Mohammadreza Asghari Oskoei | Allameh Tabataba'i University (original) (raw)

Uploads

Papers by Mohammadreza Asghari Oskoei

International Journal of Electrical and Computer Engineering (IJECE)

In neural networks, simultaneous determination of the optimum structure and weights is a challeng... more In neural networks, simultaneous determination of the optimum structure and weights is a challenge. This paper proposes a combination of teaching-learning based optimization (TLBO) algorithm and a constructive algorithm (CA) to cope with the challenge. In literature, TLBO is used to choose proper weights, while CA is adopted to construct different structures in order to select the proper one. In this study, the basic TLBO algorithm along with an improved version of this algorithm for network weights selection are utilized. Meanwhile, as a constructive algorithm, a novel modification to multiple operations, using statistical tests (MOST), is applied and tested to choose the proper structure. The proposed combinatorial algorithms are applied to ten classification problems and two-time-series prediction problems, as the benchmark. The results are evaluated based on training and testing error, network complexity and mean-square error. The experimental results illustrate that the propose...

Journal of Robotics

Indoor position estimation is essential for navigation; however, it is a challenging task mainly ... more Indoor position estimation is essential for navigation; however, it is a challenging task mainly due to the indoor environments’ (a) high noise to signal ratio and (b) low sampling rate and (c) sudden changes to the environments. This paper uses a hybrid filter algorithm for the indoor positioning system for robot navigation integrating Particle Filter (PF) algorithm and Finite Impulse Response (FIR) filter algorithm to assure the continuity of the positioning solution. Additionally, the Hector Simultaneous Localisation and Mapping (Hector SLAM) algorithm is used to map the environment and improve the accuracy of the navigation. The paper implements the hybrid algorithm that uses the integrated PF, FIR, and Hector SLAM, using an embedded laser scanner sensor. The hybrid algorithm coupled with Hector SLAM is tested in several scenarios to evaluate the performance of the system, in terms of continuity and accuracy of the position estimation, and compares it with similar systems. The s...

International Journal of Modelling, Identification and Control

2008 Ieee Rsj International Conference on Intelligent Robots and Systems, Sep 1, 2008

ABSTRACT This paper proposes a myoelectric-based virtual joystick to manipulate an electric power... more ABSTRACT This paper proposes a myoelectric-based virtual joystick to manipulate an electric powered wheelchair for people with severe motor disabilities. It is built on pattern recognition-based myoelectric control that discriminates muscular activities using forearmpsilas surface myoelectric signals. The core of the system is a support vector machine based classifier that classifies signal time domain features. Online training scheme is applied to cope with gradual changes in myoelectric signal patterns. Two indexes, contineousness and entropy, were used to update training data set in real time operation. The results confirm that the proposed myoelectric-based joystick is a reliable alternative for traditional joysticks and its performance is fairly acceptable.

This manuscript is a review over the published articles on edge detection. At first, it provides ... more This manuscript is a review over the published articles on edge detection. At first, it provides theoretical background, and then reviews wide range of methods of edge detection in different categorizes. The review also studies the relationship between categories, and presents ...

International Journal of Intelligent Systems and Applications, 2015

2015 AI & Robotics (IRANOPEN), 2015

Robot motion planning has always been one of the fundamental issues in robotic area. In this pape... more Robot motion planning has always been one of the fundamental issues in robotic area. In this paper three motion planning algorithms, A*, Rapidly Exploring Random tree (RRT) and RRT*, are simulated and compared. A* algorithm is a well-known method in motion planning problems which can find the optimum path between two point in a finite time. In contrast the RRT family algorithm, by random sampling from the environment, converges to a collision-free path. By simulating these algorithms in complex environments by using java language, it is concluded that RRT family algorithms are significantly faster than A* algorithm however the paths which are found by RRT algorithms are longer than A*. Also the influence of different distance measurement methods such as Manhattan distance and Euclidean distance, on the number of seen nodes and the path length is studied.

Knapsack problem, is one the most important issues in decision-making and optimization problems, ... more Knapsack problem, is one the most important issues in decision-making and optimization problems, especially in which time and investment has a great importance rate. Genetic Algorithm (GA) and Particle Swarm Optimization algorithm (PSO) can be mentioned as a solution to this problem. GA is one of evolutionary algorithms, that in each of all possible combinations, the best solutions are selected in order to optimize the cost-function. Also PSO algorithm opimized the nonlinear function based on the social behavior of birds. In this paper, by implementing two algorithms, GA and PSO, the process of solving the knapsack problem is comapred. The results of this study, showed that while the GA has a higher speed to converge to an answer, but the efficiency and accuracy of PSO is higher than GA algorithm.

Lecture Notes in Computer Science, 2015

2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2008

Biomedical Signal Processing and Control, 2015

Concepts, Methodologies, Tools, and Applications, 2014

2013 Fourth International Conference on Emerging Security Technologies, 2013

ABSTRACT Our society is moving towards an ageing society and the number of population with physic... more ABSTRACT Our society is moving towards an ageing society and the number of population with physical impairments and disabilities will increase dramatically. It is necessary to provide mobility support to these people so that they can live independently at home and integrated into the society. This paper presents a ROS (Robot Operating System) based multi-sensor navigation for an intelligent wheelchair that can help the elderly and disabled people. ROS provides an easy to use framework for rapid system development at a reduced cost. Some experimental results are given in the paper to demonstrate the feasibility and performance of the developed system.

2013 IEEE International Conference on Systems, Man, and Cybernetics, 2013

ABSTRACT The demographic trend is towards ageing in our society and the number of people with phy... more ABSTRACT The demographic trend is towards ageing in our society and the number of people with physical impairments and disabilities will increase dramatically in the future. It is necessary to deliver advanced healthcare and services to these people so that they can live independently and stay well at home throughout their lifespan. This paper presents a multi-robot architecture for ambient assisted living of the elderly and disabled, which is based on the robot operating system (ROS). A communication bridge is proposed for different means of human robot interaction, and ROS provides a framework for rapid system development with a reduced cost. Some experimental results are given in the paper to demonstrate the feasibility and performance of the proposed system.