检索结果-内蒙古大学图书馆

1st Zimbabwe Conference of Information and Communication Technologies, ZCICT 2022

作者： Mashonga, Aidah Kudzainyandoro, Leslie Zvarevashe, Kudakwashe University of Zimbabwe Faculty of Computer Engineering Informatics and Communication Analytics and Informatics Department Harare Zimbabwe

ISBN: (纸本)9781665475761

The thyroid gland's edge experiences an abnormal proliferation of thyroid tissue, which causes thyroid illness. The two primary types of thyroid disorders are hypothyroidism and hyperthyroidism which typically result when this gland releases excessive amounts of hormones. To identify and diagnose thyroid disease, this study suggests employing effective classifiers and feature selection strategies that consider accuracy and other performance evaluation measures. This study offers a thorough examination of various classifiers that includes the support vector machine, logistic regression, and extreme gradient boosting algorithms. The algorithms use three feature removal strategies that is recursive feature elimination, Pearson's correlation and chi-squared statistics. To determine thyroid illness, thyroid data from the Kaggle datasets were used. Numerous aspects of the experiment have been evaluated and analyzed, including accuracy, precision, and the receiver operating curve's area under the curve. The outcome showed that classifiers that use feature selection have a greater overall accuracy(Xtreme Gradient Boost 98%and support vector machine 95%) compared to without feature selection technique (support vector machine 89%). Logistics regression performed better without at 95% than 94% with feature selection. © 2022 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection using 5L-CNN 1

Fake News Detection using 5L-CNN

引用

1st Zimbabwe Conference of Information and Communication Technologies, ZCICT 2022

作者： Collen, Demo Rangarirai Nyandoro, Leslie Kudzai Zvarevashe, Kudakwashe University of Zimbabwe Faculty of Computer Engineering Informatics and Communication Analytics and Informatics Department Harare Zimbabwe

ISBN: (纸本)9781665475761

With the advent of websites and social media technologies, the internet has been a great method of transmitting news and information around the globe. However, due to lack of editorial scrutiny and monitoring by the media authorities, the news distribution has been seriously abused leading to the fast spreading of fake news. Fake news involves misleading broadcasting of information from sources that target to intentionally manipulate the way how people view some events or statements. This study seeks to develop a fake news detection model which will be able to analyze the title and text information attached to the news articles. From the researches done by previous scholars, it showed that the models did not perform very well because of the lack of sufficient feature extraction and fine tuning of the classification of the text. This research will therefore, articulate the gap by employing 5L-CNN deep learning model which will use inbuilt tokenizers for word embedding and will show better accuracy compared to the traditional machine learning models. In this paper, we compare machine learning algorithms (Decision trees, Random Forest, Logistic Regression & Naive Bayes) and deep learning algorithms (RNN, 5L-CNN & LSTM) to classify the authenticity of news articles. The model developed in this paper attained the best accuracy with 5L-CNN which had a result of 99.99%. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Quadratic Weighted Kappa Score Exploration in Diabetic Retinopathy Severity Classification Using EfficientNet 1

Quadratic Weighted Kappa Score Exploration in Diabetic Retin...

引用

1st Zimbabwe Conference of Information and Communication Technologies, ZCICT 2022

作者： Chivinge, Lincoln Nyandoro, Leslie Kudzai Zvarevashe, Kudakwashe University of Zimbabwe Faculty of Computer Engineering Informatics and Communication Analytics and Informatics Department Harare Zimbabwe

ISBN: (纸本)9781665475761

Diabetic Retinopathy (DR), chronic progressive disease of the eye, may give rise to permanent sight loss. Clinicians use fundus pictures to check if DR is present and rely on physicians to diagnose the stage or severity by visual inspection of the images. In relying on a clinician's subjective prognosis, this is deemed a procedure that takes a lot of time and susceptible to misjudgements. In discovering DR, poor Quadratic Weighted Kappa (QWK) scores have resulted from poor quality of pictures and imbalanced distribution of classes. Even though studies have shown high accuracy, sensitivity, specificity and ROC metrics, their limitation is that they do not consider the level of disparity across the classified labels. The QWK score demonstrates that even if an algorithm presents high accuracy, it is still not best fit to classify DR into its 5 classes. Many researchers have tried fine-tuning the neural network to create noise-resistant deep learning and recorded high accuracy and sensitivity but low QWK scores. The problem with the other methods is mainly pre-processing of the images and model building patterns. Most of the studied literature lacks the image augmentation step which might lead to an erroneous result. This research aims to create an algorithm from deep learning models with a data augmentation step and demonstrate how important it is for attaining better QWK scores for all stages of diabetic retinopathy. The model met study objectives and obtained an accuracy of 93% and a QWK score of 0.961. The outcomes show that the method can make accurate predictions without need for human feature extraction and that it may be used as an early DR diagnostic and staging screening tool. © 2022 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of Covid-19 based on lung CT images using Deep Convolutional Neural Networks (CNN) 1

Automatic detection of Covid-19 based on lung CT images usin...

引用

1st Zimbabwe Conference of Information and Communication Technologies, ZCICT 2022

作者： Mahachi, Shawn Zvarevashe, Kudakwashe Nyandoro, Leslie Kudzai University of Zimbabwe Faculty of Computer Engineering Informatics and Communications Analytics and Informatics Department Harare Zimbabwe

ISBN: (纸本)9781665475761

In recent years, the COVID-19 pandemic has spread all over the world. Due to its rapid transmission, techniques that automatically detect COVID-19 infections and distinguish it from other forms of pneumonia are crucial. The scientific community has embarked on finding solutions to quick detection of COVID-19 through implementation of deep learning(DL) techniques that can diagnose COVID-19 using computed tomography (CT) lung scans. The use of CT images has been widely accepted in medical imaging and it is a pertinent screening tool due to its higher sensitivity in recognizing early pneumonic changes. Also, most developed DL models developed have been end-to-end from feature extraction to categorization of the COVID19 infected images. The proposed model results showed high accuracy rates on both training and testing of the model in COVID-19 classification. A customised ResNet-50 architecture has the best results in classifying the images and achieved state of art accuracy of 97% on training and testing using the COVID dataset with 200 epochs. This work presented a computationally efficient and highly accurate model for multi-class classification of normal and infected individuals. The model can help in effective early screening of COVID-19 cases hence reducing the burden on healthcare systems. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Load balancing and auto-scaling issues in container microservice cloud-based system: a review on the current trend technologies

引用

International Journal of Web engineering and Technology 2023年第4期18卷 294-318页

作者： Rabiu, Shamsuddeen Yong, Chan Huah Syed-Mohamad, Sharifah Mashita School of Computer Sciences Universiti Sains Malaysia Penang Minden11800 Malaysia Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Terengganu Kuala Nerus21030 Malaysia

Load balancing and auto-scaling are essential to cloud features for cloud-based container microservices as they control the number of computing resources available. Many research works have proposed load balancing and auto-scaling approaches for microservices individually;however, they are less likely to propose the two approaches in solving their problems simultaneously. The paper aimed to critically analyse the current issues related to load balancing and auto-scaling in container microservices cloud-based systems. This will open room for researchers in the field to enhance performance for better QoS to the users. We present a comprehensive literature review of the existing techniques used for load balancing and auto-scaling in cloud-based containerised microservice applications. After the in-depth review, it is found that load balancing and auto-scaling contribute as a value-added feature to the microservice applications. This can optimise the issues of Servers overloaded, service failure, traffic spikes, et cetera, during the microservices communication phase. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Insurance Fraud Detection using Machine Learning 1

Insurance Fraud Detection using Machine Learning

引用

1st Zimbabwe Conference of Information and Communication Technologies, ZCICT 2022

作者： Tongesai, MacHinya Mbizo, Godfrey Zvarevashe, Kudakwashe University of Zimbabwe Faculty of Computer Engineering Informatics and Communication Analytics and Informatics Department Harare Zimbabwe

ISBN: (纸本)9781665475761

Many insurance companies today deal with the issue of fraudulent insurance claims, which results in significant yearly financial loss. Since the losses are covered by raising policyholders' premium costs, these frauds have a negative impact on society. The traditional claim investigation procedure has also been blamed for producing unreliable conclusions because it is time-consuming and laborious. Therefore, using machine learning and the XGBoost method, we construct an automated fraud detection application framework in this study. Accurately identifying fraud claims in a shorter amount of time is the goal. Data analysis is utilized throughout the process to validate, sanitize, and extract the pertinent data. As a result, the insurance firm can retain its reputation outside by employing this structure and has a reliable relationship with clients that they can share. © 2022 IEEE.

关键词： Insurance

来源：评论

学校读者我要写书评

暂无评论

Driver drowsiness detection using Convolutional Neural Networks-inspired features and Principal component analysis with K-Nearest Neighbors 1

Driver drowsiness detection using Convolutional Neural Netwo...

引用

1st Zimbabwe Conference of Information and Communication Technologies, ZCICT 2022

作者： Panganai, Marvelous Alexander Nyandoro, Leslie Kudzai Zvarevashe, Kudakwashe University of Zimbabwe Faculty of Computer Engineering Informatics and Communication Analytics and Informatics Department Harare Zimbabwe

ISBN: (纸本)9781665475761

Drowsiness and fatigue are the major reasons for triggering serious and severe road crashes in Zimbabwe and the whole world at large. The developments in technology in recent years brought support and backing to drivers using intelligent automobile systems. Several research studies used datasets of a single driver for training and testing. Some as well used mainly day time images for training and testing the models. Therefore, fatigue and drowsiness is a key possible field of study to prevent numerous number of sleep induced road crashes. In this paper, two methods of feature extraction were proposed which are the MLP (Multilayer - Perceptron), the CNN (Convolutional Neural Network). The PCA (Principal Component Analysis) method was used for dimensionality reduction. Based on these methods, five classifiers where used to detect drowsiness on the driver. The five classifiers used where the LDA, XGBoost, LR, Decision Tree and the K-Nearest neighbors. Experiments were done in order to examine the capacity and usefulness of the approaches contrasted with other techniques. Experimental outcomes demonstrate that the feature extraction technique of CNN provided high accuracy on the five classifiers. The KNN was the average best classifier with a 100% accuracy. Experimental results indicated that the PCA improved the classifiers. This study delivers important and significant answers in practice to curb motor vehicle crashes due to drowsiness. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of RouteSegmentation Algorithm in Identifying Perimeter Area Around Travel Route 16

Performance Analysis of RouteSegmentation Algorithm in Ident...

引用

16th International Conference on Information Technology and Electrical engineering, ICITEE 2024

作者： Bachmid, Muhammad Avied Anshari Haq, Muhammad Yasir Mumtaz, Muhammad Rafly Pinandito, Aryo Universitas Brawijaya Faculty of Computer Science Media Game and Mobile Laboratory Department of Informatics Engineering Malang Indonesia Universitas Brawijaya Faculty of Computer Science Malang Indonesia Universitas Brawijaya Faculty of Computer Science Media Game and Mobile Laboratory Department of Information System Malang Indonesia

ISBN: (纸本)9798350375817

Prior study has developed the RouteSegmentation algorithm to identify the perimeter area surrounding a route. In this study, a comparative experiment was carried out to investigate the performance of the RouteSegmentation algorithm implementation in contrast to the RouteBoxer algorithm. Both algorithms play a crucial role in geographical information systems (GIS), particularly in enhancing navigational tools by identifying points of interest along specified routes. Through systematic experimentation using various perimeter distance values and types of route, the trade-offs between processing efficiency and the granularity of the area identified by these algorithms were evaluated. The results demonstrate that RouteSegmentation maintained relatively consistent performance across different perimeter distance values and statistically significantly faster processing time than RouteBoxer. Furthermore, while the RouteBoxer algorithm benefits from larger perimeter distance values by reducing processing time, it compromises the coverage results of the algorithm and potentially undermines its usefulness in practical scenarios. This study not only provides insights into the optimal use of perimeter distance values for each algorithm but also guides users in selecting the appropriate algorithm based on their specific application needs, balancing detailed geographical analysis and runtime efficiency. © 2024 IEEE.

关键词： Transportation routes

来源：评论

学校读者我要写书评

暂无评论

GLCM Feature Extraction and PCA for Tuberculosis Detection with Neural Network

GLCM Feature Extraction and PCA for Tuberculosis Detection w...

引用

2022 International Seminar on Application for Technology of Information and Communication, iSemantic 2022

作者： Alfa Farah, M. Nafis Hayyin Suristiyanti, Wiwiek Ibad, Sholihul Pramunendar, Ricardus Anggi Fajar Shidik, Guruh Dian Nuswantoro University Faculty of Computer Science Postgraduate Program in Informatics Engineering Indonesia Dian Nuswantoro University Faculty of Computer Science College Teacher in Informatics Engineering Indonesia

ISBN: (数字)9781665488396

ISBN: (纸本)9781665488396

Automatic recognition system for medical images is quite a challenging job in the medical image processing field. X-rays, CT, and MRI all provide medical pictures and other modalities which are utilized for diagnostic purposes. As in medical sector, detecting tuberculosis (TB) is a very important stage before further treatment is carried out. Human interpretation of a vast array of X-ray pictures can result in detection mistakes, so an automatic recognition system is needed that can detect TB disease. In this study, we use a dataset with two classes and extract GLCM-based texture features from each class, and apply them to a two-layer feed-forward neural network, which gives a classification rate of 99%. © 2022 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Forwarding Strategy Performance Using NFD Pipeline Measurements on Vehicular Named Data Networking (V-NDN) 9

Forwarding Strategy Performance Using NFD Pipeline Measureme...

引用

9th International Conference on Wireless and Telematics, ICWT 2023

作者： Ahdan, Syaiful Syambas, Nana Rachmana Iskandar School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung40132 Indonesia Faculty of Engineering & Computer Science Lampung35132 Indonesia

ISBN: (纸本)9798350305029

The Named Data Networking (NDN) paradigm has been used as a promising vehicle communication model, namely the Vehicular Named Data Networking (V-NDN) model. In NDN, delivery of interest in the NDN network is done by selecting an existing interface. The problem is as to which interface is right in terms of fulfilling the request that suits the user. In this study, we compare the effectiveness of each forwarding strategy by creating new scenarios, such as variations in the number of interests and simulation time. We also measure the effectiveness of the forwarding strategy using the parameters specified in the NFD Forwarding Pipeline. The conclusion from the experiment is that superior forwarding strategy recommendations are based on content store (CS) management and data compatibility obtained based on consumer demand for producers. © 2023 IEEE.

关键词： Pipelines

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：