检索结果-内蒙古大学图书馆

计算机科学与技术汇刊（中英文版） 2022年第1期9卷 1-7页

作者： Qingkun Huang Askar Mijiti Dali Nursing Vocational College Dali 671000 Nanjing university of Finance&Economics Nanjing 210000

Background:The rapid development of the automobile industry has led to an increase in the output and holdings of automobiles year by year,which has brought huge challenges to the current traffic ***:This paper adopts a traffic sign recognition technology based on deep convolution neural network(CNN):step 1,preprocess the collected traffic sign images through gray processing and near interpolation;step 2,automatically extract image features through the convolutional layer and the pooling layer;step 3,recognize traffic signs through the fully connected layer and the Dropout ***:Artificial intelligence technology is applied to traffic management to better realize intelligent traffic assisted ***:This paper adopts an adam optimization algorithm for calculating the loss *** average accuracy of the experimental classification is 98.87%.Compared with the traditional gradient descent algorithm,the experimental model can quickly converge in a few iteration cycles.

关键词： Traffic Sign Recognition Convolution Neural Network(CNN) adam algorithm

来源：评论

学校读者我要写书评

暂无评论

Weld Image Recognition algorithm Based on Deep Learning

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2020年第8期34卷

作者： Li, Yan Hu, Miao Wang, Taiyong Tianjin Univ Minist Educ Key Lab Mech Theory & Equipment Design Tianjin 300072 Peoples R China Lingyun Ind Corp Ltd Res & Dev Ctr Zhuozhou 072761 Peoples R China Tianjin Univ Tianjin Engn Res CNC Technol Tianjin 300072 Peoples R China

As an important part of metal processing, welding is widely used in industrial manufacturing activities, and its application scenarios are very extensive. Due to technical limitations, the welding process always unavoidably leaves weld defects. Weld defects are extremely hazardous, and the work used must be guaranteed to be defect-free, regardless of the field. However, manual weld inspection has subjective factors such as inefficiency and easy missed detection, and although some automatic weld inspection methods have appeared, these traditional methods still do not meet actual demand in terms of detection time and detection accuracy. Therefore, there is a need for a higher quality weld image automatic detection method to replace the manual method and the traditional automatic detection method. In view of the above, this paper proposes a weld seam image recognition algorithm based on deep learning. The adam adaptive moment estimation algorithm is chosen as the backpropagation optimization algorithm to accelerate the training of convolutional neural networks and design an independent adaptive learning rate. Through the simulation of the collected 4500 tube images, the adaptive threshold-based method is used for weld seam extraction. The algorithm proposed in this paper is compared with the weld seam recognition method based on image texture feature value distribution (ITFVD) and the SUSAN-based weld defect target detection method. The results show that the proposed method can identify weld defects in a short time on different sizes of weld images, and can further detect the type of weld defects. In addition, the method in this paper is better than the other two methods in the false detection rate, recall rate and overall recognition accuracy, which shows that the experimental results have achieved the expected results.

关键词： Weld image recognition adaptive threshold deep convolutional neural network adam algorithm

来源：评论

学校读者我要写书评

暂无评论

adam Bald Eagle optimization enabled transfer learning for underwater image fusion

引用

The Journal of Photographic Science 2024年第5期72卷

作者： Devika Sarath Sucharitha M a Department of Electronics and Communication Engineering Noorul Islam Centre for Higher Education Thuckalay Kumaracoil TN India b Electronics and Communication Engineering School of Electronics Engineering VIT-AP University Amaravathi AP India

ABSTRACTIn this paper, a clear underwater image is attained by a fusion process using Transfer Learning (TL). Two images are selected from the underwater colour image dataset and those images are allowed to Discrete Wavelet Transform (DWT), Tetrolet transform and Saliency maps. Here, the outputs gained from images by the Tetrolet transform are fused and allowed for inverse Tetrolet transform. Moreover, the DWT process done with two images is fused and the output gained is allowed for inverse DWT. Similarly, the same fusion process is carried out with image outputs from Saliency maps. Finally, three image outputs that are considered as input to TL with newly devised optimization. Here, Convolutional Neural Network (CNN) is used with hyperparameters from trained models, such as SqueezeNet and AlexNet, where weights are updated using adam Based Bald Eagle algorithm (ABBEA). This ABBEA is obtained by combining the Bald Eagle Search (BES) algorithm and adam algorithm. Further, the ABBEA has Peak Signal-to-Noise Ratio (PSNR) with maximal of 38.95, Mean Squared Error (MSE) with lesser value of 20.14, Structural Similarity Index Measure (SSIM) with maximal value of 0.92, Mutual Information (MI) with maximal value of 0.86, Signal-to-Noise Ratio (SNR) with lesser value of 0.38.

关键词： SqueezeNet Bald Eagle Search algorithm AlexNet adam algorithm Discrete Wavelet Transform Convolutional Neural Network Transfer Learning SqueezeNet

来源：评论

学校读者我要写书评

暂无评论

A new high-precision sphere-fitting method with small segment angles

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2021年第1期32卷 015012-015012页

作者： Fei, Zhigen Fu, Jixiang Ma, Jun He, Wenbin Xiao, Yanqiu Zhengzhou Univ Light Ind Henan Key Lab Intelligent Mfg Mech Equipment Zhengzhou 450002 Peoples R China

Measuring a spherical surface with small segment angle (e.g. 1 degrees) precisely is a big challenge in scientific research and engineering applications. To fit sphere surfaces with small segment angles with high precision, a five-parameter constrained nonlinear least square fitting (CNLSF) method is presented in this work, where an adam optimization algorithm with a prominent anti-interference ability is employed. We discuss various factors which influence the final uncertainty evaluation of the sphere's radius. A Monte Carlo simulation is conducted by superimposing Gaussian noise on the ideal spherical data to simulate practical instrument errors, then the relationship between the fitting bias of the sphere's radius and noise the level, the number of sampling points and the segment angle is investigated by comparing the performance of the linear least square fitting algorithm, the nonlinear least square fitting algorithm and the CNLSF algorithm. Finally, the simulated and experimental results show that the CNLSF method performs more precisely and robustly than the other algorithms, even when the corresponding segment angle approaches 1 degrees, which illustrates that it is a promising and practical method in the real measurement world.

关键词： sphere fitting constrained nonlinear least square fitting small segment angle adam algorithm

来源：评论

学校读者我要写书评

暂无评论

Data-driven product design evaluation method based on multi-stage artificial neural network

引用

APPLIED SOFT COMPUTING 2021年 103卷 107117-107117页

作者： Wang, Lei Liu, Zhengchao Wuhan Univ Technol Hubei Digital Mfg Key Lab Wuhan 430070 Peoples R China Jiangxi Univ Sci & Technol Sch Mech & Elect Engn Ganzhou 341000 Peoples R China

The application of the new generation of IT technology in the manufacturing industry has brought a rich data foundation for the research of product life cycle management. However, in the product design stage, the existing design evaluation methods have not yet effectively used the data-driven advantages, which leads to over-reliance on personal experience and inefficiency. This paper presents a new data-driven product design evaluation (PDE) method to address this problem. First, a PDE model considering multi-stage evaluation indicators of the product life cycle is established. Second, to accurately and quickly realize the nonlinear mapping between the PDE model indicators, an improved multi-stage artificial neural network (ANN) based on a hybrid optimization algorithm combining particle swarm optimization and adam (PSO-adam) is proposed. The PSO is employed for a rapid convergence during the initial stage of a global search, while adam is used to optimizing the training parameters around the global optimum adaptively. Finally, comparison experiments of the smartphone design are carried out to demonstrate the effectiveness of the multi-stage ANN and the PSO-adam. The results demonstrate the proposed approach can help designers comprehensively consider design parameters and make fast and accurate design evaluation. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Data driven Product design evaluation Artificial neural network Particle swarm optimization adam algorithm

来源：评论

学校读者我要写书评

暂无评论

Lossless Image Compression algorithm Based on Long Short-term Memory Neural Network 5

Lossless Image Compression Algorithm Based on Long Short-ter...

引用

5th International Conference on Computational Intelligence and Applications (ICCIA)

作者： Zhu, Caixin Zhang, Huaiyao Tang, Yun Univ Sci & Technol China Sch Software Engn Hefei Anhui Peoples R China

ISBN: (纸本)9781728160429

People have relatively higher requirements for image storage in some specific fields, such as high-resolution cultural relic data image, medical image, infrared remote sensing image, high-precision astronomical observation image. There cannot be any pixel loss in the storage process, so the image can only be compressed by lossless compression. In this paper, a lossless image compression algorithm based on the neural network of long short-term memory (LSTM) is proposed: a LSTM model predictor based on attention mechanism is built by utilizing the memory characteristic of cyclic neural network. The previous pixel value of the image was taken as the input of the model, then the predicted pixel was obtained through the cyclic neural network, and finally the calculated difference between these values was encoded by the mixed run-length encoding and Golomb-Rice encoding. Compared with the traditional predictive lossless image compression algorithm, this algorithm proposed here comprehensively considers the correlation between more pixels and encoded pixels. The experimental results show that compared with the lossless image compression algorithms JPEG-LS and CALIC, the proposed algorithm improves the compression rate by 25% and 12% respectively.

关键词： lossless image compression LSTM adam algorithm attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Matrix Factorization Based on BatchNorm and Preference Bias 13

Matrix Factorization Based on BatchNorm and Preference Bias

引用

13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Wang, Bing Ma, Wenming Yantai Univ Sch Comp & Control Engn Yantai 264005 Peoples R China

ISBN: (纸本)9780738105451

With the rapid development of science and technology, huge amounts of information fill people's lives, and the accompanying information overload phenomenon has become an urgent problem to be solved. Because the recommendation system can quickly find the products users want in the massive item information, to a certain extent It has attracted much attention to solve the problem of information overload. Matrix factorization is a commonly used technique in recommendation systems. It can effectively improve the recommendation effect when the scoring matrix is sparse. However, due to its own reasons, matrix factorization has many problems such as sparseness, cold start, and low interpretability. In the field of deep learning, because the normalization technology BatchNorm can optimize the training process, accelerate the training speed and make the training results more stable, it has been studied by a large number of scholars. In this paper, Matrix Factorization Based on BatchNorm and Preference Bias is proposed. BatchNorm is combined with matrix factorization, user and item preferences are added, and adam algorithm is used for optimization. Experiments show that the algorithm in this paper has a good recommendation effect on sparse matrix.

关键词： matrix factorization batchnorm bias adam algorithm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on classification diagnosis model of psoriasis based on deep residual

引用

Digital Chinese Medicine 2021年第2期4卷 92-101页

作者： LI Peng YI Na DING Changsong LI Sheng MIN Hui School of Informatics Hunan University of Chinese MedicineChangshaHunan 410208China The Third Xiangya Hospital of Central South University ChangshaHunan 410013China Key Laboratory of Medical Information Research Central South UniversityCollege of Hunan ProvinceChangshaHunan 410013China Software Institute Hunan College of InformationChangshaHunan 410200China

Objective A classification and diagnosis model for psoriasis based on deep residual network is proposed in this *** using deep learning technology to classify and diagnose psoriasis can help reduce the burden of doctors,simplify the diagnosis and treatment process,and improve the quality of *** Firstly,data enhancement,image resizings,and TFRecord coding are used to preprocess the input of the model,and then a 34-layer deep residual network(ResNet-34)is constructed to extract the characteristics of ***,we used the adam algorithm as the optimizer to train ResNet-34,used cross-entropy as the loss function of ResNet-34 in this study to measure the accuracy of the model,and obtained an optimized ResNet-34 model for psoriasis *** The experimental results based on k-fold cross validation show that the proposed model is superior to other diagnostic methods in terms of recall rate,F1-score and ROC *** The ResNet-34 model can achieve accurate diagnosis of psoriasis,and provide technical support for data analysis and intelligent diagnosis and treatment of psoriasis.

关键词： Psoriasis Deep residual network Data enhancement Cross-entropy adam algorithm Recall

来源：评论

学校读者我要写书评

暂无评论

ANFIS system for classification of brain signals

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2019年第3期37卷 4033-4041页

作者： de Jesus Rubio, Jose Ricardo Cruz, David Elias, Israel Ochoa, Genaro Balcazar, Ricardo Aguilar, Arturo Inst Politecn Nacl Secc Estudios Posgrad & Invest ESIME Azcapotzalco Av Granjas 682 Mexico City 02250 DF Mexico

Recently, the Adaptive-Network-Based Fuzzy Inference System (ANFIS) is applied in many areas of knowledge, and there are multiple optimization algorithms for its learning. This work shows the design of a novel optimization algorithm for an ANFIS system that learns and classifies the behavior of brain signals between normal and abnormal. For this goal, different types of optimization algorithms for the learning of an ANFIS system are evaluated, such as the backpropagation, the mini-lots, and the adam algorithm (adaptive moment estimation). As a result, utilizing the ANFIS with adam and mini-lots provides the most accurate, fastest, and with least computational costs results.

关键词： adam algorithm ANFIS system mini-lots classification of brain signals

来源：评论

学校读者我要写书评

暂无评论

Application of Deep neural Network in Air Target Threat Assessment 3

Application of Deep neural Network in Air Target Threat Asse...

引用

IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)

作者： Zhao, Jun Guo, Qiang Teng, Long Hu, Wenfei China Aviat Radio Elect Res Inst Shanghai Peoples R China Harbin Engn Univ Coll Informat & Commun Engn Harbin Heilongjiang Peoples R China Wenzhou Vocat & Tech Coll Wenzhou Peoples R China

ISBN: (纸本)9781538662434

Air target threat assessment is a key factor in airborne sensor resource *** order to improve the accuracy of evaluation, this paper proposes a new method of target threat assessment based on Rectified Linear Units (ReLU) deep neural network (RL-DNN). Target threat assessment model and algorithm for RL-DNN predictor are *** model adds the number of network layers based on the BP neural network, using ReLU as the activation function, and the adam algorithm for back propagation, which effectively avoiding the problem of slow learning rate and falling into local *** results show that the algorithm based on RL-DNN is higher than that based on the traditional algorithms, which proves the proposed algorithm has good predictive ability and can accurately complete the air target threat assessment.

关键词： sensor resource management RL-DNN target threat assessment adam algorithm

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：