Journal of Artificial Intelligence in Electrical Engineering
Volume:8 Issue: 30, Summer 2019

Nowadays, walking is considered as an efficient biometric feature for user authentication. Although there are some studies that address the task of securing gait patterns in gait-based authentication systems, but they do not take into account the low discrimination and high diversity of gait data, which significantly affects the security and practicality of the proposed systems. In this article, we focus on addressing the above shortcomings in the inertial sensor-based gait system. In particular, we use linear discrimination analysis to increase the discrimination of gait patterns, and use the amount of gray code to extract a high, differential, and stable binary pattern. Experimental results on 38 different users showed that our proposed method significantly improves the performance and security of the gait encryption system. Specifically, we obtained a false acceptance rate of 6 × 10−5 (for example, 1 failurein 16983 experiments) and a false rejection rate of 9 2 with 148-bit security.

This paper presents a multi-objective daily voltage and reactive (Volt/VAr) control in radial distribution systems including distributed generation (DG) units. The main purpose is to determine optimum dispatch schedules for on-load tap changer (OLTC) settings at substations, substation switched capacitors and feeder-switched capacitors based on the day-ahead load forecast. The objectives are selected to minimize the voltage deviation on the secondary bus of the main transformer, total electrical energy losses, the reactive power flow through the OLTC and voltage fluctuations in distribution systems, for the next day. Since the objectives are not the same, a fuzzy system is used to calculate the best solution. In order to simplify the control actions for OLTC at substations, a time-interval based control strategy is used for decomposition a daily load forecast into several sequential load levels. A binary ant colony optimization (BACO) method is used to solve the daily voltage and reactive control which is a non-linear mixed-integer problem. To illustrate the effectiveness of the proposed method, the Volt/VAr control is performed in IEEE 33-bus and 69-bus distribution systems and its performance is compared with genetic algorithm and hybrid binary genetic algorithm and particle swarm optimization algorithms. Simulation results show the BACO algorithm has better outperforms than other algorithms.

Feature-based methods are resistant to various types of attacks including tearing, and the syntactic property of the watermarking is retained in the watermark along with prominent image features. These image features may be the main image, local areas, or feature points such as its edges, corners, texture and color. The title of second generation of watermarking is introduced based on feature points.This category of watermarking uses prominent image features in both insertion and extraction operations of watermark as a reference. Features must have properties such as resistance to image transfer, rotation, resizing, as well as resistance to noise and local changes. As a result, due to the unchangeability properties of feature points and important areas, this method is resistant to geometric attacks and image processing. Another advantage of this method is its combination in the areas of location and frequency. This paper reviewed two resistant methods of surf and Harris which are widely used in feature-based watermarking.

Recommender systems has an important role in social networks. With the growth and development ofsocial networks, this issue is becoming more and more important. Recommending systems try to predict the user's interests and then suggest the closest items to the user's tastes. Recommender systems analyze the user’s behavior and suggest the most appropriate items. By collecting user information, the system categorizes and summarizes them, allowing users to access more relevant information in less time. Recommender system is an intelligent system that creates appropriate suggestions for each person by discovering and analyzing user information.In this paper, we will investigate recommending systems in three sections: types of recommendingsystems, information confidentiality and trust in recommender systems. We will refer to the relatedworks in each section, review the challenges of them, and present our results and evaluation on thesemethods

Deep learning has progressed rapidly in recent years and has been applied in many fields, which are the main fields of artificial intelligence. Traditional methods of machine learning most use shallow structures to deal with a limited number of samples and computational units. When the target objects have rich meanings, the performance and ability to generalize complex classification problems will be quite inadequate. The convolutional neural network (CNN), which has been developed in recent years, widely used in image processing; because it has high skills in dealing with image classification and image recognition issues and it has led to great care in many machine learning tasks and it has become a powerful and universal model of deep learning. The combination of deep learning and embedded systems has created good technical dimensions. In this paper, several useful models in the field of image classification optimization, based on convolutional neural network and embedded systems, are discussed. Since this paper focuses on usable models on the FPGA board, models known for embedded systems such as MobileNet, ResNet, ResNeXt and ShuffNet have been studied.

A novel scheme of microstrip-fed fractal Multi Input Multi Output (MIMO) antenna with fractal patches for WLAN, systems is studied and presented. The operating frequency of the presented MIMO is from 4.1 GHz to 6 GHz, which covers 5.5 GHz band. The simulated and measured results of the proposed MIMO illustrate that the frequency range is set to 4.1GHz up to 6 GHz for impedance bandwidths. The presented MIMO has size of 15×30mm2. Different geometry and configurations of proposed MIMO array for multiple applications are studied. It illustrates that the attributes of small size, efficient radiation characteristic and less mutual coupling for MIMO application are promising.