检索结果-内蒙古大学图书馆

Proceedings of the 2023 4th International Conference on Machine Learning and computer Application

作者： Yiming Luo Rui Zhang Fei Wang Tao Wei Business Schoo The University of Sydney Austialia Computer and information sciences program Harrisburg University of Science and Technology United States Faculty of Science and Technology Beijing Normal University-Hong Kong Baptist University United International College China School of Chemical and Environmental Engineering Sichuan University of Science & Engineering China

ISBN: (纸本)9798400709449

Customer segmentation is an essential area of business analytics today. Accurate customer segmentation is access to improves the efficiency of marketing campaigns and customer satisfaction. This study employs multiple machine learning methods to classify Australian Retail company BIGW's customer segments and first to apply multiple model explanation methods to find insights related to customer segmentation identification. After rigorous comparison and hyperparameter fine-tuning, XGBoost is the most adept for this dataset. We derive three key insights through the model results and model interpretive methods. First, BIGW's primary clientele comprises young families in urban areas who prefer cost-effective products, establishing the foundation of their consumer base. Second, the model result indicates a notable gap in BIGW's understanding of its high-end customers, suggesting an area for immediate attention. Third, a specific customer segment emerges from the data: individuals favoring online shopping, demonstrating high total expenditure but low interest in promotions, representing a high-value segment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Double-SP Method to Enhance Privacy and Security of Smart City Applications

Double-SP Method to Enhance Privacy and Security of Smart Ci...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Nour Mahmoud Bahbouh Abdulelah Alhussain Hassan Hakami Yaser Mohammed Aljohani Adnan Ahmed Abi Sen Ahmad Alkhodre Aeshah Alsughayyir Department of Information and Communication Sciences Granada University Granada Spain Saudi Electronic University Al-Madinah Saudi Arabia YasRef Program Yanbu Saudi Arabia Computing and Information Technology Islamic University Al-Madinah Saudi Arabia Faculty of Computer and Information Systems Islamic University Al-Madinah Saudi Arabia College of Computer Science and Engineering Taibah University Al-Madinah Saudi Arabia

Smart cities promise a lot of well-being to their users in all areas of life through millions of applications and services. Smart services rely heavily on collecting data and the preferences of users. But on the dark side, the users' information is posed to threat and penetration during transmission or stored far in the clouds. Depending on encryption only is not sufficient if the attacker has strong resources or if the attacker is the service provider (SP) itself. In addition, changing data before sending is not a practical solution in many systems because of the adverse impact on the quality of a main service. This research presented a new idea to address the issue of protection. The proposed method enhanced the privacy and security of users' data without affecting the accuracy of service. The core of the suggested solution relies on a knowledge base of services that are managed by experts. Also, the solution depends on fog nodes to measure the level of security and privacy of users' queries without delay. Moreover, the fog nodes manage contact with SPs. Finally, the proposed method divided the SP into two, one for user queries and the other for user data. The simulation and analytical discussion on a practical case in smart cities demonstrated the superiority of the proposed approach over previous methods in the level of protection by maintaining the quality of services, and the resistance to attacks.

关键词： Resistance Privacy Data privacy Machine learning algorithms Smart cities Knowledge based systems Quality of service

来源：评论

学校读者我要写书评

暂无评论

Robust Feature Learning Against Noisy Labels

Robust Feature Learning Against Noisy Labels

引用

IEEE International Conference on Image Processing

作者： Tsung-Ming Tai Yun-Jie Jhang Wen-Jyi Hwang Free University of Bozen-Bolzano NVIDIA AI Technology Center International Intercollegiate Ph.D. Program National Tsing Hua University Department of Computer Science and Information Engineering National Taiwan Normal University

Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples, further learning erroneous associations of data contents to incorrect annotations. To this end, this paper proposes an efficient approach to tackle noisy labels by learning robust feature representation based on unsupervised augmentation restoration and cluster regularization. In addition, progressive self-bootstrapping is introduced to minimize the negative impact of supervision from noisy labels. Our proposed design is generic and flexible in applying to existing classification architectures with minimal overheads. Experimental results show that our proposed method can efficiently and effectively enhance model robustness under severely noisy labels.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Strategic information System Planning in the Industry 4.0 Era: A Systematic Literature Review

Strategic Information System Planning in the Industry 4.0 Er...

引用

Creative Communication and Innovative technology (ICCIT), IEEE

作者： Irfan Mahendra Arief Ramadhan Agung Trisetyarso Edi Abdurachman Muhammad Zarlis Computer Science Program Bina Nusantara University Jakarta Indonesia Information Technology Faculty Nusa Mandiri University Jakarta Indonesia Computer Science Department Bina Nusantara University Jakarta Indonesia

information systems and technology have an important role in building the Company's competitive advantage in facing the Industrial Era 4.0. Strategic information System Planning (SISP) helps companies formulate reliable information systems that are aligned with business strategies. The academic world should contribute in this regard, but currently, the amount of research related to SISP is very limited. This research is a systematic literature review, which aims to find out more about SISP research trends, research motivations and backgrounds, industries that have been handled, and the methods used in developing SISP. This research is expected to be a trigger for the emergence of new research to support the successful development of SISP in companies in various industries. The results of this research show that several topics are widely researched and need to be improved in the future, namely the alignment of IS strategies with business strategies, the development of specific SISPs in various industries, and the reliability of IS strategies by considering the application of the latest information technology, such as blockchain, artificial intelligence, big data, augmented reality, Internet of Things, and cloud computing. In addition, it is also necessary to develop a SISP framework that is more accommodating to changes in the business environment that is increasingly fast, agile, and collaborative, which includes aspects of business architecture, data/information architecture, technology architecture, information system security, governance, and human resources.

关键词： Industries Systematics Bibliographies computer architecture Market research Reliability Security

来源：评论

学校读者我要写书评

暂无评论

Unbiasing on the Fly: Explanation-Guided Human Oversight of Machine Learning System Decisions

arXiv

引用

arXiv 2024年

作者： Mamman, Hussaini Basri, Shuib Balogun, Abdullateef O. Imam, Abdullahi Abubakar Kumar, Ganesh Capretz, Luiz Fernando Department of Computer and Information Sciences Universiti Teknologi PETRONAS Bandar Seri Iskandar Perak32610 Malaysia Department of Management and Information Technology Abubakar Tafawa Balewa University Bauchi740272 Nigeria School of Digital Sciences Universiti Brunei Darussalam BE1410 Brunei Dept. of Electrical & Computer Eng. Western University London Canada MCS Program Yale-NUS College 138527 Singapore

The widespread adoption of ML systems across critical domains like hiring, finance, and healthcare raises growing concerns about their potential for discriminatory decision-making based on protected attributes. While efforts to ensure fairness during development are crucial, they leave deployed ML systems vulnerable to potentially exhibiting discrimination during their operations. To address this gap, we propose a novel framework for on-the-fly tracking and correction of discrimination in deployed ML systems. Leveraging counterfactual explanations, the framework continuously monitors the predictions made by an ML system and flags discriminatory outcomes. When flagged, post-hoc explanations related to the original prediction and the counterfactual alternatives are presented to a human reviewer for real-time intervention. This human-in-the-loop approach empowers reviewers to accept or override the ML system decision, enabling fair and responsible ML operation under dynamic settings. While further work is needed for validation and refinement, this framework offers a promising avenue for mitigating discrimination and building trust in ML systems deployed in a wide range of domains. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Performance Improvement of Clustering Affinity Propagation Method using Principal Component Analysis 4

Performance Improvement of Clustering Affinity Propagation M...

引用

4th International Conference on Computing and Applied Informatics 2019, ICCAI 2019

作者： Simanullang, Jasael Zarlis, Muhammad Muisa Zamzami, Elviawaty Graduate Program of Computer Science Indonesia Faculty of Computer Science and Information Technology Indonesia Universitas Sumatera Utara Medan Indonesia

Affinity Propagation Method it is necessary to modify the algorithm by using Principal Component Analysis (PCA). PCA method is used to reduce the attributes or characteristics that are less influential on the data so that the most influential attributes are obtained to then be carried out the clustering process with Affinity Propagation. The comparison results of the PCA + AP grouping model have better performance than the conventional AP grouping model. This is justified because the number of iterations and clusters produced by the PCA + AP clustering model does not change and converges when there are 8 optimal cluster clusters. While the performance of conventional clustering models produces an optimal number of clusters from 14 clusters with a significant number of iterations. So it can be concluded that the PCA + AP grouping model is suitable for the Air Quality dataset because it produces an optimal number of clusters and iterations of 8 clusters. The comparison results of the PCA + AP grouping model have better performance than the conventional AP grouping model. This is justified because the number of iterations and clusters produced by the PCA + AP clustering model does not change and converges when the optimal number of clusters is 5 clusters. While the performance of conventional clustering models produces a suboptimal number of 10 clusters with a significant number of iterations. So it can be concluded that the PCA + AP grouping model is suitable for the Water Quality Status dataset because it produces an optimal number of clusters and 5 cluster repetitions. © Published under licence by IOP Publishing Ltd.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Mobile Application Implementation as Agriculture 4.0 Strategy for Sugarcane Yield Prediction

Mobile Application Implementation as Agriculture 4.0 Strateg...

引用

HCI and UX Conference in Indonesia (CHIuXiD), International

作者： Hangger Gahara Mawandha Reza Rahutomo Teddy Suparyanto Bens Pardamean Faculty of Agricultural Technology Institut Pertanian Stiper Yogyakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350304084

ISBN: (纸本)9798350304091

information engineering strategies play a significant and transformative role in shaping the landscape of digital agriculture. It drives innovation and efficiency in modern farming practices, with a specific focus on enhancing the value of agricultural commodities, such as sugarcane. The application of mobile technology plays a crucial part in achieving increased sugarcane productivity. Mobile applications, equipped with advanced developer features, offer rapid and user-friendly access to vital information. Traditional methods of estimating sugarcane production relied on manual data recording on paper, followed by data transfer to computer systems, typically managed by sugar factory junior plant officers. This conventional approach presents several inherent weaknesses, including time and effort intensiveness during data recording and entry. Additionally, the potential for errors in calculation and data input is a concern. The storage capacity for paper-based documents is finite, and farmers are often unable to autonomously assess their production potential. The objective of this research is to confront these obstacles by creating a sugarcane production application for Android. This application functions as an information engineering approach focused on forecasting sugarcane yields for plantation owners and their assistants. The development procedure adhered to the systematic waterfall method, following the principles of the Software Development Life Cycle (SDLC) model. Data collection was carried out through observations, while interviews with junior plant officers provided valuable insights into sugarcane estimation techniques. Analysis involved the synthesis of observational and interview data to inform the design of the application’s interface and algorithmic system. The resulting application significantly simplifies the process of estimating production potential for farmers, enabling them to access sugarcane productivity data during harvest. Consequently, sugar

关键词： Productivity Operating systems Estimation Production facilities Raw materials Mobile applications Recording

来源：评论

学校读者我要写书评

暂无评论

Mapping Tokenomics Arrangements to Expand the Digital Nomad Ecosystem 26

Mapping Tokenomics Arrangements to Expand the Digital Nomad ...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： De Almeida, Marcos Antonio Correia, António De Souza, Jano Moreira Schneider, Daniel Rio de Janeiro Brazil Inesc Tec University of Trás-os-Montes e Alto Douro Vila Real Portugal University of Nebraska at Omaha College of Information Science & Technology OmahaNE68182 United States Postgraduate Program in Informatics PPGI/UFRJ Rio de Janeiro Brazil Tércio Pacitti Institute of Computer Applications and Research NCE/UFRJ Rio de Janeiro Brazil

ISBN: (纸本)9798350331684

The Massification of remote work, in response to the COVID-19 pandemic, has been causing significant changes in productive and working arrangements, both for individuals, organizations, and society. At the level of personal life philosophy, for example, this transformation can be evidenced in the dissemination of digital nomadism values such as work/leisure balance among corporate workers. On the other hand, at the level of gig/crowd work platforms, the emergence of tensions may indicate the exhaustion of sociotechnical design models adopted by big techs. We show how evidence collected from digital nomads in empirical ethnography studies can inform HCI/CSCWD researchers of design-oriented strands to explore emerging opportunities in new creative digital crypto-economic ecosystems. Finally, we present a proposed research agenda to explore DNs' activities in the crypto-economic ecosystem. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Investigating Author Research Relatedness through Crowdsourcing: A Replication Study on MTurk 26

Investigating Author Research Relatedness through Crowdsourc...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Correia, António Paulino, Dennis Paredes, Hugo Guimarães, Diogo Schneider, Daniel Fonseca, Benjamim Inesc Tec University of Trás-os-Montes e Alto Douro Utad Quinta de Prados Vila Real Portugal University of Nebraska at Omaha College of Information Science & Technology OmahaNE68182 United States Postgraduate Program in Informatics PPGI/UFRJ Rio de Janeiro Brazil Tércio Pacitti Institute of Computer Applications and Research NCE/UFRJ Rio de Janeiro Brazil

ISBN: (纸本)9798350331684

Determining the relatedness of publications by detecting similarities and connections between researchers and their outputs can help science stakeholders worldwide to find areas of common interest and potential collaboration. To this end, many studies have tried to explore authorship attribution and research similarity detection through the use of automatic approaches. Nonetheless, inferring author research relatedness from imperfect data containing errors and multiple references to the same entities is a long-standing challenge. In a previous study, we conducted an experiment where a homogeneous crowd of volunteers contributed to a set of author name disambiguation tasks. The results demonstrated an overall accuracy higher than 75% and we also found important effects tied to the confidence level indicated by participants in correct answers. However, this study left many open questions regarding the comparative accuracy of a large heterogeneous crowd with monetary rewards involved. This paper seeks to address some of these unanswered questions by repeating the experiment with a crowd of 140 online paid workers recruited via MTurk's microtask crowdsourcing platform. Our replication study shows high accuracy for name disambiguation tasks based on authorship-level information and content features. These findings can be of greater informative value since they also explore hints of crowd behavior activity in terms of time duration and mean proportion of clicks per worker with implications for interface and interaction design. © 2023 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Improving the Performance of K-Nearest Neighbor Algorithm by Reducing the Attributes of Dataset Using Gain Ratio 4

Improving the Performance of K-Nearest Neighbor Algorithm by...

引用

4th International Conference on Computing and Applied Informatics 2019, ICCAI 2019

作者： Hasdyna, N. Sianipar, B. Zamzami, E.M. Graduate Program of Computer Science Universitas Sumatera Utara Medan20155 Indonesia Department of Information Technology Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan20155 Indonesia

Data that has many attributes or higher dimensions will affect the performance of the K-NN classification algorithm. In this study, the Gain Ratio implemented for selecting and reducing the dataset attributes to form a new dataset for the classification process is carried out with the K-NN. The dataset used in this study are the Breast Cancer Coimbra dataset and Hepatitis C Virus dataset obtained from the UCI Machine Learning Repository. The results showed that the Breast Cancer Coimbra dataset, Gain Ratio can improve the performance of K-NN with average value 0.535596 TPR, TNR = 1, NPV = 0.608279, FNR = 1, FOR = 0.391721, Accuracy = 72.85%. In Hepatitis C Virus dataset also managed to improve the performance of K-NN with average value TPR = 0.665596, TNR = 0,876667, NPV=0,738279, FNR=0,88, FOR=0,521721, and Accuracy=86,25%. © Published under licence by IOP Publishing Ltd.

关键词： Nearest neighbor search

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：