检索结果-内蒙古大学图书馆

Self-Powered Photonic Synapses with Rapid optical Erasing Ability for Neuromorphic Visual Perception

RESEARCH 2024年第11期7卷 0526页

作者： Li, Mingchao Li, Chen Ye, Kang Xu, Yunzhe Song, Weichen Liu, Cihui Xing, Fangjian Cao, Guiyuan Wei, Shibiao Chen, Zhihui Di, Yunsong Gan, Zhixing Nanjing Normal Univ Ctr Future Optoelect Funct Mat Sch Comp & Elect Informat Sch Artificial Intelligence Nanjing 210023 Peoples R China Southeast Univ Sch Elect Sci & Engn Joint Int Res Lab Informat Display & Visualizat Nanjing 210096 Peoples R China Shenzhen Univ Nanophoton Res Ctr Shenzhen Key Lab Microscale Opt Informat Technol Shenzhen 518060 Peoples R China Taiyuan Univ Technol Coll Elect Informat & Opt Engn Key Lab Adv Transducers & Intelligent Control Syst Minist Educ & Shanxi Prov Taiyuan 030024 Peoples R China

Photonic synapses combining photosensitivity and synaptic function can efficiently perceive and memorize visual information, making them crucial for the development of artificial vision systems. However, the development of high-performance photonic synapses with low power consumption and rapid optical erasing ability remains challenging. Here, we propose a photon-modulated charging/discharging mechanism for self-powered photonic synapses. The current hysteresis enables the devices based on CsPbBr3/solvent/carbon nitride multilayer architecture to emulate synaptic behaviors, such as excitatory postsynaptic currents, paired-pulse facilitation, and long/short-term memory. Intriguingly, the unique radiation direction-dependent photocurrent endows the photonic synapses with the capability of optical writing and rapid optical erasing. Moreover, the photonic synapses exhibit exceptional performance in contrast enhancement and noise reduction owing to the notable synaptic plasticity. In simulations based on artificial neural network (ANN) algorithms, the pre-processing by our photonic synapses improves the recognition rate of handwritten digit from 11.4% (200 training epochs) to 85% (similar to 60 training epochs). Furthermore, due to the excellent feature extraction and memory capability, an array based on the photonic synapses can imitate facial recognition of human retina without the assistance of ANN.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

An Investigation for Cursive Context-Specific Printed Script Recognition Techniques 20

An Investigation for Cursive Context-Specific Printed Script...

引用

20th International Multi-conference on systems, Signals and devices, SSD 2023

作者： Rafique, Humera Javid, Tariq Hamdard University Graduate School of Engineering Sciences & Information Technology Dept. of Electrical Engineering Karachi Pakistan

ISBN: (纸本)9798350332568

Selecting suitable techniques and datasets for a machine learning problem is a great challenge. This research investigates the available machine learning architectures, datasets, and software tools, for cursive context-specific printed text. Despite the existence of millions of speakers around the globe and rich literary history of more than thousands of years, it is hard to find computational linguistic works related to the Punjabi Shahmukhi script, a member of Perso-Arabic context-specific script - a low-resource language family. An investigation of related work through collected statistics inspired by the popularity and success of artificial neural networks and associated techniques have presented. The historical development of the script follows it in a literary sense and the importance and motivation in the development of optical character recognition systems, algorithms, and techniques. The paper discussed the available datasets and the need for a custom dataset. Based on recent research trends in machine learning frameworks, the work presents the most popular deep learning techniques, convolutional neural networks, and recursive neural networks for cursive context-specific scripts. This paper incorporates actual knowledge to promote research in machine learning and natural language processing disciplines and the selection of algorithms, architectures, and resources. © 2023 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Feed-forward Neural Network based Algorithm for Intelligent Positioning of Direction Finding Crossings 16

Feed-forward Neural Network based Algorithm for Intelligent ...

引用

16th International conference on Signal processing systems, ICSPS 2024

作者： Li, Pangzhe Hu, Dexiu Zhao, Chuang Information Engineering University Signal Processing Laboratory China

ISBN: (纸本)9781510689251

This paper proposes a feed-forward neural network(FNN) based algorithm for intelligent positioning of angle of arrival(AOA) to address the problems of complex computation, slow positioning speed and low positioning accuracy of traditional cross-location direction finding methods. The algorithm obtains the position of a known target from the available data, calculates its angle of arrival at the observatory, combines them into data pairs, and inputs them into a constructed neural network to obtain the corresponding model. The network can then locate unknown targets. It is verified that the algorithm has reliable localization accuracy and higher robustness than conventional algorithms. The proposed method also shows that the training of the neural network on the basis of a large amount of data can greatly reduce the operation time and achieve real-time target localization. © 2025 SPIE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Recognition and Analysis of Glass Subsurface Defects by Integrating Machine Vision and Image processing Technology 5

Recognition and Analysis of Glass Subsurface Defects by Inte...

引用

5th International conference on Computers, information processing and Advanced Education, CIPAE 2024

作者： Lin, Chen Ling, Xiong Luo, Guangming Wuhan University of Science and Technology Wuhan China Changli Glass Honghu Co. Ltd Wuhan China

ISBN: (纸本)9798331527662

Machine vision and computer image processing technologies are widely used in the metallurgical industry, especially in recognizing and analyzing defects in glass. High surfaces of planer surface and quality in the glass and metal manufacturing sector primarily require automated and performance visual detection, and inspection systems and algorithms are constantly improving. This article, therefore, seeks to comprehensively recognize and analyze glass subsurface defects through the integration of image processing technologies and machine vision. According to the algorithm's properties and the image features typified in the process, the defects of identified glass components are primarily classified based on determining the cause and the optical features of characteristics exhibited. Given the nature of varied and detected effects determined mainly by the classifiers, an improved accuracy level was notable, and a reduction of the computational complexity was evident following the use of machine vision and image processing technologies. © 2024 IEEE.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

A target-oriented method for dividing the effective region of laser interference

A target-oriented method for dividing the effective region o...

引用

2023 International conference on Computer Graphics, Artificial Intelligence, and Data processing, ICCAID 2023

作者： Hu, Jing Lv, SiQi Ren, LiJun Ren, Jie Zhong, WeiWei Ouyang, Yan He, Jia National Key Laboratory of Science and Technology on Multi-Spectral Information Processing Wuhan China Huazhong Univ. of Science and Technology Wuhan China Air Force Early Warning Academy Wuhan China Chinese People s Liberation Army Troops 95841 China

ISBN: (纸本)9781510677685

Laser interference can interfere with target detection systems to achieve the goal of protecting the target. For example, it can obscure the target and change information such as brightness and contrast in the surrounding region of the interference zone. Therefore, it is necessary to analyze the impact of laser interference on target detection algorithms and evaluate the anti-interference performance of the algorithm. This paper analyzes the impact of laser interference on two target detection algorithms, Faster-RCNN and YOLO-V3, from two perspectives: target occlusion rate and target similarity. Then, a target-oriented method for dividing the effective region of laser interference (TODERLI) is proposed. The effectiveness of the algorithm is verified through experiments. © 2024 SPIE.

关键词： Signal detection

来源：评论

学校读者我要写书评

暂无评论

Iraqi Legal GPT 21

Iraqi Legal GPT

引用

21st International Multi-conference on systems, Signals and devices, SSD 2024

作者： Mustafa, Mustafa Samir Abdulfatah, Mustafa Basim Abdulkareem, Husain Alaa Ashir, Abubakar M. Tishk International University Dept. of Computer Engineering Erbil Iraq

ISBN: (纸本)9798350374131

This paper proposes and develops a small language model artificial intelligence (AI) system or chatbots capable of providing competent legal information to users within the Iraqi legal jurisprudence. One of the major contributions of the papers is addressing critical challenges related to the current Large Language Model (LLM) like ChatGPT of their enormous size and lack of localized knowledge of internal processes and lifestyles. The proposed model provides low latency time with limited economic resources and the availability of efficient legal professionals for understanding the legal and rights requirements of individuals within the Iraqi region which can be run on a local computer without an internet connection. The research leverages the open source h2ogpt as a backbone language model and was trained with aggregated and curated legal documents from the Iraqi legal system. This approach allows users to input questions, and through the aid of Embedding algorithms and Vector Store algorithms, the data is stored and converted into a machine-readable format for subsequent comprehension and processing by the computer. The findings indicate a promising foundation for the project, featuring a user-friendly interface (UI) and an updateable back-end to accommodate future enhancements. The system achieved a noteworthy 1-minute response time with an accuracy rate of 80%. Notably, the development objectives aimed to establish a locally deployable system that is easily accessible and modifiable to address evolving challenges in the current computational era of information dissemination. © 2024 IEEE.

关键词： information dissemination

来源：评论

学校读者我要写书评

暂无评论

A method for integrating operation and maintenance data of power information systems based on artificial intelligence technology 3

A method for integrating operation and maintenance data of p...

引用

3rd International conference on Machine Vision, Automatic Identification, and Detection, MVAID 2024

作者： Liu, Peng Wang, Dazhong Zhang, Yuxi Ren, Yusong Ren, Jiandong China Electric Power Research Institute Beijing100192 China

ISBN: (纸本)9781510681880

The conventional method of integrating operation and maintenance data for power information systems is often time-consuming and suffers from limited data coverage. Consequently, this paper proposes a new method for integrating such data using artificial intelligence technologies. Initially, we set a unified standard and classification guideline for the integration process of operation and maintenance data in power information systems, identifying data types based on their interrelationships. We then organize and process the operation and maintenance data, removing any inconsistencies and redundancies to minimize the impact of irrelevant data and enhance integration efficiency. Furthermore, we implement a standardized coding system to verify and encode the organized data, ensuring it corresponds accurately with the actual datasets. By leveraging deep learning algorithms on offline data, this approach not only minimizes system resource utilization but also increases the extent of effective data coverage. Experimental outcomes indicate that this integration approach not only accelerates the process but also achieves greater data inclusivity compared to traditional methods, thus offering significant practical value. © 2024 SPIE.

关键词： Data integration information fusion Artificial intelligence Deep learning Classification systems information operations Data processing Evolutionary algorithms Power grids Standards development

来源：评论

学校读者我要写书评

暂无评论

Application of machine learning to optical sensing and imaging

Application of machine learning to optical sensing and imagi...

引用

作者： Zhou, Chen The Pennsylvania State University

学位级别：博士

Recent years have witnessed significant advancements in optical sensing and imaging techniques. To effectively interpret complex data acquired through these techniques and accurately extract information from detectors, machine learning has emerged as a promising solution. Machine learning enables automatic learning of the relationship between raw data and desired outputs, without the need for complete and explicit physics-based models. This data-driven approach presents opportunities for making inferences on material properties, solving inverse problems in the area of optical sensing and imaging. However, the current majority of machine learning methods applied in optical systems primarily serve as post-processing tools to enhance automation and improve the signal-to-noise ratio after data acquisition with standard optical systems. This approach often utilizes precision optics that can be bulky and expensive, along with typical machine learning algorithms that may not fully exploit the underlying physics. The separation of optics and algorithms in design and optimization limits the potential for integration and performance improvement. Consequently, an area of fruitful research lies in deeply integrating machine learning into the design of efficient optical hardware systems, optimizing and streamlining their performance. This dissertation aims to demonstrate how machine learning can contribute to the design of cost-effective and portable optical devices by leveraging minimal optical components in conjunction with powerful learning models. The proposed approach adopts a holistic perspective in designing optical sensing systems. By relieving the burden on optics, simpler and more affordable optical components can be utilized. Moreover, optical domain knowledge can be effectively employed to custom design efficient machine learning algorithms. The dissertation is divided into three main parts, exploring different spaces: spectral, polarization, spatial-temporal, and mo

关键词：

来源：评论

学校读者我要写书评

暂无评论

The application of deep learning algorithms in power system load forecasting 6

The application of deep learning algorithms in power system ...

引用

6th International conference on Wireless Communications and Smart Grid, ICWCSG 2024

作者： Wang, Shilin Cui, Wei Yang, Yang Meng, Xiangliang State Grid Information & Telecommunication Group Co. Ltd. No. 10 Xuanwumen Outer Street Xicheng District 95555-0345 Beijing100029 China

ISBN: (纸本)9781510682962

This article explores the application of deep learning (DL) algorithms in power system load forecasting. With the continuous advancement of the construction of new power systems, traditional load forecasting models designed based on time series analysis are no longer in line with the actual needs of the current power system. To improve the accuracy of load forecasting, this paper attempts to transform time series data into images for analysis, and then use deep learning methods widely used in the field of image processing for power load forecasting. Convolutional neural network (CNN), as a commonly used image processing algorithm, has been applied in time series data processing. However, data is still processed as a sequence matrix, and the advantages of CNN algorithm in processing image matrices have not been fully utilized. Therefore, this article proposes a CNN algorithm based on sequence to image conversion (STI-CNN). Firstly, the load sequence is converted into a load image. Then, a dual branch deep network model is used to accurately cluster the input data. Finally, the STI-CNN model is used for load prediction. Matlab simulation experiments show that the proposed STI-CNN model has excellent performance in different prediction metrics and has higher prediction accuracy. © 2024 SPIE.

关键词： Data modeling Data conversion Image processing systems modeling Convolutional neural networks Evolutionary algorithms Statistical modeling Education and training Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Analysis and design of pervasive computing intelligent surveillance system integrating optical sensors and behavioral analysis for industrial internet 2

Analysis and design of pervasive computing intelligent surve...

引用

2nd International conference on Big Data, Computational Intelligence, and Applications, BDCIA 2024

作者： Yao, Di Luo, Chenyao Cheng, Weiwei Song, Huaju Beijing100083 China Portland Institute Nanjing University of Posts and Telecommunications Nanjing210003 China School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China School of Environmental Science NanJing XiaoZhuang University Nanjing210017 China

ISBN: (纸本)9781510689053

Nowadays, the surveillance system performing as an indispensable part for modern industrial Internet has attracted much attention. With the continuous progress of microprocessor technology, sensor technology, particularly optical sensors, and network technology, it has entered the era of pervasive computing, which leads to the breakthrough of the surveillance system and the emergence of intelligent environment safety monitoring systems. However, the intelligence of surveillance systems is still a significant challenge. In this paper, we propose a surveillance system for detecting and recognizing people based on their behaviors from images or video sequences using computer vision techniques and optical sensor data, which is implemented by designing the system architecture through a hierarchical structure, applying key techniques such as background subtraction, modeling, and optical sensing analysis, and experimentally processing and testing a variety of behavioral samples. The alarm information generated by the proposed surveillance system aided by pervasive computing system can be delivered to remote terminals. Experimental results reveal that the environmental monitoring and alarm information can be processed in real time with devices, such as cell phones, telephones, and PCs. Therefore, the proposed approach can improve the performance of the surveillance systems. © 2025 SPIE.

关键词： Alarm systems

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：