Journal of Artificial Intelligence in Electrical Engineering
Volume:8 Issue: 32, Winter 2020

In general, identifying and locating faces in images or videos is considered as the first step in face recognition. It is quite clear that an accurate detection algorithm can significantly benefit system performance and vice versa. Therefore, face recognition is one of the key steps in the application of face recognition systems. In deep learning algorithms are able to learn high-level features, which have been highly regarded by researchers for use in the field of machine vision, as well as in a variety of fields such as image classification and human gesture estimation, which are the key activities for image perception. In this paper, we present a hybrid method called Hyper-Yolo-face to identify faces, facial landmarks localization, pose estimation and recognize the gender of a given image using deep convolutional neural networks, the Yolo algorithm, and local binary patterns. The proposed network architecture is based on the AlexNet model and the integration of the binary pattern operator and Yolov3, which results in increasing performance and accuracy. Yolo changes the architecture of face recognition systems and looks at the problem of recognition as a regression problem which goes directly from the pixels of the image to the coordinates of the box and the probability of the classes. Experiments on the AFLW and FDDB datasets indicated that the proposed model performs significantly better than other algorithms and methods and improves detection accuracy.

This work proposes a new meta-mathematical method called arithmetic optimization algorithm that uses the distributive behavior of the main arithmetic operators in mathematics, including division, subtraction, and addition for now the number of distinct entries in the multiplication table n. Therefore, there is some interest in algorithms for calculating M (n) exactly or as an approximation. We compare several algorithms for exact calculation of M (n) and come up with a new algorithm with suborder execution time. We also present two Monte Carlo algorithms to approximate M (n). We give exact calculation results for values of n to 230 and compare our experimental results with Ford's order of magnitude results. Experimental results show that INTEGERS provides very promising results in solving difficult optimization problems compared to 11 other well-known optimization algorithms.

One of the most important problems in molecular electronics is to calculate the quantum transport and the contact resistance of the molecular coupling to the metal electrodes. The well-known approach to attaching nanostructures to external electrodes is to use thiolate bonds. Our computational method is based on solving the Non-equilibrium Green's function (NEGF) in conjunction with density functional theory (DFT). We use the quantum Atomistic Tool Kit (ATK) program package. We calculate quantum transmission spectra, the projected device density of states (PDDOS), the IV characteristics, and the electrical conductance of the two-probe nanostructure: gold- benzene dithiol-gold. The electronic structure and energy bandgap of a two-probe open system is achieved via PDDOS. Besides, the electrical behavior shows that the conductance of this nanostructure is nonlinear.

As the ability to perform computation increased from the early days of computers and up to the present so was the knowledge how to utilize the hardware and software to perform computation. Digital computer arithmetic emerged from that period in two ways: one as an aspect of logic design and other as development of efficient algorithms to utilize the available hardware.Given that numbers in a digital computer are represented as a string of zeroes and ones and that hardware can perform only relatively simple and primitive set of Boolean operations, all of the arithmetic operations performed are based on a hierarchy of operations that are built upon the very simple ones.

in this paper, a new example of these structures has been designed and simulated using two-dimensional photon crystals. This proposed structure uses point nano-amplifiers to couple light to waveguides, and two input and output waveguides. In the design of this all-optical switch, the mechanism of interference effect in photon crystals has been used in order to make the structure simpler and smaller. This optical structure is based on silicon technology and is designed using dielectric rods in an air bed. In this structure, the constant value of the lattice is about 549 nm, the radius of the dielectric rods is about 100 nm and the radius of the nano-optical intensifiers is 30 nm. This structure was active at 1550 nm and by examining at 1559, its performance in switching mode was analyzed. The response rate of the structure was 0.75 ps. The rate of placement losses in the structure for different inputs according to the input power of 1 mW / 2m2 is about -13 dB and the rate of shutdown rate for this input is equal to 12.8 dB. In order to optimize the structure in terms of the effects of the parameters involved in it to examine various factors, including; The input power, wavelength and central frequency, the size of the radius of the nano-resonator rods, the size of the dielectric rods and the fixed network are discussed. In order to analyze the structure in terms of scattering and photon band gap range, PWE method has been used and to analyze and obtain the output spectrum of the structure, FDTD method has been used. Due to the size of 7.86 m2, flexibility and suitable simulation results, this proposed structure is very suitable for applications of optical integrated circuits.

All designers try to get rid of all the hardware and software tools before they hit the market, but it shows that such a goal is unattainable. Some of these environmental factors are unexpected and unavoidable, as well as some potential mistakes are predictable. Due to the development of semiconductor technologies, hardware components are naturally naturally reliable and the need for component fault tolerance in applications has been reduced. However, fault tolerance remains a requirement in many critical-safety, critical-mission, and critical-commercial applications.Therefore, even when a system appears to be fully designed and implemented, the designer may experience errors outside of control. On the other hand, since it is practically impossible to build a complete and error-free system, fault tolerance is required. The main problem arises that he is sure he finds it, compensation can be applied. As a result, a tolerable system manages individual errors in hardware or software components, power supply failures, or other types of unforeseen adverse events.