检索结果-内蒙古大学图书馆

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

Optimizing the Use of Technology in Efforts to Improve Public Health, Especially with Appropriate Food Calorie Intake 9th

Optimizing the Use of Technology in Efforts to Improve Publi...

引用

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

作者： Lo, Yossy Frenlie Fernandi, Fery Saputri, Hanis Amalia Sari, Azani Cempaka Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

NutriFitPal is a web-based online application developed to help someone monitor and control their calorie intake and maintain a healthy lifestyle. This web application was built using React TypeScript for frontend development and Firebase for backend operations. The main features contained in this web application are user authentication, real-time data storage, an extensive food database, and personalized calorie recommendations based on individual user data. In testing its reliability and functionality, this web application carries out black-box testing and System Usability Scale (SUS). Future improvements will focus on incorporating user feedback and expanding the food database. © 2024 The Authors.

关键词： Food ingredients

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Encoder-Based Pretrained Models: Investigating the Performance of BERT Variants in Indonesian Question-Answering

Comparative Analysis of Encoder-Based Pretrained Models: Inv...

引用

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

作者： Islamey, Javier Jonathan, Vannes Nurzaki, Muhammad Lucky, Henry School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350368451

Question-Answering (QA) is an NLP task designed to answer questions automatically. In Indonesian QA systems, various methods, such as rule-based, semantic-based, and machine-learning approaches with deep learning, have been implemented. The unique linguistic features of Bahasa Indonesia may pose significant challenges for some of these methods. Additionally, research on generative QA systems using pre-trained models in Bahasa Indonesia is underexplored compared to English. To address these issues, this paper aims to develop a deep learning-based question-answering system for Bahasa Indonesia using a sequence-to-sequence approach with pre-trained Bidirectional Encoder Representations from Transformers (BERT) models. The proposed solution implements IndoBERT, IndoRoBERTa, and mBERT in an encoder-decoder architecture with each BERT model as both the encoder and the decoder. The models employ different weight configurations as part of an ablation experiment. The models are then evaluated on the SQuAD-ID dataset. Results have shown that IndoBERT2BERT with pre-trained weights in both encoder and decoder have consistently outperformed every model on BLEU, ROUGE-N, BERTScore, EM, and F1. This proves IndoBERT2BERT's capability to generate texts that are lexically and semantically similar to the target answer while capturing relevant information. Findings also show that IndoBERT2BERT is particularly capable of handling longer answers, showcasing its ability to work with complex passages. © 2024 IEEE.

关键词： Question answering

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

Advancements in Remote Sensing Image Dehazing: Introducing URA-Net with Multi-Scale Dense Feature Fusion Clusters and Gated Jump Connection

引用

computer Modeling in Engineering & sciences 2024年第9期140卷 2397-2424页

作者： Hongchi Liu Xing Deng Haijian Shao School of Computer Jiangsu University of Science and TechnologyZhenjiang212003China Department of Electrical and Computer Engineering University of NevadaLas Vegas89119USA

The degradation of optical remote sensing images due to atmospheric haze poses a significant obstacle,profoundly impeding their effective utilization across various *** methodologies have emerged as pivotal components of image preprocessing,fostering an improvement in the quality of remote sensing *** enhancement renders remote sensing data more indispensable,thereby enhancing the accuracy of target *** defogging techniques based on simplistic atmospheric degradation models have proven inadequate for mitigating non-uniform haze within remotely sensed *** response to this challenge,a novel UNet Residual Attention Network(URA-Net)is *** paradigmatic approach materializes as an end-to-end convolutional neural network distinguished by its utilization of multi-scale dense feature fusion clusters and gated jump *** essence of our methodology lies in local feature fusion within dense residual clusters,enabling the extraction of pertinent features from both preceding and current local data,depending on contextual *** intelligently orchestrated gated structures facilitate the propagation of these features to the decoder,resulting in superior outcomes in haze *** validation through a plethora of experiments substantiates the efficacy of URA-Net,demonstrating its superior performance compared to existing methods when applied to established datasets for remote sensing image *** the RICE-1 dataset,URA-Net achieves a Peak Signal-to-Noise Ratio(PSNR)of 29.07 dB,surpassing the Dark Channel Prior(DCP)by 11.17 dB,the All-in-One Network for Dehazing(AOD)by 7.82 dB,the Optimal Transmission Map and Adaptive Atmospheric Light For Dehazing(OTM-AAL)by 5.37 dB,the Unsupervised Single Image Dehazing(USID)by 8.0 dB,and the Superpixel-based Remote Sensing Image Dehazing(SRD)by 8.5 *** noteworthy,on the SateHaze1k dataset,URA-Net attains preeminence in overall performance,yieldi

关键词： Remote sensing image image dehazing deep learning feature fusion

来源：评论

学校读者我要写书评

暂无评论

Predictive Modelling on Caloric Expenditure: Exploring Machine Learning Techniques for Enhanced Analysis

Predictive Modelling on Caloric Expenditure: Exploring Machi...

引用

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

作者： Justin, Javier Tan, Kezia Revalina Edbert, Ivan Sebastian Suhartono, Derwin School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331511166

Predicting caloric expenditure accurately remains a significant challenges due to individual variability, which frequently results in mistakes in established approaches such as metabolic computation and self-reported data. This research tackles this issue by examining the efficacy of several machine learning methods for forecasting calorie expenditure. The study compares a variety of models, including Linear Regression, eXtreme Gradient Boosting (XGB), Gradient Boosting Regressor (GBR), Ada Regressor, ExtraTrees Regressor, Random Forest, and Stacking Regressor. The XGBoost model has outstanding performance characteristics, including a mean absolute error (MAE) of 8.494312, mean square error (MSE) of 159.6425, root mean square error (RMSE) of 12.6350, and a high R-squared (R2) score of 0.9603. These results demonstrate that machine learning algorithms can produce more precise forecasts of calorie expenditure than traditional methods. This study improves knowledge and implementation of predictive models in the realm of health by employing sophisticated modeling methodologies. © 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

Enhancing Progressive Diagnosis Prediction in Healthcare with Continuous Normalizing Flows 24

Enhancing Progressive Diagnosis Prediction in Healthcare wit...

引用

33rd Companion of the ACM World Wide Web Conference, WWW 2023

作者： Tan, Yanchao Zhang, Hengyu Zhou, Zihao Ma, Guofang Wang, Fan Liu, Weiming Liao, Xinting Hertzberg, Vicki S. Yang, Carl College of Computer and Data Science Fuzhou University China College of Computer Science Zhejiang University China School of Computer Science Zhejiang Gongshang University China Nell Hodgson Woodruff School of Nursing Emory University United States Department of Computer Science Emory University United States

ISBN: (纸本)9798400701726

Progressive diagnosis prediction in healthcare is a promising yet challenging task. Existing studies usually assume a pre-defined prior for generating patient distributions (e.g., Gaussian). However, the inferred approximate posterior can deviate from the real-world distribution, which further affects the modeling of continuous disease progression over time. To alleviate such inference bias, we propose an enhanced progressive diagnostic prediction model (i.e., ProCNF), which integrates continuous normalizing flows (CNF) and neural ordinary differential equations (ODEs) to achieve more accurate approximations of patient health trajectories while capturing the continuity underlying disease progression. We first learn patient embeddings with CNF to construct a complex posterior approximation of patient distributions. Then, we devise a CNF-enhanced neural ODE module for progressive diagnostic prediction, which aims to improve the modeling of disease progression for individual patients. Extensive experiments on two real-world longitudinal EHR datasets show significant performance gains brought by our method over state-of-the-art competitors. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review: Object Detection in Semi-Autonomous Car 6

A Systematic Literature Review: Object Detection in Semi-Aut...

引用

6th International Conference on computer and Informatics Engineering, IC2IE 2023

作者： Sunjaya, Eric Kurniadi Daniel, Christian Kurniawan, Afdhal Anggreainy, Maria Susan School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia Bina Nusantara University Binus Graduate Program Doctor of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350345162

Traffic accidents are a serious problem in developing countries. These accidents can be caused by poor infrastructure and the arrogance of drivers. In addition, semi-autonomous systems are automotive technologies that have been developed in recent years and are starting to be implemented in existing vehicles. This literature review paper will mainly discuss how object detection works in semi-autonomous systems, how semi-autonomous systems operate, and whether semi-autonomous cars can reduce the number of traffic accidents. Its main objective is to build driver confidence in semi-autonomous systems by assisting in driving and supporting the development of them. In the process of writing this paper, the method we use follows the guidelines stated in the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Protocols (PRISMA-P). © 2023 IEEE.

关键词： neural network object detection semi-autonomous car semi-autonomous system

来源：评论

学校读者我要写书评

暂无评论

Analyzing Microservices and Monolithic Systems: Key Factors in Architecture, Development, and Operations 6

Analyzing Microservices and Monolithic Systems: Key Factors ...

引用

6th International Conference on computer and Informatics Engineering, IC2IE 2023

作者： Christian, Juan Steven Kurniawan, Afdhal Anggreainy, Maria Susan School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia Bina Nusantara University Binus Graduate Program Doctor of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350345162

Microservices and monolithic systems are two prevalent architectural approaches in software development. This study provides a complete review and analysis of the key components involved in design, development, and operation in software development. A systematic review of the literature was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. This review examined various sources debating monolithic systems vs microservices, highlighting their benefits, drawbacks, and implementation in enterprises. The paper addresses important research questions, aiming to further analyze this architectural approach. Findings show that microservices offer benefits such as scalability, flexibility, and independent deployment, while monolithic systems provide simplicity and ease of development. However, challenges related to network communication, data consistency, and operational complexity were also found with microservices. This research focuses on discussing the trade-offs and factors to consider when deciding between monolithic systems and microservices, which provides in-depth information for practitioners in decision-making for software development. This research aims to help readers understand the effects of using monolithic or microservice-based systems in software development. © 2023 IEEE.

关键词： benefits drawbacks implementation Microservices Monolithic Systems PRISMA

来源：评论

学校读者我要写书评

暂无评论

Improving Maritime data: A Machine Learning-based Model for Missing Vessel Trajectories Reconstruction

引用

IEEE Transactions on Vehicular Technology 2025年第6期74卷 9565-9576页

作者： Chen, Jin Liang, Maohan Peng, Chang Zhang, Jixin Huo, Shengxu Sanya Institute Hunan University of Science and Technology China Department of Civil and Environmental Engineering National University of Singapore Singapore Singapore College of Computer Science and Electronic Engineering Hunan University China School of Computer Science Hubei University of Technology China

Advancements in maritime satellite technology have significantly impacted the maritime industry, enhancing both communication and safety at sea. These technological improvements have enabled Automatic Identification Systems (AIS) to transmit data through robust maritime communication networks. However, despite these advancements, AIS data often contain significant missing data due to limitations in both devices and network coverage. To overcome these limitations, this research presents an innovative approach for reconstructing missing points. In this paper, we first extracted the geometric shape and motion characteristics of vessels and constructed a decision tree using an adaptive sparse constraint mechanism to classify four types of vessel trajectories. Then, the vessel classification findings serve as input and the vessel acceleration features are constructed using the heading and velocity features of the trajectories at both ends. Finally, We employ a bidirectional Gate Recurrent Unit (GRU) network to simultaneously train on historical trajectory data. The method progressively shortens the reconstructed trajectory, thereby enhancing the accuracy of the reconstruction. In this paper, comparative experiments are conducted with several algorithms across various dimensions, including algorithm performance, trajectory types, and navigation scenarios. It is indicated by the experimental results that the algorithm discussed in this study outperforms baselines. Significant methodological advancements in vessel trajectory reconstruction are represented by this study, which also shows promising potential for application in intelligent maritime transportation systems. © 1967-2012 IEEE All rights reserved.

关键词： Waterway transportation

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

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

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：