检索结果-内蒙古大学图书馆

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

作者： Clintswood Lie, Delbert Giovanni Kuswandana, Lexiandy Nadia Achmad, Said Suhartono, Derwin School of Computer Science Bina Nusantara University Cyber Security Program Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350327762

Penetration testing is a method to assess the security within a network by performing or simulating a real-world cyber-attack on the network. It has been one of the best ways preferred by organizations to strengthen their network defenses against cyber threats. However, penetration testing proves that it has several drawbacks such as requiring a significant number of skills and time to perform. A survey made by The International Information System Security Certification Consortium also shows that the world is lacking cybersecurity workforces. To address this problem, this paper conducts research regarding the usage of machine learning to automate penetration testing activity. To start off, automated penetration testing tools will be created using machine learning algorithms, specifically reinforcement learning and deep reinforcement learning algorithms. The second step is to put the tools in a learning stage where it will be provided with the MITRE ATT&CK Framework. This framework will be the base for the attacks and exploitations used within the tools. The third step is to conduct a series of automated penetration testing over different target networks. The result will be then compared and analyzed with a manual penetration testing report to see how efficient and better it is compared to a manual penetration test. Lastly, the final data will then be collected for future developments and recommendations. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Machine Learning Methods for Flood Prediction 9th

Performance Comparison of Machine Learning Methods for Flood...

引用

9th International Conference on computer science and Computational Intelligence, ICCSCI 2024

作者： Linus, Josel Tanjaya, Vincent Diana Kurniawan, Afdhal Computer Science Department School of Computer Science Bina Nusantara University Jakarta14480 Indonesia

Flood is a disaster that causes problems. It causes problems such as destruction of property and disruption of civil activities. Predicting floods is a solution to prevent the devastating disaster and is crucial for mitigation. This study shows a comparison of various machine learning classification methods for flood prediction using a dataset consisting of humidity, wind speed, wind direction, location data, and other related features. We evaluated the performance of logistic regression, Naïve Bayes, K-Nearest Neighbors (KNN), decision tree, and random forest models based on metrics such as accuracy, precision, recall, and the area under the receiver operating characteristic curve (ROC-AUC). The results indicate that random forest achieved the highest accuracy at 95.902%, followed by KNN with 95.130%, decision tree with 91.448%, logistic regression with 79.513%, and naïve bayes with 77.256%. This comparative analysis highlights the strengths and limitations of each model, providing valuable insights for selecting the most appropriate approach for flood prediction. The results highlight the role of machine learning in creating an effective way of predicting floods. © 2024 The Authors.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Blockchain Implementation to Ensure the Authenticity and Integrity of Graduation and Diploma Certificates

Blockchain Implementation to Ensure the Authenticity and Int...

引用

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

作者： Shuban, Effel Zefannya Indrawan, Krisna Wira Edbert, Ivan Sebastian School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350368451

This research addresses the escalating problem of diploma forgery by proposing a novel, decentralized diploma issuance system powered by blockchain technology. The proliferation of fraudulent credentials undermines the integrity of quality education and necessitates a secure, verifiable mechanism for direct diploma authentication by institutions. This system tackles this challenge by utilizing a distributed ledger, eliminating the need for a central authority, and enhancing credential security. Designed using Solidity and deployed on a private Ethereum network, the system assigns distinct roles: educational institutions issue and manage diplomas, students retain access to their own verified credentials, and potential employers can seamlessly verify their authenticity. Our analysis of gas usage reveals that the initial issuance process on the blockchain incurs the highest cost. However, subsequent retrievals by students or industry stakeholders demonstrate a lower average gas cost, with consumption increasing proportionally to request volume. While the system highlights promising results within a private network environment, the limitations inherent to its small-scale implementation are acknowledged. This research contributes to the field of credentialing by offering a secure and verifiable solution for diploma issuance, fostering trust in quality education, and streamlining the verification process for all stakeholders. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Security Implementation Againts a Server Using SonicWall 5

Security Implementation Againts a Server Using SonicWall

引用

5th International Conference on Cybernetics and Intelligent Systems, ICORIS 2023

作者： Santoso Gunawan, Alexander Agung Wicaksana, Brahmantyo Adianto Ady Wijaya, Alexandre Christian Adi Poernama, Alexander Robi Edbert, Ivan Sebastian Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Cyber Security Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350369489

Robust security measures are required for server environments due to the complexity and sophistication of cyber-attacks, which are on the rise. This study investigates the use of SonicWall Network Security Manager (NSM) to create security against a server. For the purpose of defending servers against various cyberthreats, NSM provides centralized management, real-time monitoring, and advanced analytics. The purpose of this study is to offer a thorough examination of SonicWall NSM's security features and gauge how well it protects server architecture. The studies in this paper involve configuring a number of ports on the SonicWall network software in order to preserve and enhance the security of each port. The experiment's findings demonstrate how UDP port security on SonicWall network gear may both safeguard and reveal threats to SonicWall logs. This finding offers options to corporate network specialists so that they can safeguard themselves against data theft for the advantage of both parties. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Passengers Monitoring Models at Jakarta Bus Stops Using the YOLOv3

Passengers Monitoring Models at Jakarta Bus Stops Using the ...

引用

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

作者： Jessen Hadisurya, Nicolaas Wulandhari, Lili Ayu Alam, Islam Nur School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350368451

Public transportation plays a crucial role in supporting urban mobility in big cities such as Jakarta. This condition can lead to overcrowding issue at bus stops, especially during working hours, such as in the morning when people go to work or in the evening when people are going home. The objective of this research is to analyze the density pattern at S. Parman Transjakarta bus stop, during the evening, to determine important strategies for addressing the overcrowding issue. The AI model that was proposed and used in this study was based on a YOLOv3 algorithm that was trained on the customized COCO dataset. Our dataset will contain 2000 images that contain at least 10 people, then we will split it into a training set and testing set. This model was utilized for detecting the number of passengers from photographs taken over a span of five consecutive days, from Monday through Friday. The result shows that the number of passengers is not constant and varies by the day of the week. This finding was expected to be a source of knowledge that can help in improving the efficiency of public transportation services as well as the passengers' experience. © 2024 IEEE.

关键词： Bus terminals

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approaches for Analyzing Bank Customer Complaints

Machine Learning Approaches for Analyzing Bank Customer Comp...

引用

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

作者： Arasy, Dustin Bijou Widjaja, Shamgar Eugene T'sidkenu Edbert, Ivan Sebastian Suhartono, Derwin School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350368802

Proper customer service is the key to increasing customer retention and brand credibility in financial banks. This can be achieved by helping solve customers' issues through their complaints. This study explores the application of traditional machine learning models to classify bank customer complaints. Using the dataset from the CFPB database, this research implements four ML models to handle this task: Multinomial Naïve Bayes, Random Forest Classifier, Stochastic Gradient Descent Classifier, and Logistic Regression. The dataset first underwent preprocessing steps to clean irrelevant data using Natural Language Processing and the features were extracted using Term Frequency-Inverse Document Frequency. After evaluating the baseline results, hyperparameter tuning is implemented using GridSearchCV to analyze improvements in performance for each model. The results show that LGR achieves the best performance out of all, with the highest accuracy score: 0.827 and an F1-score: 0.825. In conclusion, traditional machine learning models have the potential to provide a cost-efficient solution for classifying bank customer complaints. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

A comprehensive framework for decoding salty taste information from electroencephalography signals:distinguishing brain reactions to saltiness of comparable intensity

引用

Food science and Human Wellness 2025年第4期14卷 1538-1545页

作者： Jingjing Liu Yifei Xu Xingwang Lian Tianming Liu Haohao Ning Xi Jiang Shixin Yu Shikun Liu Lu Huang Xiaojun Sun Jiangyong Li Dongfu Xu School of Automation Engineering Northeast Electric Power UniversityJilin 132012China Department of Computer Science the University of GeorgiaAthens 30602USA School of Life Science and Technology University of Electronic Science and Technology of ChinaChengdu 611731China

The perception of salty taste is crucial for individuals to make healthy food ***,the brain electrophysiological signals underlying salty taste perception have been poorly *** this study,electroencephalography(EEG)was used to record brain activity induced by Na Cl solution as a salty taste stimulus.A combination of a custom delivery device and stimulation paradigm was employed to preserve the salty taste signal clearly.A stimulus-response capture method was proposed that could adapt to individual differences in brain responses to salty taste and accurately segment salty taste response *** this method to the EEG processing workflow can form a complete data processing *** results showed that the neural response induced by salty taste reached a high activity level in the initial stage within a short period(0.2 s),and there was a sustained periodic response within 0.75 s after the ***,the salty taste information in the EEG signal was decoded,and discrimination of 2 similar concentrations of salty taste solutions was achieved far above the chance level(average identification rate:89.66%).This study demonstrated experimental paradigms and research methods for understanding salty taste perception,which could provide references for research on other basic tastes.

关键词： Saltiness Salty perception Electroencephalography Stimulus paradigm

来源：评论

学校读者我要写书评

暂无评论

Detecting Account Takeover (ATO) in Fintech Companies Using Machine Learning 6

Detecting Account Takeover (ATO) in Fintech Companies Using ...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Santoso, Richard Gunawan, Alexander A.S. Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798331539603

Financial technology usually called fintech, has changed the landscape of financial services by introducing technological innovations to simplify, digitize, and disrupt traditional services. However, because of these technological developments, account takeover (ATO) attacks are one of the new challenges that have appeared, threatening user security and platform reputation. Account Takeover (ATO) attacks cause a significant risk for many sectors, including financial services, online retail, and social media. However, most current efforts focus more on Sybil detection and fraud detection rather than ATO. ATO attacks cause significant harm to users and fintech companies, including identity loss and loss of customer trust. This study compares the effectiveness of Random Forest, Logistic Regression, XGBoost, and Light GBM in finding new fraud trends. This is achieved by applying Machine Learning (ML) methods to improve credit card fraud detection. This dataset contains 6,362,620 unbalanced data that are balanced using the undersampling technique. Among the four algorithms compared, the LightGBM algorithm achieves the best result with an accuracy of 0.99. These results enable fairly accurate fraud detection. This research contributes to fintech companies by advancing the understanding of ML techniques in fraud detection, providing a comparative analysis of different algorithms, and providing more effective strategies for solving credit card fraud problems. © 2024 IEEE.

关键词： Fintech

来源：评论

学校读者我要写书评

暂无评论

Cyber Security in Smart Cities and Its Challenges: A Systematic Literature Review 3

Cyber Security in Smart Cities and Its Challenges: A Systema...

引用

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

作者： Ruatta, Benedicto Theodore Piekarsa, Gabriel Jonatan Christian, Jeremia Edbert, Ivan Sebastian Gunawan, Alexander Agung Santoso School of Computer Science Bina Nusantara University Cyber Security Program Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350327762

At this time, the development of information and communication technology has mostly been used maximally to improve the quality of life of citizens around the world. The benefits that are obtained make some cities evolve into smart cities in improving living standards and provide services in the health sector because it can control information technology and communication and cybersecurity challenges that are always evolving in every era. However, Behind the developments and benefits of it all, there are risks that cannot be avoided. Risk and these threats can be overcome through the national spectrum by implementing cybersecurity in the virtual world in developing the city into a smart city. Therefore, to respond to cybersecurity in smart cities, cybersecurity must evolve in the same direction, so that the strategy that has been formed will become the basis and reference in implementing cyber security in support of smart city development and the challenges that exist. This paper will outline the relationship between the two factors, the significance of cyber security for smart cities, how such cities can be attacked, and how to defend against such attacks. And after conducting the study, the authors reach the conclusion that in order for any smart cities to develop, flourish, and ensure that everyone living there is safe from any threat, cyber security is essential. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Transforming real estate sales and marketing with AReal: Sustainable solutions through augmented reality 9th

Transforming real estate sales and marketing with AReal: Sus...

引用

9th International Conference on computer science and Computational Intelligence, ICCSCI 2024

作者： Sekar Ayu, N. Lavender Nathania, A. Tsalasa Kale, S.M. Permana, Frihandhika Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

The present paper discusses the adoption of Augmented Reality (AR) technology in the real estate industry focusing on the real estate industry. Along with the times, the marketing tactics of the industry are increasingly developing along with the times. Technology is one of the means in developing marketing strategies for the real estate industry, including AR technology. The purpose of Augmented Reality is to offer innovative means to improve efficiency in the marketing operations of the real estate industry. The waterfall approach was used to develop the Augmented Reality project, which is a linear progression from the beginning of the project to the end, starting with using a good 3D model and user interface, implementing markers, adding interactivity, testing, designing the AR layout, and maintaining After analysing the User Experience Questionnaire (UEQ) as a measurement method, we obtained positive evaluations by entering data from 30 respondents. These positive ratings were obtained for all dimensions of AReal augmented reality with above-average scores. The Perspicuity dimension showed a proficient level of clarity and comfort among users, with an average score of 1.908, which is the highest average score among the other dimensions. In contrast, the novelty dimension had the lowest average score of 1. 850 points, but the average score is above average, indicating a positive evaluation. The UEQ dimensions can be categorized into attractiveness, utilitarian quality, and hedonic quality. Practical quality scored the lowest, hedonic quality scored the highest, and attractiveness was somewhere in between. Overall, the results show that user reviews for AReal Augmented Reality are positive across multiple dimensions, with Perspicuity receiving praise and Novity results indicating that the augmented reality experience is well received overall and provides valuable insights for further improvement and development. © 2024 The Authors.

关键词： Commerce

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：