Search results

The bank is termed as an imperative part of the marketing economy. The failure or success of an institution relies on the ability of industries to compute the credit risk. The loan eligibility prediction model utilizes analysis method that adapts past and current information of credit user to make prediction. However, precise loan prediction with risk and assessment analysis is a major challenge in loan eligibility prediction.

This aim of the research technique is to present a new method, namely Social Border Collie Optimization (SBCO)-based deep neuro fuzzy network for loan eligibility prediction. In this method, box cox transformation is employed on input loan data to create the data apt for further processing. The transformed data utilize the wrapper-based feature selection to choose suitable features to boost the performance of loan eligibility calculation. Once the features are chosen, the naive Bayes (NB) is adapted for feature fusion. In NB training, the classifier builds probability index table with the help of input data features and groups values. Here, the testing of NB classifier is done using posterior probability ratio considering conditional probability of normalization constant with class evidence. Finally, the loan eligibility prediction is achieved by deep neuro fuzzy network, which is trained with designed SBCO. Here, the SBCO is devised by combining the social ski driver (SSD) algorithm and Border Collie Optimization (BCO) to produce the most precise result.

The analysis is achieved by accuracy, sensitivity and specificity parameter by. The designed method performs with the highest accuracy of 95%, sensitivity and specificity of 95.4 and 97.3%, when compared to the existing methods, such as fuzzy neural network (Fuzzy NN), multiple partial least squares regression model (Multi_PLS), instance-based entropy fuzzy support vector machine (IEFSVM), deep recurrent neural network (Deep RNN), whale social optimization algorithm-based deep RNN (WSOA-based Deep RNN).

This paper devises SBCO-based deep neuro fuzzy network for predicting loan eligibility. Here, the deep neuro fuzzy network is trained with proposed SBCO, which is devised by combining the SSD and BCO to produce most precise result for loan eligibility prediction.

With the advancements in photo editing software, it is possible to generate fake images, degrading the trust in digital images. Forged images, which appear like authentic images, can be created without leaving any visual clues about the alteration in the image. Image forensic field has introduced several forgery detection techniques, which effectively distinguish fake images from the original ones, to restore the trust in digital images. Among several forgery images, spliced images involving human faces are more unsafe. Hence, there is a need for a forgery detection approach to detect the spliced images.

This paper proposes a Taylor-rider optimization algorithm-based deep convolutional neural network (Taylor-ROA-based DeepCNN) for detecting spliced images. Initially, the human faces in the spliced images are detected using the Viola–Jones algorithm, from which the 3-dimensional (3D) shape of the face is established using landmark-based 3D morphable model (L3DMM), which estimates the light coefficients. Then, the distance measures, such as Bhattacharya, Seuclidean, Euclidean, Hamming, Chebyshev and correlation coefficients are determined from the light coefficients of the faces. These form the feature vector to the proposed Taylor-ROA-based DeepCNN, which determines the spliced images.

Experimental analysis using DSO-1, DSI-1, real dataset and hybrid dataset reveal that the proposed approach acquired the maximal accuracy, true positive rate (TPR) and true negative rate (TNR) of 99%, 98.88% and 96.03%, respectively, for DSO-1 dataset. The proposed method reached the performance improvement of 24.49%, 8.92%, 6.72%, 4.17%, 0.25%, 0.13%, 0.06%, and 0.06% in comparison to the existing methods, such as Kee and Farid's, shape from shading (SFS), random guess, Bo Peng et al., neural network, FOA-SVNN, CNN-based MBK, and Manoj Kumar et al., respectively, in terms of accuracy.

The Taylor-ROA is developed by integrating the Taylor series in rider optimization algorithm (ROA) for optimally tuning the DeepCNN.

Relief item distribution to victims is a key activity during disaster response. Currently many humanitarian organizations follow simple guidelines based on experience to assess need and distribute relief supplies. However, the interviews with practitioners suggest a problem in efficiency in relief distribution efforts. The purpose of this paper is to develop a model and solution methodology that can estimate relief center (RC) performance, measured by waiting time for victims and throughput, for any RC design and analyze the impact of key design decisions on these performance measures.

Interviews with practitioners and current practice guidelines are used to understand relief distribution and a queuing network model is used to represent the relief distribution. Finally, the model is applied to data from the 2015 Nepal earthquake.

The findings identify that dissipating congestion created by crowds, varying item assignment decisions to points of distribution, limiting the physical RC capacity to control congestion and using triage queue to balance distribution times, are effective strategies that can improve RC performance.

This research bases the RC designs on Federal Emergency Management Agency guidelines and assumes a certain area and volunteer availability.

This paper contributes to humanitarian logistics by discussing useful insights that can impact how relief agencies set up and operate RCs. It also contributes to the queuing literature by deriving analytic solutions for the steady state probabilities of finite capacity, state dependent queues with blocking.

The advancements of deep learning (DL) models demonstrate significant performance on accurate pancreatic tumor segmentation and classification.

The presented model involves different stages of operations, namely preprocessing, image segmentation, feature extraction and image classification. Primarily, bilateral filtering (BF) technique is applied for image preprocessing to eradicate the noise present in the CT pancreatic image. Besides, noninteractive GrabCut (NIGC) algorithm is applied for the image segmentation process. Subsequently, residual network 152 (ResNet152) model is utilized as a feature extractor to originate a valuable set of feature vectors. At last, the red deer optimization algorithm (RDA) tuned backpropagation neural network (BPNN), called RDA-BPNN model, is employed as a classification model to determine the existence of pancreatic tumor.

The experimental results are validated in terms of different performance measures and a detailed comparative results analysis ensured the betterment of the RDA-BPNN model with the sensitivity of 98.54%, specificity of 98.46%, accuracy of 98.51% and F-score of 98.23%.

The study also identifies several novel automated deep learning based approaches used by researchers to assess the performance of the RDA-BPNN model on benchmark dataset and analyze the results in terms of several measures.

The purpose of this paper is to focus on MHD unsteady flow of Carreau fluid over a variable thickness melting surface in the presence of chemical reaction and non-uniform heat sink/source.

The flow governing partial differential equations are transformed into ordinary ones with the help of similarity transformations. The set of ODEs are solved by a shooting technique together with the R.K.–Fehlberg method. Further, the graphs are depicted to scrutinize the velocity, concentration and temperature fields of the Carreau fluid flow. The numerical values of friction factor, heat and mass transfer rates are tabulated.

The results are presented for both Newtonian and non-Newtonian fluid flow cases. The authors conclude that the nature of three typical fields and the physical quantities are alike in both cases. An increase in melting parameter slows down the velocity field and enhances the temperature and concentration fields. But an opposite outcome is noticed with thermal relaxation parameter. Also the elevating values of thermal relaxation parameter/ wall thickness parameter/Prandtl number inflate the mass and heat transfer rates.

This is a new research article in the field of heat and mass transfer in fluid flows. Cattaneo–Christov heat flux model is used. The surface of the flow is assumed to be melting.

Serial crowdfunding is becoming a common phenomenon as entrepreneurs repeatedly return to online crowdfunding to raise capital. In this study, the authors focus attention on serial crowdfunders, that is, entrepreneurs who experience launching more than one crowdfunding project. The purpose of this paper is to investigate the role of past experience on subsequent crowdfunding performance. This study also examines whether initial success vs initial failure leads serial crowdfunders to engage in more explorative behaviors (i.e. switching industry) and to take exploitative actions (i.e. adjusting campaign strategies in terms of goal setting and funding option).

Data on serial crowdfunding projects was retrieved from Indiegogo platform. The logistic regression models are estimated to assess the impact of past entrepreneurial experience on subsequent crowdfunding decisions, and to estimate the effects of the three strategies on subsequent funding performance.

The results show that serial creators who experienced successful initial crowdfunding are more likely to explore a new industry or product category in the crowdfunding market and to set a higher target capital for the subsequent campaign when they change a project category.

Despite the fact that there are a considerably large number of serial crowdfunders in crowdfunding market, relatively little research has been conducted to investigate the presence of learning benefits from a previous to a subsequent crowdfunding project. Two competing hypotheses, drawn from the attribution theory and hubris theory of entrepreneurship, were tested in this study to determine the impact of prior success vs failure experience on both subsequent crowdfunding decisions and funding performance.

Our objective was to compare the physical health status of adult prisoners with and without a mental illness. Mental illness was diagnosed in a sample of 557 Australian prisoners using the Composite International Diagnostic Interview (CIDI). Physical health measures included self‐reported chronic health conditions, recent health complaints and symptoms, self‐assessed health using the Short‐Form 36 Health Survey (SF‐36), and markers of infectious diseases known to be highly prevalent among prisoner populations (hepatitis A, hepatitis B, and hepatitis C). Men and women with a mental illness had lower scores on the SF‐36 compared with those without a mental illness indicating poor overall health. Adjusting for age and sex, a diagnosis of any mental illness (symptoms of psychosis, anxiety or affective disorder) was positively associated with a history of head injury, back problems, asthma, peptic ulcers, cancer, and epilepsy/seizures. There was a significant association between post traumatic stress disorder and asthma, a history of head injury, peptic ulcers, and cancer. There was no significant difference in the proportion of current tobacco smokers in the mentally ill and nonmentally ill groups (81% vs. 77%, p = 0.33). However, those with a mental illness were less likely than those with no diagnosis to exercise in the past 4 weeks (79% vs. 89%, p = 0.002). Mentally ill prisoners also have significant physical co‐morbidity compared with the non‐mentally ill. These findings suggest that those providing mental health services to prisoners should adopt a holistic approach embracing both mental and physical health.

The purpose of this paper is to scrutinize the heat and mass transfer attributes of three-dimensional bio convective flow of nanofluid across a slendering surface with slip effects. The analysis is carried out subject to irregular heat sink/source, thermophoresis and Brownian motion of nanoparticles.

At first, proper transmutations are pondered to metamorphose the basic flow equations as ODEs. The solution of these ODEs is procured by the consecutive application of Shooting and Runge-Kutta fourth order numerical procedures.

The usual flow fields along with density of motile microorganisms for sundry physical parameters are divulged via plots and scrutinized. Further, the authors analyzed the impact of same parameters on skin friction, heat and mass transfer coefficients and presented in tables. It is discovered that the variable heat sink/source parameters play a decisive role in nature of the heat and mass transfer rates. The density of motile microorganisms will improve if we add Al-Cu alloy particles in regular fluids instead of Al particles solely. A change in thermophoresis and Brownian motion parameters dominates heat and mass transfer performance.

To the best of the knowledge, no author made an attempt to investigate the flow of nanofluids over a variable thickness surface with bio-convection, Brownian motion and slip effects.

The purpose of this paper is to propose the knowledge of thermal transport of magneto hydrodynamic non-Newtonian fluid flow over a melting sheet in the presence of exponential heat source.

The group of PDE is mutated as dimension free with the assistance of similarity transformations and these are highly nonlinear and coupled. The authors solved the coupled ODE’s with the help of fourth-order Runge–Kutta based shooting technique. The impact of dimensionless sundry parameters on three usual distributions of the flow was analyzed and bestowed graphically. Along with them friction factor, heat and mass transfer rates have been assessed and represented with the aid of table.

Results exhibited that all the flow fields (velocity, concentration and temperature) are decreasing functions of melting parameter. Also the presence of cross-diffusion highly affects the heat and mass transfer performance.

Present paper deals with the heat and mass transfer characteristics of magnetohydrodynamics flow of non-Newtonian fluids past a melting surface. The effect of exponential heat source is also considered. Moreover this is a new work in the field of heat transfer in non-Newtonian fluid flows.

The purpose of this paper is to analyze significant determinants to assess the probability of insureds’ intent to buy (ITB) insurance and willingness to pay (WTP) quantum of dollars for security benefits.

The authors use the Double Hurdle Model (DHM) and Neural Network (NN) architecture to analyze the insureds’ behavior for ITB and WTP. The authors apply these frameworks to all the 503 insureds of a branch of a leading insurer in the United Arab Emirates.

The DHM identified age, loans & liabilities, body mass index, travel outside the UAE, salary and country of origin (Middle Eastern and African) as significant determinants to predict WTP for social security benefits. In addition to these determinants, NN architecture identified insurance replacement, holding multiple citizenship, age of parents, mortgages, country of origin: Americas, length of travel, income of previous year and medical conditions of insured as additional important determinants to predict WTP for social security benefits; thus, NN is found to be superior to DHM due to its lowest RMSE and AIC in the holdout sample and also its flexibility and no assumptions unlike econometric models.

Insureds’ data used from one UAE Branch limit the generalizability of empirical findings.

The study findings will enable the insurers to appropriately design the insurance products that match the insurers’ behavior of ITB and WTP for social security benefits.

The study findings have the potential for insurance institutions to be more flexible in their insurance practices through public–private partnerships.

This is the authors’ original research work.