检索结果-内蒙古大学图书馆

Weld Image Recognition algorithm Based on Deep Learning

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

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

Parameter Training Methods for Convolutional Neural Networks With Adaptive Adjustment Method Based on Borges Difference

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2022年 70卷 673-685页

作者： Jian, Jing Gao, Zhe Kan, Tao Liaoning Univ Sch Math Shenyang 110036 Peoples R China Liaoning Univ Coll Light Ind Shenyang 110036 Peoples R China

This paper proposes a momentum algorithm based on Borges difference and an adaptive momentum (adam) algorithm based on Borges difference to update parameters, which can adjust the momentum information more flexibly. The Borges difference is proposed from the definition of Borges derivative to be combined with the gradient algorithm in convolutional neural networks. The proposed momentum algorithm based on Borges difference and adam algorithm based on Borges difference can be adjusted more flexibly in order to speed up the convergence. The parameter optimization algorithm with the Borges difference presents a better performance compared with the integer-order momentum algorithm and integer-order adam algorithm, with the proposed nonlinear adjustment method for the parameter tuning of convolutional neural networks. By analyzing experimental results of Fashion-MNIST dataset and CIFAR-10 dataset, the optimization algorithms based on Borges difference proposed in this paper gain better effects on the optimization model compared with the corresponding ones based on the integer-order difference, and can speed up the convergence speed and recognition accuracy of the image recognition.

关键词： Signal processing algorithms Optimization Neural networks Fractals Convergence Training Calculus Fractal difference convolution neural networks momentum adam algorithm nonlinear adaptive tuning method

来源：评论

学校读者我要写书评

暂无评论

CBR Prediction of Pavement Materials in Unsoaked Condition Using LSSVM, LSTM-RNN, and ANN Approaches

引用

INTERNATIONAL JOURNAL OF PAVEMENT RESEARCH AND TECHNOLOGY 2024年第3期17卷 750-786页

作者： Khatti, Jitendra Grover, Kamaldeep Singh Rajasthan Tech Univ Dept Civil Engn Kota India

The present research introduces the best architecture model for predicting the unsoaked California bearing ratio (CBRu) of soil by comparing the models based on the least square support vector machine (LSSVM), long- short-term memory (LSTM), and artificial neural network (ANN) approach. The two kernel functions, linear and polynomial, have been selected to create LSSVM models. The developed LSTM models have been optimized by the adam algorithm. In the employed ANN models, the Levenberg-Marquardt (LM), BFGS Quasi-Newton (BFG), scaled conjugate gradient (SCG), gradient descent with momentum (GDM), gradient descent (GD), and gradient descent with adaptive learning (GDA) algorithms have been used in the backpropagation process. For this purpose, three databases, such as training, testing and validation, have been compiled from the published research. A laboratory database has been developed by performing laboratory experiments for soil samples collected from and around Kota, Rajasthan, used for cross-validation of the best architecture model. The statistical tools, such as root means square error (RMSE), mean absolute error (MAE), correlation coefficient (R), mean absolute percentage error (MAPE), variance accounted for (VAF), weighted mean absolute percentage error (WMAPE), Nash-Sutcliffe efficiency (NS), normalized mean bias error (NMBE), Legate and McCabe's index (LMI), root mean square error to observation's standard deviation ratio (RSR), a20-index, index of agreement (IOA) and index of scatter (IOS) have been used to measure the performance of the models. The LSTM model MD 14 has achieved higher performance and accuracy (RMSE = 0.9127%, MAE = 0.8114%, R = 0.9863%, MAPE = 9.0772%, VAF = 97.26, WMAPE = 0.0669%, NS = 0.9708, NMBE = 0.0687%, LMI = 0.1926, RSR = 0.1708, a20-index = 93.88, IOA = 0.9037 and IOS = 0.0752) in testing phase. For the performance validation, model (MD) 14 has predicted the CBRu of the validation database. Also, model MD 14 has attained higher

关键词： Artificial neural network adam algorithm Effect of training database Effect of backpropagation algorithm Least square support vector machine Long short-term memory Unsoaked California bearing ratio

来源：评论

学校读者我要写书评

暂无评论

adam teaching learning optimization enabled LeNet for autism spectrum disorder detection using brain MRI

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2024年 90卷

作者： Dhamale, T. D. Bhandari, Sheetal U. Pimpri Chinchwad Coll Engn SPPU Dept Elect & Telecommun Pune Maharashtra India

The autism spectrum disorder (ASD) is a complicated, lifetime, neuro-developmental circumstance of highly unknown causes. It is greatly more ordinary than formerly believed, frequency only to mental retardation amongst serious developmental disorders. Even though, a heritable element is demonstrated in the etiology of ASD, reputed risk genes are still to be detected. Therefore, adam Teaching Learning Optimization-LeNet (ATLOLeNet) is introduced for the detection of ASD utilizing brain Magnetic Resonance Imaging (MRI). Here, input considered is provided for the image pre-processing, wherein extraction of Region of Interest (ROI) is performed and median filter is used to eradicate noises. Then, extraction of the pivotal region is completed by the devised ATLO and hence, output-1 is obtained. On the other side, features are mined from an input MRI image. The extracted features include statistical features as well as texture features. From extracted features, output-2 is attained. By considering the output-1 and output-2, ASD classification is completed by LeNet. The LeNet is trained by ATLO, which is the amalgamation of the adam algorithm and Teaching-Learning-Based Optimization (TLBO). Moreover, ATLO-LeNet acquired a maximum accuracy of 0.916, Negative Predictive Value (NPV) of 0.916and Positive Predictive Value (PPV) of 0.917 whereas it attained a minimum False Positive Rate (FPR) of 0.132 and False Negative Rate (FNR) of 0.152.

关键词： Median filter LeNet ROI extraction adam algorithm Teaching-Learning-Based Optimization (TLBO)

来源：评论

学校读者我要写书评

暂无评论

Prediction of Health Level of Multiform Lithium Sulfur Batteries Based on Incremental Capacity Analysis and an Improved LSTM

引用

Protection and Control of Modern Power Systems 2024年第2期9卷 21-31页

作者： Hao Zhang Hanlei Sun Le Kang Yi Zhang Licheng Wang Kai Wang School of Materials Science and Engineering Xi’an University of Architecture and Technology in Xi’anShanxi ProvinceChina School of Electrical Engineering Qingdao UniversityQingdao 266000China College of Materials Science and Engineering Xi’an University of Science and TechnologyXi’anShaanxi ProvinceChina School of Energy Sciences and Engineering Nanjing Tech UniversityNanjingJiangsu ProvinceChina School of Information Engineering Zhejiang University of TechnologyHangzhou provinceChina

Capacity estimation plays a crucial role in battery management systems,and is essential for ensuring the safety and reliability of lithium-sulfur(Li-S)*** paper proposes a method that uses a long short-term memory(LSTM)neural network to estimate the state of health(SOH)of Li-S *** method uses health features extracted from the charging curve and incre-mental capacity analysis(ICA)as input for the LSTM *** enhance the robustness and accuracy of the network,the adam algorithm is employed to optimize specific *** data from three different groups of batteries with varying nominal capac-ities are used to validate the proposed *** results demonstrate the effectiveness of the method in accurately estimating the capacity degradation of all three ***,the study examines the impact of different lengths of network training sets on capacity *** results reveal that the ICA-LSTM model achieves a prediction accuracy of mean absolute error 4.6%and mean squared error 0.21%with three different training set lengths of 20%,40%,and 60%.The analysis demonstrates that the lightweight model maintains high SOH estimation accu-racy even with a small training set,and exhibits strong adaptive and generalization capabilities when applied to different Li-S ***,the proposed method,supported by experimental validation and analysis,demonstrates its efficacy in ensuring accurate and reliable SOH estimation,thereby enhancing the safety and per-formance of Li-S *** Terms—adam algorithm,incremental capacity analysis,Li-S battery,long short-term memory,state of health.

关键词： adam algorithm incremental capacity analysis Li-S battery long short-term memory state of health

来源：评论

学校读者我要写书评

暂无评论

A Linear Interpolation and Curvature-Controlled Gradient Optimization Strategy Based on adam

引用

algorithmS 2024年第5期17卷 185页

作者： Sun, Haijing Zhou, Wen Shao, Yichuan Cui, Jiaqi Xing, Lei Zhao, Qian Zhang, Le Shenyang Univ Sch Intelligent Sci & Engn Shenyang 110044 Peoples R China Shenyang Univ Sch Informat Engn Shenyang 110044 Peoples R China Univ Surrey Sch Chem & Chem Engn Guildford GU2 7XH Surrey England Shenyang Univ Technol Sch Sci Shenyang 110044 Peoples R China

The adam algorithm is a widely used optimizer for neural network training due to efficient convergence speed. The algorithm is prone to unstable learning rate and performance degradation on some models. To solve these problems, in this paper, an improved algorithm named Linear Curvature Momentum adam (LCMadam) is proposed, which introduces curvature-controlled gradient and linear interpolation strategies. The curvature-controlled gradient can make the gradient update smoother, and the linear interpolation technique can adaptively adjust the size of the learning rate according to the characteristics of the curve during the training process so that it can find the exact value faster, which improves the efficiency and robustness of training. The experimental results show that the LCMadam algorithm achieves 98.49% accuracy on the MNIST dataset, 75.20% on the CIFAR10 dataset, and 76.80% on the Stomach dataset, which is more difficult to recognize medical images. The LCMadam optimizer achieves significant performance gains on a variety of neural network structures and tasks, proving its effectiveness and utility in the field of deep learning.

关键词： deep learning adam algorithm curvature-controlled gradient linear interpolation LCMadam algorithm

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

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

Multi-class Classification of Impulse and Non-impulse Sounds Using Deep Convolutional Neural Network (DCNN) 19th

Multi-class Classification of Impulse and Non-impulse Sounds...

引用

19th International Conference on Computational Science and Its Applications (ICCSA)

作者： Abayomi-Alli, Adebayo Abayomi-Alli, Olusola Vipperman, Jeffrey Odusami, Modupe Misra, Sanjay Fed Univ Agr Dept Comp Sci Abeokuta Nigeria Covenant Univ Dept Elect & Informat Engn Ota Nigeria Univ Pittsburgh Dept Mech Engn Pittsburgh PA 15261 USA

ISBN: (纸本)9783030243081

Differentiating between military sounds can be quite tasking with high false detection rate. These sounds can either be impulse sounds (sounds released from the military weapons) or non-impulse sounds (sound released from other sources) thus causing public disturbance and unnecessary panic. This paper utilizes Deep Convolutional Neural Network (DCNN) classifier to detect military impulse and non-impulse sounds and also incorporates adam algorithm for optimal classification. DCNN was utilized in this study based on its network embedded multiple hidden layers (non-linear) which can learn the very complicated relationship between the input data and require output. The dataset used in this study consist of six sound types with a total number of 37,464 datasets which was partitioned into training (67%) and testing (33%). The performance of the proposed classifier was evaluated based on the following metrics: True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), Precision, Matthews Correlation Coefficient (MCC), and Accuracy. The experimental result shows that DCNN classifier gave an optimal accuracy for the Machine gun, Wind, Thunder, Blast, Vehicle, and Aircraft sounds types as 97.43%, 96.98%, 95.16%, 95.13%, 88.83%, and 87% respectively. The average classification error rate for the six sound types was 6.57% which signifies that DCNN is a promising classifier.

关键词： Military sound DCNN Impulse and non-impulse sounds 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：