检索结果-内蒙古大学图书馆

2022 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2022

作者： Hnoohom, Narit Chotivatunyu, Pitchaya Yuenyong, Sumeth Wongpatikaseree, Konlakorn Mekruksavanich, Sakorn Jitpattanakul, Anuchit Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakorn Pathom Thailand Mahidol University Faculty of Engineering Department of Computer Engineering Nakorn Pathom Thailand University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (数字)9781665473248

ISBN: (纸本)9781665473248

Weapon detection is a difficult task that requires accurate identification of weapon objects in images. The object localization approach is mostly used because it combines a gradient with a convolutional layer to create a map of key locations on the image. This paper presents an Eigen-CAM method to localize and detect objects in an image for a Faster Region-based Convolutional Neural Network (Faster R-CNN) residual neural network (ResNet 50) model, giving a visual explanation. The Internet Movie Firearms Database (IMFDB) was used to train a deep learning model with the Faster R-CNN ResNet 50 model of the pre-trained PyTorch framework. Experimental results indicated that the Faster R-CNN ResNet 50 model achieved the highest mAP of 0.497 with 0.5 IoU. The Eigen-CAM method performed effectively for visual image representation. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Risk Assessment of Pregnancy-induced Hypertension Using a Machine Learning Approach 6

Risk Assessment of Pregnancy-induced Hypertension Using a Ma...

引用

Joint 6th International Conference on Digital Arts, Media and Technology with 4th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunication Engineering, ECTI DAMT and NCON 2021

作者： Wanriko, Sirinat Hnoohom, Narit Wongpatikaseree, Konlakom Jitpattanakul, Anuchit Musigavong, Olarik Mahidol University Image Information and Intelligence Laboratory Faculty of Engineering Department of Computer Engineering Nakhon Pathom Thailand Mahidol University Faculty of Engineering Department of Computer Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Faculty of Applied Science Department of Mathematics Bangkok Thailand Prachin Buri Thailand

ISBN: (纸本)9781665415699

This research aimed to develop a predictive model of the risk assessment of pregnancy-induced hypertension using a machine learning approach. Pregnancy-induced hypertension is a complication that has a serious impact on pregnant women and fetuses. It is the world's top three cause of death among pregnant women [1]. Nowadays, the exact cause of pregnancyinduced hypertension is unknown and therefore cannot be prevented. Early detection and received treatment can reduce the severity and danger. A public dataset of Logan (2020) was used in this research [2] the dataset was collected from a casecontrol study on the determinants of 83 pre-eclampsia and five eclampsia cases among 352 pregnant women delivering in county hospitals in Nairobi, Kenya. According to the dataset, 75 percent of the pregnant women were healthy. Only 25 percent of the pregnant women were pre-eclampsia and eclampsia. Thus, this would result in a problem of an imbalanced classification when one of the two classes had more data than the other class. As such, this problem was resolved with the Synthetic Minority Over-sampling Technique (SMOTE). Risk assessment of pregnancy-induced hypertension was performed on seven machine learning algorithms, which were logistic regression (LR), K-nearest neighbor (KNN), decision tree (DT), random forest (RF), multilayer perceptron neural network(MLP), support vector machines (SVM), and naive Bayes (NB). In the experimental results, RF had the highest accuracy at 89.62 percent compared to other machine learning algorithms. © 2021 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Retrial Queue with Lattice Distribution of Inter-Arrival Times and Constant Retrial Rate

Retrial Queue with Lattice Distribution of Inter-Arrival Tim...

引用

computer Modeling and Simulation, EMS, UKSIM European Symposium on FLAGGED

作者： Che Soong Kim Valentina Klimenok Alexander Dudin Department of Industrial Engineering Sangji University Wonju Korea Department of Applied Mathematics and Computer Science Belarusian State University Minsk Belarus

ISBN: (纸本)9781479974139

In this paper, we extend the result obtained in Kl Kim Dud for retrial queueing system with recurrent arrival flow to the case of periodic arrival process. We consider a single server retrial queueing system with lattice distribution of inter-arrival times, constant retrial rate and exponential service time distribution. For this queue, we derive the stationary distributions of the system states at arrival times and at an arbitrary times and the Laplace-Stieltjes transform of the customer sojourn time distribution. Little's formula for this system is proved. Results can be used for performance evaluation and capacity planning of telecommunication networks where effect of repeated calls is essential.

关键词： Markov processes Servers Orbits Lattices Transforms Queueing analysis Mathematical model

来源：评论

学校读者我要写书评

暂无评论

On the determination of radial electron–electron distribution functions

引用

International Journal of Quantum Chemistry 1972年第1期6卷 181-192页

作者： Benesch, Robert Faculty of Mathematics Department of Applied Analysis and Computer Science University of Waterloo Waterloo Ontario Canada

The problem of evaluating the radial electron–electron distribution function P0(r12) from the spin‐free 2‐particle density matrix P2(r1, r2Ir'1, r'2) is considered in detail. The analysis is first applied t...

The problem of evaluating the radial electron–electron distribution function P₀(r₁₂) from the spin‐free 2‐particle density matrix P²(r₁, r₂Ir'₁, r'₂) is considered in detail. The analysis is first applied to 2‐electron S‐type functions built from l² configurations. For the special case l = 0, the expression for P₀(r₁₂) reduces to the result obtained by Coulson and Neilson. For non‐spherically symmetric states of N‐electron atoms, the angular integrations are handled by a procedure used by Calais and Löwdin in their evaluation of atomic integrals containing functions of r₁₂. Consideration is also given to the evaluation of necessary radial integrals. Copyright © 1972 John Wiley & Sons, Inc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EGRA-NeRF: Edge-Guided Ray Allocation for Neural Radiance Fields

引用

Image and Vision Computing 2023年第1期134卷

作者： Gai, Zhenbiao Liu, Zhenyang Tan, Min Ding, Jiajun Yu, Jun Tong, Mingzhao Yuan, Junqing School of Computer Science Hangzhou Dianzi University Zhejiang Hangzhou310018 China Department of Applied Mathematics School of Science Zhejiang University of Technology Zhejiang Hangzhou310023 China

Recently, Neural Radiance Fields (NeRF) has demonstrated great potential in synthesizing novel views for realistic video generation. However, renderings from NeRF appear excessively blurred and contain aliasing artifacts in some textures or edges. To alleviate this problem, Edge-Guided Ray Allocation (EGRA-NeRF) module is proposed in this paper. Such method proposes a novel ray allocation strategy to focus more rays on the textures and edges of the scene during the training stage. Specially, the Canny edge detector is introduced to generate the ray guidance map. This guidance map can lead the model to find areas with more textures. To focus more rays on edges and textures, a method is explored to re-adjust the ray guidance map and re-allocate rays dynamically. Compared with the ray allocation in most existing NeRF-based methods, EGRA-NeRF focuses rays more on textures and edges, which can achieve the refinement of edges and texture details. Experiments show that NeRF-based algorithms (NeRF and Instant-NGP) with our EGRA module can achieve more realistic video generation, while maintaining almost the same computation time. © 2023

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Optimised one-class classification performance

arXiv

引用

arXiv 2021年

作者： Lenz, Oliver Urs Peralta, Daniel Cornelis, Chris Department of Applied Mathematics Computer Science and Statistics Ghent University Belgium IDLab Department of Information Technology Ghent University - imec Belgium

We provide a thorough treatment of one-class classification with hyperparameter optimisation for five data descriptors: Support Vector Machine (SVM), Nearest Neighbour Distance (NND), Localised Nearest Neighbour Distance (LNND), Local Outlier Factor (LOF) and Average Localised Proximity (ALP). The hyperparameters of SVM and LOF have to be optimised through cross-validation, while NND, LNND and ALP allow an efficient form of leave-one-out validation and the reuse of a single nearest-neighbour query. We experimentally evaluate the effect of hyperparameter optimisation with 246 classification problems drawn from 50 datasets. From a selection of optimisation algorithms, the recent Malherbe-Powell proposal optimises the hyperparameters of all data descriptors most efficiently. We calculate the increase in test AUROC and the amount of overfitting as a function of the number of hyperparameter evaluations. After 50 evaluations, ALP and SVM significantly outperform LOF, NND and LNND, and LOF and NND outperform LNND. The performance of ALP and SVM is comparable, but ALP can be optimised more efficiently so constitutes a good default choice. Alternatively, using validation AUROC as a selection criterion between ALP or SVM gives the best overall result, and NND is the least computationally demanding option. We thus end up with a clear trade-off between three choices, allowing practitioners to make an informed decision. © 2021, CC BY-NC-ND.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

The complexity of approximating critical points of quantum phase transitions

arXiv

引用

arXiv 2021年

作者： Watson, James D. Bausch, Johannes Department of Computer Science University College London United Kingdom Department of Applied Mathematics and Theoretical Physics University of Cambridge United Kingdom

Phase diagrams chart material properties with respect to one or more external or internal parameters such as pressure or magnetisation;as such, they play a fundamental role in many theoretical and applied fields of science. In this work, we prove that provided the phase of the Hamiltonian at a finite size reflects the phase in the thermodynamic limit, approximating the critical boundary in its phase diagram to constant precision is PQMAEXPcomplete. This holds even for translationally-invariant nearest neighbour couplings, and even if the system's phase diagram is promised to have a single critical boundary delineating two phases. For the simpler case of a single parameter, the same problem remains QMAEXP-hard. Our results extend the study of quantum phases to systems with more realistic phase diagrams than previously studied. Furthermore, our findings place complexity-theoretic constraints on the effectiveness of (computational or analytic) methods based on finite size criteria, similar in spirit to the Knabe bound, for the task of extrapolating the properties (e.g. gapped/gapless) of a system from finite-size observations to the thermodynamic *** Codes 68Q17, 81V70 Copyright © 2021, The Authors. All rights reserved.

关键词： Phase diagrams

来源：评论

学校读者我要写书评

暂无评论

Two approaches to machine learning classification of time series based on recurrence plots 3

Two approaches to machine learning classification of time se...

引用

3rd IEEE International Conference on Data Stream Mining and Processing, DSMP 2020

作者： Kirichenko, Lyudmyla Radivilova, Tamara Bulakh, Vitalii Zinchenko, Petro Saif Alghawli, Abed Kharkiv National University of Radio Electronics Department of Applied Mathematics Kharkiv Ukraine Kharkiv National University of Radio Electronics V.V. Popovskyy Dept. of Infocommunication Engineering Kharkiv Ukraine Prince Sattam Bin Abdulaziz University Department of Computer Science Aflaj Saudi Arabia

ISBN: (数字)9781728132143

ISBN: (纸本)9781728132143

The article considers the task of classifying fractal time series based on the construction of their recurrence plots. Short realizations of EEG signals were used as input data. Two classification machine learning methods were considered: in the first case, quantitative fractal and recurrent characteristics of the time series were classification features, in the second case, image recognition of recurrence plots was carried out. The results showed fairly high classification quality for both methods, and relative advantage of the image classification method. © 2020 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Continuing education potential to form research competence of students 1

Continuing education potential to form research competence o...

引用

1st International Scientific Conference on Advances in science, Engineering and Digital Education, ASEDU 2020

作者： Romanov, P.Y. Zlydneva, T.P. Kinzina, I.I. Ryazanova, L.S. Smirnova, L.V. Tsaran, A.A. Department of Applied Mathematics and Computer Science Nosov Magnitogorsk State Technical University pr. Lenina 38 Magnitogorsk Chelyabinskaya obl. Russia Department of Linguistics and Literature Nosov Magnitogorsk State Technical University pr. Lenina 38 Magnitogorsk Chelyabinskaya obl. Russia

The constantly changing labor market requires the formation of specialists with a desire for self-improvement, capable of moving from one type of activity to another, perhaps not related to the previous one. This task can be called a priority in the field of professional education, which dictates its relevance for mathematics education. When setting the formulated problem and solving it, special attention should be paid to recognizing the importance of the formation and development of the educational potential of the creative activity of students. The article presents an analysis of the possibilities of a continuous education system, put forward theoretical provisions and pedagogical conditions for the effective formation of research skills of students within this system. The characteristic of the structural-content model of the formation of the research competence of future teachers (or specialists of other professions requiring the formation of research competencies) in the system of three-level education is given on the example of studying one of the directions of discrete mathematics. © 2020 Institute of Physics Publishing. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

IIoT-based Predictive Maintenance for Oil and Gas Industry 22

IIoT-based Predictive Maintenance for Oil and Gas Industry

引用

Proceedings of the 2022 6th International Conference on Electronic Information Technology and computer Engineering

作者： Zhiyang Jia Jihe Wang Cheng Deng Department of Computer Science China University of Petroleum-Beijing at Karamay China Department of Mathematics West Yunnan University of Applied Sciences China

ISBN: (纸本)9781450397148

The Industrial Internet of Things (IIoT) promises to provide an expanded awareness of field assets and equipment, access to data from across locations, and actionable insights for maximizing operational performance and safety of the oil and gas industry. Using automation and machine learning, with the application of predictive maintenance, efficiencies can be boosted and problems can be mitigated sooner and more effectively. The proposed system is mainly based on the data collection, processing, analysis, and modeling of an enormous number of historical and real-time data generated during the operation of the equipment on the edge side. The data-driven predictive maintenance used machine learning models and deep learning models to predict the remaining useful life (RUL). Bi-LSTM based prediction model has been trained on the cloud, and deployed onto the edge devices. The predictive maintenance process includes data acquisition, data processing, training of machine learning model, equipment health assessment, remaining useful life prediction, strategy formulation, and strategy execution. The predictive maintenance solution driven by the IIoT helps oil and gas companies make predictions before equipment failures have a significant impact on their company's safety level and profits to improve asset reliability and promote cost savings.

关键词： Oil and Gas Industry IIot Long short-term memory Predictive maintenance

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：