scholarly journals Coupling Normalization with Moving Window in Backpropagation Neural Network (BNN) for Passive Microwave Soil Moisture Retrieval

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Soo See Chai ◽  
Kok Luong Goh ◽  
Yee Hui Robin Chang ◽  
Kwan Yong Sim
Keyword(s):  
Neural Network ◽  
Soil Moisture ◽  
Standard Deviation ◽  
Time Series Data ◽  
Back Propagation ◽  
Training Data ◽  
Series Data ◽  
Moving Window ◽  
Window Method ◽  
Testing Data

AbstractA common practice to capture the non-stationary characteristics of the time series data in Artificial Neural Network (ANN) is by randomly dividing the whole set of available data into training, validation and testing, i.e. the data in validation and testing are represented in the training data. Consequently, the usability of the developed model on data not represented by the training data used during the network model development process is always doubtful. In this work, we present a back-propagation neural network (BNN) model trained using one-day history data to predict soil moisture data at 1 km resolution for two future dates. Specifically, high soil moisture values were observed in the training data while the testing data were characterized by drier conditions due to minimal or no rainfall. Our model uses separate mean and standard deviation statistics values from the training and testing data, respectively, to the z-normalized data. With data pre-processed using this method, the BNN model next uses a moving window of size 4 km × 4 km to capture the spatial variability of the soil moisture throughout the 40 km × 40 km study area. The coupling of the normalization and moving window method managed to achieve average soil moisture with Root Mean Square (RMSE) of 3.67% and correlation coefficient, R2 of 0.89. By only using the suggested normalization without the moving window method, the BNN model managed to achieve an average RMSE of barely 5.82% with R2 = 0.83. When comparing with the normal practice of using the same mean and standard deviation statistics of the training data in the testing data, the retrieval accuracy of the BNN model deteriorates to 8.86% with R2 = 0.32. The experiment results demonstrated that the proposed coupling method performed better in terms of both RMSE and R2 for soil moisture retrieval.

scholarly journals Optimasi Fuzzy Artificial Neural Network dengan Algoritma Genetika untuk Prediksi Harga Crude Palm Oil

2020 ◽  
Vol 6 (2) ◽  
Author(s):  
Anwar Rifa'i
Keyword(s):  
Neural Network ◽  
Radial Basis Function ◽  
Palm Oil ◽  
Basis Function ◽  
Time Series Data ◽  
Training Data ◽  
Series Data ◽  
Crude Palm Oil ◽  
Testing Data ◽  
Radial Basis

Crude Palm Oil (CPO) is one of Indonesia's best export commodities. CPO production competition causes price fluctuations so that it can trigger losses. The solution that can be taken to avoid losses is to predict the price of CPO. Time series data in the previous months, starting from January 2009 until January 2020, are used as a reference to predict the next CPO price. In this research, CPO price prediction is carried out with a combination of artificial intelligence concepts, namely Radial Basis Function Neural Network (RBFNN), and fuzzy logic. The combination of these methods, namely Fuzzy Radial Basis Function Neural Network (FRBFNN), is then optimized using genetic algorithms. The prediction results show that the error based on the MAPE value for FRBFNN prediction on training data is 11.7% and the MAPE value for testing data is 9.4%. In the FRBFNN prediction that was optimized using a genetic algorithm, the MAPE value was 10.2% for training data and 8.3% for testing data.

scholarly journals Deep Neural Network Algorithm Feedback Model with Behavioral Intelligence and Forecast Accuracy

Symmetry ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 1465
Author(s):  
Taikyeong Jeong
Keyword(s):  
Neural Network ◽  
Classification Accuracy ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Training Data ◽  
Series Data ◽  
Context Aware ◽  
Data Set ◽  
Feedback Model ◽  
Data Connection

When attempting to apply a large-scale database that holds the behavioral intelligence training data of deep neural networks, the classification accuracy of the artificial intelligence algorithm needs to reflect the behavioral characteristics of the individual. When a change in behavior is recognized, that is, a feedback model based on a data connection model is applied, an analysis of time series data is performed by extracting feature vectors and interpolating data in a deep neural network to overcome the limitations of the existing statistical analysis. Using the results of the first feedback model as inputs to the deep neural network and, furthermore, as the input values of the second feedback model, and interpolating the behavioral intelligence data, that is, context awareness and lifelog data, including physical activities, involves applying the most appropriate conditions. The results of this study show that this method effectively improves the accuracy of the artificial intelligence results. In this paper, through an experiment, after extracting the feature vector of a deep neural network and restoring the missing value, the classification accuracy was verified to improve by about 20% on average. At the same time, by adding behavioral intelligence data to the time series data, a new data connection model, the Deep Neural Network Feedback Model, was proposed, and it was verified that the classification accuracy can be improved by about 8 to 9% on average. Based on the hypothesis, the F (X′) = X model was applied to thoroughly classify the training data set and test data set to present a symmetrical balance between the data connection model and the context-aware data. In addition, behavioral activity data were extrapolated in terms of context-aware and forecasting perspectives to prove the results of the experiment.

scholarly journals Analisis Pola Prediksi Data Time Series menggunakan Support Vector Regression, Multilayer Perceptron, dan Regresi Linear Sederhana

2019 ◽  
Vol 3 (2) ◽  
pp. 282-287
Author(s):  
Ika Oktavianti ◽  
Ermatita Ermatita ◽  
Dian Palupi Rini
Keyword(s):  
Time Series ◽  
Support Vector Regression ◽  
Multilayer Perceptron ◽  
Time Series Data ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Series Data ◽  
Support Vector ◽  
Contributing Factors ◽  
Testing Data

Licensing services is one of the forms of public services that important in supporting increased investment in Indonesia and is currently carried out by the Investment and Licensing Services Department. The problems that occur in general are the length of time to process licenses and one of the contributing factors is the limited number of licensing officers. Licensing data is a time series data which have monthly observation. The Artificial Neural Network (ANN) and Support Vector Machine (SVR) is used as machine learning techniques to predict licensing pattern based on time series data. Of the data used dataset 1 and dataset 2, the sharing of training data and testing data is equal to 70% and 30% with consideration that training data must be more than testing data. The result of the study showed for Dataset 1, the ANN-Multilayer Perceptron have a better performance than Support Vector Regression (SVR) with MSE, MAE and RMSE values is 251.09, 11.45, and 15.84. Then for dataset 2, SVR-Linear has better performance than MLP with values of MSE, MAE and RMSE of 1839.93, 32.80, and 42.89. The dataset used to predict the number of permissions is dataset 2. The study also used the Simple Linear Regression (SLR) method to see the causal relationship between the number of licenses issued and licensing service officers. The result is that the relationship between the number of licenses issued and the number of service officers is less significant because there are other factors that affect the number of licenses.  

scholarly journals Fuzzy Counter Propagation Neural Network Control for a Class of Nonlinear Dynamical Systems

2015 ◽  
Vol 2015 ◽  
pp. 1-12 ◽  
Author(s):  
Vandana Sakhre ◽  
Sanjeev Jain ◽  
Vilas S. Sapkal ◽  
Dev P. Agarwal
Keyword(s):  
Neural Network ◽  
Dynamical Systems ◽  
Time Series Data ◽  
Nonlinear Dynamical Systems ◽  
Back Propagation ◽  
Network Control ◽  
Series Data ◽  
Nonlinear Dynamical ◽  
Single Output ◽  
Propagation Network

Fuzzy Counter Propagation Neural Network (FCPN) controller design is developed, for a class of nonlinear dynamical systems. In this process, the weight connecting between the instar and outstar, that is, input-hidden and hidden-output layer, respectively, is adjusted by using Fuzzy Competitive Learning (FCL). FCL paradigm adopts the principle of learning, which is used to calculate Best Matched Node (BMN) which is proposed. This strategy offers a robust control of nonlinear dynamical systems. FCPN is compared with the existing network like Dynamic Network (DN) and Back Propagation Network (BPN) on the basis of Mean Absolute Error (MAE), Mean Square Error (MSE), Best Fit Rate (BFR), and so forth. It envisages that the proposed FCPN gives better results than DN and BPN. The effectiveness of the proposed FCPN algorithms is demonstrated through simulations of four nonlinear dynamical systems and multiple input and single output (MISO) and a single input and single output (SISO) gas furnace Box-Jenkins time series data.

scholarly journals Total asset prediction of the large Indonesian bank using adaptive artificial neural network back-propagation

2018 ◽  
Vol 7 (2.2) ◽  
pp. 75 ◽  
Author(s):  
Fariyanti . ◽  
Iskandar . ◽  
Rheo Malani ◽  
Bedi Suprapty
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Time Series Data ◽  
Stock Exchange ◽  
Back Propagation ◽  
Ar Model ◽  
Series Data ◽  
Net Income ◽  
Single Output ◽  
Artificial Neural

The bank is a type of company that acts as the executor of monetary policy and as a guarantor of the stability of the financial system of a country. Total assets are an important aspect for a bank to generate net income. Return on Assets (ROA) is a profitability ratio to measure the ability of a bank in generating profits with all investments owned. This study predicts the total assets of the largest banks in Indonesia, referring to the Indonesia Stock Exchange data from 2005 to 2016. The time series data model used is Autoregressive (AR) model and Multi Input Single Output (MISO) Autoregressive with exogenous input (ARX) model. Adaptive Artificial Neural Network Back-propagation (Adaptive ANN-BP) is used as an approximation model of both models.  

scholarly journals Multifraktalitas dan Studi Komparatif Prediksi Indeks dengan Metode Arima dan Artificial Neural Network (ANN)

The Winners ◽  
2008 ◽  
Vol 9 (2) ◽  
pp. 112
Author(s):  
Harjum Muharam ◽  
Muhammad Panji
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Time Series Data ◽  
Moving Average ◽  
Back Propagation ◽  
Series Data ◽  
Future Value ◽  
Auto Regressive ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

This paper discusses technical analysis widely used by investors. There are many methods that exist and used by investor to predict the future value of a stock. In this paper we start from finding the value of Hurst (H) exponent of LQ 45 Index to know the form of the Index. From H value, we could determinate that the time series data is purely random, or ergodic and ant persistent, or persistent to a certain trend. Two prediction tools were chosen, ARIMA (Auto Regressive Integrated Moving Average) which is the de facto standard for univariate prediction model in econometrics and Artificial Neural Network (ANN) Back Propagation. Data left from ARIMA is used as an input for both methods. We compared prediction error from each method to determine which method is better. The result shows that LQ45 Index is persistent to a certain trend therefore predictable and for outputted sample data ARIMA outperforms ANN.

scholarly journals A Hybrid Neural Network and H-P Filter Model for Short-Term Vegetable Price Forecasting

2014 ◽  
Vol 2014 ◽  
pp. 1-10
Author(s):  
Youzhu Li ◽  
Chongguang Li ◽  
Mingyang Zheng
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Time Series Data ◽  
Back Propagation ◽  
Warning System ◽  
Original Data ◽  
Series Data ◽  
Hybrid Neural Network ◽  
Filter Model ◽  
Linear And Nonlinear

This paper is concerned with time series data for vegetable prices, which have a great impact on human’s life. An accurate forecasting method for prices and an early-warning system in the vegetable market are an urgent need in people’s daily lives. The time series price data contain both linear and nonlinear patterns. Therefore, neither a current linear forecasting nor a neural network can be adequate for modeling and predicting the time series data. The linear forecasting model cannot deal with nonlinear relationships, while the neural network model alone is not able to handle both linear and nonlinear patterns at the same time. The linear Hodrick-Prescott (H-P) filter can extract the trend and cyclical components from time series data. We predict the linear and nonlinear patterns and then combine the two parts linearly to produce a forecast from the original data. This study proposes a structure of a hybrid neural network based on an H-P filter that learns the trend and seasonal patterns separately. The experiment uses vegetable prices data to evaluate the model. Comparisons with the autoregressive integrated moving average method and back propagation artificial neural network methods show that our method has higher accuracy than the others.

scholarly journals Prediction of Streamflow Based on Dynamic Sliding Window LSTM

Water ◽  
2020 ◽  
Vol 12 (11) ◽  
pp. 3032
Author(s):  
Limei Dong ◽  
Desheng Fang ◽  
Xi Wang ◽  
Wei Wei ◽  
Robertas Damaševičius ◽  
...  
Keyword(s):  
Time Series Data ◽  
Short Term Memory ◽  
Back Propagation ◽  
Prediction Method ◽  
Window Size ◽  
Sliding Window ◽  
Series Data ◽  
Window Method ◽  
Dynamic Sliding Window ◽  
Optimal Window

The streamflow of the upper reaches of the Yangtze River exhibits different timing and periodicity characteristics in different quarters and months of the year, which makes it difficult to predict. Existing sliding window-based methods usually use a fixed-size window, for which the window size selection is random, resulting in large errors. This paper proposes a dynamic sliding window method that reflects the different timing and periodicity characteristics of the streamflow in different months of the year. Multiple datasets of different months are generated using a dynamic window at first, then the long-short term memory (LSTM) is used to select the optimal window, and finally, the dataset of the optimal window size is used for verification. The proposed method was tested using the hydrological data of Zhutuo Hydrological Station (China). A comparison between the flow prediction data and the measured data shows that the prediction method based on a dynamic sliding window LSTM is more accurate by 8.63% and 3.85% than the prediction method based on fixed window LSTM and the dynamic sliding window back-propagation neural network, respectively. This method can be generally used for the time series data prediction with different periodic characteristics.

Sign in / Sign up

Export Citation Format

Share Document