检索结果-内蒙古大学图书馆

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

User Experience Design of Mobile Application for Tuberculosis Care and Prevention in Indonesia 2

User Experience Design of Mobile Application for Tuberculosi...

引用

2nd International Conference on Technology Innovation and Its Applications, ICTIIA 2024

作者： Felix Universitas Mikroskil Computer Science Program Informatics Faculty Medan Indonesia

ISBN: (数字)9798350351613

ISBN: (纸本)9798350351613

User experience (UX) is a major concern in m-health (mobile health) application design. In the global attempt to eliminate Covid-19, m-health apps play a remarkable role. With the same spirit, tuberculosis (TB) as the world's top infectious killer after Covid-19 can be suppressed. Unlike Covid-19 where the patient can be either cured or killed in less than a month, TB need at least 6 months to be cured for the first stage of treatment. TB are highly contagious and easily spread in the poor hygiene condition. The purpose of this research is to design a user-oriented UX design. The design then can ease programmers working with Health Ministry or healthcare units to develop a fully functioning m-health app. In order to produce a user-oriented UX design, the research uses design thinking methodology. © 2024 IEEE.

关键词： COVID-19

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

Model of Text-to-Text Transfer Transformer for Hadith Question Answering System 11

Model of Text-to-Text Transfer Transformer for Hadith Questi...

引用

11th International Conference on Information Technology, computer and Electrical Engineering, ICITACEE 2024

作者： Sulistio, Bambang Suhartono, Derwin Soeparno, Haryono Budiharto, Widodo Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Computer Science Program Jakarta11480 Indonesia

ISBN: (纸本)9798350389289

The advancement of Artificial Intelligence (AI), notably in Natural Language Processing (NLP), has been remarkable. Among its applications, Question-Answering (QA) systems stand out, assisting users in accessing pertinent information across various topics, including religious contexts. Religion plays a significant role in providing guidance on moral values to modern society, such as tolerance, compassion and social norms. Religious practices taught by religion serve as significant foundations for addressing the increasingly advancing influence of technology. The primary goal of this paper is to create a question-answering system proficient in analyzing user inquiries and precisely extracting data from translated Indonesian Hadith datasets. This research endeavors to enhance question-answering accuracy through Deep Learning techniques. Employing pre-processing methods, the system interprets user query intents. Furthermore, the Text-to-Text Transfer Transformer (T5), a text-based language Transformer model, is utilized to streamline the retrieval process for Hadith-related queries based on relevant subjects. The research findings demonstrate the precision of answers through BLEU and ROUGE scores. The novelty of this study lies in the creation of a dataset of hadith translations in Indonesian and the fine-tuning of the T5 model that has been trained using a dataset of questions and answers based on these translations. This research demonstrates the following evaluation scores: BLEU: 0.606, ROUGE-1: 0.702, ROUGE-2: 0.548, and ROUGE-L: 0.701, indicating that the answers generated by this particular research model are better compared to those produced using the standard mT5 model. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Effects of Different Optimizations at Detection of Vehicles and Pedestrians with YOLOv8 8

Effects of Different Optimizations at Detection of Vehicles ...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Iren, Ecem İzmir Kavram Vocational School Computer Programming Program İzmir Turkey

ISBN: (纸本)9798331531492

Improvements in deep learning has facilitated traffic management by providing analyzing and prediction capabilities on the road. In this study, vehicle and pedestrian detection with YOLOv8 was carried out with different optimizations such as Adam, Stochastic Gradient Descent (SGD) and RMSprop, at the end of the experiments, the model with SGD which produced 87.1 % in mAP was seen as the best optimizer when compared with others at detecting objects. © 2024 IEEE.

关键词： Adam optimization deep learning pedestrian detection RMSprop Optimization SGD optimization vehicle detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Classification of Coleoptera through Keras and TensorFlow 24

Convolutional Neural Network Classification of Coleoptera th...

引用

10th International Conference on Computing and Artificial Intelligence, ICCAI 2024

作者： Angelia, Randy Echavez Torres, John Louie B. Cagadas, Cristelle Ann G. Manigo, Annalee Computer Engineering Program College of Engineering Education University of Mindanao Philippines

ISBN: (纸本)9798400717055

An application was developed to address the time-consuming and subjective nature of physical examination and human judgment to classify the diverse families of Coleoptera more efficiently. Specifically focusing on the Coleoptera families in the Philippines, the application utilizes a Convolutional Neural Network (CNN)-based model as its classification architecture. To enhance the accuracy of the CNN model, researchers gathered images of Coleoptera from various families. The program achieves an impressive 94.44% accuracy rate and has demonstrated successful results in classifying Coleoptera families. This application offers a more streamlined and reliable approach to Coleoptera classification, benefiting researchers and enthusiasts. © 2024 ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ESG Investing: A Statistically Valid Approach to Data-Driven Decision Making and the Impact of ESG Factors on Stock Returns and Risk

引用

IEEE Access 2024年 12卷 69434-69444页

作者： Teja, Kamurthi Ravi Liu, Chuan-Ming National Taipei University of Technology International Program of Electrical Engineering and Computer Science Taipei10608 Taiwan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei10608 Taiwan

This study examines the impact of environmental, social, and governance (ESG) factors on economic investment from a statistical perspective, aiming to develop a tested investment strategy that capitalizes on the connection between ESG factors and financial performance. ESG investing: A statistically valid approach to data-driven decision-making (ESGI-SVADDM) investment strategy is based on a rigorous, statistically valid approach that utilizes data, math, statistics, and data science libraries to drive investment decisions, eliminating the need for personal opinions and subjectivity. The process includes establishing an investment thesis, formulating testable hypotheses (HPS), retrieving and refining relevant data, calculating relevant measures, and testing and validating all hypotheses. The study uses S&P 500 stock data and ESG data from Sustainalytics to test the hypotheses. The empirical tests conducted revealed a negative correlation between ESG risk and expected returns, as well as a positive trend in the relationship between ESG risk and the overall risk of stocks. Moreover, the study found that higher ESG risk scores are associated with lower returns for investors, and that adopting a strategy of investing in stocks with low ESG risk and shorting stocks with high ESG risk yields superior returns compared to the market portfolio. © 2013 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Predictive Analytics for Future Air Pollution Levels Based on Population Growth 9th

Predictive Analytics for Future Air Pollution Levels Based o...

引用

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

作者： Yeshe, Darel Wairooy, Irma Kartika Makalew, Brilly Andro Computer Science Department School of Computer Science Jakarta11480 Indonesia Mobile Application & Technology Program Computer Science Department School of Computer Science Jakarta11480 Indonesia

Air is very beneficial and crucial for every living creature on earth, hence it is very important to protect the air quality in order to avoid diseases. However, due to the increase in population, some human activities have been causing detrimental damage to the air quality. Some people have realized the potential impact of this problem and have done studies on predicting future air pollution. Some implemented machine learning models such as random forest regression, support vector machine, etc, while others have utilized deep learning models in their research.. This study will implement five different models, specifically linear regression, ridge regression, random forest regression, and multilayer perceptron regression. There will be two datasets used in this paper which will be merged and processed. There will be three key evaluation metrics being used in this paper namely root mean squared error, mean absolute error, and r-squared. The results from all of the models have concluded that more optimization and factors are needed in order to boost the final result of this study. © 2024 The Authors.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Identification of Clustering BRISK Keypoint Feature in Grocery Product Using the Elbow Method

Identification of Clustering BRISK Keypoint Feature in Groce...

引用

2024 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2024

作者： Rahmania, Rissa Anggreainy, Maria Susan Kartowisastro, Iman Herwidiana Budiharto, Widodo Computer Science Department BINUS Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798350353464

In smart retail, the problem in grocery product image classification is fine-grained image representation. Product variants are characterized by differences in color, text, and size. However, while the process of image classification involves quite complex stages, there is still a misclassification of grocery products. This is because there are many areas of the image being calculated, which makes the models not optimally calculate the most important area. This paper aims to identify a number of patch image formations as an important area of the product by involving Binary Robust Invariant Scalable Keypoints (BRISK) as a feature descriptor, K-Means Clustering, and the elbow method. First, we experiment with the BRISK keypoint feature for grocery products with different categories of brands. Second, the keypoint features are clustered using K-Means clustering. Lastly, the number of clusters is analyzed using the elbow method to find the optimal number. The result shows that the number of clusters from 8 products has variations of 5, 5, and 6 clusters. Finally, each cluster represents an important area in forming patches to support fine-grained grocery product image classification. ©2024 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Parallelization of LSTM-GRU Architectures for Multivariate Prediction of Stock Prices 9

Parallelization of LSTM-GRU Architectures for Multivariate P...

引用

9th International Conference on Information Management and Technology, ICIMTech 2024

作者： Tarigan, Gabriel Asael Hermawan, Eric Girsang, Abba Suganda Bina Nusantara University BINUS Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350390025

Anticipating stock market movements is challenging, as hasty prediction risks large financial losses. Stock price prediction is complex due to the high volatility and many influencing external factors. Recurrent Neural Network (RNN) models are made to learn time series data making it ideal for stock prediction based on records. Well-known RNN architectures for forecasting problems are Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). However, past studies only explored standalone models and have not generated convincing performance results. By integrating the efficiency of GRU to effectively handle shorter data sequences with LSTM's ability to capture long-term dependencies, our model aims to improve stock price forecasting accuracy by collaborating the strength between both architectures. The proposed model was used to forecast multivariate stock prices and evaluated using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). We found that parallelization of LSTM-GRU offers better prediction, up to 9.1% improvement compared to sequential LSTM-GRU and Bidirectional LSTM (Bi-LSTM). © 2024 IEEE.

关键词： Mean square error

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：