Image compression using a feedforward neural network

The main objective of this paper is to propose a Neuro-Fuzzy based algorithm for Image compression. The inputs to the network are original image data, while the outputs are reconstructed image data, which are close to the inputs. If the amount of data required to store the hidden unit values and the connection weights to the output layer is less than the original data, compression is achieved. The compression ratio achieved in this paper is about 9 with good reconstructed image quality. The proposed network has an additional feature that each addition of a hidden unit to the network will always improve the image quality. Further the user can trade between image quality and compression ratio depending on the application requirement. The results are found to be better than the conventional methods.

Artificial intelligent provides diverse solutions for the complex problems in agriculture research. The study aimed to use three models of artificial neural networks (Feed Forward Neural Network (FFNN), Generalized Regression Neural Network (GRNN) and Radial-Basis Neural Network (RBNN)) in the field of wheat yield prediction. 27-year data for the period (1986-2012) were utilized to improve the models and four-year data (2013 and 2016) were used to estimate the models, to compare their outputs with the measured data. Prediction data was not entered in the process of building neural network models. The results showed that the optimal configuration of the FFNN model consists of 40 neurons in the hidden layer (8-40-1). The Tan Sigmoid activation function was used in both the hidden layer and the output layer using all of these models (anterior neural feeding network and the regression neural network and radial base neural network) in the 4-year wheat yield forecast field for production (2013-2016) by applying 8 input parameters that were result of NMMS (8.6%, 7.6% and 15.7% resp.), To find that FFNN and GRNN provide the best result from BRNN because while the information set was large or in a wide range, then the range data ranges from -1 to +1 (normalization data) , GRNN gives better outcomes after the information or sample data were in large range.

Now-a-days due to the huge increase in the size of image data Lossy Image Compression is highly used to reduce the image size but without having huge data loss. Image compression using SVD coding algorithm, Compressive Encoders and using prediction Error and Vectorization ratio are proved to have numerous application in image compression. Image compression using SVD coding algorithm involves refactoring of a digital image into three matrixes. Refactoring is achieved by using singular values, and the image is represented with a smaller set of values. Though, encoders cannot directly optimize due to the inherentNon-differentiability of the compression loss but it is out performing recently proposed approaches based on RNNs. The PE-VQ method is based on Prediction Error and Vector Quantisation techniques where image performance is determined using compression ratio and PSNR values using databases namely CLEF med 2009, Corel 1k and standard images like Lena, Barbara etc. Thus, in this research article a comparative study of these three techniquesis carried out where their image quality and compression ratio is examined by using the PSNR values and compression ratios.

Pulsed Nd:YAG laser has high intensity and high quality beam characteristics, which can be used to produce micro-grooves and micro-turning surface on advanced engineering ceramics. The present research attempts to develop mathematical models by using response surface methodology approach for correlating the machining process parameters and the process responses during laser micro-turning of aluminum oxide (Al2O3) ceramics. The process parameters such as laser average power, pulse frequency, workpiece rotating speed, assist air pressure and Y feed rate were varied during experimentation. The rotatable central composite design experimental planning has been used to design the experimentation. The performance measures considered are surface roughness (Ra) and micro-turning depth deviation. Multi-objective optimization has been carried out for achieving the desired surface roughness as well as minimum depth deviation during laser micro-turning operation. Further, an artificial neural network (ANN) model has been developed to predict the process criteria. Levenberg-Marquadt training algorithm is used for multilayer feed forward backpropagation neural network. The developed ANN model has 5-10-2 feed forward network. There are 5 neurons in the input layer, 10 neurons in the hidden layer and 2 neurons in the output layers corresponding to two output responses, respectively. The developed ANN model has been validated using data obtained by conducting additional set of experiments. It was found that the developed ANN model can predict the process criteria more accurately than response surface methodology (RSM) based developed models.

A review on neural networks with random weights

Compression of images process is a step in the image processing. It is concerned with the transmission and storage of digitally created images. Fractal coding is a potential image and video compression approach with good reconstruction fidelity and relatively large compression ratios, because of its simplicity and great performance; fractal image compression (FIC) is a particularly popular approach in image compression applications. However, it has a significant disadvantage in the form of a long encoding time. This is because encoding any small bit necessitates a massive similarity search in the original data As a result; the FIC search time is reduced while the quality of the reconstructed images is maintained acceptable level in many introduced paper and other still a study topic in progress. Fractal images are images that are self-similar in that each individual part is the same as the total. This paper will discusses many attempts for more author that working on image and video compression using fractal compression technique based on various approach and with each discuss focuses on the main parameter of compression such compression ratio (CR), peak signal to noise ratio (PSNR) and encoding time, as well as the details of data set the used for testing also writing with each technique to creating fractal video and image compression. Index Terms— FIC, Video compression, parallel processing, Iteration Function System (IFS), Image processing.

An artificial neural network model is applied to the delineation of boundaries between ore bodies based on borehole geophysical logging data, such as gamma-ray, density, neutron and resistivity in a Swedish underground mine, the Renstrom Mine. The input data set includes the four geophysical logging parameters and the output data to be predicted by the neural network consist of three rock classes, waste rock (rock class 1), semi-ore (rock class 2) and ore (rock class 3). Three boreholes, B33, B34 and B36, each of a length of approximately 40 m, were analyzed. Borehole B33 was divided into 20 sections based on the core log results. The four geophysical logging parameters, initially measured at 0.1 m intervals, were averaged in each section to form the training set for the neural network. The original data from boreholes B33, B34 and B36 were used as the test set. The optimum configuration of the neural network is a 4-layer neural network with 4 neurons in the input layer, 15 neurons in the first hidden layer, 5 neurons in the second hidden layer and 3 neurons in the output layer. The minimum error rate, 0.2160, in the test set, was obtained from training the network over 29,500 epochs. The ability of the neural network to delineate the boundaries between ore bodies from the geophysical logging data is encouraging, and this technique represents a great advantage compared to diamond core drilling and a qualitative and subjective judgement by a geologist in identifying the boundaries between ore bodies from geophysical logging data.

To overcome the problem of determining the number of hidden-layer neurons in feed-forward neural networks, a polynomial feed-forward neural network with a single hidden layer is presented based on the theory of polynomial approximation, where the polynomials are employed as the activation functions of hidden-layer neurons, and the weights between input layer and hidden layer are set to be 1. We only need to adjust the weights between hidden layer and output layer. Then, using the least square method, we could deduce the formula of computing weights directly. Furthermore, the basic ideas of the sieve-decrease algorithm of polynomial neural networks are described and discussed in details, together with several new concepts, such as weight-sieve, sieve-pore diameter, sieve-decrease rate,etc. Two illustrative computer-simulations substantiate that the improved polynomial feed-forward neural networks possess superior performance, and show that the number of hidden neurons decreases respectively by 98.19% and 80%, as compared to primal neural networks.

The illustration of a neural network based voltage instability detector utilizing broad region observing system and the calculated angle of the installed Phasor Measurement Units (PMUs) is introduced in this paper. Voltage instability is regarded one of the serious troubles that harshly shape the electric power quality. The system which is affected by voltage instability can be easily subjected to a rapid breakdown due to voltage collapse. A planned neural network based voltage instability detector is presented throughout this paper. This detector counts on the installed PMUs bus voltage angles. An enhanced Feed-Forward Neural Network (FFNN) is planned and trained. The FFNN includes one input layer, two hidden layers, and one output layer. The major advantage of the smart enhanced system is that, it can sense the voltage instability of the whole power system buses in the same time. The enhanced designed system is examined on 14-bus and 30-bus IEEE standard systems. The 14 bus and 30 bus IEEE systems are simulated using MATLAB/power system toolbox program to get each system load flow consequences. In addition, the influence of various loading conditions is used to the simulated system to get their equivalent bus angles values. Concerning each one of the examined system, different studied cases are held for various loading values with different power factors on different buses. The consequences of these cases are listed, normalized and processed using the ANN. While each one of the ANN is trained then the performance of the improved system is examined. The consequences of ANN are tested and regarded to be acceptable because of the high precision and dependable operation.

A BPG (better portable graphics) coder is a novel approach that aims to replace common standards of compression such as JPEG, JPEG2000 and so on. That is why, the BPG coder needs a detailed analysis of its basic characteristics from the viewpoint of visual quality and compression ratio. The BPG coder can use different modes of chroma subsampling for color and three-channel images and it is worth analyzing and comparing them. In practice, images to be compressed are often noisy. Then, lossy compression of such images has a specific noise filtering effect. In particular, optimal operation point (OOP) might exist where compressed image quality is closer to the corresponding noise-free (true) image than uncompressed (original, noisy) image quality according to certain criterion (metric). It is also needed to analyze the coder performance from compression ratio point of view. In this paper, we pay attention on impact of different chroma subsampling modes on image quality and compression ratio. Based on simulation results obtained for a set of color images, the best possible ways of compression are recommended.

This paper introduces the use of a modified feedforward neural network to cope with the problem of predicting protein functions. Since this kind of classification task is inherently hierarchical, this work proposes the use of two different architectures for the modified feedforward neural network, both mimicking the hierarchical nature of the classes (protein functions) to be predicted. The first approach consists of four feed-forward neural networks in cascade, each one taking as input the classification obtained by the previous network, which means, the input to a network is the classes that could be assigned to the protein at the immediately higher (parent) level in the class hierarchy. The second approach is an extension of the first one, which also adds as input to each sub-network the attributes of the protein being classified. In both situations, it was used two kinds of feed-forward architectures: an Adaline network, which is composed of a single layer of adjustable weights, and a MLP (Multi-Layer Perceptron), composed by two layers of adjustable weights. Both approaches were compared with a baseline consisting of a single MLP that maps the input attributes to the classes of the lowest level in the hierarchy. The MLP was built with the input layer, plus one hidden layer and one output layer. The three approaches were compared on eight datasets, the first four involving the prediction of GPCR (G-Protein Coupled Receptor) functions and the second four datasets involving the prediction of enzymes functions. The results show that a big-bang hierarchical neural network, based on the MLP paradigm, using a top-down evaluation for new instances has better behavior in hierarchical problems, when compared to its flat version.

Biosorption of copper(II) ions by flax meal: Empirical modeling and process optimization by response surface methodology (RSM) and artificial neural network (ANN) simulation

This study investigates the effectiveness of an Artificial Neural Network (ANN) model in enhancing the classification of dry beans varieties. The dry beans dataset, comprising 13,611 samples and 16 numerical features, was preprocessed using Z-score normalization for outlier removal and Principal Component Analysis (PCA) to remove 702 outliers and reduce dimensionality to 10 components while preserving 99.99% of the original variance. A feedforward ANN architecture was designed, constructed as a feedforward neural network with three fully connected layers namely, an input layer that receives 10 features (as reduced by PCA), a first hidden layer with 16 neurons and ReLU activation, a second hidden layer with 32 neurons and ReLU activation, and an output layer with neurons equal to the number of classes, using softmax activation for multi-class probability prediction. The model was trained over 60 epochs using TensorFlow/Keras. Evaluation on a held-out test set demonstrated that the ANN model achieved a classification accuracy of 94.50%. Performance metrics, including accuracy, precision, recall, F1-score, and confusion matrix analysis, confirmed the model's robustness and generalization capability across all dry beans’ classes. The findings affirm that ANN models, when supported by appropriate preprocessing, can serve as scalable and accurate alternatives to conventional machine learning approaches in agricultural classification tasks.

A feed-forward multilayer perceptron neural network model with Levenberg-Marquardt learning algorithm has been developed to predict rheological properties of water-based drilling fluids. The developed model was based on a three-layer network containing input, hidden, and output layer. The sigmoid function was applied as the transfer function in the hidden layer and linear transfer function in the output layer. Two statistical parameters, mean square errors and correlation coefficient, were used as a criterion for evaluating artificial neural network modeling performance. Accordingly, a comparison between experimental values and those predicted by the artificial neural network showed a good coincidence proving its high accuracy in estimating target value.

In this paper a hybrid fuzzy neural approach is proposed for the image compression. The inputs to the network are the preprocessed data of original image, while the outputs are reconstructed image data, which are close to the inputs. This process is similar to a typical function approximation problem which involves determining or learning the input-output relations using numeric input-output data. A mutual subset hood based Fuzzy Neural Network is used for image compression application as a function approximator. If the amount of data required to store the hidden unit values and the connection weights to the output layer is less than the original data, compression is achieved. The network is trained for different number of quantization bits with direct impact to compression ratio. It is experimented with different images that have been segmented in the sub image blocks of equal sizes for compression process. The results encourage the possibility of using proposed fuzzy neural network for image compression.