检索结果-内蒙古大学图书馆

Design and Analysis of Energy Efficient Approximate Multipliers for image processing and Deep neural Network

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2025年第2期72卷 854-867页

作者： Kumari, Anupam Palathinkal, Roy Paily Indian Inst Technol Guwahati IIT Guwahati Dept Elect & Elect Engn Gauhati 781039 India

Numerous obstacles in enhancing the performance of computing systems have spurred the emergence of approximate computing. Extensive studies have been reported on approximate computing to develop high-performance, energy-efficient hardware designs tailored to error-resilient applications. In this brief, we proposed 8-bit approximate multipliers with 15 levels of accuracy using three techniques: recursive, bit-wise, and hybrid approximation using partial bit OR (PBO). Compared to the existing multipliers, investigated designs have significantly improved the area, power, delay, Power Delay Product (PDP), and Power Area Delay Product (PADP) by 41.68%, 73.16%, 35.57%, 72.65%, and 75.42% respectively on average. On resemblance with the accurate multiplier, the area, power, delay, PDP, and PADP were enhanced by 54.41%, 57.57%, 25.73%, 60.14%, and 74.33% correspondingly on average. Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values surpassing (30 dB, 94%), (31 dB, 96%), and (26 dB, 95%) by applying them to benchmarks in image smoothing, edge detection, and image sharpening successively. Moreover, upon scrutinizing the efficacy of multipliers in hardware implementations of deep neural networks attaining the performance exceeding 95%. The obtained results confirm that suggested multipliers are well-suited for their widespread applications.

关键词： Delays Hardware Circuits Accuracy Logic gates Adders Approximate computing Energy efficiency image edge detection artificial neural networks approximate multiplier energy efficient image processing neural network

来源：评论

学校读者我要写书评

暂无评论

A review of hyperspectral image classification based on graph neural networks

引用

artificial INTELLIGENCE REVIEW 2025年第6期58卷 1-56页

作者： Zhao, Xiaofeng Ma, Junyi Wang, Lei Zhang, Zhili Ding, Yao Xiao, Xiongwu Xian Res Inst High Technol Key Lab Opt Engn Xian 710025 Shaanxi Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430079 Peoples R China

Hyperspectral images provide rich spectral-spatial information but pose significant classification challenges due to high dimensionality, noise, mixed pixels, and limited labeled samples. Graph neural networks (GNNs) have emerged as a promising solution, offering a semi-supervised framework that can capture complex spatial-spectral relationships inherent in non-Euclidean hyperspectral image data. However, existing reviews often concentrate on specific aspects, thus limiting a comprehensive understanding of GNN-based hyperspectral image classification. This review systematically outlines the fundamental concepts of hyperspectral image classification and GNNs, and summarizes leading approaches from both traditional machine learning and deep learning. Then, it categorizes GNN-based methods into four paradigms: graph recurrent neural networks, graph convolutional networks, graph autoencoders, and hybrid graph neural networks, discussing their theoretical underpinnings, architectures, and representative applications. Finally, five key directions are further highlighted: adaptive graph construction, dynamic graph processing, deeper architectures, self-supervised strategies, and robustness enhancement. These insights aim to facilitate continued innovation in GNN-based hyperspectral imaging, guiding researchers toward more efficient and accurate classification frameworks.

关键词： Graph neural Hyperspectral image classification Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Nonlinear Noise-Resistant Zeroing neural Network Model for Solving Time-Varying Quaternion Generalized Lyapunov Equation and applications to Color image processing

引用

IEEE TRANSACTIONS ON neural networks AND LEARNING SYSTEMS 2025年 PP卷 PP页

作者： Xiao, Lin Yan, Xiangru He, Yongjun Luo, Biao Song, Qiya Hunan Normal Univ Hunan Prov Key Lab Intelligent Comp & Language Inf Changsha 410081 Peoples R China Hunan Normal Univ MOE LCSM Changsha 410081 Peoples R China Cent South Univ Sch Automat Changsha 410083 Peoples R China

The time-varying Lyapunov equation (TVLE) plays a crucial role in control design and system stability. However, there has been limited research conducted on the time-varying generalized Lyapunov equation in the quaternion field. To tackle the time-varying quaternion generalized Lyapunov equation, a nonlinear noise-resistant zeroing neural network (NNR-ZNN) model with a novel power activation function (NPAF) is devised. The issue of non-commutativity within quaternion is circumvented by utilizing the real representation. The theoretical analyses provide a sufficient explanation for the global stability, fixed-time convergence, and robustness of the NNR-ZNN model. Under several different kinds of noises, the exceptional robustness of the NNR-ZNN model is highlighted by comparison with other existing models. In the end, the successful applications of the NNR-ZNN model to color image fusion and color image denoising confirm the practical value of the NNR-ZNN model.

关键词： Mathematical models Quaternions Color artificial neural networks Numerical models Noise Noise reduction Convergence Robustness Stability analysis Activation function (AF) color image denoising color image fusion noise resistance time-varying quaternion generalized Lyapunov equation (TVQGLE) zeroing neural network (ZNN)

来源：评论

学校读者我要写书评

暂无评论

Backpropagation-Based Learning Techniques for Deep Spiking neural networks: A Survey

引用

IEEE TRANSACTIONS ON neural networks AND LEARNING SYSTEMS 2024年第9期35卷 11906-11921页

作者： Dampfhoffer, Manon Mesquida, Thomas Valentian, Alexandre Anghel, Lorena Univ Grenoble Alpes Grenoble Inst Technol CEA CNRSINAC Spintec F-38000 Grenoble France CEA LIST F-38000 Grenoble France

With the adoption of smart systems, artificial neural networks (ANNs) have become ubiquitous. Conventional ANN implementations have high energy consumption, limiting their use in embedded and mobile applications. Spiking neural networks (SNNs) mimic the dynamics of biological neural networks by distributing information over time through binary spikes. Neuromorphic hardware has emerged to leverage the characteristics of SNNs, such as asynchronous processing and high activation sparsity. Therefore, SNNs have recently gained interest in the machine learning community as a brain-inspired alternative to ANNs for low-power applications. However, the discrete representation of the information makes the training of SNNs by backpropagation-based techniques challenging. In this survey, we review training strategies for deep SNNs targeting deep learning applications such as image processing. We start with methods based on the conversion from an ANN to an SNN and compare these with backpropagation-based techniques. We propose a new taxonomy of spiking backpropagation algorithms into three categories, namely, spatial, spatiotemporal, and single-spike approaches. In addition, we analyze different strategies to improve accuracy, latency, and sparsity, such as regularization methods, training hybridization, and tuning of the parameters specific to the SNN neuron model. We highlight the impact of input encoding, network architecture, and training strategy on the accuracy-latency tradeoff. Finally, in light of the remaining challenges for accurate and efficient SNN solutions, we emphasize the importance of joint hardware-software codevelopment.

关键词： Neurons Encoding Training Biological neural networks Synapses Neuromorphics Hardware Brain-inspired computing deep learning neuromorphic computing spiking neural networks (SNNs)

来源：评论

学校读者我要写书评

暂无评论

Implementation of a High-Accuracy neural Network-Based Pupil Detection System for Real-Time and Real-World applications

引用

SENSORS 2024年第8期24卷 2548页

作者： Bonteanu, Gabriel Bonteanu, Petronela Cracan, Arcadie Bozomitu, Radu Gabriel Gheorghe Asachi Tech Univ Iasi Fundamentals Elect Dept Iasi 700050 Romania Gheorghe Asachi Tech Univ Iasi Telecommun & IT Dept Iasi 700050 Romania

In this paper, the implementation of a new pupil detection system based on artificial intelligence techniques suitable for real-time and real-word applications is presented. The proposed AI-based pupil detection system uses a classifier implemented with slim-type neural networks, with its classes being defined according to the possible positions of the pupil within the eye image. In order to reduce the complexity of the neural network, a new parallel architecture is used in which two independent classifiers deliver the pupil center coordinates. The training, testing, and validation of the proposed system were performed using almost 40,000 eye images with a resolution of 320 x 240 pixels and coming from 20 different databases, with a high degree of generality. The experimental results show a detection rate of 96.29% at five pixels with a standard deviation of 3.38 pixels for all eye images from all databases and a processing speed of 100 frames/s. These results indicate both high accuracy and high processing speed, and they allow us to use the proposed solution for different real-time applications in variable and non-uniform lighting conditions, in fields such as assistive technology to communicate with neuromotor-disabled patients by using eye typing, in computer gaming, and in the automotive industry for increasing traffic safety by monitoring the driver's cognitive state.

关键词： artificial intelligence pupil detection neural networks classifier real-time

来源：评论

学校读者我要写书评

暂无评论

Efficient Implementation of Matrix-Based image processing Algorithms for IoT applications

引用

APPLIED SCIENCES-BASEL 2025年第9期15卷 4947-4947页

作者： Zoican, Sorin Zoican, Roxana POLITEHN Bucharest Natl Univ Sci & Technol Fac Elect Telecommun & Informat Technol Telecommun Dept Bucharest 060042 Romania

This paper analyzes implementation approaches of matrix-based image processing algorithms. As an example, an image processing algorithm that provides both image compression and image denoising using random sample consensus and discrete cosine transform is analyzed. Two implementations are illustrated: one using the Blackfin processor with 32-bit fixed-point representation and the second using the convolutional neural network (CNN) accelerator in the MAX78000 microcontroller. Implementation with Blackfin can be considered a classic approach, in C language, possible on all existing microcontrollers. This implementation is improved by using two cores. The proposed implementation with the CNN accelerator is a new approach that effectively uses the dedicated accelerator for convolutional neural networks, with better results than a classical implementation. The execution time of matrix-based image processing algorithms can be reduced by using CNN accelerators already integrated in some modern microcontrollers to implement artificial intelligence algorithms. The proposed method uses CNN in a different way, not for artificial intelligence algorithms, but for matrix calculations using CNN resources effectively while maintaining the accuracy of the calculations. A comparison of these two implementations and the validation using MATLAB with 64 bits floating point representation are conducted. The obtained performance is good both in terms of quality of reconstructed image and execution time, and the performance differences between the infinite precision implementation and the finite precision implementation are small. The CNN accelerator implementation, based on matrix multiplication implemented using CNN, has a better performance suitable for Internet of Things applications.

关键词： discrete cosine transform random sample consensus visual DSP plus plus blackfin processor CNN accelerator internet of things

来源：评论

学校读者我要写书评

暂无评论

Bio-Inspired Neuromorphic Sensory Systems from Intelligent Perception to Nervetronics

引用

ADVANCED SCIENCE 2025年第1期12卷 e2409568页

作者： Boahen, Elvis K. Kweon, Hyukmin Oh, Hayoung Kim, Ji Hong Lim, Hayoung Kim, Do Hwan Hanyang Univ Dept Chem Engn Seoul 04763 South Korea Hanyang Univ Inst Nano Sci & Technol Seoul 04763 South Korea Hanyang Univ Clean Energy Res Inst Seoul 04763 South Korea Stanford Univ Dept Chem Engn Stanford CA 94305 USA

Inspired by the extensive signal processing capabilities of the human nervous system, neuromorphic artificial sensory systems have emerged as a pivotal technology in advancing brain-like computing for applications in humanoid robotics, prosthetics, and wearable technologies. These systems mimic the functionalities of the central and peripheral nervous systems through the integration of sensory synaptic devices and neural network algorithms, enabling external stimuli to be converted into actionable electrical signals. This review delves into the intricate relationship between synaptic device technologies and neural network processing algorithms, highlighting their mutual influence on artificial intelligence capabilities. This study explores the latest advancements in artificial synaptic properties triggered by various stimuli, including optical, auditory, mechanical, and chemical inputs, and their subsequent processing through artificial neural networks for applications in image recognition and multimodal pattern recognition. The discussion extends to the emulation of biological perception via artificial synapses and concludes with future perspectives and challenges in neuromorphic system development, emphasizing the need for a deeper understanding of neural network processing to innovate and refine these complex systems.

关键词： artificial synapse bio-inspired machine learning neuromorphic sensory system

来源：评论

学校读者我要写书评

暂无评论

An improved pulse coupled neural networks model for semantic IoT

引用

Digital Communications and networks 2024年第3期10卷 557-567页

作者： Rong Ma Zhen Zhang Yide Ma Xiping Hu Edith C.H.Ngai Victor C.M.Leung School of Information Science and Engineering Lanzhou UniversityLanzhou 730000China School of Medical Technology Beijing Institute of TechnologyBeijing100081China Department of Electrical and Electronic Engineer The University of Hong KongHong Kong 999077China College of Computer Science and Software Engineering Shenzhen UniversityShenzhen 518060China Department of Electrical and Computer Engineering the University of British ColumbiaVancouverBC V6T 1Z4Canada

In recent years,the Internet of Things(IoT)has gradually developed applications such as collecting sensory data and building intelligent services,which has led to an explosion in mobile data ***,with the rapid development of artificial intelligence,semantic communication has attracted great attention as a new communication ***,for IoT devices,however,processing image information efficiently in real time is an essential task for the rapid transmission of semantic *** the increase of model parameters in deep learning methods,the model inference time in sensor devices continues to *** contrast,the Pulse Coupled neural Network(PCNN)has fewer parameters,making it more suitable for processing real-time scene tasks such as image segmentation,which lays the foundation for real-time,effective,and accurate image ***,the parameters of PCNN are determined by trial and error,which limits its *** overcome this limitation,an Improved Pulse Coupled neural networks(IPCNN)model is proposed in this *** IPCNN constructs the connection between the static properties of the input image and the dynamic properties of the neurons,and all its parameters are set adaptively,which avoids the inconvenience of manual setting in traditional methods and improves the adaptability of parameters to different types of *** segmentation results demonstrate the validity and efficiency of the proposed self-adaptive parameter setting method of IPCNN on the gray images and natural images from the Matlab and Berkeley Segmentation *** IPCNN method achieves a better segmentation result without training,providing a new solution for the real-time transmission of image semantic information.

关键词： Internet of things(IoT) Semantic information Real-time application Improved pulse coupled neural network image segmentation

来源：评论

学校读者我要写书评

暂无评论

DeepBlue: Advanced convolutional neural network applications for ocean remote sensing

引用

IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE 2024年第1期12卷 138-161页

作者： Wang, Haoyu Li, Xiaofeng Chinese Acad Sci Inst Oceanog Key Lab Ocean Circulat & Waves Qingdao 266071 Peoples R China NOAA Washington DC USA

In the last 40 years, remote sensing technology has evolved, significantly advancing ocean observation and catapulting its data into the big data era. How to efficiently and accurately process and analyze ocean big data and solve practical problems based on ocean big data constitute a great challenge. artificial intelligence (AI) technology has developed rapidly in recent years. Numerous deep learning (DL) models have emerged, becoming prevalent in big data analysis and practical problem solving. Among these, convolutional neural networks (CNNs) stand as a representative class of DL models and have established themselves as one of the premier solutions in various research areas, including computer vision and remote sensing applications. In this study, we first discuss the model architectures of CNNs and some of their variants as well as how they can be applied to the processing and analysis of ocean remote sensing data. Then, we demonstrate that CNNs can fulfill most of the requirements for ocean remote sensing applications across the following six categories: reconstruction of the 3D ocean field, information extraction, image superresolution, ocean phenomena forecast, transfer learning method, and CNN model interpretability method. Finally, we discuss the technical challenges facing the application of CNN-based ocean remote sensing big data and summarize future research directions.

关键词： Oceans Remote sensing Convolutional neural networks Data models Biological system modeling Computational modeling Ocean temperature Feature extraction Predictive models Transfer learning Spatial resolution artificial intelligence Big Data Deep learning image processing Natural language processing Backpropagation algorithms

来源：评论

学校读者我要写书评

暂无评论

Fixed-Quality Compression of Remote Sensing images With neural networks

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 12169-12180页

作者： Mijares i Verdu, Sebastia Chabert, Marie Oberlin, Thomas Serra-Sagrista, Joan Univ Autnoma Barcelona Dept Informat & Commun Engn Cerdanyola Valls 08193 Spain Univ Toulouse IRIT INP ENSEEIHT F-31071 Toulouse France Univ Toulouse Federat ENAC ISAE SUPAERO ONERA F-31055 Toulouse France

Fixed-quality image compression is a coding paradigm where the tolerated introduced distortion is set by the user. This article proposes a novel fixed-quality compression method for remote sensing images. It is based on a neural architecture we have recently proposed for multirate satellite image compression. In this article, we show how to efficiently estimate the reconstruction quality using an appropriate statistical model. The performance of our approach is assessed and compared against recent fixed-quality coding techniques and standards in terms of accuracy and rate-distortion, as well as with recent machine learning compression methods in rate-distortion, showing competitive results. In particular, the proposed method does not introduce artifacts even when coding neighboring areas at different qualities.

关键词： Data compression neural network applications neural networks optical data processing remote sensing Data compression neural network applications neural networks optical data processing remote sensing

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：