检索结果-内蒙古大学图书馆

Optimal Deep Canonically Correlated Autoencoder-Enabled Prediction Model for Customer Churn Prediction

Computers, Materials & Continua 2022年第11期73卷 3757-3769页

作者： Olfat M.Mirza GJose Moses R.Rajender E.Laxmi Lydia Seifedine Kadry Cheadchai Me-Ead Orawit Thinnukool Department of Computer Science College of Computers and Information SystemsUmm Al-Qura UniversityMakkahSaudi Arabia Department of Computer Science Engineering Malla Reddy Engineering College500100India Department of Computer Science Engineering Lendi Institute of Engineering&TechnologyDenkada535005India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Applied Data Science Noroff University CollegeNorway Program in Statistics and Information Management Faculty of ScienceMaejo UniversityChiang Mai50290Thailand Department of Modern Management and Information Technology College of Arts Media and TechnologyChiang Mai UniversityChiang Mai50200Thailand

Presently,customer retention is essential for reducing customer churn in telecommunication *** churn prediction(CCP)is important to predict the possibility of customer retention in the quality of *** risks of customer churn also get essential,the rise of machine learning(ML)models can be employed to investigate the characteristics of customer ***,deep learning(DL)models help in prediction of the customer behavior based characteristic *** the DL models necessitate hyperparameter modelling and effort,the process is difficult for research communities and business *** this view,this study designs an optimal deep canonically correlated autoencoder based prediction(ODCCAEP)model for competitive customer dependent application *** addition,the O-DCCAEP method purposes for determining the churning nature of the *** O-DCCAEP technique encompasses preprocessing,classification,and hyperparameter ***,the DCCAE model is employed to classify the churners or ***,the hyperparameter optimization of the DCCAE technique occurs utilizing the deer hunting optimization algorithm(DHOA).The experimental evaluation of the O-DCCAEP technique is carried out against an own dataset and the outcomes highlighted the betterment of the presented O-DCCAEP approach on existing approaches.

关键词： Churn prediction customer retention deep learning machine learning archimedes optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Linkedin's Influence on User Success in The Professional World 9

Linkedin's Influence on User Success in The Professional Wor...

引用

9th International Conference on ICT for Smart Society, ICISS 2022

作者： Oktavia, Tanty Roekman, Faza Fakhriansyah Putera, Muhammad Ikhsan Hidayah, Muhammad Alif Rafi, Muhammad Hosoda, Takaaki Gaol, Ford Lumban BINUS Graduate Program Information System Management Bina Nusantara University Information System Management Department Jakarta Indonesia School of Information Systems Bina Nusantara University Information System Department Jakarta Indonesia Advanced Institute of Industrial Technology Decision Science Department Tokyo Japan BINUS Graduate Program Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (数字)9781665471350

ISBN: (纸本)9781665471350

Social media has now become a place for others to exchange information in the form of writing, photos, videos, and audio. Social media has become a place for humans to interact from all over the world. In the use of social media, attractive professional information is conceptualized as access to relevant information and opening up better career opportunities. User content about work and choosing personal information compilation strategies consistently predict information usefulness. This study discusses the effect of using a linked-in application on the success of its users in the professional world. It is hoped that it can provide insight into the use of this recruitment application, making it easier for users to find work. The research model used in this research is quantitative. The survey was conducted on connected users in Indonesia using an online questionnaire, and the data collected was analyzed using PLS-SEM. Of the 68 respondents who took the survey, it can be said that all research models have a positive relationship with the successful use of the linked-in platform. © 2022 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Predicting Factors Influencing the Actual Use of E-Learning Platform among Medical Students in the Philippines: Unified Theory of Acceptance and Use of technology Approach 24

Predicting Factors Influencing the Actual Use of E-Learning ...

引用

4th International Conference on Internet and E-Business, ICIEB 2024

作者： Benito, Omar Paolo Prasetyo, Yogi Tri Roque, Ralph Andre C. Flores, Fernan Patrick Cahigas, Maela Madel L. Nadlifatin, Reny Ayuwati, Irene Dyah International Bachelor Program in Engineering Yuan Ze University Taiwan Department of Industrial Engineering and Management Yuan Ze University Taiwan School of Industrial Engineering and Engineering Management Mapua University Philippines School of Graduate Studies Mapua University Philippines Department of Information Systems Sepuluh Nopember Institute of Technology Indonesia University of Surabaya Indonesia

ISBN: (纸本)9798400709739

eLearning has been utilized as a mode of instruction among medical students amidst the COVID-19 pandemic. The present study aimed to investigate the factors influencing the acceptance of eLearning platforms in medical education during the COVID-19 pandemic in the Philippines by employing the latent variables of UTAUT2, along with two additional latent variables gathered from various related literature. A sum of 360 medical students participated and answered an online survey that consists of 40 questions. A stepwise multiple linear regression was utilized and found that performance expectancy (PE), habit (HB), and instructor characteristics (IC), can successfully predict the actual use (AU) of medical students with a precision of 54.22%. A higher performance expectancy (PE), habit (HB), and instructor characteristics (IC) can enhance and promote the acceptance of medical eLearning platforms. This is the first study that has examined the acceptance of eLearning platforms among medical students in the Philippines during the COVID-19 pandemic. The outcomes of this research can serve as guidelines for the Commission on Higher Education of the Philippines for the enhancement of eLearning platforms. Although this study only utilized the latent variables of UTAUT2 along with two additional variables: Learning Value and Instructor Characteristics;the findings of this study would still hold significant value for promoting open innovation in eLearning platforms in medical fields worldwide. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Relation of Determinant Factors and Their Effect on Improving the Online Learning : A systematic literature review 5

Relation of Determinant Factors and Their Effect on Improvin...

引用

5th International Conference on Advancement in Data Science, E-Learning and information Systems, ICADEIS 2023

作者： Widiartha, Ida Bagus Ketut Hwang, Junseok Nugraha, Ryan Adhitya University of Mataram Dept. of Informatics Engineering Mataram Indonesia Seoul National University Technology Management Economic Policy Program Seoul Korea Republic of Telkom University Dept. of Information System Bandung Indonesia

ISBN: (纸本)9798350303414

This study introduces the Harmony Model, which examines factors influencing the success of online learning and the workload of lecturers. Drawing upon the Theory of Action Reason, it explores the impact of student satisfaction and lecturers' willingness to prepare course materials. The model emphasizes the challenge faced by lecturers in creating high-quality content and highlights the importance of balancing supporting factors and alleviating the associated burden. Strategies to enhance online learning effectiveness should address both lecturers' motivation and student satisfaction. Identifying determinant factors and analyzing their impact on material development can increase lecturers' willingness to provide appropriate course materials. Knowledge extraction processes and satisfaction-related factors play crucial roles. This study offers insights to enhance the online learning experience, optimize learning outcomes, and improve overall effectiveness. © 2023 IEEE.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Question Classification from Thai Sentences by Considering Word Context to Question Generation

Question Classification from Thai Sentences by Considering W...

引用

2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2022

作者： Chotirat, Saranlita Meesad, Phayung Unger, Herwig King Mongkut's University of Technology North Bangkok Information Technology Program Bangkok Thailand King Mongkut's University of Technology North Bangkok Department of Information Technology Management Bangkok Thailand Fern Universität in Hagen Department of Communication Networks Hagen Germany

ISBN: (数字)9781665473248

ISBN: (纸本)9781665473248

The potential of automated question generation is role play in the multi-fields and multi-applications such as question and answering systems, examination systems, and information retrieval. Before learning the question generated, one should understand how to classify questions. This research aims to generate possible questions considering the possible question categories from question classification based on Natural Language Processing. In this research, we compared the results on Logistic Regression, Support Vector Machine, and Multinomial Naï ve Bayes, which were traditional classification models. The deep learning techniques were Convolutional Neural Networks, Bidirectional Long Short-Term Memory, combined CNN and BiLSTM models, and BERT models. The experimental results show that the preprocessing phase using Natural Language Processing could enhance question classification. The classification of the sentence to question classification attained an average micro F1- score of 91.40% when applied BERT model by pre-trained WangchanBERTa on simple sentences. In contrast, the satisfying score with an average micro F1 - score of 82.07% (from 80.37% on original input) when applied to add all POS tags unigram + bigram TF-IDF by using the SVM model. The experimental results when the CNN model with GloVe on adding focusing POS tags is a satisfactory score with an average micro F1 - score of 79.79%. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Food delivery app continuance: a dual model and segmentation approach

引用

International Journal of Retail & Distribution management 2023年第5期51卷 569-589页

作者： Trieu Nguyen Echo Huang Dung Minh Nguyen IMBA program College of Management National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Information Management College of Management National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Marketing and Distribution Management College of Management National Kaohsiung University of Science and Technology Kaohsiung Taiwan

Purpose The outbreak of the COVID-19 pandemic has led to the pervasiveness of food delivery apps (FDAs) and the increased scholars’ attention for the topic of FDA continuance usage intention. However, the limited understanding about possible segments of FDA users has hindered food retailers from providing FDAs with a personalized manner, which impairs the effectiveness of marketing strategies. Thus, this study aims to first explore key antecedents of users’ continuance intention toward FDAs and then segment and profile Taiwanese users based on the identified antecedents of FDA continuance intention and demographics. Design/methodology/approach An online survey was implemented to collect responses from FDA users in Taiwan. With a response rate of 82.4%, the final sample of 326 respondents (average age = 28.3; female = 54.9%) was analyzed by using two techniques of structural equation modeling (SEM) and cluster analysis. Findings The results indicate six antecedents of users’ continuance usage intention towards FDAs, including information quality, system quality, information quality, perceived usefulness, perceived enjoyment and satisfaction. Additionally, three distinct clusters of FDA users are successfully identified, labeled as “value sensitive users”, “time-sensitive users” and “security sensitive users”. Originality/value This study is one of the pioneers that explores the possible segments in FDA market, which helps FDA providers and food retailers develop more focused and appropriate strategies to encourage users to continue using FDAs. Our findings contribute to building an optimized version of “FDA Tech” that becomes an omni-channel solution to serve the increased home-delivery needs in the new normal era.

关键词： Continuance usage intention Food delivery apps Food retailers COVID-19 Segmentation Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

BEST: AN INSTRUCTIONAL DESIGN MODEL TO EMPOWER GRADUATE STUDENT SELF-EFFICACY IN RESEARCH METHODOLOGY THROUGH TPACK INTEGRATION

引用

Interdisciplinary Journal of information, Knowledge, and management 2025年 20卷

作者： Sukma, Narongsak Pum, Wachiranun Master of Science Program in Professional Cyber Security Faculty of Digital Siam Technology College Bangkok Thailand Faculty of Management Science and Information Technology Nakhon Phanom University Nakhon Phanom Thailand

Aim/Purpose Traditional research methodology education faces challenges in developing student self-efficacy and integrating modern technology, necessitating innovative instructional approaches for graduate students. Background This study introduces the BEST model (begin with learner analysis, establish clear learning objectives, select engaging learning activities, and tailor instruction using technology) to address these challenges through systematic TPACK integration. Methodology A qualitative investigation was conducted with 10 graduate students through focus groups and in-depth interviews over one month, analyzed using narrative and content analysis approaches. Contribution Content analysis revealed improvements in self-efficacy (from four to eight participants), peer learning (from three to six), and critical thinking (from three to six) while maintaining active learning engagement throughout implementation. Findings Students showed significant improvements in self-efficacy (four to eight participants), peer learning (three to six), and critical thinking (three to six) while maintaining active learning engagement. Recommendations for Practitioners Institutions should implement robust technical support systems and flexible learning pathways while ensuring adequate infrastructure before adoption. A phased implementation approach with peer mentoring is recommended to address technology integration challenges. Recommendations for Researchers Future research should examine the BEST model’s effectiveness across different cultural contexts and disciplines through comparative and longitudinal studies while exploring the integration of emerging educational technologies. Impact on Society The BEST model enhances the quality of graduate research education by developing students’ confidence and competence, potentially leading to more capable researchers and improved research outcomes. Future Research Longitudinal studies should track the impact on research productivity and

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Examining Gen-Z Intention to Participate in Deposit Refund Systems: A Convergent Mixed-Method Study in Indonesia

Examining Gen-Z Intention to Participate in Deposit Refund S...

引用

Vocational Education and Electrical Engineering, International Conference on

作者： Muhamad Rachmat Gunawan Febriliyan Samopa Ahmad Mukhlason Doctoral Program in Technology Management Interdiciplinary School of Management and Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Information Systems Institut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (数字)9798331505103

ISBN: (纸本)9798331505110

The rising environmental challenges in waste management have prompted an urgent need for effective recycling initiatives. This study investigates the intention of Generation Z (Gen-Z) in Indonesia to participate in a Deposit Refund System (DRS), a system aimed at promoting recycling behaviors. Using a convergent mixed-method approach, quantitative data from 228 respondents were analyzed via Partial Least Squares Structural Equation Modeling (PLS-SEM) to assess relationships between intention, distrust, environmental concern, and behavioral intention. Qualitative data analysis, employing vector embedding and k-means clustering, revealed key patterns and themes in Gen-Z’s attitudes. Integration of qualitative and quantitative results through PLS-SEM provided a comprehensive understanding of Gen-Z motivations towards environmental sustainability. The results show that environmental concern positively impacts behavioral intention, while distrust was found to be statistically insignificant. This study offers practical and academic insights for policymakers to design more effective DRS initiatives. Future research could explore the long-term behavioral shifts resulting from DRS participation and the role of digital platforms in enhancing engagement.

关键词： Waste management Electrical engineering Analytical models Data analysis Green products Education Mathematical models Vectors Data models Recycling

来源：评论

学校读者我要写书评

暂无评论

Effects of an automated programming assessment system on the learning performances of experienced and novice learners

引用

Interactive Learning Environments 2023年第8期31卷 5347-5363页

作者： Cheng, Li-Chen Li, Wei Tseng, Judy C. R. Department of Information and Finance Management National Taipei University of Technology Taipei Taiwan STEM Education Research Center Wenzhou University Zhejiang Province Wenzhou China Ph.D. Program in Engineering Science Chung Hua University Hsinchu Taiwan Department of Computer Science and Information Engineering Chung Hua University Hsinchu Taiwan

programming ability is the core ability of this era and can be obtained and improved through practice. In this paper, an Automated programming Assessment system based on Mastery learning and Peer competition (APAMP) was proposed and developed. APAMP allows students to practice repeatedly by providing immediate feedback after their programs are submitted. It also presents an analytical dashboard as a competition mechanism for students to visualize their learning performance and compare their performance with peers. By incorporating APAMP into programming courses, students can master programming skills through repeated practice, and their enthusiasm for learning programming can also be encouraged by peer competition. To evaluate the effects of APAMP on the learning performance of students with programming language learning and novice students, a quasi-experiment was conducted in a high school. The experimental results showed that the learning achievement of the two groups of students improved significantly. Moreover, the learning attitude of students in the experienced group improved significantly, with the experienced students benefiting more from the system than the novice students. In fact, the novice students showed a significant decline in learning attitude and learning motivation, which was contrary to our intuition. © 2021 Informa UK Limited, trading as Taylor & Francis Group.

关键词： automated programming assessment systems learning performance mastery learning peer competition programming instruction

来源：评论

学校读者我要写书评

暂无评论

Enhancing Educational Innovation: A Comparative Analysis of Blockchain Adoption Strategies in Smart Learning Environments 8

Enhancing Educational Innovation: A Comparative Analysis of ...

引用

8th International Conference on Informatics and Computing, ICIC 2023

作者： Chakim, Mochamad Heru Riza Ahmad, Daelami Rusilowati, Umi Oganda, Fitra Putri Sanjaya, Yulia Putri Ayu Sunarya, Po Abas University of Raharja Economics and Business Indonesia Commercial Administration Study Program Sekolah Tinggi Ilmu Administrasi Banten Indonesia Pamulang University Management Indonesia University of Raharja Information Systems Indonesia University of Raharja Retail Management Indonesia University of Raharja Faculty of Science and Technology Indonesia

ISBN: (纸本)9798350342604

The recent improvement of traditional education systems in developing countries is supported by the adoption of the latest blockchain technology. This disruptive technology is key to improving accountability and transparency. This study investigates the main factors that influence educational institutions' intention to implement blockchain technology in e-learning. By combining blockchain adoption strategies, smart learning environments, and enhancing educational innovation this study develops an updated model of the technology Acceptance Model. This conceptual model was evaluated and validated using online survey-based structural analysis. The results revealed that the blockchain adoption strategy factor has a significant influence on blockchain adoption in smart learning environments. Other findings also had important significant effects on the adoption of blockchain technology. This research presents an updated technology Acceptance Model for blockchain adoption, providing guidance for decision-makers in developing smart learning environments for educational institutions in developing countries. © 2023 IEEE.

关键词： Blockchain

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：