Modification of Feed Forward Process and Activation Function in Back-Propagation

2011 ◽  
pp. 234-240
Author(s):  
Gwang-Jun Kim ◽  
Dae-Hyon Kim ◽  
Yong-Kab Kim
Keyword(s):  
Back Propagation ◽  
Activation Function ◽  
Feed Forward ◽  
Forward Process

scholarly journals PIXEL-BASED AND OBJECT-BASED TERRACE EXTRACTION USING FEED-FORWARD DEEP NEURAL NETWORK

2019 ◽  
Vol IV-3/W1 ◽  
pp. 1-7
Author(s):  
H. T. Do ◽  
V. Raghavan ◽  
G. Yonezawa
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Reference Data ◽  
Back Propagation ◽  
Activation Function ◽  
Rate Of Change ◽  
Feed Forward ◽  
Feed Forward Back Propagation ◽  
Object Based ◽  
Hidden Layer

<p><strong>Abstract.</strong> In this paper, we present the identification of terrace field by using Feed-forward back propagation deep neural network in pixel-based and several cases of object-based approaches. Terrace field of Lao Cai area in Vietnam is identified from 5-meter RapidEye image. The image includes 5 bands: red, green, blue, rededge and nir-infrared. Reference data are set of terrace points and nonterrace points, which are generated by randomly selected from reference map. The reference data is separated into three sets: training set for training processing, validation set for generating optimal parameters of deep neural network model, and test set for assessing the accuracy of classification. Six optimal thresholds (T): 0.06, 0.09, 0.12, 0.14, 0.2 and 0.22 are chosen from Rate of Change graph, and then used to generate six cases of object-based classification. Deep neural network (DNN) model is built with 8 hidden layers, input units are 5 bands of RapidEye, and output is terrace and non-terrace classes. Each hidden layer includes 256 units – a large number, to avoid under-fitting. Activation function is Rectifier. Dropout and two regularization parameters are applied to avoid overfitting. Seven terrace maps are generated. The classification results show that the DNN is able to identify terrace field effectively in both pixel-based and object-based approaches. Pixel-based classification is the most accurate approach, achieves 90% accuracy. The values of object-based approaches are 88.5%, 87.3%, 86.7%, 86.6%, 85% and 85.3% correspond to the segmentation thresholds.</p>

Energy Savings at Phoenix 23rd Avenue Wastewater Treatment Plant Using Feed-Forward Process Control

2009 ◽  
Vol 2009 (13) ◽  
pp. 3722-3729 ◽  
Author(s):  
Thomas Walz ◽  
J.R. Coughenour ◽  
Kevin Williams ◽  
John Jacobs ◽  
Larry Shone ◽  
...  
Keyword(s):  
Wastewater Treatment ◽  
Process Control ◽  
Wastewater Treatment Plant ◽  
Energy Savings ◽  
Treatment Plant ◽  
Feed Forward ◽  
Forward Process

scholarly journals Using Artificial Neural Networks in Predicting the Level of Stress among Military Conscripts

Mathematics ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 626
Author(s):  
Svajone Bekesiene ◽  
Rasa Smaliukiene ◽  
Ramute Vaicaitiene
Keyword(s):  
Neural Network ◽  
Transfer Functions ◽  
Back Propagation ◽  
Armed Forces ◽  
Activation Function ◽  
Optimal Number ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Classification Rate ◽  
Artificial Neural

The present study aims to elucidate the main variables that increase the level of stress at the beginning of military conscription service using an artificial neural network (ANN)-based prediction model. Random sample data were obtained from one battalion of the Lithuanian Armed Forces, and a survey was conducted to generate data for the training and testing of the ANN models. Using nonlinearity in stress research, numerous ANN structures were constructed and verified to limit the optimal number of neurons, hidden layers, and transfer functions. The highest accuracy was obtained by the multilayer perceptron neural network (MLPNN) with a 6-2-2 partition. A standardized rescaling method was used for covariates. For the activation function, the hyperbolic tangent was used with 20 units in one hidden layer as well as the back-propagation algorithm. The best ANN model was determined as the model that showed the smallest cross-entropy error, the correct classification rate, and the area under the ROC curve. These findings show, with high precision, that cohesion in a team and adaptation to military routines are two critical elements that have the greatest impact on the stress level of conscripts.

scholarly journals Modeling of Stage-Discharge Using Back Propagation ANN, ANFIS, and WANN-based Computing Technique

2021 ◽  
Author(s):  
Ravi Shukla ◽  
Pravendra Kumar ◽  
Dinesh Kumar Vishwakarma ◽  
Rawshan Ali ◽  
Rohitashw Kumar ◽  
...  
Keyword(s):  
Water Resource Management ◽  
Hydrological Modeling ◽  
Fuzzy Inference ◽  
Back Propagation ◽  
Activation Function ◽  
Neural System ◽  
Back Propagation Algorithm ◽  
Inference System ◽  
Computing Technique ◽  
Artificial Neural

Abstract The development of the stage-discharge relationship is a fundamental issue in hydrological modeling. Due to the complexity of the stage-discharge relationship, discharge prediction plays an essential role in planning and water resource management. The present study was conducted for modeling of discharge at the Gaula barrage site in Uttarakhand state of India. The study evaluated, Adaptive Neuro-Fuzzy Inference System (ANFIS), Artificial Neural Network (ANN) and Wavelet-Based Artificial Neural System (WANN) based models to estimate the discharge. The daily data of 12 years (2007-2018) were used to train and test the models. The Gamma test was used to identify the best model for discharge prediction. The input data having a stage with one-day lag and discharge with one and two-days lag and current-day discharge as output was used for discharge modeling. In the case of ANN models, the back-propagation algorithm and hyperbolic tangent sigmoid activation function was used. WANN used Haar, a trous based wavelet function. In ANFIS models, triangular, psig, generalized bell, and Gaussian membership functions were used to train and test the models. The models were evaluated qualitatively and quantitatively using correlation coefficient, root means square error, Willmott index, and coefficient of efficiency. It was found that ANFIS model performed better than ANN and WANN-based models for discharge prediction at the Gaula barrage.

scholarly journals Deep Convolutional Neural Network Feed Forward and Back Prop a gation (DCNN F BP) Algorithm f or Predicting Heart Disease u sing Internet o f Things

2021 ◽  
Vol 11 (1) ◽  
pp. 283-287
Author(s):  
Saranya N ◽  
◽  
Kavi Priya S ◽  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Heart Disease ◽  
Convolutional Neural Network ◽  
Back Propagation ◽  
High Volume ◽  
Deep Convolutional Neural Network ◽  
Machine Learning Algorithms ◽  
Batch Size ◽  
Feed Forward

In recent years, due to the increasing amounts of data gathered from the medical area, the Internet of Things are majorly developed. But the data gathered are of high volume, velocity, and variety. In the proposed work the heart disease is predicted using wearable devices. To analyze the data efficiently and effectively, Deep Canonical Neural Network Feed-Forward and Back Propagation (DCNN-FBP) algorithm is used. The data are gathered from wearable gadgets and preprocessed by employing normalization. The processed features are analyzed using a deep convolutional neural network. The DCNN-FBP algorithm is exercised by applying forward and backward propagation algorithm. Batch size, epochs, learning rate, activation function, and optimizer are the parameters used in DCNN-FBP. The datasets are taken from the UCI machine learning repository. The performance measures such as accuracy, specificity, sensitivity, and precision are used to validate the performance. From the results, the model attains 89% accuracy. Finally, the outcomes are juxtaposed with the traditional machine learning algorithms to illustrate that the DCNN-FBP model attained higher accuracy.

Sign in / Sign up

Export Citation Format

Share Document