检索结果-内蒙古大学图书馆

2024 systems of Signal Synchronization, Generating and processing in Telecommunications, SYNCHROINFO 2024

作者： Makarevich, A.L. Sokovnich, S.M. Kulachek, V.V. Zinchenko, S.V. Zaharova, Yu.V. Pridnestrovian State University Named after T.G. Shevchenko Tiraspol Moldova

ISBN: (纸本)9798350373448

The status and prospects for the development of complex photonic integrated circuits (PICs) used as switches that control flow generation in optical packet switching networks are discussed. The trends discussed apply to other classes of circuits and network devices, in particular modules of more complex systems. Our work provides an analysis of the literature on the state of development of the electronic component base for complex functional (SF) blocks intended for use in optical systems currently used for high-speed data transmission. The main components that control the formation of high-speed digital information streams in modern packet networks are switching systems, which can be implemented on CMOS transistors with design standards of 65 and 90 nm. Analysis of the state of existing developments in the field of creating an electronic component base and quantum devices intended for operation in optical information transmission systems will make it possible to create the necessary SF blocks for constructing and implementing them in the form of specialized LSIs (ASICs) manufactured using CMOS technology. © 2024 IEEE.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Enhancing Video Stability with Object-Centric Stabilization 7

Enhancing Video Stability with Object-Centric Stabilization

引用

7th IEEE International conference on Multimedia information processing and Retrieval (MIPR)

作者： Tiwari, Aparna Tiwari, Hitika Venkatesh, K. S. Sharma, Anuj Kumar AKTU Dept Mech Engn Ctr Adv Studies Lucknow India Indian Inst Technol Kanpur Dept Elect Engn Kanpur India

ISBN: (纸本)9798350351439;9798350351422

Video stabilization is essential for producing high-quality videos by eliminating unwanted camera motion, resulting in smooth, steady footage that enhances visual coherence. However, existing methods often pose several challenges such as the difficulties in accurately tracking specific objects, and high computational demands. These limitations hinder the ability to achieve optimal stabilization results and limit the practical applicability of video stabilization techniques in real-world scenarios. To address these challenges, we introduce a novel end-to-end method for object-centric video stabilization in the presence of multiple independent objects. Our approach introduces two algorithms: 1) Object-Centric Video Stabilization (OCViS), which facilitates effective detection and tracking of specific objects within each frame, followed by stabilization with respect to the object of interest, and 2) optical Flow-based Transformation Accumulation and Smoothing (OFTrAnS) to remove inherent shakiness and maintain consistent stabilization, even with multiple independent objects. Most importantly, our algorithms achieve these results without relying on deep neural networks or ground-truth data, providing a more efficient and accessible solution for enhancing video quality on mobile devices and handheld cameras. Our experiments demonstrate that the proposed approach significantly outperforms a strong baseline by a large margin emphasizing the efficacy of our method.

关键词： Object-Centric Video Stabilization Shakiness Removal Multiple Independent Objects Object Tracking Video processing

来源：评论

学校读者我要写书评

暂无评论

Frequency-domain diffusion adaptation with quantized communication 16

Frequency-domain diffusion adaptation with quantized communi...

引用

16th International conference on Signal processing systems, ICSPS 2024

作者： Peng, Yishu Zhang, Sheng Zhou, Zhengchun Han, Hongyu School of Information Science and Technology Southwest Jiaotong University Chengdu China School of Computer Science Sichuan Normal University Chengdu China

ISBN: (纸本)9781510689251

In energy- and bandwidth-limited networks, frequency-domain diffusion algorithms based on periodic communication are attractive candidates because of their low computational complexity and communication overhead. Nevertheless, these algorithms assume that intermediate estimates are transmitted exactly in each communication round, which is not realistic in practice. To this end, this paper proposes novel frequency-domain diffusion algorithms with quantized communication. Using the randomized quantizer to compress the shared information, we first develop the quantized frequency-domain diffusion least mean square (Q-FDLMS) algorithm. To mitigate the performance degradation incurred by quantization errors, the improved Q-FDLMS (IQ-FDLMS) algorithm is also designed. This enhanced version modifies the combination step and incorporates the moving-average scheme. Additionally, the mean-square stability conditions and steady-state error bound of the IQ-FDLMS algorithm are derived. Experiment results indicate that our proposed algorithms are superior to other competing algorithms. © 2025 SPIE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

A Rule-Based Expert System for Automated Document Editing 1

引用

20th International conference on Computing and information Technology (IC2IT2)

作者： Varma, Sandeep Shivam, Shivam Roy, Soumya Deep Ray, Biswarup ZS Associates Pune Pune Maharashtra India

ISBN: (数字)9783031585616

ISBN: (纸本)9783031585609;9783031585616

This research paper introduces a Rule-Based Expert System designed for the automated editing of documents in PDF and PPT formats. The system employs a set of predefined rules, extracted from guideline documents using a Large Language Model (LLM), to execute tasks such as redaction of sensitive text/logo detection and annotation of text elements that deviate from prescribed font size guidelines. Following the detection and annotation process, the system further enhances documents by resizing the detected text elements based on the predefined rules. To achieve these editing tasks, the system integrates advanced image processing techniques, leveraging fine-tuned optical Character Recognition (OCR) for accurate text extraction from document images. Furthermore, Natural Language processing (NLP) algorithms are utilized to analyze and interpret textual content. The combination of image processing, OCR, NLP, and rule extraction using LLM ensures a comprehensive approach to document editing, enhancing efficiency and accuracy. The proposed system addresses the need for automated and rule-driven document editing, contributing to advancements in information security and document standardization.

关键词： Rule-based Expert System Image processing optical Character Recognition Document Sanitization Natural Language processing

来源：评论

学校读者我要写书评

暂无评论

Research on the design of multi-source and multi-granularity educational information system based on deep learning

Research on the design of multi-source and multi-granularity...

引用

2024 International conference on algorithms, High Performance Computing, and Artificial Intelligence, AHPCAI 2024

作者： Wang, Li Shandong Institute of Commerce and Technology Shandong Jinan China

ISBN: (纸本)9781510685840

In the surge of the digital era, the role of educational information systems is increasingly prominent, serving as essential tools to enhance teaching quality and management efficiency. This paper addresses the limitations of traditional educational information systems in handling complex, multi-source data, particularly the challenges in data integration and information correlation, proposing an innovative design approach. Through deep learning technologies, notably a multi-source information correlation method based on convolutional neural networks (CNNs), this study aims to develop a system capable of effectively processing multi-source and multi-granular data within the educational domain. The system design encompasses the entire process from data collection and information correlation to system construction, striving to provide the educational sector with an efficient, intelligent information processing platform. Experimental results demonstrate significant advantages of the system in terms of educational information accuracy and processing speed, promising innovative changes for educational management and pedagogical research. © 2024 SPIE.

关键词： Data modeling Data acquisition Data processing Machine learning Neurons Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Spatial and Temporal Evolution of Wetlands in the Yellow River Delta Based on optical Flow Algorithm

引用

JOURNAL OF information processing systems 2025年第1期21卷 102-113页

作者： Liu, Chao Mu, Ruolan Wang, Chuanlong Yuan, Xiuhe Miao, Sheng Qingdao Univ Technol Sch Environm & Municipal Engn Qingdao Peoples R China Qingdao Univ Technol Sch Informat & Control Engn Qingdao Peoples R China

The Yellow River Delta (YRD) wetlands are the largest coastal wetlands in China, and it serves to control soil erosion, nourish the climate and protect biodiversity. At present, due to climate change and human activities, the wetlands of the YRD are facing ecological and environmental problems such as species invasion, vegetation degradation, and biodiversity reduction. In order to study the evolution of wetland landscape types more intuitively, this paper proposed a semantic segmentation network based on the encoder and decoder structure of ResNet-18. Then, the wetland landscapes in the YRD were classified into five types by combining the Landsat series of remote sensing images. In addition, this paper used the optical flow algorithm to visualize the identification results, which can represent the evolution pattern of wetland landscape types in different years. The results of this paper have an important significance for the subsequent development planning and protection in the YRD.

关键词： Identification of Wetland Landscape Types optical Flow Algorithm ResNet Spatial and Temporal Evolution

来源：评论

学校读者我要写书评

暂无评论

Object detection algorithm based on residual deformable convolution pyramid 4

Object detection algorithm based on residual deformable conv...

引用

4th International conference on Computer Vision and Pattern Analysis, ICCPA 2024

作者： Huang, Bin Wang, Sanqian Li, Linjie Fu, Xiang Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang*** China School of Software Nanchang Hangkong University Nanchang*** China

ISBN: (纸本)9781510682528

Considering the challenges associated with robots in optoelectronic imaging applications, typically require real-time and accurate recognition and localization of targets, especially in complex environments. Due to the potential challenges of noise, blurring, or dense targets in the images obtained by optoelectronic imaging systems, traditional object detection algorithms may face issues such as semantic information loss and difficulty in detecting small targets. By introducing residual deformable convolution structures, feature representation can be enhanced in optoelectronic imaging systems, and the shape of the convolution kernel can be dynamically adjusted to adapt to the non rigid deformation of the target, thereby better capturing the detailed features of small targets. Experimental results exhibit that RAFPN enhances the mAP of object detection algorithms RetinaNet, Faster R-CNN, and GFL by 1.2%, 0.9%, and 1.1% respectively on the MS COCO dataset, effectively enhancing the performance of object detection algorithms in optoelectronic imaging. © 2024 SPIE.

关键词： Optoelectronic devices

来源：评论

学校读者我要写书评

暂无评论

Smart Machine Vision for Universal Spatial-Mode Reconstruction

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systems 2025年 PP卷 PP页

作者： Huerta-Morales, Jose D. You, Chenglong Magana-Loaiza, Omar S. Dong, Shi-Hai Leon-Montiel, Roberto de J. Quiroz-Juarez, Mario A. Univ Nacl Autonoma Mexico Inst Ciencias Nucl Mexico City 04510 Mexico Louisiana State Univ Dept Phys & Astron Quantum Photon Lab Baton Rouge LA 70803 USA Huzhou Univ Res Ctr Quantum Phys Huzhou 310003 Peoples R China UPALM Inst Politecn Nacl Lab Cienciasde Informac Cuant CIC Mexico City 07700 Mexico Univ Nacl Autonoma Mexico Ctr Fis Aplicada & Tecnol Avanzada Queretaro 76230 Mexico

Structured light beams, in particular, those carrying orbital angular momentum (OAM), have gained a lot of attention due to their potential for enlarging the transmission capabilities of communication systems. However, the use of OAM-carrying light in communications faces two major problems, namely distortions introduced during propagation in disordered media, such as the atmosphere or optical fibers, and the large divergence that high-order OAM modes experience. While the use of nonorthogonal modes may offer a way to circumvent the divergence of high-order OAM fields, artificial intelligence (AI) algorithms have shown promise for solving the mode-distortion issue. Unfortunately, current AI-based algorithms make use of large-amount data-handling protocols that generally lead to large processing time and high power consumption. Here, we show that a low-power, low-cost image sensor can act as an artificial neural network that simultaneously detects and reconstructs distorted OAM-carrying beams. We demonstrate the capabilities of our device by reconstructing (with a 95% efficiency) individual Vortex, Laguerre-Gaussian (LG), and Bessel modes, as well as hybrid (nonorthogonal) coherent superpositions of such modes. Our work provides a potentially useful basis for the development of low-power-consumption, light-based communication devices.

关键词： Accuracy Laser beams Image reconstruction optical distortion optical fiber networks optical beams Convolutional neural networks optical fibers Deep learning Crosstalk Artificial intelligence (AI) neural networks smart machine-vision device spatial-mode reconstruction

来源：评论

学校读者我要写书评

暂无评论

Application of Artificial Intelligence algorithms in Wearable Device Signal processing systems

Application of Artificial Intelligence Algorithms in Wearabl...

引用

2023 International conference on Data Science and Network Security, ICDSNS 2023

作者： Qi, Xiaojing Xiong, Ying School of Communication Engineering and Internet of Things Chongqing Telecommunication Polytechnic College Chongqing China

ISBN: (纸本)9798350301595

Wearable devices refer to electronic devices that can be worn on the body, aiming to provide users with more information and internet services. This study proposed a wearable device signal processing system based on artificial intelligence algorithms. By investigating the basic principles and technical routes of wearable device signal processing systems, suitable artificial intelligence algorithms were selected and improved. A prototype of wearable device signal processing system based on artificial intelligence algorithms was developed, tested and validated. The experimental results showed that the accuracy of the artificial intelligence algorithm in predicting health status reached 95%, with a time consumption of 2.3 seconds. The wearable device signal processing system based on artificial intelligence algorithms could not only effectively process the raw signals collected by wearable devices, but also achieve automated analysis and prediction, which had good application prospects. © 2023 IEEE.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

Scheduling algorithm for fidelity of quantum gate circuits 3

Scheduling algorithm for fidelity of quantum gate circuits

引用

3rd International conference on Electronic information Engineering and Data processing, EIEDP 2024

作者： Liu, Xudong Xu, Jinchen Lian, Hang Information Engineering University Zhengzhou450001 China

ISBN: (纸本)9781510680531

As quantum computing technology matures, the availability and performance of quantum devices are steadily improving. However, in the NISQ (Noisy Intermediate-Scale Quantum) era, the quantum bit error rate caused by quantum noise remains a significant constraint on computational accuracy and reliability. In quantum operating systems, quantum task scheduling is a core technology crucial for fully leveraging the performance potential of quantum processors. Currently, most multi-processor scheduling algorithms focus on task load balancing and do not directly consider the characteristics of quantum circuits and the differentiated error rates of quantum computing backends. In quantum computing, the impact of noise errors in single-qubit gates, two-qubit gates, and measurement gates on the fidelity of quantum gate circuits is crucial. Therefore, intelligently matching quantum tasks with the characteristics of backend processors to optimize computational accuracy is an urgent problem to be addressed. This paper proposes a new quantum task scheduling algorithm, which matches tasks with backends based on the weight of single-qubit gates, two-qubit gates, and measurement gates in quantum circuits, as well as the error rate characteristics of each quantum computing backend. Experimental results show that the proposed scheduling algorithm for improving the fidelity of quantum gate circuits outperforms static load balancing scheduling algorithms, resulting in a 4.39% increase in the fidelity of quantum tasks. © 2024 SPIE.

关键词： Scheduling algorithms

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：