检索结果-内蒙古大学图书馆

Generic image application using GANs (Generative Adversarial networks): A Review

EVOLVING SYSTEMS 2023年第5期14卷 903-917页

作者： Porkodi, S. P. Sarada, V. Maik, Vivek Gurushankar, K. SRM Inst Sci & Technol Dept ECE Kattankulathur 603203 Tamil Nadu India South Ural State Univ Higher Med & Biol Sch Chelyabinsk Russia

The generative adversarial network (GAN), which has received considerable notice for its outstanding data generating abilities, is one of the most intriguing fields of artificial intelligence study. Large volumes of data are required to develop generalizable deep learning models. GANs are a highly strong class of networks capable of producing believable new pictures from unlabeled source prints and labeled medical imaging data is scarce and costly to produce. Despite GAN's remarkable outcomes, steady training remains a challenge. The goal of this study is to perform a complete evaluation of the GAN-related literature and to present a succinct summary of existing knowledge on GAN, including the theory following it, its intended purpose, potential base model alterations, and latest breakthroughs in the area. This article will aid you in gaining a comprehensive grasp of GAN and provide an overview of GAN and its many model types, as well as common implementations, measurement parameter suggestions, and GAN applications in image processing. It will also go over the several applications of GANs in image processing, as well as their benefits and limitations, as well as its prospective reach.

关键词： artificial intelligence Generative adversarial networks image processing neural network Supervised learning Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Contrast sensitivity function in deep networks

引用

neural networks 2023年第1期164卷 228-244页

作者： Akbarinia, Arash Morgenstern, Yaniv Gegenfurtner, Karl R. Univ Giessen Dept Expt Psychol Giessen Germany Katholieke Univ Leuven Fac Psychol & Educ Sci Leuven Belgium

The contrast sensitivity function (CSF) is a fundamental signature of the visual system that has been measured extensively in several species. It is defined by the visibility threshold for sinusoidal gratings at all spatial frequencies. Here, we investigated the CSF in deep neural networks using the same 2AFC contrast detection paradigm as in human psychophysics. We examined 240 networks pretrained on several tasks. To obtain their corresponding CSFs, we trained a linear classifier on top of the extracted features from frozen pretrained networks. The linear classifier is exclusively trained on a contrast discrimination task with natural images. It has to find which of the two input images has higher contrast. The network's CSF is measured by detecting which one of two images contains a sinusoidal grating of varying orientation and spatial frequency. Our results demonstrate characteristics of the human CSF are manifested in deep networks both in the luminance channel (a band-limited inverted U-shaped function) and in the chromatic channels (two low-pass functions of similar properties). The exact shape of the networks' CSF appears to be task-dependent. The human CSF is better captured by networks trained on low-level visual tasks such as image-denoising or autoencoding. However, human-like CSF also emerges in mid-and high-level tasks such as edge detection and object recognition. Our analysis shows that human-like CSF appears in all architectures but at different depths of processing, some at early layers, while others in intermediate and final layers. Overall, these results suggest that (i) deep networks model the human CSF faithfully, making them suitable candidates for applications of image quality and compression, (ii) efficient/purposeful processing of the natural world drives the CSF shape, and (iii) visual representation from all levels of visual hierarchy contribute to the tuning curve of the CSF, in turn implying a function which we intuitively think of as m

关键词： CSF artificial neural networks Deep learning Contrast Visual perception Visual features

来源：评论

学校读者我要写书评

暂无评论

Special Section Guest Editorial: Frontiers in image and Signal processing for Remote Sensing

引用

JOURNAL OF APPLIED REMOTE SENSING 2023年第3期17卷 32401-32401页

作者： Lin, Chi Yu, Chang Wu Dalian Univ Technol Sch Software Inst Intelligent Syst Dalian Peoples R China Chung Hua Univ Dept Comp Sci & Informat Engn Hsinchu Taiwan

Guest Editors Chi Lin and Chang Wu Yu introduce the Special Section on Frontiers in image and Signal processing for Remote Sensing.

关键词： Remote sensing image processing Signal processing image enhancement artificial neural networks Biomedical applications Intelligence systems Interferometric synthetic aperture radar Vegetation Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Current survey of Clifford geometric algebra applications

引用

MATHEMATICAL METHODS IN THE APPLIED SCIENCES 2024年第3期47卷 1331-1361页

作者： Hitzer, Eckhard Lavor, Carlile Hildenbrand, Dietmar Int Christian Univ Coll Liberal Arts Osawa 3-10-2 Mitaka Tokyo 1818585 Japan Univ Estadual Campinas IMECC UNICAMP Sao Paulo Brazil Univ Technol Darmstadt Comp Sci Dept Hessen Germany

We extensively survey applications of Clifford Geometric algebra in recent years (mainly 2019-2022). This includes engineering;electric engineering;optical fibers;geographic information systems;geometry;molecular geometry;protein structure;neural networks;artificial intelligence;encryption;physics;signal, image, and video processing;and software.

关键词： artificial intelligence Clifford geometric algebra engineering geometry physics signal and image processing software

来源：评论

学校读者我要写书评

暂无评论

An efficient convolutional global gated recurrent-based adaptive gazelle algorithm for enhanced disease detection and classification

引用

EVOLVING SYSTEMS 2024年第5期15卷 1881-1893页

作者： Maniraj, Subramanian Pitchiah Chillakuru, Prameeladevi Thangavel, Kavitha Kadam, Archana Meckanzi, Sangeetha Cheerla, Sreevardhan SRM Inst Sci & Technol Dept Data Sci & Business Syst Kattankulathur Campus Chennai India Velammal Inst Technol Dept Artificial Intelligence & Data Sci Chennai India Kongu Engn Coll Dept Comp Applicat Erode India Pimpri Chinchwad Coll Engn Dept Comp Engn Pune Maharashtra India Panimalar Engn Coll Dept Comp Sci & Engn Chennai 600123 India Koneru Lakshmaiah Educ Fdn Dept Elect & Commun Engn Vaddeswaram Andhra Pradesh India

In modern healthcare, medical image processing plays a vital role in enabling early disease detection, treatment planning, and improved patient care. However, traditional methods face challenges such as handling big data, scalability, and computational intensity. To address these issues, this paper proposes a Convolutional Global Gated Recurrent-based Adaptive Gazelle (CGGR-AG) algorithm for medical image processing applications. The CGGR-AG algorithm detects abnormalities and classifies specific objects within images by leveraging Convolutional neural networks (CNNs) for feature extraction and Gated Recurrent Units (GRUs) for capturing sequential patterns. Additionally, the Adaptive Gazelle Optimization algorithm fine-tunes parameters to enhance the effectiveness of the CGGR-AG method. Experimental validation is conducted on Tuberculosis and heart disease datasets, evaluating performance metrics including recall, specificity, accuracy, Area Under the Curve - Receiver Operating Characteristic (AUC-ROC), precision, and F1-score. Comparative analysis with state-of-the-art methods demonstrates the effectiveness of the CGGR-AG method in medical image processing applications.

关键词： Healthcare Medical image processing Convolutional neural Network Gated Recurrent Unit Adaptive Gazelle Optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Three-branch neural network for No-Reference Quality assessment of Pan-Sharpened images

引用

ENGINEERING applications OF artificial INTELLIGENCE 2025年 139卷

作者： Stepien, Igor Oszust, Mariusz Rzeszow Univ Technol Doctoral Sch Al Powstancow Warszawy 12 PL-35959 Rzeszow Poland Rzeszow Univ Technol Dept Comp & Control Engn Wincentego Pola 2 PL-35959 Rzeszow Poland

Pan-Sharpening (PS) techniques aim to enhance the spatial resolution of low-resolution multispectral images by leveraging data from high-resolution panchromatic images. Their comparison typically relies on the quality assessment of the resulting Full-Resolution (FS) pan-sharpened images. However, in the absence of a reference image, a dedicated No-Reference (NR) method must be employed. Therefore, this paper introduces a novel approach called the Three-Branch neural Network for No-Reference Quality Assessment of Pan- Sharpened images (TBN-PSI). The network consists of three subnetworks designed for perceptual processing of image channels, featuring shared extraction of low-level features and high-level semantics. Extensive experimental evaluation demonstrates the superiority of the approach over the state-of-the-art NR PS image quality assessment methods, using six datasets containing diverse satellite images that span urban areas, green vegetation, and water scenarios. Specifically, TBN-PSI outperforms the compared methods by 4% to 9% in terms of Spearman's Rank-Order Correlation Coefficient (SRCC), Pearson's Linear Correlation Coefficient (PLCC), and Kendall's Rank Correlation Coefficient (KRCC) between the obtained scores and those of three representative full-reference methods.

关键词： Remote sensing Pan-sharpening image quality assessment neural networks Three-branch neural network Pan-sharpening quality prediction

来源：评论

学校读者我要写书评

暂无评论

EPU: An Energy-Efficient Explainable AI Accelerator With Sparsity-Free Computation and Heat Map Compression/Pruning

引用

IEEE JOURNAL OF SOLID-STATE CIRCUITS 2024年第3期59卷 830-841页

作者： Kim, Junsoo Han, Seunghee Ko, Geonwoo Kim, Ji-Hoon Lee, Changha Kim, Taewoo Youn, Chan-Hyun Kim, Joo-Young Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon 34141 South Korea

Deep neural networks (DNNs) have recently gained significant prominence in various real-world applications such as image recognition, natural language processing, and autonomous vehicles. However, due to their black-box nature in system, the underlying mechanisms of DNNs behind the inference results remain opaque to users. In order to address this challenge, researchers have focused on developing explainable artificial intelligence (AI) algorithms. Explainable AI aims to provide a clear and human-understandable explanation of the model's decision, thereby building more reliable systems. However, the explanation task differs from well-known inference and training processes as it involves interactions with the user. Consequently, existing inference and training accelerators face inefficiencies when processing explainable AI on edge devices. This article introduces explainable processing unit (EPU), the first hardware accelerator designed for explainable AI workloads. The EPU utilizes a novel data compression format for the output heat maps and intermediate gradients to enhance the overall system performance by reducing both memory footprint and external memory access. Its sparsity-free computing core efficiently handles the input sparsity with negligible control overhead, resulting in a throughput boost of up to 9.48x. It also proposes a dynamic workload scheduling with a customized on-chip network for distinct inference and explanation tasks to maximize internal data reuse hence reducing external memory access by 63.7%. Furthermore, the EPU incorporates point-wise gradient pruning (PGP) that can significantly reduce the size of heat maps by a factor of 7.01x combined with the proposed compression format. Finally, the EPU chip fabricated in a 28 nm CMOS process achieves a remarkable heat map generation rate of 367 frames/s for ResNet-34 while maintaining the state-of-the-art area and energy efficiency of 112.3 GOPS/mm(2) and 26.55 TOPS/W, respectively.

关键词： artificial intelligence Heat maps Training Convolutional neural networks Task analysis Labeling Semantics Convolutional neural network (CNN) deep neural network (DNN) explainable artificial intelligence (XAI) multiple DNN acceleration neural processing unit (NPU)

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Potential of Spiking neural networks: Understanding the What, Why, and Where

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 2024年第5期16卷 1648-1663页

作者： Wickramasinghe, Buddhi Chowdhury, Sayeed Shafayet Kosta, Adarsh Kumar Ponghiran, Wachirawit Roy, Kaushik Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA

Spiking neural networks (SNNs) are a promising avenue for machine learning with superior energy efficiency compared to traditional artificial neural networks (ANNs). Recent advances in training and input encoding have put SNNs on par with state-of-the-art ANNs in image classification. However, such tasks do not utilize the internal dynamics of SNNs fully. Notably, a spiking neuron's membrane potential acts as an internal memory, merging incoming inputs sequentially. This recurrent dynamic enables the networks to learn temporal correlations, making SNNs suitable for sequential learning. Such problems can also be tackled using ANNs. However, to capture the temporal dependencies, either the inputs have to be lumped over time (e.g., Transformers);or explicit recurrence needs to be introduced [e.g., recurrent neural networks (RNNs) and long-short-term memory (LSTM) networks], which incurs considerable complexity. To that end, we explore the capabilities of SNNs in providing lightweight solutions to four sequential tasks involving text, speech, and vision. Our results demonstrate that SNNs, by leveraging their intrinsic memory, can be an efficient alternative to RNNs and LSTMs for sequence processing, especially for certain edge applications. Furthermore, SNNs can be combined with ANNs (hybrid networks) synergistically to obtain the best of both worlds in terms of accuracy and efficiency.

关键词： Neurons Training Task analysis Encoding Membrane potentials Computational modeling Recurrent neural networks Automatic speech recognition neuromorphic computing optical flow estimation spiking neural networks (SNNs)

来源：评论

学校读者我要写书评

暂无评论

Emerging memristors and applications in reservoir computing

引用

Frontiers of physics 2024年第1期19卷 219-239页

作者： Hao Chen Xin-Gui Tang Zhihao Shen Wen-Tao Guo Qi-Jun Sun Zhenhua Tang Yan-Ping Jiang School of Physics and Optoelectronic Engineering Guangdong University of TechnologyGuangzhou Higher Education Mega CenterGuangzhou 510006China

Recently, with the emergence of ChatGPT, the field of artificial intelligence has garnered widespread attention from various sectors of society. Reservoir Computing (RC) is a neuromorphic computing algorithm used to analyze time-series data. Unlike traditional artificial neural networks that require the weight values of all nodes in the trained network, RC only needs to train the readout layer. This makes the training process faster and more efficient, and it has been used in various applications, including speech recognition, image classification, and control systems. Its flexibility and efficiency make it a popular choice for processing large amounts of complex data. A recent research trend is to develop physical RC, which utilizes the nonlinear dynamic and short-term memory properties of physical systems (photonic modules, spintronic devices, memristors, etc.) to construct a fixed random neural network structure for processing input data to reduce computing time and energy. In this paper, we introduced the recent development of memristors and demonstrated the remarkable data processing capability of RC systems based on memristors. Not only do they possess excellent data processing ability comparable to digital RC systems, but they also have lower energy consumption and greater robustness. Finally, we discussed the development prospects and challenges faced by memristors-based RC systems.

关键词： reservoir computing memristor resistive switching artificial synapse neuromorphic computing

来源：评论

学校读者我要写书评

暂无评论

Detection of corrosion on steel structures using an artificial neural network

引用

STRUCTURE AND INFRASTRUCTURE ENGINEERING 2023年第12期19卷 1860-1871页

作者： Khayatazad, Mojtaba Honhon, Matthias De Waele, Wim Univ Ghent Fac Engn & Architecture Dept Electromech Syst & Met Engn SOETE Lab B-9052 Zwijnaarde Belgium SIM VZW Zwijnaarde Belgium

image based-corrosion detection has become a widespread practice for steel structures, but fine-tuning their model parameters is time-consuming. Alternatively, convolutional neural networks (CNNs) can also be trained fast and automatically, but they demand a huge training dataset. In this paper, a corrosion detection approach based on an artificial neural network (ANN) whose training dataset size is less than 0.1% of that of typical CNNs is introduced. The input layer of the proposed ANN consists of textural and color properties. In the present work, different color spaces and textural properties are examined for their impact on the robustness of the ANN. Results reveal that the best color channels can be achieved by combining CIE L*u*v* and YUV color spaces. Moreover, energy is selected as the best texture feature with respect to the ANN robustness. The proposed ANN outperforms an available image processing algorithm from the perspective of both speed and accuracy. In conclusion, this ANN can be used for actual applications after a fast and straightforward training step.

关键词： Steel structures image-based corrosion detection artificial neural networks deep hidden layers color space texture metric

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：