Journal of Computer and Robotics
Volume:12 Issue: 1, Winter and Spring 2019

One of the most important issues concerning the sensor data in the Wireless Sensor Networks (WSNs) is the unexpected data which are acquired from the sensors. Today, there are numerous approaches for detecting anomalies in the WSNs, most of which are based on machine learning methods. In this research, we present a heuristic method based on the concept of “ensemble of classifiers” of data mining.  Our proposed algorithm, at first applies a fuzzy clustering approach using the well-known C-means clustering method to create the clusters. In the classification step, we created some base classifiers, each of which utilizes the data of overlapping windows to utilize the correlation among data over time by creating time-overlapped batches of data. By aggregating these batches, the classifier proceeds to find an appropriate label for future incoming instance. The concept of “Ensemble of Classifiers” with majority voting scheme has been used in order to combine the judgment of all classifiers. The results of our implementation with MATLAB toolboxes shows that the proposed majority-based ensemble learning method attains more efficiency compared to the case of the single classifier method. Our proposed method enhances the performance of the system in terms of major criteria such as False Positive Rate, True Positive Rate, False Negative Rate, True Negative Rate, Sensitivity, Specificity and also the ROC curve.

One of the major challenges in robotic arms is to diagnosis sensor fault. To address this challenge, this paper presents an LPV approach. Initially, the dynamics of a two-link manipulator is modelled with a polytopic linear parameter varying structure and then by using a descriptor system approach and a robust design of a suitable unknown input observer by means of pole placement method along with linear matrix inequalities, in addition to providing an estimate of state variables for using in state feedback, the detection, isolation, and identification of sensor faults in the manipulator are addressed. The proposed observer provides a robust estimate of the faults along with attenuating the disturbance effects. Further, the desired angles of the joints are calculated for achieving the desired trajectory of the robot’s end-effector using the inverse kinematics and by designing a suitable state feedback law with integral mode, the reference signals are tracked. The sufficient condition for stability of the closed-loop system is obtained as a set of linear matrix inequalities at the vertices of the system. The efficiency and effectiveness of the control system, along with the designed fault diagnosis unit, are shown using numerical simulations.

Nowadays, the development of innovative technology has emerged, particularly in mobile phones. People are often using smartphones daily in almost every aspect of their lives to use different applications and share various types of information quickly while moving anywhere. Mobile’s email applications are classified as one of the important applications to communicate ubiquitously since the use of email is considered as the best formal way for communication inside any organization. Due to this importance of e-mail and the daily needs of using it especially for faculty members and students, we propose to develop a mobile application for KFU E-Mail system with secure data transmission. The proposed application has encryption and decryption features to ensure security. As a result, the students and faculty members can communicate via the email application in a safer and more comfortable way.

In recent years, many scientists in universities and research centers focused on quadcopters. One of the problems with quadcopters is the complexity of its manual control system. In a typical system, the user is the observer of robot in addition to controlling the radio controller. In this paper, using a fuzzy logic algorithm, a robot control system for main and subsidiary movements by human head or wrist voluntary-physical movements is considered. In this case, without looking at control board the user can control the robot only with changing the head control voluntary or physical movements. Simulation results show that using fuzzy algorithm for determining the bending scale in different angles can decrease the human errors and processor computations. Also using fuzzy logic algorithm in the designed system the robot can track the user voluntary-physical movements optimally. In addition, the system output noises adjust due to involuntary user movements.

The complex networks are widely used to demonstrate effective systems in the fields of biology and sociology. One of the most significant kinds of complex networks is social networks. With the growing use of such networks in our daily habits, the discovery of the hidden social structures in these networks is extremely valuable because of the perception and exploitation of their secret knowledge. The community structure is a great topological property of social networks, and the process to detect this structure is a challenging problem. In this paper, a new approach is proposed to detect non-overlapping community structure. The approach is based on multi-agents and the bat algorithm. The objective is to optimize the amount of modularity, which is one of the primary criteria for determining the quality of the detected communities. The results of the experiments show the proposed approach performs better than existing methods in terms of modularity.

In this paper, we propose a back-stepping controller scheme for the altitude subsystem of hypersonic missile of which model is nonlinear, non-minimum phase, uncertain, and highly coupled. In the scheme, the guidance law is selected as a desired flight path angle that derived from the sliding mode control method. The back-stepping technique is designed and analyzed for the altitude dynamics of hypersonic missiles for maneuvering targets. Additionally, the algorithm of adaptive neuro-fuzzy inference system (ANFIS) is used for estimating the uncertainty of model parameters and Lyapunove theorem is used to examine the stability of closed-loop systems. The simulation indicates that the proposed scheme has shown effectiveness of the control strategy, high accuracy, stability of states, and low-amplitude control inputs in the presence of uncertainties with external disturbance.

With the ever-increasing growth of electrical energy consumption in different fields of a power plant, expanding strategies in power plants is a vital, important and inevitable action. Generally, greenhouse gas emissions can be reduced by replacing wind energy instead of using fossil fuels in power plants for electricity generation. A physical system that is capable of harnessing energy for distribution and compensation electricity at a desired and determined later time is called a typical energy storage system. In this paper, a proper optimization method for expansion planning of electrical energy storage is presented. Since the meta-heuristic algorithms are a very suitable tool for optimization purposes, a hybrid of genetic algorithm (GA) and particle swarm optimization (PSO) technique are used in this research. The main objective of the optimization problem is to increase the energy storage. The implementation of the proposed method is performed using MATLAB and GAMS tools. The simulation results strongly validate the correctness and effectiveness of the proposed method.

Developing a reliable and safe system is one of the most important features of advanced computer-based systems. The software is often responsible for controlling the behavior of mechanical and electrical components as well as interactions between components in systems. Therefore, considering software safety and fault detection are essential in software development. This paper introduces an approach to engineering evidence that examines the software in its lifecycle according to the principles of software safety and system safety engineering. This approach ensures that software risks are identified and documented in the software lifecycle, after which the risks are reduced to an acceptable level in terms of safety according to the proposed methods. The presented approach was applied to a real master case with positive results, namely the Data and Command Unit.

Tracking objects in video images has attracted much attention by machine vision and image processing researchers in recent years. Due to the importance of the subject, this paper presents a method for improving object tracking tasks with partial occlusion, which increases the efficiency of tracking. The proposed approach first performs a pre-processing and extracts the tracking targets from the image. Then the salient feature points are extracted from the targets that are moving objects. In the next step, the particle filter is used for tracking. The final steps are modifying points and updates. A new approach is used to determine the speed of the feature points because the speed of some points can be out of range and this causes errors in tracking especially when there is occlusion. The location of the new points is corrected and updated using the threshold values in modifying the process as needed. The experiments performed on the video sequence of PETS2000 database show that the precision and recall of the proposed approach are higher than other compared approaches.

This paper addresses the application of using pneumatic force actuators at the hips of a five-link robotic system to provide a controllable input torque. The goal of this research is to provide a base to build upon to eventually produce an ” active” biped walking robot that utilizes the benefits of the passive walking cycle. A reduced-order mathematical model of the system consisting of the pneumatic proportional valve and actuators is utilized in designing the force controller. The model takes into account tube links, valve friction, piston friction, and valve mechanics. The five-link robot is also modeled, including moments of inertia, masses, and centers of mass to design the trajectory controller. The mathematical models provide the equations necessary to develop the nonlinear control laws based on Sliding Mode Control Theory for both the force and trajectory controller. The controllers receive input signals from both pressure and position sensors located at the hips and position sensors at the knees. These signals are then converted into digital signals and processed by the computer using numerical analysis to obtain ethical values. Once the signals are input into the controllers, the experimental results of the actual system track the desired force and position trajectories defined for each controller within desired limits.

This paper addresses the eye gaze estimation problem in low-resolution images, using the low-cost camera in order to eliminate problems caused by infrared high-resolution imaging such as needing an expensive camera, complex setup, special light sources, and being limited in lab research environments. In the proposed method, the human face is detected with Ant Colony Optimization (ACO) algorithm, and then the Kirsch compass mask is utilized to detect the position of humans’ eyes. For iris detection, a novel strategy based on ACO algorithm, which has been rarely used before, is applied. The pupil is recognized by morphological processing. Finally, the extracted features, obtained from the radius and position of the irises of the pupils, are given to the Support Vector Machine (SVM) classifier to detect the gaze pointing. In order to receive assurance of the reliability and superiority of the newly designed ACO algorithm, some other metaheuristic algorithms such as (GA, PSO, and BBO) are implemented and evaluated. Additionally, a novel dataset, comprising 700 images gazing at seven different major orientations, is created in this research. The extensive experiments are performed on three various datasets, including Eye-Chimera with 92.55% accuracy, BIOID dataset with 96% accuracy, and the newly constructed dataset with 90.71% accuracy. The suggested method outperformed the state of the art gaze estimation methods in terms of the robustness and accuracy.

The sensors in the Internet of things, especially in the health sector, requires a secure platform for data transfer. Because of the widespread use of the Internet of things, the security and longevity of these networks are becoming increasingly important. In this paper, we propose a secure channel between the group of sensors, server, and third party, as well as saving energy consumption of sensors. This channel contains a series of information, including exchanged messages between group members, servers, and a third-party that is used to perform secure encryption and authentication operations, so that sensors are safely assigned to the server and transfer the data securely. The results show that the proposed method has less communication and computational costs. Also, the energy consumption of the sensors in the channel is reduced by up to 40%.