Background/Objectives: The purpose of current research aims to a modified image representation framework for Content-Based Image Retrieval (CBIR) through gray scale input image, Zernike Moments (ZMs) properties, Local Binary Pattern (LBP), Y Color Space, Slantlet Transform (SLT), and Discrete Wavelet Transform (DWT). Methods/Statistical analysis: This study surveyed and analysed three standard datasets WANG V1.0, WANG V2.0, and Caltech 101. The features an image of objects in this sets that belong to 101 classes-with approximately 40-800 images for every category. The suggested infrastructure within the study seeks to present a description and operationalization of the CBIR system through automated attribute extraction system premised on CNN infrastructure. Findings: The results acquired through the investigated CBIR system alongside the benchmarked results have clearly indicated that the suggested technique had the best performance with the overall accuracy at 88.29% as opposed to the other sets of data adopted in the experiments. The outstanding results indicate clearly that the suggested method was effective for all the sets of data. Improvements/Applications: As a result of this study, it was found the revealed that the multiple image representation was redundant for extraction accuracy, and the findings from the study indicated that automatically retrieved features are capable and reliable in generating accurate outcomes.
Business organizations have faced many challenges in recent times, most important of which is information technology, because it is widely spread and easy to use. Its use has led to an increase in the amount of data that business organizations deal with an unprecedented manner. The amount of data available through the internet is a problem that many parties seek to find solutions for. Why is it available there in this huge amount randomly? Many expectations have revealed that in 2017, there will be devices connected to the internet estimated at three times the population of the Earth, and in 2015 more than one and a half billion gigabytes of data was transferred every minute globally. Thus, the so-called data mining emerged as a
... Show MoreIn this paper, we derive and prove the stability bounds of the momentum coefficient µ and the learning rate ? of the back propagation updating rule in Artificial Neural Networks .The theoretical upper bound of learning rate ? is derived and its practical approximation is obtained
The speech recognition system has been widely used by many researchers using different
methods to fulfill a fast and accurate system. Speech signal recognition is a typical
classification problem, which generally includes two main parts: feature extraction and
classification. In this paper, a new approach to achieve speech recognition task is proposed by
using transformation techniques for feature extraction methods; namely, slantlet transform
(SLT), discrete wavelet transforms (DWT) type Daubechies Db1 and Db4. Furthermore, a
modified artificial neural network (ANN) with dynamic time warping (DTW) algorithm is
developed to train a speech recognition system to be used for classification and recognition
purposes. T
Artificial Neural Networks (ANN) is one of the important statistical methods that are widely used in a range of applications in various fields, which simulates the work of the human brain in terms of receiving a signal, processing data in a human cell and sending to the next cell. It is a system consisting of a number of modules (layers) linked together (input, hidden, output). A comparison was made between three types of neural networks (Feed Forward Neural Network (FFNN), Back propagation network (BPL), Recurrent Neural Network (RNN). he study found that the lowest false prediction rate was for the recurrentt network architecture and using the Data on graduate students at the College of Administration and Economics, Univer
... Show MoreThe aim of this paper is to approximate multidimensional functions f∈C(R^s) by developing a new type of Feedforward neural networks (FFNS) which we called it Greedy ridge function neural networks (GRGFNNS). Also, we introduce a modification to the greedy algorithm which is used to train the greedy ridge function neural networks. An error bound are introduced in Sobolov space. Finally, a comparison was made between the three algorithms (modified greedy algorithm, Backpropagation algorithm and the result in [1]).
High peak to average power ration (PAPR) in orthogonal frequency division multiplexing (OFDM) is an important problem, which increase the cost and complexity of high power amplifiers. One of the techniques used to reduce the PAPR in OFDM system is the tone reservation method (TR). In our work we propose a modified tone reservation method to decrease the PAPR with low complexity compared with the conventional TR method by process the high and low amplitudes at the same time. An image of size 128×128 is used as a source of data that transmitted using OFDM system. The proposed method decrease the PAPR by 2dB compared with conventional method with keeping the performance unchanged. The performance of the proposed method is tested with
... Show MoreThe inverse kinematics of redundant manipulators has infinite solutions by using conventional methods, so that, this work presents applicability of intelligent tool (artificial neural network ANN) for finding one desired solution from these solutions. The inverse analysis and trajectory planning of a three link redundant planar robot have been studied in this work using a proposed dual neural networks model (DNNM), which shows a predictable time decreasing in the training session. The effect of the number of the training sets on the DNNM output and the number of NN layers have been studied. Several trajectories have been implemented using point to point trajectory planning algorithm with DNNM and the result shows good accuracy of the end
... Show More