A multilayer perceptron is a feedforward artificial neural network model that maps sets of input data onto a set of appropriate output. It is a modification of the standard linear perceptron in that it uses three or more layers of neurons (nodes) with nonlinear activation functions, and is more powerful than the perceptron in that it can distinguish data that is not linearly separable, or separable by a hyper plane. MLP networks are general-purpose, flexible, nonlinear models consisting of a number of units organised into multiple layers. The complexity of the MLP network can be changed by varying the number of layers and the number of units in each layer. Given enough hidden units and enough data, it has been shown that MLPs can approximate virtually any function to any desired accuracy. This paper presents the performance comparison between Multi-layer Perceptron (back propagation, delta rule and perceptron). Perceptron is a steepest descent type algorithm that normally has slow convergence rate and the search for the global minimum often becomes trapped at poor local minima. The current study investigates the performance of three algorithms to train MLP networks. Its was found that the Perceptron algorithm are much better than others algorithms.

With the evolution of mobile technologies and its applications, more and more government agencies are putting forth a huge effort to encourage citizens to use mobile government services. Hence, the citizens’ opinion is important to enhance the services and improve their engagement in the government services. Hence, this study has critically reviewed and explored the existing technology acceptance models and theories in order to develop an evaluation framework. The proposed framework is empirically tested by structural equation modeling using data collected from a structured questionnaire. Furthermore, the validated research model contains important variables to ensure the acceptance of mobile services. We hope that the implications of this study will help the public organizations and governments to gain more understanding about what drives the development and acceptance of mobile government services

It is really important to diagnose jaw tumor in its early stages to improve its prognosis. A differential diagnosis could be performed using X-ray images; therefore, accurate and fully automatic jaw lesions image segmentation is a challenging and essential task. The aim of this work was to develop a novel, fully automatic and effective method for jaw lesions in panoramic X-ray image segmentation. The hybrid Fuzzy C-Means and Neutrosophic approach is used for segmenting jaw image and detecting the jaw lesion region in panoramic X-ray images which may help in diagnosing jaw lesions. Area error metrics are used to assess the performance and efficiency of the proposed approach from different aspects. Both efficiency and accuracy are analyzed. Specificity, sensitivity and similarity analyses are conducted to assess the robustness of the proposed approach. Comparing the proposed approach with the Hybrid Firefly Algorithm with the Fuzzy C-Means, and the Artificial Bee Colony with the Fuzzy C-Means algorithm, the proposed approach produces the most identical lesion region to the manual delineation by the Oral Pathologist and shows better performance (FP rate is 6.1%, TP rate is 90%, specificity rate is 0.9412, sensitivity rate is 0.9592 and similarity rate is 0.9471)

Fish Recognition Based on Robust Features Extraction from Size and Shape Measurements Using Neural Network

The purpose of this paper, acceptance of Electronic Health Records (EHRs) system in the Jordan eHealth sector, is to contribute to develop the quality of hospitals, reduce medical error issues and reduce health costs. However, few researches have addressed the antecedent factors of healthcare professionals’ intentions to use an EHR system. Founded on trust factors integrated with the UTAUT2 model, a theoretical model is proposed to explain the exercise behaviour of healthcare professionals to use an EHR system.