检索结果-内蒙古大学图书馆

Denoising The Wireless Channel Corrupted Images Using Machine Learning 20

Denoising The Wireless Channel Corrupted Images Using Machin...

20th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, networking and Parallel/Distributed computing (SNPD 2019)

作者： Sufiant, Muhammad Khan, Aimal Saced, Takreem Khan, Zirak NUST CEME Dept Comp Engn Islamabad Pakistan

ISBN: (纸本)9781728116518

Digital communication depends on channel coding for the integrity and correct reception of the data. The traditional communication techniques ignore the context and content associated with the received data while mitigating the channel effects. Image transmission in digital communication have many major constraints. Image quality degrades over wireless channel due to limited characteristic of transmitted data. To mitigate the effects of the noisy channel on the images different image denoising techniques are used such as DCT, Convolutional Denoising Autoencoders, DWT, BM3D, FFT, NLM and Deep Learning. Main objective of this paper is to study the application of machine learning in digital communication to correct errors and remove the effects of channel degradation. This will help us improve the energy consumption, resource utilization, and the Bit Error Rate. It will enable us to communicate with low bandwidth and using minimum resources. Machine learning for denoising the image has attracted substantial attentions because of its high denoising performance. We have constructed a Convolutional neural network that will denoise the image which is corrupted by the noisy channel. The existing traditional models only denoise the image for a specific noise type (Gaussian noise) and certain noise level sigma = 25, but our trained network denoise the image for unknown noise level. By using the methods of batch normalization and residual learning the denoising performance is increased. Experiments prove that our trained model displays high efficiency in image denoising. The proposed network is trained in MATLAB and Python with the help of GPU computing which accelerates neural network's performance. The application areas of this paper mainly are in the domains related to digital communications. This include wireless communications, optical communications and line communications. However, as the wireless communications (especially underwater wireless) is extremely error prone,

关键词： Digital Communication Machine Learning Batch Normalization Image Transmission Residual Learning Image Denoising Deep Learning Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Guided Learning for Efficient optical Flow Estimation

Guided Learning for Efficient Optical Flow Estimation

引用

International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI)

作者： Canrong Yao Junyi Wu Shiyu Miao Renyu Huang Zhipeng Gao Jianqiang Zhao AI Research Center Xiamen Meiya Pico Information Co.Ltd Xiamen China School of Electronic Science and Engineering Xiamen University Xiamen China

ISBN: (数字)9781728196381

ISBN: (纸本)9781728196398

Current optical flow estimation models require a large number of computing resources, resulting in excessive runtimes to perform inference for mobile devices. Considerable efforts have been exerted to compress deep neural networks, but these approaches have resulted in reduced accuracy. Comparing with other network compression methods, guided learning achieves competitive performance without the need of modifying or retraining the original network as network pruning or specific hardware environment support as network quantization. Guided learning has demonstrated excellent improvements in classification and detection. However, there is still leak of research on guided learning for optical flow estimation. In this work, we propose a novel framework to learn a compact and fast optical flow estimation network, and it can achieve competitive performance through guided learning. We train the small network through additional supervision from high-level feature maps in original optical flow estimation networks to effectively learn robust and efficient features. The overall compression framework is implemented by distilling knowledge from the feature maps of the decoder in original network with a proposed feature guiding loss to transfer knowledge to small network. Lastly, we conduct a comprehensive empirical evaluation over three datasets. Results show consistent improvement in accuracy-speed tradeoffs for the optical flow estimation network.

关键词： Performance evaluation Knowledge engineering Runtime Quantization (signal) Estimation Task analysis optical flow

来源：评论

学校读者我要写书评

暂无评论

Deep CNN framework for retinal disease diagnosis using optical coherence tomography images

引用

Journal of Ambient Intelligence and Humanized computing 2020年第7期12卷 7569-7580页

作者： Rajagopalan, Nithya Narasimhan, Venkateswaran Kunnavakkam Vinjimoor, Swetha Aiyer, Janani Department of Biomedical Engineering Sri Sivasubramaniya Nadar College of Engineering Chennai India Department of Electronics and Communication Engineering Sri Sivasubramaniya Nadar College of Engineering Chennai India

Accurate and robust diagnosis of retinal diseases using OCT imaging is considered an essential part for clinical utility. We propose a deep learning based, a fully automated diagnosis system for detecting retinal disorders namely, Drusen macular degeneration (DMD) and diabetic macular edema (DME) using optical coherence tomography (OCT) Images. If it is not diagnosed and treated, these degenerative abnormalities may result in moderate to severe vision loss. Early detection of these diseases reduces the risk of further complications and expedites the treatment process. We propose a deep convolutional neural network (CNN) framework for the diagnosis and classification into Normal, DMD and DME effectively. First, despeckling of the input OCT images is performed using the Kuan filter to remove inherent speckle noise. Further, the CNN network is tuned using hyperparameter optimization techniques. Additionally, K-fold validation is performed to ensure complete usage of the dataset. We evaluate the proposed model with number of performance metrics using Mendeley database consisting of labelled OCT images. The resulting classification accuracy of the proposed model is 95.7%. Further, an authoritative study is performed between the pre-trained models and proposed framework using the acquired performance metrics to demonstrate the efficacy of our model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Claßification of brain lesions from MRI images using a novel neural network 15

Claßification of brain lesions from MRI images using a nove...

引用

Multimodal Biomedical Imaging XV 2020

作者： Bamba, Udbhav Pandey, Deepanshu Lakshminarayanan, Vasudevan Department of Mathematics and Computing Indian Institute of Technology Dhanbad India Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science University of Waterloo Waterloo Canada

ISBN: (纸本)9781510632271

There is considerable interest in using convolutional neural networks for computer aided medical diagnostics. In this paper, we present some recent results on brain lesion segmentation. While algorithms have been developed to automate the proceß, the results often lack accuracy in tracing the lesions. Here, we present our results on the publically available ATLAS R1.1 dataset using deep CNN architectures. We utilize a deep U-net architecture with 3D convolutions, consisting of an encoder and a corresponding decoder along with dense residual connections between them, leveraging both low and high level features from the encoder at each step. We also analyze the use of Inception, Residual and Inception-Res blocks for the encoder. The architecture also makes use of an attention gate for the decoder part to suppreß irrelevant parts of the incoming input while highlighting the salient features. The dataset had 239 3D MRI images of dimensions (197 x 233 x 189) with their corresponding segmentation maps. We used a train-validation-test split of 7:2:1, employing mean normalization, histogram equalization and suitable data augmentation techniques. We used SGD optimizer with focal Tversky loß function. The Dice score and AUC were used as metrics. We were able to achieve a Dice coefficient of 0.53 with an AUC around 0.95 with a single end-to-end model, unlike previous models that either focus only on one part of the brain or use other metadata, and matched their performance in every aspect. We further discuß the poßibilities of improving the results through denoising and data cleansing using standard machine learning and computer vision methodologies. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Noisy Machines: Understanding Noisy neural networks and Enhancing Robustness to Analog Hardware Errors Using Distillation

arXiv

引用

arXiv 2020年

作者： Zhou, Chuteng Mattina, Matthew Kadambi, Prad Whatmough, Paul N. Arm Research BostonMA United States Arm Research Boston MA United States School of Electrical Computer and Energy Engineering Arizona State University TempeAZ United States

The success of deep learning has brought forth a wave of interest in computer hardware design to better meet the high demands of neural network inference. In particular, analog computing hardware has been heavily motivated specifically for accelerating neural networks, based on either electronic, optical or photonic devices, which may well achieve lower power consumption than conventional digital electronics. However, these proposed analog accelerators suffer from the intrinsic noise generated by their physical components, which makes it challenging to achieve high accuracy on deep neural networks. Hence, for successful deployment on analog accelerators, it is essential to be able to train deep neural networks to be robust to random continuous noise in the network weights, which is a somewhat new challenge in machine learning. In this paper, we advance the understanding of noisy neural networks. We outline how a noisy neural network has reduced learning capacity as a result of loss of mutual information between its input and output. To combat this, we propose using knowledge distillation combined with noise injection during training to achieve more noise robust networks, which is demonstrated experimentally across different networks and datasets, including ImageNet. Our method achieves models with as much as ∼ 2× greater noise tolerance compared with the previous best attempts, which is a significant step towards making analog hardware practical for deep learning. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep-learning algorithm for the diagnosis and prediction of hydroxychloroquine retinopathy: An International, multi-institutional study

引用

Ophthalmology Retina 2025年

作者： Peter Woodward-Court Jeffry Hogg Terry Lee Priyal Taribagil Cindy S. Zhao Vanessa Otti William R. Tucker Michael Allingham Oleg Alekseev Siegfried K. Wagner David Myung Loh-Shan Leung Eleonora M. Lad Hani Hasan James Talks Daniel C. Alexander Pearse A. Keane Eliot R. Dow NIHR Biomedical Research Centre Moorfields Eye Hospital NHS Foundation Trust UCL Institute of Ophthalmology London UK Department of Ophthalmology Newcastle-upon-Tyne Hospital NHS Foundation Trusts Newcastle-upon-Tyne UK Department of Ophthalmology Duke University Medical Center 2351 Erwin Rd Durham North Carolina 27705 Byers Eye Institute at Stanford Department of Ophthalmology Stanford University School of Medicine Palo Alto California 94303 Veterans Affairs Palo Alto Health Care System Palo Alto CA USA 94304 Centre for Medical Image Computing Department of Computer Science UCL London UK Retinal Consultants Medical Group Sacramento CA USA 95825

Purpose We sought to develop a deep-learning algorithm - HCQuery - to detect the presence of hydroxychloroquine retinopathy and predict its future occurrence from spectral-domain optical coherence tomography (SD-OCT) images. Design We trained and validated a deep-learning algorithm using retrospective SD-OCT images from patients taking hydroxychloroquine. Participants The study involved a retrospective, non-consecutive collection of 409 patients (171 positive for hydroxychloroquine retinopathy, 238 negative for retinopathy) and 8251 SD-OCT b-scans (1988 volumes) from five independent international clinical locations. Methods Imaging macular volumes from two different SD-OCT devices (Heidelberg Spectralis, Zeiss Cirrus) at two clinical sites were used to train and validate a convolutional neural network (EfficientNet-b4) to produce a Likelihood of Retinopathy Score (LRS) for each SD-OCT b-scan. LRS scores were processed across SD-OCT volumes for an eye- and patient-level binary decision output of the presence or absence of retinopathy. The adjudicated consensus of up to three independent retina specialists using patient clinical data and multimodal testing served as the reference standard for hydroxychloroquine retinopathy. The algorithm was tested on four withheld test sets, one internal (Data Set 1) and three external (Data Sets 3, 4, and 5). The test sets were obtained in two countries (United States, United Kingdom) and represented two SD-OCT devices each with diverse acquisition parameters. Main Outcome Measures The algorithm was assessed with sensitivity, specificity, accuracy, negative predictive value (NPV), positive predictive value (PPV), area under the receiver-operator characteristic (AUROC), and area under the precision-recall curve (AUPRC) for the detection of hydroxychloroquine retinopathy either at the time of clinical diagnosis or up to 18 months in advance of clinical diagnosis. Results The algorithm demonstrated discriminated hydroxychloroquine ret

关键词： hydroxychloroquine retinopathy HCQ machine learning AUROC area under the receiver-operator characteristic AUPRC area under the precision-recall curve CNN convolutional neural network HCQ hydroxychloroquine LRS likelihood of retinopathy score mfERG multifocal electroretinography NPV negative predictive value PPV positive predictive value PACS picture archiving and communication system SaMD software as a medical device SD-OCT spectral domain optical coherence tomography VF visual field

来源：评论

学校读者我要写书评

暂无评论

Extraction of Information from Handwriting using optical Character recognition and neural networks

Extraction of Information from Handwriting using Optical Cha...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： Piyush Mishra Pratik Pai Mihir Patel Reena Sonkusare Sardar Patel Institute Of Technology Mumbai India

ISBN: (数字)9781728163871

ISBN: (纸本)9781728163888

Image Processing is a vital tool when one is dealing with several images and wishes to perform several complex actions on the same. With advances in technologies, one can now compress, manipulate, extract required information, etc. from any image one wants to. One such application of Image processing is detecting handwritten text and converting it to a digital text format. The main objective is to bridge the gap between the actual bit of paper and the digital world and in doing so, one can operate on the digital data much faster as compared to the actual data. Hence, in this paper, we aim to implement the detection of handwritten text via optical Character Recognition (OCR). The entire paper will be implemented on TensorFlow. This research work has also analyzed various results and taken appropriate dataset to train the model. Further, the importance of this paper lies in the fact that it can facilitate and open various unexplored avenues. The key novelty of the paper lies in the fact that the data-set used is comprehensive which helps us to produce better result. In addition, the paper successfully analyzes handwritten scripts and extracts it in digital form. Analyzing the text can help combat forgery, understand certain temperaments of the person writing the text, and so on. Coupled with this, this paper has successfully implemented an improved version as compared to the pre-existing solutions by using the convergence of convoluted neural networks (CNN) and the Recurrent neural network (RNN).

关键词： optical character recognition software Hidden Markov models Recurrent neural networks Character recognition optical imaging optical computing Training

来源：评论

学校读者我要写书评

暂无评论

光学神经网络研究进展

引用

宇航计测技术 2025年第2期45卷 49-62页

作者：冯佳楠胡建阳张修建林杰金鹏哈尔滨工业大学微系统与微结构制造教育部重点实验室哈尔滨150001 北京航天计量测试技术研究所人工智能计量测试与标准重点实验室北京100076

近年来,以深度学习为代表的人工智能技术快速发展,人工智能深度赋能传统行业,引领实现新一轮产业技术革命。然而,电子芯片晶体管的尺寸正逐步接近物理极限,导致传统电子神经网络无法满足指数增长的算力需求。受益于光子的独特优势,光计... 详细信息

近年来,以深度学习为代表的人工智能技术快速发展,人工智能深度赋能传统行业,引领实现新一轮产业技术革命。然而,电子芯片晶体管的尺寸正逐步接近物理极限,导致传统电子神经网络无法满足指数增长的算力需求。受益于光子的独特优势,光计算技术将光电子技术与神经网络模型相结合,具有并行化、高速度、低功耗、多维度处理优势。文章对光学神经网络研究过程进行了梳理,重点对光学衍射神经网络的计算架构进行了分析讨论,最后总结了大规模光学衍射神经网络实用化面临的挑战,并对未来发展趋势进行了展望。

关键词：光学信息处理光计算光学神经网络

来源：评论

学校读者我要写书评

暂无评论

Wavefield Reconstruction of Distributed Acoustic Sensing: Lossy Compression, Wavefield Separation, and Edge computing

Journal of Geophysical Research: Machine Learning and Comput...

引用

Journal of Geophysical Research: Machine Learning and Computation 2024年第3期1卷

作者： Yiyu Ni Marine A. Denolle Qibin Shi Bradley P. Lipovsky Shaowu Pan J. Nathan Kutz Department of Earth and Space Sciences University of Washington Seattle WA USA Department of Applied Mathematics University of Washington Seattle WA USA Now at the Department of Mechanical Aerospace and Nuclear Engineering Rensselaer Polytechnic Institute Troy NY USA

Distributed acoustic sensing (DAS) presents challenges and opportunities for seismological research and data management. This study explores wavefield reconstruction using deep learning methods for data compression and wavefield separation. We test various architectures to treat DAS data as two-dimensional arrays, such as the implicit neural representation (INR) models and the SHallow REcurrent Decoder (SHRED) model. The INR models present better data compression ability but do not generalize over space and time, a major practical limitation. On the other hand, SHRED generalizes over space and time for a single optical fiber with data from 20% decimated channels for the reconstruction. Despite good performance in reconstructing long-wavelength features, the shallow recurrent decoder does not reconstruct transient earthquake wavefields at shorter wavelengths, limiting its usability for seismic data transmission. Nevertheless, we leverage wavefield reconstruction of ocean waves to separate them from the seismic wavefield and improve seismological use cases for earthquake detection and Earth imaging. In summary, as a lightweight deep learning model, SHRED is well suited for wavefield separation and lossy compression of the DAS data. Shallow Recurrent Decoder network provides a form of wavefield reconstruction for sparse networks Wavefield reconstruction allows for low-cost, efficient compression of large array data, such as distributed acoustic sensing The smooth reconstructed wavefield can be separated from the original data to enhance high-frequency transient seismic waves In this study, we address the challenge of handling large amounts of data from distributed acoustic sensing (DAS), particularly in offshore areas like Cook Inlet, Alaska. DAS records various ground motions from oceanic and seismic waves, making data management complex. We explore the compression and reconstruction of wavefield data using emerging deep-learning methods. We find that a simple SHallow

关键词：

来源：评论

学校读者我要写书评

暂无评论

PixMap: Automatic License Plate Recognition with Convolutional neural network based on saliency maps

PixMap: Automatic License Plate Recognition with Convolution...

引用

Conference on Digital optical Technologies

作者： Sanogo, Assan LLanza, Arcadi Shvai, Nadiya Hasnat, Abul Khata, Marouan El Khattabi, Yassine Meicler, Antoine Hemery, Alice Nakib, Amir Cyclope Ai 6 Pl Colonel Bourgoin F-75012 Paris France Univ Paris Est Lab LISSI Vitry Sur Seine France

ISBN: (纸本)9781510628045

Automatic License Plate Recognition (ALPR) is a technology designed to automatically read vehicle license plates. Traditional ALPR systems first detect the License Plate (LP), then apply the optical Character Recognition (OCR) pipeline, which includes LP image pre-processing, character segmentation, character classification and post-processing. An ALPR system developed with such approaches often fails to provide acceptable results due to numerous challenging situations, which significantly increase the appearance variability of LPs as well as the characters to be classified. Recently, Convolutional neural network (CNN) models have proved efficient for ALPR problems. However, many of these CNN-based methods yet exhibit vulnerabilities to properly localize the region of the characters' sequence and therefore provide an incorrect segmentation. Herein, this paper presents a novel real-time ALPR system that uses the concept of saliency map within the CNN model. The key contribution is at the segmentation step where the characters are located by means of the saliency map, which helps to refine the character classification step. The proposed ALPR pipeline consists of the two modules: 1) LP-localization-CNN to detect the LP and 2) Saliency-Map-CNN to segment the characters in the LP. Experiments are conducted on a private and three public datasets and the proposed method is compared to the state-of-the-art methods. Results show that it performs well with respect to both accuracy and computation time, and hence clearly demonstrate the usefulness of the proposed system for the real-world ALPR applications.

关键词： OCR CNN cloud-computing super-resolution saliency map real-time processing embedded systems weakly supervised training

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：