检索结果-内蒙古大学图书馆

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

Fundamental Dynamics of Popularity-Similarity Trajectories in Real Networks

引用

Physical Review Letters 2024年第25期132卷 257401-257401页

作者： Evangelos S. Papaefthymiou Costas Iordanou Fragkiskos Papadopoulos Department of Electrical Engineering Computer Engineering and Informatics Cyprus University of Technology 3036 Limassol Cyprus.

Real networks are complex dynamical systems, evolving over time with the addition and deletion of nodes and links. Currently, there exists no principled mathematical theory for their dynamics—a grand-challenge open problem. Here, we show that the popularity and similarity trajectories of nodes in hyperbolic embeddings of different real networks manifest universal self-similar properties with typical Hurst exponents H≪0.5. This means that the trajectories are predictable, displaying antipersistent or “mean-reverting” behavior, and they can be adequately captured by a fractional Brownian motion process. The observed behavior can be qualitatively reproduced in synthetic networks that possess a latent geometric space, but not in networks that lack such space, suggesting that the observed subdiffusive dynamics are inherently linked to the hidden geometry of real networks. These results set the foundations for rigorous mathematical machinery for describing and predicting real network dynamics.

关键词： Evolving networks Real world networks Evolving network models Self-similarity

来源：评论

学校读者我要写书评

暂无评论

Energy Theft Detection in Smart Grids:Taxonomy,Comparative Analysis,Challenges,and Future Research Directions

引用

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 578-600页

作者： Mohsin Ahmed Abid Khan Mansoor Ahmed Mouzna Tahir Gwanggil Jeon Giancarlo Fortino Francesco Piccialli the Department of Computer Science COMSATS University Islamabad the Department of Computer Science School of ComputingEngineering and Digital TechnologiesTeesside University the Innovative Value Institute Maynooth University the Department of Computer Science Bahria University the School of Electronic Engineering Xidian University the Department of Embedded Systems Engineering Incheon National University IEEE the Department of Informatics ModelingElectronics and SystemsUniversity of Calabria the Department of Mathematics and Applications“R.Caccioppoli” University of Naples FedericoⅡ

Electricity theft is one of the major issues in developing countries which is affecting their economy *** with the introduction of emerging technologies,this issue became more *** many new energy theft detection(ETD)techniques have been proposed by utilising different data mining(DM)techniques,state&network(S&N)based techniques,and game theory(GT)***,a detailed survey is presented where many state-of-the-art ETD techniques are studied and analysed for their strengths and *** levels of taxonomy are presented to classify state-of-the-art ETD *** types and ways of energy theft and their consequences are studied and summarised and different parameters to benchmark the performance of proposed techniques are extracted from *** challenges of different ETD techniques and their mitigation are suggested for future *** is observed that the literature on ETD lacks knowledge management techniques that can be more effective,not only for ETD but also for theft *** can help in the prevention of energy theft,in the future,as well as for ETD.

关键词： Challenges comparative analysis energy theft detection future research directions smart grid taxonomy

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

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

Using Goal-Conditioned Reinforcement Learning with Deep Imitation to Control Robot Arm in Flexible Flat Cable Assembly Task

引用

IEEE Transactions on Automation Science and engineering 2024年第4期21卷 6217-6228页

作者： Li, Jingchen Shi, Haobin Hwang, Kao-Shing Northwestern Polytechnical University School of Computer Science Xi'an710072 China National Sun Yat-sen University Department of Electrical Engineering Kaohsiung81164 Taiwan Kaohsiung Medical University Department of Healthcare Administration and Medical Informatics Kaohsiung80708 Taiwan

Leveraging reinforcement learning on high-precision decision-making in Robot Arm assembly scenes is a desired goal in the industrial community. However, tasks like Flexible Flat Cable (FFC) assembly, which require highly trained workers, pose significant challenges due to sparse rewards and limited learning conditions. In this work, we propose a goal-conditioned self-imitation reinforcement learning method for FFC assembly without relying on a specific end-effector, where both perception and behavior plannings are learned through reinforcement learning. We analyze the challenges faced by Robot Arm in high-precision assembly scenarios and balance the breadth and depth of exploration during training. Our end-to-end model consists of hindsight and self-imitation modules, allowing the Robot Arm to leverage futile exploration and optimize successful trajectories. Our method does not require rule-based or manual rewards, and it enables the Robot Arm to quickly find feasible solutions through experience relabeling, while unnecessary explorations are avoided. We train the FFC assembly policy in a simulation environment and transfer it to the real scenario by using domain adaptation. We explore various combinations of hindsight and self-imitation learning, and discuss the results comprehensively. Experimental findings demonstrate that our model achieves fast and advanced flexible flat cable assembly, surpassing other reinforcement learning-based methods. Note to Practitioners - The motivation of this article stems from the need to develop an efficient and accurate FFC assembly policy for 3C (computer, Communication, and Consumer Electronic) industry, promoting the development of intelligent manufacturing. Traditional control methods are incompetent to complete such a high-precision task with Robot Arm due to the difficult-to-model connectors, and existing reinforcement learning methods cannot converge with restricted epochs because of the difficult goals or trajectories. To

关键词： Manipulators

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

Performance Evaluation of Intrusion Detection System with SVM 6

Performance Evaluation of Intrusion Detection System with SV...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Diaz, Ricky Aurelius Nurtanto Putra, I. Ketut Gede Darma Sudarma, Made Sukarsa, I. Made Department of Computer Systems Faculty of Informatics and Computer Institut Teknologi dan Bisnis STIKOM Bali Bali Indonesia Department of Information Technology Faculty of Engineering Udayana University Jimbaran Hill Bali Indonesia Department of Electrical Engineering Faculty of Engineering Udayana University Jimbaran Hill Bali Indonesia

ISBN: (纸本)9798331539603

Various machine learning techniques have been proposed to improve the effectiveness of Intrusion Detection Systems (IDS), where IDS is one of the important parts of the network that functions to maintain network security. With its various capabilities and reputation, Support Vector Machine (SVM) is often applied in various classification cases. However, it has constraints with accuracy and computing time when it comes to data that has large dimensions. Utilizing metaheuristic techniques is one possibility that researchers can use to solve this problem. To overcome this, in this study, we will evaluate the performance of SVM for the IDS case by utilizing the metaheuristic Grey Wolf Optimization (GWO) algorithm. From the experiments with three different iteration models, the best results of the combination of SVM and GWO were found in a model with 10 GWO iterations and 10 populations with an accuracy of 97.47% using 15 features out of 48 original features of the UKM-IDS20 dataset. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Simulation of optimal methodologies for channel estimation in a MISO RIS-aided system 27

Simulation of optimal methodologies for channel estimation i...

引用

27th Pan-Hellenic Conference on Progress in Computing and informatics with International Participation, PCI 2023

作者： Drampalou, Stamatia Miridakis, Nikolaos Karkazis, Panagiotis Department of Informatics and Computer Engineering University of West Attica 250 Thivon Av. Athens12244 Greece

ISBN: (纸本)9798400716263

Extensive research in telecommunications and especially in wireless systems assisted by reconfigurable intelligent surfaces (RIS) has emerged at the forefront of cutting-edge wireless communications nowadays. RISs are composed of several arrays of passive elements, where their purpose is to receive the transmitted signal and send it to the corresponding receiver. One of the main disadvantages of RIS, due to the various processes performed in the RIS controller, is the channel estimation time. Therefore, research has focused on optimized channel estimation algorithms in multiple input- multiple output (MIMO) systems to reduce channel overhead and estimation time. In a previous publication, we presented the methodologies that have been used for channel estimation and our goal in this research is to simulate the proposed algorithms on a common system and common parameters. The presentation of the operation mode of the optimal channel estimation methodologies is implemented in a multiple input- single output (MISO) system and in a Base Station (BS) -RIS-user channel. Then we will present in detail the results of the comparison of the methods and mention future scenarios that can be tested. © 2023 Owner/Author.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Improving Open Weather Prediction Data Accuracy Using Machine Learning Techniques 14

Improving Open Weather Prediction Data Accuracy Using Machin...

引用

14th International Conference on Information, Intelligence, Systems and Applications, IISA 2023

作者： Tsipis, Evangelos Banti, Konstantina Louta, Malamati Dimokas, Nikos University of Western Macedonia Department of Electrical and Computer Engineering Kozani Greece University of Western Macedonia Department of Informatics Kastoria Greece

ISBN: (纸本)9798350318067

Weather prediction methods have evolved significantly over the past fifty years, including advances in numerical weather prediction, high-performance computing, mesoscale modeling, assimilation of observations from new sources, and ensemble prediction systems. In recent years, machine learning techniques, including Long Short- Term Memory (LSTM) models, have shown promise in improving the accuracy of weather predictions. In this paper, we aim at investigating the use of LSTM models to improve the accuracy of open weather datasets. Our work was conducted as part of the AUGEIAS research project, which aims at capitalizing on research results in the field of Internet of Things (IoT) and Low Power Wide Area Networks (LPWAN). More specifically, the project target is to create a smart ecosystem, utilizing machine learning techniques that will enable and optimize the use of treated wastewater reuse in agriculture. Our research indicates that, within the context of the AUGEIAS project, single-step LSTM models outperform multistep models in enhancing weather prediction accuracy. © 2023 IEEE.

关键词： Internet of things

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：