检索结果-内蒙古大学图书馆

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Nurmara, Muhammad Azril Kurniawan Hakim, Muhammad Naufal Ardy, Oey Hans Christian Jeffrey, Reynaldo Setiono, Vincentius Albert Kanigoro, Bayu Irwansyah, Edy Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Financial Technology (FinTech) is a popular name for innovative technology utilized by financial organizations, with a focus on security and privacy concerns. These concerns include threats, attacks, hostile activity, and adversaries, as well as potential responses. The goal of this study is to undertake an assessment of current advances in financial industry security and privacy issues. FinTech is viewed as a gateway to increased business potential by financial sectors and entrepreneurs, but in order to explore such possibilities, mobile applications and other digital platforms must be established. However, security vulnerabilities to mobile applications have expanded dramatically, posing a dilemma for users and FinTech entrepreneurs. The findings of this study can be used to develop a theoretical framework for FinTech security and privacy, which will provide critical support for the establishment of a trustworthy security mechanism in FinTech. © 2023 The Authors. Published by Elsevier B.V.

关键词： financial technology machine learning security

来源：评论

学校读者我要写书评

暂无评论

Hate Speech Detection in Indonesian Song Lyric Using BERT 9

Hate Speech Detection in Indonesian Song Lyric Using BERT

引用

9th IEEE International Conference on Computing, Engineering and Design, ICCED 2023

作者： Andryan Chandra, Nathalia Pramunita, Putu Devi Ariska Parmonangan, Ivan Halim Diana Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350370126

This study was conducted with the aim of detecting hate speech in song lyrics. The background of this study stems from the numerous negative impacts caused by hate speech. We focus on detecting hate speech in song lyrics because music is a popular form of art that can have significant impacts on people's lives. There have been many previous studies that attempted hate speech detection using various methods. However, one issue still persists, especially when dealing with slang or uncommon sentence structures. According to the previous works, deep learning algorithms, such as using pre-trained BERT model for sentiment analysis and R-CNN as a classifier, have shown promise in addressing these issues. Hence, we decided to utilize the BERT pre-trained model for sentiment analysis and R-CNN as the classifier in their study. The dataset used in this research was collected from the Twitter dataset on Kaggle and also utilized the Spotify API. The study resulted in an precision score of 100% a recall score of 37% and an F1-score of 54% for the hate speech detection. Our result suggests that more relevant data, such as datasets consisting of poetry or sentences with implicit meanings, will be beneficial to enhance hate speech detection in song lyrics. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Digital Marketplace Design & Development for Creative Recycle Product 9

Digital Marketplace Design & Development for Creative Recycl...

引用

9th IEEE Information Technology International Seminar, ITIS 2023

作者： Indrawan, Krisna Wira Kristiawan, Sena Zoe, Timothy Micha Tania, Steffi Song, Febrian Ivan Saputra, Jeremy Nathaniel Alam, Islam Nur Andryani, Nur Afny Catur School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350306835

The increasing issue of recycling and the lack of consideration for the end-of-life treatment of synthetic polymers have led to significant environmental and health concerns. Encouraging pro-environmental behaviors, such as recycling, is crucial to address this issue. Leveraging the widespread use of the internet. This research project proposed to make a web based marketplace application to open business opportunities for waste craftsmen, by showcasing and selling their work through a dedicated marketplace. This project aligns with previous research highlighting the effectiveness of web- based applications in increasing recycling behaviors and awareness. This research aims to reduce waste accumulation in Indonesia while increasing the value and appreciation of recycled materials as art pieces or practical tools, also by helping economic growth for every craftsmen that place their product in out website. In conclusion, this research contributes to the efforts of promoting recycling, raising awareness about waste management, and supporting waste craftsmen. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approaches for Customer Segmentation and Product Recommendation

Hybrid Approaches for Customer Segmentation and Product Reco...

引用

2023 International Conference on Informatics, Multimedia, Cyber and Information Systems, ICIMCIS 2023

作者： Septiana Putra, Muhammad Fauzi Aswie, Annastasia Stephanie Edbert, Ivan Sebastian Suhartono, Derwin Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350307306

The trend of influencer marketing is increasing massively in the digital age. Despite this, the majority of marketing strategies are still not optimally using this trend. Marketing strategies can be implemented by applying customer segmentation and product recommendations through the implementation of artificial intelligence technology. Customer segmentation can be implemented using clustering techniques, and product recommendations can be applied using association rules. The clustering methods K-Means and K-Medoids will be compared to find the best clusters, and then each clustering method will be combined with the Apriori association rules method. The objective of this research is to identify the combination of clustering methods and association rules that produces the best performance. The elbow method is used to determine the optimal number of clusters. Based on three used evaluation metrics, it is found that between the two clustering methods, K-Means has a better evaluation metric. After the associations are combined, the result shows that K-Medoids and Apriori have a slightly higher confidence score than K-Means and Apriori with 39.265s for runtime and 244.175Mb for memory. This research will help companies identify various groups of customer characteristics and products that have strong ties to these groups. Therefore, this will help companies gain the necessary business insights. © 2023 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of Generative Adversarial Network Potential in AI Artwork

A Systematic Literature Review of Generative Adversarial Net...

引用

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

作者： Rasyad, Farrel Kongguasa, Hardi Andry Onggususilo, Nicholas Christandy Anderies Kurniawan, Afdhal Gunawan, Alexander Agung Santoso Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350320954

Humans have studied calligraphy and calculated programs to foster creativity for years. Image generation technology using artificial intelligence and Generative Adversarial Networks is currently reaching the peak of its performance. While there are newer and newer algorithms to improve the image generation system, the output of the images is still suitable at best and only excels in their category. While it is true that some of the images generated are good enough to be used, it is still unclear whether the capabilities of AI image generation can outperform their creative human counterparts. Therefore, this literature study aims to explore the basics of AI image generation, how they work, and what factors contribute to creating art such as simple pictures. Previous studies from several years ago show that most generated images are not good enough for creative usage because they only replicate traces of their dataset. The most significant factor contributing to this is the algorithm used and how it is used to create new images. In general, the concluded that while current AI-generated images are improving, they are still not creative enough to replace human creativity. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Development of an Automated Scoring Model Using SentenceTransformers for Discussion Forums in Online Learning Environments

引用

Journal of Computing and Information Technology 2022年第2期30卷 85-99页

作者： Dhini, Bachriah Fatwa Girsang, Abba Suganda Department of Computer Science BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta Indonesia

Due to the limitations of public datasets, research on automatic essay scoring in Indonesian has been restrained and resulted in suboptimal accuracy. In general, the main goal of the essay scoring system is to improve execution time, which is usually done manually with human judgment. This study uses a discussion forum in online learning to generate an assessment between the responses and the lecturer's rubric in the automated essay scoring. A SentenceTransformers pre-trained model that can construct the highest vector embedding was proposed to identify the semantic meaning between the responses and the lecturer's rubric. The effectiveness of monolingual and multilingual models was compared. This research aims to determine the model's effectiveness and the appropriate model for the Automated Essay Scoring (AES) used in paired sentence Natural Language Processing tasks. The distiluse-base-multilingual-cased-v1 model, which employed the Pearson correlation method, obtained the highest performance. Specifically, it obtained a correlation value of 0.63 and a mean absolute error (MAE) score of 0.70. It indicates that the overall prediction result is enhanced when compared to the earlier regression task research. ACM CCS (2012) Classification: Computing methodologies → Modeling and simulation → Model development and analysis → Model verification and validation Applied computing → Education → Distance learning. © 2022, University of Zagreb Faculty of Electrical Engineering and Computing. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Crude Palm Oil Price Prediction Using Machine Learning and Hybrid Ensemble Approach

Crude Palm Oil Price Prediction Using Machine Learning and H...

引用

2023 International Conference on Informatics, Multimedia, Cyber and Information Systems, ICIMCIS 2023

作者： Godeliva Sitepu, Aubrey Theodore Syavin Eka Lesmana, Muhamamad Iswanto, Irene Anindaputri Lucky, Henry Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350307306

Crude oil is a crucial global commodity. With an increasing population and expanding industries, crude oil prices are highly erratic and subject to high uncertainty. The slightest change in supply or demand can cause significant price changes. This research paper investigates the development of an ensemble model for predicting the price of crude oil. The study builds upon previous research in the field of crude oil price prediction, which emphasizes the limitations of traditional econometric models and the advantages of deep learning algorithms such as Long-Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and Wavelet Neural Network (WNN). The proposed ensemble model incorporates multiple machine learning algorithms, including Support Vector Regression (SVR), Extreme Gradient Boost (XGB), and Light Gradient Boost (LGB) to enhance prediction speed while maintaining or improving the accuracy. The result shows improvement regarding the prediction speed while giving less error than the previous model. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Classification of Hoax News Using Machine Learning and Neural Networks with BERT Embeddings 3

Classification of Hoax News Using Machine Learning and Neura...

引用

3rd International Conference on Electronic and Electrical Engineering and Intelligent System, ICE3IS 2023

作者： Juarto, Budi School of Computer Science Bina Nusantara University Computer Science Department Bandung Indonesia

ISBN: (纸本)9798350327762

In the digital era, hoax news poses a serious threat, especially during elections, impacting unity and causing conflicts. With 8.7 million fake news articles circulating, public susceptibility to hoaxes, often fueled by emotional language and lack of source verification, adds to the risk. Deep learning offers a potential solution by utilizing advanced neural networks for in-depth text analysis, effectively distinguishing valid news from hoaxes based on content patterns. This approach holds promise in eradicating hoax news, raising awareness, and safeguarding the nation' s unity. This study focuses on detecting hoax news using machine learning and deep learning techniques. The researchers used a general dataset containing 44,898 news articles, with 23,481 labeled as hoaxes and 21,417 as factual. Preprocessing involved tokenization, stopword removal, and lemmatization/stemming before converting text into vectors using TF-IDF. For deep learning, the BERT method was employed to extract contextual embeddings. The models were evaluated using different combinations of news titles and content. Among the machine learning models, Support Vector Machine (SVM) performed best, with an F1-score of 94% when using only news titles. However, the decision tree method outperformed others with a 99.6% F1 score when using titles and content. Nevertheless, all machine learning models were outperformed by BERT + NN, achieving an F1-score of 98.72% with titles only and 99.9% with both titles and content. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Recommendation System Based Collaborative Filtering for Deciding Travelling Place 4

Recommendation System Based Collaborative Filtering for Deci...

引用

4th International Conference on Artificial Intelligence and Data sciences, AiDAS 2023

作者： Oktavius, Anthony Kevin Suhartono, Derwin School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350318432

This Indonesia has a vast number of tourist destinations, and it can be overwhelming for people to decide where to go, either because they have many options to choose from or because they are bored with places they have visited before. To address this issue, this research uses collaborative filtering-based recommendation systems to provide users with personalized recommendations based on their previous ratings. The research will compare five recommendation system algorithms: the Hybrid Algorithm with ContentKNN (Content K Nearest Neighbors) and RBM (Restricted Boltzmann Machine), SVD++ (Singular Value Decomposition++), Efficient Deep Learning, Scalable Deep Learning, and Naïve Bayes. These algorithms will be tested based on their evaluation metrics, namely RMSE (Root Mean Squared Error) and MAE (Mean Absolute Error). The model that has the best evaluation metrics will be selected to provide travelling place recommendations. To develop algorithm models for the recommendation system, the research will use the CRISP-DM (Cross-Industry Standard Process for Data Mining) model. Based on the workflow, Efficient Deep Learning has the best RMSE and MAE value from all of the models, with these following parameters: 250 neurons and SELU (Scaled Exponential Linear Unit) activation type. Future works for this research includes additional rating dataset, adding different combinations of fields, distance metrics, and other evaluation metrics. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Android - Based Smart Nutrition Application for Children Nutritional Awareness 9

Android - Based Smart Nutrition Application for Children Nut...

引用

9th IEEE Information Technology International Seminar, ITIS 2023

作者： Kwon, Patrick Hariyani, Retno Shintya Christiansen, Reynard Juan, Jefferson Wen, Marvelio Keven Chandra, Nicholas Andryani, Nur Afny Catur Alam, Islam Nur School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350306835

Malnutrition in children has emerged as a critical public health concern in the modern era, with significant implications for their long-term health and well-being. Lack of proper nutrition knowledge and awareness among parents often contributes to this issue. While prior research has created food identification systems to help people know the food nutrition, there is a glaring lack of applications expressly made to help parents understand their children's nutrition. To address this gap, we propose a smart nutrition application that aims to provide parents with essential information about the nutritional content of their children's food, thereby increasing their awareness and understanding of nutrition. The application's main feature utilizes an AI camera equipped with the You Only Look Once (YOLO) algorithm, enabling it to scan a meal and display detailed nutrient information. Furthermore, a UI-based and text-based ingredients calculator is provided to help parents calculate calories and food nutrition. Moreover, the article feature is intended to serve as a resource for parents to gain knowledge about children's nutrition. By leveraging TensorFlow, a machine learning framework, the proposed application achieves efficient and accurate food recognition with an overall accuracy rate of 90%. © 2023 IEEE.

关键词： Nutrition

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：