检索结果-内蒙古大学图书馆

Information Technology Research and Innovation (ICITRI), International Conference on

作者： Fuad Muftie Muhammad Haris Computer Science Study Program Universitas Nusa Mandiri Jakarta Indonesia

Text data augmentation has been able to improve the performance of models or algorithms for text classification and sentiment analysis. In major cases, rule-based augmentation techniques can be easily applied to various languages such as Indonesia language. However, language model-based augmentation techniques rarely investigated for Indonesian language data. Therefore, this paper presents a text data processing model for Indonesian language, which has limited data, to perform text preprocessing and data augmentation techniques by selectively inserting words based on IndoBERT. This IndoBERT-based augmentation is able to generate data that still retains meaning and sentiment similar to the original data. The testing of this Twitter text dataset yielded results showing that the proposed augmentation technique was able to increase accuracy and outperform the Random Insert augmentation technique.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimization of hyper parameter bandwidth on naïve Bayes kernel density estimation for the breast cancer classification 2

Optimization of hyper parameter bandwidth on naïve Bayes ke...

引用

2nd International Conference on Information and Communications Technology, ICOIACT 2019

作者： Sasongko, Theopilus Bayu Arifin, Oki Al Fatta, Hanif Information Technology Department Faculty of Computer Science Universitas Amikom Yogyakarta Yogyakarta Indonesia Management of Informatics Study Program Economy and Business Departement Politeknik Negeri Lampung Lampung Indonesia

ISBN: (纸本)9781728116556

Cancer is viewed as the most harmful disease in the world. One of the most deadly cancer diseases attacking the women is breast cancer. In this paper, used Naïve Bayes classifier Kernel Density Estimation in breast cancer Wisconsin dataset take from UCI data repository. Naïve Bayes with Kernel Density Estimation was used as it could enable the Naïve Bayes to process the quantitative data. However, the performance of KDE (kernel density estimation) highly depends upon the size of the bandwidth parameter used to control the curve. The problem an accurate choice of parameter bandwidth (h) using trial and error technique requires a long process. A large bandwidth (h) will over-smooth the density and mask the structure in the data, a small bandwidth (h) will yield a density estimate that is spiky and very hard to interpret. The aim of this research is to compare the optimization of grid search parameter with the genetic algorithm to determine the bandwidth parameter (h) on the Naïve Bayes Kernel Density Estimator algorithm. The parameters used to compare the two optimization methods included accuracy, AUC (Area under Curve), and computation time. The experiment results on the test of the significance value on the comparison of grid search and algorithm in determination of the bandwidth parameter (h) naïve Bayes kernel density used Mann-Whitney Test. The result of the significance ranking showed that mean rank of the genetic algorithm accuracy was 489.95 better than the mean value of the rank of grid search accuracy at only 189.05, mean rank of AUC genetic algorithm was 491.82 better than mean rank of AUC grid search only at 187.18. The mean rank of computation time grid search was 243.37 faster than mean rank of computation time genetic algorithm at 435.63. © 2019 IEEE

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Analysis on Handwriting Patterns and Its Relationship to Personality: A Systematical Review

Convolutional Neural Network Analysis on Handwriting Pattern...

引用

International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Zaid Romegar Mair Widya Cholil Evi Yulianti Dona Marcelina Theresiawati Ika Nurlaili Isnainiyah Informatics Study Program Computer and Natural Science Faculty Indo Global Mandiri University Indonesia Informatics Study Program Computer Science Faculty Universitas Pembangunan Nasional Jakarta Indonesia Information System Study Program Computer and Natural Science Faculty Indo Global Mandiri University Indonesia

It can be argued that the Convolutional Neural Network (CNN) used in this research is an efficient algorithm for classifying images based on the end prediction of the path taken. In every plot that is made, there is a similar process for achieving a prediction of the final result. The implementation for each of these procedures follows the steps that are summarized into a flow of analysis stages that can help to develop the application of an algorithm. The initial stage is to take the handwriting from the user which is then pre-processed the image, to eliminate existing noise, and sharpen the contrast, so that the image can be seen clearly. Images will be processed and analyzed using the Convolutional Neural Network model, training will be carried out, with an average training of a dataset of 100 epochs or about 7 to 10 minutes, and labeling on the trained dataset. The accuracy of the training reached 98.89%, as a proportion of the different characteristics of the handwriting sample.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Citrus Limon L. Ripeness Identification Using Feature Extraction of Mean RGB, HSV, LBP and K-Nearest Neighbor

Citrus Limon L. Ripeness Identification Using Feature Extrac...

引用

2023 International Seminar on Application for Technology of Information and Communication, iSemantic 2023

作者： Priyo Utomo, Ade Cahyo Sari, Christy Atika Rachmawanto, Eko Hari Hadi, Heru Pramono Mostafa, Salama A. Al-Dayyeni, Wisam Subhi Talib University of Dian Nuswantoro Study Program in Informatics Engineering Semarang Indonesia University of Dian Nuswantoro Study Program in Information Systems Semarang Indonesia Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Johor Malaysia Ada University School of Information Technologies and Engineering Baku Azerbaijan

ISBN: (纸本)9798350339215

Citrus Limon L. (Lemon) is a type of fruit that is currently widely consumed, because it contains abundant vitamin C, fiber, and antioxidants. This fruit have high potential in the agribusiness sector and is widely cultivated by traditional farmers. However, during harvest time, traditional farmers generally still use manual methods using the human eye in distinguishing the maturity level of lemons which is less efficient because it has a low accuracy. Digital image processing is one solution to this problem. In the research on the classification of lemon maturity levels using digital image processing with the feature extraction method of the Mean RGB, HSV, and LBP methods and the K-Nearest Neighbor classification algorithm in this study, a total of 120 lemon images were used which were divided into 80 training image data and 40 image data. testing. The results of model performance measurements in the form of the highest accuracy level in the Mean RGB method of 100%, the highest accuracy in the HSV method of 98%, and the highest accuracy in the LBP method of 82.5%. © 2023 IEEE.

关键词： Citrus fruits

来源：评论

学校读者我要写书评

暂无评论

Evaluation of E-government services based on social media using structural equation modeling 4

Evaluation of E-government services based on social media us...

引用

4th International Conference on Information Management and Technology, ICIMTech 2019

作者： Nindito, Hendro Madyatmadja, Evaristus Didik Dian Sano, Albert Verasius Information Systems Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia Computer Science Study Program Bina Nusantara Institute of Creative Technology Malang65126 Indonesia

ISBN: (纸本)9781728133331

Today many local governments have provided aspiration services or social media based complaints about the community to participate in giving aspirations and report problems that occur around the area. To improve the usefulness of this service, we conduct research with the aim of evaluating and identifying the factors that affect the service's application. The impact of this study is that the government can provide services according to the wishes of the community, because the model found can be a reference for the government to increase public trust and satisfaction for users of government services. The influence on the adoption of Aspiration Services is explained by using perceptions of trust, attitudes, and intentions of use that refer to technology acceptance models (TAM). Data processing and analysis in our research using the SEM-PLS method (Structural Equation Model-Partial Least Square). The results in this research will present that services applying technology that gain a positive effect on the awareness of usability and benefit for service users. © 2019 IEEE.

关键词： Least squares approximations

来源：评论

学校读者我要写书评

暂无评论

The Application of AGNES Algorithm to Optimize Knowledge Base for Tourism Chatbot 3

The Application of AGNES Algorithm to Optimize Knowledge Bas...

引用

3rd International Conference on Information Management and Technology, ICIMTech 2018

作者： Sano, Albert Verasius Dian Imanuel, Tanto Daud Intanadias Calista, Mega Nindito, Hendro Condrobimo, Andreas Raharto Bina Nusantara Institute of Creative Technology Computer Science Study Program Malang65126 Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9781538658215

Most tourists have limited time and schedule when they are visiting a particular tourism area. One of the main issues faced by those tourists is that they can not make simple queries to search engines about, for example, which sites or places to visit optimally if we only have one day or two-day visit? Search engines are better and better in replying users' queries with relevant answers. However, search engines are not always able to respond queries suited to users' characteristics such as their styles, personalities, knowledge backgrounds, etc. Also, search engines are not as flexible as chatbots in enabling dialogical-communication-queries. This case study aims to respond aformentioned issue by applying hierarchical cluster analysis on a set of tourism sites around Malang city, Malang regency, and Batu city based on AGNES (Agglomerative Nesting) algorithm. The result, then, is fed into chatbot's knowledge base. This chatbot will assist tourists to get information on which possible sites they have to visit optimally if they are under limited vacancy-Time constraints. © 2018 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Teachers and Mobile Learning Perception: Towards a Conceptual Model of Mobile Learning for Training

引用

Procedia - Social and Behavioral sciences 2015年 176卷 425-430页

作者： Iin Karmila Yusri Robert Goodwin Carl Mooney School of Computer science Engineering and Mathematics Flinders University Australia Computer and Networking Engineering Study Program Ujung Pandang State of Polytechnic Indonesia

Before designing and implementing a mobile learning system, it is important to ascertain the perception of future users towards mobile learning since their perception will influence their willingness and readiness to use the system. This research investigated the perception of teachers in Indonesia of mobile learning to ascertain their readiness to engage in mobile learning for training. This study conducted a survey with 308 high school teacher respondents. The results show that teachers in Indonesia had positive perception of mobile learning and were looking forward to engage in mobile learning. Financial and device issues were not obstacles for the teachers to participate in a mobile learning environment. Interestingly, the knowledge and readiness for mobile learning of teachers who taught ICT subject was lower than teachers with mathematics, science, and other subjects. Findings obtained from this study are used as a base for designing and developing a mobile learning system for ICT training for teachers in Indonesia.

关键词： teachers mobile learning perception training system

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and Digital Media Industry Through Social Media Based on OpenAI Technology in the Indonesian Presidential Election 2024 10

Artificial Intelligence and Digital Media Industry Through S...

引用

10th International Conference on Smart Computing and Communication, ICSCC 2024

作者： Pinatih, I Gusti Ayu Agung Dewi Sucitawathi Antari, Ni Putu Bayu Widhi Marijan, Kacung Sakarkar, Gopal Universitas Pendidikan Nasional Public Administration Master's Study Program Denpasar Indonesia Universitas Pendidikan Nasional Public Administration Study Program Denpasar Indonesia Universitas Airlangga Political Department Surabaya Indonesia Dr. Vishwanath Karad MIT World Peace University Department of Computer Science and Applications Pune India

ISBN: (纸本)9798350363104

This research aims to explain the use of social media based on OpenAI technology in the 2024 Presidential Election in Indonesia. The methodology used is based on a descriptive qualitative study with primary and secondary data analysis techniques. Primary data was obtained through interviews with academician in the fields of political marketing and academician in the fields of information technology. Secondary data was obtained through several journal literatures and official websites related to the research topic. The validity of the data is obtained through source triangulation based on interview data from different informants and documentation studies to obtain valid information. This study found that the use of AI-based social media is based on the advantages of OpenAI's more sophisticated technological features, fast and real-time data analysis capabilities, and content visualization capability of image rebranding. © 2024 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Improving University Community Service Communication with Kukerti’s Fuzzy String Matching Chatbot

Improving University Community Service Communication with Ku...

引用

International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Yanti Andriyani Ricki Firyadi Evfi Mahdiyah Aidil Fitriansyah Al Aminuddin Sonya Meitarice Zatin Niqotaini Computer Science Department Information System Study Program University of Riau Pekanbaru Indonesia Computer Science Department Information System Study Program Universitas Pembangunan Nasional Veteran Jakarta Jakarta Indonesia

Efficient communication plays a pivotal role in the success of university community service programs. This study highlights the innovative approach taken by the University of Riau to enhance communication within their community service initiative through the implementation of Kukerti, a cutting-edge chatbot system. Developed specifically for Bahasa Indonesia-speaking users, Kukerti utilizes advanced fuzzy string-matching algorithms to process user inputs and generate relevant responses. In this study, we delve into the deployment and impact of the Kukerti chatbot within the University of Riau’s community service program. We explore its functionality in addressing the common challenge of delayed responses from web administrators, which had previously hindered efficient information retrieval for students and participants. Our research aims to explore how does the implementation of the Kukerti chatbot system with advanced fuzzy string-matching algorithms impact the efficiency of communication and information retrieval within the University of Riau’s community service program. The result shows the implementation of fuzzy string-matching algorithms improves the communication process and the evaluation of the Kukerti chatbot showed that the implementation of fuzzy string-matching has an accuracy rate of 93.33% in providing the answers. By exploring the fuzzy string-matching implementation in the Kukerti chatbot, it is expected to provide further understanding regarding the implementation and encourage other chatbot developers to use it.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Information System Design with Decision Model and Notation (DMN): A Comprehensive Approach to Decision Modeling

Enhancing Information System Design with Decision Model and ...

引用

International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Yanti Andriyani Evfi Mahdiyah Al Aminuddin Zatin Niqotaini Computer Science Department Information System Study Program University of Riau Pekanbaru Indonesia Computer Science Department Information System Study Program Universitas Pembangunan Nasional Veteran Jakarta Jakarta Indonesia

ISBN: (数字)9798331533243

ISBN: (纸本)9798331533250

Business rules are essential for organizational decision-making, shaping the functional requirements of information systems. These rules establish constraints within business processes, influencing decisions like product pricing strategies or supplier compliance evaluations. Integrating business rules into information systems ensures accurate, consistent decisions aligned with organizational objectives. The Decision Model and Notation (DMN) provides a standardized way to model decision logic, capture dependencies, and organize related data elements. DMN enhances the Business Process Model and Notation (BPMN) by incorporating decision-making logic into business process models, making them accessible to both business and technical stakeholders. While the Unified Modeling Language (UML) and BPMN are widely used in system modeling, DMN's practical application for decision modeling remains underexplored. This paper presents a practical implementation of DMN, focusing on its integration with BPMN for a comprehensive approach to information system design. Using a case study, we demonstrate how DMN effectively represents decision logic, showcasing benefits such as improved clarity, flexibility, and reusability. In evaluating different scenarios, Scenario S1 achieved the highest efficiency improvement of 19%, while Scenario S3 showed the least with only a 5% gain. These findings indicate that the adjustments in Scenario S1 can significantly enhance the performance of the Publication Incentive Information System, leading to recommendations for decision-makers to optimize evaluation criteria and processes.

关键词： Visualization Process modeling Unified modeling language Decision making Systems modeling Data models Logic Stakeholders Information systems Business

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：