1) Simulation and Implementation of Multilevel Inverter Fed Induction Motor for Performance Improvement
(pp. 190-197)

Authors: Mr. Yogesh S. Bais, Dr. S.B.Deshpande

Abstract - Multilevel inverter (MI) starts from three level. The poor quality of voltage and current of a Conventional Inverter fed Induction machine is due to the presence of harmonics and hence there is significant level of energy losses. The inverters with large number of steps can generate high quality voltage waveforms. In the proposed scheme, a 3-level Diode Clamped Inverter fed induction motor is simulated using SPWM technique to give the 3-level output voltage with lesser distortion resulting in better drive performance. Also the Hardware circuit is prepared using MOSFET as the switching device and Sinusoidal Pulse Width Modulation (SPWM) for Gate triggering circuit. This generates output voltages with less distortion and lesser dv/dt. The multilevel inverter output has reduced harmonics and higher torque. It also reduces the heat generated in the stator winding of the induction motor. The simulation results reveal that the proposed circuit effectively controls the motor speed and enhances the drive performance through reduction in Total Harmonic Distortion (THD).


2) Removal of Shadow in Video Sequences Using Effectual Modeling of Descriptors Statistically
(pp. 198-202)

Authors: MM. Prakash, T.Grace Winsolin

Abstract - The identification and tracking of the moving objects in a color video sequence brings out the features of the images found in it and there found the shadows which later to remove the shadows from the identified objects play an important problem in computer vision applications in several fields, such as video surveillance and target tracking. Most techniques reported in the literature use background sub-traction techniques to obtain foreground objects, and apply shadow detection algorithms exploring spectral information of the images to retrieve only valid moving objects using Gaussian mixture model and Kernel density estimation. In this paper, foreground extraction is done by applying the background model through RGB color components as color video sequences are used. The background image is modeled using robust statistical descriptors and a noise estimate is obtained. Foreground pixels are extracted and a morphological operators are required which thus processed to take out the isolated foreground pixels. Finally, the collective frames are considered for analysis and comparison using sensitivity rate for indoor and outdoor environments and results has been showed for one another data sets in a compared format.


3) Composite Web Service Selection based on Co-evolutionary Co-operative Shuffled Frog Leaping Algorithm
(pp. 203-210)

Authors: C.Rajeswary, G. Krishnaveni

Abstract - The Composite Web Service Selection (CWSS) raises the challenging problem in selecting optimal web services. The copious collection of composite services makes the difficult selection process. WSS is an important part of web service composition and the process of selecting optimal services based on the user query has the direct influence on the Quality of Service (QoS). Hence, the optimal selection of composite service turns out to be an NP-hard problem. Inorder to tackle the NP-hard problem many Evolutionary Algorithms (EA) are applied. Since, it achieves a tremendous success by making use of the random decisions in different modules. The applications of EA’s are computational biology, Engineering, logistics and telecommunications. The EAs such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Ant Colony System (ACS), Bee Algorithm (BA), Invasive Weed Optimization (IWO), Shuffled Frog Leaping Algorithm (SFLA) and Firefly Algorithm (FA) works effectively on optimization problems. The benefits of EA over traditional local search methods, when search spaces are highly multimodal, discontinuous, or highly constrained. Despite its benefits, EAs tend to performs poor in situation such as Cartesian product of two more large problems and subspaces interaction problem. Inoder to avoid those difficulties in EAs the researches done the natural extension of EAs called co-evolution and co-operation. The naturally inspired co-evolutionary co-operative SFLA (CCSFLA) is applied to enhance the composite service selection. So we proposed the CCSFLA for CWSS problem to enhance an optimal selection. The other EAs are tested under multi-modal optimization test functions, the simulation results shows that CCSFLA approach significantly outperforms the existing method.


4) QoS-aware Composite Web Service Selection using Memetic Algorithm
(pp. 211-220)

Authors: G.Krishnaveni, M.Sathya, C.Rajeswary

Abstract - QoS driven composite web service selection (WSS) is a process of selecting the group of services to form abstract services is the NP hard as well as combinatorial optimization problem; evolutionary algorithms are more suitable to solve that kind of problem. The evolutionary algorithms such as genetic algorithm (GA), particle swarm optimization (PSO) and co-operative co-evolutionary algorithms and so on are used to solve WSS problem with QoS constraint up to some extent. As it plays a vital role in web service composition process, it has direct relation with the quality of composite service. In order to improve the QoS parameter in solving WSSP, Memetic Algorithm (MA), a meta-heuristic optimization algorithm is applied in this paper. MA employs two algorithms to select the services where, GA is used in WSSP first to perform global search and hill climbing (HC) algorithm is used as a sub module in GA where local search is performed. HC algorithm employed as a part of MA to provide the QoS in efficient way and better convergence results. Service QoS representing through trusted ontology. Advantage of this ontology is well representation and understanding of concepts. We have applied four optimization test functions compared with GA and PSO shows better performance. Experimental analysis are done through optimization test functions results the memetic algorithm can better satisfy QoS as well as time convergence requirements than other algorithm for optimal composite web service selection.



5)  Modeling an Affectionate Virtual Teacher for e-Learning
(pp. 221-226)

Authors: Hua Wang, Ishizuka Mitsuru, Shaikh Mostafa Al Masum

Abstract - “E-learning could become the major form of training and development in organizations as technologies will improve to create a fully interactive and humanized learning environment”. With a notion to acknowledge the above statement, this paper explains an affective role model of a virtual teacher intertwined with emotional states of e-learners to facilitate interactive and successful learning. The paper first presents the relationships between emotion and learning from different literature and surveys. Then model of an affectionate virtual teacher is explained with the help of a three-dimensional emotion model. Laboratory experiments to interrelate learners’ emotional state to the behavioral dynamics of virtual teacher’s are then discussed. The paper concludes with
the notion of future research.


6) A Reliable Distributed Grid Scheduler for Independent Tasks
(pp. 227-232)

Authors: Kovvur Ram Mohan Rao, Ramachandram S, Vijaya Kumar Kadappa and Govardhan A

Abstract - Scheduling of jobs is one of the crucial tasks in grid environment. We consider non-preemptive scheduling of independent tasks in a computational grid. Recently, a general distributed scalable grid scheduler (GDS) was proposed, which prioritizes mission-critical tasks while maximizing the number of tasks meeting deadlines. However, the GDS scheduler did not consider the reliability factor, which may result in low successful schedule rates. In this paper, we propose a novel distributed grid scheduler which takes reliability factor (RDGS) into consideration with respect to the failure of grid nodes. The proposed scheduler invokes the tasks allocated to deficient grid nodes and maintains them in a queue. Further the queued tasks are rescheduled to the other nodes of the grid. It is observed that RDGS scheduler shows a significant improvement in terms of successfully scheduled tasks as compared to a variation of GDS without priority and deadlines (GDS-PD). The results of our exhaustive simulation experiments demonstrate the superiority of   RDGS over the GDS-PD scheduler.


7) Improving Support Vector Machine Generalization via Input Space Normalisation
(pp. 233-239)

Authors: Shawkat Ali and Kate A. Smith

Abstract - Data pre-processing always plays a key role in learning algorithm performance. In this research we consider data pre-processing by normalization for Support Vector Machines (SVMs). We examine the normalization effect across 112 classification problems with SVM using the rbf kernel. We observe a significant classification improvement due to normalization. Finally we suggest a rule based method to find when normalization is necessary for a specific classification problem. The best normalization method is also selected by SVM itself.