检索结果-内蒙古大学图书馆

Deep Learning algorithm research and Performance Optimization of Financial Treasury Big Data Monitoring Platform

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第6期15卷 322-331页

作者： Wang, Yanbing Ding, Ding Huishang Vocat Coll Dept Elect Informat Hefei 231201 Peoples R China AnHui Audit Coll Hefei 230601 Peoples R China

With the rapid development of information technology and the advent of the digital age, the management of fiscal treasury is facing unprecedented challenges and opportunities. In order to improve the efficiency and effectiveness of deep learning algorithms in the financial and treasury big data monitoring platform, this paper further studies the performance optimization methods of the model. This paper deeply studies deep learning algorithm research and performance optimization of financial Treasury big data monitoring platforms. This paper reviews the basic concepts, methods, and applications of deep learning and their application in the financial database big data monitoring platform. In the financial Treasury big data monitoring platform, deep learning algorithms are widely used in image recognition, natural language processing, recommendation systems and other fields. This article first conducts in-depth theoretical research on deep learning algorithms, including various neural network structures (such as convolutional neural network CNN, recurrent neural network RNN, etc.), optimization algorithms (such as gradient descent method and its variants), regularization techniques, etc. In addition, we also studied the practical applications of deep learning in fields such as image processing, natural language processing, and recommendation systems. In order to verify the effectiveness of deep learning algorithms in the financial and treasury big data monitoring platform, we designed corresponding experiments. These experiments include using deep learning algorithms for image recognition of financial documents, natural language processing, and building recommendation systems. We collected real fiscal treasury data as the experimental dataset and preprocessed and annotated the data.

关键词： Deep learning financial database big data monitoring algorithm research performance optimization

来源：评论

学校读者我要写书评

暂无评论

algorithm research of intelligent filtering elimination treatment by ultrasonic ranging signal

引用

JOURNAL OF DISCRETE MATHEMATICAL SCIENCES & CRYPTOGRAPHY 2017年第6-7期20卷 1423-1427页

作者： Wang, Zhibing Dongguan Polytech Dept Elect Engn Dongguan 523808 Peoples R China

Currently, a threshold is set in the ultrasonic ranging for filtering. This kind of method is not suitable for long-distance ultrasonic measurement. This paper designs an algorithm for ultrasonic ranging signal filtering based on two-step correlation method. First, the range of the ultrasonic wave is corrected by the cross correlation function between the envelope of the transmitted signal and the square envelope of the echo signal. Then, the transmission function of the filter of ultrasonic ranging space is studied to short the process time of the algorithm. Finally, the the projection function is designed to complete the filter process. The experimental results show that the algorithm has great ability to filter interference, and the anti-jamming performance is obviously enhanced.

关键词： Ultrasonic ranging Signal Intelligent filtering algorithm research

来源：评论

学校读者我要写书评

暂无评论

research on Personalized Recommendation algorithm of Educational Resources Based on Deep Neural Network

Research on Personalized Recommendation Algorithm of Educati...

引用

2024 International Conference on Electronics and Devices, Computational Science, ICEDCS 2024

作者： Ma, Chuanjin Ding, Xiangyu Liu, Siyi Shandong University of Technology Business School Zibo City China

ISBN: (纸本)9798331527624

Personalized learning is a trend in the development of higher education. We use artificial intelligence technology to realize recommendation of educational resources which becomes issue in higher education. By studying the algorithm and content and combining with deep learning technology, this paper establishes model of educational resources, and puts forward related algorithms of resource filtering from three aspects: resource filtering, recommendation and display respectively. At the same time, an online learning platform is combined with Python language to train model through data sets. The algorithm is compared with traditional algorithms such as SVM, ER and DT. The average absolute error and mean square error and effectiveness of the algorithm proposed in this paper, and further improve the efficiency of educational resource recommendation. It provides a reference of educational resources. © 2024 IEEE.

关键词： algorithm research Deep neural network Educational resources Personalized recommendation

来源：评论

学校读者我要写书评

暂无评论

research on Realistic Effect Generation algorithm of Rendering Images Based on GAN 14

Research on Realistic Effect Generation Algorithm of Renderi...

引用

14th International Conference on Graphics and Image Processing (ICGIP)

作者： Gan, Runmin Su, Hu Southwest Jiaotong Univ Sch Elect Engn Chengdu Peoples R China

ISBN: (纸本)9781510666313;9781510666320

Saving algorithmic overhead for realistic effect generation is always a hot topic in graphics research. The algorithm in this paper applies the method of the Generative Adversarial Network (GAN) to the study of realistic computer graphics, proposing a new solution to reduce the algorithm overhead. We adopt conditional GAN and add an additional module before the generator to provide the lighting information of the current scene. This extra module represents the illuminating direction with grayscale gradient maps of different angles helping the network get lighting information through image input. In addition, we optimize the loss function by adding the L1 loss and the feature perception loss to improve the generative effect of our network. In the feature perception loss, we use a pre-trained VGG network to calculate the detail feature gap between images, to help the model generate images with better light and shadow effects. Our algorithm can add realistic effects to the existing coarse-rendered image according to the lighting conditions and obtain the corresponding fine-rendered image in single light scenes. The extensive experimental results show that our algorithm has a good post-processing effect on realistic rendering, and the time overhead of the algorithm is independent of the complexity of the scene. From the robustness test, we can know that our network also has a good generalization ability.

关键词： GAN realistic computer graphics rendering post-processing algorithm research

来源：评论

学校读者我要写书评

暂无评论

research on multi-sensor information fusion and intelligent optimization algorithm and related topics of mobile robots

引用

EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING 2021年第1期2021卷 1-17页

作者： Guo, Yuan Fang, Xiaoyan Dong, Zhenbiao Mi, Honglin Shanghai Inst Technol Sch Mech Engn Shanghai 201418 Peoples R China Shanghai Inst Technol Sch Foreign Languages Shanghai 201418 Peoples R China

research on mobile robots began in the late 1960s. Mobile robots are a typical autonomous intelligent system and a hot spot in the high-tech field. They are the intersection of multiple technical disciplines such as computer artificial intelligence, robotics, control theory and electronic technology. The product not only has potentially very attractive application value and commercial value, but the research on it is also a challenge to intelligent technology. The development of mobile robots provides excellent research for various intelligent technologies and solutions. This dissertation aims to study the research of multi-sensor information fusion and intelligent optimization methods and the methods of applying them to mobile robot related technologies, and in-depth study of the construction of mobile robot maps from the perspective of multi-sensor information fusion. And, in order to achieve this function, combined with autonomous exploration and other related theories and algorithms, combined with the Robot Operating System (ROS). This paper proposes the area equalization method, equalization method, fuzzy neural network and other methods to promote the realization of related technologies. At the same time, this paper conducts simulation research based on the SLAM comprehensive experiment of the JNPF-4WD square mobile robot. On this basis, the high precision and high reliability of robot positioning are further realized. The experimental results in this paper show that the maximum error of the X-axis and Y-axis, FastSLAM algorithm is smaller than EKF algorithm, and the improved FASTSALM algorithm error is further reduced compared with the original FastSLAM algorithm, the value is less than 0.1.

关键词： Multi-sensor Information fusion algorithm research Intelligent optimization Mobile robot Route plan

来源：评论

学校读者我要写书评

暂无评论

research on the dehazing effect of orthogonal polarization method based on atmospheric scattering model and considering extinction ratio parameter

引用

INTERNATIONAL JOURNAL OF REMOTE SENSING 2024年第5期45卷 1556-1573页

作者： Shi, Dongdong Huang, Fuyu Jia, Leilei Niu, Yuandong Chen, Shuangyou Jiao, Liting Huang, Yanhua Liu, Limin Army Engn Univ PLA Shijiazhuang Campus Shijiazhuang 050000 Peoples R China Army Engn Univ PLA Dept Gen Educ Nanjing Peoples R China

The hazy weather is currently one of the most common atmospheric environments. It is an urgent problem to realize clear imaging in hazy environment. Orthogonal polarization dehazing is one of the classical dehazing techniques attracting a widespread attention from research workers. However, while using this method, the extinction ratio (ER) parameter of the polarizer was neglected leading to poor dehazing. Therefore, we have introduced the ER of polarizers into the orthogonal polarization dehazing technique in this paper. In the process of sky region division, this study proposes to use HSV, RGB and Lab colour channels to create a comprehensive mask to select the sky region. And the morphological corrosion operation is utilized to increase the region connectivity for better sky region division. Based on subjective visualization, it can be found that the dehazing effect is significantly enhanced with the introduction of ER. The dehazing effect was evaluated based on four parameters of contrast (C0), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM) and information entropy (En). It is further demonstrated the necessity of introducing ER. The experimental results show that the ER can make the dehazing effect of the orthogonal polarization dehazing technique improved, which is valuable for the engineering application of image processing in hazy environment. The experimental results proved to be encouraging. The main highlights of this work are the following three points:The NDC parameter of the polarizer is a crucial factor that many researchers tend to overlook when utilizing polarizers for detection in the polarization dehazing process. This study aims to address this oversight by incorporating polarizers for detection and introducing the NDC parameter to rectify images at varying polarization angles. Consequently, the polarization dehazing operation yields superior results compared to those achieved without NDC polarization dehazing techno

关键词： Polarization-based dehazing extinction ratio algorithm research image processing

来源：评论

学校读者我要写书评

暂无评论

Acquiring supply chain agility through information technology capability: the role of demand forecasting in retail industry

引用

KYBERNETES 2023年第10期52卷 4712-4730页

作者： Bai, Bingfeng Shanghai Univ Sch Management Shanghai Peoples R China

Purpose Despite the importance of demand forecasting in retail industry, its influence on supply chain agility has not been sufficiently examined. From a total information technology (IT) capability perspective, the purpose of this paper is to examine the antecedent of supply chain agility through retail demand forecasting. Design/methodology/approach Combining the literature reviews, the quantitative method of algorithm analysis was targeted at, and the firm data were processed on MATLAB. Findings This paper summarizes IT dimensions of demand forecasting in retail industry and distinguishes the relationship of supply chain agility and demand forecasting from an IT capability view. Practical implications Managers can derive a better understanding and measurement of operating activities that appropriately balance among supply chain agility, IT capability and demand forecast practice. Demand forecasting should be integrated into the firm operations to determine the agility level of supply chain in marketplace. Originality/value This paper constructs new theoretical grounds for research into the relationship of demand forecasting-supply chain agility and provides an empirical assessment of the essential components for the means to prioritize IT-supply chain.

关键词： Supply chain agility Demand forecasting Information technology capability Retail industry algorithm research

来源：评论

学校读者我要写书评

暂无评论

A network security algorithm using SVC and sliding window

引用

WIRELESS NETWORKS 2023年第1期29卷 345-351页

作者： Zhao, Xuemin Zhengzhou Univ Aeronaut Sch Intelligent Enineering Zhengzhou 450015 Henan Peoples R China

With the rapid development and popularization of the Internet, the dependency of human life on the Internet is increasing by degrees. The demand for video transmission is also rising with the emergence of portable and handheld devices such as mobile phones, tablets, laptops, etc. The scalability of Scalable Video Coding (SVC) determines that it can meet the needs of the newly emerged devices or terminals. Despite this advancement, security is still one of the major challenges. Based on the research of network security, this paper deeply discusses the encryption technology, and puts forward a new point multiplication algorithm using SVC and sliding window, which makes the algorithm more flexible, improves the efficiency of the algorithm to a certain extent, greatly reduces the expected calculation and storage of the algorithm, and makes the algorithm to adapt the memory limited environment such as smart card. Critical analysis of the proposed DES algorithm is carried out and different fragile keys are recommended which is not safe for secure encryption. This study also present the complete overview of the SVC technology and its multi-layered stream representation in the form of temporal, spatial, and SNR resolution. In addition, an encryption method based on the DES algorithm is also proposed.

关键词： Scalable video coding (SVC) Network security algorithm research sliding window

来源：评论

学校读者我要写书评

暂无评论

Image recognition algorithm based on hybrid deep learning

引用

INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT 2023年 1-11页

作者： Xiangdong, Tang Qingdao Univ Coll Comp Sci & Technol Qingdao 266071 Peoples R China

As we embrace the information age, our lives have experienced revolutionary transformations. With the continuous advancement of computer technology, data sharing and information exchange have become increasingly robust. Consequently, the widespread adoption of hybrid deep learning algorithms has been prioritized. The emergence of deep learning is intricately linked to the progress of artificial intelligence, with deep learning serving as a tangible manifestation of AI. Deep learning algorithms are an important part of the field of robotics research and development. In image recognition, deep learning algorithms are playing an irreplaceable role. Based on the technological breakthrough of convolutional neural network, deep learning is unique in image recognition. In addition, aspects such as speech recognition, body function monitoring, and sports data analysis all have deep learning, and they are advancing all the way with unstoppable development momentum. Of course, with the current development of computer technology, image data also shines on its basis. Not only has it achieved a substantial surpass in quantity, but its types and styles are coming out in a variety of colors. On the basis of this series of developments, we are faced with a problem: traditional recognition algorithms cannot meet our next development requirements. Therefore, a new type of algorithm to deal with this problem has emerged: the research of image recognition algorithms based on hybrid deep learning. In the research of this article, we will focus on comparing its various algorithms to find out their advantages and disadvantages. So as to promote the further development of image recognition.

关键词： Deep learning Image recognition algorithm research Neural network

来源：评论

学校读者我要写书评

暂无评论

Exploration on Facial Image Recognition and Processing algorithms under Hadoop

Exploration on Facial Image Recognition and Processing Algor...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Gu, Meifang Tang, Hailin Li, Lili Guangdong Baiyun University Institutional Research Center Guangdong Guangzhou China Guangdong Baiyun University Faculty of Intelligent Manufacturing Engineering Guangdong Guangzhou China Guangdong Baiyun University Faculty of Megadata and Computing Guangdong Guangzhou China

ISBN: (纸本)9798350315455

Face recognition is an important technology in the field of digital image processing, which has a crucial impact on subsequent work. This article introduced an example of facial recognition based on the combination of Hadoop algorithm and facial feature extraction. The experimental results were validated in the MATLAB environment and trained using neural networks to improve system performance and adaptability. The test results indicated that the processing speed was between 0.84 and 0.97;the highest resource utilization rate was 0.06, and the lowest was 0.02;the throughput range of facial data was between 13598 and 15479, and the throughput range of user data was between 5037 and 5879. This indicated that the system had fast recognition speed and high-precision image output, and exhibited good fault tolerance and robustness compared to other methods. Exploring facial image recognition and processing algorithms in the Hadoop environment can utilize Hadoop's distributed computing capabilities to accelerate the processing of large-scale facial image data, achieve fast and efficient processing of large-scale facial image data, accelerate algorithm operation, and possess distributed computing capabilities. Multiple computing nodes can be used for parallel processing to improve algorithm performance. © 2023 IEEE.

关键词： algorithm research facial recognition Hadoop algorithm image processing

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：