检索结果-内蒙古大学图书馆

Nonlinear Neural Network Based Forecasting Model for Predicting COVID-19 Cases

NEURAL PROCESSING LETTERS 2023年第1期55卷 171-191页

作者： Namasudra, Suyel Dhamodharavadhani, S. Rathipriya, R. Natl Inst Technol Patna Dept Comp Sci & Engn Patna Bihar India Periyar Univ Dept Comp Sci Salem India

The recent COVID-19 outbreak has severely affected people around the world. There is a need of an efficient decision making tool to improve awareness about the spread of COVID-19 infections among the common public. An accurate and reliable neural network based tool for predicting confirmed, recovered and death cases of COVID-19 can be very helpful to the health consultants for taking appropriate actions to control the outbreak. This paper proposes a novel Nonlinear Autoregressive (NAR) Neural Network Time Series (NAR-NNTS) model for forecasting COVID-19 cases. This NAR-NNTS model is trained with Scaled Conjugate Gradient (SCG), Levenberg Marquardt (LM) and Bayesian Regularization (BR) training algorithms. The performance of the proposed model has been compared by using Root Mean Square Error (RMSE), Mean Square Error (MSE) and correlation co-efficient i.e. R-value. The results show that NAR-NNTS model trained with LM training algorithm performs better than other models for COVID-19 epidemiological data prediction.

关键词： Levenberg Marquardt Bayesian regularization Scaled conjugate gradient Forecasting training algorithm Regression

来源：评论

学校读者我要写书评

暂无评论

Prediction of abrasive wears behavior of dental composites using an artificial neural network

引用

COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING 2023年第6期26卷 710-720页

作者： Suryawanshi, Abhijeet Shivaji Behera, Niranjana VIT Sch Mech Engn SMEC Vellore Tamil Nadu India

Resin composites are widely used as dental restorative materials since dental parts are subjected to prolonged wear and ultimately need to be replaced. The objective of this study is to analyze the potential of the feed-forward back propagation artificial neural network (ANN) in assessing the wear of dental composite materials when immersed in chewable tobacco solution, by utilizing the in-vitro test results of the pin-on-disc tribometer [ASTM G99-04]. In this study, four different dental composite material specimens are dipped in a chewable tobacco solution for a few days, and the specimens are removed from the solution for conducting the wear test. Three different training procedures are used to simulate ANN models for predicting the wear of dental composite specimens. The Bayesian regularization training algorithm outperforms the other algorithms significantly. The findings of the ANN modeling were prominently matching with the results of the experiments;therefore, parametric analysis was used based on the model's predicted values.

关键词： Artificial neural network training algorithm wear dental composite chewable tobacco

来源：评论

学校读者我要写书评

暂无评论

Study on Stochastic Gradient Descent Without Explicit Error Backpropagation with Momentum 2

Study on Stochastic Gradient Descent Without Explicit Error ...

引用

2nd IEEE Conference on Artificial Intelligence (CAI)

作者： Mahboubi, Shahrzad Ninomiya, Hiroshi Shonan Inst Technol Dept Informat Fujisawa Kanagawa Japan

This paper describes a novel training algorithm based on the Stochastic Gradient Descent method without explicit error backpropagation (SWDP) with momentum term for faster neural network training.

ISBN: (纸本)9798350354102;9798350354096

This paper describes a novel training algorithm based on the Stochastic Gradient Descent method without explicit error backpropagation (SWDP) with momentum term for faster neural network training.

关键词： neural network training algorithm stochastic gradient descent weight difference propagation momentum

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Swarm Intelligence based training algorithm for RBF Neural Networks in Function Approximation 2

An Enhanced Swarm Intelligence based Training Algorithm for ...

引用

2014 Second World Conference on Complex Systems (WCCS)

作者： Salem, Mohammed Zingla, Meriem Amina Khelfi, Mohamed Faycal Univ Mascara Fac Sci & Technol Mascara Algeria Univ Carthage LISI Res Lab INSAT Tunis Tunisia Univ Fac Appl & Exact Sci Oran Algeria

ISBN: (纸本)9781479946471

This paper is dedicated to the presentation of enhanced swarm intelligence based training algorithm for Radial basis functions neural networks. The proposed training algorithm (ABC-PP) is hybridization between the Artificial Bees Colony (ABC) and a predator and prey behavior to improve the diversification mechanism of the ABC. Statistical analysis is carried out with nonparametric tests to evaluate the proposed training algorithm comparing it with ABC, GA and PSO based RBF training algorithms in function approximation. The proposed algorithm is applied to identify a real inverted pendulum model giving acceptable results.

关键词： component Artificial Bees Colony predator and prey RBF neural networks training algorithm Nonparametric tests Function approximation Inverted pendulum

来源：评论

学校读者我要写书评

暂无评论

A noise injection strategy for graph autoencoder training

引用

NEURAL COMPUTING & APPLICATIONS 2021年第10期33卷 4807-4814页

作者： Wang, Yingfeng Xu, Biyun Kwak, Myungjae Zeng, Xiaoqin Middle Georgia State Univ Dept Informat Technol Macon GA 31206 USA Beijing Kubao Technol Co Beijing 100124 Peoples R China Hohai Univ Inst Intelligence Sci & Technol Nanjing 210098 Jiangsu Peoples R China Univ Tennessee Dept Comp Sci & Engn Chattanooga TN 37403 USA

Graph autoencoder can map graph data into a low-dimensional space. It is a powerful graph embedding method applied in graph analytics to lower the computational cost. Researchers have developed different graph autoencoders for addressing different needs. This paper proposes a strategy based on noise injection for graph autoencoder training. This is a general training strategy that can flexibly fit most existing training algorithms. The experimental results verify this general strategy can significantly reduce overfitting and identify the noise rate setting for consistent training performance improvement.

关键词： Graph autoencoder Noise injection training algorithm Overfitting

来源：评论

学校读者我要写书评

暂无评论

training of Convolutional Neural Networks for Image Classification with Fully Decoupled Extended Kalman Filter

引用

algorithmS 2024年第6期17卷 243页

作者： Gaytan, Armando Begovich-Mendoza, Ofelia Arana-Daniel, Nancy Inst Politecn Nacl Ctr Invest & Estudios Avanzados Unidad Guadalajara Zapopan 45019 Jalisco Mexico Univ Guadalajara Ctr Univ Ciencias Exactas & Ingn Guadalajara 44430 Jalisco Mexico

First-order algorithms have long dominated the training of deep neural networks, excelling in tasks like image classification and natural language processing. Now there is a compelling opportunity to explore alternatives that could outperform current state-of-the-art results. From the estimation theory, the Extended Kalman Filter (EKF) arose as a viable alternative and has shown advantages over backpropagation methods. Current computational advances offer the opportunity to review algorithms derived from the EKF, almost excluded from the training of convolutional neural networks. This article revisits an approach of the EKF with decoupling and it brings the Fully Decoupled Extended Kalman Filter (FDEKF) for training convolutional neural networks in image classification tasks. The FDEKF is a second-order algorithm with some advantages over the first-order algorithms, so it can lead to faster convergence and higher accuracy, due to a higher probability of finding the global optimum. In this research, experiments are conducted on well-known datasets that include Fashion, Sports, and Handwritten Digits images. The FDEKF shows faster convergence compared to other algorithms such as the popular Adam optimizer, the sKAdam algorithm, and the reduced extended Kalman filter. Finally, motivated by the finding of the highest accuracy of FDEKF with images of natural scenes, we show its effectiveness in another experiment focused on outdoor terrain recognition.

关键词： deep learning extended Kalman filter image classification neural networks convolutional neural networks training algorithm

来源：评论

学校读者我要写书评

暂无评论

A review of research on co-training

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2023年第18期35卷

作者： Ning, Xin Wang, Xinran Xu, Shaohui Cai, Weiwei Zhang, Liping Yu, Lina Li, Wenfa Chinese Acad Sci Inst Semicond Beijing Peoples R China Cognit Comp Technol Joint Lab Wave Grp Beijing Peoples R China Shenzhen Wave Kingdom Co Ltd Shenzhen Peoples R China Beijing Univ Posts & Telecommun Beijing Peoples R China Cent South Univ Forestry & Technol Sch Logist & Transportat Changsha Peoples R China Beijing Union Univ Coll Robot Beijing Peoples R China

Co-training algorithm is one of the main methods of semi-supervised learning in machine learning, which explores the effective information in unlabeled data by multi-learner collaboration. Based on the development of co-training algorithm, the research work in recent years was further summarized in this article. In particular, three main steps of relevant co-training algorithms are introduced: view acquisition, learners' differentiation, and label confidence estimation. Finally, we summarized the problems existing in the current co-training methods, gave some suggestions for improvement, and looked forward to the future development direction of the co-training algorithm.

关键词： co‐ training algorithm label confidence machine learning semi‐ supervised learning unlabeled data

来源：评论

学校读者我要写书评

暂无评论

Landslide susceptibility mapping at Ovack-Karabuk (Turkey) using different artificial neural network models: comparison of training algorithms

引用

BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT 2019年第1期78卷 89-102页

作者： Can, Asli Dagdelenler, Gulseren Ercanoglu, Murat Sonmez, Harun Hacettepe Univ Dept Geol Engn TR-06800 Ankara Turkey

This study aims to investigate the performances of different training algorithms used for an artificial neural network (ANN) method to produce landslide susceptibility maps. For this purpose, Ovack region (southeast of Karabuk Province), located in the Western Black Sea Region (Turkey), was selected as the study area. A total of 196 landslides were mapped, and a landslide database was prepared. Topographical elevation, slope angle, aspect, wetness index, lithology, and vegetation index parameters were taken into account for the landslide susceptibility analyses. Two different ANN structures, which were composed of single and double hidden layers, were applied to compare the effects of the ANN. Four different training algorithms, namely batch back-propagation, quick propagation, conjugate gradient descent (CGD), and Levenberg-Marquardt, were used for the training stage of the ANN models. Thus, eight different landslide susceptibility maps were produced for the study area using different ANN structures and algorithms. In order to assess the effects and spatial performances of the considered training algorithms on the ANN models, the relative operating characteristics (ROC) and relation value (r(ij)) approaches were used. The susceptibility map produced by CGD1 has the highest AUC (0.817) and r(ij) values (0.972). Comparison of the susceptibility maps indicated that CGD training algorithm is the slowest one among the other algorithms, but this algorithm showed the highest performance on the results.

关键词： Artificial neural network Landslide susceptibility map Ovack (Karabuk) training algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing anomaly detection: A comprehensive approach with MTBO feature selection and TVETBO-Optimized - Optimized Quad-LSTM classification

引用

COMPUTERS & ELECTRICAL ENGINEERING 2024年第PartA期119卷

作者： Reddy, N. V. Raja Sekhar Divya, N. Sree Jagadesh, B. Gandikota, Ramu Lella, Kranthi Kumar Pydala, Bhasha Vatambeti, Ramesh MLR Inst Technol Dept Informat Technol Hyderabad 500043 India Mahatma Gandhi Inst Technol Dept Informat Technol Hyderabad India VIT AP Univ Sch Comp Sci & Engn Vijayawada India Narsimha Reddy Engn Coll Dept Comp Sci & Engn Hyderabad 500075 India Mohan Babu Univ Dept Data Sci Tirupati India

The rapid growth of computer networks has heightened system vulnerabilities, challenging traditional Machine Learning (ML) techniques in network anomaly detection due to the abundance of data, imbalanced attack classes, and large-scale datasets. This paper introduces a novel approach leveraging the AWID3 dataset, utilizing advanced preprocessing techniques such as data splitting and normalization. We propose the Mountaineering Team-Based Optimization (MTBO) algorithm for robust feature selection, inspired by social behavior and human collaboration. Additionally, we deploy a Quad-LSTM framework, integrating ConvLSTM, CNN-LSTM, E3DLSTM, and SAConvLSTM models, fine-tuned by the Technical and Vocational Education and training-Based Optimizer (TVETBO). Our approach achieves a remarkable 99.91 % accuracy, significantly surpassing existing models, thus enhancing network security by effectively addressing the complexities of anomaly detection.

关键词： Anomaly detection Network security Mountaineering team-based optimization Long short term memory Technical and vocational education and training algorithm

来源：评论

学校读者我要写书评

暂无评论

Food Cooking Process Modeling With Neural Networks

引用

IEEE ACCESS 2024年 12卷 175866-175881页

作者： Fananas-Anaya, Javier Lopez-Nicolas, Gonzalo Sagues, Carlos Llorente, Sergio Univ Zaragoza Inst Invest Ingn Aragon I3A Zaragoza 50018 Spain BSH Home Appliances Grp Prod Div Cookers Res & Dev Dept Induct Technol Zaragoza 50016 Spain

Food cooking process are complex dynamical systems to model. In the state of the art we find that a good solution consists of physics-based finite element models (FEM). FEM models, although being very accurate, have a high computational cost making them unfeasible for real-time applications. To solve this problem, we consider neural networks (NN) trained from FEM simulations. Specifically, we propose a Nonlinear AutoRegressive with eXogenous inputs Neural Network (NARX-NN). The main novelty is that we define a novel training algorithm adapted to the modeling of real-time dynamical systems, allowing a NARX-NN with a simple structure to obtain a negligible error compared to the results of the original FEM model. The NARX-NN trained with the proposed training algorithm obtains an R-squared of more than 0.99 in the test simulations, while the same NARX-NN trained with the standard training algorithm obtains an R-squared of 0.78 in the same tests. The proposed NARX-NN achieves a speedup of 8 orders of magnitude compared to the original FEM model. Moreover, the developed NN is able to predict the complete cooking of the food in a few milliseconds without the need of external sensors. Alternatively, our approach can also be used in real time with information captured with sensors. The presented methodology is highly scalable and could be adapted to different types of food and cooking processes, as well as to other dynamical systems in general.

关键词： Food modeling neural network real-time sensors simulation training algorithm Food modeling neural network real-time sensors simulation training 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：