Artificial neural networks bidirectional associative memory
This paper focuses on the bidirectional associative memory its features and the future aspects and the current context of application. BAM is a type of neural network. Artificial neural network (Ann’s) resembled the human nervous system, with algorithms consisting of weighted interconnecting processing units (like neural map of the human brain). To address a particular problem using Ann’s, the interrelated connections are tuned and the value of weights between units is needed. Neural network is a new unexplored topic of interest for the computer scientists. Bam comes under recurrent types of network called Hopfield network. BAM is a resonance model, in the sense that information is passed back and forth between two layers of units until a stable sate is reached. The Hopfield network is said to be auto associative, because it uses a partial and noisy pattern to recall the best match of itself. BAM includes: ASSOCIATIVE NEURAL MEMORIES: Associative neural memories are a class of artificial neural networks (connectionist nets) which have gained substantial attention relative to other neural net paradigms. Associative memories have been the subject of research. NOISE TOLERANCY: This paper analyzes the sensitivity to noise in BAM (Bidirectional Associative Memory), and then proves the noise immunity of BAM relates not only to the minimum absolute value of net inputs (MAV) but also to the variance of weights associated with synapse connections.
Please Login using your Registered Email ID and Password to download this PDF.
This article is not included in your organization's subscription.The requested content cannot be downloaded.Please contact Journal office.Click the Close button to further process.
[PDF]
Suppression of conducted EMI in AC-DC converters using chaotic PWM
Electro Magnetic Interference (EMl) emission is always of grave concern for power electronic circuit designers. Due to rapid switching of high current and high voltage, interference emission is a serious problem in switching power circuits. Many products fail to make it to the market because of their failure to comply with the government EMI regulations. Numerous companies have cited EMI problems as the culprit in the delay of their product introduction; a new chaotic pulse width modulation (PWM) scheme is proposed and implemented to reduce the conducted electromagnetic interference (EMI) in power converters. Based on the analysis of constant frequency, Experiments have been made on a power converter. The experiment results show that the EMI spectrum is decided completely by the PWM spectrum, and the chaotic frequency-spreading has an obvious impact on EMI suppressing, compared with the other schemes. To chaoize a frequency-modulated signal which then modulates the carrier frequency. The proposed scheme not only suppresses the peaky EMI, but also avoids the occurrence of low-order noises and mechanical resonance.
Please Login using your Registered Email ID and Password to download this PDF.
This article is not included in your organization's subscription.The requested content cannot be downloaded.Please contact Journal office.Click the Close button to further process.
[PDF]
Design and analysis of optimal power flow for power system using lagrangian relaxation technique
This paper mainly deals with the solution of Optimal Power Flow (OPF) problem which can be formulated as a Quadratic Programming (QP) model and then decomposed by Lagrangian Relaxation (LR) method.The objective of this model is to minimize the total cost of real power generation. Many researchers have discussed the solution for OPF by using different methodologies like Newton Raphson (NR) method, Particle Swarm Optimization (PSO) method, Genetic Algorithm (GA), Artificial Intelligence (AI) method, Interior Point (IP) method, Differential Evolution (DE) algorithm. In this paper the proposed methodology is compared with the other methods like Particle Swarm Optimization method, Genetic Algorithm and Differential Evolution algorithm. These methods have been tested through the results of IEEE 30 bus system. The optimum generation cost is minimized for OPF using Lagrangian Relaxation method.
Please Login using your Registered Email ID and Password to download this PDF.
This article is not included in your organization's subscription.The requested content cannot be downloaded.Please contact Journal office.Click the Close button to further process.
[PDF]
Grid connected inverter with SVPWM technique for photovoltaic application
The global electrical energy consumption is rising and there is a steady increase of the demand on the power capacity, efficient production, distribution and utilization of energy. Power electronics, the technology of efficiently processing electric power, play an essential part in the integration of the dispersed generating stations for higher efficiency and better performance of the power systems. This project deals with the simulation of grid connected inverter for Photovoltaic applications. Space vector pulse width modulation (SVPWM) technique has been adopted for generating pulses for the two level inverter. The entire system comprising of Photovoltaic array (PVA) and two level inverter has been developed in Mat lab-Simulink. The PVA model characteristics including the effects of temperature and solar irradiation change on maximum power point are also presented in this paper. The inverter output has been synchronized with the grid using d-q theory and the power flow is controlled at 200kw. Finally, the inverter has been tested in grid connected mode.
Please Login using your Registered Email ID and Password to download this PDF.
This article is not included in your organization's subscription.The requested content cannot be downloaded.Please contact Journal office.Click the Close button to further process.
[PDF]
Comparative analysis of various feature selection algorithms based on fuzzy-rough set approach
Rough Set Theory provides a formal framework for data mining. Feature Selection or Attribute Reduction is a preprocessing step in data mining, and it is very effective in reducing dimensionality, reducing irrelevant data, increasing learning accuracy and improving comprehensibility. The fuzzy-rough feature selection algorithm was used to handle the continuous real-valued data as well as to handle noisy data. It was implemented by standard fuzzification techniques enabling linguistic labels to be associated with attribute values. It also provides uncertainty modeling by allowing the possibility of the membership value to more than one fuzzy label. In this paper, we use an Improved Quickreduct algorithm by redefining the lower and upper approximations based on fuzzy set theory. The membership degrees of feature values to fuzzy sets are exploited in the process of dimensionality reduction. The experiments are carried out on public domain datasets available in UCI machine learning repository and real Tuberculosis data set.
Please Login using your Registered Email ID and Password to download this PDF.
This article is not included in your organization's subscription.The requested content cannot be downloaded.Please contact Journal office.Click the Close button to further process.
[PDF]
Soft computing in intelligent multi – modal systems
As man has started using computers to track the work of machines, the flexibility with which the humans communicate and request information from the computers must increase. There arises a need for the computers to understand and process the ambiguous queries put forth by authorized persons. This has been accomplished in this paper by introducing soft computing in multi – modal systems. This architecture first uses vascular pattern recognition to identify whether the user is an authorized person or not by using the image of his blood vessels obtained by using near – infrared light. Then the architecture consists of six main components - a reasoner, a speech system, a vision system, a non intrusive neural network based gaze tracking system, an integration platform and an application interface, using which we can process speech, text, face images, gaze information and simulated gestures. Fuzzy and probabilistic techniques have been used in the reasoner to establish temporal relationships and learn interaction sequences. This architecture can be used in Process control and Instrumentation where the authorized users can query the values of some physical parameters (pressure, temperature etc). The ambiguities of these queries are resolved using gaze tracking. Example: Query (recognized by speech): show me this of that machine. (That machine is pointed using mouse) Ambiguity: this (physical parameter) - identified by where the user’s gaze is fixed on the screen. Final query: show parameterA of machineB.
Please Login using your Registered Email ID and Password to download this PDF.
This article is not included in your organization's subscription.The requested content cannot be downloaded.Please contact Journal office.Click the Close button to further process.
[PDF]
Comparison of several cloud computing providers
An important transition in IT service delivery today is buzzword Cloud Computing. The tools, building blocks and best practices are evolving for cloud computing which in turn increases challenges to deploy the best suited cloud solutions. Initially the big players like Google, Microsoft, Amazon set the stage for how to deploy web applications & pay for their use on the web. Thus with number of platforms and services available to for a cloud it is hard to make a reasonable choice for at least a novice who has just entered into cloud. The paper is intended to provide an insight into few cloud providers’ services with respect to their features and scenarios. This comparison may help in the selection of a platform and may leverage as a starting point for a researcher.
Please Login using your Registered Email ID and Password to download this PDF.
This article is not included in your organization's subscription.The requested content cannot be downloaded.Please contact Journal office.Click the Close button to further process.
[PDF]
Qos based energy efficient routing in adhoc networks using genetic algorithm
Multicast routing optimization problem is addressed by considering parameters like cost, battery power, delay and bandwidth. The objectives proposed in this work are minimizing the cost and maximizing the battery power subject to the constraints delay and bandwidth. To find the optimal route with the above objectives, binary coded genetic algorithm (GA) technique has been chosen. In this work, an avoidance strategy is included to avoid the illegal chromosome creation during genetic operation. The simulations are done with the test system which consists of standard graphs with different size. Performances of the given networks are compared with existing approach in terms of fitness values, probabilities of genetic operators, network life and generation of convergence.
Please Login using your Registered Email ID and Password to download this PDF.
This article is not included in your organization's subscription.The requested content cannot be downloaded.Please contact Journal office.Click the Close button to further process.
[PDF]
A concept graph for rough set theory
Conceptual graphs (CGs) are a system of logic based on the existential graphs of Charles Sanders Peirce and the semantic networks of artificial intelligence. They express meaning in a form that is logically precise, humanly readable, and computationally tractable. With a direct mapping to language, conceptual graphs serve as an intermediate language for translating computer-oriented formalisms to and from natural languages. With their graphic representation, they serve as a readable, but formal design and specification language. CGs have been implemented in a variety of projects for information retrieval, database design, expert systems, and natural language processing. The rough set philosophy is founded on the assumption that with every object of the universe of discourse we associate some information (data, knowledge). For example if objects are patients suffering from a certain disease symptoms of the disease form information about patients- Objects characterized by the same information are indiscernible similar in view of the available information about them. The indiscernibility relation generated in this way is the mathematical basis of rough set theory.
Please Login using your Registered Email ID and Password to download this PDF.
This article is not included in your organization's subscription.The requested content cannot be downloaded.Please contact Journal office.Click the Close button to further process.
[PDF]
Fuzzy logic, PI and ANN in improvement of power quality using unified Power quality conditioner
The unified power quality conditioner (UPQC) is being used as a universal active power conditioning device to mitigate both current and voltage harmonics at a distribution side of power system network. This paper emphasis enhancement of power quality by using UPQC with fuzzy logic controller(FLC)and proportional- integral(PI)controller. The main purpose of the proposed (FLC)is capable of providing good static and dynamic performances compared to PID controller.
Please Login using your Registered Email ID and Password to download this PDF.
This article is not included in your organization's subscription.The requested content cannot be downloaded.Please contact Journal office.Click the Close button to further process.
[PDF]