检索结果-内蒙古大学图书馆

2023 IEEE World AI IoT Congress, AIIoT 2023

作者： Haines, Samantha Eaton, Eric Ali, Md Liakat Rider University Dept. of Computer Science and Physics LawrencevilleNJ United States

ISBN: (纸本)9798350337617

Breast cancer is among the most common forms of cancer, representing 30% of cancer cases in the United States per year and is the leading cause of cancer-induced mortality. Diagnosis is determined through biopsies followed by analysis of histopathological images. Machine Learning (ML) proves to be an essential image classification tool, with Convolutional Neural Networks (CNN) providing high accuracy, but long training time. To provide optimal ML models for medical use and evaluate model performance, unstructured images are converted to structured data. Singular Value Decomposition extracted features from 277,524 histopathological images and Recursive Feature Selection reduced the dimensionality of the resultant dataset. Logistic Regression, Decision Tree, XGBoost, K-Nearest neighbours and Multi-layer Perceptron ML models were trained and evaluated. K-Nearest neighbours had the highest accuracy of 77.94%. While these models do not have optimal accuracy for real world applications, their exceptional speed provides support for further improvement and exploration. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

The metric-aware kernel-width choice for LIME 1

The metric-aware kernel-width choice for LIME

引用

Joint 1st World Conference on eXplainable Artificial Intelligence: Late-Breaking Work, Demos and Doctoral Consortium, xAI-2023: LB-D-DC

作者： Barrera-Vicen, Aurelio Paluzo-Hidalg, Eduardo Gutiérrez-Naranjo, Miguel A. Dept. Computer Science and Artificial Intelligence University of Seville Spain Dept. Applied Mathematics I University of Seville Spain

Local Interpretable Model-Agnostic Explanations (LIME) are a well-known approach to provide local interpretability to Machine Learning models. LIME uses an exponential smoothing kernel based on the kernel width value, which defines the width of the local neighbourhood. In this paper, we study the influence of the distances for these local explanations, and we explore the choice of kernel width to guarantee a fair performance comparison between the distances. © 2023 CEUR-WS. All rights reserved.

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Complete Visibility Algorithm for Luminous Robots on Grid 11

Asynchronous Complete Visibility Algorithm for Luminous Robo...

引用

11th International Symposium on Computing and Networking Workshops, CANDARW 2023

作者： Kim, Yonghwan Katayama, Yoshiaki Wada, Koichi Nagoya Institute of Technology Dept. of Computer Science Nagoya Japan Hosei University Dept. of Applied Informatics Tokyo Japan

ISBN: (纸本)9798350306941

An autonomous mobile robot system is a distributed system consisting of mobile computational entities (called robots) that autonomously and repeatedly perform three operations: Look, Compute, and Move. Various problems related to autonomous mobile robots, such as gathering, pattern formation, or flocking, have been extensively studied to understand the relation between each robot's capabilities and the solvability of these problems. In this study, we focus on the complete visibility problem, which involves relocating all the robots on an infinite grid plane so that each robot is visible to every other robot. We assume that each robot is a luminous robot (i.e., has a light with a constant number of colors) and opaque (not transparent). In this paper, we propose an algorithm to achieve complete visibility (i.e., every robot can observe all the other robots) when a set of robots is given. The algorithm ensures that complete visibility is achieved even when robots operate asynchronously and have no knowledge of the total number of robots on the grid plane using only two colors. © 2023 IEEE.

关键词： Visibility

来源：评论

学校读者我要写书评

暂无评论

The Use of Encryption to Preserve the Privacy and Security of Electronic Health Records 2

The Use of Encryption to Preserve the Privacy and Security o...

引用

2nd International Conference on Business Analytics for Technology and Security, ICBATS 2023

作者： Naz, Naila Samar NCBA&E Dept. of Computer Science Lahore Pakistan Applied Science Private University Applied Science Research Center Amman11937 Jordan

ISBN: (纸本)9798350335644

Cloud computing is the storage of data over the Internet rather than locally on a user's device, and it is one of the most extensively used applications of computers and related technologies in today's world. Since cloud computing became publicly available, its popularity has risen. End customers may be able to obtain a better application that is more convenient, less expensive, and both effective and efficient because of cloud computing. When storing and managing sensitive data, it is critical to select a storage and management solution that provides security and privacy safeguards. Patients have long been maintained on the cloud, but the data has always been protected by ciphertext encryption. One of the most challenging challenges in a cloud computing environment is the need to protect users' online activities as well as their personal information. The healthcare system was created with the intention of addressing the demands of medical practitioners by providing a solid foundation, simple means to obtain patient information, and efficient ways to use the system. This work describes, with implementation details, an innovative approach for establishing a reliable and effective e-health cloud model employing identity-based encryption. This approach is suggested in this article. The time, power, and energy requirements for encryption and decryption of the suggested strategy were estimated and compared to those of the currently used method. It has been demonstrated that the cryptographic approach presented can reduce the time required for data decoding by up to 50%. Because the decryption process is quicker, the cryptographic procedures may be conducted with less power. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT MODELING OF POLARIZED REFLECTION SPECTRA IN METASURFACES USING DEEP LEARNING FRAMEWORKS

引用

UPB Scientific Bulletin, Series A: applied Mathematics and physics 2025年第1期87卷 189-198页

作者： Ilie, Alexandra Mănăilă-Maximean, Doina Dănilă, Octavian Faculty of Engineering in Foreign Languages National University of Science and Technology POLITEHNICA of Bucharest Romania Dept. of Physics National University of Science and Technology POLITEHNICA of Bucharest Romania Academy of Romanian Scientists Romania Faculty of Applied Sciences National University of Science and Technology POLITEHNICA of Bucharest Romania

Modeling the electromagnetic responses of metasurfaces, advanced materials engineered to manipulate electromagnetic waves, remains computationally intensive, particularly for complex geometries such as polygonal and ringlike designs. This study explores the potential of frequency-domain prediction, followed by spectral transformation, as a viable approach for capturing x-and y-polarized reflection spectra of metasurfaces. To this end, a deep learning framework is developed, combining Variational Autoencoders (VAEs) and Convolutional Neural Networks (CNNs). The VAE effectively encodes spectral features in a low-dimensional latent space, while the CNN utilizes residual connections to directly map metasurface patterns to their spectral responses. By integrating frequency-domain representations with inverse Fourier transforms, the framework ensures compatibility with traditional time-domain data while maintaining computational efficiency. The proposed models achieve high predictive accuracy, with the VAE outperforming the CNN across multiple error metrics. This dual focus on methodological development and performance evaluation demonstrates the feasibility and advantages of integrating machine learning for rapid and precise metasurface analysis and design. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Automating Neural Model Selection in Spiking Neural Networks Using AutoML Techniques 22

Automating Neural Model Selection in Spiking Neural Networks...

引用

22nd International Learning and Technology Conference, L and T 2025

作者： Sanaullah Honda, Hirotada Roy, Kaushik Schneider, Axel Wasmuth, Joachim Jungeblut, Thorsten University of Applied Sciences and Arts Dept. of Mathematics and Engineering Bielefeld Germany Toyo University Dept. of Information Networking Tokyo Japan A&T State University Dept. of Computer Science NC United States

ISBN: (纸本)9798331532215

The selection of optimal neural models in Spiking Neural Networks (SNNs) traditionally depends on a trial-and-error approach, which is both time-consuming and sometimes tends to suboptimal selection of the neural model. This research study explores the integration of Automated Machine Learning (AutoML) techniques into SNNs to simplify the process of designing an SNN model by automatically selecting the most optimal neural model. For example, in traditional neural networks, AutoML proves that it has the potential to significantly reduce the time and effort required to identify the best-performing architectures, by automating the selection and updating of loss functions and hyper-parametric values. To this end, we present a stand-alone framework for applying AutoML in SNNs, highlighting how this approach can improve accuracy, efficiency, and reliability in the selection process of optimal neural models, as these neural models are the core principle of designing SNN architecture. The proposed method not only accelerates the development of SNN models but also enhances their performance by systematically identifying optimal configurations that might be overlooked through manual methods. Therefore, to validate our approach, the proposed architecture was tested using different well-known benchmarks with different sets of neurons, ranging from 100 to 3000 neurons, and demonstrated state-of-the-art results in image classification tasks. © 2025 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Topic Modelling using Latent Dirichlet Allocation (LDA) and Analysis of Students Sentiments 20

Topic Modelling using Latent Dirichlet Allocation (LDA) and ...

引用

20th International Joint Conference on computer science and Software Engineering, JCSSE 2023

作者： Ishmael, Ontiretse Kiely, Etain Quigley, Cormac McGinty, Donal Atlantic Technological University Dept. Computer Science & Applied Physics Galway Ireland Atlantic Technological University Dept. Department of Analytical Biopharmaceutical Galway Ireland Atlantic Technological University Dept. Computing Services Galway Ireland

ISBN: (纸本)9798350300505

Open-ended question responses are an unstructured data source that contains extremely useful information. The idea of obtaining information using open-ended questions is particularly popular and frequently employed in various schools and digital platforms. In the field of education, universities collect and generate vast amounts of data daily, left unused or not analysed. This demonstrates the need to develop different models to promote the use of text-based data analysis techniques. In this study, surveys with open-ended questions were used to draw out analytical insights from student views on automated personalised feedback assessments. Opened-ended questions present questions that require answers that use natural language. The human language data described in text documents is made possible by the use of various Natural Language Processing (NLP) approaches. These approaches include the Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) that analyse open ended questions and surveys data. In this study, LDA is used for modelling topics to analyse students' sentiments on the feedback assessment given to them regarding their performance on the module. Providing automated personalised feedback to large student groups has many challenges, such as the type of communication delivery mode and the language used for feedback about their progress. This study offers an application of NLP in an education environment to provide meaningful and useful student feedback. The paper presents the steps, algorithm and findings so that practitioners can apply this model to their education setting. The findings reveal 87% of students have positive sentiments, 7% are neutral, 5% are confused by the personalised feedback forms. This informs practitioners about the value of the feedback but also areas for future work when offering feedback to students. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Software Defect Predictor and Classifier Tool Using Machine Learning Techniques

Software Defect Predictor and Classifier Tool Using Machine ...

引用

2023 IEEE International Conference on Network, Multimedia and Information Technology, NMITCON 2023

作者： Shankar, Sahana P. Pushp, Divyansh Makadia, Nemi Dubey, Raghav Nayak, Anusha Shashikant Chaudhari, Shilpa Ramaiah University of Applied Sciences Dept. of Computer Science and Engineering Karnataka Bangalore India M S Ramaiah Institute of Technology Dept. of Computer Science and Engineering Karnataka Bangalore India

ISBN: (纸本)9798350300826

The Software testing is critical for ensuring the quality of software, but it can consume more than half of a software project's total expenses. This research can help software development teams identify potential bugs early on, leading to efficient and effective software creation. To improve the efficiency of software testing, this report presents research on software defect prediction using a hybrid machine learning algorithm that combines supervised and unsupervised learning techniques. The study used publicly available datasets to train and evaluate various machine learning models, including an ensemble learning model. A comparative analysis was conducted among KNN, Random Forest, Adaboost, Multilayer Perceptron, CNN, and Gaussian Naïve Bayes on different datasets. Feature selection was performed using various methods, including Recurrent Feature Elimination (RFE), SelectKBest, and Correlation, implemented by a tool created to select any feature selection algorithm and compare the results for various combinations with the above mentioned classifiers. The results achieved by the model are showed in detail for each of the algorithms on the selected datasets. The main objectives of the research are to create a tool to apply various machine learning techniques to the datasets and determine the most effective ones, as well as to explore different feature selection methods for improving the accuracy of defect prediction. © 2023 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Multilingual Sentiment Analysis using DistilBert

Multilingual Sentiment Analysis using DistilBert

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Gupta, Nishi Bhattarai, Mandip Chavan, Abhishek Pimpri Chinchwad College of Engineering Dept. of Applied Science and Humanities Maharastra Pune India Pimpri Chinchwad College of Engineering Dept. of Computer Engineering Maharastra Pune India

ISBN: (纸本)9798331517953

In today's virtual age, studying feelings and sentiments through textual content and emojis is essential. This research article explores a way to use natural language processing (NLP) techniques to interpret feelings from textual content and emoji content. We used the distilbert-base-uncased-finetuned-sst2english version, a small variant model of BERT, to categorize feelings as positive or negative. Our experiments confirmed that the version executed extraordinarily properly throughout more than one language, with especially great effects on Indonesian textual content. Our assessment confirmed that the version has an excellent accuracy of91.50% and an F1 rating of 91.44% for Indonesian, highlighting its wonderful overall performance in this language. It additionally plays properly in English, French, German, Arabic, and Italian, even though overall performance may also range through language. These effects reveal the version's effectiveness for duties, social media monitoring, client comments evaluation, and inventory marketplace fashion assessment. We finish with a conclusion about the results of those findings. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Supermarket Refrigeration Systems using Transformer Models: A Comparative Study

Anomaly Detection in Supermarket Refrigeration Systems using...

引用

2024 Lock-in or log out? Wie digitale Souveranitat gelingt, INFORMATIK 2024

作者： Meyer, Melina Gergeleit, Martin Krechel, Dirk RheinMain University of Applied Sciences Dept. Design Computer Science Media Kurt-Schumacher-Ring 18 Wiesbaden65197 Germany

ISBN: (纸本)9783885797463

This study investigates anomaly detection methods in supermarket refrigeration systems. A transformer-based model is introduced in this field and compared with LSTM autoencoders. The models are trained and evaluated using preprocessed refrigeration data, with parameters optimized for accuracy, recall, precision and F1 score. Our findings aim to enhance system monitoring and maintenance strategies, ultimately improving reliability, energy efficiency, and operational excellence in supermarket refrigeration technology. © 2024 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Retail stores

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：