http://localhost:8080/xmlui/handle/123456789/7606 2026-04-12T21:31:47Z http://localhost:8080/xmlui/handle/123456789/8237 Novel Class Detection with Concept Drift in Data Stream - AhtNODE Gandhi, Jay; Gandhi, Vaibhav Data stream mining has become an interesting analysis topic and it is a growing interest in data discovery method. There are several applications supporting stream data processing like device network, electronic network, etc. Our approach AhtNODE (Adaptive Hoeffding Tree based NOvel class DEtection) detects novel class in the presence of concept drift in streaming data. It addresses there are three challenges of streaming data: infinite length, concept drift, and concept evolution. This approach automatically detects the novel class whenever it arrives in the data stream. It is a multi-class approach that distinguishes novel class from existing classes. The authors tend to apply the Adaptive Hoeffding Tree as a classification model that is also used to handle the concept drift situation. Previous approaches used the ensemble model to handle concept drift. In AHT, classification is done in the single pass. The experiment result proves the effectiveness of AhtNODE compared to existing ensemble classifier in terms of classification accuracy, speed and use of memory. 2020-01-01T00:00:00Z http://localhost:8080/xmlui/handle/123456789/8222 Machine learning based stochastic dynamic analysis of functionally graded shells Vaishali; Mukhopadhyay, T; Karsh, P. K.; Basu, B.; Dey, S This paper presents stochastic dynamic characterization of functionally graded shells based on an efficient Support Vector Machine assisted finite element (FE) approach. Different shell geometries such as cylindrical, spherical, elliptical paraboloid and hyperbolic paraboloid are investigated for the stochastic dynamic analysis. Monte Carlo Simulation is carried out in conjunction with the machine learning based FE computational framework for obtaining the complete probabilistic description of the natural frequencies. Here the coupled machine learning based FE model is found to reduce the computational time and cost significantly without compromising the accuracy of results. In the stochastic approach, both individual and compound effect of depth-wise source-uncertainty in material properties of FGM shells are considered taking into account the influences of different critical parameters such as the power-law exponent, temperature, thickness and variation of shell geometries. A moment-independent sensitivity analysis is carried out to enumerate the relative significance of different random input parameters considering depth-wise variation and collectively. The presented numerical results clearly indicate that it is imperative to take into account the relative stochastic deviations (including their probabilistic characterization) of the global dynamic characteristics for different shell geometries to ensure adequate safety and serviceability of the system while having an economical structural design. 2020-01-01T00:00:00Z http://localhost:8080/xmlui/handle/123456789/8219 Radial Basis Function-Based Stochastic Natural Frequencies Analysis of Functionally Graded Plates Karsh, P. K.; Kumar, R. R.; Dey, S. This paper deals with portraying the stochastic natural frequencies of cantilever plates made up of functionally graded materials (FGMs) by employing the radial basis function (RBF)-based finite element (FE) approach. The material modeling of FGM plates is carried out by employing three different distribution laws, namely power law, sigmoid law, and exponential law. A generalized algorithm is developed for uncertainty quantification of natural frequencies of the FGM structures due to stochastic variation in the material properties and temperature. The deterministic FE code is validated with the previous literature, whereas convergence study is carried out in between stochastic results obtained from full scale direct Monte Carlo Simulation (MCS) and MCS results obtained from RBF surrogate model of different sample sizes. The percentage of error present in the RBF model is also determined. The influence of crucial parameters such as distribution law, degree of stochasticity, power law index and temperature are determined for natural frequencies analysis of FGMs plates. The results illustrate the input parameters considered in the present study have significant effects on the first three stochastic natural frequencies of cantilever FGM plates. 2020-01-01T00:00:00Z http://localhost:8080/xmlui/handle/123456789/8208 Comparison of COD removal from petrochemical wastewater by electro-Fenton and electro oxidation processes: optimization and kinetic analyses Sandhwar, Vishal Kumar; Saxena, Diksha; Verma, Shilpi; Garg, Krishan Kishor; Prasad, Basheshwar This study reveals comparison between electro-Fenton (EF) and electro-oxidation (EO) methods to study chemical oxidation demand (COD) removal from synthetic petrochemical wastewater. Initially 54.60% of COD removal was found by acid precipitation treatment at optimum conditions. Subsequently, electrochemical treatments such as EF and EO using graphite electrodes were imposed to the supernatant and process parameters such as time (20→80 min), current density (60.97→121.95 A/m2), pH (2→6), Fe2+concentration (1→2 mmole/L), electrolyte concentration (1→3gL), and electrode gap (1→5 cm) were optimized by Box Behnken Design. Maximum removal of COD was obtained 66.23% and 56.57% with electric energy-consumption (kWh/kg CODremoved): 33.30 and 35.27 during EF and EO treatments respectively at optimum conditions. 2020-01-01T00:00:00Z