检索结果-内蒙古大学图书馆

Photonic Convolutional neural networks Using Integrated Diffractive Optics

IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS 2020年第5期26卷

作者： Ong, Jun Rong Ooi, Chin Chun Ang, Thomas Y. L. Lim, Soon Thor Png, Ching Eng ASTAR Inst High Performance Comp Singapore 138632 Singapore

With recent rapid advances in photonic integrated circuits, it has been demonstrated that programmable photonic chips can be used to implement artificial neural networks. Convolutional neural networks (CNN) are a class of deep learning methods that have been highly successful in applications such as image classification and speech processing. We present an architecture to implement a photonic CNN using the Fourier transform property of integrated star couplers. We show, in computer simulation, high accuracy image classification using the MNIST dataset. We also model component imperfections in photonic CNN and show that the performance degradation can be recovered in a programmable chip. Our proposed architecture provides a large reduction in physical footprint compared to current implementations as it utilizes the natural advantages of optics and hence offers a scalable pathway towards integrated photonic deep learning processors.

关键词： Photonics Discrete Fourier transforms Couplers Optical waveguides Convolution High-speed optical techniques Optical interferometry artificial neural networks neuromorphics photonic integrated circuits silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Physics-constrained comprehensive optical neural networks 24

Physics-constrained comprehensive optical neural networks

引用

Proceedings of the 38th International Conference on neural Information processing Systems

作者： Yanbing Liu Jianwei Qin Yan Liu Xi Yue Xun Liu Guoqing Wang Tianyu Li Fangwei Ye Wei Li Beijing University of Posts and Telecommunications Beijing China Shanghai Jiao Tong University Shanghai China Beijing Institute of Space Mechanics and Electricity Beijing China University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798331314385

With the advantages of low latency, low power consumption, and high parallelism, optical neural networks (ONN) offer a promising solution for time-sensitive and resource-limited artificial intelligence applications. However, the performance of the ONN model is often diminished by the gap between the ideal simulated system and the actual physical system. To bridge the gap, this work conducts extensive experiments to investigate systematic errors in the optical physical system within the context of image classification tasks. Through our investigation, two quantifiable errors—light source instability and exposure time mismatches—significantly impact the prediction performance of ONN. To address these systematic errors, a physics-constrained ONN learning framework is constructed, including a well-designed loss function to mitigate the effect of light fluctuations, a CCD adjustment strategy to alleviate the effects of exposure time mismatches and a 'physics-prior-based' error compensation network to manage other systematic errors, ensuring consistent light intensity across experimental results and simulations. In our experiments, the proposed method achieved a test classification accuracy of 96.5% on the MNIST dataset, a substantial improvement over the 61.6% achieved with the original ONN. For the more challenging QuickDraw16 and Fashion MNIST datasets, experimental accuracy improved from 63.0% to 85.7% and from 56.2% to 77.5%, respectively. Moreover, the comparison results further demonstrate the effectiveness of the proposed physics-constrained ONN learning framework over state-of-the-art ONN approaches. This lays the groundwork for more robust and precise optical computing applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Detection and Categorization of Thyroid Nodules from Medical Ultrasound images

Efficient Detection and Categorization of Thyroid Nodules fr...

引用

artificial Intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Prarthana A. Deshkar Punit Fulzele Department of Computer Technology Yeshwantrao Chavan College of Engineering Nagpur Datta Meghe Institute of Higher Education and Research Sawangi Wardha

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

The use of ML and DL in medical imaging for early illness symptom prediction is substantial. Since 2013, DL has been one of the rising trends in general data analysis. With its multiple hidden layers that allow for a high degree of data abstraction, it is an enhancement of artificial neural networks (ANN). One promising approach for computer vision applications is the use of convolutional neural networks (CNNs). Automatic learning of raw data, particularly photographs, is a capability of deep CNNs. Both the capture and interpretation of images are crucial for the correct diagnosis or evaluation of illness. Devices are able to gather data at a rapid pace with improved resolution because to advancements in image acquisition over the last decade. Nevertheless, computer technology has only just started to improve picture interpretation. Since they are subjective and need highly trained doctors, they are often created by radiologist, physicians, and senior doctors. In medical imaging, computerised tools play a crucial role in facilitating results and improving diagnosis. Early detection and categorization of thyroid nodules by visual inspection and manual study of thyroid ultrasonography (USG) images has traditionally been a tedious process. Identifying benign from malignant thyroid nodules requires manual evaluation of thyroid USG images, which may be a time-consuming and laborious process. The medical industry has seen the emergence of many deep learning models, particularly for the categorization of thyroid nodules, thanks to the growth in processing resources and the fast improvement in technology. Clinical interventions and therapies may be more successful when these nodules are detected early. Thus, a growing number of academics are pushing for the use of computer diagnostic systems (CDS) as a means to statistically and scientifically evaluate USG pictures of thyroid nodules. Creating effective models for identifying and classifying thyroid nodules using ML and DL

关键词： Industries Deep learning Computational modeling Optimization methods Ultrasonography Manuals Convolutional neural networks Medical diagnostic imaging Thyroid Cancer

来源：评论

学校读者我要写书评

暂无评论

Multidimensional Convolution Operation with Synthetic Frequency Dimensions in Photonics

引用

Physical Review Applied 2022年第3期18卷 034088-034088页

作者： Lingling Fan Zhexin Zhao Kai Wang Avik Dutt Jiahui Wang Siddharth Buddhiraju Casey C. Wojcik Shanhui Fan Department of Electrical Engineering Ginzton Laboratory Stanford University Stanford California 94305 USA Department of Mechanical Engineering and Institute for Physical Science and Technology University of Maryland College Park Maryland 20742 USA Department of Applied Physics Stanford University Stanford California 94305 USA

The convolution operation is widely used in signal and image processing and represents the most computationally intensive step in convolutional neural networks. We introduce a scheme to achieve arbitrary convolution kernels in the synthetic frequency dimension with a simple setup consisting of a ring resonator incorporating a phase and an amplitude modulator. This scheme can be used to perform multidimensional convolutions. We provide an analytic approach that determines the required modulation profile for any convolution kernel. Our work points to a direction of using optical computing to remove the computational bottleneck in traditional electronic circuits and may be useful in improving machine-learning hardware in artificial-intelligence applications.

关键词： Photonics artificial neural networks Convolutional neural networks Machine learning Optical computing

来源：评论

学校读者我要写书评

暂无评论

A New Lightweight In Situ Adversarial Sample Detector for Edge Deep neural Network

引用

IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS 2021年第2期11卷 252-266页

作者： Wang, Si Liu, Wenye Chang, Chip-Hong Nanyang Technol Univ Dept Elect & Elect Engn Singapore 639798 Singapore

The flourishing of Internet of Things (IoT) has rekindled on-premise computing to allow data to be analyzed closer to the source. To support edge artificial Intelligence (AI), hardware accelerators, open-source AI model compilers and commercially available toolkits have evolved to facilitate the development and deployment of applications that use AI at its core. This paradigm shift in deep learning computations does not, however, reduce the vulnerability of deep neural networks (DNN) against adversarial attacks but introduces a difficult catch-up. This is because existing methodologies rely mainly on off-line analysis to detect adversarial inputs, assuming that the deep learning model is implemented on a 32-bit floating-point graphical processing unit (GPU) instance. In this paper, we propose a new hardware-oriented approach for in-situ detection of adversarial inputs feeding through a spatial DNN accelerator architecture or a third-party DNN Intellectual Property (IP) implemented on the edge. Our method exploits controlled glitch injection into the clock signal of the DNN accelerator to maximize the information gain for the discrimination of adversarial and benign inputs. A light gradient boosting machine (lightGBM) is constructed by analyzing the prediction probability of unmutated and mutated models and the label change inconsistency between the adversarial and benign samples in the training dataset. With negligibly small hardware overhead, the glitch injection circuit and the trained lightGBM detector can be easily implemented alongside with the deep learning model on a Xilinx ZU9EG chip. The effectiveness of the proposed detector is validated against four state-of-the-art adversarial attacks on two different types and scales of DNN models, VGG16 and ResNet50, for a thousand-class visual object recognition application. The results show a significant increase in true positive rate and a substantial reduction in false positive rate on the Fast Gradient Sign Method

关键词： Hardware artificial intelligence Computational modeling Deep learning Perturbation methods image edge detection Detectors Deep neural network deep learning accelerator edge AI adversarial examples AI security

来源：评论

学校读者我要写书评

暂无评论

AI-Supported Pneumonia Diagnosis: Performance of Deep Learning Models and Synthetic Data Generation

AI-Supported Pneumonia Diagnosis: Performance of Deep Learni...

引用

Signal processing Algorithms, Architectures, Arrangements and applications (SPA)

作者： Baran Atbaş Efe Calşşkan Oğuzhan Erdem Department of Electrical and Electronics Engineering Trakya University Edirne TURKEY

ISBN: (数字)9788362065486

ISBN: (纸本)9798350373806

Pneumonia, a respiratory infection that affects the lungs and leads to serious health complications, is diagnosed by physicians based on symptoms, physical exam findings and imaging tests such as chest X-rays, but these methods can be time-consuming and subjective. In this study, we propose a Convolutional neural Network (CNN) based pneumonia disease detection model utilizing X-ray images for accelerating diagnosis and initiate treatment early to prevent disease progression. Due to the insufficient number of original X-ray samples, we also produced synthetic images with our developed Deep Convolutional Generative Adversarial Network (DC-GAN) model. We comparatively evaluated the performance of our models with pretrained VGG16 and ResNet50 models on synthetic and original image datasets separately and combined. Our results show that all models performed best with the synthetic dataset and also the combined set expanded with synthetic data gave better results in all cases than using the original data alone. The average test accuracy results of all models were obtained as $93 \%$, $89 \%$ and $91 \%$ with synthetic, original and combined datasets, respectively. Thus, it proves that the good quality of the produced synthetic images that can be used to solve the problem of medical image data need, especially in artificial intelligence-based decision support systems. When the models were compared, our CNN model achieved the best performance in all scenarios with the accuracy values of $95 \%, 91 \%$ and $93 \%$ with synthetic, original and combined datasets, respectively.

关键词： Deep learning Pneumonia Accuracy Signal processing algorithms Medical services Data models Convolutional neural networks X-ray imaging Synthetic data Diseases

来源：评论

学校读者我要写书评

暂无评论

Applying the artificial neural networks with Multiwavelet Transform on Phoneme recognition 2

Applying the Artificial Neural Networks with Multiwavelet Tr...

引用

2nd International Conference of Modern applications on Information and Communication Technology, ICMAICT 2020

作者： Alkhafaji, Baydaa Jaffer Salih, May A. Shnain, Shaymaa Abdulhussein Rashid, Omar Adel Rashid, Abdulla Adil Hussein, Moheeb Tariq Computer Science Department College of Education for Pure Science/Ibn Al-Haitham University of Baghdad Iraq Math and Computer Science Department Basic Education College University of Babylon Hilla Iraq

There are several advantages of Phoneme recognition. identification. It is easier to use speech for data entrance spoken communication for data ingress than other tools. It allows writing user-friendly data entrance exploiter-friendly data ingress programs. There are several difficulties in speech voice communication recognition. One of these difficulties is noise. Variability in speech is another problem. Even the speech of same speaker varies. The ability of artificial neural networks to generalize and optimize more quickly than some conventional algorithms algorithmic rule has been observed in different areas of research inquiry such as speech and pattern convention recognition, financial forecasting prognostication, image data compression and noise reduction simplification in signal processing. neural networks take advantage of the redundancy incorporated in their distributed processing structures the proposed system depends on artificial neural networks Network as decision making qualification algorithm to find the best match peer for the tested phonemes. Phoneme. The data used in this project are Arabic phonemes language phoneme stored as 8-bit mono infectious mononucleosis 8000Hz PCM WAVE Sound Auditory sensation file. The results showed that the accuracy of the proposed system is 98% recognizes the phonemes efficiently. © Published under licence by IOP Publishing Ltd.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

Developments in image processing using Deep learning and Reinforcement learning

Developments in Image Processing using Deep learning and Rei...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： Sarla More Durgesh Mishra Department of IT School of Computer Science and Information Technology Dr. B R Ambedkar NIT Jalandhar (Punjab) Symbiosis University of Applied Sciences Indore MP

The continuously surging volume of data, estimated to surpass 180 zettabytes by 2025, presents substantial challenges for both organizations and society as a whole. This influx of data not only brings about increased size but also introduces heightened complexity, presenting new theoretical and computational obstacles. Over the past two decades, the field of data science has experienced a notable surge in popularity due to its versatile applications in managing complex data, ensuring high accuracy, providing customizable flexibility, and demonstrating excellent adaptability. However, the analysis of image datasets introduces additional challenges, particularly when the goal is to enhance image quality, which in turn increases the volume of data for processing. Despite the continued dominance of traditional machine learning (ML) techniques in various research fields and industries, there is a growing interest among the scientific community in exploring innovative artificial intelligence (AI) approaches. The resurgence of neural networks, in particular, has led to significant breakthroughs, especially in the domains of image understanding and processing. This research conducts an extensive examination of the latest progress in designing and optimizing artificial intelligence (AI) solutions specifically tailored to tackle challenges in image processing. Despite the significant accomplishments, the field continues to grapple with various difficulties. The present study thoroughly explores essential and recent improvements, applications, and advancements within the sphere of image processing, offering insights into a domain characterized by continual and swift evolution. Additionally, the paper delineates prospective avenues for future research in this dynamic field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Models for Moving Vehicle Detection in Traffic Surveillance Video for Smart City applications 1

引用

2nd International Conference on Electronic Governance with Emerging Technologies, EGETC 2023

作者： Risha, K. Jude Hemanth, D. Department of ECE Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9783031439407

ISBN: (纸本)9783031439391

In the last few decades, CCTV surveillance has become a piece of unavoidable equipment in public places. The most important application is for traffic monitoring. Recently, accident cases have been rapidly increasing day by day. So, continuous analysis of vehicles is a challenging task. Developing an algorithm to find a specific vehicle or pedestrian is highly beneficial in such cases. Such a procedure can be done by video processing. Video processing and its applications have improved over the last few years. The advancements in this area are helpful in numerous fields. At the same time, the intervention of artificial intelligence also has a relevant role in this area. Machine learning has also become essential and valuable in various complex cases. image classification using artificial intelligence provides a highly accurate result rather than any other classification method. This paper mainly compares different convolutional neural networks on moving objects detected by background subtraction and GMM with the morphological operation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DBAN: Adversarial Network With Multi-Scale Features for Cardiac MRI Segmentation

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2021年第6期25卷 2018-2028页

作者： Yang, Xinyu Zhang, Yuan Lo, Benny Wu, Dongrui Liao, Hongen Zhang, Yuan-Ting Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligen Chongqing 400715 Peoples R China Imperial Coll London Hamlyn Ctr London SW7 2AZ England Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Tsinghua Univ Sch Med Dept Biomed Engn Beijing 100084 Peoples R China City Univ Hong Kong Dept Mech & Biomed Engn Hong Kong Peoples R China

With the development of medical artificial intelligence, automatic magnetic resonance image (MRI) segmentation method is quite desirable. Inspired by the power of deep neural networks, a novel deep adversarial network, dilated block adversarial network (DBAN), is proposed to perform left ventricle, right ventricle, and myocardium segmentation in short-axis cardiac MRI. DBAN contains a segmentor along with a discriminator. In the segmentor, the dilated block (DB) is proposed to capture, and aggregate multi-scale features. The segmentor can produce segmentation probability maps while the discriminator can differentiate the segmentation probability map, and the ground truth at the pixel level. In addition, confidence probability maps generated by the discriminator can guide the segmentor to modify segmentation probability maps. Extensive experiments demonstrate that DBAN has achieved the state-of-the-art performance on the ACDC dataset. Quantitative analyses indicate that cardiac function indices from DBAN are similar to those from clinical experts. Therefore, DBAN can be a potential candidate for short-axis cardiac MRI segmentation in clinical applications.

关键词： image segmentation Magnetic resonance imaging Convolution Training Informatics Kernel Biomedical imaging Cardiac MRI Medical image processing Automatic Segmentation Method Adversarial Network

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：