检索结果-内蒙古大学图书馆

2023 International Conference on science, Engineering and Business for Sustainable Development Goals, SEB-SDG 2023

作者： Akinrotimi, Akinyemi Omololu Ogundokun, Roseline Oluwaseun Mabayoje, Modinat Abolore Oyekunle, Rafiat Ajibade Adebiyi, Marion Olubunmi Augustine University Department of Mathematics Sciences Computer Science Program Ilara-Epe Epe Nigeria Kaunas University of Technology Department of Multimedia Engineering Lithuania Landmark University Omu Aran Sdg 4. Quality Education Nigeria University of Ilorin Department of Computer Science Ilorin Nigeria University of Ilorin Department of Information and Communication Ilorin Nigeria Landmark University Omu-Aran Department of Computer Science Omu Aran Nigeria

ISBN: (纸本)9798350324785

The financial backbone of every telecommunications company is strictly made up of the number of customers patronizing the organization. Due to the high level of competition amongst existing telecommunication companies, customers sometimes leave, dropping the services of a particular one for the other. Predicting which subscribers may want to leave a telecommunications company and providing solutions to keep them from doing so, are the main objectives of customer churn prediction. Churn prediction helps classify consumers who are likely to move from one business to another. The ability to foresee churners before they leave has been increasingly useful in recent years, especially in light of increased competition among communications carriers. To compute churners for telecommunications providers, the study described in this paper used oversampling techniques to balance churn data and applied the dimensionality reduction technique to discover optimal features with a strong predictive ability for detecting would-be churners and non-churners. The model used Logistic Regression and the Naïve Bayes Classification Algorithm to implement comparative classification strategies. The performance levels of these strategies were compared using a Telecommunications Customer Churn data set, as well as performance metrics such as accuracy, sensitivity, and specificity. The Naïve Bayes Algorithm proves more efficient than its counterpart giving higher positive rate detection and a lower negative rate detection. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Recommendation News for Joumalist Based on Twitter Data Using CNN 6

Recommendation News for Joumalist Based on Twitter Data Usin...

引用

6th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2022

作者： Harvy, Ikrar Girsang, Abba Suganda Saragih, Melva Hermayanty Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia Management Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798350399615

Getting the update news fast is important for journalist. This study uses Twitter data which is fast and rich information for get the update news and useful for journalist. This study starts from collecting data from Twitter, then predicting the category of tweet using convolution neural network (CNN) algorithm. With convolution neural network data, Twitter can categorize 10 news categories that mention news to official Twitter media on Twitter social media. Scenario data in predicting news by dividing the data based on 70% training, 15% validation, and 15% testing. Then the data is converted into vector form where the convolution neural network predicts the data in vector form. The results show that, the convolution neural network is able to conduct the good performance based on the values of accuracy, precision, recall and f1 score. It also compares by the other methods. © 2022 IEEE.

关键词： classification news convolution neural network deep learning journalist Social media

来源：评论

学校读者我要写书评

暂无评论

A systematic literature review of machine learning application in COVID-19 medical image classification

引用

Procedia computer science 2023年 216卷 749-756页

作者： Tjeng Wawan Cenggoro Bens Pardamean Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia. Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia. Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia.

Detecting COVID-19 as early as possible and quickly is one way to stop the spread of COVID-19. Machine learning development can help to diagnose COVID-19 more quickly and accurately. This report aims to find out how far research has progressed and what lessons can be learned for future research in this sector. By filtering titles, abstracts, and content in the Google Scholar database, this literature review was able to find 19 related papers to answer two research questions, i.e. what medical images are commonly used for COVID-19 classification and what are the methods for COVID-19 classification. According to the findings, chest X-ray were the most commonly used data to categorize COVID-19 and transfer learning techniques were the method used in this study. Researchers also concluded that lung segmentation and use of multimodal data could improve performance.

关键词： COVID-19 classification disease machine learning medical images

来源：评论

学校读者我要写书评

暂无评论

The High Economic Value for Videos in a YouTube Channel by Communication using Digital social media (Case Study: Successful Videos about A Particular Motorcycle Group in a YouTube Channel) 23

The High Economic Value for Videos in a YouTube Channel by C...

引用

6th International Conference on computers in Management and Business, ICCMB 2023

作者： Pane, Murty Magda Siregar, Christian Sriyanto, Hari Character Building Development Center School of Computer Science Computer Science Department Bina Nusantara University Jakarta Indonesia Character Building Development Center Mass Communication Program Communication Department Faculty of Digital Communication and Hotel and Tourism Bina Nusantara University Jakarta Indonesia Character Building Development Center Information System Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9781450398046

This research's objective is to describe the sustainable activities of a particular motorcycle club (TP) by delivering reciprocal humor and showing nice friendship on social media from a business perspective, especially from a business psychology perspective. The research used a qualitative method by observations in seven periods for seven tour opportunities. Their high amount of interactive communication has led them into the most popular motorcycle group (recognized by the high number of views, like expressions, and positive comments on the YouTube channel and Instagram) which has also led it to a higher economic value. Their particular cohesiveness and engagement were transmitted and deployed in their internal communications in the videos that influence the netizens and the business world positively through their reciprocal humor and nice friendship. © 2023 ACM.

关键词： Motorcycles

来源：评论

学校读者我要写书评

暂无评论

WORDS ARE ALL YOU NEED? LANGUAGE AS AN APPROXIMATION FOR HUMAN SIMILARITY JUDGMENTS 11

WORDS ARE ALL YOU NEED? LANGUAGE AS AN APPROXIMATION FOR HUM...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Marjieh, Raja van Rijn, Pol Sucholutsky, Ilia Sumers, Theodore R. Lee, Harin Griffiths, Thomas L. Jacoby, Nori Department of Psychology Princeton University United States Max Planck Institute for Empirical Aesthetics Germany Department of Computer Science Princeton University United States Max Planck Institute for Cognitive and Brain Sciences Germany

Human similarity judgments are a powerful supervision signal for machine learning applications based on techniques such as contrastive learning, information retrieval, and model alignment, but classical methods for collecting human similarity judgments are too expensive to be used at scale. Recent methods propose using pre-trained deep neural networks (DNNs) to approximate human similarity, but pre-trained DNNs may not be available for certain domains (e.g., medical images, low-resource languages) and their performance in approximating human similarity has not been extensively tested. We conducted an evaluation of 611 pre-trained models across three domains - images, audio, video - and found that there is a large gap in performance between human similarity judgments and pre-trained DNNs. To address this gap, we propose a new class of similarity approximation methods based on language. To collect the language data required by these new methods, we also developed and validated a novel adaptive tag collection pipeline. We find that our proposed language-based methods are significantly cheaper, in the number of human judgments, than classical methods, but still improve performance over the DNN-based methods. Finally, we also develop 'stacked' methods that combine language embeddings with DNN embeddings, and find that these consistently provide the best approximations for human similarity across all three of our modalities. Based on the results of this comprehensive study, we provide a concise guide for researchers interested in collecting or approximating human similarity data. To accompany this guide, we also release all of the similarity and language data, a total of 206,339 human judgments, that we collected in our experiments, along with a detailed breakdown of all modeling results. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Word reuse and combination support efficient communication of emerging concepts

arXiv

引用

arXiv 2024年

作者： Xu, Aotao Kemp, Charles Frermann, Lea Xu, Yang Department of Computer Science University of Toronto Canada School of Computing and Information Systems University of Melbourne Australia School of Psychological Sciences University of Melbourne Australia Cognitive Science Program University of Toronto Canada

A key function of the lexicon is to express novel concepts as they emerge over time through a process known as lexicalization. The most common lexicalization strategies are the reuse and combination of existing words, but they have typically been studied separately in the areas of word meaning extension and word formation. Here we offer an information-theoretic account of how both strategies are constrained by a fundamental tradeoff between competing communicative pressures: word reuse tends to preserve the average length of word forms at the cost of less precision, while word combination tends to produce more informative words at the expense of greater word length. We test our proposal against a large dataset of reuse items and compounds that appeared in English, French and Finnish over the past century. We find that these historically emerging items achieve higher levels of communicative efficiency than hypothetical ways of constructing the lexicon, and both literal reuse items and compounds tend to be more efficient than their non-literal counterparts. These results suggest that reuse and combination are both consistent with a unified account of lexicalization grounded in the theory of efficient communication. © 2024, CC BY-NC-ND.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Neurocognitive assessment under various human-robot teaming environments

Neurocognitive assessment under various human-robot teaming ...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Anna L. Packy Jayesh Jayahankar Arya Teymourlouei Joshua Stone Hyuk Oh Garrett E. Katz James A. Reggia Rodolphe J. Gentili Neuroscience and Cognitive Science Program University of Maryland College Park USA Department of Computer Science University of Maryland College Park USA Department of Electrical & Computer Engineering University of Maryland College Park USA Department of Kinesiology University of Maryland College Park USA Department of Electrical Engineering & Computer Science Syracuse University Syracuse USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Human-robot teaming has become increasingly important with the advent of intelligent machines. Prior efforts suggest that performance, mental workload, and trust are critical elements of human-robot dynamics that can be altered by the robot’s behavior. Most prior human-robot teaming studies used behavioral analyses, but a limited number used neural markers, without the use of physical robots and complex tasks. Here we combine behavioral and EEG cortical dynamics to examine cognitive-motor processes when individuals complete a complex task under various team environments with a robot. The results revealed that altering the robot quality affected both behavioral and EEG dynamics. Task completion with an experienced robot led to greater team performance and human trust along with lower mental workload compared to an inexperienced teammate or when individuals performed alone. EEG changes suggest that different attentional processes were engaged when humans worked with the robot and performed alone, and that visual processing was more prominent when teaming with an inexperienced teammate. This work can inform human cognitive-motor processes and the design of robotic controllers in human-robot teams.

关键词： Visualization Process control Humanoid robots Collaboration Human factors Control systems Electroencephalography Behavioral sciences Engineering in medicine and biology Robots

来源：评论

学校读者我要写书评

暂无评论

TransMorpher: A Phonologically Informed Transformer-based Morphological Analyzer

TransMorpher: A Phonologically Informed Transformer-based Mo...

引用

2022 International Conference and Workshop on Agglutanative Language Technologies as a Challenge of Natural Language Processing, ALTNLP 2022

作者： Şahin, Karahan Atlamaz, Ümit Cognitive Science Program Boğaziçi University İstanbul Turkey Department of Linguistics Boğaziçi University İstanbul Turkey

We introduce TransMorpher, a phonologically informed Transformer-based morphological analyzer that returns disambiguated morphological parses. TransMorpher consists of a phonological normalization module (inspired by the modular architecture widely adopted in the field of Generative Linguistics), a character-based encoder with multi-head self-attention for encoding words, and a pre-trained language model for encoding context, and a decoder with multi-head self-attention. The language-specific phonological normalization module maps phonological variants of morphemes into unique abstract representations. Normalized words are fed to the word encoder, whose output representations are concatenated with the contextual representation of each word obtained from the pre-trained model. The concatenated representations are then fed to the decoder, which auto-regressively generates a single disambiguated morphological parse for each word. We evaluate TransMorpher on Turkish, an agglutinative language with rich morpho-phonological variation in a relatively low-resource setting, and obtain promising results with 85% accuracy. Our experiments show that phonological normalization contributes to a 5% gain in tag accuracy and 10% in lemma accuracy. We also tested our model without the phonological normalization module on Danish, Russian, and Finnish in low-resource contexts and achieved acceptable accuracy rates. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Exploring User Attitudes and Innovative System Design for Remote Lighting Control Systems in Thailand's Creative Industries

Exploring User Attitudes and Innovative System Design for Re...

引用

2024 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2024

作者： Jeerasottikule, Thammanoon Cooharojananone, Nagul Atchariyachanvanich, Kanokwan Technopreneurship and Innovation Management Program Graduate School Chulalongkorn University Bangkok Thailand Department of Mathematics and Computer Science Faculty of Science Chulalongkorn University Bangkok Thailand School of Information Technology King Mongkut's Institute of Technology Ladkrabang Bangkok Thailand

ISBN: (纸本)9798350386097

In this paper, the authors investigate the current state of the lighting design and control sector in Thailand's creative industry. The government aims to promote the creative industry as a key source of income, but there needs more skilled professionals in the industry. The authors have found that successful cases have used the Internet for remote controlling in the creative industry in other countries. Therefore, the paper will explore the potential of using technology to improve professional efficiency and assess the feasibility of implementing remote lighting control systems via the Internet with Thai lighting designers and lighting console operators. Data will be collected through qualitative in-depth interviews and quantitative surveys. The results have shown a promising acceptance rate of wireless devices for lighting control due to their mobility, flexibility, cost-effectiveness, and positive attitudes toward adopting Internet technology. The authors have also proposed a concept design for an internet-based control system tailored to Thai users, focusing on simplicity, ease of connection, and user-friendliness to accommodate those with limited network configuration knowledge. The proposed system aims to reduce professionals, save time, and increase convenience, leveraging Thailand's extensive wireless internet coverage. These systems could significantly benefit Thailand's creative industry by addressing the shortage of skilled professionals and improving efficiency. © 2024 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of Recent Trends and Challenges in Digital Twin Implementation 10

A Systematic Literature Review of Recent Trends and Challeng...

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Arin, Ikrar Adinata Meyliana Warnars, Harco Leslie Hendric Spits Murad, Dina Fitria Bina Nusantara University BINUS Graduate Program Doctor of Computer Science Computer Science Department Jakarta Indonesia School of Information Systems Bina Nusantara University Information System Department Jakarta Indonesia Bina Nusantara University BINUS Online Learning Information Systems Department Jakarta Indonesia

ISBN: (纸本)9798350339543

This paper reviews the latest trends and challenges in implementing digital twin technology. A digital twin is a tool used in various industries to improve efficiency, optimize processes, and enable advanced analysis. The review involved searching major research databases and search engines for articles published between 2018 and 2023. The findings reveal several important trends, including the development of different types of digital twin dimensions, each with its own advantages and limitations. The benefits of digital twin implementation include improved decision-making, increased productivity, and operational efficiency. However, there are challenges, such as data integration, security and privacy concerns, a lack of standardization, and the need for experts to effectively design and operate digital twins. The implications of these trends and challenges are discussed regarding their impact on the successful adoption and implementation of digital twin technology. The review also highlights the need to address these challenges and explore new approaches for maximizing the benefits of digital twin technology. Overall, this comprehensive review is a valuable resource for researchers, practitioners, and organizations seeking to understand the current landscape, identify areas for improvement, and make informed decisions when implementing digital twin technology. © 2023 IEEE.

关键词： Decision making

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：