检索结果-内蒙古大学图书馆

Cognitive learning enabled agile optical network

JOURNAL OF optical COMMUNICATIONS AND networkING 2024年第11期16卷 1170-1178页

作者： Cheng, Yijun Chen, Zejun Hu, Zihe Xiang, Meng Yan, Zhijun Qin, Yuwen Fu, Songnian Huazhong Univ Sci & Technol Sch Opt & Elect Informat Wuhan 430074 Peoples R China Guangdong Univ Technol Inst Adv Photon Technol Sch Informat Engn Guangzhou 510006 Peoples R China Guangdong Univ Technol Guangdong Prov Key Lab Informat Photon Technol Guangzhou 510006 Peoples R China Guangdong Univ Technol Key Lab Photon Technol Integrated Sensing & Commun Minist Educ China Guangzhou 510006 Peoples R China

Nonlinear equalization (NLE) is essential for guaranteeing the performance of an optical network (ON). Effective NLE implementation relies on key parameters of the transmission link, including the modulation format (MF) and the launch power. As ONs become more agile, the parameters of fiber optical transmission need to be adaptive and relevant to the routing condition. Therefore, successful NLE implementation relies on the realization of transmission awareness (TA). Although machine learning-enabled optical performance monitoring (OPM) has been extensively investigated in the past few years, current NLE algorithms cannot autonomously perceive transmission parameters. Furthermore, current TA implementation still needs human intervention to guide the NLE. In addition, existing ML-based OPM and NLE cannot be trained autonomously, leading to the incapability of environmental change and mislabeling. Here, we propose cognitive learning (CL) for TA-guided NLE in agile ONs. We perform an experiment involving 32 Gbaud polarization-division-multiplexed (PDM)-quadrature phase shift keying (QPSK)/16-quadrature amplitude modulation (QAM) transmission over 1500 km of standard single-mode fiber (SSMF) with a variable launch power from 0 to 3 dBm. When a deep neural network (DNN) with amplitude histograms (AHs) as inputs and one step per span-learned digital back-propagation (1stps-LDBP) are developed, the CL simultaneously enables both TA and NLE, with the capability of self-learning, mislabeling resistance, and dynamic adaptation. The proof-of-concept experimental results indicate that both the accuracy of TA and the Q-factor of PDM-16QAM can be improved by 34.8% and 0.84 dB, respectively, when the launch power is 3 dBm. Moreover, the accuracy of TA is enhanced by 35.3%, even when the used data has 30% mislabeling. Therefore, the CL framework can be customized to satisfy various NLE implementations, thereby supporting the adaptive transmission of agile ONs.

关键词： Training Nonlinear optics Heuristic algorithms Monitoring optical receivers Signal processing algorithms optical polarization optical modulation optical computing Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Integrating Tesseract OCR with Large Language models for Enhancing Textual Understanding 15

Integrating Tesseract OCR with Large Language Models for Enh...

引用

15th International Conference on Advances in computing, Control, and Telecommunication Technologies, ACT 2024

作者： Sriharsha, A.V. Bhavana, Mekala Tejaswee, Syamala Ahmed, Mynasaheb Bushra Reddy, Peddi Reddi Jaipal Tirupati India Department of Computer Science and Systems Engineering Sree Vidyanikethan Engineering College Tirupati India

ISBN: (纸本)9798331300579

optical Character Recognition (OCR) is a technology that automatically extracts textual information from document images. An LLM, a large language model, is a neural network designed to understand, generate, and respond to human-like text. These models are deep neural networks trained on massive amounts of text data, sometimes encompassing large portions of the entire publicly available text on the internet. LLMs require textual data to be converted into numerical vectors, known as embeddings since they can't process raw text. Embeddings transform discrete data (like words or images) into continuous vector spaces, making them compatible with neural network operations. The combined strengths of Tesseract OCR's image-based text extraction and the deep language understanding of LLMs enhance the accuracy and depth of textual comprehension. The proposed integrated model establishes a novel paradigm in enhancing textual understanding, progress in document analysis, information retrieval, and various NLP applications. © Grenze Scientific Society, 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Universal and High-Fidelity Resolution Extending for Fluorescence Microscopy Using a Single-Training Physics-Informed Sparse neural network

INTELLIGENT COMPUTING

引用

INTELLIGENT computing 2024年 3卷

作者： Ye, Zitong Huang, Yuran Zhang, Jinfeng Chen, Yunbo Ye, Hanchu Ji, Cheng Jin, Luhong Gan, Yanhong Sun, Yile Tao, Wenli Han, Yubing Liu, Xu Chen, Youhua Kuang, Cuifang Liu, Wenjie Zhejiang Univ Coll Opt Sci & Engn State Key Lab Extreme Photon & Instrumentat Hangzhou 310027 Zhejiang Peoples R China Zhejiang Univ Ningbo Res Inst Ningbo 315100 Zhejiang Peoples R China Zhejiang Univ Dept Biomed Engn Key Lab Biomed Engn Minist Educ Hangzhou 310027 Zhejiang Peoples R China Zhejiang Lab Hangzhou 311121 Zhejiang Peoples R China

As a supplement to optical super-resolution microscopy techniques, computational super-resolution methods have demonstrated remarkable results in alleviating the spatiotemporal imaging trade-off. However, they commonly suffer from low structural fidelity and universality. Therefore, we herein propose a deep-physics-informed sparsity framework designed holistically to synergize the strengths of physical imaging models (image blurring processes), prior knowledge (continuity and sparsity constraints), a back-end optimization algorithm (image deblurring), and deep learning (an unsupervised neural network). Owing to the utilization of a multipronged learning strategy, the trained network can be applied to a variety of imaging modalities and samples to enhance the physical resolution by a factor of at least 1.67 without requiring additional training or parameter tuning. Given the advantages of high accessibility and universality, the proposed deep-physics-informed sparsity method will considerably enhance existing optical and computational imaging techniques and have a wide range of applications in biomedical research.

关键词： Fluorescence microscopy

来源：评论

学校读者我要写书评

暂无评论

Industry-Oriented Detection Method of PCBA Defects Using Semantic Segmentation models

引用

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1438-1446页

作者： Yang Li Xiao Wang Zhifan He Ze Wang Ke Cheng Sanchuan Ding Yijing Fan Xiaotao Li Yawen Niu Shanpeng Xiao Zhenqi Hao Bin Gao Huaqiang Wu Department of Internet of Things Technology and Application China Mobile Research InstituteBeijing 100053China Beijing Advanced Innovation Center for Integrated Circuits the School of Integrated CircuitTsinghua UniversityBeijing 100084China SigmaStar Technology Limited Xiamen 361199China IEEE

Automated optical inspection(AOI)is a significant process in printed circuit board assembly(PCBA)production lines which aims to detect tiny defects in *** AOI equipment has several deficiencies including low throughput,large computation cost,high latency,and poor flexibility,which limits the efficiency of online PCBA *** this paper,a novel PCBA defect detection method based on a lightweight deep convolution neural network is *** this method,the semantic segmentation model is combined with a rule-based defect recognition algorithm to build up a defect detection *** improve the performance of the model,extensive real PCBA images are collected from production lines as *** optimization methods have been applied in the model according to production demand and enable integration in lightweight computing *** results show that the production line using our method realizes a throughput more than three times higher than traditional *** method can be integrated into a lightweight inference system and pro-mote the flexibility of *** proposed method builds up a general paradigm and excellent example for model design and optimization oriented towards industrial requirements.

关键词： Automated optical inspection(AOI) deep learning defect detection printed circuit board assembly(PCBA) semantic segmentation.

来源：评论

学校读者我要写书评

暂无评论

Programming nonlinear propagation for efficient optical learning machines

引用

Advanced Photonics 2024年第1期6卷 73-83页

作者： Ilker Oguz Jih-Liang Hsieh Niyazi Ulas Dinc Ugur Tegin Mustafa Yildirim Carlo Gigli Christophe Moser Demetri Psaltis École Polytechnique Fédérale de Lausanne Institute of Electrical and Micro EngineeringEcublensSwitzerland Koc University Department of Electrical and Electronics EngineeringIstanbulTurkey

The ever-increasing demand for training and inferring with larger machine-learning models requires more efficient hardware solutions due to limitations such as power dissipation and *** is a promising contender for providing lower power computation,since light propagation through a nonabsorbing medium is a lossless ***,to carry out useful and efficient computations with light,generating and controlling nonlinearity optically is a necessity that is still *** fibers(MMFs)have been shown that they can provide nonlinear effects with microwatts of average power while maintaining parallelism and low *** propose an optical neural network architecture that performs nonlinear optical computation by controlling the propagation of ultrashort pulses in MMF by wavefront *** a surrogate model,optimal sets of parameters are found to program this optical computer for different tasks with minimal utilization of an electronic *** show a remarkable decrease of 97%in the number of model parameters,which leads to an overall 99%digital operation reduction compared to an equivalently performing digital neural *** further demonstrate that a fully optical implementation can also be performed with competitive accuracies.

关键词： neural networks nonlinear optics fiber optics surrogate optimization neuromorphic computing wavefront shaping

来源：评论

学校读者我要写书评

暂无评论

Late sensor fusion approach with a designed multi-segmentation network

引用

neural computing and Applications 2024年第27期36卷 17125-17143页

作者： Çaldıran, Bekir Eren Acarman, Tankut Acartec Intelligent Vehicle Technologies Sanayi Mah. Teknopark Bulvarı 1/4C Istanbul Turkey Computer Engineering Department Galatasaray University Çırağan Cad. Ortaköy Istanbul Turkey

Sensors have different perceptive abilities against environment. Sensor fusion plays a crucial role at achieving better perception by accumulating the information acquired at different times. But, the decision of the observation may conflict with each other due to usage of different algorithms, thresholds on processing algorithms, and different perceptive character of sensors. This study presents the late fusion method applied to outputs provided by deep learning models fed by camera and lidar sensor’s measurement data. For camera sensor, a deep learning model as a multi-task network is proposed to multi-classify cars, motorcycles, bicycles, buses, trucks, and pedestrians under the category of dynamic traffic objects. In addition, color classified traffic lights and traffic signs with a capability of segmenting drivable area and detecting lane lines are classified under the category of static traffic objects. The proposed multi-network is trained and tested with the BDD100K dataset and benchmarked with publicly available multi-networks. The presented method is the second fastest multi-network reaching at 52 FPS runtime, ranked second based on the drivable area segmentation and lane line detection performance. For segmentation of dynamic objects, the network performance is increased by 22.45%, and considering mIoU overall performance increase is 3.96%. For a lidar sensor, a different modality is presented to detect objects. Two sensors’ data are fused by proposed fusion algorithm, and results are tested and evaluated with the KITTI dataset. The proposed fusion methodology outperforms the stand-alone lidar methods about 3.58% and 3.63% on BEV and 3D detection MAP, respectively. Overall, benchmarking with two distinct fusion approaches illustrates the effectiveness of the proposed method. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： optical radar

来源：评论

学校读者我要写书评

暂无评论

Shape completion with azimuthal rotations using spherical gidding-based invariant and equivariant network

引用

neural computing and Applications 2024年第21期36卷 13269-13292页

作者： Wu, Hang Miao, Yubin Fu, Ruochong School of Mechanical Engineering Shanghai Jiao Tong University 800 Dong Chuan Road Shanghai200240 China

Point cloud completion aims to restore full shapes of objects from their partial views obtained by 3D optical scanners. In order to make point cloud completion become more robust to azimuthal rotations and more adaptive to real-world scenarios, we propose a novel network for simultaneous rotation invariant and equivariant completion with no need of data augmentation, while other existing approaches require separately trained models for different completion types. Our method includes several main steps: First, Density Compensation Mapping (DCM) as well as Aggregative Gaussian Gridding (AGG) modules are introduced to transfer partial point clouds to spherical signals and avoid unbalanced sampling. Second, an encoder based on group correlation is designed to extract rotation invariant global features and equivariant azimuthal features from spherical signals. Third, parallel groups of decoders are proposed to realize rotation invariant completion based on feature fusion. Finally, a feature remapping module as well as Pose Voting Alignment (PVA) algorithm are proposed to unify feature space and realize rotation equivariant completion. Based on these modules, we find that the application of group correlation can be extended to the domain of shape completion;equivariant and invariant completions can be unified in one pipeline, and our inherent rotation equivariant and invariant framework can achieve competitive performances when comparing with existing representative methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Rotation

来源：评论

学校读者我要写书评

暂无评论

optical Diffusion models for Image Generation 38

Optical Diffusion Models for Image Generation

引用

38th Conference on neural Information Processing Systems, NeurIPS 2024

作者： Oguz, Ilker Dinc, Niyazi Ulas Yildirim, Mustafa Ke, Junjie Yoo, Innfarn Wang, Qifei Yang, Feng Moser, Christophe Psaltis, Demetri École Polytechnique Fédérale de Lausanne Switzerland Google Research United States Google United States

Diffusion models generate new samples by progressively decreasing the noise from the initially provided random distribution. This inference procedure generally utilizes a trained neural network numerous times to obtain the final output, creating significant latency and energy consumption on digital electronic hardware such as GPUs. In this study, we demonstrate that the propagation of a light beam through a semi-transparent medium can be programmed to implement a denoising diffusion model on image samples. This framework projects noisy image patterns through passive diffractive optical layers, which collectively only transmit the predicted noise term in the image. The optical transparent layers, which are trained with an online training approach, backpropagating the error to the analytical model of the system, are passive and kept the same across different steps of denoising. Hence this method enables high-speed image generation with minimal power consumption, benefiting from the bandwidth and energy efficiency of optical information processing. © 2024 neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AE-D2NN: Autoencoder in Diffractive neural network Form

AE-D2NN: Autoencoder in Diffractive Neural Network Form

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Feng, Peijie Zhang, Zongkun Chong, Mingzhe Tan, Yunhua Peking University School of Electronics Beijing China

ISBN: (纸本)9798350375909

The development and potency of deep neural networks have revolutionized numerous fields, demonstrating unprecedented capabilities in complex tasks. Despite this, the advancement of deep neural networks is increasingly constrained by the computational limits of hardware. In response, many researchers are shifting their focus to optical neural networks for higher computation efficiency and speed, seeking to harness the ultra-fast processing capabilities of light and its potential for parallel computing. Among them, the diffractive deep neural network stands out, uniquely utilizing the principles of light diffraction and interference for data processing. However, its application has predominantly focused on functioning as a multi-layer linear perceptron for classification tasks utilizing light waves, leaving its potential in other deep learning tasks and models largely untapped. Autoencoder, as a fundamental part of generative models in deep learning, excel in unsupervised learning for efficient data encoding, showcasing their potential in data compression and reconstruction. Therefore, in this article, we explored the combination of autoencoder and diffractive deep neural network, and proposed the AE-D2NN model. We adopted a knowledge distillation strategy, using a teacher AE model to train the student AE-D2NN model on the MNIST and Fashion MNIST datasets. The trained model is capable of performing image compression and reconstruction, which can also be interpreted as beam focusing and holographic imaging functions. The AE-D2NN model is a twin of the autoencoder model under the framework of diffractive neural networks, representing an initial exploration of the integration of diffractive neural network with generative models. This work may also inspire new approaches to electromagnetic wave manipulation. © 2024 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Enhancing network traffic classification with CNN and multi-layer BiGRU-attention

Enhancing network traffic classification with CNN and multi-...

引用

2024 International Conference on Algorithms, High Performance computing, and Artificial Intelligence, AHPCAI 2024

作者： Dong, Haifeng An, Yi Xi'an Shiyou University Computer Science Department Xi'an China

ISBN: (纸本)9781510685840

The rise in network security awareness has led to an exponential increase in the use of encrypted traffic. While encryption protects user privacy, it also presents significant challenges for network security detection. This paper introduces a novel encrypted traffic classification method combining Convolutional neural networks (CNN) and multi-layer Bidirectional Gated Recurrent Unit networks (BiGRU). The CNN extracts detailed and global information from traffic data frames, while the temporal attention mechanism in BiGRU captures the temporal relationships between frames. Experimental results indicate that the proposed CNN + BiGRU model achieves over 97.5% accuracy on test sets, outperforming existing deep learning models in both accuracy and F1 score. © 2024 SPIE.

关键词： Convolutional neural networks

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：