检索结果-内蒙古大学图书馆

25th ieee International symposium on a World of Wireless, Mobile and Multimedia Networks (ieee WoWMoM)

作者： Sharma, Ekta Deo, Ravinesh C. Davey, Christopher P. Carter, Brad D. Salcedo-Sanz, Sancho Univ Southern Queensland Sch Math Phys & Comp Springfield Qld 4300 Australia Univ Southern Queensland Ctr Astrophys Toowoomba Qld 4350 Australia Univ Alcala Dept Signal Proc & Commun Alcala De Henares 28805 Spain

ISBN: (纸本)9798350394665;9798350394672

Artificial intelligence (AI) and Software Defined Radio (SDR) are transforming the field of signal intelligence. However, the full extent of the capabilities is unknown. This poster presents a paper in development that introduces a cloud-based platform leveraging artificial intelligence to detect and apply 11 modulation schemes (8 digital and 3 analog) to complex or quadrature radio signals. The SNR values analysed range from 0.0 to 40.0, with moderate drift, slight fading, and labelled increments. A comprehensive synthetic database developed by DeepSig is used to train four AI models. These will be integrated with the Google Cloud AI platform to enhance flexibility and processing power. The system will undergo testing with an SDR platform in GNU Radio, showcasing its potential for real-world signal processing applications. Cloud-based platforms offer the adaptability and computational power needed to replace traditional computers for AI-driven signal processing. Initial results indicate successful identification and accurate modulation type detection, with convenient access to the system through internet-connected devices.

关键词： cloud computing artificial intelligence software-defined radio modulation GNU Radio signal classification

来源：评论

学校读者我要写书评

暂无评论

Defects Detection of Catenary Suspension Device Based on image processing and CNN

Defects Detection of Catenary Suspension Device Based on Ima...

引用

ieee symposium Series on computational intelligence (SSCI)

作者： Li, Yongguang Wei, Dehua Wei, Xiukun Wu, Kuan Liang, Yong Shen, Xing Shengzhou Tongzhen Technol Co Beijing Peoples R China Beijing Jiaotong Univ Sch Traff & Transportat Beijing Peoples R China Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing Peoples R China CRRC Changchun Rail Transit Bus Co Ltd Changchun Peoples R China

ISBN: (纸本)9781728124858

Catenary suspension device (CSD) is a critical part of the pantograph-catenary system, which is a fundamental power equipment to supply electricity to urban rail transit vehicles. Whether the CSD is in a normal state is of great significance to the safe operation of operating vehicles. Therefore, it is important to detect the defects of CSD in time and automatically. In this paper, innovative and intelligent methods using image processing technologies and convolutional neural network (CNN) are proposed. Firstly, the insulators and bolts of CSD are extracted in the detected images using template matching algorithm. After that, an improved Bag of Features (BOF) model is proposed for the defect detection of CSD. Furthermore, in order to further improve the detection efficiency, AlexNet is trained for the defect detection and identification of CSD. The experimental results show that the proposed methods can detect the defects of CSD in time, with high robustness and accuracy.

关键词： defect detection catenary suspension device image processing alexNet CNN

来源：评论

学校读者我要写书评

暂无评论

Segmentation of hippocampus in MRI images based on the improved level set

Segmentation of hippocampus in MRI images based on the impro...

引用

2011 4th International symposium on computational intelligence and Design, ISCID 2011

作者： Zhao, Shuying Zhang, Dan Song, Xiangman Tan, Wenjun College of Information Science and Engineering Northeastern University Shenyang Liaoning 110819 China

ISBN: (纸本)9780769545004

For hippocampus of MRI demonstrating the low contrast, low signal to noise ratio(SNR), boundary discrete, intensity in homogeneities features, this paper proposed an improved level set model that based on regional and edge information. Refer to the intensity in homogeneities image, the global image information of external energy item is joined, to optimize the segmentation result, adopt edge information that is extracted by wavelet, which is used as an edge constraint stop item. Experimental results of many times segmentation of the hippocampus of MRI image show that this algorithm can precisely segment intensity in homogeneities image and improve the segmentation speed, so this algorithm can be applied to the complex structure segmentation, such as the hippocampus. © 2011 ieee.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

A flexible fully-multiplicative orthogonal-group based ICA algorithm

A flexible fully-multiplicative orthogonal-group based ICA a...

引用

ieee symposium on computational intelligence in Bioinformatics and computational Biology

作者： Ye, Yalan Wan, Jing Zhang, Zhi-Lin Jia, Chen Lei, Wu Univ Elect Sci & Technol China Sch Engn & Comp Sci Chengdu 610054 Peoples R China Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai 200240 Peoples R China

ISBN: (纸本)9781424407101

In this paper, we propose a flexible fully-multiplicative orthogonal-group based ICA (FlexibleOgICA) algorithm, which can instantaneously separate the mixture of sub-Gaussian and super-Gaussian source signals. It adopts a self-adaptive nonlinear function, which adjusts its parameter to achieve better performance based on the estimation of the kurtosis of super-Gaussian source signals. We also have successfully applied the algorithm to obtain the fetal electrocardiogram (FECG) signal, showing its fast convergence speed and high separation performance.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for JPEG image Compression Using Baseline Coding with Parallel Process 5

A Novel Framework for JPEG Image Compression Using Baseline ...

引用

5th ieee International Conference on computational intelligence and Computing Research (ieee ICCIC)

作者： Naidu, Balaka Ramesh Babu, M. S. Prasad AITAM Engn Coll Autonomous Dept IT Tekkali India Andhra Univ Dept Comp Sci & Syst Engn Visakhapatnam Andhra Pradesh India

ISBN: (纸本)9781479939756

Digital image communication is being used in many areas like Remote sensing, Weather forecast, Medical image Satellite applications. Data transformation of images in network is a difficult task because of their size and requirement of image quality. To fulfill this requirement several researchers proposed different Compression and Decompression Techniques, still they required further exploration. In this paper, we proposed Parallel processing Technique (PPT) in Joint Photographic Experts Group (JPEG) compression using Discrete Cosine Transform (DCT). The main goal of this proposed method is to reduce the storage space, execution time and effective utilization of bandwidth. Experiments are performed on benchmark Red-Green-Blue (RGB) images. We performed time calculations for Encoder, Decoder and also evaluated Root Mean Square Error (RMSE), Peak signal-to-Noise Ratio (PSNR) and Compression Ratio (CR) values.

关键词： Discrete Cosine Transform Peak signal-to-Noise Ratio Compression Ratio Root Mean Square Error Joint Photographic Experts Group

来源：评论

学校读者我要写书评

暂无评论

COLLABORATIVE intelligence FOR VISION TRANSFORMERS: A TOKEN SPARSITY-DRIVEN EDGE-CLOUD FRAMEWORK 31

COLLABORATIVE INTELLIGENCE FOR VISION TRANSFORMERS: A TOKEN ...

引用

2024 International Conference on image processing

作者： Busto, Monikka Roslianna Enomoto, Shohei Eda, Takeharu NTT Software Innovat Ctr Tokyo Japan

ISBN: (纸本)9798350349405;9798350349399

Collaborative intelligence (CI) streamlines DNN deployment in edge-cloud infrastructure by optimizing workload between the edge and the cloud. It leverages data sparsity for both data compression for cloud transmission and the reduction of the overall computational cost of the system. Despite the rising popularity of the Vision Transformer (ViT), its higher computational overhead poses challenges for edge-cloud deployment compared to CNNs. Existing CI methods favor CNNs, utilizing feature map sparsity. In contrast, ViTs exploit token-based sparsity, complicating the direct application of CNN-optimized CI methods. This motivates us to propose a novel CI approach exploiting the token sparsity of ViT. We propose an offloading policy network, which computes scores that reveal the tokens' relevance to the task before inference, effectively using sparse tokens in the offloaded data improving compression rate and computational cost for an edge-cloud system. Our method shows 41.98-45.75% computational cost reduction of ViT while maintaining accuracy degradation within 1.96-3.10 points and achieving a compression rate up to 36.85%.

关键词： Collaborative intelligence Vision Transformer Token Sparsity Edge Computing

来源：评论

学校读者我要写书评

暂无评论

IIR Filter Approximation of an Innovative Digital Audio Equalizer

IIR Filter Approximation of an Innovative Digital Audio Equa...

引用

8th International symposium on image and signal processing and Analysis (ISPA)

作者： Virgulti, Marco Cecchi, Stefania Piazza, Francesco Univ Politecn Marche DII A3lab I-60131 Ancona Italy

ISBN: (纸本)9789531841948;9789531841870

Digital audio equalization is used to enhance the listening experience introducing corrections in the auditory frequency response. The equalizer performance depends on its implementation which includes optimal filters with sharp transition bandwidth development and a low computational complexity. Starting from a previous FIR implementation based on multirate systems and filterbanks theory, an optimized digital audio equalizer is derived. The proposed approach employs an approximation of the FIR structure using IIR filters, in order to improve the filterbanks structure developed to avoid interferences between adjacent bands. The effectiveness of the optimized implementation is shown comparing it with the previous approaches of the state of the art. The experimental results confirms that the presented solution has several advantages increasing the equalization performance in terms of low computational complexity, low delay, and uniform frequency response.

关键词： FIR filters IIR filters audio signal processing channel bank filters frequency response

来源：评论

学校读者我要写书评

暂无评论

Lightweight Deep Neural Network Model With Padding-Free Downsampling

引用

ieee signal processing LETTERS 2024年 31卷 865-869页

作者： Liu, Dengfeng Guo, Xiaohe Wang, Ning Wu, Qin Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi 214122 Peoples R China Jiangnan Univ Engn Res Ctr Intelligent Technol Healthcare Minist Educ Wuxi 214122 Peoples R China Wuxi Machinery & Electron Higher Profess & Tech Sc Wuxi 214028 Peoples R China

Deep neural networks have achieved impressive performance in image classification tasks. However, due to limitations in hardware resources, including computing units and storage capacity, deploying these networks directly on resource-constrained devices such as mobile and edge devices is challenging. While lightweight network models have made significant advancements, the downsampling stage has received little attention. As the feature map is reused multiple times, the reduction of its size during the downsampling stage not only reduces the computational cost of the downsampling module itself but also lowers the computational burden of subsequent stages. This letter addresses this gap by proposing a padding-free downsampling module that effectively reduces computational costs and can seamlessly integrates into various deep learning models. Furthermore, we introduce a hybrid stem layer to obtain competitive accuracy. Extensive experiments were conducted on CIFAR-100, Stanford Dogs, and imageNet datasets. On the CIFAR-100 dataset, the results show that the proposed module reduces computational costs by approximately 20% and improves inference speed on resource-constrained devices by around 10%.

关键词： Deep learning image classification model architecture design neural network lightweighting

来源：评论

学校读者我要写书评

暂无评论

ON-BOARD MULTISPECTRAL image COMPRESSION WITH AN ARTIFICIAL intelligence BASED ALGORITHM

ON-BOARD MULTISPECTRAL IMAGE COMPRESSION WITH AN ARTIFICIAL ...

引用

ieee International Geoscience and Remote Sensing symposium (IGARSS)

作者： Guerrisi, Giorgia Bencivenni, Gianmarco Schiavon, Giovanni Del Frate, Fabio Tor Vergata Univ Rome DICII I-00133 Rome Italy GEO K Srl I-00133 Rome Italy

ISBN: (纸本)9798350360332;9798350360325

Remote Sensing (RS) is applied for a variety of purposes, thanks to the large availability of heterogeneous data. Furthermore, the growing number of CubeSat missions is encouraging increasingly advanced, flexible, and configurable RS missions, that also include the use of Artificial intelligence (AI) on-board. Indeed, specific hardware allows advanced processing on-board the satellites even if the computational capability is not the same as on the ground. In the context of on-board processing, the compression of acquired images is crucial because permits to save bandwidth for data transmission. We propose an AI-based lossy image compression algorithm for multispectral images that can be executed on-board a CubeSat. The algorithm is based on a Convolutional AutoEncoder (CAE) Neural Network (NN). In lossy compression part of the information stored in the original image is lost. Therefore, the results evaluation includes the assessment of the usability of the decompressed images for common applications.

关键词： on-board processing artificial intelligence image compression multispectral images cubesats

来源：评论

学校读者我要写书评

暂无评论

High accuracy WaDi image interpolation with local gradient features

High accuracy WaDi image interpolation with local gradient f...

引用

International symposium on Intelligent signal processing and Communication Systems

作者： Yuan, S Abe, M Taguchi, A Kawamata, M Tohoku Univ Grad Sch Engn Dept Elect Engn Aoba Ku Sendai Miyagi 9808579 Japan

ISBN: (纸本)0780392663

In this paper, we propose a new computational method of the warped distance (WaDi) for digital image interpolation. The conventional WaDi algorithm only uses the local asymmetry features of image edges to compute the WaDi and then uses the computed WaDi in place of the interpolation operator in the linear interpolations. The local gradient features are one kind of the important features of image edges as well as the local asymmetry features. In this paper, we adopt both the local asymmetry features and the local gradient features in the WaDi computation. Experimental results show that the proposed method can obtain high accuracy interpolated images.

关键词： Interpolation

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：