检索结果-内蒙古大学图书馆

International Conference on Machine Vision (ICMV)

作者： Mariam Rehman Vatcharapon Esichaikul Computer Science and Information Management Program Asian Institute of Technology Pathum Thani Thailand

Many organizations collect large amounts of data to support their business and decision making processes. The data collected from various sources may have data quality problems in it. These kinds of issues become prominent when various databases are integrated. The integrated databases inherit the data quality problems that were present in the source database. The data in the integrated systems need to be cleaned for proper decision making. Cleansing of data is one of the most crucial steps. In this research, focus is on one of the major issue of data cleansing i.e. ¿duplicate record detection¿ which arises when the data is collected from various sources. As a result of this research study, comparison among standard duplicate elimination algorithm (SDE), sorted neighborhood algorithm (SNA), duplicate elimination sorted neighborhood algorithm (DE-SNA), and adaptive duplicate detection algorithm (ADD) is provided. A prototype is also developed which shows that adaptive duplicate detection algorithm is the optimal solution for the problem of duplicate record detection. For approximate matching of data records, string matching algorithms (recursive algorithm with word base and recursive algorithm with character base) have been implemented and it is concluded that the results are much better with recursive algorithm with word base.

关键词： Databases Detection algorithms computer science information management Decision making Machine vision Prototypes Customer satisfaction Government Protection

来源：评论

学校读者我要写书评

暂无评论

An agent interaction model for performance enhancement of network system

引用

WSEAS Transactions on computers 2005年第5期4卷 440-448页

作者： Suesaowaluk, Poonphon Sadananda, Ramakoti Computer Science and Information Management Program School of Advanced Technologies Asian Institute of Technology Patumthani 12120 Thailand

We envisage a scenario where a system of network computer initially with random loads, exchange jobs to balance load among themselves to enhance their individual performance and to provide augmented quality of service (QoS) to the user community. We model the individual machines as agents interacting with one another. The agents have beliefs and aspirations. The aspiration of an agent is seek load from other, when it did not have enough to begin with, and sheds the same of it finds itself excessively loaded. This paper develops the concept with a design of a utility function to reflect the agent aspiration. We also propose a measure of load imbalance between networked machines. Negotiation mechanism is developed for exchange of jobs between agents. We report our result of the simulation with two machines and extend the same for three machines. The extension of the idea to a large number of machines entail coming to term with complexity in form of administrative overloads. We discuss the "small word" concept in the content of a simulation massively large number of machines interconnected.

关键词： Software agents

来源：评论

学校读者我要写书评

暂无评论

CALE: A context-aware living environment based on Zigbee sensor network

CALE: A context-aware living environment based on Zigbee sen...

引用

International Conference on Mobile Ad-hoc and Sensor Networks

作者： Yu, Kun-Ming Liou, Jian-Yuan Yeh, Bo-Han Yu, Chang Wu Tien, Ching-Cheng Wang, Chih-Hu Wang, Ping-Yu Department of Computer Science and Information Engineering Chung Hua University Taiwan Ph.D. Program of Technology Management Chung Hua University Taiwan Department of Electrical Engineering Chung Hua University Taiwan

ISBN: (纸本)9780769543154

The paper employed some independently developed sensors based on the Octopus X platform to build a Zigbee-based Sensor Networks. Also, we implemented a Location-aware living environment by deploying the developed Zigee-based sensor. Besides, through the created window console interface, the sensed data can be transmitted and transformed to the database for further utilized. Moreover, by the devised Web interface, the update request data can be observed efficiently and responded effectively to any situations. © 2010 IEEE.

关键词： Zigbee

来源：评论

学校读者我要写书评

暂无评论

information Technology Challenges for Integrated Governance, Risk and Compliance (GRC) 1

Information Technology Challenges for Integrated Governance,...

引用

1st International Conference on Smart Technology, Applied Informatics, and Engineering, APICS 2022

作者： Mahendra, Irfan Meyliana Prabowo, Harjanto Hidayanto, Achmad Nizar Bina Nusantara University Computer Science Program Jakarta11480 Indonesia Nusa Mandiri University Technology Information Faculty Jakarta11450 Indonesia Bina Nusantara University Information System Department Jakarta11480 Indonesia Bina Nusantara University Management Departement Jakarta11480 Indonesia Universitas Indonesia Faculty of Computer Science Depok16424 Indonesia

ISBN: (数字)9781665489850

ISBN: (纸本)9781665489850

Integrated GRC is an area of concern for organizations today. Integrated GRC provides benefits for increasing competitiveness and organizational excellence, realizing effectiveness, efficiency, and optimization, as well as supporting the prevention of corruption and fraud. information technology has a very important role in determining the success of implementing an integrated GRC in the organization. However, based on the research conducted, adequate research on the application of information technology in the implementation of integrated GRC is still lacking. In this paper, a study will be conducted on trends and research gaps related to the application of information technology in the current integrated GRC implementation. The conclusion of this study states that there is a great opportunity for wider research on the opportunities and challenges of implementing the latest information technology such as blockchain, artificial intelligence, big data, and cloud computing to support the effectiveness and success of integrated GRC implementation. © 2022 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Comparing the Effect of Attention Mechanism and Aspect Embedding on the Performance of Long Short-term Memory Model for Aspect-Based Sentiment Analysis

Comparing the Effect of Attention Mechanism and Aspect Embed...

引用

2023 International Conference on computer science, information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Murad, Dina Fitria Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

The attention mechanism is one of the key enablers which have positioned transformer models as the state-of-the-art models in Natural Language Processing. By having the attention mechanism, the first version (vanilla) transformer model can retrieve the hidden state but at the same time can maintain a low requirement on the context vector dimension by selectively choosing to which encoder hidden states to give priority attention. The objective of this study is to evaluate the effect of modified Long Short-term Memory models architecture on the model performance as a predictive model. The first model is modified by adding an attention mechanism to its architecture;whilst, the second model is modified by adding additional input to its architecture. The performance of both models is compared by assigning each model the same task: to address the aspect-based sentiment analysis task. The experiment results show that adding an attention mechanism is not significantly increase the performance of the Long Short-term Memory model in comparison to adding input to the same model. In particular, the average training accuracy of the former model is 0.885;whilst, the average training accuracy of the latter model is 0.942. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Restaurant Customer Feedback Sentiment Analysis using Aspect Embedding Long Short-term Memory Model

Restaurant Customer Feedback Sentiment Analysis using Aspect...

引用

2023 International Conference on computer science, information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Fitria Murad, Dina Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

In the past ten years, there has been a proliferation of unstructured textual data from a variety of fields, allowing for the analysis of the sentiment polarity of the text authors in each of those datasets. To analyze sentiment polarity from unstructured data, machine learning tasks such as aspect-based sentiment analysis are used. The public dataset of restaurant patron feedback was used as the input for this study's empirical results of aspect-based sentiment analysis utilizing the Aspect Embedding Long Short-Term Memory model. The primary experiment's results show that the aspect embedding long short-term memory model can predict aspect sentiment polarization from customer feedback to restaurant service and aspect text representation (aspect text embedding) as input with excellent performance. For example, the Aspect Embedding Long Short-term Memory model, which uses ReLU as its activation function in the Dense layer tends to achieve higher performance (0.97 average accuracies) than the same model equipped with Sigmoid, and Tanh functions which achieve 0.954 and 0.956 average training accuracy respectively. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Aspect-based Sentiment Analysis using Long Short-term Memory Model for Leveraging Restaurant Service management

Aspect-based Sentiment Analysis using Long Short-term Memory...

引用

2023 International Conference on computer science, information Technology and Engineering, ICCoSITE 2023

ISBN: (纸本)9798350320954

In general, the hospitality industry has been acknowledged as a major sector that gives a high contribution to economic development in many countries including Indonesia. For that reason, many initiatives have been implemented to help the growth of the hospitality industry in many countries including Indonesia to rebound from the harsh impact of the Covid-19 Pandemic. One such initiative is improving restaurant services as the main sector of the hospitality industry. This paper presents empirical results of sentiment analysis as a means to assess the quality of restaurant services as the first step to improving service quality. In particular, this study explores the aspect-based sentiment analysis method to identify some aspects of restaurant service which need improvement by learning the polarity of customers toward the restaurant services without having to meet the customers directly. By using the aspect-based sentiment analysis method, the customer sentiments comprising opinions, sentiments, evaluations, attitudes, and emotions from restaurant service can be analyzed using customers' online reviews as input. The main experiment findings showed that the Long Short-term Memory model can achieve high performance in predicting aspect polarization in restaurant service reviews. Other findings suggest that Sigmoid as an activation function achieved 0.97 average training accuracy and 0.69 average testing accuracy giving a better performance to the model in comparison to ReLU, Tanh, and ELU activation functions. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Personal Health Record in FHIR Format Based on Blockchain Architecture 9th

Personal Health Record in FHIR Format Based on Blockchain Ar...

引用

9th International Conference on Frontier Computing, FC 2019

作者： Kung, Hsin Hua Cheng, Ya-Fang Lee, Hsiu-An Hsu, Chien-Yeh Department of Information Management National Taipei University of Nursing and Health Sciences Taipei Taiwan Department of Computer Science and Information Engineering Tamkang University New Taipei City Taiwan Master Program in Global Health and Development Taipei Medical University Taipei Taiwan

ISBN: (纸本)9789811532498

Until the present moment, most of the medical records are only stored in hospitals. The hospital systems are still in Electronic Medical Records and haven’t developed into Personal Health Records yet to let people manage their own health records. If there is no medical record exchange between hospitals, it may cause a lot of medical resources waste and medical problems. The medical data cannot be exchanged smoothly because of different data standards, data inconsistency, and privacy of patient data. However, Blockchain technology can solve data consistency problems, privacy issues, and centralization problems. So use Blockchain technology to establish a PHR system that people can manage by themselves and use FHIR of National Medical information Standard as the data format. People can share their PHR with doctors at any time and at any place, and doctors can give a more appropriate and accurate diagnosis. We use Ethereum’s private Blockchain. The system encrypts the PHR with an asymmetric key and then uses the Hash function to generate a hash value and write them into the block to ensure data consistency and security. The user can also select the record sharing with others. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

Establish a Medical Image Analysis and Identification Platform 9th

Establish a Medical Image Analysis and Identification Platfo...

引用

9th International Conference on Frontier Computing, FC 2019

作者： Chen, Hsiao-Hsuan Chen, Yin-Chen Lee, Hsiu-An Hsu, Chien-Yeh Department of Information Management National Taipei University of Nursing and Health Sciences Taipei Taiwan Department of Computer Science and Information Engineering Tamkang University New Taipei City Taiwan Master Program in Global Health and Development Taipei Medical University Taipei Taiwan

ISBN: (纸本)9789811532498

The proportion of China’s 65-year-old population has increased year by year. As we enter old age, people’s average life expectancy increases year by year. The risk of disease in the elderly population increases. According to the statistics of the Ministry of Health and Welfare of Taiwan, most people over the age of 65 suffer from cancer and heart disease. Pneumonia, cerebrovascular disease, and diabetes. With medical advancement, more and more disease characteristics can be found in medical imaging. With the development of technology, the higher the resolution of the image, the more information that can be contained, and the doctor will spend more time marking and diagnosing. There is currently no open imaging training and recognition platform for users to use, so this study uses deep learning CNN technology to construct an image analysis and recognition platform with analysis and recognition interface. In the future, retraining and batch identification capabilities can be added to complete the integrity of the platform. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

The Evaluation of Trust Towards The Intention to Use of Blockchain-Based Crowdwork Systems (Case Study of Creative Industry) 8

The Evaluation of Trust Towards The Intention to Use of Bloc...

引用

8th International Conference on information management and Technology, ICIMTech 2023

作者： Hartono, Sugiarto Prabowo, Harjanto Meyliana Hidayanto, Achmad Nizar School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Binus Business School Undergraduate Program Bina Nusantara University Management Department Jakarta11480 Indonesia Universitas Indonesia Faculty of Computer Science Depok Indonesia

ISBN: (纸本)9798350326093

Current crowdwork research still has issues related to trust. Workers and employers do not know each other, so problems related to trust will arise. This trust issue will influence the desire to use the crowdwork system. This study will evaluate trust in the intention to use blockchain-based crowdwork systems in creative industries. The methodology used is a quantitative approach (questionnaire) which is distributed to 200 respondents consisting of workers and employers. After that, testing the inner and outer models was carried out. The results obtained are technology, risk, and reputation which have the greatest impact on trust. The use of blockchain technology can minimize risks when using a crowdwork system, such as data that cannot be changed, data tracing can be done, and so on. The rating and review features are also important to be able to find out the user's reputation in the system. © 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：