scholarly journals Evolving Hybrid Cascade Neural Network Genetic Algorithm Space–Time Forecasting

Symmetry ◽  
2021 ◽  
Vol 13 (7) ◽  
pp. 1158
Author(s):  
Rezzy Eko Caraka ◽  
Hasbi Yasin ◽  
Rung-Ching Chen ◽  
Noor Ell Goldameir ◽  
Budi Darmawan Supatmanto ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Genetic Algorithm ◽  
Time Series ◽  
Absolute Error ◽  
Time Lapse ◽  
Space Time ◽  
Time Series Forecasting ◽  
Percentage Error ◽  
Cascade Neural Network

Design: At the heart of time series forecasting, if nonlinear and nonstationary data are analyzed using traditional time series, the results will be biased. At the same time, if just using machine learning without any consideration given to input from traditional time series, not much information can be obtained from the results because the machine learning model is a black box. Purpose: In order to better study time series forecasting, we extend the combination of traditional time series and machine learning and propose a hybrid cascade neural network considering a metaheuristic optimization genetic algorithm in space–time forecasting. Finding: To further show the utility of the cascade neural network genetic algorithm, we use various scenarios for training and testing while also extending simulations by considering the activation functions SoftMax, radbas, logsig, and tribas on space–time forecasting of pollution data. During the simulation, we perform numerical metric evaluations using the root-mean-square error (RMSE), mean absolute error (MAE), and symmetric mean absolute percentage error (sMAPE) to demonstrate that our models provide high accuracy and speed up time-lapse computing.

Estimation of structural response using convolutional neural network: application to the Suramadu bridge

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Arya Panji Pamuncak ◽  
Mohammad Reza Salami ◽  
Augusta Adha ◽  
Bambang Budiono ◽  
Irwanda Laory
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Structural Response ◽  
Force Sensor ◽  
Absolute Error ◽  
Percentage Error ◽  
Learning Approaches ◽  
Content Type ◽  
Cable Force

PurposeStructural health monitoring (SHM) has gained significant attention due to its capability in providing support for efficient and optimal bridge maintenance activities. However, despite the promising potential, the effectiveness of SHM system might be hindered by unprecedented factors that impact the continuity of data collection. This research presents a framework utilising convolutional neural network (CNN) for estimating structural response using environmental variations.Design/methodology/approachThe CNN framework is validated using monitoring data from the Suramadu bridge monitoring system. Pre-processing is performed to transform the data into data frames, each containing a sequence of data. The data frames are divided into training, validation and testing sets. Both the training and validation sets are employed to train the CNN models while the testing set is utilised for evaluation by calculating error metrics such as mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE). Comparison with other machine learning approaches is performed to investigate the effectiveness of the CNN framework.FindingsThe CNN models are able to learn the trend of cable force sensor measurements with the ranges of MAE between 10.23 kN and 19.82 kN, MAPE between 0.434% and 0.536% and RMSE between 13.38 kN and 25.32 kN. In addition, the investigation discovers that the CNN-based model manages to outperform other machine learning models.Originality/valueThis work investigates, for the first time, how cable stress can be estimated using temperature variations. The study presents the first application of 1-D CNN regressor on data collected from a full-scale bridge. This work also evaluates the comparison between CNN regressor and other techniques, such as artificial neutral network (ANN) and linear regression, in estimating bridge cable stress, which has not been performed previously.

A Study on Time Series Forecasting using Hybridization of Time Series Models and Neural Networks

2020 ◽  
Vol 13 (5) ◽  
pp. 827-832
Author(s):  
Iflah Aijaz ◽  
Parul Agarwal
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Time Series ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Hybrid Models ◽  
Time Series Forecasting ◽  
Percentage Error ◽  
Mean Square

Introduction: Auto-Regressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANN) are leading linear and non-linear models in Machine learning respectively for time series forecasting. Objective: This survey paper presents a review of recent advances in the area of Machine Learning techniques and artificial intelligence used for forecasting different events. Methods: This paper presents an extensive survey of work done in the field of Machine Learning where hybrid models for are compared to the basic models for forecasting on the basis of error parameters like Mean Absolute Deviation (MAD), Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Normalized Root Mean Square Error (NRMSE). Results: Table 1 summarizes important papers discussed in this paper on the basis of some parameters which explain the efficiency of hybrid models or when the model is used in isolation. Conclusion: The hybrid model has realized accurate results as compared when the models were used in isolation yet some research papers argue that hybrids cannot always outperform individual models.

STATISTICAL AND MACHINE LEARNING HIGH-FREQUENCY TIME SERIES FORECASTING METHODS IN AUTOMATIC MODE

2020 ◽  
pp. 3-11
Author(s):  
Sai Van Cuong ◽  
M. V. Shcherbakov
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Time Series ◽  
High Frequency ◽  
Network Models ◽  
Time Series Forecasting ◽  
Neural Network Models ◽  
Automatic Mode ◽  
Forecasting Methods ◽  
The Neural Network

The research of the problem of automatic high-frequency time series forecasting (without expert) is devoted. The efficiency of high-frequency time series forecasting using different statistical and machine learning modelsis investigated. Theclassical statistical forecasting methods are compared with neural network models based on 1000 synthetic sets of high-frequency data. The neural network models give better prediction results, however, it takes more time to compute compared to statistical approaches.

scholarly journals Forecasting gold prices in India using ARIMAX and machine learning algorithms

2020 ◽  
Vol 11 (2) ◽  
pp. 299-310
Author(s):  
P. Sai Shankar ◽  
M. Krishna Reddy
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Stock Exchange ◽  
Learning Algorithms ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Percentage Error ◽  
Lasso Regression ◽  
Explanatory Variables ◽  
Repo Rate

Forecasting is a function in management to assist decision making. It is also described as the process of estimation in unknown future situations. In a more general term it is commonly known as prediction which refers to estimation of time series or longitudinal type data. The main object of this paper is to compare the traditional time series model with machine learning algorithms. To predict the gold prices based on economic factors such as inflation, exchange rate, crude price, bank rate, repo rate, reverse repo rate, gold reserve ration, Bombay stock exchange and National stock exchange. Two lagged variables are taken for each variable in the analysis. The ARIMAX model is developed to forecast Indian gold prices using daily data for the period 2016 to 2020 obtained from World Gold Council. We fitted the ARIMAX (4,1,1) model to our data which exhibited the least AIC values. In the mean while, decision tree, random forest, lasso regression, ridge regression, XGB and ensemble models were also examined to forecast the gold prices based on host of explanatory variables. The forecasting performance of the models were evaluated using mean absolute error, mean absolute percentage error and root mean squared errors. Ensemble model out performs than that of the other models for predicting the gold prices based on set of explanatory variables.

Deep Learning for text in limted data settings

2020 ◽  
Author(s):  
Pathikkumar Patel ◽  
Bhargav Lad ◽  
Jinan Fiaidhi
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Transfer Learning ◽  
Text Classification ◽  
State Of The Art ◽  
Time Series Forecasting ◽  
Text Data ◽  
Performance Levels

During the last few years, RNN models have been extensively used and they have proven to be better for sequence and text data. RNNs have achieved state-of-the-art performance levels in several applications such as text classification, sequence to sequence modelling and time series forecasting. In this article we will review different Machine Learning and Deep Learning based approaches for text data and look at the results obtained from these methods. This work also explores the use of transfer learning in NLP and how it affects the performance of models on a specific application of sentiment analysis.

scholarly journals Detection and Severity Evaluation of Combined Rail Defects Using Deep Learning

Vibration ◽  
2021 ◽  
Vol 4 (2) ◽  
pp. 341-356
Author(s):  
Jessada Sresakoolchai ◽  
Sakdirat Kaewunruen
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Machine Learning Techniques ◽  
Rolling Stock ◽  
Raw Data ◽  
Learning Techniques ◽  
Combined Defects

Various techniques have been developed to detect railway defects. One of the popular techniques is machine learning. This unprecedented study applies deep learning, which is a branch of machine learning techniques, to detect and evaluate the severity of rail combined defects. The combined defects in the study are settlement and dipped joint. Features used to detect and evaluate the severity of combined defects are axle box accelerations simulated using a verified rolling stock dynamic behavior simulation called D-Track. A total of 1650 simulations are run to generate numerical data. Deep learning techniques used in the study are deep neural network (DNN), convolutional neural network (CNN), and recurrent neural network (RNN). Simulated data are used in two ways: simplified data and raw data. Simplified data are used to develop the DNN model, while raw data are used to develop the CNN and RNN model. For simplified data, features are extracted from raw data, which are the weight of rolling stock, the speed of rolling stock, and three peak and bottom accelerations from two wheels of rolling stock. In total, there are 14 features used as simplified data for developing the DNN model. For raw data, time-domain accelerations are used directly to develop the CNN and RNN models without processing and data extraction. Hyperparameter tuning is performed to ensure that the performance of each model is optimized. Grid search is used for performing hyperparameter tuning. To detect the combined defects, the study proposes two approaches. The first approach uses one model to detect settlement and dipped joint, and the second approach uses two models to detect settlement and dipped joint separately. The results show that the CNN models of both approaches provide the same accuracy of 99%, so one model is good enough to detect settlement and dipped joint. To evaluate the severity of the combined defects, the study applies classification and regression concepts. Classification is used to evaluate the severity by categorizing defects into light, medium, and severe classes, and regression is used to estimate the size of defects. From the study, the CNN model is suitable for evaluating dipped joint severity with an accuracy of 84% and mean absolute error (MAE) of 1.25 mm, and the RNN model is suitable for evaluating settlement severity with an accuracy of 99% and mean absolute error (MAE) of 1.58 mm.

Sign in / Sign up

Export Citation Format

Share Document