检索结果-内蒙古大学图书馆

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

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

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

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

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

The Impact of Interest Flooding Attack (IFA) and Collusive IFA on Named Data Networking (NDN) 6

The Impact of Interest Flooding Attack (IFA) and Collusive I...

引用

6th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2023

作者： Jupriyadi Mulyana, Eueung Syambas, Nana Rachmana School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Universitas Teknokrat Indonesia Faculty of Engineering and Computer Lampung Indonesia

ISBN: (纸本)9798350358346

Named Data Networking (NDN) is a proposed future Internet architecture that has the advantage of bringing content data closer to users. NDN focuses on securing content data rather than securing transmission channels. The NDN network is also not free from threats and attacks that can disrupt network performance. One of the attacks on the NDN network is a denial of service (DoS) attack. The attacker carries out this attack by sending a large number of request packets. This attack is known as an interest flooding attack (IF A). The IF A attack itself has developed into a collusive IFA to avoid existing detection systems. In this paper, we examine the comparative impact of IF A and CIF A attacks on clients or consumers. Knowing the impact and characteristics of IF A and CIF A attacks can be used as a reference in the attack detection system. Attacks are carried out locally and remotely by looking at 3 types of attacks, namely attacks by sending requests for packets that are on the network, attacks by sending requests for containers that are not available on the net, hybrid attacks, and 1 collusive IF A attack. Based on the exploration carried out, it was found that local attacks had a very significant impact compared to remote attacks. IFA attacks that have a major impact on the network are attacks that send content that is not available on the net. The effect of this attack meant that requests sent by consumers were only served by 40% of the total bids. © 2023 IEEE.

关键词： Denial-of-service attack

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

eduARM: Web Platform to Support the Teaching and Learning of the ARM Architecture 15

eduARM: Web Platform to Support the Teaching and Learning of...

引用

15th International Conference on computer Supported Education, CSEDU 2023

作者： Alves, Maria Inês Araújo, António Duarte Lima, Bruno Faculty of Engineering University of Porto Porto Portugal INESC TEC Department of Electrical and Computer Engineering Faculty of Engineering University of Porto Porto Portugal INESC TEC Department of Informatics Engineering Faculty of Engineering University of Porto Porto Portugal

ISBN: (纸本)9789897586415

computer architecture is a prevalent topic of study in informatics and Electrical engineering courses, though students’ overall grasp of this subject’s concepts is many times hampered, mainly due to the lack of educational tools that can intuitively represent the internal behaviour of a CPU. With the evolution of the ARM architecture and its adoption in higher education institutions, the demand for this sort of tool has increased. Educational tools, specifically developed for the ARMv8 processor, are scarce and inadequate for what is necessary in an academic context. In order to contribute towards solving this problem, eduARM, a practical and interactive web platform that simulates how a ARMv8 CPU functions, was developed and is presented through this paper. Since this tool’s main purpose is to aid computer architecture students, contributing to an improvement in their learning experience, it comprises varied concepts of computer architecture and organization in a simple and intuitive manner, such as the internal structure of a CPU, in both its unicycle and pipelined versions, and the effects of executing a set of instructions. As to better understand its value, the developed tool was then validated through a case study with the participation of computer architecture students. Copyright © 2023 by SCITEPRESS – Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

The Effect of Data Augmentation and Optimization Technique on the Performance of EfficientNetV2 for Plant-Parasitic Nematode Identification

The Effect of Data Augmentation and Optimization Technique o...

引用

2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2023

作者： Shabrina, Nabila Husna Lika, Ryukin Aranta Indarti, Siwi Universitas Multimedia Nusantara Faculty of Engineering and Informatics Department of Computer Engineering Tangerang Indonesia Universitas Gadjah Mada Faculty of Agriculture Department of Plant Protection Yogyakarta Indonesia

ISBN: (纸本)9798350313635

Plant-parasitic nematodes are major agricultural pathogens contributing to massive crop losses worldwide. It is crucial to identify plant-parasitic nematodes to decide the best pest control and management strategy. The current identification technique is based on visual observation from nematode microscopic images done by the nematologist. However, this method requires a long process and is prone to error. A deep learning-based method can be implemented to speed up the current identification process. This study explores the effect of combining several data augmentation techniques, namely brightness, contrast, blur, and noise, on the performance of the EfficientNetV2B0 and EfficientNetV2M models for identifying plant-parasitic nematodes. Moreover, this study also compared three optimizers while training the models to find the best optimizer for each model and data augmentation. The results show that the EfficientNetV2B0 model yielded the highest test accuracy of 96.91% when employing no augmentation and trained using SGD and RMSProp optimizer. Furthermore, the EfficientNetV2M model gave the highest test accuracy of 96.91% when the combination of brightness and contrast augmentations was applied and trained using the RMSProp optimizer. © 2023 IEEE.

关键词： Luminance

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：