检索结果-内蒙古大学图书馆

14th International Conference on computing Communication and networking Technologies, ICCCNT 2023

作者： Paayas, P. Sridevi, S. Kanimozhi, T. Valliammai, M. Mohanraj, J. Vinodh Kumar, N. Bakiya, A. Prasanna Kumar, R. Rithani, M. Amrita Vishwa Vidyapeetham School of Computing Computer Science and Engineering Chennai India Vellore Institute of Technology Scope Chennai India VelTech Rangarajan Dr.Sagunthala R & D Inst.of Sci.and Tech. Ece India

ISBN: (纸本)9798350335095

This paper emphasizes an effort to effectively identify and categorize structural defects in Photonic Band Gap (PBG) Crystals, which are vital in material characterization and structure analysis. These PBG materials have unique optical characteristics that are quite advantageous in the design of photonic devices and solar cells however, their imperfections may exert an adverse impact on these characteristics. The challenging task of recognizing and classifying these PBG crystal defects with high accuracy and efficiency can be handled by using machine learning techniques. We propose the use of a Hybrid Classical Quantum neural network (HCQNN) model that leverages the traits of quantum computing to efficiently classify the types of structural defects in the PBG crystals. The quantum part of the HCQNN model is contrived with a quantum node encompassing three qubits, Angle Embedding layer and Basic entangling layer with 500 numbers of shots. The quantum node interface is integrated with generalized classical dense layers, and the entire HCQNN model is trained with a classical optimizer. The experimental results demonstrate that the proposed HCQNN architecture outperforms existing machine learning and Artificial neural network models in terms of classification accuracy, precision, and other critical model parameters. © 2023 IEEE.

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

The power of AI, IoT, and advanced quantum based optical systems in smart cities

引用

optical AND QUANTUM ELECTRONICS 2024年第3期56卷 450-450页

作者： Rajkumar, N. Viji, C. Latha, Pandala Madhavi Vennila, V. Baby Shanmugam, Sathish Kumar Pillai, Nataraj Boothalingam Alliance Univ Alliance Coll Engn & Design Dept Comp Sci & Engn Bangalore Karnataka India VR Siddhartha Engn Coll Dept Informat Technol Kanuru Vijayawada India SSM Coll Engn Kumarapalayam 638183 Namakkal India M Kumarasamy Coll Engn Dept Elect & Elect Engn Karur India Sri Ramakrishna Engn Coll Dept Elect & Commun Engn Coimbatore Tamil Nadu India

This paper explores the transformative fusion of Quantum computing, Artificial Intelligence (AI), the Internet of Things (IoT), and advanced optical systems within smart city development. A significant innovation within this study is the concept of "optical IoT," wherein IoT relies on advanced optical technologies, including high-resolution cameras, LiDAR scanners, meters, sensors, and wearables, strategically distributed throughout urban environments for real-time image data acquisition. Traditional smart city models may rely on conventional data acquisition methods that are not real-time or high-resolution, leading to delayed and less accurate urban management decisions. Existing models might use disparate systems for monitoring and management, which can result in inefficient resource allocation and coordination, especially in critical situations like emergency response. In this research Advanced Smart City Architecture (ASCA) this integration empowers the system to excel in tasks such as semantic segmentation, enabling precise identification and categorization of urban elements. Quantum optical systems are employed in quantum-enhanced sensors, such as quantum-enhanced interferometers and atomic clocks. These sensors offer improved precision for measurements like distance, time, and acceleration. The ASCA approach equips city planners, administrators, and emergency responders with real-time urban monitoring and management capabilities. This dynamic system yields numerous advantages, including optimized resource allocation, enhanced traffic management, improved environmental quality, and swift emergency response capabilities. This research underscores the immense potential of ASCA in reshaping urban development and sustainability within smart cities. By harmonizing AI, IoT, and advanced optical systems, this paradigm shift enables smart cities to evolve into more efficient and resilient urban environments. These cities become finely attuned to the ever-evolving nee

关键词： Smart cities Urban development Advanced quantum optical systems IoT Convolutional neural network LSTM Real-time monitoring

来源：评论

学校读者我要写书评

暂无评论

Advancements in Deep Learning-Based optical Flow Estimation: A Comprehensive Review of models and Techniques 6

Advancements in Deep Learning-Based Optical Flow Estimation:...

引用

6th International Conference on Intelligent computing in Data Sciences, ICDS 2024

作者： Adil, Omar Mahraz, Mohammed Adnane Riffi, Jamal Tairi, Hamid Sidi Mohammed Ben Abdellah University FSDM FES Morocco

ISBN: (纸本)9798350351200

optical flow estimation is a fundamental task in computer vision as it plays a pivotal role in numerous applications, including but not limited to motion analysis, video compression, and object tracking. Traditional methods for optical flow estimation often face challenges in handling complex motion patterns and variations in scene structure. In recent years, deep learning has emerged as a powerful paradigm for addressing these challenges, enabling end to end learning of complex motion representations directly from image data. This review article provides a comprehensive overview of recent advancements in deep learning-based optical flow estimation over the past six years. We present an in-depth analysis of 8 state-of-The-Art models, including FlowNet, FlowNet 2.0, SpyNet, PWC-Net, and RAFT, discussing their architectures, strengths, weaknesses, and performance on benchmark datasets. Additionally, we conduct a comparative analysis of these models based on criteria such as accuracy, computational efficiency, robustness, and generalization. Finally, we discuss future research directions and challenges in deep learning-based optical flow estimation, highlighting opportunities for further advancements in the field. This review serves as a valuable resource for researchers and practitioners interested in understanding the current landscape of deep learning techniques for optical flow estimation and charting the course for future research endeavors. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A structured pruning method based on MobileNetV3

A structured pruning method based on MobileNetV3

引用

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

作者： Pan, Haixia Wang, Shiheng Ye, Huolong Lin, Sinan School of Software Beihang University China Jomoo China

ISBN: (纸本)9781510685840

In recent years, deep neural networks have made significant advancements, surpassing traditional models in computer vision. However, the vast number of parameters in deep models poses challenges such as increased network size, sluggish computation, high computational costs, and extensive storage requirements, thus hindering deployment on resource-constrained platforms like mobile devices. This paper focuses on compressing convolutional neural networks to address these challenges. This paper proposes a structured pruning method that integrates MobileNet features to prune the MobileNetV3-Large model, resulting in a more compact and efficient model. The approach involves sparse regularization training to obtain a sparser network model, which is followed up by structured pruning. This pruning is performed by leveraging the product of the sparsity values of convolutional layers and the scaling factors of batch normalization layers to identify and remove redundant filters. Experiments were conducted on the CIFAR-10 dataset. The experimental results demonstrate that the proposed compression method effectively reduces model parameters, decreases model size, minimizes runtime memory usage, and diminishes computational operations, while maintaining comparable performance levels despite the compression. Specifically, for MobileNetV3-Large, the model's parameter count is reduced by 40%, and computational operations are reduced by 35%, all while maintaining the same level of accuracy. © 2024 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Improved model for detecting randomly oriented objects on remote sensing images 5

Improved model for detecting randomly oriented objects on re...

引用

5th Edge computing Workshop, doors 2025

作者： Pilkevych, Ihor A. Romanchuk, Mykola P. Naumchak, Olena M. Fedorchuk, Dmytro L. Naumchak, Leonid M. Korolyov Zhytomyr Military Institute 22 Myru Ave. Zhytomyr10004 Ukraine

Object detection in optical remote sensing images is an important task. In recent years, methods based on convolutional neural networks have shown progress. However, due to object variations such as scale, aspect ratio, and random orientation, detection is difficult to further improve. Most convolutional neural networks use rectangular bounding boxes for object detection parallel to the image coordinate axes, which is effective. However, for military objects in satellite images, which may have a large aspect ratio and be randomly oriented, rectangular bounding boxes may not always provide sufficient target localization. In this paper, methods based on the rotation of rectangular frames or other polygonal boundaries are considered, including the following. Rotation Region Proposal network (RRPN) and Rotation Region CNN (R2CNN). One-stage models such as SSD, YOLO, and RetinaNet have demonstrated high speed and accuracy. The new YOLOv11 model, which is a further development of the one-stage model approaches, demonstrates an increase in the accuracy and speed of object detection and recognition. The purpose of the study is the analysis of modern neural network models and their improvement to enhance the accuracy of detecting and recognizing small densely located, randomly oriented objects on satellite images. The paper proposes a model with a five-parameter regression that includes the parameter of the rotation angle of the bounding box. The results of the study show that this model improves the accuracy of object detection in complex scenarios by providing accurate determination of their orientation and scale. © 2025 Copyright for this paper by its authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An improved analysis of Light Propagation in optical Fibers using deep learning 15

An improved analysis of Light Propagation in Optical Fibers ...

引用

15th International Conference on computing Communication and networking Technologies, ICCCNT 2024

作者： Vijayakumari, P. Jayakumar, T. Jayamani, K. Gnanasekar, A.K. Dinesh, M. Sairam Engineering College Department of Ece Chennai India Kcg College of Technology Department of Mechatronics Engineering Chennai India Rajalakshmi Institute of technology Department of Ece Chennai India P.T.Lee.Chengalvaraya Naicker College of Engineering and Technology Department of Cse Kancheepuram India Saveetha University Saveetha School of Engineering Department of Vlsi Microelectronics Chennai India

ISBN: (纸本)9798350370249

One of the most fascinating fields in optical communications is Light Propagation in optical Fibers with wealthy applications such as high-speed data transmission, data storage, and medical imaging. Conventional methods to analyze light propagation in optical fibers employ intricate mathematical models and simulations typically entailing long computational time. Deep learning has become a state-of-the-art machine learning strategy in recent years, and people have seen its success across several domains. This article focuses on a more specific analysis intended to improve the study of light propagation on optical fibers by applying deep learning techniques. This method benefits from deep neural networks to model the complex relations between input parameters and output variables, thus making quicker and more accurate predictions. We also implemented a data augmentation process to enhance the training of the neural network. Extensive simulations and comparisons with the conventional methods show our proposed approach's effectiveness and efficiency in analyzing light propagation in optical fibers, indicating its promising potential for further research on this subject. © 2024 IEEE.

关键词： Augmentation Comparisons Deep Learning Potential Simulations

来源：评论

学校读者我要写书评

暂无评论

Gesture recognition of radar micro doppler signatures using separable convolutional neural networks

引用

Materials Today: Proceedings 2023年 80卷 1961-1964页

作者： Helen Victoria, A. Maragatham, G. Department of School of Computing SRM Institute of Science and Technology Kattankulathur Chennai600045 India

Gesture Recognition which is an inevitable part of human computer interaction is an ever evolving active research area. This has been in use under varied applications like smart home systems, sign language recognition, augment reality and in device controls. The acquisition of hand gestures are usually through optical sensors, in this work a radar based hand gesture data set is used for classifying the gestures. Micro doppler signatures were used as the input to the model. Radar dataset has fewer data samples compared to optical based data sets. The proposed work uses separable convolutional neural networks model which does depth wise convolution followed by point wise convolution to reduce overfitting effect of the training data. The proposed model was built in such a way that the model is capable of classifying any unseen data without exactly mimicking the training samples. The proposed model has achieved 94.56% as the testing accuracy which is certainly better than the previous work on this Dop Net data set. Moreover the model has also minimized the computational hours of the model using separable convolutions. © 2021

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

2024 4th International Conference on Intelligent Communications and computing, ICICC 2024

2024 4th International Conference on Intelligent Communicati...

引用

4th International Conference on Intelligent Communications and computing, ICICC 2024

ISBN: (纸本)9798331530365

The proceedings contain 48 papers. The topics discussed include: LCAF: a novel side-channel analysis method based on self-attention mechanism;a method for estimating the total retrieved ground ozone based on deep neural network;evaluating the efficacy of pre-trained ImageNet weights for constellation diagram classification using deep learning models;design simulation and verification of a key negotiation scheme based on physical layer noise error parameters in optical fiber transmission systems;research on the application of reconfigurable intelligent surface technology in radar;fuzzy multi keyword searchable encryption scheme based on counting bloom filter;and enhanced 3D style transfer of neural radiance fields via generalized gaussian distribution transformation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Role of all-optical neural networks

引用

Physical Review Applied 2024年第1期21卷 014028-014028页

作者： M. Matuszewski A. Prystupiuk A. Opala The Institute of Physics Polish Academy of Sciences Aleja Lotników 32/46 Warsaw PL-02-668 Poland Center for Theoretical Physics Polish Academy of Sciences Aleja Lotników 32/46 Warsaw PL-02-668 Poland Institute of Experimental Physics Faculty of Physics University of Warsaw ul. Pasteura 5 Warsaw PL-02-093 Poland

In light of recent achievements in optical computing and machine learning, we consider the conditions under which all-optical computing may surpass electronic and optoelectronic computing in terms of energy efficiency and scalability. When considering the performance of a system as a whole, the cost of memory access and data acquisition is likely to be one of the main efficiency bottlenecks not only for electronic, but also for optoelectronic and all-optical devices. However, we predict that all-optical devices will be at an advantage in the case of inference in large neural network models, and the advantage will be particularly large in the case of generative models. We also consider the limitations of all-optical neural networks, including footprint, strength of nonlinearity, optical signal degradation, limited precision of computations, and quantum noise.

关键词： Energy-efficient infrastructure Machine learning Neuromorphic computing optical quantum information processing Photonics Quantum fluctuations & noise Artificial neural networks optical computing

来源：评论

学校读者我要写书评

暂无评论

Research on coherent optical communication performance monitoring and damage compensation technology based on machine learning

Research on coherent optical communication performance monit...

引用

2024 International Conference on Signal Processing and Communication Security, ICSPCS 2024

作者： Liu, Hao He, Qiuting Key&Core Technology Innovation Institute of the Greater Bay Area Guangzhou510535 China

ISBN: (纸本)9781510681699

As optical fiber communication technology develops towards high speed, large capacity and long distance, the impact of optical fiber nonlinearity and other damages in optical fiber communication systems is becoming more and more serious. In order to ensure the reliability and stability of the system, optical performance monitoring (OPM) technology is of vital importance. It's important. At present, a single optical signal-to-noise ratio (OSNR) monitoring technology is difficult to meet the requirements of system operation and maintenance. Joint monitoring of OSNR, nonlinearity and modulation format is an important development direction of OPM. This paper studies multi-parameter joint monitoring technology of OSNR, nonlinear noise power and modulation format based on different deep learning models. Asynchronous complex histogram (ACH) is designed as the input feature data of the neural network, and the MT-CNN joint monitoring scheme based on AAH is designed. The monitoring results show that the joint monitoring scheme reduces the total number of learnable parameters and saves computing resources and memory overhead. For QPSK, 16QAM, and 32QAM signals, high-precision modulation format identification can be achieved. The root mean square error of nonlinear noise power and OSNR monitoring values reaches 0.21 dB and 0.22 dB respectively. It can also realize changing transmission distance and emission The robustness of power and laser linewidth is superior in performance and computational efficiency;a low-complexity optical fiber nonlinear damage compensation scheme based on a simple recurrent neural network is studied. This compensation scheme significantly reduces the number of triple products required for the equalization process, which can reflect the nonlinear damage characteristics of the optical fiber, by taking advantage of the time memory of the recurrent neural network. © 2024 SPIE.

关键词： optical fibers

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：