检索结果-内蒙古大学图书馆

Bio-Inspired Neuromorphic Sensory Systems from Intelligent Perception to Nervetronics

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

Assessment of Rain Attenuation in Satellite Telecommand Signals Using Numerical Weather Prediction Model and artificial neural networks 32

Assessment of Rain Attenuation in Satellite Telecommand Sign...

引用

32nd IEEE Signal processing and Communications applications conference (SIU)

作者： Gozutok, Arif Armagan TURKSAT AS Ankara Turkiye

ISBN: (纸本)9798350388978;9798350388961

In this study, the signal fading prediction model was implemented with artificial neural networks by obtaining precipitation parameters and atmospheric conditions in order to evaluate the signal attenuation observed in the telecommand signals of the geosynchronous telecommunication satellite. For a real situation, the application of artificial deep neural networks (ANN) over the 24-hour high-resolution Weather Research & Forecast (WRF) model simulation outputs was performed on two high-resolution simulation areas and used to estimate and model satellite signal attenuation. Preliminary results obtained from error analysis (RMSE) on multiple-input single-output feedforward neural network (MISO FFNN) prediction model outputs tested with various artificial neural network algorithms agree with observations of signal attenuation observed in downlink telemetry (receiver automatic gain control TM) obtained from the satellite receiver equipment. showed quite high correlation accuracy.

关键词： numerical weather prediction signal fading artificial intelligence neural networks atmospheric attenuation

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis for Advancements and Challenges in Deep Learning Models for image processing 5th

A Comprehensive Analysis for Advancements and Challenges in ...

引用

5th International conference on Data Science, Machine Learning and applications

作者： Ch, Ravikumar Chary, Kalvog Prakasha Srinivas, S. Bhavani, Tedla Veeranna Chaitanya Bharathi Inst Technol Dept Artificial Intelligence & Data Sci Hyderabad Telangana India CVR Coll Engn Dept CSE Cyber Secur Hyderabad Telangana India CVR Coll Engn Dept Comp Sci & Engn Hyderabad Telangana India Vardhaman Coll Engn Dept Comp Sci & Engn Hyderabad Telangana India Sri Indu Coll Engn & Technol Dept Informat Technol Hyderabad Telangana India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

Deep learning, a profound advancement in artificial intelligence, has demonstrated remarkable achievements, particularly in image processing. The rapid evolution of deep learning in architecture, training methods, and specifications has driven the expansion of image processing techniques. However, the increasing complexity of model structures challenges the effectiveness of the back propagation algorithm, and issues like the accumulation of unlabeled training data and class imbalances hinder deep learning performance. To address these challenges, there's a growing need for innovative deep models and cutting-edge computing paradigms to enable more sophisticated image content analysis. In this study, we conduct a comprehensive examination of four deep learning models utilizing Convolutional neural networks (CNNs), clarifying their theoretical foundations within the image processing context, opening the door for further research. CNNs are notably essential for image processing due to their ability to handle complex images effectively.

关键词： Deep learning image processing Backpropagation algorithm Convolutional neural networks (CNNs) Model structures

来源：评论

学校读者我要写书评

暂无评论

Creative and Experimental Design of Artwork Based on artificial neural Network Algorithm and Internet of Things

引用

Computer-Aided Design and applications 2024年第S13期21卷 92-104页

作者： Shi, Huawei Yuan, Tao School of Architectural Decoration Jiangsu Vocational Institute of Architectural Technology Xuzhou221116 China

Art creativity and experimental design are fields full of creativity and exploration, and traditional design methods are often limited by the personal abilities and experiences of designers. Therefore, introducing artificial intelligence (AI) algorithms can help designers better explore creativity and improve design efficiency. This article investigates the application of artificial neural networks (ANN) and the Internet of Things (IoT) in computer-aided artwork creativity and experimental design. By analyzing and learning a large amount of artwork data, the creative patterns and features of artwork are extracted, providing creative suggestions and optimization solutions for artists. The results indicate that the art creation computer-aided design (CAD) system constructed in this article has strong interactive capabilities and a good user experience. Meanwhile, ANN has significant advantages in image processing time compared to Support Vector Machine (SVM). This system can be applied to creative design, experimental creation, and image processing of artworks, providing more efficient and intelligent auxiliary tools for artists and designers. © 2024 U-turn Press LLC,

关键词： neural networks

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

End-to-end image Classification in Linear Hybrid Cellular Automata

End-to-end Image Classification in Linear Hybrid Cellular Au...

引用

International Joint conference on neural networks (IJCNN)

作者： Sawahashi, Naoki Principe, Jose C. Univ Florida Elect & Comp Engn Gainesville FL 32610 USA

ISBN: (纸本)9798350359329;9798350359312

Cellular automata have ideal properties for scalable and efficient computing, but a lack of a training method limits their real-world applications. First, we propose to partition the cellular lattice into three regions: input, output, and processing. Second, we propose a novel synthesis method to train a linear hybrid cellular automaton. Third, we show image classification on the MNIST dataset using only logic operations. By mapping local states over the globally linear lattice, the proposed model achieved above 90% test accuracy in binary image classification. Our method does not require any pre or post-processors to perform computation over the lattice. Hence, the lattice maintains its massive parallelism and locality of computation, ideal for ultra-low power processing in machine learning.

关键词： cellular automata image classification parallel processing neuromorphic computing machine learning

来源：评论

学校读者我要写书评

暂无评论

Joint Exit Selection and Offloading Decision for applications Based on Deep neural networks

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第23期11卷 38098-38112页

作者： Narmeen, Ramsha Mach, Pavel Becvar, Zdenek Ahmad, Ishtiaq Czech Tech Univ Fac Elect Engn Prague 16627 Czech Republic

User applications based on the deep neural networks (DNNs), such as object or anomaly detection, image recognition, or language processing, running on computation- and energy-constrained user equipment (UE) can be partially or fully processed in the edge computing servers to reduce a processing time and save an energy in the UE. To further reduce the processing time and the UE's energy consumption, DNN with multiple exit points can be incorporated. In this article, we address the problem of the decision on whether the computation should be offloaded from the UE to the edge computing server or processed locally by the UE and we solve this problem jointly and "on-the-fly" together with DNN exit selection. Since the formulated problem is very complex, we exploit the deep deterministic policy gradient for the exit selection and the offloading decisions (labeled DDPG-EOD) for the DNN-based applications. To this end, we first convert the problem into the Markov decision process, and then, we employ an end-to-end learning via DDPG with the actor-critic architecture. Second, we use a knowledge distillation-based technique to efficiently select the DNN's exit to minimize the delay and energy consumption. Simulation results show that the proposal is highly scalable, converges very quickly, and surpasses the best performing state-of-the-art approach by up to 120% and 100% in terms of the overall DNN processing delay and the energy consumption, respectively.

关键词： Delays Task analysis Servers artificial neural networks Computer architecture Accuracy Energy consumption Deep neural network (DNN) delay edge computing energy exit selection offloading

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

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：