检索结果-内蒙古大学图书馆

7th International Conference on Information Management and Technology, ICIMTech 2022

作者： Roslynlia Suhartono, Derwin BINUS Graduate Program - Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (数字)9781665450904

ISBN: (纸本)9781665450904

Conventionally, assessing people's personality done by psychology experts requires more time and effort. Hence automatic personality prediction is starting to get noticed by researchers. Nowadays, many people engage themselves in social media platforms, one of which is Twitter. This platform stores actions done in this media which reflect one's personality. This research focuses on improving the performance of personality prediction models based on machine learning algorithms, by augmenting the dataset using Easy Data Augmentation to overcome imbalance dataset, thereafter combining n-grams with POS-tag weighted by TF-IDF. Results show that this method outperforms other machine learning approaches and decreases bias, with a maximum of 72.62% of the best average accuracy and 72.72% best average Fl score using Support Vector Machine classifier. The second-best model is obtained by XGBoost and, lastly, Naive Bayes classifier. Overall, this study shows that data augmentation with the addition of POS-tag feature is evident in improving the performance of personality prediction models. However, larger data is needed. © 2022 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

News Classification Based On News Headline Using SVC Classifier 16

News Classification Based On News Headline Using SVC Classif...

引用

16th International Conference on Telecommunication Systems Services and Applications, TSSA 2022

作者： Leonard, Goldius Sisnadi, Fukriandy Wardhana, Nicholas Vigo Aziz Al-Ghofari, Muhammad Abdul Girsang, Abba Suganda School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Binus Graduate Program - Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665455947

News gives new insight and information from all over the world. News has many categories, such as politic, economy, science, and other common news categories. Every news will have their own category based on its content. The classification of news is usually done manually by inputting the category during the news posting. Some of the categories may be inputted incorrectly. The news classifier can be the solution for problem, but the news classifications out there are usually based on the news content. The classifier will receive the word vector inputs that are taken from the news content and try to classify it into one of certain categories. Unfortunately, news contents can be longer and harder to be processed rather than processing the news headline. The news headline is shorter and packs a decent information for the classifier to find out what category it is. Besides the news headline usage, the classifier also needs to be chosen correctly. In this paper, the SVC model will be tested using the news headline data to classify the news and compare with several other models, such as Linear Regression, Multinomial Naive Bayes, Decision Tree, and Random Forest. The common variables to be compared are the accuracy, recall, and precision to evaluate the SVC model. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Twitter-based Sentiment Analysis for Indonesian Drug Products using Supervised Feature Engineering 5

Twitter-based Sentiment Analysis for Indonesian Drug Product...

引用

5th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2022

作者： Purwandari, Kartika Jeremy, Nicholaus Hendrik Arisaputra, Panji Philip, Samuel Suhartono, Derwin School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665455121

Social media communications offer valuable feedback to firms about their products. Twitter users share their opinions about e-commerce products on social networking sites. This paper reports a study in sentiment classification for Indonesian drug products for automatically classifying Twitter data as expressing positive or negative sentiments or opinions. The study investigates the effectiveness of using a Decision Tree, Support Vector Machine, Random Forest, Na rve Bayes, and Logistic Regression, along with the term frequency-inverse document frequency used to classify 531 tweets into recommended (positive sentiment) and not recommended (negative sentiment). Among all traditional machine learning models, the highest average accuracy value is 88.6 in the RF model and the lowest average accuracy value is 80.2 when using the LR model. Judging from the average accuracy obtained, the DT and RF model used has a considerable performance © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Hate Speech Text Classification Using Long Short-Term Memory (LSTM) 4

Hate Speech Text Classification Using Long Short-Term Memory...

引用

4th IEEE International Conference of computer science and Information Technology, ICOSNIKOM 2022

作者： Ariwibowo, Suminar Girsang, Abba Suganda Diana Bina Nusantara University Binus Graduate Program-Master of Computer Science Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350399073

This paper aims to build hate speech text classification model by applying a combination of LSTM and FastText. The features of hate speech & non-hate speech, target hate speech, and categories of the hate speech. Dataset of those features taken from previous research by Okky Ibrohim. FastText word embeddings is used for formation of text vectors that will be used as input of the LSTM training model. The evaluation results obtained by getting the level of accuracy using confusion matrix. The accuracy value of text classification in this study is 83.52% on the classification of hate speech, 78.44% on the classification of target labels for hate speech, 82.75% on the classification of the label for category of hate speech. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Social Network Analysis of Cryptocurrency using Business Intelligence Dashboard

HighTech and Innovation Journal

引用

HighTech and Innovation Journal 2022年第2期3卷 220-229页

作者： Setyono, Jonathan C. Suryawidjaja, William S. Girsang, Abba S. Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

There are currently more than 10.000 cryptocurrencies available to buy from the online market, with a vast range of prices for each coin it sells. The fluctuation of each coin is affected by any social events or by several important companies or people behind it. The aim of this research is to compare three cryptocurrencies, which are Bitcoin, Ethereum, and Binance Coin, using Social Network Analysis (SNA) by visualizing them using Business Intelligence (BI Dashboard). This study uses the SNA parameters of degree, diameter, modularity, centrality, and path length for each network and its actors and their actual market price by crawling (data collecting process) from Twitter as one of the social media platforms. From the research conducted, the popularity of cryptocurrencies is affected by their market price and the activeness of their actors on social media. These results are important because they could help in the decision-making to buy cryptocurrencies with high popularity on social media because they tend to retain their value over time and could benefit from price spikes from influential people. © Authors retain.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Optimizing Government Funding Allocation with Ensemble Machine Learning Models

Optimizing Government Funding Allocation with Ensemble Machi...

引用

International Conference on Computing, Engineering, and Design (ICCED)

作者： Budi Prasetyo Suharjito Computer Science Department Binus Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Barat Indonesia

ISBN: (数字)9798331529376

ISBN: (纸本)9798331529383

Given the limited availability of state funds, managing state finances in an effective, efficient, and prudent manner is essential. High demand for additional state funds without sound justification can lead to inefficiencies and poor budget execution. Therefore, decisions regarding the allocation of additional funds should be made selectively and based on historical data reflecting the quality of the work unit in budget management. This research aims to develop a machine learning application to assist decision-makers in recommending additional funding percentages. Utilizing the Budget Implementation Quality Indicator (IKPA) data, we performed feature selection using Principal Component Analysis (PCA), resulting in three selected features. These features were then used to build models with base models (Decision Tree Regression, K-Nearest Neighbor Regression) and ensemble learning methods (Stacking, Bagging, Random Forest, Boosting: AdaBoost, XGBoost, LightGBM). After to-Fold Cross-Validation and hyperparameter tuning, LightGBM demonstrated the lowest error rate with a Root Mean Square Error (RMSE) of 0.0646 and a Mean Absolute Error (MAE) of 0.0520, outperforming XGBoost in predicting additional fund allocation proportions. The application supports informed and accountable financial decision-making, promoting efficient and prudent national financial management. By comparing base models and ensemble techniques, this research provides critical insights into machine learning applications in financial management, driving methodological innovation and advancing the field.

关键词： Biological system modeling Government Machine learning Financial management Data models Resource management Ensemble learning Root mean square Regression tree analysis Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Prediction of Oil Palm Conditions Using Deep Learning Based on the Visible Atmospherically Resistant Index on UAV Imagery

Prediction of Oil Palm Conditions Using Deep Learning Based ...

引用

2023 International Conference on Informatics Engineering, science and Technology, INCITEST 2023

作者： Mimboro, Prasetyo Soewito, Benfano Soeparno, Haryono Budiharto, Widodo Bina Nusantara University Binus Graduate Program Computer Science Computer Science Departement Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Computer Science Departement Jakarta11480 Indonesia

ISBN: (纸本)9798350317862

Artificial neural network (ANN)-based computer vision techniques are becoming increasingly popular for palm oil disease detection and classification. Deep learning models' capacity to automatically learn and extract relevant image features has enabled accurate and efficient detection and classification of palm oil diseases. In this research, research was conducted to test the deep learning method to predict the condition of oil palm plantations based on the visible atmospherically resistant index on the Unmanned Aerial Vehicle Image. Some diseases that can attack oil palm trees are root disease or oil palm root rot (blast disease), basal stem rot (ganoderma), bud rot (spear rot), yellow line disease (patch yellow). This study aims to predict the condition of oil palm trees based on the VARI so that the process of detecting the spread of disease in oil palm trees can be accelerated. In this study, the prediction model for the condition of oil palm trees using the ANN algorithm succeeded in predicting the condition of oil palm trees and provided satisfactory prediction results, namely an accuracy rate of 94.7% and a loss of 21.58%. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning Method for Malaria Identification 8

Transfer Learning Method for Malaria Identification

引用

8th International Conference on Informatics and Computing, ICIC 2023

作者： Herli, Cecilia Audrey Wijaya, Daniel Zerge Hansen Angela, Michelle Pragusma, Zakaria Berlam Wulandari, Ajeng Anggreainy, Maria Susan Bina Nusantara University Computer Science Department School of Computer Science Jakarta11480 Indonesia Bina Nusantara University Computer Science Department BINUS Graduate Program Computer Science Jakarta11530 Indonesia

ISBN: (纸本)9798350342604

Malaria is a severe disease caused by parasites of the genus Plasmodium, which are transmitted to humans through the bite of an infected female Anopheles mosquito. Symptoms of malaria begin to appear at least within 10 to 15 days. If malaria is not treated immediately, it is feared that it will cause respiratory problems, shortness of breath, and death. To avoid the occurrence of these events, the idea arose to create an AI (Artificial Intelligence) project that can recognize the presence of malaria parasites in blood cells. Thus, the main objective of this project is to find out how to create a Machine Learning model that can efficiently identify malaria parasites in the human body. The AI project uses CNN (Convolutional Neural network) as an algorithm to recognize the presence or absence of parasites in blood cell images that will be inputted by the user. Process of implementing CNN, using VGG19 which is an advanced CNN that has pre-trained layers and a good understanding of describing an image, both the shape, color, and structure of the image. After implementing the Transfer Learning algorithm on the dataset, the result is a Transfer Learning algorithm that can detect the presence of Malaria parasites in blood cells with an accuracy rate of 92 percent a specificity of 95 percent, and a sensitivity of 89 percent. The accuracy can still increase depending on the diversity of the data provided. The more often we train and input test data as train data, the accuracy of AI will also increase. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Drug Demand Prediction Based on Epidemiology Factors Using Random Forest 15

Drug Demand Prediction Based on Epidemiology Factors Using R...

引用

15th International Congress on Advanced Applied Informatics Winter, IIAI-AAI-Winter 2023

作者： Emmanuel, Gunadi Arifin, Yulyani Sonata, Ilvico Zarlis, Muhammad Bina Nusantara University Doctor of Computer Science Program Jakarta Indonesia Bina Nusantara University Binus Graduate Program-Doctor of Computer Science Computer Science Department Jakarta Indonesia Binus Graduate Program Bina Nusantara University Information System Management Department Jakarta Indonesia

ISBN: (纸本)9798350383829

The characteristics of the disease that spreads quickly, the number of sufferers, and the severity of sufferers of Coronavirus Disease 2019 are components of uncertainty during the pandemic. In an uncertain situation, prediction models for the need for drugs and medical devices are of great concern to policymakers in government, drug manufacturers, distributors, and pharmaceutical installation managers to maintain drug availability. Drug need prediction models that rely on historical data components on drug use are no longer reliable. Learning from the COVID-19 case, epidemiological variables correlate with predicting drug demand. This research includes data on ten major diseases in private hospital units for 2017-2022 to complete historical data on drug use. This study implements the Random Forest algorithm. The research method uses literature studies and processing field data from pharmaceutical installations. The analysis process uses KNIME software. The level of accuracy in predicting drug demand from historical drug use data was 77.272%, increasing to 81.818% with a model for predicting drug demand based on consumption cycles and classification of drug therapy groups. Furthermore, predictions of drug demand can consider variables recorded in medical records related to the seasonal frequency of diseases. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Analysis of the 5Rs in Thailand Medication Error Classification through Natural Language Processing 20

Analysis of the 5Rs in Thailand Medication Error Classificat...

引用

20th International Joint Conference on computer science and Software Engineering, JCSSE 2023

作者： Udomnuchaisup, Peachyasitt Imsombut, Aurawan Suwannahitatorn, Picha Saethang, Thammakorn Kasetsart University Biomedical Data Science Master's Program Faculty of Science Bangkok Thailand Kasetsart University Faculty of Science Department of Computer Science Bangkok Thailand Bangkok Thailand

ISBN: (纸本)9798350300505

Medication errors threaten patient safety considerably, underscoring the necessity for enhanced detection and prevention techniques. A prevalent classification system in hospitals relies on the standard practice of medication administration known as the Five Rights (5R). This study seeks to develop an NLP-based tool designed to expand 5R error categorization coverage and alleviate the workload of medical professionals. The proposed method focuses on Thai medical text, incorporating Thai and English vocabulary. In this investigation, we developed a supervised learning classification framework using the Universal Sentence Encoder (USE) for sentence embedding, followed by an Artificial Neural Network (ANN) for model training. Additionally, we explored a zero-shot classification model employing pre-trained Large Language Models (PLMs). Our findings reveal that the supervised learning classification model provides the most favorable performance, albeit with the limitation of reliance on labeled datasets, which can be resource intensive. Conversely, the zero-shot classification framework's performance is less optimal. However, future advancements in Thai medical PLMs may improve efficacy and present a viable alternative for medical data analysis without dependence on labeled datasets. This initiative lays the groundwork for potential future applications and advantages within Thailand's medical domain. © 2023 IEEE.

关键词： Neural networks

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

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

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：