检索结果-内蒙古大学图书馆

image processing and Computer applications (ICIPCA), IEEE International Conference on

作者： Shengkai Wang School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China

ISBN: (数字)9798350360240

ISBN: (纸本)9798350384161

In this paper, the problem of precise control of single-stage inverted pendulum system is deeply discussed and practiced. The dynamic modeling and simulation of the inverted pendulum system were carried out in the course of the experiment, and the whole process of the inverted pendulum control was vividly reproduced by visual means, which enhanced the intuitiveness and effectiveness of the model design and control strategy analysis. In the design of control strategy, two advanced methods of neural network control and cascade fuzzy control are combined. The neural network controller uses its powerful nonlinear mapping ability and self-learning characteristics to approximate the complex dynamic behavior of the inverted pendulum system in real time and accurately. The cascade fuzzy controller realizes the hierarchical fine control of the Angle and angular velocity of the inverted pendulum through the upper and lower two-level control system, which improves the stability and robustness of the control system. After a series of rigorous experimental testing and optimization adjustment, the control output curve and the response curve of inverted pendulum state under different control methods are obtained successfully. Through the comparative analysis of these results, the advantages of the comprehensive scheme based on cascade fuzzy control and neural network control in improving the stable equilibrium time of inverted pendulum, reducing the overthrow amplitude and enhancing the anti-disturbance ability are revealed, and the effectiveness and superiority of the control strategy are verified, providing a new idea and reference for the theoretical research and practical application of inverted pendulum control.

关键词： Fuzzy control Analytical models Visualization neural networks Process control Stability analysis Robustness Real-time systems Angular velocity Testing

来源：评论

学校读者我要写书评

暂无评论

Solving Optimization Problems Through Fully Convolutional networks: An Application to the Traveling Salesman Problem

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2021年第12期51卷 7475-7485页

作者： Ling, Zhengxuan Tao, Xinyu Zhang, Yu Chen, Xi Zhejiang Univ Coll Control Sci & Engn Hangzhou 310027 Peoples R China Zhejiang Univ Coll Control Sci & Engn Key Lab Ind Control Technol Hangzhou 310027 Peoples R China

In the new wave of artificial intelligence, deep learning is impacting various industries. As a closely related area, optimization algorithms greatly contribute to the development of deep learning. But the reverse applications are still insufficient. Is there any efficient way to solve certain optimization problem through deep learning? The key is to convert the optimization to a representation suitable for deep learning. In this article, a traveling salesman problem (TSP) is studied. Considering that deep learning is good at image processing, an image representation method is proposed to transfer a TSP to an image. Based on samples of a ten city TSP, a fully convolutional network (FCN) is used to learn the mapping from a feasible region to an optimal solution. The training process is analyzed and interpreted through stages. A visualization method is presented to show how an FCN can understand the training task of a TSP. Once the training is completed, no significant effort is required to solve a new TSP and the prediction is obtained on the scale of milliseconds. The results show good performance in finding the global optimal solution. Moreover, the developed FCN model has been demonstrated on TSP's with different city numbers, proving excellent generalization performance.

关键词： Urban areas Optimization Deep learning neural networks Feature extraction image resolution Heuristic algorithms Deep learning fully convolutional network (FCN) mapping optimization traveling salesman

来源：评论

学校读者我要写书评

暂无评论

SD-Depth: Light-ight Monocular Depth Estimation Using Space and Depth CNN for Real-me applications 4

SD-Depth: Light-ight Monocular Depth Estimation Using Space ...

引用

4th International Conference on Machine Learning and Intelligent Systems, MLIS 2022

作者： Ibrahem, Hatem Salem, Ahmed Kang, Hyun-Soo School of Information and Communication Chungbuk National University Korea Republic of

ISBN: (纸本)9781643683560

With the help of the space-to-depth and depth-to-space modules, we provide a convolutional neural network design for depth estimation. We show designs that down sample the spatial information of the picture utilizing space-to-depth (SD) as opposed to the widely used pooling methods (Max-pooling and Average-pooling). The space-to-depth module may shrink the image while maintaining the spatial information of the image in the form of additional depth information. This technique is far superior to Max-pooling, which diminishes the image's information and features. We also suggest a lightweight decoder step that builds a high-resolution depth map out of many low-resolution feature maps using the depth-to-space (DS) module. The suggested architecture effectively learns depth estimation with high processing speed and accuracy. We trained and evaluated our suggested model on NYU-depthV2 dataset and attained low error values (RMSE=0.342) and high delta accuracies (δ3=0.996) at a fast-processing speed (25Fps). © 2022 The authors and IOS Press.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Special Session: Architecture-Level DCIM Technologies for Edge AI Computing applications

Special Session: Architecture-Level DCIM Technologies for Ed...

引用

IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems

作者： Chun-Lung Hsu Hsuan-Yu Chen Yi-Lin Chen National Central University (NCU) Taoyuan Taiwan

ISBN: (数字)9798350366884

ISBN: (纸本)9798350366891

Nowadays, deep neural networks (DNNs) and artificial intelligence (AI) are widely used in image recognition, autonomous vehicles, speech recognition, and natural language processing. However, the Von-Neumann bottleneck slows down data retrieval from memory, consuming significant time and energy. The technique of computing in memory (CIM) (including analog CIM (ACIM) and digital CIM (DCIM)) has emerged as a solution, integrating computing logic into memory to improve power efficiency by reducing data movement. Despite CIM's advantages, it still faces challenges like accuracy, adaptability and dataflow flexibility due to the computing complexity. This paper addresses the architecture-level digital computing in memory (DCIM) framework to discuss the abovementioned issues, ensuring the features of low-power, high-precision, reconfigurability, and repairability across diverse DNN applications. Additionally, for large-scale language model applications like LLMs and Transformers, a scalable DCIM chiplet architecture is introduced, leveraging 2.5D/3D heterogeneous packaging technologies to achieve flexible scalability, meeting various edge AI computing requirements.

关键词： Three-dimensional displays Memory management Stacking Edge AI artificial neural networks Speech recognition Very large scale integration Transformers Common Information Model (computing) Common Information Model (electricity)

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Different Convolution neural Network Architectures for Hyperspectral image Classification 7

A Comparative Study of Different Convolution Neural Network ...

引用

7th International Conference on Computing, Communication and Security, ICCCS 2022 and 2022 4th International Conference on Big Data and Computational Intelligence, ICBDCI 2022

作者： Singh, Manoj Kumar Kumar, Brajesh MJP Rohilkhand University Department of Computer Science and Information Technology Uttar Pradesh Bareilly243006 India

ISBN: (纸本)9798350309904

In recent years, remote sensing and other applications have used hyperspectral image processing in a variety of ways. For more precise and in-depth information extraction, hyperspectral images offer a wealth of spectral information to recognize and discriminate spectrally identical materials. Numerous cutting-edge methods based on spectral and spatial data are available for hyperspectral image classification. Convolutional neural network (CNN), a subclass of artificial neural networks has gained popularity in a number of fields, including hyperspectral image classification. CNN is built to automatically and adaptively learn spatial hierarchies of data by backpropagation using a variety of building blocks, including convolution layers, pooling layers, and fully connected layers. In this paper, different CNN architectures such as IDCNN, 2D-CNN, 3D-CNN and 3D2D-CNN are evaluated to classify hyperspectral images. Experiments are performed on Indiana Pines and Pavia University images. Experimental results show that 3D2D-CNN gives highest classification accuracy. © 2022 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

artificial neural networks for Recognition of Brain Tumors on MRI images 16th

Artificial Neural Networks for Recognition of Brain Tumors o...

引用

16th International Conference on Information and Communication Technologies in Education, Research, and Industrial applications, ICTERI 2020

作者： Kondratenko, Yuriy Sidenko, Ievgen Kondratenko, Galyna Petrovych, Valentyn Taranov, Mykyta Sova, Ivan Intelligent Information Systems Department Petro Mohyla Black Sea National University 68th Desantnykiv Street 10 Mykolaiv54003 Ukraine

ISBN: (纸本)9783030775919

In this paper, artificial neural networks for recognition of brain tumors on MRI images are analyzed. This analysis allows to choose the most appropriate neural network architecture and various preprocessing techniques to increase the precision of tumor instance recognition. Understanding the image and extracting information from it to accomplish some result is an important area of application in digital image technology. image recognition has quickly found its use in medicine and specifically oncology. Precise recognition masks may not be critical in other cases, but marginal recognition errors in medical images may render the results unreliable for clinical use. Therefore, biomedical problems require much higher boundary detection precision to improve further analysis. Various methods and algorithms for image recognition and segmentation are considered. The advantages and disadvantages of neural network architectures (ResNet, U-Net, SegNet, YOLO v3) are considered and analyzed in more detail. Additionally, the analysis of data preprocessing methods was carried out, as well as a study of the input data. Comparison of different artificial neural networks algorithms and architectures will achieve the highest accuracy of recognition. During the comparison, a system of the U-Net architecture with additional processing methods was selected as the final model. Its accuracy reached 94%, which is a significant result compared to manual image recognition. © 2021, Springer Nature Switzerland AG.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of lightweight network-based bot detection using mouse movements

引用

ENGINEERING applications OF artificial INTELLIGENCE 2024年 135卷

作者： Niu, Hongfeng Zhou, Yuxun Chen, Jiading Cai, Zhongmin Xi An Jiao Tong Univ MOE KLINNS Lab 28 Xianning West Rd Xian 710049 Peoples R China Henan Polytech Univ Sch Comp Sci & Technol Jiaozuo 454000 Henan Peoples R China

Confronted with the challenge of malicious bot abuse disrupting daily life, bot detection has become a crucial field of research. Among the various methods proposed, a behavior-driven framework analyzing mouse movements stands out for its widespread applicability, adaptability, and non-intrusive nature. Traditionally, this area of research has relied on manually extracted features from mouse dynamics and classical machine learning techniques, which often struggle to identify complex behavior patterns. To address these limitations, our research turns to Convolutional neural networks (CNNs), which have proven effective in image processing, to explore their application in bot detection using mouse movement data. We employ various visual representation techniques to convert mouse movements into trajectory images suitable for CNN analysis. Our empirical findings show that among all the lightweight networks tested, EfficientNet_b3 not only achieves the highest accuracy, with an impressive precision of 99.82%, but also surpasses more complex models like ResNet50 in terms of detection accuracy and modeling speed. These results not only enhance the practical application of deep learning in bot detection but also offer valuable insights into more effective strategies for advancing bot detection technologies.

关键词： Bot detection Mouse movements Convolutional neural Network Lightweight network

来源：评论

学校读者我要写书评

暂无评论

Development of NDVI Prediction Model Using artificial neural networks 4th

Development of NDVI Prediction Model Using Artificial Neura...

引用

4th International Conference on Recent Trends in image processing and Pattern Recognition, RTIP2R 2021

作者： Gaikwad, Sandeep V. Vibhute, Amol D. Kale, Karbhari V. Department of Computer Science and IT Dr. Babasaheb Ambedkar Marathwada University MH Aurangabad431004 India School of Computer Science MIT-World Peace University MH Pune411038 India

ISBN: (纸本)9783031070044

The use of remotely sensed images in the agriculture sector plays a vital role in knowing crop status on a higher spatial scale. Researchers have developed various indices for this purpose. The Normalized Difference Vegetation Index (NDVI) is an important indices that measure the vegetation vigor of crop. The agricultural community has shown its uses in various applications, viz. crop growth assessment, crop health monitoring, crop yield estimation, etc. The NDVI forecasting helps to make an educated guess, based on its temporal behavior in past years, on likely vegetation conditions ahead of time and thus supports decision-makers to formulate mitigation strategies. In this paper, Moderate-resolution Imaging Spectroradiometer (MODIS) satellite data has been used to calculate the NDVI, and then NDVI forecasting is performed based on 2002–2014 NDVI time-series data. The results are promising and can be used in agricultural applications. © 2022, Springer Nature Switzerland AG.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Convolutional neural networks

arXiv

引用

arXiv 2023年

作者： Skliar, Andrii Weiler, Maurice Gavves, Efstratios

Deep Learning is mostly responsible for the surge of interest in artificial Intelligence in the last decade. So far, deep learning researchers have been particularly successful in the domain of image processing, where Convolutional neural networks are used. Although excelling at image classification, Convolutional neural networks are quite naive in that no inductive bias is set on the embedding space for images. Similar flaws are also exhibited by another type of Convolutional networks - Graph Convolutional neural networks. However, using non-Euclidean space for embedding data might result in more robust and explainable models. One example of such a non-Euclidean space is hyperbolic space. Hyperbolic spaces are particularly useful due to their ability to fit more data in a low-dimensional space and tree-likeliness properties. These attractive properties have been previously used in multiple papers which indicated that they are beneficial for building hierarchical embeddings using shallow models and, recently, using MLPs and RNNs. However, no papers have yet suggested a general approach to using Hyperbolic Convolutional neural networks for structured data processing, although these are the most common examples of data used. Therefore, the goal of this work is to devise a general recipe for building Hyperbolic Convolutional neural networks. We hypothesize that ability of hyperbolic space to capture hierarchy in the data would lead to better performance. This ability should be particularly useful in cases where data has a tree-like structure. Since this is the case for many existing datasets (Miller, 1995;Deng et al., 2009;Toutanova et al., 2015), we argue that such a model would be advantageous both in terms of applications and future research prospects. © 2023, CC BY.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Efficient Design of artificial neural networks using Approximate Compressors and Multipliers 7

Efficient Design of Artificial Neural Networks using Approxi...

引用

7th IEEE International Symposium on Smart Electronic Systems (IEEE-iSES)

作者： Naresh, Kattekola Majumdar, Shubhankar Sai, Y. Padma Sai, P. Rohith NIT Meghalaya ECE Dept Shillong Meghalaya India VNR VJIET Hyderabad Telangana India VNR VJ1ET ECE Dept Hyderabad Telangana India

ISBN: (纸本)9781728187532

Nowadays, artificial neural networks (ANNs) secured impressive results with multiple applications and approaches in various research fields, as well as image processing, face recognition and semantic segmentation. Here, the focus is to minimize the complexity of ANN hardware in keeping accuracy as a major concern. ANN is a subsystem that is approximate, in machine learning where it trains the neurons to get the relevant output according to the target value. By using this ANN, interfacing can be possible between approximate arithmetic circuits. 3:2, 4:2 compressors are designed with unique error positions, usually gives better power area and delay constraints in between 5 to 25%. The designed approximate ANN gains the design constraints in the range of 3 to 30%. The simulation results were done by using synopsys design compiler at 90nm Technology.

关键词： Approximate Computing artificial neural networks Multipliers Neurons Compressors

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：