检索结果-内蒙古大学图书馆

Efficient Ship:A Hybrid Deep Learning Framework for Ship Detection in the River

computer Modeling in Engineering & sciences 2024年第1期138卷 301-320页

作者： Huafeng Chen Junxing Xue Hanyun Wen Yurong Hu Yudong Zhang School of Computer Engineering Jingchu University of TechnologyJingmen448000China School of Computer Science Yangtze UniversityJingzhou434023China School of Computing and Mathematic Sciences University of LeicesterLeicesterLE17RHUK

Optical image-based ship detection can ensure the safety of ships and promote the orderly management of ships in offshore *** deep learning researches on optical image-based ship detection mainly focus on improving one-stage detectors for real-time ship detection but sacrifices the accuracy of *** solve this problem,we present a hybrid ship detection framework which is named EfficientShip in this *** core parts of the EfficientShip are DLA-backboned object location(DBOL)and CascadeRCNN-guided object classification(CROC).The DBOL is responsible for finding potential ship objects,and the CROC is used to categorize the potential ship *** also design a pixel-spatial-level data augmentation(PSDA)to reduce the risk of detection model *** compare the proposed EfficientShip with state-of-the-art(SOTA)literature on a ship detection dataset called *** show our ship detection framework achieves a result of 99.63%(mAP)at 45 fps,which is much better than 8 SOTA approaches on detection accuracy and can also meet the requirements of real-time application scenarios.

关键词： Ship detection deep learning data augmentation object location object classification

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review: Forecasting Stock Price Using Machine Learning Approach

A Systematic Literature Review: Forecasting Stock Price Usin...

引用

2023 International Conference on Data science and Its Applications, ICoDSA 2023

作者： Lumoring, Niclauss Chandra, Daniel Gunawan, Alexander Agung Santoso Bina Nusantara University School of Computer Science Mathematic Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350305197

With the increasing popularity of stock trading, individuals, and financial entities such as investment companies, hedge funds, and retail investors are actively participating in the stock market to generate profits. Numerous strategies, ranging from traditional methods employing fundamental and technical analysis to modern approaches utilizing cutting-edge technology, have been developed and implemented. However, determining the optimal method remains challenging. Designing an effective strategy in the complex and dynamic stock market environment poses significant difficulties. Therefore, this study aims to provide an overview of machine learning applications in the stock market and identify the most frequently used machine learning models or methods for market prediction. Furthermore, the study aims to identify the strategy that achieves the highest accuracy in predicting stock prices. Based on a systematic literature review encompassing quantitative and qualitative analyses, it is found that Support Vector Machine (SVM) emerges as the most popular machine learning technique for predicting stock prices. However, Long Short-Term Memory (LSTM) stands out as the machine learning technique that demonstrates the highest level of accuracy, achieving an impressive accuracy rate of 99.58%. These findings highlight the effectiveness of LSTM in forecasting stock values with exceptional precision. The results of this study contribute to a comprehensive understanding of machine learning in the stock market domain and offer valuable insights for developing effective trading strategies. Traders and investors can leverage LSTM and SVM techniques to enhance their stock market predictions and make informed investment decisions. © 2023 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Comparative Performance Analysis of Javascript Frontend Web Frameworks 3

Comparative Performance Analysis of Javascript Frontend Web ...

引用

3rd International Conference on Electronic and Electrical Engineering and Intelligent System, ICE3IS 2023

作者： Tong, Jason Jikson, Ricky Rivaldo Gunawan, Alexander Agung Santoso School of Computer Science Bina Nusantara University Mathematic Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350327762

One of the most popular tools today for building engaging, robust, and easy to manage websites is the JavaScript programming language. Over the past 10 years, numerous front-end frameworks have been developed on top of JavaScript, making it simpler to develop, design, and maintain interactive websites. Currently, the most popular JavaScript front-end frameworks are *** and ***. *** is a relatively new framework that is also catching developers' attention and growing in popularity. This paper assesses the performance of these prominent front-end JavaScript frameworks, analyzing aspects like browser performance, speed index, interactive time, and the efficiency of specific DOM operations such as adding, editing, and removing elements. Using benchmark applications tailored for each framework, we conducted extensive testing to gauge their performance across different DOMs, leveraging technology-based data. Finally, our study of three front-end frameworks concluded that *** offers superior performance, ***'s focus on JavaScript dynamics leads to latency, and *** exhibits average speed, particularly in 'to-do list' and 'image gallery' project contexts. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Wireless Sensor Network Intrusion Detection Model for Real-time Hazardous Chemical Monitoring 3

Wireless Sensor Network Intrusion Detection Model for Real-t...

引用

3rd International Conference on Smart Data Intelligence, ICSMDI 2023

作者： Xu, Bing Chen, Youying School of Computer Science and Engineering Yulin Normal University Guangxi Yulin537000 China School of Mathematic and Computer Science Guangdong Ocean University Guangdong Zhanjiang524088 China

ISBN: (纸本)9781665464871

Intelligent video surveillance technology is composed of the extremely complex algorithms and technologies. Hence, this article proposes a wireless sensor network intrusion detection model to perform real-time hazardous chemical monitoring. The video surveillance is mainly obtained through the on-site investigation process. After a preliminary understanding of the on-site situation, the 'centripetal method' or 'centrifugal method' is used to visit the periphery, and finally the surveillance video will be detected. To improve the security, the network intrusion detection model is employed. The performance is validated by testing the model under different conditions. © 2023 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Control for T-S Fuzzy Semi-Markovian Jump Delay Systems Via Quantized Sampled-Data Control

Asynchronous Control for T-S Fuzzy Semi-Markovian Jump Delay...

引用

2023 International Conference on New Trends in Computational Intelligence, NTCI 2023

作者： Zhang, Jiangping Xiong, Lianglin School of Mathematic and Computer Science Yunnan Minzu University Kunming China School of Media and Information Engineering Yunnan Open University Kunming China

ISBN: (纸本)9798350380859

This article, by quantized sampled-data controller (QS-DC), addresses asynchronous control for T-S fuzzy semi-Markovian jump delay systems (TSFSMJDSs), which a weak innitesimal operator (WIO) working on a function with double semi-Markovian jump parameters (DSMJPs). Firstly, an innovative augmented Lyapunov-Krasovskii functional (LKF) is formated that includes both the message of states within the sampled-data intervals and involves with DSMJPs, which not only fully utilize the real sample pattern but also loosen the monotonic constraint of LKF. In addition, the designed QS-DC can enhance the control performance and design flexibility. Finally, verifying the feasibility of theoretical results via a numerical example. © 2023 IEEE.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

mathematical model estimation and prediction application of Covid-19 infection in Indonesia using Levenberg-Marquardt Algorithm based on Python 7

Mathematical model estimation and prediction application of ...

引用

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Aryatama, Fonggi Yudi Kurniadi, Felix Indra Manik, Ngarap Im Mathematic Department School of Computer Science Bina Nusantara University Jakarta11530 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11530 Indonesia

COVID-19 was originally diagnosed in Wuhan, China, in late December 2019;it subsequently expanded internationally, affecting around 7 million people and caused 300,000 deaths by May 2020. An Application that could surveillance the Covid-19 in Indonesia is needed. Therefore, we proposed a prediction application for the COVID-19 pandemic situation in Indonesia by referring to public compliance with surveillance policies using the SPCIRD model. The Levenberg Marquardt curve fitting method was chosen because it is simple and produces a reasonably good model. According the result of questionnaire and black box testing our application performed really well. The result of our SPCIRD model with Levenberg-Marquardt optimization achieved R2 with the score-1.248 in active cases,-0.235 in recovered and-3.982 in death for 281 number of iterations. We are also achieved 93.3% that agree and very agree with the application usability to understand and to predict pattern from COVID-19. It was also had 83.3\% respondent that satisfy with the prototype. © 2022 Elsevier B.V.. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Modelling Flood Prone Area in North America with Geomorphic Flood Index Method

Modelling Flood Prone Area in North America with Geomorphic ...

引用

2022 International Conference on Informatics Electrical and Electronics, ICIEE 2022

作者： Yolina, Hanni Irwansyah, Edy Rojali School of Computer Science Bina Nusantara University Dept. of Mathematic Jakarta Indonesia School of Computer Science Bina Nusantara University Dept. of Computer Science Jakarta Indonesia

ISBN: (纸本)9781665486224

A flood is a natural disaster that has the potential to cause a loss in terms of material and fatalities, especially in an urban area. The ability to know flood-prone areas in a region will be helpful in the prevention and countermeasures of the flood. Currently, there are many methods to determine floodprone areas in a region, unfortunately, most traditional methods require complicated data which not necessarily owned by a region. Nevertheless, there is the Geomorphic Flood Index method which is a method to find flood-prone areas in a region using easy-To-find data and have a fast process. The goal of this work is to examine this Geomorphic Flood Index method which has been implemented on the Geomorphic Flood Area plugin. From the results, the Geomorphic Flood Area plugin has an accuracy of 60.57%. It was also found that there was an error in the GFA plugin code which might affect accuracy. © 2022 IEEE.

关键词： Floods

来源：评论

学校读者我要写书评

暂无评论

mathematical model estimation and prediction application of Covid-19 infection in Indonesia using Levenberg-Marquardt Algorithm based on Python

引用

Procedia computer science 2023年 216卷 120-127页

作者： Fonggi Yudi Aryatama Felix Indra Kurniadi Ngarap Im Manik Mathematic Department School of Computer Science Bina Nusantara University Jakarta 11530 Indonesia. Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11530 Indonesia.

COVID-19 was originally diagnosed in Wuhan, China, in late December 2019; it subsequently expanded internationally, affecting around 7 million people and caused 300,000 deaths by May 2020. An Application that could surveillance the Covid-19 in Indonesia is needed. Therefore, we proposed a prediction application for the COVID-19 pandemic situation in Indonesia by referring to public compliance with surveillance policies using the SPCIRD model. The Levenberg Marquardt curve fitting method was chosen because it is simple and produces a reasonably good model. According the result of questionnaire and black box testing our application performed really well. The result of our SPCIRD model with Levenberg-Marquardt optimization achieved R2 with the score -1.248 in active cases, -0.235 in recovered and -3.982 in death for 281 number of iterations. We are also achieved 93.3% that agree and very agree with the application usability to understand and to predict pattern from COVID-19. It was also had 83.3\% respondent that satisfy with the prototype.

关键词： COVID-19 Levenberg-Marquardt Python SPCIRD Waterfall

来源：评论

学校读者我要写书评

暂无评论

Experiments to Review Literature on Topic Trends in Technology Development in Educational Information Systems 7

Experiments to Review Literature on Topic Trends in Technolo...

引用

7th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2023

作者： Santiko, Irfan Soeprobowati, Tri Retnaningsih Surarso, Bayu Universitas Amikom Purwokerto Faculty of Computer Science Informatic Departement Indonesia School of Post Graduate Diponegoro University Information System Departement Semarang Indonesia School of Post Graduate Diponegoro University Faculty of Science and Mathematic Semarang Indonesia

ISBN: (纸本)9798350382266

The smart campus is a phenomenon that occurs in the industrial era 4.0. Many people understand that a smart campus is a campus where all resources can work and produce learning with high effectiveness and maximum efficiency. Everyone talks about elements of information technology that play a role in the sustainability of smart campuses. However, what actually makes the definition of a smart campus itself is not defined with certainty. This is because the world of education itself is experiencing major disruption. This causes innovation in the world of education, especially learning, to pay less attention to the actual aspects of education. This means that education has relied too much on technology which will actually cause a shift in the essence of education itself. In this paper, we will review how effective and efficient learning concepts actually are using information technology. The method used is an analysis of the literature review with an experimental survey and bibliometric analysis. As a result, it will be known that information technology that is in accordance with the essence of education is a matter that does not only focus on technical aspects but also needs to pay attention to aspects of methods, materials, and media. So that the results that are known will provide insight into the development of learning models on an ongoing basis according to the true essence of education. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

FNIN: A Fourier Neural Operator-based Numerical Integration Network for Surface-form-gradients 39

FNIN: A Fourier Neural Operator-based Numerical Integration ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Leng, Jiaqi Ju, Yakun Duan, Yuanxu Zhang, Jiangnan Lv, Qingxuan Wu, Zuxuan Fan, Hao Haide College Ocean University of China China Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China School of Computing and Mathematic Sciences University of Leicester United Kingdom Department of Computer Engineering Qingdao City University China College of Computer Science and Technology Ocean University of China China

ISBN: (纸本)157735897X

Surface-from-gradients (SfG) aims to recover a three-dimensional (3D) surface from its gradients. Traditional methods encounter significant challenges in achieving high accuracy and handling high-resolution inputs, particularly facing the complex nature of discontinuities and the inefficiencies associated with large-scale linear solvers. Although recent advances in deep learning, such as photometric stereo, have enhanced normal estimation accuracy, they do not fully address the intricacies of gradient-based surface reconstruction. To overcome these limitations, we propose a Fourier neural operator-based Numerical Integration Network (FNIN) within a two-stage optimization framework. In the first stage, our approach employs an iterative architecture for numerical integration, harnessing an advanced Fourier neural operator to approximate the solution operator in Fourier space. Additionally, a self-learning attention mechanism is incorporated to effectively detect and handle discontinuities. In the second stage, we refine the surface reconstruction by formulating a weighted least squares problem, addressing the identified discontinuities rationally. Extensive experiments demonstrate that our method achieves significant improvements in both accuracy and efficiency compared to current state-of-the-art solvers. This is particularly evident in handling high-resolution images with complex data, achieving errors of fewer than 0.1 mm on tested objects. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep learning

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：