检索结果-内蒙古大学图书馆

Personality Identification from Social Media Using Ensemble BERT and RoBERTa

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

Evaluation of Deep Convolutional Neural Network-Based Tattoo Detection 7

Evaluation of Deep Convolutional Neural Network-Based Tattoo...

引用

7th International Congress on Ambient Intelligence, Software Engineering, and e-Health and Mobile Health, AmITIC 2024

作者： Jiménez-Delgado, E. Quesada-López, C. Méndez-Porras, A. Lara-Petitdemange, A. Alfaro-Velasco, J. Graduate Program in Computer Science and Informatics University of Costa Rica Costa Rica Technological Institute of Costa Rica Computer Engineering Department Costa Rica School of Computer Science and Informatics University of Costa Rica Costa Rica

ISBN: (纸本)9798350364538

In this study, two deep learning models for automatic tattoo detection were analyzed;a modified Convolutional Neural Network (CNN) and pre-trained ResNet-50 model. In order to achieve this, ResNet-50 uses transfer learning with fine-tuning. The purpose of this study was to evaluate the accuracy, precision, recall, F1-score, and computational efficiency of the system being considered. To augment the dataset included 1000 photos that were equally divided between those showing tattoos and those that did not show tattoos. A k-fold cross-validation approach was employed in training and testing the models. Although custom CNNs are effective, utilizing pre-trained ones like ResNet-50 can offer even better outcomes. Specifically, ResNet-50 attained a higher accuracy (0.86 compared to 0.79), precision (0.85 versus 0.78), recall (0.91 against 0.86), and F1-score (0.91 vis-a-vis 0.86) as compared to custom CNNs. In selecting these models for examination, two main motivations were considered. The first motivation is to see whether transfer learning with a pre-trained ResNet-50 model does well when compared with a customized CNN designed specifically for tattoo detection. Secondly,the intent of this study is to know what advantages can be derived from each approach and their demerits too. Furthermore, it seeks to determine if transfer learning can provide an alternative in contrast to the common CNN techniques with regards to precision and computational efficiency. In this research, two models will be evaluated in order to answer the question of what is better for tattoo detection: transfer learning or designing custom architectures. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

NoSQL Injection Detection Using Deep Neural Network and Principal Component Analysis of Injection Feature Vectors 11

NoSQL Injection Detection Using Deep Neural Network and Prin...

引用

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

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

Evaluation of an agent-based reinforcement learning framework for model-based testing 7

Evaluation of an agent-based reinforcement learning framewor...

引用

7th International Congress on Ambient Intelligence, Software Engineering, and e-Health and Mobile Health, AmITIC 2024

作者： Ramírez-Méndez, Jose Quesada-López, Christian University of Costa Rica Graduate Program in Computing and Informatics San Pedro Costa Rica University of Costa Rica Department of Computer Science and Informatics San Pedro Costa Rica

ISBN: (纸本)9798350364538

This study evaluates an agent-based reinforcement learning framework for model-based testing (MBT). The framework's performance was assessed on three key metrics: effectiveness and efficiency in achieving model coverage objectives, the quantity and uniqueness of generated test cases, and code coverage. The results show improved metrics for the framework compared to traditional testers in model coverage evaluation and test case metrics. Specifically, the framework achieved higher effectiveness and efficiency, generating a higher average number of test cases with a substantial proportion of unique cases, indicating more diverse and thorough testing. Additionally, the framework, along with random and greedy testers, achieved over 70% coverage across branch, method, and line code metrics. The framework showed slightly higher values in method and line coverage compared to other testers. The evaluation highlights the use of agent-based reinforcement learning to support model-based testing in planning test case generation, exploring models using multiple strategies, and learning guided by testing metrics. Future work will focus on further refining the framework learning model, including error coverage evaluation, and testing its applicability across different software systems. © 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 fuzzy transformation approach to enhance active learning for heart disease prediction

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 9957-9973页

作者： de Oliveira, Heveraldo R. Vieira, Antônio Wilson Santos, Laércio Ives Osório Camargos Filho, Murilo César Ya. Ekel, Petr Dangelo, Marcos Flávio S.V. Department of Computer Science UNIMONTES MG Montes Claros Brazil Graduate Program in Computer Modeling and Systems UNIMONTES Montes Claros Brazil Department of Exact Sciences UNIMONTES MG MG Montes Claros Brazil Instituto Federal do Norte de Minas Gerais – IFNMG MG Montes Claros Brazil Graduate Program in Health Sciences UNIMONTES MG Montes Claros Brazil Graduate Program in Informatics Pontifical Catholic University of Minas Gerais MG Belo Horizonte Brazil

When providing patient care, healthcare professionals often rely on interpreting laboratory and clinical test results. However, their analysis is constrained by human capacity, leading to uncertainties in diagnoses. Machine learning has the potential to evaluate a larger amount of data and identify patterns and relationships that may otherwise go unnoticed. However, popular machine learning algorithms typically require abundant and labeled data, which is not always available. To address this challenge, the adoption of active learning allows for the selection of the most relevant instances for training, reducing the need for extensive labeling. Additionally, fuzzy logic offers the ability to handle uncertainties. This paper proposes a novel approach that utilizes fuzzy membership functions to transform data as a pre-processing step for active learning. The objective is to approximate similar instances, specifically for the purpose of prediction, thereby minimizing the workload of human experts in labeling data for model training. The results of this study demonstrate the effectiveness of this approach in predicting heart disease and highlight the potential of using membership functions to enhance machine learning models in the analysis of medical information. By incorporating fuzzy logic and active learning, healthcare professionals can benefit from improved accuracy and efficiency in diagnosing and predicting pacients’ health conditions. © 2024 – IOS Press.

关键词： Fuzzy logic

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

Implementation of the EfficientNet Model for Identification of Wild Edible Plants 4

Implementation of the EfficientNet Model for Identification ...

引用

4th International Conference of science and Information Technology in Smart Administration, ICSINTESA 2024

作者： Anggreainy, Maria Susan Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11530 Indonesia

ISBN: (纸本)9798350376111

Wild plants are plants that are not cultivated but wild plants can be easily found in the neighborhood. However, not all wild plants can be utilized as food crops by the community. Therefore, it is necessary to know what wild plants can be consumed so that people do not have to worry about food availability. The purpose of this study is to determine whether the EfficientNet model can be used to identify wild plants that can be consumed. Experimental results show that the EfficientNet model has an accuracy of 85% in identifying wild plants that can be consumed. © 2024 IEEE.

关键词： convolutional neural network (CNN) edible wild plant EfficientNet image classifier machine learning

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：