检索结果-内蒙古大学图书馆

11th International Conference on computer, Control, Informatics and its Applications, IC3INA 2024

作者： Soegiharto, Irwin Santoso Girsang, Abba Suganda Computer Science Department Binus Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department Binus Graduate Program - Master of Computer Science Binus Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331542313

NoSQL database has gained popularity in Big Data and other various applications for its simplicity and flexibility. The non-relational nature of NoSQL database such as MongoDB proves to improve development lifecycles and resources efficiency. However, security challenges arise along with increasing usage of NoSQL database, and NoSQL database is no exception to injection attacks. Machine learning proved to be an efficient method, as much has been researched. However, in the future there may be an increasing complexity of features that may prove costly to the model’s performance. Therefore, this research aims to utilize principal component analysis as dimensionality reduction and deep neural network as the classification method, to improve the security of NoSQL database. The text query is converted to feature vectors then further processed to reduce the input dimension of the deep neural network using PCA. The features used are based on previous research and various sources, and some are added after analyzing the dataset.10-fold cross validation is also applied to ensure that the model does not overfit the data, attempting to reduce bias to the result. The 10-fold cross validation model accuracy result is in average 97.44% with a standard deviation of 1.7%, and the testing results are 97.5% in accuracy,95.65% in precision, 91.67% in recall, and 93.61% in F1 score. Thus, it can be concluded that the usage of PCA on injection feature vectors can reduce complexity of the model. © 2024 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Integrated Framework for IT Asset Physical Security: A Risk Management Approach Using NIST and ISO Standards

Integrated Framework for IT Asset Physical Security: A Risk ...

引用

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

作者： Alamsyah, Ricky Arifin, Yulyani Bina Nusantara University BINUS Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331511470

This study presents a comprehensive approach to IT asset security risk management in physical access control systems, integrating NIST SP 800-116, 800-53, 800-30, ISO 31000, and 27002:2022 standards. Using a mixed-method approach, we conducted interviews, discussion forums, and observations with IT and security professionals in manufacturing and insurance sectors in Indonesia. Our findings reveal seven key factors crucial for physical security of IT assets, including policies, access authorization, and environmental controls. The study proposes a risk assessment model that determines authentication factor levels based on risk severity. Results indicate discrepancies between current practices and recommended security levels, particularly in server rooms and production areas. We provide a set of control recommendations aligned with ISO 27002:2022 to enhance physical security measures. This research contributes to both theory and practice by offering a holistic framework for managing physical security risks in IT environments, particularly relevant for organizations in emerging economies. © 2024 IEEE.

关键词： ISO Standards

来源：评论

学校读者我要写书评

暂无评论

Analysing the Impact of Rhythm Game in Enhancing Typing Performance 10

Analysing the Impact of Rhythm Game in Enhancing Typing Perf...

引用

10th International HCI and UX Conference in Indonesia, CHIuXiD 2024

作者： Lancaster, Lemuel Arifin, Yulyani Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350380439

The research was centered on adapting and assessing a new, unique game concept. The game onKeys presents a new approach and poses as an alternative method for improving typing skills. However, despite offering a promising avenue, the game still grapples with certain limitations. Utilizing the MDA Framework, the study seeks to integrate additional game components into onKeys and evaluate its effectiveness in improving typing skills. A paired T-test is used to assess the Pre-Test and Post-Test data. The System Usability Scale gathers subjective feedback about the game design's usability. This study found that the onKeys game has little impact on players' typing speed and accuracy, which may be attributed to a higher average typing speed, short period of playtime or a small sample size. However, upon reviewing the record and survey data, particularly the System Usability Score, it becomes evident that the game design still has potential. Further research can delve deeper into this game concept and design. © 2024 IEEE.

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Offensive Language Detection Using Soft Voting Ensemble Model

Mendel

引用

Mendel 2023年第1期29卷 1-6页

作者： Fieri, Brillian Suhartono, Derwin Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Offensive language is one of the problems that have become increasingly severe along with the rise of the internet and social media usage. This language can be used to attack a person or specific groups. Automatic moderation, such as the usage of machine learning, can help detect and filter this particular language for someone who needs it. This study focuses on improving the performance of the soft voting classifier to detect offensive language by experimenting with the combinations of the soft voting estimators. The model was applied to a Twitter dataset that was augmented using several augmentation techniques. The features were extracted using Term Frequency-Inverse Document Frequency, sentiment analysis, and GloVe embedding. In this study, there were two types of soft voting models: machine learning-based, with the estimators of Random Forest, Decision Tree, Logistic Regression, Naïve Bayes, and AdaBoost as the best combination, and deep learning-based, with the best estimator combination of Convolutional Neural Network, Bidirectional Long Short-Term Memory, and Bidirectional Gated Recurrent Unit. The results of this study show that the soft voting classifier was better in performance compared to classic machine learning and deep learning models on both original and augmented datasets. © 2023, Brno University of Technology. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Personality Identification from Social Media Using Ensemble BERT and RoBERTa

引用

Informatica (Slovenia) 2023年第4期47卷 537-544页

作者： Tsani, Eggi Farkhan Suhartono, Derwin Computer Science Department Binus Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Social media growth was fast because many people used it to express their feelings, share information, and interact with others. With the growth of social media, many researchers are interested in using social media data to conduct research about personality identification. The identification result can be used as a parameter to screen candidate attitudes in the company's recruitment process. Some approaches were used for research about personality;one of the most popular is the Big Five Personality Model. In this research, an ensemble model between BERT and RoBERTa was introduced for personality prediction from the Twitter and Youtube datasets. The data augmentation method also introduces to handling the imbalance class for each dataset. Pre-trained model BERT and RoBERTa was used as the feature extraction method and modeling process. To predict each trait in the Big Five Personality, the voting ensemble from BERT and RoBERTa achieved an average f1 score 0,730 for Twitter dataset and 0,741 for Youtube dataset. Using the proposed model, we conclude that data augmentation can increase average performance compared to the model without data augmentation process. © 2023 Slovene Society Informatika. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of LSTM and Transformer for Time Series Data Forecasting 7

Comparison of LSTM and Transformer for Time Series Data Fore...

引用

7th International Conference on Informatics and Computational sciences, ICICoS 2024

作者： Sonata, Ilvico Heryadi, Yaya Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350375886

Time series data is data that is collected periodically and has certain time intervals. Time series data is widely available in the fields of finance, meteorology, signal processing, health, and economics. Weather data, stock prices, and sales data are examples of time series data. Time series data analysis can be used to predict future conditions based on patterns and values from previous data through a forecasting process. These forecasting results are useful for identifying trends and data patterns for decision making. The rapid development of deep learning models can now be used as a method for forecasting time series data. Deep learning models that are suitable for forecasting include sequence-to-sequence models such as Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and Transformer. LSTM and Transformer are sequence-to-sequence models that are widely used for forecasting time series data. Research to compare the accuracy of the two models is still very limited. This article will discuss the use of the LSTM and Transformer models for the time series data forecasting process using Hewlett Packard stock price data from 1962 to 2022. The accuracy results show that the LSTM model outperforms the Transformer model in forecasting Hewlett Packard stock prices. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Passive Identification of Rogue Industrial Access Points Using a One-Class Machine Learning Model 50

Passive Identification of Rogue Industrial Access Points Usi...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： de Paula, André L.S. Viegas, Eduardo K. Santin, Altair O. Graduate Program in Computer Science Pontifical Catholic University of Parana Brazil

ISBN: (纸本)9781665464543

Access point (AP) security has become increasingly important as wireless local area networks (WLANs) proliferate in industrial environments. Rogue APs are often used by attackers to conduct man-in-the-middle (MiTM) attacks. They can redirect users to malicious servers or do eavesdropping and manipulation of their *** this paper, we propose a novel one-class machine learning model to passively identify rogue APs in industrial environments. The implementation of the model is twofold. First, we passively extract the hardware and software characteristics of the evaluated AP according to its generated messages. This results in a comprehensive feature set that captures both low-level and high-level behaviors of the evaluated ***, we apply a one-class machine learning model to identify APs that significantly deviate from the previously known profile of legitimate APs. The combined evaluation of hardware and software behaviors integrated with an outlier detection scheme to effectively identify rogue APs is the insight of our proposal. We demonstrate the feasibility of our model, achieving an F1 score of 0.89 and a true positive rate of 0.9 in experiments conducted on our new publicly available dataset of 357 unique AP behaviors. © 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

A Multi-View Android Malware Detection Model Through Multi-Objective Optimization 23

A Multi-View Android Malware Detection Model Through Multi-O...

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Fransozi, Philipe Geremias, Jhonatan Viegas, Eduardo K. Graduate Program in Computer Science Pontifical Catholic University of Parana Brazil

ISBN: (纸本)9798350374889

Over the past few years, several highly accurate Machine Learning (ML) techniques have been proposed for Android malware detection. Unfortunately, proposed schemes are rarely used in production, a situation usually caused by their limited generalization capabilities, leading to low accuracies when deployed. This paper proposes a new multi-view Android malware detection model, implemented in two stages. First, we extract multiple feature sets from an analyzed Android application package. The feature sets provide a complementary Android app behavioral vector for the classification task, enhancing the system's generalization. Secondly, we conduct a multi-objective optimization to select the optimal feature subset from each view for subsequent ensemble-based classification. Our proposal's insight is to proactively select each feature subset that simultaneously improves accuracy and reduces processing requirements in a multi-view setting. Experiments on our new dataset, comprising over 40 thousand Android app samples, demonstrated the feasibility of our proposal. Our scheme can improve true-positive rates by an average of 4.4 while demanding only up to 65% of inference processing costs. © 2024 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Towards a Feasible Palm Vein Verification Scheme Using Deep Autoencoder and Siamese Networks 23

Towards a Feasible Palm Vein Verification Scheme Using Deep ...

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Nunes, Mateus Viegas, Eduardo K. Santin, Altair O. Pontifical Catholic University of Parana Graduate Program in Computer Science Brazil

ISBN: (纸本)9798350374889

Palm vein pattern recognition offers a unique personal identification feature. Unfortunately, these techniques typically require a Near Infrared (NIR) camera sensor to extract the individual's venous pattern, challenging their wide deployment. This paper proposes a new feasible palm vein verification scheme using a Deep Autoencoder and a Siamese Network, implemented threefold. First, we capture the individual's palm using a traditional visible spectrum camera sensor and perform preprocessing tasks to correct imprecise positioning, easing palm support accessories requirements. Second, we eliminate NIR sensor requirement by fine-tuning a Deep Autoencoder model to convert images from the visible spectrum to their infrared counterparts. Third, generated images are processed by a lightweight Siamese network using a contrastive loss function for individual verification. Experiments conducted on a publicly available dataset with over a hundred individuals confirmed the feasibility of our proposal. Our scheme reaches up to 0.97 of true-negative rate, with only 0.01 decrease compared to traditional NIR-based approaches. In addition, individual identification can be conducted in less than 6 seconds in a resource-constrained environment thanks to our lightweight model's implementation. © 2024 IEEE.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Detection of Narcotics Money Laundering in Suspicious Financial Transactions Using Convolutional Extreme Gradient Boosting (ConvXGB) 4

Detection of Narcotics Money Laundering in Suspicious Financ...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Winarno, Leonardus Verrell Sayoga Kinantra Wibowo, Antoni School of Computer Science Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331506490

With the development of narcotics problems that continue to increase, the Indonesian Government responds through the Badan Narkotika Nasional (BNN) with data showing the condition of narcotics tends to grow every year and is followed by the number of assets of money laundering (ML) crimes against narcotics cases. One of the banks in Indonesia as a reporting party for suspicious financial transactions (SFT) has obstacles in detecting narcotics ML due to complex and rarely found patterns. Some previous studies conducted experiments using Convolutional Neural Network (CNN), Extreme Gradient Boosting (XGBoost), and even a combination of both into Convolutional Extreme Gradient Boosting (ConvXGB), and improved model performance in several datasets. This paper designs a model using the ConvXGB algorithm by adopting the CNN architecture, LeNet-5, by applying several convolution layers and pooling layers as a baseline model for feature learning, and the XGBoost as feature classification. Three phases of research are the preprocessing phase by collecting data, transforming data, balancing data with a hybrid sampling technique, splitting data, and scaling data, followed by the implementation phase by creating a ConvXGB model, training and testing the model, then finally the evaluation phase by analyzing results and hyperparameter tuning. The dataset used is SFT from the bank during 2023. This ConvXGB has three convolution layers, a pooling layer, and a flattened layer. The performance test results are the accuracy value and F1-Score value of 99.11% each after hyperparameter tuning. By performing a hybrid model, the model performance results are better. © 2024 IEEE.

关键词： Laundering

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：