No-reference image quality assessment using modified extreme learning machine classifier

In this paper, we present a machine learning approach to measure the visual quality of JPEG-coded images. The features for predicting the perceived image quality are extracted by considering key human visual sensitivity (HVS) factors such as edge amplitude, edge length, background activity and background luminance. Image quality assessment involves estimating the functional relationship between HVS features and subjective test scores. The quality of the compressed images are obtained without referring to their original images ('No Reference' metric). Here, the problem of quality estimation is transformed to a classification problem and solved using extreme learning machine (ELM) algorithm. In ELM, the input weights and the bias values are randomly chosen and the output weights are analytically calculated. The generalization performance of the ELM algorithm for classification problems with imbalance in the number of samples per quality class depends critically on the input weights and the bias values. Hence, we propose two schemes, namely the k-fold selection scheme (KS-ELM) and the real-coded genetic algorithm (RCGA-ELM) to select the input weights and the bias values such that the generalization performance of the classifier is a maximum. Results indicate that the proposed schemes significantly improve the performance of ELM classifier under imbalance condition for image quality assessment. The experimental results prove that the estimated visual quality of the proposed RCGA-ELM emulates the mean opinion score very well. The experimental results are compared with the existing JPEG no-reference image quality metric and full-reference structural similarity image quality metric.

Application of artificial intelligence for the assessment of the status of power transformers

The Dissolved Gas Analysis (DGA) a non destructive test procedure, has been in vogue for a long time now, for assessing the status of power and related transformers in service. An early indication of likely internal faults that may exist in Transformers has been seen to be revealed, to a reasonable degree of accuracy by the DGA. The data acquisition and subsequent analysis needs an expert in the concerned area to accurately assess the condition of the equipment. Since the presence of the expert is not always guaranteed, it is incumbent on the part of the power utilities to requisition a well planned and reliable artificial expert system to replace, at least in part, an expert. This paper presents the application of Ordered Ant Mner (OAM) classifier for the prediction of involved fault. Secondly, the paper also attempts to estimate the remaining life of the power transformer as an extension to the elapsed life estimation method suggested in the literature.

Assessment of the residual fatigue strength in RC beams

In conventional analysis and design procedures of reinforced concrete structures, the ability of concrete to resist tension is neglected. Under cyclic loading, the tension-softening behavior of concrete influences its residual strength and subsequent crack propagation. The stability and the residual strength of a cracked reinforced concrete member under fatigue loading, depends on a number of factors such as, reinforcement ratio, specimen size, grade of concrete, and the fracture properties, and also on the tension-softening behavior of concrete. In the present work, a method is proposed to assess the residual strength of a reinforced concrete member subjected to cyclic loading. The crack extension resistance based approach is used for determining the condition for unstable crack propagation. Three different idealization of tension softening models are considered to study the effect of post-peak response of concrete. The effect of reinforcement is modeled as a closing force counteracting the effect of crack opening produced by the external moment. The effect of reinforcement percentage and specimen size on the failure of reinforced beams is studied. Finally, the residual strength of the beams are computed by including the softening behavior of concrete.

Assessment of conditional moment closure models of turbulent autoignition using DNS data

A systematic assessment of the submodels of conditional moment closure (CMC) formalism for the autoignition problem is carried out using direct numerical simulation (DNS) data. An initially non-premixed, n-heptane/air system, subjected to a three-dimensional, homogeneous, isotropic, and decaying turbulence, is considered. Two kinetic schemes, (1) a one-step and (2) a reduced four-step reaction mechanism, are considered for chemistry An alternative formulation is developed for closure of the mean chemical source term , based on the condition that the instantaneous fluctuation of excess temperature is small. With this model, it is shown that the CMC equations describe the autoignition process all the way up to near the equilibrium limit. The effect of second-order terms (namely, conditional variance of temperature excess sigma(2) and conditional correlations of species q(ij)) in modeling is examined. Comparison with DNS data shows that sigma(2) has little effect on the predicted conditional mean temperature evolution, if the average conditional scalar dissipation rate is properly modeled. Using DNS data, a correction factor is introduced in the modeling of nonlinear terms to include the effect of species fluctuations. Computations including such a correction factor show that the species conditional correlations q(ij) have little effect on model predictions with a one-step reaction, but those q(ij) involving intermediate species are found to be crucial when four-step reduced kinetics is considered. The "most reactive mixture fraction" is found to vary with time when a four-step kinetics is considered. First-order CMC results are found to be qualitatively wrong if the conditional mean scalar dissipation rate is not modeled properly. The autoignition delay time predicted by the CMC model compares excellently with DNS results and shows a trend similar to experimental data over a range of initial temperatures.

Ecological Assessment of Lentic Water Bodies of Bangalore

The restoration, conservation and management of water resources require a thorough understanding of what constitutes a healthy ecosystem. Monitoring and assessment provides the basic information on the condition of our waterbodies. The present work details the study carried out at two waterbodies, namely, the Chamarajasagar reservoir and the Madiwala Lake. The waterbodies were selected on the basis of their current use and locations. Chamarajasagar reservoir serves the purpose of supplying drinking water to Bangalore city and is located on the outskirts of the city surrounded by agricultural and forest land. On the other hand, Madiwala lake is situated in the heart of Bangalore city receiving an influx of pollutants from domestic and industrial sewage. Comparative assessment of the surface water quality of both were carried out by instituting the various physico–chemical and biological parameters. The physico-chemical analyses included temperature, transparency, pH, electrical conductivity, dissolved oxygen, alkalinity, total hardness, calcium hardness, magnesium hardness, nitrates, phosphates, sodium, potassium and COD measurements of the given waterbody. The analysis was done based on the standard methods prescribed (or recommended) by (APHA) and NEERI. The biological parameter included phytoplankton analysis. The detailed investigations of the parameters, which are well within the tolerance limits in Chamarajasagar reservoir, indicate that it is fairly unpolluted, except for the pH values, which indicate greater alkalinity. This may be attributed to the natural causes and the agricultural runoff from the catchment. On the contrary, the limnology of Madiwala lake is greatly influenced by the inflow of sewage that contributes significantly to the dissolved solids of the lake water, total hardness, alkalinity and a low DO level. Although, the two study areas differ in age, physiography, chemistry and type of inflows, they still maintain a phytoplankton distribution overwhelmingly dominated by Cyanophyceae members,specifically Microcystis aeruginosa. These blue green algae apparently enter the waterbodies from soil, which are known to harbour a rich diversity of blue green flora with several species common to limnoplankton, a feature reported to be unique to the south Indian lakes.Chamarajasagar water samples revealed five classes of phytoplankton, of which Cyanophyceae (92.15 percent) that dominated other algal forms comprised of one single species of Microcystis aeruginosa. The next major class of algae was Chlorophyceae (3.752 percent) followed by Dinophyceae (3.51 percent), Bacillariophyceae (0.47 percent) and a sparsely available and unidentified class (0.12 percent).Madiwala Lake phytoplankton, in addition to Cyanophyceae (26.20 percent), revealed a high density of Chlorophyceae members (73.44 percent) dominated by Scenedesmus sp.,Pediastrum sp., and Euglena sp.,which are considered to be indicators of organic pollution. The domestic and industrial sewage, which finds its way into the lake, is a factor causing organic pollution. As compared to the other classes, Euglenophyceae and Bacillariophyceae members were the lowest in number. Thus, the analysis of various parameters indicates that Chamarajasagar reservoir is relatively unpolluted except for the high percentage of Microcystis aeruginosa, and a slightly alkaline nature of water. Madiwala lake samples revealed eutrophication and high levels of pollution, which is clarified by the physico–chemical analysis, whose values are way above the tolerance limits. Also, the phytoplankton analysis in Madiwala lake reveals the dominance of Chlorophyceae members, which indicate organic pollution (sewage being the causative factor).

Comprehensive seismic hazard assessment of Tripura and Mizoram states

Northeast India is one of the most highly seismically active regions in the world with more than seven earthquakes on an average per year of magnitude 5.0 and above. Reliable seismic hazard assessment could provide the necessary design inputs for earthquake resistant design of structures in this' region. In this study, deterministic as well as probabilistic methods have been attempted for seismic hazard assessment of Tripura and Mizoram states at bedrock level condition. An updated earthquake catalogue was collected from various national and international seismological agencies for the period from 1731 to 2011. The homogenization, declustering and data completeness analysis of events have been carried out before hazard evaluation. Seismicity parameters have been estimated using G R relationship for each source zone. Based on the seismicity, tectonic features and fault rupture mechanism, this region was divided into six major subzones. Region specific correlations were used for magnitude conversion for homogenization of earthquake size. Ground motion equations (Atkinson and Boore 2003; Gupta 2010) were validated with the observed PGA (peak ground acceleration) values before use in the hazard evaluation. In this study, the hazard is estimated using linear sources, identified in and around the study area. Results are presented in the form of PGA using both DSHA (deterministic seismic hazard analysis) and PSHA (probabilistic seismic hazard analysis) with 2 and 10% probability of exceedance in 50 years, and spectral acceleration (T = 0. 2 s, 1.0 s) for both the states (2% probability of exceedance in 50 years). The results are important to provide inputs for planning risk reduction strategies, for developing risk acceptance criteria and financial analysis for possible damages in the study area with a comprehensive analysis and higher resolution hazard mapping.