检索结果-内蒙古大学图书馆

Cost-Optimized Task Offloading for Dependent Applications in Collaborative Edge and Cloud computing

IEEE Internet of Things Journal 2025年第9期12卷 12975-12988页

作者： Yuan, Haitao Hu, Qinglong Wang, Shen Bi, Jing Buyya, Rajkumar Lu, Jinhu Yang, Jinhong Zhang, Jia Zhou, MengChu Beihang University School of Automation Science and Electrical Engineering Beijing100191 China City University of Hong Kong Department of Computer Science Kowloon Tong Hong Kong Beijing University of Technology School of Software Engineering Faculty of Information Technology Beijing100124 China Laboratory School of Computing and Information Systems MelbourneVIC3010 Australia CSSC Systems Engineering Research Institute Beijing100036 China Southern Methodist University Lyle School of Engineering Department of Computer Science DallasTX75205 United States New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States

A collaborative system that includes mobile devices (MDs), edge nodes (ENs), and the cloud is needed where ENs at the network edge can run offloaded tasks of MDs with limited resources and energy for timely processing for latency-sensitive applications. Unlike existing studies, we formulate a total cost minimization problem for the system for applications, which can be divided into several interdependent subtasks. Each subtask can be executed in MDs, ENs, and the cloud. This work formulates a mixed-integer nonlinear program to minimize the total system cost. To address it, a novel meta-heuristic optimization algorithm called Genetic Simulated-annealing-based Particle swarm optimization with Auto-Encoder (GSPAE) is proposed, which innovatively combines feature extraction of deep learning and global search of meta-heuristic optimization. Genetic operations provide diverse solutions, the Metropolis acceptance of annealing offers a robust global search, and autoencoders (AEs) extract distribution characteristics of particles toward high-quality regions for fast convergence. Thus, GSPAE optimizes the associations between ENs and MDs and the scheduling of subtasks among MDs, ENs, and the cloud. Experiments with large-scale Google cluster datasets show that compared to state-of-the-art benchmark methods, GSPAE reduces the total cost by at least 17% while strictly meeting limits of application latency, available energy, computing, and communication resources of ENs and MDs. © 2014 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Robustness of cellular neural networks in image deblurring and texture segmentation

引用

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS 1996年第3期24卷 381-396页

作者： Sziranyi, T Analogical and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (MTA SZTAKI) pf. 63 H-1518 Budapest Hungary

Template parameters of cellular neural networks (CNNs) should be robust enough to random variability of VLSI tolerances and noise. Using the CNN for image processing, one of the main problems is the robustness of a given task in a real VLSI chip. It will be shown that very different tasks such as 2D or 3D deconvolution and texture segmentation can be solved in a real VLSI CNN environment without significant loss of efficiency and accuracy under low precision (about 6-8 bits) and random variability of the VLSI parameters. The CNN turns out to be very robust against template noise, image noise, imperfect estimation of templates and parameter accuracy. The parameters of a template are tuned using genetic learning. These optimized parameters depend on the precision of the architecture. It was found that about 6-8 bits of precision is enough for a complicated multilayer deconvolution, while only 4 bits of precision is enough for difficult texture segmentation in the presence of noise and parameter variances, The tolerance sensitivity of template parameters is considered for VLSI implementation. Theory and examples are demonstrated by many results using real-life microscopic images and natural textures.

关键词： Cellular neural networks

来源：评论

学校读者我要写书评

暂无评论

Spatial depth extraction using random stereograms in analogic CNN framework

引用

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS 1996年第1期24卷 69-92页

作者： Radvanyi, AG Analogical and Neural Computing Systems Laboratory Computer and Automation Institute Hungarian Academy of Sciences POB 63 H-1518 Budapest Hungary

Demonstrated and motivated on human stereo vision analogic CNN algorithms are proposed to extract 3D spatial information from computer-generated random-dot stereograms as well as real scene random-dot like ones produced with simple optical devices, projector and camera. Several aspects of making real scene stereograms are considered to minimize perspective distortion and enable local CNN processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CNN Universal Machine as Classificaton Platform: An ART-like Clustering Algorithm

引用

International Journal of neural systems 2003年第6期13卷 415-425页

作者： Balya, David Analogical and Neural Computing Laboratory HAS Computer and Automation Research Institute Kende u. 13 BudapestH-1111 Hungary

Fast and robust classification of feature vectors is a crucial task in a number of real-time systems. A cellular neural/nonlinear network universal machine (CNN-UM) can be very efficient as a feature detector. The next step is to post-process the results for object recognition. This paper shows how a robust classification scheme based on adaptive resonance theory (ART) can be mapped to the CNN-UM. Moreover, this mapping is general enough to include different types of feed-forward neural networks. The designed analogic CNN algorithm is capable of classifying the extracted feature vectors keeping the advantages of the ART networks, such as robust, plastic and fault-tolerant behaviors. An analogic algorithm is presented for unsupervised classification with tunable sensitivity and automatic new class creation. The algorithm is extended for supervised classification. The presented binary feature vector classification is implemented on the existing standard CNN-UM chips for fast classification. The experimental evaluation shows promising performance after 100% accuracy on the training set. © 2003 World Scientific Publishing Company.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

SUBPIXEL PATTERN-RECOGNITION BY IMAGE HISTOGRAMS

引用

PATTERN RECOGNITION 1994年第8期27卷 1079-1092页

作者： SZIRANYI, T Analogical and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (MTA SZTAKI) P.O. Box 63 H-1518 Budapest Hungary

Recognition of small patterns covering only a few pixels in an image cannot be done by conventional recognition methods. A theoretically new pattern recognition method has been developed for undersampled objects which are (much) smaller than the window-size of a picture element (pixel), i.e. these objects are of subpixel size. The proposed statistical technique compares the gray-level histogram of the patterns of a set of scanned objects to be examined with the (calculated) gray-level densities of different (in shape or size) possible objects, and the recognition is based on this comparison. This method does not need high-precision movement of scanning sensors or any additional hardware. Moreover, the examined patterns should be randomly distributed on the screen, or a random movement of camera is (or target or both are) needed. Effects of noise are analysed, and filtering processes are suggested in the histogram domain. Several examples of different object shapes (triangle, rectangle, square, circle, curving lines, etc.) are presented through simulations and experiments. A number of possible application areas are suggested, including astronomy, line-drawing analysis and industrial laser measurements.

关键词： SUBPIXEL-RECOGNITION HISTOGRAM NOISE FILTERING UNDERSAMPLING SUPERRESOLUTION IMAGE ANALYSIS PATTERN CLASSIFICATION CONVOLUTION STATISTICAL PATTERN RECOGNITION LIGHT-SENSOR ARRAYS DENSITY ESTIMATION

来源：评论

学校读者我要写书评

暂无评论

Dual prototypes contrastive learning based semi-supervised segmentation method for intelligent medical applications

引用

Engineering Applications of Artificial Intelligence 2025年 154卷

作者： Yue, Tianai Xu, Rongtao Wu, Jingqian Yang, Wenjie Du, Shide Wang, Changwei Johns Hopkins University Baltimore21218 United States Jinan250014 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan250014 China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The University of Hong Kong 999077 Hong Kong College of Computer and Big Data Fuzhou University Fuzhou350108 China

In medical intelligence applications, the labeling of medical data is crucial and expensive, so it becomes urgent to explore labeling-efficient ways to train applications. Semi-supervised techniques for medical image segmentation have demonstrated potential, effectively training models using scarce labeled data alongside a wealth of unlabeled data. Therefore, semi-supervised medical image segmentation is a key issue in engineering applications of medical intelligence. Consistency constraints based on prototype alignment provide an intuitively sensible way to discover valuable insights from unlabeled data that can motivate segmentation performance. In this work, we propose a Dual prototypes Contrastive Network to motivate semi-supervised medical segmentation accuracy by imposing image-level global prototype and pixel-level local prototype constraints. First, we introduce a Background-Separation Global Prototype Contrastive Learning technique that utilizes the natural mutual exclusivity of foreground and background to separate the inter-class distances and encourage the segmentation network to obtain segmentation results that are more complete and do not contain background regions. Second, we design a Cross-Consistent Local Prototype Contrastive Learning techniques to extend the perturbation consistency of the two networks to the prototype's localized response to the feature map, thereby shaping a more stable intra-class prototype space and producing accurate and robust pixel-level predictions. Finally, we comprehensively evaluate our method on mainstream semi-supervised medical image segmentation benchmarks and settings, and experimental results show that our proposed method outperforms current state-of-the-art methods. Specifically, our method achieves a Dice Coefficient score of 91.8 on the Automatic Cardiac Diagnosis Challenge dataset using only 10% labeled data training, 1.1% ahead of the second best method. Code is available at https://***/yuelily2024/DPC

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

HIGH-SPEED CHARACTER-RECOGNITION USING A DUAL CELLULAR neural-NETWORK ARCHITECTURE (CNND)

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems II-EXPRESS BRIEFS 1993年第3期40卷 223-231页

作者： SZIRANYI, T CSICSVARI, J Analogic and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Budapest Hungary

An effective new character recognition procedure implemented on a new type of hardware system is proposed. This procedure applied a new architecture, called CNND. This CNND contains one or more analog cellular neural Networks (CNN) and some digital logic, incorporating the advantages of the fast analog CNN signal processing and the fast and easy decision capability of digital logics. This paper shows that this CNND system can be used for recognition of multifont printed or handwritten characters. Implemented in hardware, the system could hit the 100 000 char/s recognition speed with a recognition rate of more than 95 %. We show that the CNN results of pictures (maximum 40 * 40 pixels) of printed characters can be coded into about n * 20 bits (n = 2 ... 6) , so the coded results can be used to address memories of about 1 MB. The codes of CNN results of possible character pictures are used to address the memories while the memory contents are filled by the character categories. Prior to the hardware implementation the decision memories are filled by the results of recognition simulation for the possible pictures of each character-class in a filling procedure. In the memory filling procedure the simulated recognition uses a new random-type nearest neighbor (NN) method, which is ideal for the recent proposal of hardware applications. Recognition of handwritten characters is demonstrated in the same system with good recognition accuracy.

关键词： Character recognition Cellular neural networks Image edge detection Handwriting recognition neural networks Detectors Logic Hardware Charge coupled devices Filling

来源：评论

学校读者我要写书评

暂无评论

FORMING AN INFORMATION TECHNOLOGY DEPARTMENT IN TURBULENT TIMES

引用

IEEE COMMUNICATIONS MAGAZINE 1992年第11期30卷 52-56页

作者： ROSKA, T Dual and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (ATOMKI) Hungary

The goals, objectives, characteristics, prerequisites, and courses of an information technology curriculum developed at the University of Veszprem in Hungary are discussed. Basic, introductory, and core courses as well as special subjects are listed, and the program schedule of the five years is presented. The place and role of information engineering in a changing world is discussed, including some thoughts on the role of information technology in the general university curricula.< >

关键词： Information technology Laboratories Education Educational technology automation Europe Mechanical engineering Electrical engineering computing Informatics Solids

来源：评论

学校读者我要写书评

暂无评论

DFMC:Feature-Driven Data-Free Knowledge Distillation

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Zhang, Zherui Xu, Rongtao Wang, Changwei Xu, Wenhao Chen, Shunpeng Xu, Shibiao Xu, Guangyuan Guo, Li Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing100876 China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing100190 China Qilu University of Technology Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250316 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China

Data-Free Knowledge Distillation (DFKD) enables knowledge transfer from teacher networks without access to the real dataset. However, generator-based DFKD methods often suffer from insufficient diversity or low-confidence in synthetic images, negatively impacting student network performance. This paper introduces DFMC, a generative feature-driven framework to mitigate the inherent limitations of DFKD. We propose exploiting semantic description between generative feature domains to guide augmentation strategies, avoiding random abstract inputs caused by inconsistent semantic quality. Then, by applying noise to the generative features, we produce contrastive learning pairs indirectly, limiting the sampling range of the feature domain to encourage the student network to learn domain-invariant features. Finally, we guide the student network to deeply mimic the teacher’s layer-wise implicit classification behavior for the augmented synthetic images. Extensive experiments across various datasets and downstream tasks demonstrate the effectiveness of DFMC, achieving significant improvements while preventing student networks from overfitting to semantic ambiguous images. © 1991-2012 IEEE.

关键词： Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Markov random field image segmentation using cellular neural network

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems I-FUNDAMENTAL THEORY AND APPLICATIONS 1997年第1期44卷 86-89页

作者： Sziranyi, T Zerubia, J Analogical and Neural Computing Systems Research Laboratory Computer and Automation Institute Hungarian Academy of Sciences (MTA-SZTAKI) Budapest Hungary I.N.R.I.A. Sophia Antipolis Sophia-Antipolis France

Markovian approaches to early vision processes need a huge amount of computing power. These algorithms can usually be implemented on parallel computing structures. with the Cellular neural Networks (CNN), a new image processing toot is coming into consideration, Its VLSI implementation takes place on a single analog chip containing several thousands of cells. Herein se use the CNN UM architecture for statistical image segmentation. The Modified Metropolis Dynamics (MMD) method can be implemented into the raw analog architecture of the CNN, We are able to implement a (pseudo) random held generator using one layer (one memory/cell) of the CNN. We can introduce the whole pseudostochastic segmentation process in the CNN architecture using 8 memories/cell, We use simple arithmetic functions (addition, multiplication), equality-test between neighboring pixels and very simple nonlinear output functions (step, jigsaw, With this architecture, a real VLSI CNN chip can execute a pseudostochastic relaxation algorithm of about 100 iterations in about 1 ms, In the proposed solution the segmentation is unsupervised. We have developed a pixel-level statistical estimation model. The CNN turns the original image into a smooth one. Then we have two gray-level values for every pixel: the original and the smoothed one. These two values are used for estimating the probability distribution of region label at a given pixel. Using the conventional first-order Markov Random Field (MRF) model, some misclassification errors remained at the region boundaries, because of the estimation difficulties in case of low SNR. By using a greater neighborhood, this problem has been avoided. In our CNN experiments, we used a simulation system with a fixed-point integer precision of 16 bits, Our results show that even in the case of the very constrained conditions of value-representations (the interval is (-64, +64), the accuracy is 0.002) can result in an effective and acceptable segmentation.

关键词： Markov processes VLSI analogue integrated circuits analogue processing circuits cellular neural nets estimation theory image segmentation neural chips neural net architecture parallel algorithms probability CNN UM architecture Markov random field image s Parallel algorithms Cellular neural networks neural network hardware Probability estimation theory image segmentation neural net architecture Analog integrated circuits analogue processing circuits Very large scale integration Markov random fields Markov chain

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：