Forward Back Propagation Neural Network Research Articles

Quantitative recognition of flammable and toxic gases with artificial neural network using metal oxide gas sensors in embedded platform

Artificial Neural Network (ANN) based pattern recognition technique is used for ensuring the reliable evaluation of responses from an array of Zinc Oxide (ZnO) based sensors comprising of pure ZnO nano-rods and composites of ZnO–SnO2. All the sensors were fabricated in the lab. The paper first reports the development of an artificial neural network based model for successfully recognizing different concentration of hydrogen, methane and carbon mono-oxide. Feed forward back propagation neural network was used for the classification of the gases at critical concentrations. The optimized ANN algorithm is then embedded in the microcontroller based circuit and finally verified under lab conditions.

Bistatic measurements for the estimation of rice crop variables using artificial neural network

An outdoor rice crop bed (4×4m2) was specially prepared for a bistatic ground based scatterometer measurements at various growth stages of rice crop from transplanting to ripening stage at like polarizations (HH- and VV-) in the angular range of 20–70° at the steps of 5°. The computed scattering coefficients showed increasing behavior from transplanting to reproductive stage and started decreasing at ripening stage. The angular dependency of scattering coefficient was found to decrease initially with age and became negligible near the ripening stage of rice crop. The polynomial regression analysis showed higher values of coefficient of determination (R2) at 30° incidence angle for both like polarizations. Two types of feed forward back propagation neural network (FFBPNN) models were developed for the estimation of rice crop growth variables namely FFBPANN-I and FFBPANN-II model. The FFBPANN-I model was developed with one input neuron (HH- or VV-polarized scattering coefficient) and one output neuron (biomass or leaf area index or plant height or chlorophyll content) while the FFBPANN-II model was developed with two input neurons (HH- and VV-polarized scattering coefficient) and four output neurons (biomass, leaf area index, plant height and chlorophyll content). Performances of both the types of FFBPANN models were found good for the estimation of rice crop variables. However, the performance of FFBPANN-II model was found better in comparison to the FFBPANN-I model at suitable incidence angle 30°.

Forecasting Groundwater Level by Artificial Neural Networks as an Alternative Approach to Groundwater Modeling

Abstract The main purpose of this article is to apply feed forward back propagation neural network (FNN) to predict groundwater level of Aghili plain, which is located in southwestern Iran. An optimal design is completed for the two hidden layers with four different algorithms: descent with momentum (GDM), Levenberg Marquardt (LM), resilient back propagation (RP), and scaled conjugate gradient (SCG). The training data for ANN is obtained from observation data. Rain, evaporation, relative humidity, temperature, discharge of irrigation canal, and groundwater recharge from the plain boundary were used in input layer while future groundwater level was used as output layer. Before training, the available data were divided into three groups, according to hydrogeological characteristics of different parts of the plain surrounding each piezometer. Statistical analysis in terms of Mean-Square-Error (MSE) and correlation coefficient (R) was used to investigate the prediction performance of ANN. FFN-LM algorithm has shown best result in the present study for all three hydrogeological groups. Now, to predict water level, the t time data (October 2003 to July 2009) and t+1 time data (October 2004 to July 2010) were used as input and output respectively. The best condition of this network was achieved for each group of data. Next, with defining the new input data related to August 2010 to January 2011 groundwater level was predicted for the following year. The achieved results of ANN model in contrast with results of finite difference model showed very high accuracy of artificial neural network in predicting groundwater level.

River Water Quality Modelling Using Artificial Neural Network Technique

Dissolved oxygen (DO) concentrations have been used as primary indicator of stream water quality. A problem of great social importance is determining how to best retain the quality of stream water and maintain DO concentrations using various pollution control activities. This paper presents the use of artificial neural network (ANN) technique to estimate the DO concentrations at the downstream of Mathura city, India, located at the bank of River Yamuna in the state of Uttar Pradesh, India. In the analysis, the most commonly used feed forward error back propagation neural network technique has been applied. Monthly data sets on flow discharge, temperature, pH, biochemical oxygen demand (BOD) and dissolved oxygen (DO) at three locations, namely, Mathura (upstream), Mathura (central) and Mathura (downstream) have been used for the analysis. Feed forward error back propagation algorithm, the most commonly used ANN technique, was used to develop three types of ANN models using different combinations of input variables and input stations, namely: (a) All the data sets for stations Mathura (upstream), Mathura (central) and Mathura (downstream) except DO values at Mathura (downstream) (b) All data sets for the stations Mathura (upstream), and Mathura (central), and (c) All the data sets for the stations Mathura (upstream). The performance of the ANN technique has been evaluated using statistical tools (in terms of root mean square error and coefficient of correlation). The predicted values of DO showed prominent accuracy by producing high correlations (upto 0.9) between measured and predicted values.

Application of Artificial Neural Networks for Prediction of Ibuprofen Yield from Ultrasound-Assisted Anti-Solvent Crystallization

The aim of the study was to develop neural network model to predict the yield obtained from ultrasound-assisted anti-solvent crystallization of ibuprofen in terms of formulation and processing factors. The different factors of anti-solvent crystallization method, such as type of additive, concentration of additive, sonication time and harvesting time, were used as independent variables. The ibuprofen yield was used as response variable. The correlation between independent and response variables was investigated using feed forward-back propagation neural networks. The goodness of fit test and predictability were used for optimization of in silico models. The results revealed that the type of polyethylene glycol (PEG) was a critical factor that affected the response variable in different patterns. The best artificial neural networks (ANNs) model with a configuration of 3-4-1 for input, hidden, and output layers gave the r2 of 0.7067 and 0.8729 and the root mean square error of 0.3693 and 0.2667 for the model using PEG 400 and PEG 4000, respectively. The predictive ability of these models was validated by a set of 4 formulations that were not included in the training set. The predicted and experimental of ibuprofen yields were correlated.

Feed Forward Back Propagation Neural Network Coupled With Rice Data Simulator for Prediction of Rice Production in Tamilnadu

This paper is the continuation of the paper published by the authors Arun Balaji and Baskaran [2]. Multiple linear regression (MLR) equations were developed between the years of rice cultivation and Feed Forward Back Propagation Neural Network (FFBPNN) method of predicted area of rice cultivation / rice production for different districts pertaining to Kuruvai, Samba and Kodai seasons in Tamilnadu. The average r 2 value in area of cultivation is 0.40 in Kuruvai season, 0.42 in Samba season and 0.46 in Kodai season, where as the r 2 value in rice production is 0.31 in Kuruvai season, 0.23 in Samba season and 0.42 in Kodai season. The Rice Data Simulator (RDS) predicted the area of rice cultivation and rice production using the MLR equations developed in this research. The range of average predicted area for Kuruvai, Samba and Kodai seasons varies from 12052.52 ha to 13595.32 ha, 48998.96 ha to 53324.54 ha and 4241.23 ha to 6449.88 ha respectively whereas the range of average predicted rice production varies from 45132.88 tonnes to 46074.48 tonnes in Kuruvai, 128619 tonnes to 139693.29 tonnes in Samba and 15446.07 to 20573.50 tonnes in Kodai seasons. The mean absolute relative error (ARE) between the FFBPNN and multiple regression methods of prediction of area of rice cultivation was found to be 15.58%, 8.04% and 26.34% for the Kuruvai, Samba and the Kodai seasons respectively. The ARE for the rice production was found to be 17%, 11.80% and 24.60% for the Kuruvai, Samba and the Kodai seasons respectively. The paired t test between the FFBPNN and MLR methods of predicted area of cultivation in Kuruvai shows that there is no significant difference between the two types of prediction for certain districts.

Wavelet Linear Prediction Coding with Feed Forward Backpropagation Neural Network for Noisy Speaker Identification System

Wavelet Linear Prediction Coding with Feed Forward Backpropagation Neural Network for Noisy Speaker Identification System

English

In this paper, new multilayer perceptron's feed forward back propagation Neural Network (NN) performance using BFGS quasi newton , Levenberg -Marquardt (LM), Gradient descent back propagation with adaptive learning rate(GDA) Algorithms are being anticipated with the project detached to develop a lossless image solidity technique using NN and to design and contrivance image compression using Neural network to achieve maximum peak signal to noise ratio (PSNR), and low mean square error (MSE) and compression levels. This paper presents a NN based procedure that may be practical to data compression and breaks down large images into smaller blocks (1x64) and eradicates redundant information. Lastly, this technique uses a NN training functions like and conversion of block codes to vector codes and vice versa. Results obtained with proposed techniques leads to better compression material. Finally, this technique uses a NN training functions like and adaptation of block codes to vector codes and vice versa. Consequencesacquired with proposed techniques leads to better compression ratio at the same time conserving the image quality. The investigational result shows that the BFG quasi newton algorithm is best among the three proposed algorithm which offers better PSNR value and also reduces the MSE value.

Refracture candidate selection using hybrid simulation with neural network and data analysis techniques

Abstract By now very few analytical models have been developed to select well refracture candidates due to complicated multi-parameter relationships. In this study, we proposed a new method by merging mathematical data analysis with feed forward back propagation neural network utilizing post-fracturing data. The model preference is thereby based on the correlation coefficients of several selected independent variables against production performance. The solution to this expense is a tool that can identify restimulation candidates quickly and economically. We employ two mathematical analysis techniques to filter several independent yet influential parameters as inputs. These parameters are supposed to be primary factors with high impact on potential production improvement. Then we use these well data to train an artificial neural network (ANN) to predict post-fracture production. The errors of the best samples should decrease consistently along with the training samples. A minimal error of the training sets is not necessary because over-fitting of the network could be memorizing rather than generalizing. The testing results showed that there is higher than 80% prediction accuracy, which is good enough for decision making. This methodology gives credible prediction results when it is applied in Zhongyuan oilfield and provides the operators with useful recommendations to make decisions for restimulation.

Aşağı Sakarya Nehri akımlarının yapay sinir ağları ile tahmin edilmesi

Sakarya River is located in Sakarya Basin which determined by DSI,is 12th of 26 basin. Sakarya River basin, which is the most important river in the region, is an important source of natural energy. With the dams built on the area provides drinking and irrigation water. In this study, the amount of Lower Sakarya River’s flow estimated from Artificial Neural Networks (ANN) models using Feed Forward Backpropagation Neural Networks. Time shift done under a variety of scenarios, the best scenario to be determined from results. In scenarios Flow Observation Station No. 1221 Doagancay flow data used. Obtained results are evaluated the four day time shift scenario has the highest coefficient of determination (R) value. The study on Sakarya River will be helpful to future studies in energy and flood.

Neural Network-Based Prediction of Effective Heat Storage Coefficient of Building Materials

In the present paper, we have employed the application of artificial neural networks (ANN) to predict effective heat storage coefficient (HSC) of building materials. First we prepared a database to train and test the models developed here. Two types of architectures from different networks are developed, one with three inputs and the other with four inputs mixed architecture combining an ANN with a theoretical model developed by us previously. These ANN models are built, trained and tested by the feed forward back propagation algorithm, to obtain the effective properties of building materials from the properties of their constituents. Feed forward back propagation neural network structure has been developed, which includes an input layer, a hidden layer and an output layer. The number of neurons in the input layer is equal to the number of input parameters and the number of neurons in the output layer is equal to the output parameters. A good agreement has been found between the predicted values using ANN and the experimental results reported in the literature.

Threshold prediction for segmenting tumour from brain MRI scans

ABSTRACTIn recent decades, region growing methods in image segmentation plays a vital role in medical image processing. Nonetheless, the method needs more advancement to cope up with the images of current acquisition devices. This paper attempts to solve the problem of maintaining diversity among wide image specifications by optimizing the threshold. In order to accomplish this, we introduce a hybrid framework of Artificial Bee Colony and Genetic Algorithm in a region growing variant, in which gradient and intensity levels are used for segmentation. Eventually, the proposed work is subjected to classify the tumor and non‐tumor images, followed by the segmentation of tumor region in MRI images. Classification methodologies such as feed forward back propagation neural network, radial basis neural network, support vector machine with quadratic programming and adaptive neuro‐fuzzy inference system are considered for experimental investigation in which support vector machine with quadratic programming is found to be dominant than other methodologies. Proposed region growing method outperforms well on the classified image, when compared with the region growing variant and standard region growing method. The results are demonstrated with the aid of wide set of performance measures. © 2014 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 24, 129–137, 2014

An Improved EEG Signal Classification Using Neural Network with the Consequence of ICA and STFT

Signals of the Electroencephalogram (EEG) can reflect the electrical background activity of the brain generated by the cerebral cortex nerve cells. This has been the mostly utilized signal, which helps in effective analysis of brain functions by supervised learning methods. In this paper, an approach for improving the accuracy of EEG signal classification is presented to detect epileptic seizures. Moreover, Independent Component Analysis (ICA) is incorporated as a preprocessing step and Short Time Fourier Transform (STFT) is used for denoising the signal adequately. Feature extraction of EEG signals is accomplished on the basis of three parameters namely, Standard Deviation, Correlation Dimension and Lyapunov Exponents. The Artificial Neural Network (ANN) is trained by incorporating Levenberg-Marquardt(LM) training algorithm into the backpropagation algorithm that results in high classification accuracy. Experimental results reveal that the methodology will improve the clinical service of the EEG recording and also provide better decision making in epileptic seizure detection than the existing techniques. The proposed EEG signal classification using feed forward Backpropagation Neural Network performs better than to the EEG signal classification using Adaptive Neuro Fuzzy Inference System (ANFIS) classifier in terms of accuracy, sensitivity, and specificity.

Kannada Handwritten numeral Recognition using FFBPNN Classifiers

This paper presents the performance of Kannada handwritten numeral recognition using feed forward back propagation neural network (FFBPNN) classifiers. The classifier is designed to recognize the Kannada handwritten numerals. Samples are represented by the few features extracted by the zoning technique. The input numeral samples in binary form are stored in a fixed window size of 12x12 and partitioned into nine sub regions of 4x4 sizes for their representation. A normalized feature value is computed by the one‟s present each sub region for their representation in two different approaches. On experimentation, it is found the overall recognition rate of 99.7% and 95.5% for the feature extraction approaches M1 and M2 respectively. General Terms Pattern Recognition, Feed Forward Back Propagation Neural Network, Character Recognition

An Efficient Optimization based Vehicle Movement Prediction with Aid of Feed Forward Back Propagation Neural Network

Moving vehicle location prediction method mainly based on their spatial and temporal data .The moving objects has been developed as a specific research area of Geographic Information Systems (GIS). Most of the techniques have been used for performing the vehicle movement detection and prediction process. This type of work is a lack of analysis in predicting the moving vehicles location in current as well as in the future. Existing methods are using a Genetic Algorithm (GA) and Particle Swarm Optimization algorithm (PSO) for finding optimal paths in moving objects. Within the previous technique, there’s no guarantee for fulfillment to finding a vehicle optimal path and also still now wants to improvement for choosing optimal path. To beat the disadvantage in the existing method, during this paper, to propose moving vehicle location prediction algorithm is an Artificial Bee Colony algorithm (ABC) and Feed Forward Back Propagation Neural Network (FFBNN). During this proposed algorithm is used for compute vehicle optimal path and selected optimal paths are given to the FFBNN to accomplish the training process. The trained FFBNN is then used to find the vehicle moving from the current location. By combining ABC algorithm and FFBNN, the moving vehicle’s location is predicted more efficiently. The outcomes of the FFBNN-ABC algorithm are compared with results of previous method, such as FFBNNGA, FFBNN-PSO. The evaluation result shows that the proposed technique more accurate than other algorithms.

Investigation of ANFIS and FFBNN Recognition Methods Performance in Tamil Speech Word Recognition

In speech word recognition systems, feature extraction and recognition plays a most significant role. More number of feature extraction and recognition methods are available in the existing speech word recognition systems. In most recent Tamil speech word recognition system has given high speech word recognition performance with PAC-ANFIS compared to the earlier Tamil speech word recognition systems. So the investigation of speech word recognition by various recognition methods is needed to prove their performance in the speech word recognition. This paper presents the investigation process with well known Artificial Intelligence method as Feed Forward Back Propagation Neural Network (FFBNN) and Adaptive Neuro Fuzzy Inference System (ANFIS). The Tamil speech word recognition system with PAC-FFBNN performance is analyzed in terms of statistical measures and Word Recognition Rate (WRR) and compared with PAC-ANFIS and other existing Tamil speech word recognition systems.

FEED FORWARD BACK PROPAGATION NEURAL NETWORK BASED CHARACTER RECOGNITION SYSTEM FOR TAMIL PALM LEAF MANUSCRIPTS

Optical character recognition refers to the process of translating segmented hand-written images or typewritten images into machine editable text. In this study, we propose a Tamil palm leaf manuscripts character recognition system using FFBNN technology. First the palm leaf manuscripts characters are segmented by exploiting the sliding window and adaptive histogram calculation. Afterwards, these segmented characters are assembled and then stored in a database. To accomplish the character recognition process, the characters thus stored in the database are learn by Feed Forward Back Propagation Neural Network (FFBNN). Ten set of Tamil palm leaf manuscripts are utilized to evaluate the performance of proposed FFBNN based character recognition system. The results show the effectiveness of proposed character recognition system in recognizing the palm leaf manuscripts characters and the achieved improvement in character recognition shows accuracy of 90%. The performance of the proposed FFBNN based character recognition system is evaluated by changing the number hidden layers for ten set of Tamil palm leaf manuscripts."

Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm

Computer-aided detection/diagnosis (CAD) systems can enhance the diagnostic capabilities of physicians and reduce the time required for accurate diagnosis. The objective of this paper is to review the recent published segmentation and classification techniques and their state-of-the-art for the human brain magnetic resonance images (MRI). The review reveals the CAD systems of human brain MRI images are still an open problem. In the light of this review we proposed a hybrid intelligent machine learning technique for computer-aided detection system for automatic detection of brain tumor through magnetic resonance images. The proposed technique is based on the following computational methods; the feedback pulse-coupled neural network for image segmentation, the discrete wavelet transform for features extraction, the principal component analysis for reducing the dimensionality of the wavelet coefficients, and the feed forward back-propagation neural network to classify inputs into normal or abnormal. The experiments were carried out on 101 images consisting of 14 normal and 87 abnormal (malignant and benign tumors) from a real human brain MRI dataset. The classification accuracy on both training and test images is 99% which was significantly good. Moreover, the proposed technique demonstrates its effectiveness compared with the other machine learning recently published techniques. The results revealed that the proposed hybrid approach is accurate and fast and robust. Finally, possible future directions are suggested.

Rapid and Precise GLONASS GDOP Approximation using Neural Networks

Russian global navigation satellite system (GLONASS) provides civilian and military users three-dimensional position determination and navigation services as same as US global positioning system. Geometric dilution of precision (GDOP) provides a simple interpretation of positioning precision. Usual method for GLONASS GDOP calculation is matrix inversion. However this process imposes a huge calculation load on receiver, especially when large number of visible satellites exists. To overcome this problem, artificial neural network is used. Different configurations and training methods are simulated on a data base obtained by a GLONASS receiver. Then navigation precision and execution times are explored and compared. Results show that recurrent neural network has 0.00024 RMS error, which is the best against other focused tools including feed forward back propagation and radial basis function neural network with usual training and with genetic algorithm adopted weights and biases.

Classification of power quality disturbances using minimum entropy and feed forward back propagation neural network approach

Classification of power quality disturbances using minimum entropy and feed forward back propagation neural network approach