作者： TIAN Jialue ZHU Yulian LIU Jiahui College of Computer Science and Technology/College of Artificial Intelligence Nanjing University of Aeronautics and AstronauticsNanjing 211106P.R.China Fundamental Experimental Teaching Department Nanjing University of Aeronautics and Astronautics

Non-convex methods play a critical role in low-rank tensor completion for their approximation to tensor rank is tighter than that of convex *** they usually cost much more time for calculating singular values of large *** this paper,we propose a double transformed tubal nuclear norm(DTTNN)to replace the rank norm penalty in low rank tensor completion(LRTC)*** turns the original non-convex penalty of a large tensor into two convex penalties of much smaller tensors,and it is shown to be an equivalent ***,DTTNN could take advantage of non-convex envelopes while saving *** results on color image and video inpainting tasks verify the effectiveness of DTTNN compared with state-of-the-art methods.

关键词： double transformed tubal nuclear norm low tubal-rank non-convex optimization tensor factorization tensor completion

来源：评论

学校读者我要写书评

暂无评论

Reply to:comment on"Early cancer detection by serum biomolecular fingerprinting spectroscopy with machine learning"

引用

光：科学与应用（英文版） 2025年第2期14卷 566-578页

作者： Shilian Dong Dong He Qian Zhang Chaoning Huang Zhiheng Hu Chenyang Zhang Lei Nie Kun Wang Wei Luo Jing Yu Bin Tian Wei Wu Xu Chen Fubing Wang Jing Hu Xiangheng Xiao School of Physics and Technology National Demonstration Center for Experimental Physics EducationWuhan UniversityWuhan 430072China Department of Laboratory Medicine Zhongnan Hospital of Wuhan UniversityWuhan 430071China School of Computer Science Wuhan UniversityWuhan 430072China Department of Hepatobiliary Pancreatic Surgery Hubei Cancer HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430079China Department of Clinical Laboratory Tianjin Medical University General HospitalTianjin 300052China Department of Blood Transfusion Wuhan Hospital of Traditional Chinese and Western MedicineTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430022China Laboratory of Printable Functional Materials and Printed Electronics Research Center for Graphic CommunicationPrinting and PackagingWuhan UniversityWuhan 430072China Sichuan Provincial Key Laboratory for Human Disease Gene Study and the Center for Medical Genetics Department of Laboratory MedicineSichuan Academy of Medical Sciences & Sichuan Provincial People's HospitalUniversity of Electronic Science and TechnologyChengdu 611731China School of Medicine University of Electronic Science and Technology of ChinaChengdu 611731China

Dear Editor, In the accompanying Comment,Bratchenko et *** two concerns about the spectral data analysis pipeline employed for the Surface-enhanced Raman scattering and Artificial Intelligence for Cancer Screening(SERS-AICS)technique in our original paper1:(1)inappropriate accu-racy presentation and(2)the use of a single data split for model *** a promising technique for molecular fingerprinting,SERS-based early cancer detection approaches using biofluids and liquid biopsy are typically evaluated based strictly on their accuracy and reliability2-8.

关键词： fingerprinting learning detection cancer with biomolecular comment early machine reply

来源：评论

学校读者我要写书评

暂无评论

Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution

引用

IEEE Transactions on Multimedia 2025年

作者： Fu, Congrui Yuan, Hui Jiang, Shiqi Zhang, Guanghui Shen, Liquan Hamzaoui, Raouf Center of Experimental Teaching China Shandong University School of Control Science and Engineering China Ministry of Education Key Laboratory of Machine Intelligence and System Control China Shandong University School of software Shandong Jinan China Shandong University School of Computer Science and Technology China Shanghai University School of Communication and Information Engineering Shanghai China De Montfort University School of Engineering and Sustainable Development LeicesterLE1 9BH United Kingdom

By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose a convolutional neural network (CNN) for space-time video super-resolution, namely GIRNet. Our method combines long-term global information and short-term local information from the video to better extract complete and accurate spatial-temporal information. To generate highly accurate features and thus improve performance, the proposed network integrates a feature-level temporal interpolation module with deformable convolutions and a global spatial-temporal information-based residual convolutional long short-term memory (convLSTM) module. In the feature-level temporal interpolation module, we leverage deformable convolution, which adapts to deformations and scale variations of objects across different scene locations. This provides a more efficient solution than conventional convolution for extracting features from moving objects. Our network effectively uses forward and backward feature information to determine inter-frame offsets, leading to the direct generation of interpolated frame features. In the global spatial-temporal information-based residual convLSTM module, the first convLSTM is used to derive global spatial-temporal information from the input features, and the second convLSTM uses the previously computed global spatial-temporal information feature as its initial cell state. This second convLSTM adopts residual connections to preserve spatial information, thereby enhancing the output features. Experiments on the Vimeo90K dataset show that the proposed method outperforms open source state-of-the-art techniques in peak signal-to-noise-ratio (by 1.45 dB, 1.14 dB, and 0.2 dB over STARnet, TMNet, and 3DAttGAN, respectively), structural similarity index(by 0.027, 0.023, and 0.006 over STARnet, TMNet, and 3DAttGAN, respectiv

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Boiling simulation and PEC evaluation of helically corrugated tubes in vertical grooves with different pipe diameters 4

Boiling simulation and PEC evaluation of helically corrugate...

引用

4th International Conference on Material Strength and Applied Mechanics, MSAM 2021

作者： Gao, J.Y. Teng, W.Q. Wang, J.F. Xie, J. College of Food Science and Technology Shanghai Ocean University Shanghai201306 China Shanghai Prof. Technol. Serv. Platform on Cold Chain Equip. Performance and Energy Saving Evaluation Shanghai201306 China Shanghai Engineering Research Center of Aquatic Product Processing and Preservation Shanghai201306 China National Experimental Teaching Demonstration Center for Food Science and Engineering Shanghai201306 China

The double tube structure is simulated, R32 in the inner helical corrugated tubes with vertical grooves is heated by the water flowing in the outer tube to make it boil. The influence of pipe diameter and number of vertical grooves on the performance of double tube is analyzed. The evaporation temperature of the refrigerant is 283K. The temperatures of inlet refrigerant and inlet water are 280K and 320K, respectively. The flow velocity of inlet refrigerant and inlet water are 1m/s and 5m/s, respectively. The simulation results show that, compared with the smooth pipe, when the inner pipe diameter is 3, 4, 5, 6, 7mm, the surface heat transfer coefficients of the double tube have been increased by 160%, 150%, 147%, 138%, and 130%, respective. when PEC=1.691, the performance of the inner helical corrugated tube is the best, whose inner pipe diameter is 3 mm, outer pipe diameter is 6.2 mm, number of vertical grooves is 10. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Refrigerants

来源：评论

学校读者我要写书评

暂无评论

Construction of practical teaching system for integration of specialism and innovation based on virtual simulation technology 29th

Construction of practical teaching system for integration of...

引用

29th National Conference on computer science technology and Education, NCCSTE 2019

作者： Wang, Yangping Dang, Jianwu Yong, Jiu Wang, Wenrun Yue, Biao School of Electronic and Information Engineering Lanzhou Jiaotong University Lanzhou China National Computer Science and Technology Experimental Teaching Demonstration Center Lanzhou Jiaotong University Lanzhou China Gansu Provincial Engineering Research Center for Artificial Intelligence and Graphics and Image Processing Lanzhou China

ISBN: (纸本)9789811553899

The practical teaching for the majors of rail transit in colleges and universities involves a large number of high-cost, high-consumption, large-scale or comprehensive training. It will often encounter high-risk or extreme environment, inaccessible or irreversible operation, which seriously affects the cultivation of students professional engineering ability. In this paper, a practical teaching system based on virtual simulation technology is constructed for rail transit specialty. The system integrates the professional advantages and practical platform in the university, develops virtual simulation experimental teaching resources and practical teaching cases, and enables students to carry out "independent, cooperative and inquiry" learning in an open, safe, realistic and interactive virtual environment. This system will enhance students professional engineering practice ability and innovation ability, promote the training level of rail transit professionals and the overall quality of students. And for students, it can achieve the goal of strengthening the basic principles of curriculum, training design and research thinking, and enhancing innovation and entrepreneurship ability. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Fingertip interactive tracking registration method for AR assembly system

引用

Advances in Computational Intelligence 2022年第2期2卷 1-26页

作者： Jiu, Yong Jianguo, Wei Yangping, Wang Jianwu, Dang Xiaomei, Lei The National Virtual Simulation Experiment Teaching Center of Railway Traffic Information and Control Lanzhou Jiaotong University Lanzhou China College of Intelligence and Computing Tianjin University Tianjin China The National Experimental Teaching Demonstration Center of Computer Science and Technology Lanzhou Jiaotong University Lanzhou China The School of Electronic and Information Engineering Lanzhou Jiaotong University Lanzhou China Gansu Provincial Engineering Research Center for Artificial Intelligence and Graphics and Image Processing Lanzhou China Gansu Meteorological Service Meteorological Information and Technological Supporting Center Lanzhou China

Aiming at the problems of single input mode and lack of naturalness in the assembly process of existing AR systems, a tracking registration method of mobile AR assembly system is proposed based on multi-quantity and multi-degree of freedom natural fingertip interaction. Firstly, the real-time and stable tracking of hand area in complex environment is realized based on the hand region tracking; secondly, the fingertip detection and recognition based on K-COS and parallel vector is used to improve the precision and stability of fingertip recognition; thirdly, the special movement track of fingertip is recognized based on improved DTW algorithm, which has strong compatibility and feature gradient transformation for complex fingertip trajectory recognition; finally, through the real-time transformation of projection relationship between fingertip and virtual object, the interaction between fingertip and virtual object is made more natural and realistic. The experimental results show that in the complex environment of background, illumination, scale and rotation, the precision of fingertip detection and recognition is about 93%, and the precision of fingertip motion template matching is about 91%. The translation error of the registration method based on visual feature recognition is reduced by about 100pix compared with fingertip tracking registration method, and the efficiency of mobile AR-guided assembly method is improved by about 24.77% compared with the traditional manual assisted assembly method. These data verifies the strong interaction and practicability of the fingertips based on the user's multi-quantity and multi-degree of freedom features in the process of mobile AR guided assembly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development and Characterization of Starch/Polyvinyl Alcohol Controlled Release Active Film Containing Microporous Starch Loaded with Oregano Essential Oil

SSRN

引用

SSRN 2022年

作者： Wang, Jiaxi Gao, Hao Chen, Chenwei Xie, Jing College of Food Science and Technology Shanghai Ocean University Shanghai 201306 China Shanghai Engineering Research Center of Aquatic-Product Processing & Preservation Shanghai 201306 China Ministry of Agriculture Shanghai 201306 China National Experimental Teaching Demonstration Center for Food Science and Engineering Shanghai Ocean University Shanghai 201306 China

Microporous starch (MS) was used as an adsorption carrier to load with oregano essential oil (OEO).The starch/polyvinyl alcohol (STA/PVA) films containing OEO or MS loaded with OEO (OEO-MS) were prepared and their effects on the film properties were investigated. The SEM results demonstrated that loading OEO into MS promoted dispersion of OEO in the film. The incorporation of OEO-MS improved tensile strength of film and reduced its flexibility. The water vapor and oxygen permeability of film decreased for OEO-MS incorporation, while the addition of OEO showed opposite results. Their incorporations showed little influence on the films’ thermal stability. The film containing OEO or OEO-MS both exhibited antioxidant and antibacterial activities. It showed the release rate of OEO from films into the food simulant was slowed down significantly for loading OEO into MS. It indicated a good potential to develop the controlled release STA/PVA active packaging film based on this concept. © 2022, The Authors. All rights reserved.

关键词： Starch

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：