Search

The application of metamodeling technique to overcome computational challenge of Monte Carlo simulation (MCS) technique for response uncertainty quantification under stochastic earthquake load is a difficult task due to the high-dimensional nature of stochastic load. Recent developments in the sequential models for forecasting and prediction have opened a new avenue in this regard. Various deep learning algorithms, particularly the convolutional neural network and recurrent neural network are quite suitable for response uncertainty quantification of nonlinear stochastic dynamic system. However, most of the existing studies consider stochastic load as the only source of uncertainty assuming the parameters characterizing a structure as deterministic. The present study proposes a long short-term memory (LSTM) based deep learning algorithm for seismic response uncertainty quantification by duly addressing both the stochastic nature of dynamic load and structural system parameter uncertainty. The functional application program interface feature of Keras that allows layers sharing to form more complex model is explored to form a response approximation model. It incorporates more than one input source i.e., stochastic dynamic excitation sequence as well as structural system parameter uncertainty. The proposed algorithm is elucidated through two numerical examples i.e., a proof-of-concept example and one realistic structural engineering problem by considering the direct MCS based results as the benchmark. The results of accuracy matrices, regression analysis results, comparison of seismic response statistics and reliability results with the results of direct MCS technique clearly revealed the enhanced prediction capability of the proposed LSTM model. • A long short term memory based deep learning algorithm for seismic response uncertainty quantification. • Duly address both the stochastic nature of dynamic load and system parameter uncertainty. • Exploits functional API feature of Keras for layers sharing to form more complex response approximation model. • Effectiveness elucidated numerically considering the direct MCS based results as the benchmark. [ABSTRACT FROM AUTHOR]

In this study, three TMT bars and one cold-drawn bar with diameters of 6 mm, 8 mm, 10 mm, and 6 mm, respectively, are spot welded. The hardness values of these welded samples are tested at three locations, i.e., base, welded zone, and heat-affected zone (HAZ). The mechanical properties of different areas of the welded samples change after welding. In all cases, the weld zone hardness increases the most, and in the HAZ, the hardness increases more than in the base metal zone. In the base area, more ferrite is present, resulting in lower hardness than pearlite. Moreover, Widmanstätten structure or Thomas structure is present in HAZ for TMT bars, which is likely near the fusion edge and tends to increase the hardness (212–238 HV) than that of the base metal (185–193 HV). The welded zone consists of a columnar dendritic structure of fused metal with more pearlite than ferrite, causing higher hardness (266–267 HV) than base metal and HAZ. On the contrary, a higher hardness for cold-drawn steel with more hardness variation is observed between weld (250–308 HV), HAZ (230–245 HV), and base (200–225 HV) than those of TMT bars. The tensile strength is predicted using forecast analysis in MS Excel based on the available literature data. Among the four experimental bars, 6 mm TMT and 6 mm cold-drawn wire show excellent weld joint characteristics with efficiencies of 97% and 77%, respectively regarding shear strength, good weld penetration, and hardness variation. [ABSTRACT FROM AUTHOR]

• We have proposed a ranking support vector machine (rSVM) with convolutional neural network in deep learning field for the detection of diabetic retinopathy. • The spatial features of the retinal images have been extracted from RGB channel and mapped into a single binary features plane by the computing of pixel by pixel score using rSVM. • A deep convolutional neural network has been designed for the retinal image segmentation followed by automatic anomaly detection using morphological operations. • The rSVM computes a score function which is more suitable for multi-level classification to binary features classification in order to reduce the overall execution time in the segmentation task. • To validate the proposed model we have employed publicly available database and the performance of them outperform state-of-the-art algorithms. Retinal image analysis is an emerging research field in ophthalmological disease diagnosis since falsely detected optic disc, fovea, and blood vessels have become essential levels for automated diagnosis practices. In this article, we introduce a novel retinal image segmentation based on ranking support vector machine (rSVM) with convolutional neural network in deep learning field for the detection of diabetic retinopathy. Firstly, the spatial features of the retinal images have been extracted from RGB channel and mapped into a single binary features plane by the computing of pixel by pixel score using rSVM. Thereafter, we have designed a deep convolutional neural network for the retinal image segmentation followed by automatic anomaly detection using morphological operations. The rSVM computes a score function which is more suitable for multi-level classification to binary features classification in order to reduce the overall execution time in the segmentation task. The CNN has been designed with rSVM to define a consistent feature label in the network that reduces the number of channels in the CNN which lead to fast convergence. As a consequence, we have achieved good segmentation accuracy such as 96.4%, 97% and 98.2% for three different databases through post processing steps in comparison with other existing model. [ABSTRACT FROM AUTHOR]

Automated mammogram image segmentation is one of the most important methods in the domain of medical diagnosis and decision systems. Accurate segmentation of mammogram plays a key role for the detection of any kind of abnormality like lesion tissues, cyst in mammogram images for medical diagnosis. In this study, a novel hybrid soft computing entrenched segmentation method for mammograms is introduced for the detection of breast cancer in early stages. Here, we have designed a novel automatic mammogram segmentation method using intuitionistic fuzzy soft sets (IFSS) and Multigranulation rough set. First, the proposed clustering algorithm accomplishes a soft information structure from the source image using IFSSs via multiple fuzzy membership functions with Yager generating function. The IFSS handles the ambiguity among lesion and non-lesion pixels through the hesitant degree while shaping the membership function. To reduce distant pixels which do not belong to the region of interest (ROI), the lesion tissues in mammogram image is segregated by decision making scheme via a rough approximation of a fuzzy concept under the field of multigranulation space. Later, the proposed scheme utilizes soft-information builder with accuracy and roughness scores on multigranulation approximation space for segregation of normal and abnormal (lesion tissues) pixel from mammograms. The proposed model has generated a threshold image from accuracy and roughness scores via defuzzification process. The proposed segmentation model performs better than the existing methods using evaluation metrics like segmentation accuracy, Jeccards similarity coefficient. • Intuitionistic fuzzy soft rough set clustering is aimed for mammogram segmentation. • Initial centroids and clustering numbers are chosen by histogram methods. • The proposed IFSRCM clustering handles uncertain pixel precisely by hesitant score. • Parameterization tool builds lower and upper approximations reducing the features. • The rough set deals with boundary regions precisely for fast convergence. [ABSTRACT FROM AUTHOR]

Bayesian linear regression (BLR) based demand prediction models are proposed for efficient seismic fragility analysis (SFA) of structures utilizing limited numbers of nonlinear time history analyses results. In doing so, two different BLR models i.e. one based on the classical Bayesian least squares regression and another based on the sparse Bayesian learning using Relevance Vector Machine are explored. The proposed models integrate both the record-to-record variation of seismic motions and uncertainties due to structural model parameters. The magnitude of uncertainty involved in the fragility estimate is represented by providing a confidence bound of the fragility curve. The effectiveness of the proposed BLR models are compared with the commonly used cloud method and the maximum likelihood estimates methods of SFA by considering a nonlinear single-degree-of-freedom system and a five-storey reinforced concrete building frame. It is observed that both the BLR models can estimate fragility with improved accuracy compared to those common analytical SFA approaches considering direct Monte Carlo simulation based fragility results as the benchmark. • Seismic demand prediction models based on Bayesian linear regression. • Integrate uncertainties due to record-to-record variation and structural parameters. • Efficient estimate of seismic fragility and its confidence bound. • Comparison with the results of direct Monte Carlo Simulation as benchmark. • Comparison with commonly used analytical seismic fragility analysis methods. [ABSTRACT FROM AUTHOR]

Image enhancement algorithms are commonly used to increase the contrast and visual quality of low-dose x-ray images. This paper proposes an automated enhancement method using soft fuzzy sets with a new decision-making scheme based on Dempster-Shafer theory of evidence for the visual interpretation of pneumonia malformation in low-dose x-ray images, called as XEFSDS. The XEFSDS model first generates an original source x-ray image into a complementary image, then each original and complement image is applied to the characterized image object and background areas of fuzzy space. The S-function is utilized to define fuzzy soft sets for the classification of gray level ambiguity in both images, and hence a decision criterion via Dempster-Shafer approach and fuzzy interval has been adapted to discriminate uncertainties on the pixel intensity and the spatial information. Modified membership grade operations have been performed on each object/background area, and Werner's AND/OR operator (an aggregation operator) has been utilized to build a new membership function from two modified membership functions. Finally, an enhanced image is obtained from the new membership function via defuzzification. Experiments on different pneumonia X-ray images demonstrate that the XEFSDS scheme produces better results than the existing methods. To show the advantages of the XEFSDS scheme, we have executed a segmentation based examination on enhanced image for the detection of pneumonia malformation as well as abnormal lobe (lobar pneumonia) or bronchopneumonia. [ABSTRACT FROM AUTHOR]

Graphical description of the computational methodology for quenching and partitioning steel microstructure type classification model development using k -NN. [Display omitted] The paper proposed a machine learning model for multiclass classification of quenched and partitioned (Q&P) steel microstructure type. In this work, we implemented the k- nearest neighbor (k -NN) algorithm to train the classifier. A Q&P steel microstructure-type database has been compiled from the previous research data comprising the information of 348 steel samples. The feature space was described by the steel composition, lower critical temperature (Ac 1), upper critical temperature (Ac 3), martensitic-start temperature (M s), etc., and the Q&P heat treatment parameters. At the same time, the target or dependent variable was recorded as the microstructure type, for example, martensite-retained austenite {M, RA}, martensite-bainite-retained austenite {M, B, RA} etc. The proposed classifier could achieve an overall performance of 97.7% and 77.7%, measured as f1-Score in the training and testing dataset, respectively. The martensite-retained austenite {M, RA} type was found to be the most confusing class. The model explored the effect of compositional parameters and heat treatment variables on the evolution of microstructure. The re-engineering through model study for targeted martensite-retained austenite microstructure type has depicted a steel composition and heat treatment window, which has been validated by experimental development of steel microstructure. The optical and SEM micrographs, along with hardness, strongly corroborated the model analysis from a re-engineering perspective. [ABSTRACT FROM AUTHOR]

The present paper is primarily focused to understand the strain driven alterations in thermoelectric (TE) properties of two-dimensional SiH and GeH monolayers from first-principle calculations. Electronic band structures and the associated TE properties of the compounds under ambient and external strains have been critically unveiled in terms of Seebeck coefficients, electrical conductivities, power factors and electronic thermal conductivities. The phonon dispersion relations have also been investigated to estimate the lattice thermal conductivities of the systems. The TE figure of merits of SiH and GeH monolayers under ambient and external strains have been explored from the collective effects of their Seebeck coefficients, electrical conductivities, electronic and lattice thermal conductivities. The present study will be helpful in exploring the strain induced TE responses of SiH and GeH compounds which in turn may bear potential applications in clean and global energy conservation., (© 2024 IOP Publishing Ltd.)

The present paper is primarily focused on predicting the band gaps of nitride perovskites from machine learning (ML) models. The ML models have been framed from the feature descriptors and band gap values of 1563 inorganic nitride perovskites having formation energies <-0.026 eV and band gaps ranging from ∼1.0 to 3.1 eV. Four supervised ML models such as multi-layer perceptron (MLP), gradient boosted decision tree (GBDT), support vector regression (SVR) and random forest regression (RFR) have been considered to predict the band gaps of the said systems. The accuracy of each model has been tested from mean absolute error, root-mean-square error and determination coefficient R 2 values. The bivariate plots between the predicted and input band gaps of the compounds for both the training and test datasets have also been estimated. Additionally, two ABN 3 -type nitride perovskites CeBN 3 (B = Mo, W) have been selected and their electronic band structures and optoelectronic properties have been studied from density functional theory (DFT) calculations. The band gap values of the said compounds have been estimated from DFT calculations at PBE, HSE06, G 0 W 0 @PBE, G 0 W 0 @HSE06 level of theories. The present study will be helpful in exploring the ML models in predicting the band gaps of nitride perovskites which in turn may bear potential applications in photovoltaic cells and optical luminescent devices., Competing Interests: There are no conflicts of interest to declare., (This journal is © The Royal Society of Chemistry.)