检索结果-内蒙古大学图书馆

2023 International Conference on Science, Engineering and Business for Sustainable Development Goals, SEB-SDG 2023

作者： Ogundokun, Roseline Oluwaseun Soladoye, Elijah Iseoluwa Asani, Emmanuel Oluwatobi Akande, Oladipupo Ishola, Oluwaseun Joshua Akinwumi, Oyinkansola Aremu, Charity Onye Babatunde, Akinbowale Nathaniel Landmark University Department of Computer Science Omu Aran Nigeria Kaunas University of Technology Department of Multimedia Engineering Lithuania Kwara State University Department of Computer Science Malete Nigeria

ISBN: (纸本)9798350324785

Thanks to innovative sensing systems for smart cities that integrate the future into the present, civilization is through one of its brief transitional phases. The congestion of urban areas necessitates the creation of an adaptable strategy formulation that integrates architecture, creativity, and technology to accommodate paradigm change. A unique sensor approach that is the foundation of a smart parking system (SPS) is provided to enhance accessibility in municipalities with an increasing vehicle pool. The SPS consists of a small single-board computer, a proximity sensor, a camera, a LED indication, a buzzer, and a battery and is designed to determine the availability of a parking spot. This smart transportation technology comprises three major components, specifically sensors, a mobile application, and a monitoring centre, all of which collaborate to monitor, regulate, analyze, and show real-time parking spot information to drivers. Also, the design and execution of the three components of the overall system are shown. © 2023 IEEE.

关键词： Churn prediction classification algorithm Dimensionality reduction Oversampling technique

来源：评论

学校读者我要写书评

暂无评论

Liver Tumour Parameter Prediction Using Feature Extraction and Supervised Function 1

Liver Tumour Parameter Prediction Using Feature Extraction a...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Kumar, Ankit Singh, Kamred Udham Singh, Teekam Banu, Nargis Rathore, Yogesh Kumar Pandey, Saroj Kumar Gla University Department of Computer Engineering & Apllications UP Mathura India School of Computing Graphic Era Hill University Dehradun India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Geetanjali Institute of Technical Studies Dabok Udaipur India India

ISBN: (纸本)9798350330915

The process of extracting features is essential to simplifying and condensing a wide variety of data dimensions while at the same time combining essential factors into a single influential parameter. In the field of medical research, predicting liver tumours represents a daunting task, which calls for the development of a more advanced detection mechanism that is focused towards achieving higher levels of identification precision. Even though experienced medical professionals can make preliminary predictions regarding liver tumours based on their clinical experience and diagnostic tools such as imaging and scans, there is still a compelling need for systematic assistance in making a final decision. This is especially true when evaluating patient symptoms. For the sake of our application, the approach of feature extraction that we have choose to use is called linear discriminant analysis (LDA). LDA displays its usefulness by being able to accommodate classification techniques with more than two classes and by exceeding logistic regression in terms of accuracy of classification. We make use of the power of supervised functions, in particular decision trees and the Naive Bayes algorithm, in order to make an accurate prediction about the existence of liver illness. These algorithms produce predictions regarding the existence of liver disease with a high degree of accuracy by using the factors discovered during LDA analysis. For the purposes of our simulation work, we make use of the flexible scikit-learn library in Python. This library offers a dependable infrastructure for the performance of machine learning activities. The part of this research under 'Methodology and Implementation' digs into the specifics of our approach and outlines the actions that are required to evaluate the effectiveness of our prediction model. © 2023 IEEE.

关键词： classification algorithm feature extraction LDA Linear Discriminant Analysis Liver tumor Supervised function Supervised function

来源：评论

学校读者我要写书评

暂无评论

Validation of the influence of biosignals on performance of machine learning algorithms for sleep stage classification

引用

DIGITAL HEALTH 2023年 9卷

作者： Choi, Junggu Kwon, Seohyun Park, Sohyun Han, Sanghoon Yonsei Univ Yonsei Grad Program Cognit Sci Seoul South Korea Munice Inc Vienna VA USA Yonsei Univ Underwood Int Coll Econ Seoul South Korea Yonsei Univ Dept Psychol Seoul South Korea Yonsei Univ Dept Psychol Seoul 03722 South Korea Yonsei Univ Yonsei Grad Program Cognit Sci Seoul 03722 South Korea

BackgroundSleep stage identification is critical in multiple areas (e.g. medicine or psychology) to diagnose sleep-related disorders. Previous studies have reported that the performance of machine learning algorithms can be changed depending on the biosignals and feature-extraction processes in sleep stage classification. MethodsTo compare as many conditions as possible, 414 experimental conditions were applied, considering the combination of different biosignals, biosignal length, and window length. Five biosignals in polysomnography (i.e. electrocardiogram (ECG), electroencephalogram (EEG), electromyogram (EMG), electrooculogram left, and electrooculogram right) were used to identify optimal signal combinations for classification. In addition, three different signal-length conditions and six different window-length conditions were applied. The validity of each condition was examined via classification performance from the XGBoost classifiers trained using 10-fold cross-validation. Furthermore, results considering feature importance were examined to validate the experimental results in terms of model explanation. ResultsThe combination of EEG + EMG + ECG with a 40 s window and 120 s signal length resulted in the best classification performance (precision: 0.853, recall: 0.855, F1-score: 0.853, and accuracy: 0.853). Compared to other conditions and feature importance results, EEG signals showed a relatively higher importance for classification in the present study. ConclusionWe determined the optimal biosignal and window conditions for the feature-extraction process in machine learning algorithm-based sleep stage classification. Our experimental results inform researchers in the future conduct of related studies. To generalize our results, more diverse methodologies and conditions should be applied in future studies.

关键词： Sleep stage classification polysomnography biosignal machine learning classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Machine Learning Method for Extracting Malicious Web Page Features 11

Research on Machine Learning Method for Extracting Malicious...

引用

11th Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2023

作者： Wang, Lin School of Marxism Hohai University Nanjing China

ISBN: (纸本)9798350333664

Based on the analysis of traditional webpage features of several malicious web pages: webpage URL, JavaScript code, and HTML code, this article defines several features for malicious web page recognition;Proposed several features based on HTTP request information;And a malicious web page recognition method based on feature fusion and machine learning was proposed, which combines HTTP request features with traditional web page features, and then uses machine learning classification algorithms to construct a web page classification model to distinguish between normal and malicious web pages. Select 500 normal web pages from Alexa, and select a total of 500 web pages from PhishTank and Malwaredomains as malicious web pages to construct a dataset and train a web page classification model. Through experiments, it was verified that the method based on URL features, webpage code features, and HTTP request features is superior to the method without HTTP request features, and it was found that the random forest classification algorithm is more suitable for malicious webpage recognition. © 2023 IEEE.

关键词： classification algorithm Feature selection Machine learning Malicious web pages

来源：评论

学校读者我要写书评

暂无评论

A Literature Review on Remaining Useful Life Prediction of Lithium-Ion Batteries 7

A Literature Review on Remaining Useful Life Prediction of L...

引用

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Khandelwal, Kunal S. Shete, Vriendra V. MIT School of Engineering MIT ADT University Ece Deptt. Pune India

ISBN: (纸本)9798350304268

Lithium-ion batteries have evolved into a critical part of the power supply system, and predicting their remaining usable life is critical to ensuring their reliability. Intricate operational characteristics of lithium-ion batteries with the changes with their model parameter as they age, improving the accurateness in the online remaining usable life forecast is hard yet important for the reliable power supply application. We've analyzed research papers in different aspects like: dataset utilized for evaluations, different techniques utilized for Machine Learning, Analysis of SOH prediction, classification of RUL prediction, filtering based methods as well as different data-driven algorithms. The paper also summarizes, each of for accuracy, error, and cost. Moreover, the current challenges faced in the RUL prediction will be rendered, which will stand a milestone for the future investigators. © 2023 IEEE.

关键词： classification algorithm Research Gaps and Challenges Filtering based Methods Lithim-ion batteries Machine Learning (ML) Remaining Useful Life (RUL) State of Charge (SOC) State of Health (SOH) prediction

来源：评论

学校读者我要写书评

暂无评论

From Text to Visuals: Advancements in Depression Prediction Using AI and Machine Learning Techniques

From Text to Visuals: Advancements in Depression Prediction ...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Annapoorani, S. Saravanan, P. Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulatur India

ISBN: (纸本)9798350305708

Social lifestyle and COVID pandemic situation to produce a direct impact on mental health. Depression remains a primary cause of disability worldwide and contributes significantly to the global health burden. It can typically lead to suicidal ideation and have a negative impact on anyone's professional and personal life. Artificial intelligence, machine learning, and deep learning techniques can forecast depression in a timely manner utilizing a variety of resources. Different kinds of sources, such as surveys, social networking sites, video images, and speech, can be used to accurately identify depression without the assistance of a psychiatrist. People on social networking sites express their feelings through appropriate text, which may be examined using machine learning algorithms. Through visual and speech data, deep learning approaches properly provide remarkable accuracy in predicting depression. This survey study is useful in identifying depression accuracy in advanced ways utilizing diverse resources. © 2023 IEEE.

关键词： classification algorithm Deep Learning Depression Ensemble Method Machine Learning

来源：评论

学校读者我要写书评

暂无评论

An efficient approach for clustering and classification for fraud detection using bankruptcy data in IoT environment

引用

International Journal of Information Technology (Singapore) 2021年第6期13卷 2497-2503页

作者： Srikanth, Panigrahi Department of CSE GMR Institute of Technology GMR Nagar Rajam 532127 Andhra Pradesh India

The fraud identification area is distinguished by a classify the data (also known as fraud/legitimate) which are not representative general of the population due to sampling bias. To deal with unsupervised fraud detection (FD) methods, which are uncommon in policies fraud detection studies, we use with these problems with the domain. Our approach consists of applying FD approaches to companies in the same sector and facilitates an effective auditing technique that can be implemented by policy authorities. Therefore, new technology must be researched and evaluated in order to leverage the insight gained from the study for the prediction of fraud and for the creation of systems to avoid fraud with additional checks for minimizing suspicious occurrences. Increased reliance on emerging technology such as Internet of Things (IoT) with FD has compounded the issue in recent years. In this context, the key challenges are to determine the proposed novel similarity measure to satisfy properties, to generate clusters with the proposed measure of similarity and to minimize dimensionality, and to recognize fraud to increase machine efficiency. Our administration involves the regulation issuers to effectively identify illegal activities to protect consumer rights and reduce fraud risks and compliance costs. Our proposed methods are highly efficient and successful have demonstrated real time polish companies data to improve high accuracy and system performance. © 2021, Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： Bankruptcy data classification algorithm Clustering algorithm Dimensionality reduction Fraud detection with IoT Similarity measure

来源：评论

学校读者我要写书评

暂无评论

Comparing Several Pixel-based classification Methods for Vegetation Structural Composition Mapping using Sentinel 2A Imagery in Salatiga Area, Central Java 7

Comparing Several Pixel-based Classification Methods for Veg...

引用

7th Geoinformation Science Symposium

作者： Hadi, Haeydar Anggara Danoedoro, Projo Univ Gadjah Mada Remote Sensing Lab Dept Geog Informat Sci Fac Geog Yogyakarta Indonesia

ISBN: (数字)9781510650411

ISBN: (纸本)9781510650411;9781510650404

Pixel-based classification is considered as a classic method of extracting land-cover related information from remotely sensed imagery, and has been used in various applications, including vegetation mapping. However, several recent studies also mentioned the weakness of the pixel-based approach, including the vegetation index transformation, in mapping the structural composition of vegetation. This study aimed to test several pixel-based classification algorithms for mapping the structural composition of vegetation using Sentinel-2A (10 meters) imagery in Salatiga and its surrounding, Central Java. In this study three classification algorithms, namely Maximum Likelihood, Minimum Distance to Mean, and Support Vector Machine were compared with respect to their accuracy results in mapping the vegetation structural composition. The authors evaluated the effects of additional data in the classification process by comparing two different datasets, i.e. (i) the one using original bands only, and (ii) the one containing original bands and additional data in the form of several vegetation indices and Leaf Area Index (LAI). We collected field samples using stratified random strategy, which were separated into two sub-datasets, as a basis for structural composition classification reference and accuracy assessment. In addition, comparison was also carried out using the original results and the one which was majority filtered. The results showed that the Maximum Likelihood algorithm performed the highest accuracies at a range of 74-86% using a combination of original bands and RVI (Ratio Vegetation Index). The result that was processed using a 5x5 majority filter showed the highest accuracy 86.29%. These results demonstrated that the pixel-based classification of Sentinel 2A imagery using the Maximum Likelihood algorithm could be used to map the structural composition of vegetation in the study area

关键词： Sentinel 2A pixel-based classification vegetation structural composition classification algorithm vegetation index

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Learning algorithm Based on AFS Theory and LogitBoost algorithm 41

Semi-Supervised Learning Algorithm Based on AFS Theory and L...

引用

第41届中国控制会议

作者： Peng Gao Xiaodong Liu School of Control Science and Engineering Faculty of Electronic Information and Electrical EngineeringDalian University of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

There are a wide variety of classification problems in the world,so the classification task has always been a fundamental and important machine learning ***,many scholars have focused on the accuracy and training speed of classification models,while neglecting an important factor of classifier models:*** many cases,it is extremely difficult to collect labeled data,so the use of both labeled and unlabeled data to train classifiers that generate better semi-supervised learning is also the focus of many *** the above reasons,this paper proposes a new classifier,which is based on the axiomatic fuzzy set(AFS) *** not only realizes the interpretability of the fuzzy theory,but also uses the LogitBoost algorithm to verify the inconsistency of the axiomatic fuzzy set theory.

关键词： Semi-supervised Learning Axiomatic Fuzzy Set Theory classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Automatic classification and Coding of Low-Level Events in Nuclear Power Plants Based on Machine Learning 24

Automatic Classification and Coding of Low-Level Events in N...

引用

24th IEEE International Conference on Computer Supported Cooperative Work in Design (IEEE CSCWD)

作者： Zhang, Lian Cai, Hankun Yang, Meng Ying, Qiang Res Inst Nucl Power Operat Operat Technol Res & Evaluat Ctr Wuhan Peoples R China Shaoxing K3i Technol Co Ltd Zhuji Peoples R China

ISBN: (纸本)9781728165974

At present, Experience Feedback Systems have been established in all currently operating and under construction nuclear power plants, and as such, a large number of low-level events have been collected. Due to human and material constraints, these low-level events have not been well utilized. The main problem is that the number of low-level events is so large that it is impossible to code all events manually. In this paper, through the use of seven classification learning algorithms, automatic coding research on low-level events of nuclear power plants is carried out to demonstrate the feasibility of applying a classification learning algorithm to the field of nuclear power text processing. This paper first introduces low-level events in nuclear power plants, low-level event trend coding, and the classification algorithms based on machine learning and deep learning used in this study. Then, comparative experiments are designed and the results of the experiments are analyzed in detail. Finally, based on the results of this study, suggestions for the use of artificial intelligence in the field of nuclear power text processing are proposed. This study provides a reference for the application of machine learning in the field of nuclear power texts processing.

关键词： Nuclear Power Plant Status Report Automatic classification Coding Bert Machine Learning Deep Learning classification algorithm

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：