Aashish Kumar Bohre¹, Ganga Agnihotri¹, Manisha Dubey¹ and Jitendra Singh Bhadoriya², ¹MANIT, Bhopal and ² DAVV, Indore

Abstract: The proposed work introducing new coefficients and some modern control parameters such as sensitivity (s(t)) and probability of nectar (p(t)) and modification of the conventional parameter (
). With presenting these parameters the performance and searching ability of the BF-PSO is significantly increased compared to standered PSO. This new algorithm is inspired by the intelligent behavior of butterfly during the nectar search process. Which clarify a relationship between intelligent network structures of the BF-PSO and the performances. This work pays attention to the sensitivity and the probability of nectar based on the degree of nodes used in BF-PSO. The proposed results indicate the searching performance of the BF-PSO is depended on the degree of the node. The presented results for the BF-PSO applying on benchmark function are shown in tables. The search performance of the BFPSO is improved according to the sensitivity and probability of nectar.

Keywords: Artificial intelligence, BF-PSO (Butterfly-PSO), Butterfly communication network, sensitivity, probability of nectar, Degree of the node.

Full Text

Alireza Rezvani and Majid Gandomkar, Islamic Azad University, Saveh, Iran

 

Abstract: Photovoltaic (PV) systems have one of the highest potentials and operating ways for generating electrical power by converting solar irradiation directly into the electrical energy. In order to control maximum output power, using maximum power point tracking (MPPT) system is highly recommended. This paper simulates and controls the photovoltaic source by using artificial neural network (ANN) and genetic algorithm (GA) controller. Also, for tracking the maximum point the ANN and GA are used. Data are optimized by GA and then these optimum values are used in neural network training. The simulation results are presented by using Matlab/Simulink and show that the neural network-GA controller of grid-connected mode can meet the need of load easily and have fewer fluctuations around the maximum power point, also it can increase convergence speed to achieve the maximum power point (MPP) rather than conventional method. Moreover, to control both line voltage and current, a grid side p-q controller has been applied.

 

Keywords: Mppt; neural network; genetic algorithm; controller; Photovoltaic

 

  

Full Text

Maziar Izadbakhsh and Majid Gandomkar1, Islamic Azad University, Saveh, Iran

 

Abstract: Environmental and sustainability concerns are developing the significance of distributed generation (DG) based on renewable energy sources. In this paper, dynamic responses investigation of grid connected wind turbine using permanent magnet synchronous generator (PMSG) under variable wind speeds and load circumstances is carried out. In order to control of turbine output power using Fuzzy Logic controller (FLC) in comparison with PI controller is proposed. Furthermore, the pitch angle based on FLC using wind speed and active power as inputs, can have faster responses, thereby leading to smoother power curves, enhancement of dynamic performance of wind turbine and prevention of mechanical damages to PMSG. Inverter adjusted the DC link voltage and active power is fed by d-axis and reactive power is fed by q-axis (using P-Q control mode). Simulation of wind power generation system (WPGS) is carried out in Matlab/Simulink, and the results verify the correctness and feasibility of control strategy.

 

Keywords: Dynamic responses, FLC, Pitch Angle, PMSG, P-Q control

 

  

Full Text

S.Kannan¹ , S.Chinnaiya¹ and S.U.Prabha², ¹K.S.R. College of Engineering Tiruchengode, India and ²Sri Ramakrishna Engineering College,Coimbatore, India

 

Abstract: An advanced direct torque control (DTC) technique using Model predictive control (MPC) is proposed for matrix converter (MC)-based permanent-magnet synchronous motor (PMSM) drive system, which reduces the torque ripples, does not need the duty cycle calculation, and ensures the fixed switching frequency. Analytical expressions of change rates of torque and flux of PMSM as a function of MC - dqo components are derived. The predictive model of PMSM and MC is realized by means of State model. Then, the advanced MC-fed DTC algorithm is implemented based on Cost function evaluation. The simulation results exhibit remarkable torque ripple reduction with the help of MPC. As a result, the proposed strategy is proved to be effective in minimizing the torque ripples for MC-based PMSM drives.

 

Keywords: Direct torque control (DTC), matrix converter (MC), permanent-magnet synchronous motor (PMSM), Model predictive control (MPC), and Cost function

 

  

Full Text

Yasel Garc_es, Esley Torres, Osvaldo Pereira and Roberto Rodr__guez, Institute of Cybernetics, Cuba

 

Abstract: Ring theory is one of the branches of the abstract algebra that has been broadly used in images. However, ring theory has not been very related with image segmentation. In this paper, we propose a new index of similarity among images using Zn rings and the entropy function. This new index was applied as a new stopping criterion to the Mean Shift Iterative Algorithm with the goal to reach a better seg-mentation. An analysis on the peformance of the algorithm with this new stopping criterion is carried out. The obtained results proved that the new index is a suitable tool to compare images

 

 

Full Text

Aruna Bhat, Indian Institute of Technology Delhi, India

 

Abstract: Face recognition is one of the most unobtrusive biometric techniques that can be used for access control as well as surveillance purposes. Various methods for implementing face recognition have been proposed with varying degrees of performance in different scenarios. The most common issue with effective facial biometric systems is high susceptibility of variations in the face owing to different factors like changes in pose, varying illumination, different expression, presence of outliers, noise etc. This paper explores a novel technique for face recognition by performing classification of the face images using unsupervised learning approach through K-Medoids clustering. Partitioning Around Medoids algorithm (PAM) has been used for performing K-Medoids clustering of the data. The results are suggestive of increased robustness to noise and outliers in comparison to other clustering methods. Therefore the technique can also be used to increase the overall robustness of a face recognition system and thereby increase its invariance and make it a reliably usable biometric modality.

 

Keywords: Medoids, Clustering, K-Means, K-Medoids, Partitioning Around Medoids

 

  

Full Text

Habiba Benzater, Samira Chouraqui, University of Science and Technology of Oran-Mohammed Boudiaf, Algeria

 

Abstract: In the industry, Multi-objectives problems are a big defy and they are also hard to be conquered by conventional methods. For this reason, heuristic algorithms become an executable choice when facing this kind of problems. The main objective of this work is to investigate the use of the Non-dominated Sorting Genetic Algorithm II (NSGA-II) technique using the real valued recombination and the real valued mutation in the tuning of the computed torque controller gains of a PUMA560 arm manipulator. The NSGA-II algorithm with real valued operators searches for the controller gains so that the six Integral of the Absolute Errors (IAE) in joint space are minimized. The implemented model under MATLAB allows an optimization of the Proportional-Derivative computed torque controller parameters while the cost functions and time are simultaneously minimized.. Moreover, experimental results also show that the real valued recombination and the real valued mutation operators can improve the performance of NSGA-II effectively.

 

Keywords: PD Computed Torque Control, Intelligent Control, PUMA560 arm manipulator, Multi-objective, Optimization, NSGA-II algorithm, real valued recombination.

 

Full Text

Ed-Edily M. Azhari, Mudzakkir M. Hatta, Zaw Zaw Htike and Shoon Lei Win, Faculty of Engineering, IIUM, Malaysia

 

Abstract: A tumor also known as neoplasm is a growth in the abnormal tissue which can be differentiated from the surrounding tissue by its structure. A tumor may lead to cancer, which is a major leading cause of death and responsible for around 13% of all deaths world-wide. Cancer incidence rate is growing at an alarming rate in the world. Great knowledge and experience on radiology are required for accurate tumor detection in medical imaging. Automation of tumor detection is required because there might be a shortage of skilled radiologists at a time of great need. We propose an automatic brain tumor detection and localization framework that can detect and localize brain tumor in magnetic resonance imaging. The proposed brain tumor detection and localization framework comprises five steps: image acquisition, pre-processing, edge detection, modified histogram clustering and morphological operations. After morphological operations, tumors appear as pure white color on pure black backgrounds. We used 50 neuroimages to optimize our system and 100 out-of-sample neuroimages to test our system. The proposed tumor detection and localization system was found to be able to accurately detect and localize brain tumor in magnetic resonance imaging. The preliminary results demonstrate how a simple machine learning classifier with a set of simple image-based features can result in high classification accuracy. The preliminary results also demonstrate the efficacy and efficiency of our five-step brain tumor detection and localization approach and motivate us to extend this framework to detect and localize a variety of other types of tumors in other types of medical imagery.

 

Keywords: Tumor Detection, Medical Imaging, Computer Vision, Machine Learning

 

Full Text

M. E. Abdel-Aal, Benha University,Egypt

 

Abstract: In this paper, we show that the number of edges for any odd harmonious Eulerian graph is congruent to 0 or 2 (mod 4), and we found a counter example for the inverse of this statement is not true. We also proved that, the graphs which are constructed by two copies of even cycle Cn sharing a common edge are odd harmonious. In addition, we obtained an odd harmonious labeling for the graphs which are constructed by two copies of cycle Cn sharing a common vertex when n is congruent to 0 (mod 4). Moreover, we show that, the Cartesian product of cycle graph Cm and path Pn for each n ≥ 2, m ≡ 0 (mod 4) are odd harmonious graphs. Finally many new families of odd harmonious graphs are introduced.

 

Keywords: Odd harmonious labeling, Eulernian graph, Cartesian product, Cyclic graphs

 

  

Full Text