In this paper, a new hybrid population based algorithm (DE-FPA) is proposed with the combination of differential evolution optimization and flower pollination algorithm. The main idea to integrate natural characteristics in behavior flowering plant synthesize strength power both algorithms. robust sense that globalization takes place evolution. Some benchmark test functions are utilized here compare individual DE FPA algorithms searching best solution. results show possesses better...

abstract A tripartite array of vertical seismographs was operated for 5.5 months in late 1979 the Shillong Massif area northeast India. During this time, 719 local earthquakes were recorded. Of these, 359 located (2.4 ≦ M D 5.1), using some events additional arrival times from WWSSN/IMD station and portable stations by NGRI/RRL. The Mikir Hills (60 km radius within our array) showed a high seismicity rate about four per week with ≧ 3 1 4 . This activity contrasted strongly Assam Gap where...

Error minimization using conventional back-propagation algorithm for training feed forward neural network (FNN) suffers from problems like slow convergence and local minima trap. Here in this paper gradient free optimization is used error to avoid minima. Hence we introduce a new hybrid integrating the concepts of physics inspired gravitational search biology flower pollination algorithm. Gravitational novel meta-heuristic method based on Newtonian law gravity mass interaction, whereas an...

Multilevel Inverter has been becoming extremely popular in modern power system. Rapid expansion of renewable energy sectors, transformer less grid synchronization and demand for harmonic free quality are such igniting factors its popularity. As electronic devices prone to various faults, hence ensure the stability reliability system operation, this paper presents an intelligent fault detection method open switch failure a five level cascaded inverter. Wavelet decomposition is used extract...

This paper presents a novel scheme for fast fault detection and isolation (FDI) of position sensors based on signal processing fault-tolerant control (FTC) speed tracking an electric vehicle (EV) propelled by permanent magnet synchronous motor (PMSM). The is detected using comparison algorithm between the measured delayed rotor signals. proposed more practical diagnosing faults over wide range since it does not use estimated value. In addition, to ensure continuous propulsion retain...

Drift in sensors, mainly chemical or gas sensors is an unavoidable problem that introduces shift feature values the dataset. This makes sample classification and identification process more challenging over time olfactory machines. The generation of uncertain sensor drift long term degradation properties no matter what they are made of, how expensive are, accurate. To deal with this a multiple classifier approach using artificial neural network (ANN) k nearest neighbour (KNN) proposed here...

The advancement of information technology has made public health management system more efficient on keeping an eye major outbreaks like dengue fever than before. Vigorous prediction not only helps the to act faster but also medical professionals treat and suggest a good solution patients. In this context, paper aims develop intelligent computing models using multilayer perceptron support vector machine for classifying positive negative cases dengue. Decision taking is vital in field, final...

Health information technology is spreading all over the world to provide right medical advice for healthcare. In this context, paper describes application of data mining techniques identify jaundice by analyzing liver function test reports. Artificial neural network and support vector machine classifiers are employed here classification on basis condition. Since correct a sensitive decision making process, seeking multiple expert opinions may be good choice. Henceforth, classifier fusion...

Edge detection techniques are widely used in image processing for object based on segmentation of images local changes intensity. Here a novel method is presented that detects edges an with more accuracy and precision. The proposed technique locates the edge by comparing pixels entire using 3×3 binary matrix. A comparative study different like Sobel, Canny, Prewitt, Roberts presented. new gives better results terms smoothness, sharpness execution time much faster than conventional techniques.

A large variety of fruit juices are available in the Indian market. These differ from one another terms quality and added ingredients. Fruit two different commercial brands compared with their consequent homemade ones using a portable near infrared (NIR) spectrometer range 250-925 nm wavelength. Juices extracted apple, grapes, mango, orange, pineapple pomegranate used as samples for our experiment. The results clustered linear discriminant analysis (LDA) visualization class distinction....

Multilevel inverter topology are becoming extremely important now-a-days due to the rapid growth in renewable energy sector. Any kind of fault directly hampers normal operation smart grid. In this context, paper presents an intelligent technique for switch detection diode clamped inverters mid power application. It is necessary detect and locate location remove it quickly as reliability electronics components stable system electric drives. probabilistic neural network with discrete wavelet...

In this paper, a variant of particle swarm optimization (PSO), called craziness based (CRPSO) is used for the design 8th order infinite impulse response (IIR) digital filter. The proposed technique global heuristic search algorithm and better exploration exploitation multidimensional space can be achieved with closely mimicked behaviour in fundamental PSO equation. Performance compared some well accepted evolutionary algorithms such as real coded genetic (RGA). From simulation study it...

Training of feed-forward neural network using stochastic optimization techniques recently gained a lot importance invarious pattern recognition and data mining applications because its capability escaping local minima trap. However such may suffer from slow poor convergence. This fact inspires us to work on meta-heuristic technique for training the network. In this respect, train network, we focus implementing gravitational search algorithm(GSA) which is based Newton's law motion principle...

A virtual Instrument is designed, prototyped and developed for the real time measurement recording of galvanic skin response (GSR), also known as electrodermal to recognize human psycho physiological state under stressed condition. The instrument analyzes signals by statistical features. Galvanic Skin Response (GSR) a measure conductivity which extensively linked emotional condition during stress activation. An reaction often causes increased sweat gland activity in palms hands soles feet,...

A comparative study on performance in terms of transient time response specifications for position control a separately excited DC Servomotor using Fuzzy logic PD strategy and general is done. Logic Controller (FLC) based designed both the inference mechanisms- Mamdani type Takagi-Sugeno type. Robustness test controllers-FLC controller has shown that more robust as compared to controller. All work, experiments simulation are done MATLAB software.

The paper investigates the discrimination ability of short-wave near-infrared spectroscopy for classification various edible oils used in India. Spectral characterization mustard, olive, rice bran, sunflower and soybean are recorded by a portable near infrared (NIR) spectrometer range 250-925 nm wavelength. Due to high dimensionality problem, principal component analysis (PCA) is here extracting only significant features from spectra. Hidden clusters dataset identified applying (PCA). For...

The multiple-beam klystrons (MBKs) are well known for some distinct performance advantages over their single-beam versions. of the MBKs include higher average power, relatively lower operating voltages, bandwidth, and low individual beam current. However, design is more extensive requires thorough careful three-dimensional electromagnetic simulations analysis. In this article, a four-beam klystron compatible with predesigned electron gun reported. Starting simple analytical approach,...

Abstract An essential metric for the quality of a particle-identification experiment is its statistical power to discriminate between signal and background. Pulse shape discrimination (PSD) basic method this purpose in many nuclear, high-energy rare-event search experiments where scintillation detectors are used. Conventional techniques exploit difference decay-times pulses from background events or pulse signals caused by different types radiation quanta achieve good discrimination....