Search

Rotary wing drones stand out among Unmanned Aerial Vehicles with their vertical landing and take-off feature and are used in many industrial applications and different sectors. Ensuring the stability of motion in these vehicles is crucial. Errors in the motor assembly can disrupt the stability of the motion in rotary wing drones. Therefore, it is essential to detect these errors during the assembly phase. In this study, we propose a cost-effective method based on deep learning to detect assembly failure of brushless direct current motors, which are widely used in rotary wing drones. A test setup representing the motor assembly defects is created and vibration data for three different speeds of the motor are obtained through a low-cost vibration sensor. The combined one- and two-dimensional deep convolutional neural network (WDD-CNN), used to classify these data was trained with the Case Western Reserve University (CWRU) dataset and the data collected in this study. The hyper-parameter settings of the network were determined using the CWRU data set and the data obtained from the experimental setup described in the paper. The network parameters of the WDD-CNN network were transferred to the Raspberry Pi micro-controller with specialized software, and the classification process was performed there. The fact that the proposed method runs on a micro-controller reduces its cost. Because there is already a micro-controller card in drones. In addition, the selected sensor is cost-effective. Thanks to these features, the proposed method is cost effective. In this classification process performed on Raspberry Pi 5, assembly errors were detected with 97–100% accuracy. [ABSTRACT FROM AUTHOR]

In this study, for the first time in the literature, identification of different chaotic systems by classifying graphic images of their time series with deep learning methods is aimed. For this purpose, a data set is generated that consists of the graphic images of time series of the most known three chaotic systems: Lorenz, Chen, and Rossler systems. The time series are obtained for different parameter values, initial conditions, step size and time lengths. After generating the data set, a high-accuracy classification is performed by using transfer learning method. In the study, the most accepted deep learning models of the transfer learning methods are employed. These models are SqueezeNet, VGG-19, AlexNet, ResNet50, ResNet101, DenseNet201, ShuffleNet and GoogLeNet. As a result of the study, classification accuracy is found between 96% and 97% depending on the problem. Thus, this study makes association of real time random signals with a mathematical system possible. [ABSTRACT FROM AUTHOR]

In this study, for the first time in the literature, a Variable-Order Fractional Hopfield Neural Network Under Electromagnetic Radiation (VOFHNNUER) has been presented. Also, for the first time, Pseudo Random Number Generator (PRNG) based image encryption and data hiding application for VOFHNNUER using Least Significant Bit (LSB) method has been performed and digital circuit implementation over the sound card of a PC has been implemented. In the study, first of all, a numerical solution for VOFHNNUER, which is a four-dimensional chaotic system, has been made with Grünwald-Letnikov method. The obtained time series from the numerical solutions have been physically realized through a sound card in two channels. In addition, using the calculated state variables, a PRNG has been designed and tested with NIST-800-22 test. Finally, a PRNG-based image encryption and data hiding algorithm with the LSB method has been developed and applied for an RGB image. In this algorithm, first, a gray-scale image (message data) was encrypted and then the encrypted image was hidden into the RGB image. So, a two-level data security application has been realized. [ABSTRACT FROM AUTHOR]

In this study, a new variable-order fractional chaotic neural network with frequency effect is proposed based on Hopfield Neural Network Under Electromagnetic Radiation, which is used to model brain functions in the literature. The numerical solution of this proposed system is carried out by the Grünwald–Letnikov (G–L) method, and time series and phase portraits are presented. In addition, the chaotic behavior is analyzed by Lyapunov exponent analysis according to the frequency parameter used for the variable-order function. A Pseudo-Random Number Generator (PRNG) is designed for data security applications using the obtained state variables and the usability of the PRNG is demonstrated with the NIST-800-22 test. Afterward, a data-hiding algorithm for personal data is presented for multi-channel biomedical signals based on the designed PRNG. With this algorithm, implementations are made for EEG, ECG, and EMG signals. It is shown in time and frequency domains that the method is usable for data-hiding applications. In addition, the effectiveness of the newly developed algorithm is proven with statistical methods. [ABSTRACT FROM AUTHOR]

Today, all smartphones, notebooks, or other communication devices could connect to the cloud, so the data are accessible everywhere. When these devices are interconnected through the internet, they make an Internet of Things (IoT) network that exchanges data among network nodes and other services. IoT has a broad application area from smart applications to various industrial usages. However, the high volume of data transferred in the IoT network makes it crucial to implement mechanisms to transfer the data safe and secure. Enciphering is one of the best techniques to offer end-to-end security. Considering an IoT network, nodes have restricted resources, and applying classical cryptography methods are costly and not efficient, so lightweight block ciphers are one of the sophisticated solutions to overcome security drawbacks in this scope. In this paper, ten lightweight algorithms involve AES, PRESENT, LBlock, Skipjack, SIMON, XTEA, PRINCE, Piccolo, HIGHT, RECTANGLE tested to evaluate their performance for key factors such as memory usage (RAM and ROM), energy consumption, throughput, and execution time for both encryption and decryption modes over cloud transmission. We have done simulations using Raspberry Pi 3 and Arduino Mega 2560 as the leading devices in the IoT scope. As a result, this paper will help IoT developers to choose the right platform and enciphering algorithm to set up a secure network due to multiple factors like energy and memory usage, especially for software platforms. [ABSTRACT FROM AUTHOR]

With rapid technology development, data sizes are increasing and more powerful hardware structures are needed to process these data. An alternative solution for this process is to parallel the transactions to be realized, to provide the time gain, increase the efficiency and reduce the transaction costs. In this article, a new chaos-based parallel encryption algorithm design is presented to meet this requirements. In the study, a new random number generator (RNG) and chaos-based parallel encryption algorithm are developed. Using developed RNG, confusion and encryption of pixel in images have been realized. Also parallel computing has been used to increase security and speedup the encryption. With the new parallel encryption algorithm, the security and performance tests of the image encryption application and the encryption process have been made. In addition, the evaluated performance of the parallel computing is described in speedup and efficiency. [ABSTRACT FROM AUTHOR]

In this article a simple chaotic flow with hidden attractor is proposed. Various dynamics of this new system such as periodic and chaotic oscillations can be achieved by setting bifurcation parameters in a proper value. Nowadays chaos based engineering applications like encryption and hiding data face some significant problems. Chaotic systems with hidden attractors, which our system belongs to them, may unfold some primary steps to solve these problems. As the first step, chaotic behavior of our proposed system has been realised in physical existence by using the Orcard-PSpise software. We have found a proper qualitative likeness between experimental and simulation result. Then, chaos-based random number generator design is carried out using the proposed chaotic system. The numbers obtained from the random number generator are applied to the NIST 800-22 tests, and all of the random numbers are passed through the all tests. A chaos-based encryption algorithm with a random number generator is developed and image encryption application is implemented. Encryption results are compared with the AES algorithm, and performance and security evaluation of the developed encryption algorithm is performed. [ABSTRACT FROM AUTHOR]

In this study, a novel chaos-based hybrid encryption algorithm design for secure and effective image encryption is presented. To design the algorithm, the Zhongtang chaotic system has been selected because of its rich dynamic features and its dynamical analysis is performed. On the base of this system, a new chaos-based random number generator (RNG) is developed and usefulness of the designed RNG in an encryption process is shown over NIST 800-22 randomness tests. S-Box generation algorithm is designed, and the performance tests of S-Box are realized. By using the designed RNG and S-Box generation algorithms, the new hybrid image encryption algorithm based on AES (CS-AES) is developed. Image encryption applications are performed for comparison with other encryption algorithms in the literature to show its security level and efficiency. Security and performance analyses are made, and results are evaluated. So, it is proved that the proposed CS-AES algorithm is more secure and effective. [ABSTRACT FROM AUTHOR]

This paper presents a new class of chaotic systems with infinite number of equilibrium points like a three-leaved clover. They signify an exciting class of dynamical systems which represent many major characteristics of regular and chaotic motions. These chaotic systems belong to the general class of chaotic systems with hidden attractors. By using a systematic computer search, three chaotic systems with three-leaved-clover-shaped equilibria were found which are classified into dissipative systems. Dynamics of the chaotic system with the three-leaved-clover-equilibria has been investigated by using phase portraits, bifurcation diagram, Lyapunov exponents, Kaplan-Yorke dimension and Poincaré map. Moreover, an electronic circuit implementation of the theoretical system is designed to check its effectiveness. Random number generator design has been realized with newly developed chaotic systems. The obtained random bit sequences are used for image encryption. Security analysis of image encryption processes has been performed. [ABSTRACT FROM AUTHOR]

Substitution Box (S-Box) is one of the most significant structures used to create an encryption which is strong and resistant against attacks in block encryption algorithms. S-Box plays an important role in data encryption. This paper presents a novel S-Box generation algorithm design based on scaled Zhongtang chaotic system. In this study, a new random number generator which uses the new scaled Zhongtang chaotic system with very complicated and interesting dynamic features is designed; also, a new effective and strong S-Box design algorithm utilizing this RNG (random number generator) is developed. Bits generated by RNG are put to NIST tests and they passed all the NIST tests. Non-linearity, bit independence criteria, strict avalanche criteria, differential approximation probability performance tests are run on the proposed S-Box produced by new S-Box design algorithm. The proposed S-Box is compared with other studies available in the literature, and it is proved stronger and more effective. [ABSTRACT FROM AUTHOR]