With the rapid expansion of electronic data transmission, unauthorized data access is growing. Information security against unwanted access is becoming increasingly essential in data storage and data transfer. Images are a common type of information that is used in almost every aspect of life, so the security of image data against unwanted access is critical. In this article, we propose an encryption technique that uses a symmetric encryption method based on XOR operation between the plain image and another image that will be used as a key agreed upon by both the sender and recipient. To ensure the security of the plain images, the scheme performs pixel permutation procedures dynamically using random numbers on the key image and plain image in each encryption process, which renders the encryption algorithm strong and brute-force resistant. Simulation results on several standard images showed a random distribution of pixel values and a higher pass rate correlated with entropy and ideal values for analysis parameters. Thus, through the use of randomization, the proposed algorithm is resistant to various attacks and offers promising security measurements while maintaining efficient and fast execution.
1 March 2024 in IAES International Journal of Artificial Intelligence (IJ-AI)
Handwritten digit recognition has been widely researched by the recognition society during the last decades. Deep convolutional neural networks (CNN) have been exploited to propose efficient handwritten digit recognition approaches. However, the CNN model may need an optimization algorithm to achieve satisfactory performance. In this work, a performance evaluation of seven optimization methods applied in a straightforward CNN architecture is presented. The inspected algorithms are stochastic gradient descent (SGD), adaptive gradient (AdaGrad), adaptive delta (AdaDelta), adaptive moment estimation (ADAM), maximum adaptive moment estimation (AdaMax), nesterov-accelerated adaptive moment estimation (Nadam), and root mean square propagation (RMSprop). Experiments have been carried out on two standard digit datasets, namely Modified National Institute of Standards and Technology (MNIST) and Extended MNIST (EMNIST). The results have shown the superior performance of RMSprop and Adam algorithms over the peer methods, respectively.
Over the past decade, the Global Positioning System (GPS) has been extensively employed in land vehicle navigation systems. Inertial Navigation Systems (INSs) are utilized in scenarios where GPS fails to deliver consistent and reliable navigation solutions. It is well-known that the low-cost INS sensors can exhibit significant errors. To mitigate these errors, the measurements of position and velocity sensors from GPS are integrated and fused. In this study, an intelligent technique has been proposed to optimize the benefits of GPS and INS while minimizing their drawbacks. This study employed an artificial intelligence model to predict the instantaneous INS error based on instantaneous de-noised measurements and readings. Different artificial neural network (ANN) models have been tested, examined and compared. The results revealed that a considerable improvement has been reached in terms of ability to predict INS error during different GPS outages. However, a promising result have been found using RNN model. As compared to other ANN models, the RNN model gives better performance in terms of standard deviations of position and velocity errors. The standard deviations of prediction position errors resulting from RNN are equal to 0.0864, 0.0726, and 0.1297 min the sense of x, y and z channels, respectively, while the standard deviations of predicted velocity errors are 0.0025, 0.0029, and 0.0049 m s −1 on the x, y, and z axis, respectively.
Optimizers are approaches or algorithms dependent to enhance the characteristics of the Neural Network (NN) like weights and learning rate in order to decrease the loss rate, On the other hand, Siamese Neural Network (SNN) are two identical sub-networks, they work in parallel and they are sharing parameters and weight, SNN uses for indicate similarity. In this research, we study the effect of optimizers Siamese Neural Network, using Digits handwritten (MINST) dataset, the effects is studied for Adam, Nadam, Adadelta and SGD optimizers with respect to process time and accuracy, the accuracy is 97%, 97%, 79% and 92%.
28 September 2023 in Iraqi Journal of Computers, Communications, Control and Systems Engineering
The artificial intelligence techniques such as neural networks and fuzzy systems play an important role to disconnect flexion & expansion of the swing leg, the earth response force of the other foot has been redesigned. Underthat paper, we think the fuzzy controller plan issue for yield following flawed genuine investigation of nonlinear systems. For examination, an essential fuzzy control plot has been bristly developed dependent on a current methodology delegate under the field.In this paper, the Feedforward Neural Network has been implemented with integer, fixed point and floating point data representations. Additionally, The Fuzzy Logic Controllers in both analog and digital forms has been implemented in hardware. Both designs use less hardware resources and operate with reasonable speed compared to other existing designs. The digital implementation of Fuzzy Logic Controller has been tested for a simulated first order liquid level process and the performance results have been compared with those of the Matlab version of Fuzzy Logic Controller. Here, Fuzzy Logic Controller is used as the controller and is trained adaptively for the changes in process parameters using recursive k-means clustering algorithm for updating the centers of the hidden layer and Recursive Least Square algorithm for updating the weights of the output layer, the result of the settling time about 20ms and takes 20 iterations, and the squared error reaches zero at approximately 20 µs. Index Terms— Fuzzy Controller, leg interaction force, Prosthetic legs, Human walking, GyroAccelerate,Fuzzy Logic System.