检索结果-内蒙古大学图书馆

Advancements in exponential synchronization and encryption techniques: Quaternion-Valued artificial neural networks with two-sided coefficients

引用

neural networks 2025年 183卷 106982页

作者： Li, Chenyang Kou, Kit Ian Zhang, Yanlin Liu, Yang Univ Macau Fac Sci & Technol Dept Math Taipa 999078 Macao Peoples R China Zhejiang Normal Univ Dept Math Zhejiang 321004 Peoples R China

This paper presents cutting-edge advancements in exponential synchronization and encryption techniques, focusing on Quaternion-Valued artificial neural networks (QVANNs) that incorporate two-sided coefficients. The study introduces a novel approach that harnesses the Cayley-Dickson representation method to simplify the complex equations inherent in QVANNs, thereby enhancing computational efficiency by exploiting complex number properties. The study employs the Lyapunov theorem to craft a resilient control system, showcasing its exponential synchronization by skillfully regulating the Lyapunov function and its derivatives. This management ensures the stability and synchronization of the network, which is crucial for reliable performance in various applications. Extensive numerical simulations are conducted to substantiate the theoretical framework, providing empirical evidence supporting the presented design and proofs. Furthermore, the paper explores the practical application of QVANNs in the encryption and decryption of color images, showcasing the network's capability to handle complex data processing tasks efficiently. The findings of this research not only contribute significantly to the development of complex artificial neural networks but pave the way for further exploration into systems with diverse delay types.

关键词： Quaternion-Valued artificial neural networks Exponential synchronization Controllers Encryption of image Two-sided coefficient

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

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

Integration of Convolutional neural Network and image processing for Pulp Fibril Detection and Measurement

引用

IEEE ACCESS 2025年 13卷 74630-74642页

作者： Chirakitsakul, Tanachot Wattuya, Pakaket Somboon, Phichit Jansakra, Panthira Watcharopas, Chakrit Kasetsart Univ Dept Comp Sci Bangkok Thailand Kasetsart Univ Fac Sci Artificial Intelligence Technol & Innovat Ctr Hlth Bangkok 10900 Thailand Kasetsart Univ Dept Forest Prod Bangkok 10900 Thailand

The fibrillation index is a critical metric in paper manufacturing, quantifying the degree of fibrillation achieved during the pulp refining process. Optimizing this metric enhances both paper quality and production efficiency. However, traditional measurement methods-such as manual visual examination of pulp samples under microscopy-are slow, error-prone, and labor-intensive, limiting their scalability in industrial applications. This study proposes a novel method that integrates deep learning with image processing techniques to automate fibril detection and fibrillation index computation. The proposed method leverages the discriminative capabilities of convolutional neural networks (CNNs) with adaptive image processing techniques to overcome key challenges such as low contrast, image noise, and variability in fibril morphology. The patch-based classification approach effectively filters out irrelevant objects, especially those whose features visually resemble fibrils, thus improving fibril segmentation accuracy. The method was comprehensively validated against expert-labeled ground truth images and achieved a promising average error rate of 0.4494 +/- 0.4187. Experimental results also demonstrate the strong robustness of the proposed method, with consistent performance across diverse refining conditions and image qualities, making it suitable for real-world application in the pulp and paper industry. Furthermore, this study paves the way for broader applications in materials science and biomedical imaging, where precise feature detection in microscopic images is essential.

关键词： Optical fiber networks Optical fibers Optical fiber testing Indexes image processing Microscopy Refining Noise Feature extraction Length measurement Convolutional neural network deep learning image segmentation fibril detection pulp fibril analysis fibrillation index

来源：评论

学校读者我要写书评

暂无评论

Robust pattern retrieval in an optical Hopfield neural network

引用

OPTICS LETTERS 2025年第1期50卷 225-228页

作者： Katidis, Michael Musa, Khalid Kumar, Santosh Li, Zhaotong Long, Frederick Qu, Chunlei Huang, Yu-ping Stevens Inst Technol Dept Phys Hoboken NJ 07030 USA Stevens Inst Technol Ctr Quantum Sci & Engn Hoboken NJ 07030 USA US Army DEVCOM Armaments Ctr Picatinny Arsenal NJ 07806 USA

Hopfield neural networks (HNNs) promise broad applications in areas such as combinatorial optimization, memory storage, and pattern recognition. Among various implementations, optical HNNs are particularly interesting because they can take advantage of fast optical matrix-vector multiplications. Yet their studies so far have mostly been on the theoretical side, and the effects of optical imperfections and robustness against memory errors remain to be quantified. Here we demonstrate an optical HNN in a simple experimental setup using a spatial light modulator with 100 neurons. It successfully stores and retrieves 13 patterns, which approaches the critical capacity limit of alpha c = 0.138. It is robust against random phase flipping errors of the stored patterns, achieving high fidelity in recognizing and storing patterns even when 30% pixels are randomly flipped. Our results highlight the potential of optical HNNs in practical applications such as real-time image processing for autonomous driving, enhanced AI with fast memory retrieval, and other scenarios requiring efficient data processing. (c) 2024 Optica Publishing Group. All rights, including for text and data mining (TDM), artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： image processing neural networks Optical neural systems Pattern recognition Real time imaging Spatial light modulators

来源：评论

学校读者我要写书评

暂无评论

Accelerating Convolutional processing by Harnessing Channel Shifts in Arrayed Waveguide Gratings

引用

LASER & PHOTONICS REVIEWS 2025年第1期19卷

作者： Yi, Dan Zhao, Caiyue Zhang, Zunyue Xu, Hongnan Tsang, Hon Ki Chinese Univ Hong Kong Dept Elect Engn Shatin Hong Kong Peoples R China Tianjin Univ Sch Precis Instrument & Optoelect Engn Tianjin 300072 Peoples R China

Convolutional neural networks are a powerful category of artificial neural networks that can extract features from raw data to provide greatly reduced parametric complexity and enhance pattern recognition and the accuracy of prediction. Optical neural networks offer the promise of dramatically accelerating computing speed while maintaining low power consumption even when using high-speed data streams running at hundreds of gigabit/s. Here, we propose an optical convolutional processor (CP) that leverages the spectral response of an arrayed waveguide grating (AWG) to enhance convolution speed by eliminating the need for repetitive element-wise multiplication. Our design features a balanced AWG configuration, enabling both positive and negative weightings essential for convolutional kernels. A proof-of-concept demonstration of an 8-bit resolution processor is experimentally implemented using a pair of AWGs with a broadband Mach-Zehnder interferometer (MZI) designed to achieve uniform weighting across the whole spectrum. Experimental results demonstrate the CP's effectiveness in edge detection and achieved 96% accuracy in a convolutional neural network for MNIST recognition. This approach can be extended to other common operations, such as pooling and deconvolution in Generative Adversarial networks. It is also scalable to more complex networks, making it suitable for applications like autonomous vehicles and real-time video recognition. A novel convolutional processor is proposed using the shifted spectral response of a pair of arrayed waveguide gratings (AWGs) to mimic the kernel shifts during image convolution. This inherent mixing of inputs in the AWG's spectral response eliminates the need for repetitive element-wise computations while enabling the simultaneous generation of convolved output maps. image

关键词： array waveguide grating convolutional processor deep learning image processing optical computing

来源：评论

学校读者我要写书评

暂无评论

DiffStyler: Controllable Dual Diffusion for Text-Driven image Stylization

引用

IEEE TRANSACTIONS ON neural networks AND LEARNING SYSTEMS 2025年第2期36卷 3370-3383页

作者： Huang, Nisha Zhang, Yuxin Tang, Fan Ma, Chongyang Huang, Haibin Dong, Weiming Xu, Changsheng Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Comp Technol Beijing 100190 Peoples R China Kuaishou Technol Beijing 100085 Peoples R China

Despite the impressive results of arbitrary image-guided style transfer methods, text-driven image stylization has recently been proposed for transferring a natural image into a stylized one according to textual descriptions of the target style provided by the user. Unlike the previous image-to-image transfer approaches, text-guided stylization progress provides users with a more precise and intuitive way to express the desired style. However, the huge discrepancy between cross-modal inputs/outputs makes it challenging to conduct text-driven image stylization in a typical feed-forward CNN pipeline. In this article, we present DiffStyler, a dual diffusion processing architecture to control the balance between the content and style of the diffused results. The cross-modal style information can be easily integrated as guidance during the diffusion process step-by-step. Furthermore, we propose a content image-based learnable noise on which the reverse denoising process is based, enabling the stylization results to better preserve the structure information of the content image. We validate the proposed DiffStyler beyond the baseline methods through extensive qualitative and quantitative experiments. The code is available at https://***/haha-lisa/Diffstyler.

关键词： Arbitrary image stylization diffusion textual guidance neural network applications

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：