1 Job Scheduling Using Fuzzy Neural Network Algorithm in Cloud Environment, V. Venkatesa Kumar and K. Dinesh
Cloud Computing is providing computing as a service rather than product such as shared resources, software information, etc...Cloud computing can be used for dispatching user tasks or jobs to the available system resource like storage and software. Scheduling algorithm is used for dispatching user tasks. In Job scheduling using fuzzy neural network algorithm, first user tasks are classified based on Quality of service parameters like bandwidth, memory, CPU utilization and size. The classified tasks are given to fuzzier where the input values are converted into the range between 0 and 1. Neural network contains input layer, hidden layer and output layer for adjusting the weight of user task and match with system resources. The function of de-fuzzier is to reverse the operation performed by fuzzier. The exemplar input is matched with the exemplar output label by adjusting weights. The algorithm is implemented with the help of simulation tool (CloudSim) and the result obtained reduces the total turnaround time and also increase the performance.
2 Expected Time to Recruitment in A Single Graded Man Power System With Inter- Decision Times As A Geometric Process, G. Ishwarya, N. Shivaranjani and A. Srinivasan
Random depletion of manpower occurs in any marketing organization due to the attrition of personnel when the management takes policy decisions regarding pay, perquisites and targets. This attrition will adversely affect the smooth functioning of the organization in due course of time when the loss of man power is not compensated by recruitment. Frequent recruitment is not advisable as it involves more cost. In view of this situation and from a suitable recruitment policy to plan for recruitment. In this context, for a single graded organization a mathematical model is constructed in this paper using a bivariate recruitment policy based on shock model approach. Assuming that the inter-decision times form a geometric process, the mean time to recruitment is obtained for different cases on the distribution of the thresholds. The influence of nodal parameters on the mean time to recruitment is studied numerically and relevant findings and conclusions are presented.
3 An Advanced Genetic Optimization Algorithm to Solve Combined Economic and Emission Dispatch Problem, R. Gopalakrishnan and Dr.A. Krishnan
The dispatch of electric load is one of the key functions in electrical power system operation, management and planning. The key intention of economic load dispatch is to reduce the total production cost of the generating system and at the same time the necessary equality and inequality constraints should also be fulfilled. In the present time, energy resources to generate mechanical power supplied to the rotor shaft of generating units are of fossil fuels. This leads to the emission of huge amount of carbon dioxide (CO2), sulfur dioxide (SO2) and nitrogen oxides (NOx) that results in atmospheric pollution. Reducing those pollutions resulted by usage of fossil-fired generating units has received great consideration. This provides wide field for the researchers to develop a better system to handle those needs. This leads to the development of Combined Economic and Emission Dispatch (CEED) techniques. There are various technique proposed by several researchers to solve CEED problem based on optimization techniques. The efficient optimization technique among the proposed work is Genetic Algorithm (GA). But still some problems like slower convergence and higher computational complexity exists in using GA for solving CEED problem. To overcome those difficulties, this paper uses Non- Dominated Ranked Genetic Algorithm (NRGA) which uses rank based Roulette Wheel selection algorithm with Pareto-based population ranking Algorithm. The simulation result shows that the proposed technique for solving combined economic and emission dispatch problem results in better convergence rate when compared to the existing techniques.
4 LU Decomposition Method for Solving Fully Fuzzy Linear System with Trapezoidal Fuzzy Numbers, S. Radhakrishnan, R. Sattanathan and P. Gajivaradhan
System of simultaneous linear equations plays a vital role in mathematics, Operations Research, Statistics, Physics, Engineering and Social Sciences etc. In many applications at least some of the system's parameters and measurements are represented by fuzzy numbers rather than crisp numbers. Therefore it is imperative to develop mathematical models and numerical procedures to solve such a fuzzy linear system. The general model of a fuzzy linear system whose coefficient matrix is crisp and the right hand side column is an arbitrary fuzzy vector. In the fully fuzzy linear system all the parameters are considered to be fuzzy numbers. Since triangular fuzzy numbers is a special case of trapezoidal fuzzy numbers, hence in this paper we considered fully fuzzy linear system with trapezoidal fuzzy numbers. LU decomposition method for a crisp matrix is well known in solving linear system of equations. We discuss LU decomposition of the coefficient matrix of the fully fuzzy linear system, in which the coefficients are trapezoidal fuzzy numbers.
5 Vector Quantization and MFCC based Classification of Dysfluencies in Stuttered Speech, P. Mahesha and D.S. Vinod
Stuttering also known as stammering is a speech disorder that involves disruptions or dysfluencies in speech. The observable signs of dysfluencies include repetitions of syllable or word, prolongations, interjections, silent pauses, broken words, incomplete phrases and revisions. The repetitions, prolongations and interjections are important parameter in assessing the stuttered speech. The objective of the paper is to classify the above mentioned three types of dysfluencies using Mel-Frequency Cepstral Coefficients (MFCC) and Vector Quantization (VQ) framework. For each dysfluency MFCC features are extracted and quantized to a number of centroids using the K-means algorithm. These centroids represent the codebook of dysfluencies. The dysfluencies are classified according to the minimum quantization distance between the centroids of each dysfluency and the MFCC features of testing sample.
6 Converting Objects in Physical World into Digital World Using Color Recognition, V. Prasanna and S. Gopinath
Gestures do speak well than commands. We usually interact computers with GUI based HID devices. It would be more realistic if the Holy Grail gesture based natural interface enables illiterates even to augment machine usability. This evolution shouldn't be an overhead to the consumerism. Also economical constraint should not force this to be inefficient due to productivity cost. In this paper, we proposed a new genre of interacting with computational devices and our goal is to make the user interface more intuitive. Rather using the mouse and touch pads to achieve the tasks like moving, left & right clicks of the mouse pointer, with our new algorithm you can achieve that with your own color marker tapped finger. In this beginning version of this algorithm we used color markers to reduce false detection of the user finger. With our algorithm it produces a high degree of accuracy in color recognition and make your own finger tapped with the recognized color marker to function as like a computer mouse. Hence such an idea of making the existing wheel to be fit into the new body seems good. Thus by integrating various efficient pragmatics into a new paradigm, syntactically this system is proposed.
7 Applying Multi Layer Feed Forward Neural Networks on Large Scale Data, G. Jananii
Investigation on large data sets is extremely important in data mining.Large amount of data generally requires a specific learning method or of any optimization method. Particularly some standard methods are used for example Artificial Neural Network, back propagation neural network and other neural networksnecessitate very long learning time.The existing technique that does not performed well on the large data sets. So in this paper presents a new approach called multi layered feed forward neural network which can work efficiently with the neural networks on large data sets.Data is separated into several segments, and learned by anidentical network structure whereas all weights from the set of networks are integrated. The results from the experiments show that the proposed method can protect the accuracy while the training time is significantly reduced.
8 Logic for Mode Transition of Autopilots in Lateral Direction for Commercial Aircrafts, Aparna S Nair, Yogananda Jeppu and C.G. Nayak
Complexity in autopilot logic design and confusion involved in its mode transition is one of the major reasons for the accidents in highly automated airliner. In this paper we present the usage of a recently proposed array logic based technique for designing the autopilot mode transition logic for a commercial aircraft in the lateral direction. This designing technique helps to reduce the design effort in the development of an autopilot. Ease to understand and very concise way to specify a large number of transitions in simple tabular column is one the highlight of this method. This paper provides some observations about lateral modes and logic concerning lateral mode transition in a less complex way compared to the prevailing methods for autopilot design. Here various mode possibilities of lateral mode transition in an autopilot is mentioned along with specification criteria's that bound these transition and these possible transitions were given a frame work using MATLAB software.
9 A Multi-objective Optimization Approach for Design of Worm and Worm Wheel Based on Genetic Algorithm, Y.K. Mogal and V.D. Wakchaure
Number of conventional methods are available for solving different types of optimization problems. But due to their complexity and convergence problems these methods are not able to give optimal solution. A gear transmission problem is one of the most complex optimization problems because of relationship between different variables. A Gear design require the designer to compromise many design variables; i.e. continuous, discrete & integer variables in order to determine best performance of gear set. Therefore researchers are now going to use Evolutionary Techniques. Genetic Algorithm (GA) is one of such technique. In this paper the attempt has been made to optimize worm and worm wheel with multiple objectives, which takes gear ratio (i), face width of worm & worm wheel (b) and pitch circle diameters of worm (dw) & worm wheel (dg) as design variables. The main objective function is to minimize volume of worm and worm wheel and remaining objectives are taken as constraints such as centre distance, deflection of worm and beam strength of worm gear.
10 ANN Model to Predict Coronary Heart Disease Based on Risk Factors, H.S. Niranjana Murthy and Dr.M. Meenakshi
This paper presents a neural network based on Levenberg-Marquardt back-propagation algorithm for prediction of degree of angiographic coronary heart disease. The novelty of this work is training a one hidden layer neural network with Levenberg-Marquardt back-propagation algorithm for multivariate large dataset. An ANN model is developed for prediction of degree of angiographic coronary heart disease, and subsequently, its performance is evaluated using heart disease database obtained from Cleveland Clinic Foundation Database with all attributes are numeric-valued. About 88 cases of different aged angiographic coronary heart disease subjects with 13 attributes have been tested in this model. This study exhibits ANN based prognosis of coronary heart disease and improves the diagnosis accuracy to 95.5 % which is comparably higher with earlier works.