Showing papers by "Velagapudi Ramakrishna Siddhartha Engineering College published in 2015"

Improved Bat algorithm for the detection of myocardial infarction

Abstract: The medical practitioners study the electrical activity of the human heart in order to detect heart diseases from the electrocardiogram (ECG) of the heart patients. A myocardial infarction (MI) or heart attack is a heart disease, that occurs when there is a block (blood clot) in the pathway of one or more coronary blood vessels (arteries) that supply blood to the heart muscle. The abnormalities in the heart can be identified by the changes in the ECG signal. The first step in the detection of MI is Preprocessing of ECGs which removes noise by using filters. Feature extraction is the next key process in detecting the changes in the ECG signals. This paper presents a method for extracting key features from each cardiac beat using Improved Bat algorithm. Using this algorithm best features are extracted, then these best (reduced) features are applied to the input of the neural network classifier. It has been observed that the performance of the classifier is improved with the help of the optimized features.

Influence of Al3 + ions on luminescence efficiency of Eu3 + ions in barium boro-phosphate glasses

Abstract: The emission and life time decay characteristics of Eu 3 + ions in barium boro-phosphate glasses mixed with different concentrations of Al 2 O 3 are studied. The emission spectra exhibited bands due to 5 D 0 → 7 F 0 , 7 F 1 , 7 F 2 , 7 F 3 , 7 F 4 transitions of Eu 3 + ions. The highest intensity of these transitions is observed when the glasses are mixed with 3.0 mol% of Al 2 O 3 . Using the emission spectra, the Judd–Ofelt (J–O) parameters and the radiative parameters viz., emission probability, A, the radiative lifetime, τ, and the fluorescent branching ratio, β of different transitions originated from 5 D 0 level of Eu 3 + ions are evaluated. The results have been analyzed as a function of Al 2 O 3 concentration with the aid of IR spectral data. The IR spectral data have indicated that Al 3 + ions participate in larger proportions in octahedral positions in the glasses mixed with 3.0 mol% of Al 2 O 3 , which induce bonding defects, de-cluster the Eu 3 + ions and facilitate for minimizing the emission losses due to quenching. The quantitative analysis of these results further indicated that 3.0 mol% of Al 2 O 3 is optimal for achieving the highest luminescence efficiency in these glasses.

Mechanical and degradation properties of successive alkali treated completely biodegradable sisal fiber reinforced poly lactic acid composites

Abstract: The natural fiber reinforced biodegradable polymer composites were prepared with short sisal fiber as reinforcement in poly lactic acid (PLA) matrix. The sisal fiber is treated with 10% NaOH follow...

Hybrid Bacterial Foraging and Particle Swarm Optimization for detecting Bundle Branch Block.

Abstract: Abnormal cardiac beat identification is a key process in the detection of heart diseases. Our present study describes a procedure for the detection of left and right bundle branch block (LBBB and RBBB) Electrocardiogram (ECG) patterns. The electrical impulses that control the cardiac beat face difficulty in moving inside the heart. This problem is termed as bundle branch block (BBB). BBB makes it harder for the heart to pump blood effectively through the heart circulatory system. ECG feature extraction is a key process in detecting heart ailments. Our present study comes up with a hybrid method combining two heuristic optimization methods: Bacterial Forging Optimization (BFO) and Particle Swarm Optimization (PSO) for the feature selection of ECG signals. One of the major controlling forces of BFO algorithm is the chemotactic movement of a bacterium that models a test solution. The chemotaxis process of the BFO depends on random search directions which may lead to a delay in achieving the global optimum solution. The hybrid technique: Bacterial Forging–Particle Swarm Optimization (BFPSO) incorporates the concepts from BFO and PSO and it creates individuals in a new generation. This BFPSO method performs local search through the chemotactic movement of BFO and the global search over the entire search domain is accomplished by a PSO operator. The BFPSO feature values are given as the input for the Levenberg–Marquardt Neural Network classifier.

Smart Wireless Sensor Network for Automated Greenhouse

Abstract: A greenhouse is an enclosed structure that provides micro-climate for the plant growth. This paper presents the design of a wireless sensor network that provides real-time monitoring of temperature, humidity and soil moisture of a greenhouse. An automated control system for managing these micro-climate parameters is developed to optimize the parameters and use of water. The sensor node developed handles the data from the sensors and triggers actuators based on the threshold algorithm programmed into the microcontroller. The gateway receives the sensor data and control information through Zigbee and transmits the data to the web application for remote monitoring. The monitor software provides network view with nodes and their information. Information management system is also designed to monitor the data at any required time.

Spectroscopic characterization of manganese-doped alkaline earth lead zinc phosphate glasses

Abstract: Alkaline earth lead zinc phosphate glasses doped with Mn(II) are characterized by spectroscopic techniques like X-ray diffraction (XRD), UV–visible, differential scanning calorimetry (DSC), electron paramagnetic resonance (EPR), Fourier transform infrared (FTIR) and Raman. Optical absorption spectrum exhibits four bands which are characteristic of Mn(II) in distorted octahedral site symmetry. The crystal field parameter Dq and Racah interelectronic-repulsion parameters B and C have been evaluated. All investigated samples exhibit EPR signals which are characteristic to the Mn2+ ions. The shapes of spectra are also changed with varying alkaline earth ions content. FTIR spectra show specific vibrations of phosphate units. The characteristic Raman bands of these glasses due to stretching and bending vibrations were identified and analysed by varying alkaline earth content. The intensity and frequency variations for the characteristic phosphate group vibrations have been correlated with the changes of the structural units present in these glasses. Depolymerization of the phosphate chains in all the glasses is observed with replacement of alkaline earth content by spectroscopic studies. This leads to a strong decrease of the average chain length and a small decrease of the average P–O–P bridging angle with replacement of alkaline earth content.

Spectroscopic studies of chromium doped alkali earth lead zinc phosphate glasses

Abstract: X-Ray diffraction, energy dispersive X-ray, Fourier transform infrared, Raman spectroscopy, differential scanning calorimetry, UV–Visible spectroscopy and electron paramagnetic resonance spectroscopic studies have been carried out on alkali earth lead zinc phosphate glasses doped with 0.1 % chromium ions. The energy dispersive X-ray spectra reveal fundamental compositional information of the glasses. Infrared spectra indicate that phosphate network is depolymerized with progressive substitution of alkali earth content and inform the characteristic vibrations of PO4 3− units. Raman spectra suggest that these glasses are consisting of metaphosphate [Q2] units along with some bands related to pyrophosphate [Q1] and orthophosphate [Q0] units. The crystal-field parameter and inter-electronic repulsion parameters have been evaluated from optical absorption spectral data. Electron spin resonance spectra of Cr3+ systems indicate that g ∥ > g ⊥ and Cr3+ ions are located at sites with lower symmetry. It is obtained that the glass transition temperatures fall in region of 377–360 °C. Increase in density of the glass system brings changes in structure of the glasses on replacement of alkali earth content.

Detection of Atrial Fibrillation using Autoregressive modeling

Abstract: A ‎ atrial fibrillation (AF) is the arrhythmia that commonly causes death in the adults. We measured AR coefficients using Burg’s method for each 15 second segment of ECG. These features are classified using the different statistical classifiers: kernel SVM and KNN classifier. The performance of the algorithm was evaluated on signals from MIT Physionet database.. The effect of AR model order and data length was tested on the classification results. This method shows better results can be used for practical use in the clinics. ‏

Improved emotion recognition using GMM-UBMs

Abstract: In recent past a lot of scientific attention is paid on recognizing the emotional state of the speaker from his speech. Emotion recognition is a challenging task as human emotions are complex, subtle and emotive state in human speech does not persist long. So it is important to study the presence of emotion identifiable information in smaller segments of speech. This study is aimed at studying the presence of emotional specific information with relevance to the position of the word in the utterance. During the present study, spectral features are employed to represent emotion specific information in speech. Spectral features from smaller speech segments of speech based on their position in the utterance are employed to study the presence of emotion in speech. Due to the lack of adequate data in small speech segments to support conventional GMM during the course of present study Gaussian mixture modeling with a universal background model (GMM-UBM) is used for developing a emotion recognition system. Speech data from IITKGP-SESC is used during the course of the present study. During the present study 4 (Anger, Fear, Happy and Neutral) emotions are considered.

Change detection analysis of tornado disaster using conditional copulas and Data Fusion for cost-effective disaster management

Abstract: The up-to-date results are presented from an ongoing study of the Data Fusion of multi-temporal and multi-sensor satellite datasets for near real time damage and debris assessment after a tornado disaster event. The space-borne sensor datasets comprising of: (i) C-band SAR dataset from RADARSAT-2; (ii) Multi-Spectral (MS) optical dataset including NIR from RapidEye; (iii) MS and panchromatic dataset of Advanced Linear Imaging (ALI), are studied for multi-sensor data fusion. A combined approach of multi-polarized radiometric and textural feature extraction, and statistical learning based feature classification is devised for fine tuning of the complex and generalized change detection model. We also investigated the use of multi-variate conditional copula as a classifier technique, by formulating the change and no-change as a binary-class classification problem in this study. The classification results from the above technique are used for assessment of damage and debris cover after the tornado disaster event. The performance of the above approach yields a very significant Kappa accuracy up to 75%. A 10-fold cross validation strategy is used for quantitative analysis of the performance of the classification model. This study will be further extended for modelling the effect of incidence angle discrepancies or climatic condition variances, which will address the heterogeneity factor in terms of local statistics of the dataset.

SLGAS: Supervised Learning Using Gain Ratio as Attribute Selection Measure to Nowcast Snow/No-Snow

Abstract: Considering the weather nowcasting, which has no prospect of intervention, they cause the vital results in human life and animal life, accurate analysis and estimation of these variables is very important and crucial. There is an increased interest in nowcasting the bad weather conditions, among which presence of snow/no-snow is crucial, in order to fully capture the global atmospheric water cycle. This paper introduces an efficient decision tree algorithm named Supervised Learning using Gain Ratio as Attribute Selection measure (SLGAS), expanded to our previous algorithm Supervised Learning Using Entropy as Attribute Selection Measure (SLEAS), for the prediction of snow/no-snow using 31 international locations historical datasets, collected from various meteorological departments. The algorithm has been validated extensively with five performance measures namely accuracy, specificity, precision, dice and error rate respectively. Further, we compared our proposed method with the SLIQ and SLEAS decision tree algorithms in terms of the overall classification performance measures and it is clearly showing that the SLGAS algorithm is outperforming with an average accuracy of 85.92%, error rate of 14.07%.

Optimal tuning of PID controller using Particle Swarm Optimization

Abstract: This paper proposes an optimization method for determining the optimal tuning parameters of PID controller, for level control of three tank system. The main objective is to obtain a fast and stable system by tuning the PID controller using Particle Swarm Optimization algorithm. The simulation is done using MATLAB software. The response of PSO based PID controller is compared with Z-N tuned PID controller in terms of time domain specifications. The simulation results shows that tuning the PID controller using PSO provides fast and stable system with low overshoot.

Mixed convective heat transfer from a vertical plate embedded in a saturated non-Darcy porous medium with concentration and melting effect

Abstract: The effect of melting and solute dispersion on heat and mass transfer in non-Darcy fluid flow over a vertical surface has been studied numerically in the present article. The flow is assumed to be laminar and steady state. Using similarity transformations, the governing boundary layer equations are transformed into self-similar nonlinear ordinary differential equations, which are then solved by using boundary value problem solver. A comparison with the numerical results made for different R a/P e values in the absence of some particular parameters. The velocity and concentration inside the boundary layer are observed to be influenced by the parameters like R a/P e,L,B,M. The flow heat and mass transfer coefficients are discussed through the plots.

Electrochemical and surface analytical studies of carbon steel protected from corrosion in a low-chloride environment containing a phosphonate-based inhibitor

Abstract: Electrochemical and surface analytical techniques have been used to study carbon steel protected from corrosion by use of a new ternary inhibitor formulation containing nitrilotris(methylenephosphonic acid) (NTMP), zinc ions, and nicotinic acid (NA). Potentiodynamic polarization studies indicate that the ternary inhibitor acts as a mixed-type inhibitor. Electrochemical impedance studies imply formation of a protective film at the metal–solution interface. Surface analysis by X-ray photoelectron spectroscopy (XPS) showed that the protective surface film contains Fe, Zn, P, N, C, and O. On the basis of shifts in the binding energies of these elements, it is inferred that the protective film comprises a multiligand complex, Fe(III), Zn(II)–NTMP–NA, Zn(OH)2, and smaller quantities of oxides and/or hydroxides of iron. Analysis of the protective film by Fourier-transform infrared spectroscopy also supports this interpretation of the XPS results. Surface morphology and topography were studied by scanning electron microscopy and atomic force microscopy, respectively. On the basis of the results from all these studies, a plausible mechanism for inhibition of corrosion by the formulation is proposed.

A Novel Approach for Detection and Tracking of Vehicles Using Kalman Filter

Abstract: Detecting moving objects in videos is an important task in many computer vision applications, including human interaction, traffic monitoring and Structural Health Monitoring. When having a stationary camera, a basic method to detect the objects of interest is background subtraction. However, precise moving object detection using such a method is an extremely difficult task in a varying environment. This paper introduces a new technique for detecting, tracking as well as counting the vehicles based on Kalman filtering approach. In this method background is updated using Kalman filter to detect, track and count the vehicles. The proposed algorithm is tested with different videos and results clearly show the efficiency of the algorithm.

Detection of atrial fibrillation using continuous wavelet transform and wavelet coherence

Abstract: Atrial fibrillation AF is a type of heart ailment that occurs when atria beats quicker than normal to move blood from atria to the ventricles. Our present study proposes a technique to detect AF ECG patterns with the use of continuous wavelet transform CWT, wavelet coherence WTC is presented. The wavelet coherence function finds common frequencies between two signals and evaluates similarity of the two signals. The mother wavelet used is db4. The ECG variation of atrial fibrillation AF is observed in lead II of ECG. For the detection of normal and AF beats, WTC output values are given as the input features for the Levenberg-Marquardt neural network LMNN classifier. The data was collected from MIT/BIH AF database.

Suboptimal control of singularly perturbed multiparameter discrete control system

Abstract: Study of a generalized problem is very important in the sense it provides complete picture of the problem. Accordingly a generalized singularly perturbed multiparemter discrete control system is considered. An open-loop optimal control problem based on Pontriagin's Minimum Principle (PMP) is formulated. The resulting optimal control solution needs special numerical techniques as the system is highly stiff due to multitime scale nature of the system with n small parameters. Hence it is proposed to go for a suboptimal controller that mitigates this problem. Singular Perturbation Method (SPM) that reduces the order and removes the stiffness of the system is an ideal choice for this problem. Here a generalized SPM is presented for this multiparameter problem. The SPM consists of an outer, n initial boundary layer correction (BLC) solutions and n terminal BLC solutions for this problem. An example is provided. The numerical results substantiate the proposed suboptimal controller.

Sentiment Analysis on Twitter Streaming Data

Abstract: Twitter, an online social networking service is devised so as to treasure trove what is circumstance at any juncture in time, everywhere in the globe and it can provoke the data streams at rapid momentum In the twitter network all the messages generate a data momentum and handle eminently vigorous behaviours of the actors in the twitter network Twitter serves an enormous collection of APIs and actors can utilize them without registering In twitter data information streams are mannered and categorizing issues are concentrated and these streams are evaluated for discovering analysis of sentiment and extracting the opinion The automatic collection of corpus and linguistic analysis of the collected corpus for sentiment analysis is shown A sentiment classifier that is able to determine decisive, pesimisive and non-decisive sentiments for a document is performed using the collected corpus Using various learning algorithms like Naive Bayesian Algorithm, Max Entropy Algorithm, Baseline Algorithm and Support Vector Machine, a research on twitter data streams is performed

Homogenization of partial debond effect on the effective thermal conductivities of FRP composite using finite element analysis

Abstract: Accurate prediction of effective properties of composites prevents catastrophic failure of components designed, which depends on the non-similarities such as voids, debond, cracks and fibre orientation. Prediction of effective properties of composites with the inclusion of non-similarities in composites by micromechanics approach is prohibitively expensive; Homogenization (macro-mechanics) approach solves the problem by reducing computational capabilities. In this study, finite element models are presented for predicting effective thermal conductivities of a partially debonded unidirectional square-packed array composite. Partial debond angle effect and its location effect are studied. Also applicability of Homogenization approach is tested for three different cases and is found that maximum error between macro- and micro-mechanics approaches (homogenization) is 2.1 %. Effective longitudinal thermal conductivity of the composite is not affected by partial debond.

Comparative study of theoretical ultrasonic velocities of binary liquid mixtures containing quinoline and mesitylene at temperatures T = (303.15,308.15,313.15 and 318.15) K

Abstract: Ultrasonic velocities and densities of binary liquid mixtures containing quinoline and mesitylene have been measured at temperatures T = (303.15,308.15,313.15 and 318.15) K over the entire molefraction range of quinoline under frequency of 3 MHz. Theoretical velocities have been evaluated by using Nomoto (U NOM ), Impedance (U IMP ), Van-Dael and Vangeel (U VDV ), Junjie (U JUN ) and Rao's specific velocity (U RAO ) models. A good agreement has been found between experimental and theoretical values. U 2 EXP /U 2 IMX has also been evaluated for non-ideality in the liquid mixtures. The results are discussed in terms of intermolecular interactions between the component molecules of the binary liquid mixtures.

Vehicle detection and counting based on color space model

Abstract: Detecting moving objects in videos is an important task in many computer vision applications, including human interaction, traffic monitoring and Structural Health Monitoring. When having a stationary camera, a basic method to detect the objects of interest is background subtraction. However, precise moving object detection using such a method is an extremely difficult task in a varying environment. This paper introduces a new technique for detecting and counting the vehicles based on color space model. This model uses each pixel's color distortion and brightness distortion to detect the vehicle foreground pixels. In this work filtering methods are used to eliminate the noise. The proposed algorithm is tested with different videos and results clearly show the efficiency of the algorithm.

Effect of Lubrication in Cold Upsetting Using Experimental and Finite Element Modeling

Abstract: An effective lubricant will always enhance the formability of a material when applied at the die–billet interface in cold upsetting processes. High friction at the die–billet interface leads to adhesion of the cylindrical billets to the surfaces of the die, and barreling can occur. The present work focuses on the experimental and finite element investigation of the cold upsetting process of AA2014-T6 cylindrical billets under different friction conditions. The forces, stresses, and strains required for deformation were analyzed for different lubrication conditions using the finite-element-based software DEFORM 2D. The sliding velocity and sliding distance of the material are explained with the aid of computational results. The barreling radii determined from the computational techniques and analytical results were in close agreement. The influence of lubrication on stresses—namely, axial stress, hoop stress, and hydrostatic stress—was investigated. Finite element investigations were conducted for friction factors ranging from m = 0 to m = 1 to predict the effect of stresses on the formability of the billets.