检索结果-内蒙古大学图书馆

19th International Conference on Software Technologies, ICSOFT 2024

作者： Jara, Nicolás Pempelfort, Hermann viera, Erick Sanchez, Juan Pablo España, Gabriel Borquez-Paredes, Danilo Department of Electronics Engineering Universidad Tecnica Federico Santa Maria Valparaíso Chile Faculty of Engineering and Sciences Universidad Adolfo Ibáñez Viña del Mar Chile

ISBN: (纸本)9789897587061

A novel open-source toolkit for a straightforward implementation of deep reinforcement learning (DRL) techniques to address any resource allocation problem in current and future optical network architectures is presented. The tool follows OpenAI GYMNASIUM guidelines, presenting a versatile framework adaptable to any optical network architecture. Our tool is compatible with the Stable Baseline library, allowing the use of any agent available in the literature or created by the software user. For the training and testing process, we adapted the Flex Net Sim Simulator to be compatible with our toolkit. Using three agents from the Stable Baselines library, we exemplify our framework performance to demonstrate the tool’s overall architecture and assess its functionality. Results demonstrate how easily and consistently our tool can solve optical network resource allocation challenges using just a few lines of code applying Deep Reinforcement Learning techniques and ad-hoc heuristics algorithms. © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of garbage classification and detection system based on YOLOv8 9

Design and implementation of garbage classification and dete...

引用

9th International Symposium on Sensors, Mechatronics, and Automation System, ISSMAS 2023

作者： Wang, Quanfu Wen, Bin Nanfang College Guangzhou 882 Wenquan Avenue Guangzhou China

ISBN: (纸本)9781510672802

Garbage classification can be seen everywhere in today's society, but due to the changes of the times, the awareness that different types of waste should go into different types of bins is not widespread among most people. Even some people don't even know what kinds of garbage there are. Therefore, it is very important to identify garbage. In order to speed up training and recognition, the author improved the YOLOv8 algorithm newly released this year, and at the same time used crawlers to crawl thousands of pictures of different types of garbage on the Internet for training. The author obtained the model with the highest accuracy by increasing the number of epochs and adjusting the batch. © 2024 SPIE.

关键词： Data modeling Education and training Object detection Detection and tracking algorithms Classification systems Design and modelling Data conversion Convolution Image processing algorithms and systems Performance modeling

来源：评论

学校读者我要写书评

暂无评论

Research on traffic sign recognition algorithms for autonomous vehicles in smart city traffic systems 4

Research on traffic sign recognition algorithms for autonomo...

引用

4th International Conference on Computer vision and Pattern Analysis, ICCPA 2024

作者： Wang, Chuanfei School of Government Beijing Normal University Beijing100875 China

ISBN: (纸本)9781510682528

With the continuous advancement of smart city construction, autonomous driving technology is playing an increasingly important role in urban traffic systems. This study aims to explore the development and optimization of traffic sign recognition algorithms for autonomous vehicles in smart city traffic environments. By comprehensively analyzing current traffic sign recognition technologies, this paper proposes a traffic sign recognition system based on the YOLOv5 algorithm and utilizes the open-source COCO dataset for model training and testing. The images were preprocessed and annotated, employing CSPDarknet53 as the backbone network, which effectively extracts image features through multiple convolutional layers and residual blocks. A deep learning model was trained, capable of recognizing and classifying various traffic signs such as stop, speed limit, and turn signs. The research results indicate that the model demonstrates high average precision (AP) on the COCO dataset, effectively identifying traffic signs of different sizes and angles, even in complex backgrounds, with high robustness. Compared to traditional methods, the recognition accuracy has improved by 15%, and it has a significant advantage in real-time processing. © 2024 SPIE.

关键词： Object detection Detection and tracking algorithms Unmanned vehicles Performance modeling Feature extraction Image processing Data modeling Image segmentation Mathematical optimization

来源：评论

学校读者我要写书评

暂无评论

Low-Power B5G Communication Technology Based on Digital Beamforming and DOA Estimation 2

Low-Power B5G Communication Technology Based on Digital Beam...

引用

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

作者： Tayebelasmaa, Haboob Chen, Peng Southeast University School of Information Science and Engineering Nanjing210096 China Southeast University State Key Laboratory of Millimeter Waves Nanjing210096 China

ISBN: (纸本)9798331515669

This study explores advancements in Beyond 5G (B5G) communication systems, focusing on improving signal quality, system efficiency, and energy management. We assess the impact of Digital Beamforming (DBF), Direction of Arrival (DOA) estimation, and Deep Learning (DL) algorithms across three configurations: without advanced technology, with DBF and DOA, and with DBF, DOA, and DL integration. Numerical simulations confirm that incorporating DL significantly enhances signal integrity and energy efficiency, particularly in long-range scenarios. The proposed DL model achieves competitive performance metrics, with MSE, MAE, and RMSE values all below 0.1, indicating its effectiveness in optimizing spectral and energy efficiency. These findings highlight the potential of DL in real-time beamforming and underscore its role in the future development of B5G networks. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

False data injection attack detection in smart grid based on CNN-BiGRU 9

False data injection attack detection in smart grid based on...

引用

9th International Conference on Energy Materials and Electrical Engineering, ICEMEE 2023

作者： Zeng, Yuan Huang, Yue Chen, Yaling Guangxi Normal University Mathematics and Statistics Department of Mathematics and Applied in Mathematics Guilin China

ISBN: (纸本)9781510672765

False Data Injection Attacks (FDIAs) are a common security threat to power systems, where an attacker injects false data into the system to interfere with its normal operation. Most of the current research on false data injection attack detection has been conducted in the physical grid environment, while relatively little research has been conducted on new and advanced sensing and measurement technologies to achieve the efficient and smooth operation of smart grids. In this paper, we first provide a comprehensive understanding of FDIAs and investigate the incidents and impacts of FDIA on power systems worldwide. By searching the literature, the existing detection methods for FDIAs are collated, and it is found that most of the existing detection methods use rules or statistical models, which are vulnerable to deception by attackers. Secondly, CNN is used to reduce the dimensionality and extract the spatial features of the high-dimensional measurement information of the power system in the smart grid, and then combined with BiGRU to fully explore the time series features in the information, thus proposing a CNN-BiGRU based detection method of FDIAs in smart grids, and then detecting the measurement information input model of power system and classifying it. This paper also conducts comparison experiments with three commonly used algorithms, CNN, RNN and MLP, and obtains that the research in this paper has high accuracy and certain feasibility. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： systems modeling Feature extraction Power grids Data modeling Neural networks Data processing Data acquisition Detection and tracking algorithms Statistical analysis

来源：评论

学校读者我要写书评

暂无评论

End-to- end integrated pipeline for underwater optical signal detection using 1D integral imaging capture with a convolutional neural network

引用

OPTICS EXPRESS 2023年第2期31卷 1367-1385页

作者： Huang, Yinuo Krishnan, Gokul O'Connor, Timothy Joshi, Rakesh Javidi, Bahram Univ Connecticut Elect & Comp Engn Dept 371 Fairfield Way Unit 4157 Storrs CT 06269 USA Univ Connecticut Biomed Engn Dept 260 Glenbrook RdUnit 3247 Storrs CT 06269 USA

Underwater optical signal detection performance suffers from occlusion and turbidity in degraded environments. To tackle these challenges, three-dimensional (3D) integral imaging (InIm) with 4D correlation-based and deep-learning-based signal detection approaches have been proposed previously. Integral imaging is a 3D technique that utilizes multiple cameras to capture multiple perspectives of the scene and uses dedicated algorithms to reconstruct 3D images. However, these systems may require high computational requirements, multiple separate preprocessing steps, and the necessity for 3D image reconstruction and depth estimation of the illuminating modulated light source. In this paper, we propose an end-to-end integrated signal detection pipeline that uses the principle of one-dimensional (1D) InIm to capture angular and intensity of ray information but without the computational burden of full 3D reconstruction and depth estimation of the light source. The system is implemented with a 1D camera array instead of 2D camera array and is trained with a convolutional neural network (CNN). The proposed approach addresses many of the aforementioned shortcomings to improve underwater optical signal detection speed and performance. In our experiment, the temporal-encoded signals are transmitted by a light-emitting diode passing through a turbid and partial occluded environment which are captured by a 1D camera array. Captured video frames containing the spatiotemporal information of the optical signals are then fed into the CNN for signal detection without the need for depth estimation and 3D scene reconstruction. Thus, the entire processing steps are integrated and optimized by deep learning. We compare the proposed approach with the previously reported depth estimated 3D InIm with 3D scene reconstruction and deep learning in terms of computational cost at receiver's end and detection performance. Moreover, a comparison with conventional 2D imaging is also included. The ex

关键词： Bit error rate Camera calibration High speed photography optical signals optical wireless communication Three dimensional reconstruction

来源：评论

学校读者我要写书评

暂无评论

Statistical processing of Uncertainty in Artificial Intelligence

Statistical Processing of Uncertainty in Artificial Intellig...

引用

2023 International Conference on algorithms, High Performance Computing, and Artificial Intelligence, AHPCAI 2023

作者： Nan, Jing Ren, Jing Zhang, Yuanyan Li, Deyang Wang, Hao Ji, Shengkai Chen, Yu The sixth Research Institute of China Electronic Information Industry Group Co. LTD Unit 96901 of the People's Liberation Army China

ISBN: (纸本)9781510671881

Dealing with uncertainty is an important issue in artificial intelligence, as real-world data and scenarios often come with uncertainty. The existence of uncertainty requires artificial intelligence systems to have the ability to handle incomplete information, randomness and unknownness. Statistics provides multiple methods to deal with uncertainty. The methods can assist in reasoning and prediction in artificial intelligence systems. Artificial intelligence has the robustness and adaptability. It is crucial to consider how to better handle uncertainty. Because it can enhance the robustness and adaptability of the artificial intelligence system. © 2023 SPIE. All rights reserved.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Nonlinear multimode photonics: nonlinear optics with many degrees of freedom

引用

OPTICA 2022年第7期9卷 824-841页

作者： Wright, Logan G. Renninger, William H. Christodoulides, Demetri N. Wise, Frank W. NTT Res Inc Phys & Informat Labs 940 Stewart Dr Sunnyvale CA 94085 USA Cornell Univ Sch Appl & Engn Phys Ithaca NY 14853 USA Univ Rochester Inst Opt Rochester NY 14627 USA Univ Cent Florida Coll Opt & Photon CREOL Orlando FL 32816 USA

The overall goal of photonics research is to understand and control light in new and richer ways to facilitate new and richer applications. Many major developments to this end have relied on nonlinear optical techniques, such as lasing, mode-locking, and parametric downconversion, to enable applications based on the interactions of coherent light with matter. These processes often involve nonlinear interactions between photonic and material degrees of freedom spanning multiple spatiotemporal scales. While great progress has been made with relatively simple optimizations, such as maximizing single-mode coherence or peak intensity alone, the ultimate achievement of coherent light engineering is complete, multidimensional control of light-light and light-matter interactions through tailored construction of complex optical fields and systems that exploit all of light's degrees of freedom. This capability is now within sight, due to advances in telecommunications, computing, algorithms, and modeling. Control of highly multimode optical fields and processes also facilitates quantitative and qualitative advances in optical imaging, sensing, communication, and information processing since these applications directly depend on our ability to detect, encode, and manipulate information in as many optical degrees of freedom as possible. Today, these applications are increasingly being enhanced or enabled by both multimode engineering and nonlinearity. Here, we provide a brief overview of multimode nonlinear photonics, focusing primarily on spatiotemporal nonlinear wave propagation and, in particular, on promising future directions and routes to applications. We conclude with an overview of emerging processes and methodologies that will enable complex, coherent nonlinear photonic devices with many degrees of freedom. (C) 2022 Optica Publishing Group

关键词： Laser materials processing Nonlinear optical devices optical components optical design optical imaging optical systems

来源：评论

学校读者我要写书评

暂无评论

Analyzing Radar Cross Section signatures at automotive microwave radar 3

Analyzing Radar Cross Section signatures at automotive micro...

引用

3rd International Computing Imaging Conference, CITA 2023

作者： Wang, Zizheng Qi, Feng Wu, Hongming Xidian University Xi’an710126 China Shenyang Institute of Automation Chinese Academy of Sciences China The Key Laboratory of Liaoning Province in Terahertz Imaging and Sensing Shenyang110169 China The Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China The Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang110169 China College of information science anf engineering Northeastern University Liaoning Province Shenyang110819 China

ISBN: (纸本)9781510671409

With the increasing demand for autonomous vehicles, the reliable detection and recognition of objects have become paramount. Millimeter-wave radar systems operating at frequencies such as 94GHz offer several advantages, including high resolution, precise range measurement, and resilience to adverse weather conditions. However, accurately characterizing the RCS of objects at this frequency range is essential to optimize the performance of these radar systems. In this work, we present Radar Cross Section (RCS) measurements of various objects commonly encountered on the road such as the metal balls, the bricks. The acquired findings illuminate the radar signal fluctuations demonstrated by different entities at a frequency of 94GHz. This knowledge serves as a foundation for developing robust algorithms and signal processing techniques that enhance the object detection, classification, and tracking capabilities of radar-based autonomous driving systems. Moreover, our research provides a valuable dataset of RCS measurements for different objects at 94GHz, which can serve as a benchmark for future studies in the field of radar system design and testing. The availability of such a dataset facilitates the development and validation of radar system models, the evaluation of sensor fusion approaches, and the comparison of performance across different radar hardware and signal processing algorithms. The results contribute to the advancement of radar-based autonomous driving systems by providing crucial insights into the scattering characteristics of objects at millimeter-wave frequencies. The findings have practical implications for optimizing the design, testing, and performance of radar systems, ultimately enhancing the safety and efficiency of autonomous vehicles in real-world scenarios. © 2023 SPIE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Research on simulation of human brain neural network and signal processing technology 5

Research on simulation of human brain neural network and sig...

引用

5th International Conference on Signal processing and Computer Science, SPCS 2024

作者： Wang, Haochen Xuteli College Beijing Institute of Technology Beijing China

ISBN: (数字)9781510686731

ISBN: (纸本)9781510686724

With the cross development of computational neuroscience and artificial intelligence, research on human brain neural network simulation and signal processing technology has become a hot topic of common concern in both academia and industry. This study used a multi-level and multi-scale computational model and high-precision algorithm to simulate the dynamic behavior of human brain neural networks, exploring the complex interactions between neurons and their impact on information processing capabilities. Real time dynamic simulation of billions of neurons was achieved on a simulation platform using ultra large-scale integrated circuit chips, simulating signal processing patterns similar to those of the human brain. By using an improved backpropagation algorithm to decode and reconstruct neural signals, the efficiency of the algorithm and the accuracy of signal processing have been improved. On this basis, combined with experimental data obtained from functional magnetic resonance imaging, the similarities and differences between neural network simulation results and actual human brain activity were compared and analyzed, revealing the potential connection between cognitive function and brain network activity patterns. This study not only achieved new breakthroughs in simulation technology and signal processing algorithms, but also provided a new quantitative tool and theoretical support for related neuroscience research, which is of great significance for the development of brain computer interfaces and intelligent information processing systems. In addition, the study also delved into the balance between ensuring model complexity and processing efficiency, as well as the challenges and opportunities brought by interdisciplinary collaboration in the field of neuroscience. Through cross validation and error analysis of simulation experiments, the effectiveness of the model and the accuracy of prediction results were ensured. Based on this, feasible suggestions for opt

关键词： Magnetic resonance imaging

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：