检索结果-内蒙古大学图书馆

2nd international conference on machine learning and data engineering, icmlde 2023

作者： Ghosh, Subhayu Dhar, Sandipan Yoddha, Raktim Kumar, Shivam Thakur, Abhinav Kumar Jana, Nanda Dulal National Institute of Technology Durgapur713209 India Mizoram University Aizawl796004 India

In today's AI-driven era, deep learning (DL) algorithms play a crucial role in automatically detecting life-threatening skin cancers, thereby significantly enhancing survival rates. It makes skin cancer detection using DL algorithms an exciting area of exploration. While much of the prior research has focused on single-model approaches, combining ensembles of multiple models can enhance classification accuracy. Previous studies mainly relied on deep convolutional neural networks (DCNNs), which have limitations in capturing global features. Recent advancements have introduced capsule networks (Caps-Net) and vision transformers (ViT) for more effective feature extraction. In our study, we harness the power of DCNN, Caps-Net, and ViT frameworks to extract diverse image embeddings. These obtained feature vectors work as input data to train an ensemble model based on a majority voting mechanism. This ensemble model consists of five machine-learning models, including Random Forest, XGBoost, SVM, KNN, and logistic regression. The incorporation of this ensemble mechanism leads to a significant improvement in the overall model's performance. It is noteworthy that the proposed ensemble model serves as a lightweight model, which achieves an impressive accuracy of 91.6% when considering the melanoma skin cancer dataset. These results underscore the superiority of our proposed mechanism over individual state-of-the-art (SOTA) models. © 2024 Elsevier B.V.. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Tool for the Implementation of an Educational data Mining Model Applied to Universities

A Tool for the Implementation of an Educational Data Mining ...

引用

international conference on Communication and Applied Technologies (ICOMTA)

作者： Novillo-Rangone, G. A. Montejano, G. A. Garis, A. G. Molina, W. R. Natl Univ Villa Mercedes Villa Mercedes Argentina Natl Univ San Luis San Luis Argentina

ISBN: (纸本)9789811963469;9789811963476

This work proposes a tool for the implementation of an educational data mining model that applies automated machine learning and machine learning interpretability. Starting from the selection between different types of educational problems, the tool: allows semi-automatically building the data set, obtaining an optimized machine learning model using automated machine learning and enabling the explanation of results with machine learning interpretability methods. The proposal allows university institutions to draw conclusions on complex problems, requiring a minimum number of experts in data science and providing a framework for both end users and legal entities to inform themselves about results.

关键词： AutoML data science Educational data mining Educational data mining tool IML

来源：评论

学校读者我要写书评

暂无评论

Comparison and Analysis of the Accuracy of Multiple machine learning Algorithms in the Field of Spam Classification 3

Comparison and Analysis of the Accuracy of Multiple Machine ...

引用

3rd international conference on machine learning and Computer Application, ICMLCA 2022

作者： Liu, Junchen School of Science Qingdao University of Technology Shandong Qingdao266525 China

ISBN: (纸本)9781510664814

With the continuous advancement of science and technology, network data dissemination technology has been rapidly developed, but at the same time, the problem of spam is becoming more and more serious. This paper aims to analyse the classification principle of each machine learning classifier and compare the differences in the classification effect of each classifier. For the classification of spam, this paper mainly does the following aspects of the work: first, the selection of mail datasets and the pre-processing of email text information, the second is the extraction of the text characteristics of the email, The data is then divided into two parts, one for training and one for testing, using each machine to train the model, using the test set to test the model. Finally, parameters such as accuracy, precision, recall, and F1 score are calculated according to the mail classification results, comparing each model. The results show that the best classification effect is the neural network model and the naïve Bayes model, which can obtain better generalization ability in the test data and should be applied more in practice. © 2023 SPIE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Facing-Masonry Surface Biodeterioration through Convolutional Neural Networks 11th

Early Detection of Facing-Masonry Surface Biodeterioration t...

引用

11th international conference of Ar.Tec.

作者： D'Orazio, Marco Gianangeli, Andrea Monni, Francesco Quagliarinie, Enrico UNIVPM Dept Construct Civil Engn & Architecture DICEA Ancona Italy

ISBN: (纸本)9783031718656;9783031718632;9783031718625

Preventive conservation is the proposed and recommended approach to preserve historic building heritage from deterioration problems caused by several types of actions. It is based on data collection, steady monitoring, inspections, and control of environmental agents. Architectural heritage is subjected to many deterioration issues caused by different types of pathologies, among which attention must certainly be paid to the growth of living microorganisms (bio-colonization). Monitoring actions able to represent the evolution of buildings' deterioration state have been proposed and implemented towards the creation of predictive models based on machine learning methods with the aim of reduce the need for major interventions. In this paper is proposed a method for the early detection of microalgae growth on facing-masonry surfaces. Images representing the microalgae growth process on facing-masonry facades, collected during experimental activities in controlled conditions, was used for training and testing a convolutional neural network. The trained model can ensure an accuracy of 83% and is able to recognize the starts of the bio-colonization process on different types of clay bricks. The work shows that by processing these images with the trained convolutional neural network it is possible to disclose the first stage of bio-deterioration phenomena. This work is part of a more extensive research for the early detection of different types of building facade damages and could be implemented for real cases monitoring.

关键词： Biodeterioration Historical Buildings Convolutional Neural Network machine learning Monitoring

来源：评论

学校读者我要写书评

暂无评论

machine learning in additive manufacturing: A comprehensive insight

引用

international Journal of Lightweight Materials and Manufacture 2025年第2期8卷 264-284页

作者： Equbal, Md Asif Equbal, Azhar Khan, Zahid A. Badruddin, Irfan Anjum Department of Mechanical Engineering Gaya College of Engineering Gaya823003 India Department of Mechanical Engineering Faculty of Engineering and Technology Jamia Millia Islamia New Delhi110025 India Mechanical Engineering Department College of Engineering King Khalid University Asir Abha61413 Saudi Arabia

Additive manufacturing (AM) is a technological advancement gaining colossal popularity due to its advantages and simplified fabrication. AM facilitates the manufacturing of complex, light, and strong products from digitized designs. With recent advancements, AM can bring digital flexibility and improved efficiency to industrial operations. Despite the various advantages, there is continuous variation in the qualities of AM products, which remains the main challenge in the wide application of AM. The performance of printed parts is directly influenced by processing parameters, and adjusting the parameters in the AM process can be quite challenging. The barrier can be minimized by proper monitoring of the AM process and precise measurement of AM materials and components, which is difficult to achieve through analytical and numerical models. Current research demonstrates machine learning (ML) and its techniques as a novel way to reduce costs. It also helps achieve optimal process design and part quality using the fundamentals of the AM process. ML is a subcategory of artificial intelligence (AI) that enables systems to learn and improve from measured data and past experiences. The present paper is focused on presenting a broad understanding of the current applications of ML in AM and thus provides a solid background for practitioners and researchers to apply ML in AM. Very few earlier reviews were presented before, but their studies mostly focus on artificial neural network technology and other irrelevant papers. In addition, most papers were published in 2021 and 2022 and were not discussed in earlier reviews. This state-of-the-art review is based on the latest database collected from Web of Science (WoS), Publons, Scopus, and Google Scholar using machine learning and additive manufacturing as the keywords. Extensive information collected on the possible applications of ML in AM shows that ML can be effectively applied to improve AM part quality and process reliabilit

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Evaluating Differential Privacy in Federated learning Based on Membership Inference Attacks 10

Evaluating Differential Privacy in Federated Learning Based ...

引用

10th international conference on Big data Computing and Communications, BIGCOM 2024

作者： He, Peng Wang, Xinyu Zhang, Weijiao Wang, Zhongkai Wang, Song Ou, Chuangxin Li, Guozheng Beijing Institute of Technology Beijing China China Academy of Railway Sciences Cooperation Limited Beijing China The Center of National Railway Intelligent Transportation System Engineering and Technology Beijing China PICC Information Technology Company Limited Beijing China

ISBN: (纸本)9798331509538

While machine learning has achieved tremendous success, the privacy security of its models faces challenges. To protect the privacy of machine learning models, researchers have proposed methods such as federated learning and differential privacy. However, the effectiveness of these methods in defending against attacks on model privacy at the practical level has not been comprehensively evaluated. In this paper, we focus on membership inference attacks targeting the privacy of machine learning models. By employing classical black-box membership inference attacks and a white-box membership inference attack proposed in this paper, we evaluate the privacy performance of the federated differential privacy framework in scenarios where privacy attacks are actively defended. Experimental results demonstrate that compared to centralized learning with differential privacy methods, models trained using the federated differential privacy framework exhibit stronger privacy performance and higher utility. We investigate the impact of differential privacy implementation mechanisms and privacy budgets on the privacy performance of federated learning models, providing insights and guidance for selecting critical privacy mechanisms and parameters in the practical application of the federated differential privacy framework. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Review and Meta-Analysis of machine learning Applications in Screening for Diabetic Retinopathy Analysis

Comprehensive Review and Meta-Analysis of Machine Learning A...

引用

2024 IEEE international Students' conference on Electrical, Electronics and Computer Science, SCEECS 2024

作者： Siddiqui, Ahmad Talha Kaur, Harleen Naaz, Sameena Tanveer, Safdar School of Engineering & Technology Department of Computer Science & Engineering New Delhi110062 India

ISBN: (纸本)9798350348460

The leading cause: diabetic retinopathy global blindness, affects 10% to 24% of individuals with type 1 or type 2 diabetes in primary care. Early detection using deep learning methods is critical for timely intervention and preserving vision. Our comprehensive review, including a meta-analysis, evaluates the effectiveness of these algorithms in DR detection. This study extensively assessed machine learning's diagnostic accuracy in identifying diabetic retinopathy across diverse cases using color fundus images, aiming to pinpoint the most advanced ML strategy available. We extensively reviewed relevant literature from January 2015 to December 2022, utilizing EMBASE, PubMed, Google Scholar, and Scopus. Following PRISMA guidelines, we focused on machine learning-based study designs. Two authors independently assessed articles for inclusion based on predefined criteria, and data were collected using a standardized form. The meta-analysis reveals strong performance of machine learning in detecting diabetic retinopathy in color fundus photos, indicating readiness for clinical use. However, caution is advised due to methodological limitations in some earlier studies, such as lack of external validation and potential biases in participant selection © 2024 IEEE.

关键词： diabetic retinopathy feature extraction machine learning

来源：评论

学校读者我要写书评

暂无评论

machine learning-Based Smart Home data Analysis and Forecasting Method

Machine Learning-Based Smart Home Data Analysis and Forecast...

引用

IEEE international conference on Consumer Electronics (ICCE)

作者： Park, Sanguk Kangwon Natl Univ Dept Elect Informat & Commun Engn Samcheok South Korea

ISBN: (纸本)9781665491303

The goal of this paper is to enable cost-effective IoT system design by removing and integrating redundant IoT sensors through correlation analysis between sensing data collected in a smart home environment. This paper presents data analysis and prediction technology that induces meaningful inference through data correlation analysis between different heterogeneous IoT sensors installed inside a smart home. Through this, we propose an intelligent service model that can be implemented based on machine learning/deep learning in a smart home environment.

关键词： data analysis Prediction machine learning

来源：评论

学校读者我要写书评

暂无评论

Real Time Bimodal Emotion Recognition using Hybridized Deep learning Techniques 2

Real Time Bimodal Emotion Recognition using Hybridized Deep ...

引用

2nd international conference on machine learning and data engineering, icmlde 2023

作者： Bhat, Akshata A. Kavitha, S. Satapathy, Shashank Mouli Kavipriya, J. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India

Emotion detection has become an important study subject due to the potential uses that it has in many other domains. It incorporates data from various sources, such as facial expressions, voice patterns, physiological indications, and textual signals. To identify human emotions, a real-time bimodal image and audio-based detection-based approach has been proposed. The approach is termed as "bimodal" since images and audio data are considered as inputs to the proposed model. In this study, hybridized CNN-LSTM for the image-based model and Multi-Layer Perceptron is used for the developing audio model. For the image-based model, two combined layers of CNN, and LSTM along with regularization techniques like drop-out, and batch normalization have been adopted for model development. Similarly, for the audio model, the dataset has been fine-tuned using a standard scaler and PCA before training. Based on the combined results of both models, the user's final emotion is determined. Both the audio-based model and the video-based model outperform the existing models discussed in the literature with higher performance accuracy of 79.34% and 77.27% respectively. © 2024 Elsevier B.V.. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Health monitoring data driven prediction of the civil aircraft structural condition

Health monitoring data driven prediction of the civil aircra...

引用

2022 international conference on Statistics, data Science, and Computational Intelligence, CSDSCI 2022

作者： Liu, Yu COMAC Shanghai Aircraft Design & Research Institute No.5188 Jinke Road Zhangjiang Shanghai200120 China

ISBN: (纸本)9781510661325

In order to ensure the structural health of civil aircraft in service, health monitoring systems that can collect large amounts of data to reflect the structural condition of civil aircraft have been put into use, which has led to the "big data" era of structural health monitoring of civil aircraft. The data collected by health monitoring systems is characterized by large capacity, diversity and real-time. The research of advanced theoretical methods to extract effective information from health monitoring data and efficiently and accurately identify the structural health status has become a new problem in the field of structural health monitoring of civil aircraft. Theories such as data-driven deep learning and machine learning, as the latest research results in pattern recognition, have achieved fruitful results in various fields of big data processing with powerful modelling and characterization capabilities. Combining the characteristics of health monitoring data with the advantages of data-driven theoretical approaches, this paper proposes a new method for processing health monitoring data of civil aircraft structures. The method uses machine learning and deep learning algorithms to train structural state prediction models. The advantage of this method is that it is able to extract and make intelligent judgements on the state of the airframe without relying on the processing technology and engineering diagnosis experience of a large amount of collected data. This paper also compares the accuracy of various machine learning and deep learning algorithms, and explores the differences in the weight of the acquisition signals and the dimensionality reduction of the acquisition data. Experimental results show that the method achieves accurate identification and prediction of the number of structural cycle take-offs and landings and crack expansion states in segment-level fatigue testing of aircraft. © 2023 SPIE.

关键词： Structural health monitoring

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：