检索结果-内蒙古大学图书馆

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Qiu, Ran Liang, Hu Liu, Yuchen Zhao, Shengrong Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Qilu University of Technology Shandong Academy of Sciences Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350330717

Image inpainting, which aims to reconstruct reasonably clear and realistic images from known pixel information, is one of the core problems in computer vision. However, due to the complexity and variability of the underwater environment, the inability to extract valid pixel points and insufficient correlation between feature information in existing image inpainting techniques lead to blurring in the generated images. Therefore, a novel gated attention feature fusion image inpainting network based on generative adversarial networks (GAF-GAN) is proposed. The accuracy of feature similarity matching depends heavily on the validity of the information contained in the features. On the one hand, gating values are dynamically generated by gated convolution to reduce the interference of invalid information. On the other hand, semantic information at distant locations in an image is accurately acquired by the attention mechanism. For these reasons, we designed an improved gated attention mechanism. Gated attention mechanism make the network focus on effective information such as high-frequency texture and color fidelity of restored images. In addition, the dense feature fusion module is added to expand the overall receptive field of the network to fully learn the image features. Experimental results show that the proposed method can effectively repair defective images with complex texture structures and improve the reality and integrity of image details and structures. © 2023 IEEE.

关键词： Dense feature fusion module Gated attention mechanism Image inpainting Underwater environment

来源：评论

学校读者我要写书评

暂无评论

UNeLF: Unconstrained Neural Light Field for Self-Supervised Angular Super-Resolution

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zhao, Mingyuan Sheng, Hao Chen, Rongshan Cong, Ruixuan Cui, Zhenglong Yang, Da Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Data Science and Intelligent Computing Laboratory Hangzhou International Innovation Institute Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

Compared to supervised learning methods, self-supervised learning methods address the domain gap problem between light field (LF) datasets collected under varying acquisition conditions, which typically leads to decreased performance when differences exist in the distribution between the training and test sets. However, current self-supervised light field angular super-resolution (LFASR) techniques primarily focus on exploiting discrete spatial-angular features while neglecting continuous LF information. In contrast to previous work, we propose a self-supervised unconstrained neural light field (UNeLF) to continuously represent LF for LFASR. Specifically, any LF can be described as the camera pose for each sub-aperture image (SAI) and the two-plane that captures these SAIs. To describe the former, we introduce a SAIs-dependent pose optimization method to solve the issue that arises from the narrow baseline of most LF data, which hinders robust camera pose estimation. This mechanism reduces the number of trainable camera parameters from a quadratic to a constant scale, thereby alleviating the complexity of joint optimization. For the latter, we propose a novel adaptive two-plane parameterization strategy to determine the two-plane that captures these SAIs, facilitating refocusing. Finally, we jointly optimize the camera parameters, near-far planes and neural light field, efficiently mapping each adaptive two-plane parameterized ray to its correspondence color in a continuous manner. Comprehensive experiments demonstrate that UNeLF achieves faster training and inference with fewer computational resources while exhibiting superior performance on both synthetic and real-world datasets. © 1991-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Using Data Analytics to Derive Business Intelligence: A Case Study

arXiv

引用

arXiv 2023年

作者： Orji, Ugochukwu Obianuju, Ezugwu Ezema, Modesta Ugwuishiwu, Chikodili Ukwandu, Elochukwu Agomuo, Uchechukwu Department of Computer Science Faculty of Physical Science University of Nigeria Enugu State Nsukka Nigeria Department of Applied Computing and Engineering Cardiff School of Technologies Cardiff Metropolitan University Wales United Kingdom

The data revolution experienced in recent times has thrown up new challenges and opportunities for businesses of all sizes in diverse industries. Big data analytics is already at the forefront of innovations to help make meaningful business decisions from the abundance of raw data available today. Business intelligence and analytics (BIA) has become a huge trend in today’s IT world as companies of all sizes are looking to improve their business processes and scale up using data-driven solutions. This paper aims to demonstrate the data analytical process of deriving business intelligence via the historical data of a fictional bike-share company seeking to find innovative ways to convert their casual riders to annual paying registered members. The dataset used is freely available as "Chicago Divvy Bicycle Sharing Data" on Kaggle. The authors used the R-Tidyverse library in RStudio to analyze the data and followed the six data analysis steps of;ask, prepare, process, analyze, share, and act to recommend some actionable approaches the company could adopt to convert casual riders to paying annual members. The findings from this research serve as a valuable case example, of a real-world deployment of BIA technologies in the industry, and a demonstration of the data analysis cycle for data practitioners, researchers, and other potential users. © 2023, CC BY-NC-SA.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

QI-BRiCE: Quality Index for Bleeding Regions in Capsule Endoscopy Videos

引用

Computers, Materials & Continua 2021年第5期67卷 1697-1712页

作者： Muhammad Arslan Usman Muhammad Rehan Usman Gandeva Bayu Satrya Muhammad Ashfaq Khan Christos Politis Nada Philip Soo Young Shin Faculty of Science Engineering and ComputingKingston UniversityLondonKT12EEUK School of Electrical Engineering Superior UniversityLahorePakistan School of Applied Sciences Telkom UniversityBandungIndonesia Department of Network Computing System Architecture LabDongguk UniversitySeoulKorea Department of IT Convergence Engineering Kumoh National Institute of TechnologyGumiKorea

With the advent in services such as telemedicine and telesurgery,provision of continuous quality monitoring for these services has become a challenge for the network *** standards for provision of such services are application specic as medical imagery is quite different than general purpose images and *** paper presents a novel full reference objective video quality metric that focuses on estimating the quality of wireless capsule endoscopy(WCE)videos containing bleeding *** regions in gastrointestinal tract have been focused in this research,as bleeding is one of the major reasons behind several diseases within the *** method jointly estimates the diagnostic as well as perceptual quality of WCE videos,and accurately predicts the quality,which is in high correlation with the subjective differential mean opinion scores(DMOS).The proposed combines motion quality estimates,bleeding regions’quality estimates based on support vector machine(SVM)and perceptual quality estimates using the pristine and impaired WCE *** method Quality Index for Bleeding Regions in Capsule Endoscopy(QI-BRiCE)videos is one of its kind and the results show high correlation in terms of Pearson’s linear correlation coefcient(PLCC)and Spearman’s rank order correlation coefcient(SROCC).An F-test is also provided in the results section to prove the statistical signicance of our proposed method.

关键词： Automated bleeding detection high efciency video coding video quality assessment wireless capsule endoscopy

来源：评论

学校读者我要写书评

暂无评论

Renewable energy EV charging station

Renewable energy EV charging station

引用

2021 International Aegean Conference on Electrical Machines and Power Electronics, ACEMP 2021 and 2021 International Conference on Optimization of Electrical and Electronic Equipment, OPTIM 2021

作者： Dorin, Petreus Toma, Patarau Radu, Etz Marcian, Cirstea Technical University of Cluj-Napoca Faculty of Electronics Telecommunications and Information Technology Department of Applied Electronics Cluj-Napoca Romania Anglia Ruskin University School of Computing and Information Science Faculty of Science and Engineering Cambridge United Kingdom

ISBN: (纸本)9781665402989

Due to the increased interest in electric vehicle (EV) technologies and the cost reduction of photovoltaic systems, industrial development of battery charging stations for electric vehicles based on solar energy has started. Although it is convenient to charge EVs at night, when there is less electricity consumption, there will always be consumers who prefer or need to charge their EV during daytime and even during peak hours. In this paper, an EV charging station integrating renewable energy in the form of solar energy is proposed and analyzed. Using a local battery pack, the charging station allows semi-fast and fast charging and can be installed in individual homes and apartment buildings, where the maximum power delivered by the grid is limited to 3.6kW. The charging station uses converters widely available on the market. A simulation model for this charging station is developed and various distinct operation modes are presented, validating the correct operation of the entire system. © 2021 IEEE.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Application of Genetically Optimized LVQ Neural Network in Trade Economic Forecasting

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第2期9卷 945-958页

作者： Zhang, Xin Wei, Yan-Qiu Ni, Lin Hashim, Zrdplwa School of Business Applied Technology College of Soochow University Suzhou215325 China Fan Li Business School Shaoxing Vocational & Technical College Shaoxing312000 China Faculty of Engineering Computing and Science Swinburne University of Technology Kuching93350 Malaysia

For the purpose of enhancing the prediction accuracy of trade economic cost under increasingly complex environment, genetic optimization LVQ neural network (AGLVQ) algorithm is intended for trade economic forecast. First, this paper optimizes LVQ neural network algorithm by updating the weight vector. Then, on the ground of this, this paper further enhances the individual selection strategy in genetic algorithm to select the optimal individual and the individual with poor fitness value with a large probability and the individual with medium fitness value with a small probability, actually eluding the overfitting phenomenon of training data. The characteristic data affecting import and export costs should be fully considered in the forecasting model of trade economy to guarantee the forecasting accuracy. Finally, MATLAB R2017a is used to forecast and simulate trade economic costs. The simulation outcome signifies that when the genetic variation probability is 0.1, the optimization iteration time of test sample prediction is short and the root mean square error (RMSE) is small. The predicted cost is almost the same as the actual cost, and AGLVQ algorithm has high prediction accuracy. © 2024, J. Network Intell. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

An XAI Social Media Platform for Teaching K-12 Students AI-Driven Profiling, Clustering, and Engagement-Based Recommending

arXiv

引用

arXiv 2024年

作者： Pope, Nicolas Kahila, Juho Vartiainen, Henriikka Saqr, Mohammed López-Pernas, Sonsoles Roos, Teemu Laru, Jari Tedre, Matti University of Eastern Finland School of Computing Joensuu Finland University of Eastern Finland Applied Educational Science and Teacher Education Finland University of Helsinki Department of Computer Science Helsinki Finland University of Oulu Faculty of Educational Sciences and Psychology Oulu Finland

This paper, submitted to the special track on resources for teaching AI in K-12, presents an explainable AI (XAI) education tool designed for K-12 classrooms, particularly for students in grades 4-9. The tool was designed for interventions on the fundamental processes behind social media platforms, focusing on four AI- and data-driven core concepts: data collection, user profiling, engagement metrics, and recommendation algorithms. An Instagram-like interface and a monitoring tool for explaining the data-driven processes make these complex ideas accessible and engaging for young learners. The tool provides hands-on experiments and real-time visualizations, illustrating how user actions influence both their personal experience on the platform and the experience of others. This approach seeks to enhance learners’ data agency, AI literacy, and sensitivity to AI ethics. The paper includes a case example from 12 two-hour test sessions involving 209 children, using learning analytics to demonstrate how they navigated their social media feeds and the browsing patterns that emerged. © 2024, CC BY.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Cross-Selling Artificial Intelligence-Based Approaches in Insurance Industry: A Review

Cross-Selling Artificial Intelligence-Based Approaches in In...

引用

Electrical Engineering (ICEENG), 12th International Conference on

作者： Shaden Mohamed Aref Mohamed Mostafa Fouad Hend Attia Sayed Menna Ibrahim Gaber Faculty of Management Science October University for Modern Science and Arts Cairo Egypt Arab Academy for Science Technology and Maritime Transport College of Computing and Information Technology Cairo Egypt Mathematics Insurance and Applied Statistics Department Faculty of Commerce and Business Administration Helwan University Cairo Egypt Business Information Systems Department Faculty of Commerce and Business Administration Helwan University Cairo Egypt

ISBN: (数字)9798350343427

ISBN: (纸本)9798350343434

For the analysis of exceedingly complex insurance data, artificial intelligence methods have evolved into the most valuable and significant tools. Worldwide, the insurance industry and its clients require a method for efficiently managing the enormous amount of data produced. The current review paper provides an overview of the research conducted in recent years on various cross-selling insurance approaches that have utilized machine learning and deep learning techniques. An evident transition from the utilization of machine learning methods to deep learning methods is demonstrated through the current literature review.

关键词： Industries Training Deep learning Self-organizing feature maps Reviews Transfer learning Neural networks

来源：评论

学校读者我要写书评

暂无评论

Detecting Covid-19 in Chest X-Ray Images with Convolutional Neural Network 2

Detecting Covid-19 in Chest X-Ray Images with Convolutional ...

引用

2nd International Conference on Computer science and Engineering, IC2SE 2021

作者： Rashid, Nurullainy Mat Shuib, Liyana Eke, Christopher Ifeanyi Azmi, Nor A. Faculty of Computer Science and IT University of Malaya Department of Information Systems Kuala Lumpur Malaysia Faculty of Computing Federal University of Lafia Department of Computer Science Nasarawa State Nigeria School of Diagnostic and Applied Health Sciences Faculty of Health Sciences Bangi Malaysia

ISBN: (纸本)9781665400459

The World Health Organization (WHO) had declared Coronavirus disease (COVID-19), a deadly respiratory illness, as a pandemic in March 2020. The number of infected and deaths in COVID-19 positive patients has been rising at a distressing rate. A massive number of chest X-rays to analyse and the exhaustion from monotonous routine work may become prone to the escalation of error rate. For this reason, the use of the artificial intelligence-based tool will be beneficial in detecting subtle COVID-19, as well as to prevent false diagnoses on patients. In this study, several multi-class image classifications were developed using pre-Trained models, namely VGG16, ResNet50, MobbileNetV2, and Xception. A publicly available dataset of 14,220 chest X-ray images comprised of four different classes was used. Extensive evaluation and analysis of the Convolutional Neural Network model in predicting COVID-19 positives have been conducted. The MobileNetV2 model has been demonstrated as the best performing model out of four classifiers with an overall accuracy score of 92.48%. The model also yields 92.67% precision and 92.48% recall score, thus exhibiting a high success in the detection of COVID-19. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

IoT Based Smart Fish-Feeder and Monitoring System

IoT Based Smart Fish-Feeder and Monitoring System

引用

2022 International Conference on Business Analytics for Technology and Security, ICBATS 2022

作者： Abu-Khadrah, Ahmed Issa, Ghassan F. Aslam, Shaukat Shahzad, Muhammad Ateeq, Karamath Hussain, Munawar Saudi Electronic University College of Computing and Informatics Riyadh Saudi Arabia Skyline University College School of Information Technology Sharjah United Arab Emirates NCBAandE School of Computer Science Lahore Pakistan Riphah International University Department of Computing and Applied Sciences Lahore Pakistan Skyline University Bsit Faculty Sharjah United Arab Emirates

ISBN: (纸本)9781665409209

People have always enjoyed having pets around them, but in today's hectic world, it might be difficult to properly care for pets, particularly fish, which require more attention. When fish owners are out of town, their fish may be left with a feed shortfall or over-feed. Another consideration is the water quality (temperature, PH level, and so on). As a result, a solution is provided in this article to address the aforementioned issues. Two components comprise the proposed system. The first is for fish eating, while the second is for water feature and level monitoring. The first module also includes electrical, automatic, and communication parts that are connected to the Internet of Things (IoT) to allow fish to be fed on a schedule or remotely through a web interface. Microcontrollers with PH, Ammonia, Temperature and other sensors are included in the second module, which is used to monitor the aquarium's environment. © 2022 IEEE.

关键词： Internet of things

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：