Elsayed A. Sallam

Adaptive fuzzy sliding mode control using supervisory fuzzy control for 3 DOF planar robot manipulators

Control of an industrial robot includes nonlinearities, uncertainties and external perturbations that should be considered in the design of control laws. This paper presents a control strategy for robot manipulators, based on the coupling of the fuzzy logic control with the so-called sliding mode control, SMC, approach. The motivation for using SMC in robotics mainly relies on its appreciable features, such as design simplicity and robustness. Yet, the chattering effect, typical of the conventional SMC, can be destructive. In this paper, this problem is suitably circumvented by adopting an adaptive fuzzy sliding mode control, AFSMC, approach with a proportional-integral-derivative, PID sliding surface. For this proposed approach, we have used a fuzzy logic control to generate the hitting control signal. Moreover, the output gain of the fuzzy sliding mode control, FSMC, is tuned on-line by a supervisory fuzzy system, so the chattering is avoided. The stability of the system is guaranteed in the sense of the Lyapunov stability theorem. Numerical simulations using the dynamic model of a 3 DOF planar rigid robot manipulator with uncertainties show the effectiveness of the approach in trajectory tracking problems. The simulation results that are compared with the results of conventional SMC with PID sliding surface indicate that the control performance of the robot system is satisfactory and the proposed AFSMC can achieve favorable tracking performance, and it is robust with regard to uncertainties and disturbances.

An enhanced differential evolution optimization algorithm

The Differential Evolution (DE) algorithm, introduced by Storn and Price in 1995, has become one of the most efficacious population-based optimization approaches. In this algorithm, use is made of the significant concepts of mutation, crossover, and selection. The tuning control parameters are population size, mutation scaling factor, and crossover rate. Over the last decade, several variants of DE have been presented to improve its performance aspects. In the present paper, we further enhance DE. The population size and mutation scaling factor are taken alone in the tuning process; the crossover rate is treated implicitly in the crossover stage. Five forms for crossover are suggested for the first 100 iterations of the computational algorithm. After this learning period, we pick the form which yields the best value of the objective function in the greatest number of iterations (among the 100). Our algorithm is tested on a total of 47 benchmark functions: 27 traditional functions and 20 special functions chosen from CEC2005 and CEC2013. The results are assessed in terms of the mean and standard deviation of the error, success rate, and average number of function evaluations over successful runs. Convergence characteristics are also investigated. Comparison is made with the original DE and Success-History based Adaptive DE (SHADE) as a state-of-the-art DE algorithm, and the results demonstrate the superiority of the proposed approach for the majority of the functions considered.

Hand gesture recognition using fourier descriptors

Accurate, real-time hand gesture recognition is a challenging and crucial task due to the need of more natural human-computer interaction methods. The major problem lies in fining a good compromise between the accuracy of recognition and the computational load for the algorithm to run in real-time. In this paper we propose a method for static hand gesture recognition using Fourier descriptors for feature extraction with different classifiers. Fourier descriptors have the advantage of giving a set of features that are invariant to rotation, translation and scaling. They are also efficient in terms of speed as they only use a small number of points from the entire image. The proposed method is evaluated using images from the Cambridge Hand Gesture Dataset at different number of features and different classifiers. The effectiveness of the method is shown through simulation results.

Self adaptive Hadoop scheduler for heterogeneous resources

Nowadays, Hadoop is a widely used framework for processing large data. Hadoop scheduler is a critical element which has a big effect on Hadoop performance. Finding a dynamic scheduler which adapts to different nodes computing capabilities and the same node performance is a challenging problem. Most of the current Hadoop schedulers consider the homogeneity of the resources on which Hadoop is running and assign each node in the cluster a fixed capacity over the run time, neglecting the different nodes computing capabilities and the performance of each node over the run time. This causes under/over utilization of resources, poor performance and longer run time. So, we propose a dynamic Hadoop scheduler which adapts to the performance and the computing capabilities of each node separately. The proposed scheduler controls the capacity of each node which represented by the number of tasks that can be processed concurrently at a time. The scheduler extends/shrinks the capacity of each node depending on its available resources and performance over the run time. Our scheduler is implemented on Hadoop and compared by the Hadoop Fair Scheduler. The experimental results show that our scheduler has achieved less average completion time and higher resources utilization.

A proposed generalized mean single multiplicative neuron model

This paper presents a single multiplicative neuron model based on a polynomial architecture. The proposed neuron model consists of a non-linear aggregation function based on the concept of generalized mean of all multiplicative inputs. This neuron model has the same number of parameters as the single multiplicative neuron model (SMN). The SMN model is a special case of the proposed generalized mean single multiplicative neuron (GMSMN) model. The structure of this model is simpler than higher-order neuron model. The simulation results show that the performance of the proposed neuron model is better than SMN model.

A classification framework for diagnosis of focal liver diseases

Computer-aided detection/diagnosis (CAD) systems are critical for doctors to understand the medical images and to improve the accuracy of detection/diagnosis of various diseases. The goal of this paper is to propose a classification framework for diagnosing different focal liver diseases based on ultrasound (US) images. Ultrasound medical imaging is one of the most common modality, which is used in diagnostic systems because of its safety and cost effectiveness. In this paper, we introduced a framework for a CAD system to diagnosing three classes of focal liver diseases, which are Cyst, Hemangioma (HEM), and Hepatocellular Carcinoma (HCC). The proposed system begins with a preprocessing step to make enhancement and noise removal of US images using a median filter. The segmentation of the liver lesions regions is done using level set method followed by the fuzzy c-mean clustering algorithm. Finally, we have used a multi-support vector machine (multi-SVM) classifier to diagnosis the classes of the focal liver diseases. By using 10-fold cross validation method, we have got an overall classification accuracy of 96.5%. Our proposed system is compared with some state of the art techniques. The experimental results show that the proposed system gives better overall accuracy than the other tested techniques.

Modeling and Analysis of a Novel Flexible Capacitive-Based Tactile Sensor

In recent years, autonomous robots have been increasingly deployed in unstructured and unknown environments. In order to survive in theses environments, robots are equipped with sensors. One of the main sensors is tactile sensor which provides the robots with tactile information like texture, stiffness, temperature, vibration and normal and shear forces. In this paper, we propose a flexible capacitive tactile sensor which is designed for measuring both normal and shear forces. The tactile sensing unit consists of five layers, a bottom layer of Polyethylene Terephthalate (PET) with a pillar, two copper electrodes embedded into a Polydimethylsiloxane (PDMS) film, a spacer, a Polyimide (PI) film and finally a top PI bump. The bump and the pillar structure play a significant role in producing a torque for shear force measurement. Finite element modeling (FEM) is conducted to analyze the deformation of the sensing unit and simulated using COMSOL Multiphysics. The change of capacitance verse normal and shear forces are obtained, a comparison between the proposed sensor and other pervious sensor is conducted. The sensitivity of a cell is 0.22%/N within the full scale range of 10 N for normal force and 4%/N within the full scale range of 10 N for shear force.

Modelling of CVBF algorithm using Coloured Petri Nets

Modelling is a general method used throughout the development of systems. Numerous modelling languages were proposed for analyzing and building systems. Petri Nets language is considered as one of the formal modelling and analysis techniques. These techniques allow users to do both the performance evaluation and model checking. Coloured Petri Nets (CPN) is one of the modelling languages especially for discrete-event systems. In this paper, we use Coloured Petri Nets to model and analyze the behavior of the Clustering Vector-Based Forwarding (CVBF) routing protocol in Underwater Wireless Sensor Networks (UWSNs). Our proposed model is tested and verified by the state space statistics analysis which results that the proposed CPN model is liveness, responsiveness and free from deadlocks. The results of the performance evaluation of the proposed model demonstrate the proposed model capability to increase both the packet delivery ratio and the average end-to-end delay.

Single multiplicative neuron model based on generalized mean

This paper presents a single multiplicative neuron model based on a polynomial architecture. The proposed neuron model consists of a non-linear aggregation function based on the concept of generalized mean of all multiplicative inputs. This neuron model has the same number of parameters as the single multiplicative neuron model (SMN). The SMN model is a special case of the proposed generalized mean single multiplicative neuron (GMSMN) model. The structure of this model is simpler than higher-order neuron model. The simulation results show that the performance of the proposed neuron model is better than SMN model.

Efficient transmission of 1D and 2D chaotic map encrypted images with orthogonal frequency division multiplexing

Image transmission takes place as an important research branch in multimedia broadcasting communication systems in the last decade. Our paper presents image transmission over a FFT-OFDM (Fast Fourier Transform Orthogonal Frequency Division Multiplexing). The need for encryption techniques increase with the appearance of the expression which said that our world became small village, and the use of image application such as conference and World Wide Web which increase rapidly in recent years. Encryption is an effective method for protecting the transmitted data by converting it into a form being invisible over transmission path and visible in receiver side. This paper presents a new hybrid encryption technique based on combination of Backer maps and logistic map. This proposed technique aims to increase PSNR and reduce the noise in the received image. The encryption is done by shuffling the positions of a pixel image using two dimensional Baker maps then encrypt using XOR operation with logistic map to generate cipher image over orthogonal frequency multiplexing (OFDM). The encryption approach adopted in this paper is based on chaotic Baker maps because the encoding and decoding steps in this approach are simple and fast enough for HDTV applications. The experimental results reveal the superiority of the proposed chaotic based image encryption technique using two logistic maps and two dimensional Backer map over normal Backer map.