abbas miry - Academia.edu (original) (raw)

Papers by abbas miry

Automatic lesion segmentation is an important part of computer-based image analysis of pigmented ... more Automatic lesion segmentation is an important part of computer-based image analysis of pigmented skin lesions. Currently, there is a great interest in the development of Computer-Aided Diagnosis (CAD) systems for dermoscopic images. The segmentation step is one of the most important ones, since its accuracy determines the eventual success or failure of a CAD system. This study introduced new method of dermoscopic images segmentation. The preprocess was the filtering operation to dermoscopy image to remove most of difficulties facing the efficient segmentations, like a variety of lesion shapes, sizes, color, changes due to different skin types and textures and presence of hairs. Segmentation based mainly on histogram thresholding. The enhancements of image achieved by using mathematical morphology in order to obtain better segmentation with smooth border and without any noise in the lesion region. The proposed method evaluated by using Hammoude Distance (HM) and the True Detection Rate (TDR). Also the proposed method is compared with other skin lesions segmentation methods such as Otsu, adaptive thresholding and fuzzy Cmeans. The accuracy of proposed method was 96.32%, which is highly promised result and dependable.

This work presents a simulation of artificial human arm. It is aimed to allow the robotic system ... more This work presents a simulation of artificial human arm. It is aimed to allow the robotic system to perform motion of human arm. The work includes mathematical modeling of the kinematics and the dynamics of the human arm .The model permits direct forward dynamics simulation, which accurately predicts hand position, also presents a solution to the inverse problem of determining set of joints angle to achieve a given position or motion. This paper tries to explore the potential of using soft computing methodologies in control of plant (human arm). It presents a PD tuning method that uses a Particle Swarm Optimization (PSO) as a main gain of PD tuning using multi objective to improve the time response of system such settling time and overshoot MATLAB Ver.2009a software is used to show the efficiency of the proposed tuning rule. Simulation results demonstrate that better performance can be achieved with this method.

Soft computing research is concerned with the integration of artificial intelligent tools in a co... more Soft computing research is concerned with the integration of artificial intelligent tools in a complementary hybrid framework for solving real world problems. This paper tries to explore the potential of using soft computing methodologies in control of plant (human arm),utility and effectiveness of soft computing approaches for the control of seven degree of freedom of human arm with structured is presented. It presents a PID tuning method that uses a Particle Swarm Optimization (PSO) as a main gain of PID tuning using multi objective to improve the time response of system such settling time and overshoot. The method implements in the 3D space using Virtual Reality (VR) to compare between the proposed tuning rules and the traditional tuning rules under disturbance load. MATLAB Ver.2009a software is used to show the efficiency of the proposed tuning rule. Simulation results demonstrate that better performance can be achieved with this method relative to 1) trial and error tuning 2)Ziegler-Nichols tuning 3)conventional tuning .

This work presents a simulation methodology applied to a human arm. It is aimed to allow the huma... more This work presents a simulation methodology applied to a human arm. It is aimed to allow the human-assisting manipulators to perform complex movement based on electromyography (EMG) signal for patient person in Virtual Reality (VR). This work achieves better classification with multiple parameters based K-Nearest Neighbor for different movements of a prosthetic arm. A K-Nearest Neighbor (K-NN) rule is one of the simplest and the most important methods in pattern recognition. The method implements in the 3D space and uses the MATLAB Ver.2009a approach. This methodology can be used with different robots to test the behavior of system and the different motion.

This work presents a novel simulation methodology applied to a human arm. It is aimed to allow th... more This work presents a novel simulation methodology applied to a human arm. It is aimed to allow the robotic system to perform complex movement operations of human arm. The human arm is represented by using virtual reality (VR). The work includes mathematical modeling of the direct kinematics ,inverse kinematic and the dynamics of the human arm .The model permits direct forward dynamics simulation, which accurately predicts hand position, also presents a solution to the inverse problem of determining set of joints angle to achieve a given position or motion. The method is implemented in the 3D space and uses the Simulink/ MATLAB Ver.2009a approach. This methodology can be used with different robots to test the behavior and control laws.

—In a human–robot interface, the prediction of motion, which is based on context information of a... more —In a human–robot interface, the prediction of motion, which is based on context information of a task, has the potential to improve the robustness and reliability of motion classification to control human-assisting manipulators. The electromyography (EMG) signals can be used as a control source of artificial arm after it has been processed. The objective of this work is to achieve better classification with multiple parameters using K-Nearest Neighbor for different movements of a prosthetic arm. A K-Nearest Neighbor (K-NN) rule is one of the simplest and the most important methods in pattern recognition. The proposed structure is simulated using MATLAB Ver. R2009a, and satisfied results are obtained by comparing with conventional method of recognition using Artificial Neural Network(ANN), that explains the ability of the proposed structure to recognize the movements of human arm based EMG signals. Results show the proposed technique achieved a uniformly good performance with respect to ANN in term of time which is important in recognition systems, better accuracy in recognition when applied to lower SNR signal .

In this paper, a recognition system for image identification by using principal component analysi... more In this paper, a recognition system for image identification by using principal component analysis (PCA) and back propagation (BP) Neural Network is proposed. The system consists of three steps. At the very outset some pre-processing are applied on the input image. Secondly image features are extracted by using PCA, which will be taken as the input to the Back-propagation Neural Network (BPN) in the third step and classification. Principal Component Analysis (PCA) is one of the most popular appearance-based methods used mainly for dimensionality reduction in compression and recognition problems, this will reduce the size of training data which it entered to neural network. In our work, The proposed model is tested on a number of images with different value of learning rate. Experimental results demonstrate the proposed model is better, efficient and it reduces the ratio of the number of iteration training to half comparing with results of the Neural Network.

Images take lot of computer space, in many practical situations, all original images cannot be st... more Images take lot of computer space, in many practical situations, all original images cannot be stored, and a compression must be used. Moreover, in many such situations, compression ratio provided by even the best lossless compression is not sufficient, so lossy compression is used. Image compression requires higher performance as well as new features. A standard is currently being developed, called the Joint Photographic Experts Group (JPEG). One of drawback of JPEG method is the blocking effect in edge region .In this paper, we propos a method to overcome this problem by using different compression ratio depending on the region. In edge region, which contains important information the compression ratio is reduced to get good edge representation, while in the smoothness region which has not important information high compression ratio is used .The proposed method shows better results when compared with JPEG

Automatic lesion segmentation is an important part of computer-based image analysis of pigmented ... more Automatic lesion segmentation is an important part of computer-based image analysis of pigmented skin lesions. Currently, there is a great interest in the development of Computer-Aided Diagnosis (CAD) systems for dermoscopic images. The segmentation step is one of the most important ones, since its accuracy determines the eventual success or failure of a CAD system. This study introduced new method of dermoscopic images segmentation. The preprocess was the filtering operation to dermoscopy image to remove most of difficulties facing the efficient segmentations, like a variety of lesion shapes, sizes, color, changes due to different skin types and textures and presence of hairs. Segmentation based mainly on histogram thresholding. The enhancements of image achieved by using mathematical morphology in order to obtain better segmentation with smooth border and without any noise in the lesion region. The proposed method evaluated by using Hammoude Distance (HM) and the True Detection Rate (TDR). Also the proposed method is compared with other skin lesions segmentation methods such as Otsu, adaptive thresholding and fuzzy C-means. The accuracy of proposed method was 96.32%, which is highly promised result and dependable.

Biped robot has become more general purpose in our live as general behavioral patterns. It can wa... more Biped robot has become more general purpose in our live as general behavioral patterns. It can walk very similar to human walking pattern. Therefore, many robots have been researched and developed in recent years. Through this paper a planner biped robot is modeled for specific task. This paper tries to explore the potential of using Simulated Annealing (SA) methodologies in the Inverse Kinematic Problem (IKP),utility and effectiveness of this method for the solve IKP of biped robot is presented. It presents a new objective function to find the optimal posture of biped robot by employing some constrain in the objective function to meet best posture. A comparison between the proposed method and the classical method using Genetic Algorithm (GA) are made through the Matlab 2009a software to show the efficiency of the new method. Experimental results demonstrate that better performance can be achieved with this method. INTRODUCTION he word " Robot " first appeared in 1920 describing the perfect worker. It was only possible to actually develop a mechanical man after the invention of integrated circuits. The compact and electrically advanced IC's were able to give some sense of supervised intelligence to mechanical parts. The beginning of research on biped robots began with the development of the lower limb of a robot.

Face recognition is important in human identification. The biological recognition technique acts ... more Face recognition is important in human identification. The biological recognition technique acts as a good method and broad applications in security areas. This work presents a method to improve the face recognition accuracy using a combination of Principal Component Analysis (PCA), and Wavelet Transform. Wavelet Transform is used to decompose the input image with different levels and rearrangement of subband of wavelet in a way that extract a good information from the image; PCA is used as data redundancy and take the better representation of input data. We apply the proposed method on standard face recognition dataset, the ORL data and dataset from our environment to make the proposed method be practical. The comparison for different levels of wavelet show that the third level has better recognition accuracy with respect to other levels .Finally the performance of the proposed method is compared with other methods and gives better recognition accuracy.

Face recognition is an important in human identification. The biological recognition technique ac... more Face recognition is an important in human identification. The biological recognition technique acts as a good method and broad applications in security areas. This work presents a method to improve the face recognition accuracy using a combination of PCA, and Complex Wavelet Transform. Wavelet Transform is used to decompose the input image with different levels and rearrangement of subband of wavelet in a way that extract good information from the image; PCA is used as data redundancy and take the better representation of input data. We apply the proposed method on standard face recognition dataset, the ORL data and dataset from our environment to make the proposed method is practical. The comparison for different levels of wavelet show that the third level has better recognition accuracy with respect to other levels .Also the complex wavelet can be recognize the rotated images .Finally the performance of the proposed method is compared with other methods and gives better recognition accuracy.

— Soft computing research is concerned with the integration of artificial intelligent tools in a ... more — Soft computing research is concerned with the integration of artificial intelligent tools in a complementary hybrid framework for solving real world problems. This work presents a simulation of artificial human arm. The work includes mathematical modeling of the kinematics and the dynamics of the human arm .The model permits direct forward dynamics simulation, which accurately predicts arm position, also presents a solution to the inverse problem of determining set of joints angle to achieve a given position or motion. This paper tries to explore the potential of using soft computing methodologies in control of plant (human arm). It presents a PD tuning method that uses a Particle Swarm Optimization (PSO) as a main gain of PD tuning using multi objective to improve the time response of system such settling time and overshoot. This paper presents a strategy based on combine's analytical solutions with nonlinear optimization algorithm solutions to solution the IKP. A analytical solutions is used to reduce the size of problem from seven variable of joint angle to single variable and nonlinear optimization algorithm was used to find approximate solution which make the computation time is very small.

Kinematics for robotic systems with many degrees of freedom (DOF) and high redundancy are still a... more Kinematics for robotic systems with many degrees of freedom (DOF) and high redundancy are still an open issue. Namely, computation time in robotic applications is often too high to reach good solution, for parts of the kinematic chain; the problem of inverse kinematics is not linear, as rotations are involved. This means that analytical solutions are only available in limited situations. In all other cases, alternative methods will have to be an employed.The most-used alternative is numerical solutions optimization. This paper presents a strategy based on combine's analytical solutions with nonlinear optimization algorithm solutions to solution the IKP. A analytical solutions is used to reduce the size of problem from seven variable of joint angle to single variable and nonlinear optimization algorithm was used to find approximate solution which make the computation time is very small

Automatic lesion segmentation is an important part of computer-based image analysis of pigmented ... more Automatic lesion segmentation is an important part of computer-based image analysis of pigmented skin lesions. Currently, there is a great interest in the development of Computer-Aided Diagnosis (CAD) systems for dermoscopic images. The segmentation step is one of the most important ones, since its accuracy determines the eventual success or failure of a CAD system. This study introduced new method of dermoscopic images segmentation. The preprocess was the filtering operation to dermoscopy image to remove most of difficulties facing the efficient segmentations, like a variety of lesion shapes, sizes, color, changes due to different skin types and textures and presence of hairs. Segmentation based mainly on histogram thresholding. The enhancements of image achieved by using mathematical morphology in order to obtain better segmentation with smooth border and without any noise in the lesion region. The proposed method evaluated by using Hammoude Distance (HM) and the True Detection Rate (TDR). Also the proposed method is compared with other skin lesions segmentation methods such as Otsu, adaptive thresholding and fuzzy C-means. The accuracy of proposed method was 96.32%, which is highly promised result and dependable.