Evapotranspiration Modeling Using Different Tree Based Ensembled Machine Learning Algorithm

Water Resources Management - The present study investigates and evaluate the scope and potential of modern computing tools and techniques such as ensembled machine learning methods in estimating...     

Scanning Acoustic Microscopy of SCS-6 Silicon Carbide Fiber

Scanning acoustic microscopy of SCS-6 silicon carbide fiber reveals large radial variations in acoustic reflectivity associated with the chemical composition and microstructure of a given fiber region. Rayleigh wave fringe patterns observed in each of five subregions are used to calculate the average Young modulus of that subregion. The Young modulus is found to increase monotonically from 40 GPa in the carbon core to a value of 413 GPa in the stoichiometric SiC region. The effective Young modulus of the fiber as a whole is estimated from the moduli of the individual regions and it is compared with mechanical measurements reported in the literature.     

Constructing candidate word lists using acoustically similar wordgroups

A method for identifying a set of candidate words that matches well with a given utterance is discussed. The method uses precomputed groups of acoustically similar words. Given a vocabulary, for each word a short list of words that are acoustically similar to it is computed. These groups are constructed using training utterances recorded by several speakers and used in an isolated utterance recognition system to construct candidate word lists during recognition. Experiments show that the correct word appears on the short list of candidate words constructed during recognition using this scheme over 98% of the time     

A neuro-fuzzy approach to automatic diagnosis and location of stator inter-turn faults in CSI-fed PM brushless DC motors

The paper presents a neuro-fuzzy-based perspective to the automation of diagnosis and location of stator-winding interturn short circuits in CSI-fed brushless dc motors. Performance of the drive under normal and short-circuit conditions are obtained through classical lumped-parameter network models. Waveforms of the electromagnetic torque and summation of phase voltages are monitored to develop two independent diagnostic algorithms. Diagnostic indices derived from the characteristic waveforms using discrete Fourier transform (DFT) lead to identifying the number of shorted turns. Fault location is achieved through a different set of indices extracted by the short-time Fourier transform (STFT). Adaptive neuro-fuzzy inference systems (ANFIS) are trained based on simulation results to automate the diagnostic process. ANFIS testing along with the good agreement between simulated and measured waveforms show the effectiveness of the proposed techniques.     

Ionic transport studies of the glassy silver vanadomolybdate system

Ionic conductivity of the Ag₂O-MoO₃-V₂0₅ system has been studied over a wide range of frequency, temperature and composition. A narrower glass forming region has been found in comparison to the corresponding Ag₂O-MoO₃-P₂O₅ and Ag₂O-B₂O₃-P₂O₅ systems. The highest conductivity at room temperature, _rt, = 3.21 × 10^–6–1 cm^–1 (d.c.) with an activation energy,E _act, of 0.466 eV, was observed for the glass former's ratio of unity. Further, it reached a maximum value of 2.2 × 10^–2¨-1 cm^–1 withE _act = 0.153 eV when the oxide-base glass was dissolved with Agl. D.c. conductivity, hopping rate and relaxation time in the present system have been found to be characterized by the same activation energy.     

An Efficient Lossless Telemetry Data Compression and Fault Analysis System Using 2SMLZ and CMOW-DLNN

Wireless Personal Communications - In this paper, the effect of perfect electric conductor (PEC) as a ground plane on antenna array is investigated. Vertical electric dipole which is of...     

Stochastic Gradient Boosting Model for Twitter Spam Detection

In today’s world of connectivity there is a huge amount of data than we could imagine. The number of network users are increasing day by day and there are large number of social networks which keeps the users connected all the time. These social networks give the complete independence to the user to post the data either political, commercial or entertainment value. Some data may be sensitive and have a greater impact on the society as a result. The trustworthiness of data is important when it comes to public social networking sites like facebook and twitter. Due to the large user base and its openness there is a huge possibility to spread spam messages in this network. Spam detection is a technique to identify and mark data as a false data value. There are lot of machine learning approaches proposed to detect spam in social networks. The efficiency of any spam detection algorithm is determined by its cost factor and accuracy. Aiming to improve the detection of spam in the social networks this study proposes using statistical based features that are modelled through the supervised boosting approach called Stochastic gradient boosting to evaluate the twitter data sets in the English language. The performance of the proposed model is evaluated using simulation results.

     

An electron microscopic investigation of oxides related to ß-alumina

High resolution electron microscopic (HREM) investigation of potassium-alumina and the related gallate and ferrite has revealed that whereas the aluminate and gallate are highly disordered, consisting of random sequence of and units, the ferrite is more ordered. The aluminate and gallate are sensitive to electron beam irradiation exhibiting beam-induced damage similar to sodium-alumina. Significantly, the ferrite is beamstable, the difference in behaviour amongst these related oxides arising from the different mechanisms by which alkali metal nonstoichiometry is accommodated. Barium hexaaluminate and hexaferrite are both highly ordered; specimens prepared by the barium borate flux method exhibit a new 3a×3a superstructure of the hexagonal magnetoplumbite cell.Contribution No. 241 from the Solid State and Structural Chemistry Unit.     

Magnetization study of Fe-doped ZnO co-doped with Cu: Synthesized by wet chemical method

Fe- and Cu-doped ZnO of nominal compositions Zn_0.95Fe_0.05O and Zn_0.94Fe_0.05Cu_0.01O were synthesized by a wet chemical route. X-ray diffraction analysis of the samples annealed at 575 K showed that they are single phase without any secondary phases. DC magnetization measurements of Cu co-doped samples (Zn_0.94Fe_0.05Cu_0.01O) as a function of field at room temperature showed ferromagnetic signature while the samples without Cu co-doping (Zn_0.95Fe_0.05O) are paramagnetic in nature. On increasing the temperature of annealing from 575 K to 1,075 K an impurity phase emerges in both the samples, which has been identified as a variant of ZnFe₂O₄. Both the samples heated at and above 1,075 K are found to be paramagnetic at room temperature. These observations, the absence of room temperature ferromagnetism in Zn_0.95Fe_0.05O and the disappearance of ferromagnetism in Zn_0.94Fe_0.05Cu_0.01O on raising the temperature of annealing clearly rules out the likelihood of room temperature ferromagnetism arising from the impurity phases like γ-Fe₂O₃ and/or ZnFe₂O₄ that might have been formed during the synthesis. Our results strongly suggest that room temperature ferromagnetism in Zn_0.94Fe_0.05Cu_0.01O can be attributed to the formation of a secondary phase of Cu-doped ZnFe₂O₄.