检索结果-内蒙古大学图书馆

3rd International Conference on Innovative computing and Communication, ICICC 2020

作者： Sarin, Sumit Chugh, Anirudh Mittal, Antriksh Srivastava, Smriti Netaji Subhas Institute of Technology New Delhi India

ISBN: (纸本)9789811551475

Human gait is a biometric feature based on the walking manner of an individual. In this paper, we have compared different Convolutional neural network architectures for the task of human identification, which has a variety of applications in domains such as security and surveillance. This is a contribution to the existing literature in gait recognition where most of the research till now has only used VGG-like networks despite new and better networks having been developed in recent times. The architectures explored and compared include VGGNet, ResNet, and DenseNet. The CASIA-B dataset is used for evaluating the models. We have discussed the results and compared the models in terms of their advantages and disadvantages in gait recognition. We discovered that VGGNet and DenseNet architectures perform well by efficiently utilizing gait data for human identification. The choice of the architecture to be used would depend on the requirements and constraints of the problem. For instance, we found that DenseNet, while using the least number of trainable parameters, gives a very good rank-5 accuracy;while VGGNet performs better in terms of Rank-1 accuracy. We also found that even though ResNet uses the most number of trainable parameters, it does not give any advantage over the other architectures. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.

关键词： optical flows

来源：评论

学校读者我要写书评

暂无评论

Study of Various Deep Learning models for COVID-19 Detection Based on Fractional Order optical Flow

Study of Various Deep Learning Models for COVID-19 Detection...

引用

International Conference on computing and networking Technology (ICCNT)

作者： Bhavana Singh Muzammil Khan Pushpendra Kumar Department of Mathematics Bioinformatics & Computer Applications Maulana Azad National Institute of Technology Bhopal India

The world entered into a new phase in the wake of Covid-19, which is declared as a global threat because countless people were losing their lives worldwide due to this disease every day. Even the best medical facilities were crumbling due to the rise of COVID-19 and lack of funding. However the use of nucleic acid-based testing generates an excessive amount of bio-waste and increases the risk of infection to the healthcare personnel. These tests take a lot of time, which contributes to the high mortality rate. To address these challenges, vision based techniques have been demonstrated to be beneficial in the early and swift diagnosis of COVID-19. Earlier imaging techniques used X-ray or CT-scan images to detect COVID-19. Consequently, these techniques do not filter out non-COVID cases, resulting in longer processing time. In this paper, COVID-19 identification is accomplished through the dynamic characteristics obtained from chest X-ray (CXR) images. These dynamic characteristics are derived as optical flow (OF). Moreover a fractional order-based variational model is used to estimate OF from two consecutive images of lungs. The novelty of this work is to use OF instead of images in COVID-19 detection. Further, the classification of lung dynamic features is performed with a convolutional neural network (CNN) in coordination of various machine learning (ML) classifiers. A detailed comparison is provided to show the significance of the algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accurate Neuroanatomy Segmentation Using 3D Spatial and Anatomical Attention neural networks 14

Accurate Neuroanatomy Segmentation Using 3D Spatial and Anat...

引用

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Cheng, Hewei Ren, Zhengyu Li, Peiyang Tian, Yin Wang, Wei Li, Zhangyong Fan, Yong Research Center of Biomedical Engineering Chongqing University of Posts and Telecommunications Chongqing China Chongqing Engineering Laboratory of Digital Medical Equipment and Systems Chongqing University of Posts and Telecommunications Chongqing China Chongqing Engineering Research Center of Medical Electronics & Information Technology Chongqing University of Posts and Telecommunications Chongqing China Center for Biomedical Image Computing and Analytics Department of Radiology Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States

ISBN: (纸本)9781510657564

Brain structure segmentation from 3D magnetic resonance (MR) images is a prerequisite for quantifying brain morphology. Since typical 3D whole brain deep learning models demand large GPU memory, 3D image patch-based deep learning methods are favored for their GPU memory efficiency. However, existing 3D image patch-based methods are not well equipped to capture spatial and anatomical contextual information that is necessary for accurate brain structure segmentation. To overcome this limitation, we develop a spatial and anatomical context-aware network to integrate spatial and anatomical contextual information for accurate brain structure segmentation from MR images. Particularly, a spatial attention block is adopted to encode spatial context information of the 3D patches, an anatomical attention block is adopted to aggregate image information across channels of the 3D patches, and finally the spatial and anatomical attention blocks are adaptively fused by an element-wise convolution operation. Moreover, an online patch sampling strategy is utilized to train a deep neural network with all available patches of the training MR images, facilitating accurate segmentation of brain structures. Ablation and comparison results have demonstrated that our method is capable of achieving promising segmentation performance, better than state-of-the-art alternative methods by 3.30% in terms of Dice scores. © 2022 SPIE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

End-to-end deep learning with neuromorphic photonics 25

End-to-end deep learning with neuromorphic photonics

引用

Conference on Integrated Optics - Devices, Materials, and Technologies XXV

作者： Dabos, G. Mourgias-Alexandris, G. Totovic, A. Kirtas, M. Passalis, N. Tefas, A. Pleros, N. Aristotle Univ Thessaloniki Dept Informat Thessaloniki Greece Aristotle Univ Thessaloniki Ctr Interdisciplinary Res & Innovat Thessaloniki Greece

ISBN: (纸本)9781510642140

Neuromorphic computing has emerged as a highly-promising compute alternative, migrating from von-Neuman architectures towards mimicking the human brain for sustaining computational power increases within a reduced power consumption envelope. Electronic neuromorphic chips like IBM's TrueNorth, Intel's Loihi and Mythic's AI platform reveal a tremendous performance improvement in terms of computational speed and density;at the same time, neuromorphic photonic layouts are constantly gaining ground in exploiting their large component portfolio for enabling GHz-bandwidth and low-energy neurons. Progressing in tight synergy with appropriate training techniques, this evolution has already started to translate into performance improvements in end-to-end applications, highlighting the practical perspectives of the new neural network hardware when effectively synergized with new training frameworks. Herein, we present a complete portfolio of neuromorphic photonic subsystems and architectures, highlighting their utilization in practical application scenario for time series classification and fiber transmission links. Our work extends along feed-forward and recurrent photonic NN models, demonstrating experimental results together with the required training methods for bridging the gap between software-deployed NNs and the photonic hardware. We report on the experimentally validated performance of a 10GHz photonic time series classification engine, presenting also preliminary results on how photonic neurons can replace DSP modules in end-to-end fiber transmission schemes. The perspectives of these layouts to yield energy and area efficiency benefits are discussed through a detailed energy and area breakdown of neuromorphic photonic technologies, highlighting a promising roadmap when plasmo-photonic hardware is adopted.

关键词： Neuromorphic photonics photonic integrated circuits neural networks optical computing artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Handwritten Text Recognition using VGG19 and HOG Feature Descriptors

Handwritten Text Recognition using VGG19 and HOG Feature Des...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： Saikrishna Devendiran Jyothiratnam Prema Nedungadi Raghu Raman School of Computing Amrita Vishwa Vidhyapeetham Amritapuri Kerala India Amrita Create Amrita Vishwa Vidhyapeetham Amritapuri Kerala India School of Computing Amritapuri Amrita Vishwa Vidhyapeetham Amritapuri Kerala India School of Business Amrita Vishwa Vidhyapeetham Amritapuri Kerala India

Recognition of Tamil characters has been a challenging task, and especially handwritten text recognition has been a bigger hassle. The intricacy of the script with its inherent cursive nature and the existence of numerous diacritical marks adds to the complexity of automating its recognition. In this research, we delve into the realm of optical Character Recognition (OCR) with a focus on handwritten Tamil characters, employing two distinct deep learning models: Model A using Histogram of Oriented Gradients (HOG) for feature extraction and Model B leveraging the robust architecture of VGG-19. We present a comprehensive dataset, meticulously compiled from over a thousand individuals across various age groups to capture the rich diversity of handwriting styles. Through a multi-stage preprocessing pipeline involving cropping, resizing, noise reduction, and grayscale conversion, we condition the images for optimal feature extraction. The study contrasts the performance of HOG-based feature extraction against the convolutional neural network approach of VGG-19, demonstrating the latter's superior efficacy in handling the complexity of Tamil character recognition. The results indicate a significant advancement in the accuracy and reliability of OCR for Tamil, with potential applications in digitizing historical manuscripts, facilitating digital learning, and supporting the preservation of this classical language.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bessel equivariant networks for inversion of transmission effects in multi-mode optical fibres 22

Bessel equivariant networks for inversion of transmission ef...

引用

Proceedings of the 36th International Conference on neural Information Processing Systems

作者： Joshua Mitton Simon Peter Mekhail Miles Padgett Daniele Faccio Marco Aversa Roderick Murray-Smith School of Computing Science University of Glasgow Glasgow Scotland UK School of Physics & Astronomy University of Glasgow Glasgow Scotland UK

ISBN: (纸本)9781713871088

We develop a new type of model for solving the task of inverting the transmission effects of multi-mode optical fibres through the construction of an SO+ (2, 1)-equivariant neural network. This model takes advantage of the of the azimuthal correlations known to exist in fibre speckle patterns and naturally accounts for the difference in spatial arrangement between input and speckle patterns. In addition, we use a second post-processing network to remove circular artifacts, fill gaps, and sharpen the images, which is required due to the nature of optical fibre transmission. This two stage approach allows for the inspection of the predicted images produced by the more robust physically motivated equivariant model, which could be useful in a safety-critical application, or by the output of both models, which produces high quality images. Further, this model can scale to previously unachievable resolutions of imaging with multi-mode optical fibres and is demonstrated on 256 × 256 pixel images. This is a result of improving the trainable parameter requirement from O(N4) to O(m), where N is pixel size and m is number of fibre modes. Finally, this model generalises to new images, outside of the set of training data classes, better than previous models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Near-Infrared Spectroscopy for Blood Glucose Level Classification

Intelligent Near-Infrared Spectroscopy for Blood Glucose Lev...

引用

Iranian Conference on Electrical Engineering (ICEE)

作者： Shahrooz Sharifi Amirhoseein Maddah-T. Mohammad-R. Akbarzadeh-T. Department of Electrical Engineering Ferdowsi University of Mashhad Mashhad Iran Centre of Excellence on Soft Computing and Intelligent Information Processing Ferdowsi University of Mashhad Mashhad Iran

ISBN: (数字)9798350376340

ISBN: (纸本)9798350376357

Diabetes Mellitus is a disease characterized by inadequate control of blood glucose levels, and it ranks among the leading causes of human mortality, the measurement of which, requires fingertip pricking. Nowadays, non-invasive healthcare monitoring systems based on wearable sensors and machine learning models hold the future of smart health. However, the nature of these methods is such that they get affected by internal physiological and external parameters, which is one of the obstacles to this path. This study aims to introduce a non-invasive blood glucose level classification method based on machine learning analysis. The device's sensor consists of an optical finger sensor that transmits near-infrared light, filtering, and amplification to reduce the noise of the extracted photoplethysmography signal. Moreover, we have adopted the four-stage framework of biomedical signal processing to analyze the acquired PPG signal. Before using the Savitzky-Golay derivation to pre-filter the signal and prepare it for feature extraction, it was normalized using Standard Normal Variate (SNV). In addition, four different machine learning models, including Support Vector Machine (SVM), Weighted K-Nearest Neighbors (KNN), Wide neural network, and Decision Tree were used for blood glucose level classification. For this study, a dataset was created consisting of 106 data, gathered from 27 subjects. Findings revealed that the Weighted KNN exhibited the best performance among other classification models, having 90.5% accuracy.

关键词： Support vector machines Stimulated emission Smart healthcare Machine learning Nearest neighbor methods Feature extraction Glucose

来源：评论

学校读者我要写书评

暂无评论

High-Accuracy Recognition of Orbital Angular Momentum Modes Propagated in Atmospheric Turbulences Based on Deep Learning

引用

IEEE ACCESS 2020年 8卷 159542-159551页

作者： Hao, Yuan Zhao, Lin Huang, Tao Wu, Yi Jiang, Ting Wei, Zhongchao Deng, Dongmei Luo, Ai-Ping Liu, Hongzhan South China Normal Univ Sch Informat & Optoelect Sci & Engn Guangzhou 510006 Peoples R China South China Normal Univ Guangdong Prov Key Lab Nanophoton Funct Mat & Dev Guangzhou 510006 Peoples R China

The atmospheric turbulence (AT) causes distortion of phase fronts of orbital angular momentum (OAM) beams, which hinders the recognition of OAM modes. Convolutional neural network (CNN), a deep learning (DL) technique, can be utilized to realize the effective recognition of OAM modes. In this article, we propose a properly designed six-layer CNN model that can achieve high recognition accuracy (RA) of OAM modes at a reasonable computing complexity. We used intensity images of Laguerre-Gaussian (LG) beams to train our CNN model and explored the relationship between the RA for different single OAM modes and many factors including the number of training epochs, AT intensity, transmission distance, and the number of single OAM modes. Our CNN model can obtain an RA of 97.1% under moderate turbulence and 80% under strong turbulence, which are better than some CNN models proposed previously. Compared with these previous CNN models, our CNN model can also reduce the time consumption for at most 70%. Our research could contribute in achieving higher data capacity in OAM-based free space optical (FSO) communication systems.

关键词： Computational modeling Feature extraction Laser beams Atmospheric modeling Complexity theory Training Fluctuations Atmospheric turbulence (AT) convolutional neural network (CNN) free-space optical (FSO) communication orbital angular momentum (OAM)

来源：评论

学校读者我要写书评

暂无评论

UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking neural networks 39

UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Qian, Yuanbin Ye, Shuhan Wang, Chong Cai, Xiaojie Qian, Jiangbo Wu, Jiafei Faculty of Electrical Engineering and Computer Science Ningbo University China Merchants’ Guild Economics and Cultural Intelligent Computing Laboratory Ningbo University China Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

ISBN: (纸本)157735897X

Video anomaly detection plays a significant role in intelligent surveillance systems. To enhance model’s anomaly recognition ability, previous works have typically involved RGB, optical flow, and text features. Recently, dynamic vision sensors (DVS) have emerged as a promising technology, which capture visual information as discrete events with a very high dynamic range and temporal resolution. It reduces data redundancy and enhances the capture capacity of moving objects compared to conventional camera. To introduce this rich dynamic information into the surveillance field, we created the first DVS video anomaly detection benchmark, namely UCF-Crime-DVS. To fully utilize this new data modality, a multi-scale spiking fusion network (MSF) is designed based on spiking neural networks (SNNs). This work explores the potential application of dynamic information from event data in video anomaly detection. Our experiments demonstrate the effectiveness of our framework on UCF-Crime-DVS and its superior performance compared to other models, establishing a new baseline for SNN-based weakly supervised video anomaly detection. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Primer on silicon neuromorphic photonic processors: architecture and compiler

引用

NANOPHOTONICS 2020年第13期9卷 4055-4073页

作者： de Lima, Thomas Ferreira Tait, Alexander N. Mehrabian, Armin Nahmias, Mitchell A. Huang, Chaoran Peng, Hsuan-Tung Marquez, Bicky A. Miscuglio, Mario El-Ghazawi, Tarek Sorger, Volker J. Shastri, Bhavin J. Prucnal, Paul R. Queens Univ Dept Phys Engn Phys & Astron Kingston ON KL7 3N6 Canada Princeton Univ Dept Elect Engn Princeton NJ 08544 USA George Washington Univ Dept Elect & Comp Engn Washington DC 20052 USA

Microelectronic computers have encountered challenges in meeting all of today's demands for information processing. Meeting these demands will require the development of unconventional computers employing alternative processing models and new device physics. neural network models have come to dominate modern machine learning algorithms, and specialized electronic hardware has been developed to implement them more efficiently. A silicon photonic integration industry promises to bring manufacturing ecosystems normally reserved for microelectronics to photonics. Photonic devices have already found simple analog signal processing niches where electronics cannot provide sufficient bandwidth and reconfigurability. In order to solve more complex information processing problems, they will have to adopt a processing model that generalizes and scales. Neuromorphic photonics aims to map physical models of optoelectronic systems to abstract models of neural networks. It represents a new opportunity for machine information processing on sub-nanosecond timescales, with application to mathematical programming, intelligent radio frequency signal processing, and real-time control. The strategy of neuromorphic engineering is to externalize the risk of developing computational theory alongside hardware. The strategy of remaining compatible with silicon photonics externalizes the risk of platform development. In this perspective article, we provide a rationale for a neuromorphic photonics processor, envisioning its architecture and a compiler. We also discuss how it can be interfaced with a general purpose computer, i.e. a CPU, as a coprocessor to target specific applications. This paper is intended for a wide audience and provides a roadmap for expanding research in the direction of transforming neuromorphic photonics into a viable and useful candidate for accelerating neuromorphic computing.

关键词： neuromorphic computing optical neural networks photonic integrated circuits silicon photonics ultrafast information processing

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：