检索结果-内蒙古大学图书馆

Prediction of NFT Sale Price Fluctuations on OpenSea Using Machine Learning Approaches

Computers, Materials & Continua 2023年第5期75卷 2443-2459页

作者： Zixiong Wang Qiuying Chen Sang-Joon Lee Interdisciplinary Program of Digital Future Convergence Service Chonnam National UniversityGwangju61186Korea

The rapid expansion of the non-fungible token(NFT)market has attracted many ***,studies on the NFT price fluctuations have been relatively *** date,the machine learning approach has not been used to demonstrate a specific error in NFT sale price fluctuation *** aim of this study was to develop a prediction model for NFT price fluctuations using the NFT trading information obtained from OpenSea,the world’s largest NFT *** used Python programs to collect data and summarized them as:NFT information,collection information,and related account *** and Random Forest(RF)algorithms were employed to predict the sale price and price fluctuation of NFTs using regression and classification models,*** found that the NFT related account information,especially the number of favorites and activity status of creators,confer a good predictive power to both the *** in the regression model had more accurate predictions,the root mean square error(RMSE)in predicting NFT sale price was *** predicting NFT sale price fluctuations,RF performed better,which the area under the curve(AUC)reached *** suggest that investors should pay more attention to the information of NFT *** anticipate that these prediction models will reduce the number of investment failures for the investors.

关键词： NFT sale price fluctuation OpenSea AdaBoost Random forest

来源：评论

学校读者我要写书评

暂无评论

Predicting ESG Ratings by Machine Learning and Analyzing Influencing Factors by XAI 24

Predicting ESG Ratings by Machine Learning and Analyzing Inf...

引用

7th International Conference on Software Engineering and Information Management, ICSIM 2024

作者： Choi, Jeong-Cheol Chen, Qiuying Lee, Sang-Joon Interdisciplinary Program of Digital Future Convergence Service Chonnam National University Korea Republic of

ISBN: (纸本)9798400709197

This study examines the role of Environmental, Social, and Governance (ESG) management in corporate strategy, particularly focusing on predicting ESG ratings with machine learning. Given the diverse ESG evaluation criteria employed by global rating agencies, there's a need for clear guidelines to facilitate effective ESG management. The research aims to develop an ESG rating prediction model utilizing a triennial compendium of Korean corporate financial data. This process involves a comparative analysis of linear models, tree-based models, and neural network-based models. Additionally, this study explains the importance of various variables by applying SHAP, one of the XAI techniques. The results indicate that XGB is the most effective, achieving an 85.1% F1 score in ESG rating predictions. By understanding how financial factors impact ESG ratings, companies can develop more effective ESG strategies, forming an essential foundation for sustainable growth. © 2024 ACM.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

View Types and Visual Communication Cues for Remote Collaboration

引用

Computers, Materials & Continua 2023年第2期74卷 4363-4379页

作者： Seungwon Kim Weidong Huang Chi-Min Oh Gun Lee Mark Billinghurst Sang-Joon Lee AI Convergence College Chonnam National UniversityGwangju61186Korea University of Technology Sydney Sydney2007Australia SafeMotion Gwangju61011Korea School of ITMS University of South AustraliaAdelaide5001Australia Interdisciplinary Program of Digital Future Convergence Service Chonnam National UniversityGwangju61186Korea

Over the last several years,remote collaboration has been getting more attention in the research community because of the COVID-19 *** previous studies,researchers have investigated the effect of adding visual communication cues or shared views in collaboration,but there has not been any previous study exploring the influence between *** this paper,we investigate the influence of view types on the use of visual communication *** compared the use of the three visual cues(hand gesture,a pointer with hand gesture,and sketches with hand gesture)across two view types(dependent and independent views),*** conducted a user study,and the results showed that hand gesture and sketches with the hand gesture cueswerewell matchedwith the dependent viewcondition,and using a pointer with the hand gesture cue was suited to the independent view *** the dependent view,the hand gesture and sketch cues required less mental effort for collaborative communication,had better usability,provided better message understanding,and increased feeling of co-presence compared to the independent *** the dependent view supported the same viewpoint between the remote expert and a local worker,the local worker could easily understand the remote expert’s hand *** contrast,in the independent view case,when they had different viewpoints,it was not easy for the local worker to understand the remote expert’s hand *** sketch cue had a benefit of showing the final position and orientation of the manipulating objects with the dependent view,but this benefit was less obvious in the independent view case(which provided a further view compared to the dependent view)because precise drawing in the sketches was difficult from a *** the contrary,a pointer with the hand gesture cue required less mental effort to collaborate,had better usability,provided better message understanding,and an increased feeling of co-presence in the independent view con

关键词： Mixed reality remote collaboration

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Multivariate Prediction of Building Energy Performance of Residential Buildings

引用

Computers, Materials & Continua 2023年第6期75卷 5947-5964页

作者： Ibrahim Aliyu Tai-Won Um Sang-Joon Lee Chang Gyoon Lim Jinsul Kim Department of ICT Convergence System Engineering Chonnam National UniversityGwangju61186Korea Graduate School of Data Science Chonnam National UniversityGwangju61186Korea Interdisciplinary Program of Digital Future Convergence Service Chonnam National UniversityGwangju61186Korea Department of Computer Engineering Chonnam National UniversityYeosu59626Korea

In the quest to minimize energy waste,the energy performance of buildings(EPB)has been a focus because building appliances,such as heating,ventilation,and air conditioning,consume the highest ***,effective design and planning for estimating heating load(HL)and cooling load(CL)for energy saving have become *** this vein,efforts have been made to predict the HL and CL using a univariate ***,this approach necessitates two models for learning HL and CL,requiring more computational ***,the one-dimensional(1D)convolutional neural network(CNN)has gained popularity due to its nominal computa-tional complexity,high performance,and low-cost hardware *** this paper,we formulate the prediction as a multivariate regression problem in which the HL and CL are simultaneously predicted using the 1D *** the building shape characteristics,one kernel size is adopted to create the receptive fields of the 1D CNN to extract the feature maps,a dense layer to interpret the maps,and an output layer with two neurons to predict the two real-valued responses,HL and *** the 1D data are not affected by excessive parameters,the pooling layer is not applied in this ***,the use of pooling has been questioned by recent *** performance of the proposed model displays a comparative advantage over existing models in terms of the mean squared error(MSE).Thus,the proposed model is effective for EPB prediction because it reduces computational time and significantly lowers the MSE.

关键词： Artificial intelligence(AI) convolutional neural network(CNN) cooling load deep learning energy energy load energy building performance heating load prediction

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven digital Twin Network Architecture in the Industrial Internet of Things (IIoT) Applications

arXiv

引用

arXiv 2023年

作者： Isah, Abubakar Shin, Hyeju Aliyu, Ibrahim Oh, Sangwon Lee, Sangjoon Park, Jaehyung Hahn, Minsoo Kim, Jinsul Department of ICT Convergence System Engineering Chonnam National University Gwangju Korea Republic of Interdisciplinary Program of Digital Future Convergence Service Chonnam National University Gwangju Korea Republic of Astana IT University Astana Kazakhstan

A new network named the "digital Twin Network" (DTN) uses the "digital Twin" (DT) technology to produce virtual twins of real things. The network load and size continue to grow as a result of the development of 5G, the Internet of Things, and cloud computing technology as well as the advent of new network services. As a result, network operation and maintenance are becoming more difficult. A digital twin connects the real and digital worlds, exchanging data in both directions and revealing information about the progression of a network process. The framework of the Industrial Internet of Things, data processing, and digital twin network is taken into consideration in this article as a key aspect. This paper proposed a data-driven digital twin network architecture, that comprises the physical network layer (PNL), the digital twin layer(DTL), the application layer (AL), and what those layers encompass and beyond. Also, we presented DTN data types and protocols to be used for data integration. Copyright © 2023, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach to Predict Customer Churn of a Delivery Platform

A Machine Learning Approach to Predict Customer Churn of a D...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Qing Liu QiuYing Chen Sang-Joon Lee Interdisciplinary Program of Digital Future Converged Service Chonnam National University Gwangju South Korea School of Business Administration Chonnam National University Gwangju South Korea

The use of delivery platforms has become widespread due to the impact of the Covid-19 and the O2O industry. However, the ELEME delivery platform, a subsidiary of Alibaba Group, which represents China, has recently been losing market share. This means that companies need to constantly look at strategies to attract new customers and maintain existing ones. In general, it costs at least five times more to attract new customers than it does to manage existing customers. This paper attempts to predict customer churn using the ELEME customer dataset to develop strategies to identify and prevent churn in advance. The results of the analysis using machine learning approach found that the most influential feature that can predict churn is the number of clicks made by the user. This paper presents the process and explanation of applying various algorithms for predicting customer churn on a distribution platform. It also proposes strategies for dealing with customer churn.

关键词： Industries COVID-19 Machine learning algorithms Costs Machine learning Companies Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Assessing the efficacy of ChatGPT in addressing Chinese financial conundrums: An in-depth comparative analysis of human and AI-generated responses

Computers in Human Behavior: Artificial Humans

引用

Computers in Human Behavior: Artificial Humans 2023年第2期1卷

作者： Chen Ren Sang-Joon Lee Chenxi Hu School of Economics and Business Administration Hefei University China Interdisciplinary Program of Digital Future Convergence Service Chonnam National University Gwangju 61186 South Korea Key Laboratory of Financial Big Data Hefei University China

ChatGPT, the latest iteration of OpenAI's natural language generation model, has found applications in a wide range of tasks such as question answering, text summarization, machine translation, classification, code generation, and dialogue A.I. Its potential in the financial industry has garnered significant attention. This paper aims to bridge the gap between chatGPT and human services in the financial domain, while also exploring the opportunities and challenges it presents in this industry. To comprehensively evaluate the processing capabilities of chatGPT in the financial field, we collected a dataset of n = 7165 financial questions and analyzed the perplexity value, emotion value, accuracy, professionalism, and real-time performance of both human-generated and chatGPT-generated content using machine learning algorithms and evaluation tests. The experimental results indicate that chatGPT exhibits higher levels of professionalism and accuracy compared to manual services, leading to improved efficiency, cost reduction, and enhanced customer satisfaction, thereby boosting the competitiveness and profitability of financial institutions. However, challenges such as a lack of emotional value in its responses, potential bias from one-sided training data, information errors, and the risk of job displacement need to be addressed. These findings provide theoretical and data-driven support for the future implementation of chatGPT in financial innovation and development.

关键词： ChatGPT Python Language model NLP AI Fintech

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：