检索结果-内蒙古大学图书馆

2024 International Conference on Information Technology Systems and Innovation, ICITSI 2024

作者： Amadeo, Adriel Justin Andryan Siento, Joyceline Graciella Pramunita, Putu Devi Ariska Hongastu, Vanessa Aprily Purwandari, Kartika Nusantara University Department of Computer Science School of Computer Science Bina Jakarta Indonesia

ISBN: (纸本)9798331511470

In today's competitive business environment, efficient warehouse management is crucial for the growth and operational success of Small and Medium Enterprises (SMEs). However, many SMEs struggle with inventory tracking, transaction management, and financial analysis due to limited technological resources. To address these challenges, we present "Manageinaja,"a web-based application designed to streamline warehouse operations and optimize business management. Built on the Laravel framework with PHP, Blade templates, and JavaScript, the system features a secure password authentication mechanism and intuitive user interface. Using Entity-Relationship Diagrams (ERD) for database structuring, "Manageinaja"enables users to monitor stock movements, manage transactions, and analyze financial data effectively. This application empowers SMEs to improve decision-making, enhance productivity, and maintain data integrity through a comprehensive and user-friendly platform. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of BERT-CNN, TRANS-BLSTM, and RoBERTa Models for Sentiment Analysis 8

Comparative Study of BERT-CNN, TRANS-BLSTM, and RoBERTa Mode...

引用

8th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2024

作者： Silitonga, Christopher Alden Anugrah Dermawan, Marco Davincent Adeta, Franz Nadia, Nadia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350368970

In the field of Natural Language Processing (NLP), various milestones and improvements have been made due to the advent of deep learning, mainly in sentiment analysis of text data. BERT has excelled through its capability to comprehend emotional context. Nonetheless, there are some limitations with BERT like long inference times as well as interpretability challenges. Therefore, combinations of such architectures with BERT, for instance TRANS-BLSTM, BERT-CNN and RoBERTa have been studied. These hybrid models aim at leveraging on the strengths that BERT possesses while making sentiment analysis tasks more efficient and interpretable. This investigation demonstrates ongoing attempts to develop the better NLP models that can comprehend human emotions reflected in text data more effectively. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Scalable data Pipeline for Multiclass Attack Classification in Large-Scale IoT Networks

引用

Big data Mining and Analytics 2024年第2期7卷 500-511页

作者： Selvam Saravanan Uma Maheswari Balasubramanian Department of Computer Science and Engineering Amrita School of ComputingAmrita Vishwa VidyapeethamBengaluru 560035India

The current large-scale Internet of Things(IoT)networks typically generate high-velocity network traffic *** use IoT devices to create botnets and launch attacks,such as DDoS,Spamming,Cryptocurrency mining,Phishing,*** service providers of large-scale IoT networks need to set up a data pipeline to collect the vast network traffic data from the IoT devices,store it,analyze it,and report the malicious IoT devices and types of ***,the attacks originating from IoT devices are dynamic,as attackers launch one kind of attack at one time and another kind of attack at another *** number of attacks and benign instances also vary from time to *** phenomenon of change in attack patterns is called concept ***,the attack detection system must learn continuously from the ever-changing real-time attack patterns in large-scale IoT network *** meet this requirement,in this work,we propose a data pipeline with Apache Kafka,Apache Spark structured streaming,and MongoDB that can adapt to the ever-changing attack patterns in real time and classify attacks in large-scale IoT *** concept drift is detected,the proposed system retrains the classifier with the instances that cause the drift and a representative subsample instances from the previous training of the *** proposed approach is evaluated with the latest dataset,IoT23,which consists of benign and several attack instances from various IoT *** classification accuracy is improved from 97.8%to 99.46%by the proposed *** training time of distributed random forest algorithm is also studied by varying the number of cores in Apache Spark environment.

关键词： Internet of Things(IoT) concept drift Apache Spark MongoDB Apache Kafka streaming

来源：评论

学校读者我要写书评

暂无评论

Uncovering Fake Profiles Using Machine Learning Algorithms

Uncovering Fake Profiles Using Machine Learning Algorithms

引用

2024 International Conference on Artificial Intelligence, Blockchain, Cloud Computing, and data Analytics, ICoABCD 2024

作者： Amadea Hardjono, Ignatia Christabelle Tanumihardja, Raymond Willy Lucky, Henry Suhartono, Derwin School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350368451

Fake user profiles has been one of the biggest security issues in all online social networks (OSN) platforms. Whether operated by bots or humans, their sole presence disrupts the online social environment by being either a direct or indirect form of threat to users and platforms alike. Thus, detection of fake profiles plays a crucial role to mitigate this sort of issue, and with the help of machine learning algorithms this can be done simply and automatically while still achieving reliable and high-quality outcomes. In this paper, the research that was done employs and introduces an Ensemble Learning of three algorithms, namely Support Vector Machine (SVM), Random Forest algorithm, and Logistic Regression - a combination that has been sparsely tested and trialed compared to their individual applications. The aim of this approach is to enhance the generalizability while maintaining robustness of the detection model. Synthetic Minority Oversampling Technique (SMOTE), a data preprocessing method was also applied before the training and testing to prevent risks from associated with imbalanced data. The model evaluation will be determined by obtaining the precision results of the conducted experiment, highlighting the proposed methodology's effectiveness in identifying fake accounts. The findings from the conducted study are expected to contribute to the improvement of automated methods, as well as to provide insights that may be beneficial in strengthening security and user trust across different OSN platforms. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Offensive Text Detection on Social Media Using Machine Learning

Offensive Text Detection on Social Media Using Machine Learn...

引用

2024 International Conference on Control and Automation, Electronics, Robotics, Internet of Things, and Artificial Intelligence, CERIA 2024

作者： Tanuwijaya, Jesslyn Edbert, Ivan Sebastian Arinardi, Hans Christian Suhartono, Derwin School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331511166

People are social creatures, people of all ages use social media to engage with one another. But not everything that circulates on social media is suitable for all ages;some content, such hate speech, bullying, and cursing, can be harmful to users' mental and physical health. Thus, the necessity for a social media content filtering tool arises. To solve this problem, the researcher proposed a model to classify English tweets by implementing machine learning algorithms specifically Random Forest Classifier, SVM, XGboost, Logistic Regression were used to detect and classify offensive text messages. In this case, dataset were extracted by using countvectorizer algorithm, the researchers also apply data cleaning to remove stop words, punctuation, url and prefix that come from the dataset. Because the imbalance of the dataset the researchers try to fix by using undersampling technique. The best result of the experiments are Random Forest Classifier perform 0.8808 accuracy. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Framework for Securing and Enhancing Internet of Things Ecosystems

Blockchain-based Framework for Securing and Enhancing Intern...

引用

2024 International of Seminar on Application for Technology of Information and Communication, iSemantic 2024

作者： Josh, Satyasiddhi Maxwellee, Frederick Achmad, Said Sutoyo, Rhio Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350366648

The rapid proliferation of Internet of Things (IoT) devices has amplified security concerns, making data protection and ensuring reliable device interactions paramount. This research investigates the potential of blockchain technology to address these security challenges and enhance the quality and functionality of IoT ecosystems. With its decentralized, immutable, and tamper-resistant nature, blockchain offers a robust solution by improving device authentication and authorization processes and ensuring data integrity. Utilizing a systematic literature review (SLR) methodology based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, this paper analyzes current research to explore the benefits, challenges, and strategies for integrating blockchain into IoT systems. The findings demonstrate that blockchain can significantly enhance IoT security by reducing single points of failure and improving data integrity through its decentralized ledger system. Blockchain's capabilities in managing device identities and automating interactions through smart contracts further strengthen IoT security frameworks. However, scalability, energy consumption, and integration complexity remain. Addressing these hurdles requires the development of more efficient consensus algorithms and seamless integration tools. This study provides valuable insights into the potential of blockchain to revolutionize IoT security, offering a pathway to creating a more secure and trusted IoT ecosystem. Future research should focus on scalability, energy-efficient consensus mechanisms, standardized integration protocols, and real-world case studies to refine blockchain solutions tailored for IoT environments, ensuring continued innovation and interdisciplinary collaboration between blockchain and IoT experts. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Indonesian Batik Pattern Recognition Using Siamese Network with Triplet Loss

Indonesian Batik Pattern Recognition Using Siamese Network w...

引用

2024 International Conference on computer Engineering, Network and Intelligent Multimedia, CENIM 2024

作者： Makmur, Stephanie Anastasia Sunjaya, Fredy Lucky, Henry Meiliana School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350368802

This paper describes Indonesian batik pattern recognition depending on a Siamese Neural Network with a triplet loss function. The fabric art considered as Indonesian, that is batik is complex and comes in a wide variety of designs and hence hard to be staged and categorized. This paper has therefore developed a method that entails the acquisition and preprocessing of batik image dataset, data augmentation to enrich the dataset, the training of the Siamese Network coupled with CNNs (VGG16, DenseNet169, ResNet152) for feature extraction and optimizing the triplet loss function. This would show the efficiency of the Siamese Network in achieving high accuracy at a limited dataset over the traditional methods in pattern recognition. From several experiments carried out, the highest accuracy was obtained by the base model DenseNet169 with an accuracy level of 84% as a Siamese Network with trainable parameters set to false, where from this result there was an increase of 13% from the previous 71% when implemented on CNN with the same parameters. By carrying out this research, it is hoped that in the future more data can be collected from several regions in Indonesia regarding the diversity of batik patterns and motifs. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Limb Detection and Classification using computer Vision and Machine Learning

Limb Detection and Classification using Computer Vision and ...

引用

2024 International Conference on Artificial Intelligence, Blockchain, Cloud Computing, and data Analytics, ICoABCD 2024

作者： Wibawa, Andrew Wijaya, Nathanael Marvin Lucky, Henry Suhartono, Derwin School of Computer Science Bina Nusantara University Computer science department Jakarta Indonesia

ISBN: (纸本)9798350368451

This research delves into the development of a limb detection system that harnesses the power of contemporary computer vision and machine learning techniques. The primary objective of this study is to improve the accuracy and reliability of human limb recognition within video data, an area with significant implications for various fields such as healthcare, sports analytics, and interactive media in the near future. The study presents a detailed comparative analysis of several machine learning models, including Logistic Regression, Ridge Classifier, Random Forest, and Gradient Boosting. Among these, the Random Forest model emerged as the most promising, demonstrating superior performance in limb detection tasks. Our findings from this research highlights the potential for these models that can be applied in real-world scenarios, where precise motion detection is crucial. This paper not only contributes to the current body of knowledge by offering a comprehensive evaluation of these models but also lays the groundwork for future research and development in automated motion detection systems. The implications of our research can extend beyond academic inquiry, suggesting practical applications that could revolutionize industries dependent on accurate human motion analysis. This study also underscores the importance of model selection and hyperparameter tuning in achieving optimal performance, providing a foundation for further advancements in the field of computer vision and machine learning. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Integration of Land and Tax Geospatial data with Artificial Intelligence (AI)-Based Clustering 11

Integration of Land and Tax Geospatial Data with Artificial ...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Chandra, Billy Daniel Willyanto, Samuel Irwansyah, Edy School of Computer Science Bina Nusantara University Department of Computer Science Jakarta Indonesia

ISBN: (纸本)9798350389654

Integrating Land Geospatial data and Tax Geospa-tial data is challenging due to differences in file formats and attributes. This research addresses these challenges and seeks to effectively combine the datasets. Initially, the study identifies a suitable file format that can handle the various attributes of both datasets without losing data quality. A systematic approach is then employed to align the different attributes. The research focuses on data from East Jakarta, Indonesia. The land data includes files such as. shp,. shx,. dbf, and. prj, representing the shapes and attributes of land parcels. The tax data includes sim-ilar files containing detailed tax information. Since the datasets lack common attributes, spatial relationships are used to join them using QGIS software. The process begins by simplifying the data structures and clipping them to the relevant areas. Spatial joins are performed based on where the data overlaps the most. Post-integration, the dataset is cleaned to remove any duplicate or unnecessary information. K-Means clustering with Scikit-Iearn is then used to analyze the data and identify patterns. The results show that land and tax data can be combined spatially, but not by their attributes. When joined, the tax data, which may be divided among multiple owners, follows the land parcel data, resulting in a single ownership representation. This method ensures that the datasets are effectively merged, enabling better analysis and decision-making. The approach demonstrates a robust methodology for integrating disparate geospatial datasets, enhancing data accessibility and utility. © 2024 IEEE.

关键词： clustering geospatial integration land data tax data

来源：评论

学校读者我要写书评

暂无评论

Exploration of MBTI Personality Prediction through the Application of Traditional data Augmentation

Exploration of MBTI Personality Prediction through the Appli...

引用

2024 International Conference on Advanced Information Scientific Development, ICAISD 2024

作者： Rizandi, Nathasya Zega, Grisella Meirisia Lucky, Henry Meiliana Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350392036

All the various forms of social interaction do not avoid the tendency of each individual's personality characteristics. With the increasing use of social media, the language patterns shown through posts are considered to be representative of a person's personality traits, Therefore, this research will conduct personality prediction experiments using online forum post on the basis of the MBTI personality model. Our focus is to test how effective the use of traditional data augmentation is in helping to overcome the problem of data imbalance and its effect on the accuracy of the results. We used the three best models that have been used in previous studies, namely Random Forest, Support Vector Machine (SVM), and a light gradient boosting machine (LightGBM). These experiments show that traditional data augmentation is still insufficient to provide the best results compared to synthetic data generation as done in previous studies. However, it still proves the need for augmentation data to help generalize the model with the best average results of 0.937 in Random Forest model training and 0.766 in SVM model testing, as well as an F1 with a score of 0.778 for the SVM model. © 2024 IEEE.

关键词： Prediction models

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：