检索结果-内蒙古大学图书馆

4th International Conference on Novel and Intelligent Digital Systems, NiDS 2024

作者： Dritsas, Elias Trigka, Maria Mylonas, Phivos Athena Research and Innovation Center Industrial Systems Institute Patras Greece Department of Informatics and Computer Engineering University of West Attica Athens Greece

ISBN: (纸本)9783031733437

In the era of Big Data and Artificial Intelligence (AI), the unprecedented scale and complexity of data collection, processing, and analysis pose significant privacy challenges. This paper presents a survey, providing a comprehensive and focused overview of privacy-enhancing technologies (PETs) designed to mitigate these challenges and ensure the protection of sensitive information. We explore cryptographic and non-cryptographic techniques including differential privacy (DP), homomorphic encryption (HE), secure multi-party computation (SMPC), and federated learning (FL). Each of these techniques is examined in terms of its basic principles and advantages. Also, some key challenges and ethical issues for implementing PETs are briefly discussed. Finally, we conclude the survey by denoting our future research directions in the field. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Comparison of Transformer Based and Traditional Models on Sentiment Analysis on Social Media Datasets 6

Comparison of Transformer Based and Traditional Models on Se...

引用

6th International Conference on computer and informatics engineering, IC2IE 2023

作者： Lubis, Arif Ridho Fatmi, Yulia Witarsyah, Deden Politeknik Negeri Medan Department of Computer Engineering and Informatics Medan Indonesia School of Industrial and System Engineering Telkom University Bandung Indonesia

ISBN: (纸本)9798350345162

In the field of computers and natural language processing, there is an interesting sub-field, namely sentiment analysis. Currently, the use of social media Twitter to actively communicate between individuals contains various review data, opinion data, and emotional data from discussions of topics between users on social media. So that the data generated by Twitter social media can identify patterns in the data for the field of sentiment analysis. In the sentiment analysis sub-sector, there are approaches, namely transformer-based models and traditional models, the traditional model includes the naïve Bayes algorithm, support vector machine, and regression have weaknesses in overcoming data complexity in Indonesian language tweets on Twitter social media while the transformer model includes the BERT (Bidirectional Encoder Representations from Transformers) algorithm is often applied because it has advantages in overcoming the complexity of Indonesian sentences in tweets obtained from social media and in the process this model goes through a training stage with large amounts of data then is adjusted in the concept of sentiment analysis. © 2023 IEEE.

关键词： bert naïve bayes sentiment analysis social media

来源：评论

学校读者我要写书评

暂无评论

Electrohysterogram Data Augmentation Using Generative Adversarial Network for Pregnancy Outcome Prediction

引用

IEEE Access 2025年 13卷 92468-92482页

作者： Cheema, Muhammad Omar Din, Zia Mohy Ud Imran, Azhar Khan, Fawad Salam Al-Rawi, Mahmood Basil A. El-Meligy, Mohammed Gul, Jahan Zeb Air University Department of Biomedical Engineering Islamabad44000 Pakistan Air University Faculty of Computing & AI Department of Creative Technologies Islamabad44000 Pakistan King Saud University College of Applied Medical Sciences Department of Optometry Riyadh Saudi Arabia Amman Arab University College of Computer Science and Informatics Amman Jordan Maynooth University Department of Electronic Engineering Ireland

There are many difficulties in managing and detecting preterm pregnancies, especially in the early stages. Analyzing electrohysterogram data, which show the electrical activity of uterine muscles, is a promising non-invasive method for classifying term and preterm pregnancies. However, the effectiveness of machine learning classifiers is hampered by the inherent class imbalance in datasets. In order to overcome this constraint, this study uses a Generative Adversarial Network to produce high-quality synthetic EHG data while maintaining the statistical properties of actual signals. By successfully reducing class imbalance, the enhanced dataset makes it possible for machine learning models to be trained with resilience. Real and synthetic features did not differ significantly, according to statistical validation using a t-test (p > 0.05). With this method, the Random Forest classifier obtained a ROC-AUC of 0.99 and a 10-fold cross-validation accuracy of 98%. The suggested GAN-based method’s simplicity and efficacy demonstrate its promise for resolving class imbalance and developing reliable classification systems for diagnostic applications. © 2013 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of the Invasive Weed Optimization K-Means Algorithm With Particle Swarm Optimization K-Means for Banking Data 6

Performance Comparison of the Invasive Weed Optimization K-M...

引用

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

作者： Suwirmayanti, Ni Luh Gede Pivin Putra, I. Ketut Gede Darma Sudarma, Made Sukarsa, I. Made Setyaningsih, Emy Department of Computer Systems Faculty of Informatics and Computer Institut Teknologi dan Bisnis STIKOM Bali Bali Indonesia Department of Information Technology Faculty of Engineering Udayana University Jimbaran Hill Bali Indonesia Department of Electrical Engineering Faculty of Engineering Udayana University Jimbaran Hill Bali Indonesia Department of Computer Systems Engineering Faculty of Applied Science Universitas AKPRIND Indonesia Yogyakarta Indonesia

ISBN: (纸本)9798331539603

Banking produces extensive and diverse data, so a clustering process is needed to understand customer behavior patterns and transactions more effectively. This clustering has been widely utilized with the K-Means algorithm due to its simplicity and efficiency. However, this algorithm is limited in determining the optimal cluster center, affecting the accuracy of the clustering results. This study proposes applying two metaheuristic algorithms, Invasive Weed Optimization (IWO) and Particle Swarm Optimization (PSO), as additional solutions combined with K-Means. These two algorithms were chosen because of their ability to find global solutions and convergence speed to handle large and complex banking data. The results show the superiority of IWOKM compared to PSOKM in terms of SSE and DBI. From the SSE value, IWOKM produces a lower value (3029.77), which indicates that this method is better at minimizing clustering errors and producing more accurate clustering than PSOKM (80007.09). From the DBI value, IWOKM also produces a better value (1.6684) than PSOKM (1.6782), which shows that the clusters produced by IWOKM are more compact and more separated. However, in terms of computation time, PSOKM is more efficient, with a faster average computation time. Although IWOKM produces better clustering quality, PSOKM offers advantages in terms of processing speed. This finding confirms that the selection of the IWO algorithm is more appropriate for use on datasets with characteristics such as the German Credit Dataset. © 2024 IEEE.

关键词： Invasive weed optimization

来源：评论

学校读者我要写书评

暂无评论

Combination of CRITIC and PROMETHEE II Methods as An Early Detection of Potential Dropout Students 6

Combination of CRITIC and PROMETHEE II Methods as An Early D...

引用

6th International Conference on Information and Communications Technology, ICOIACT 2023

作者： Yusa, Mochammad Coastera, Funny Farady Rahmadani, Deni Sari, Julia Purnama Kusrini, Kusrini Hartanto, Anggit Dwi University of Bengkulu Faculty of Engineering Department of Informatics Bengkulu Indonesia University of Bengkulu Faculty of Engineering Department of Information System Bengkulu Indonesia Universitas Amikom Yogyakarta Magister of Informatics Engineering Faculty of Computer Science Yogyakarta Indonesia Universitas Amikom Yogyakarta Faculty of Computer Science Department of Information System Yogyakarta Indonesia

ISBN: (纸本)9798350315639

Dropout (DO) has negative implications for individuals and educational institutions. The field of education data mining (EDM) offers valuable contributions to prevent dropout cases and improve student retention. This study focuses on implementing EDM to identify students at risk of dropping out by integrating academic activity criteria with real-time data sources. Previous studies have encountered limitations in classification and clustering techniques, with classification relying on labeled training data (supervised learning) and clustering constrained by attribute or criteria weight (unsupervised learning). This study aims to address these limitations by combining the PROMETHEE II ranking approach and the CRITIC weighting method, producing a list of students with dropout potential. The results can aid stakeholders in implementing preventive measures. The study involves several steps: 1) Collecting data through integration with academic portals;2) Filtering and selecting criteria for student academic activities;3) Transforming and normalizing the data;4) Applying automatic weighting using CRITIC;5) Calculating criteria rankings using the PROMETHEE II technique;and 6) Validating the ranking outcomes. © 2023 IEEE.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Exploring Network Dynamics: Community Detection and Influencer Analysis in Multidimensional Social Networks

Exploring Network Dynamics: Community Detection and Influenc...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Kanavos, Andreas Vonitsanos, Gerasimos Karamitsos, Ioannis Al-Hussaeni, Khalil Ionian University Department of Informatics Corfu Greece University of Patras Computer Engineering and Informatics Department Patras Greece Rochester Institution of Technology Dubai United Arab Emirates Rochester Institute of Technology Computing Sciences Department Dubai United Arab Emirates

ISBN: (纸本)9798350362480

In the digital era, multidimensional social networks have become integral to daily communication, catering to diverse relational needs, from interpersonal to professional and commercial. This study utilizes two comprehensive datasets from Twitter to explore and visualize user interactions within these networks. Focusing on advanced community detection algorithms, we apply the Louvain and Label Propagation methods to delineate the structure of these communities and identify influential users effectively. Through systematic analysis, our research reveals significant insights into the dynamics of network clusters and the pivotal role of influencers. We demonstrate that community structures significantly influence in formation dissemination and user engagement, providing key data to optimize digital communication strategies in complex environments. The findings underscore the importance of strategic influencer engagement and tailored community management in enhancing interaction within multidimensional social networks. Additionally, our results suggest that understanding the network's structural nuances can aid in developing targeted interventions that leverage influencer capabilities to maximize communication impact, illustrating potential applications across various sectors, including marketing, politics, and public health. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Utilizing Different Predictive Methods to Optimize Hyperledger Fabric Instance 2

Utilizing Different Predictive Methods to Optimize Hyperledg...

引用

2nd International Conference on computer System, Information Technology, and Electrical engineering, COSITE 2023

作者： Aqid, Bukhori Muhammad Chacko, Jeeta Ann Jacobsen, Hans Arno Department of Computer Science University of Indonesia Jakarta Indonesia Department of Informatics Technical University of Munich Munich Germany Electrical and Computer Engineering University of Toronto Toronto Canada

ISBN: (纸本)9798350343069

This paper explores the use of reinforcement learning and various machine learning techniques to optimize the configurations of Hyperledger Fabric v2 Channels and Orderers. Our goal is to increase the average throughput and success rate. To achieve this, we train multiple optimization agents using different algorithms, such as Q-learning and Deep Q Network. These agents interact with a Hyperledger Fabric v2 instance in a single host environment, using FabCar as the smart contract and Hyperledger Caliper as the benchmark platform. Based on the data collected from our reinforcement learning agents, we observed that the agents tend to choose larger batch sizes to optimize their results. Our training data also suggests that it is possible to achieve an average throughput of more than 98% for send rates up to 200 TPS. Our prediction results demonstrate that, even with the limitation of training time, reinforcement learning agents can increase the average throughput by around 59% and the average success rate by around 18%, while machine learning models can increase the average throughput by around 45% and the average success rate by around 8%, compared to the baseline results provided by the default configuration. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Integration of Advanced AI Chatbots for Biological Pathway Curation

Evaluation and Integration of Advanced AI Chatbots for Biolo...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Azam, Muhammad He, Fei Santosh, Krpns Xu, Dong Popescu, Mihail University of Missouri Department of Electrical Engineering and Computer Science ColumbiaMO United States University of Missouri Department of Health Management and Informatics ColumbiaMO United States

ISBN: (纸本)9798350386226

The rapid expansion of biological literature presents significant challenges in manually curating pathway knowledge from images for biological and medical research. Recent advancements in AI, particularly multimodal AI chatbots like GPT-4V, Claude, and Gemini, offer promising capabilities for image understanding and extraction of biological interactions. This study evaluates the effectiveness of these AI chatbots in curating gene interactions from 50 curated tumor signaling pathway images. Our results highlight the superior performance of GPT-4V, achieving a precision of 0.778, a recall of 0.664, an F1-score of 0.716 in non-directional analysis, and a precision of 0.566, a recall of 0.471, an F1-score of 0.512 in directional analysis. Claude followed with a precision of 0.735, recall of 0.594, and F1-score of 0.6571 in non-directional analysis, and a precision of 0.500, recall of 0.400, and F1-score of 0.445 in directional analysis. Gemini recorded the lowest performance metrics across both analyses. We further developed a model fusion integrating Claude-3 chatbots and our pathway curation pipeline, achieving notable improvements. © 2024 IEEE.

关键词： AI Chatbots Bio-Curation Gene Interactions Precision Oncology Signaling Pathways

来源：评论

学校读者我要写书评

暂无评论

Empowering Early Childhood English Education through Android-Based Transportation Game Prototypes 3

Empowering Early Childhood English Education through Android...

引用

3rd International Conference on Creative Communication and Innovative Technology, ICCIT 2024

作者： Oktavia, Petricia Frindo, Muhamad Meky Pujiati, Tri Nugroho, Fajar Agung Yasser Arafat, Muhamad Pratiangga, Aptanta Pamulang University Departement of Informatics Engineering Tangerang Indonesia University of Trunojoyo Madura Department of English Literature Madura Indonesia Rey Department of Computer Systems Tangerang Indonesia

ISBN: (纸本)9798350367492

This paper presents the design and development of an educational game application aimed at introducing transportation vocabulary in English to early childhood education students. The application development follows a five-stage prototype methodology there are communication, quick planning, modeling quick design, prototype construction, and deployment with feedback. Using photoshop, paint for graphic design, unity for programming, and we developed an Android-based offline-accessible application. The application's effectiveness was evaluated via a questionnaire administered to 35 respondents, resulting in a significant improvement in children's interest in learning English, with an average score of 82.9%. These findings indicate that the educational game application is an effective and engaging tool for teaching transportation vocabulary to young learners, potentially enhancing early childhood education methodologies. © 2024 IEEE.

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Enhancing Classification Algorithm Recommendation in Automated Machine Learning: A Meta-Learning Approach Using Multivariate Sparse Group Lasso

引用

computer Modeling in engineering & Sciences 2025年第2期142卷 1611-1636页

作者： Irfan Khan Xianchao Zhang Ramesh Kumar Ayyasamy Saadat M.Alhashmi Azizur Rahim School of Software Dalian University of TechnologyDalian116620China Faculty of Information and Communication Technology Universiti Tunku Abdul RahmanKampar31900Malaysia College of Computing and Informatics University of SharjahSharjah27272United Arab Emirates Department of Computer Systems Engineering University of Engineering and Applied SciencesSwat19200Pakistan

The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods have become impractical due to their resource *** Machine Learning(AutoML)systems automate this process,but often neglect the group structures and sparsity in meta-features,leading to inefficiencies in algorithm recommendations for classification *** paper proposes a meta-learning approach using Multivariate Sparse Group Lasso(MSGL)to address these *** method models both within-group and across-group sparsity among meta-features to manage high-dimensional data and reduce multicollinearity across eight meta-feature *** Fast Iterative Shrinkage-Thresholding Algorithm(FISTA)with adaptive restart efficiently solves the non-smooth optimization *** validation on 145 classification datasets with 17 classification algorithms shows that our meta-learning method outperforms four state-of-the-art approaches,achieving 77.18%classification accuracy,86.07%recommendation accuracy and 88.83%normalized discounted cumulative gain.

关键词： Meta-learning machine learning automated machine learning classification meta-features

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：