Browse Items (16481 total)
Sort by:
-
An analytical hierarchy process-based approach to building resilience in the Indian healthcare supply chain
Healthcare supply chains are constantly evolving and, thus, are subject to an array of disruptive risks. Apart from being crucial to the sustenance of human life, the healthcare supply chains are pivotal in adding value to the economy. The Indian healthcare supply chain is an intricate structure of indigenous and international entities functioning in unison to provide healthcare products to the masses. Bottlenecks along the healthcare supply chain can lead to disruptive consequences at any point. Thus, the identification of these disruptive risks is crucial in articulating risk mitigation strategies and ensuring business continuity. This study identifies supply chain risks along the Indian healthcare supply chain through unstructured interviews with industry experts. The identified risks are prioritised using the analytic hierarchy process (AHP) decision matrix. The results revealed that the Indian healthcare supply chain is facing obstacles with respect to import and export activities. Copyright 2026 Inderscience Enterprises Ltd. -
Stock Price Prediction using Deep Learning and FLASK
The forecasting of stock prices is one of the most explored issues, and it attracts the attention of both academics and business professionals. It is quite difficult to make predictions about the stock market, and it takes extensive research into the patterns of data. With the expansion of the internet and indeed the growth of social media, online media and opinions frequently mirror investor sentiment. The volatility and non-linear structure of the financial stock markets makes accurate forecasting difficult. One of the sophisticated analysis techniques that is being used by academics in a variety of fields is the neural network. In this paper, we proposed deep learning techniques for google stock price prediction. A dataset from Kaggle was collected and applied deep learning techniques RNN, LSTM variants. We achieved better results with Bidirectional LSTM. We also created a web app for stock prediction using Christ University python FLASK. 2022 IEEE. -
Airline Twitter Sentiment Classification using Deep Learning Fusion
Since the advent of the Internet, the way people express their ideas and beliefs has undergone significant transformation. Blogs, online forums, product review websites and social media are increasingly the primary means of distributing information about new products. Twitter, in particular, is giving people a platform to air their views and opinions about a variety of events and products. In order to continually enhance the quantity and quality of their products and services, entrepreneurs constantly need input from their customers. Businesses are always looking for ways to increase the quality of their products and services. As a result, it's tough to understand the consumer's sentiments because of the large volume of data. In this research work, a Kaggle dataset of airline tweets for sentiment analysis was used. The dataset contains 11,540 reviews. We proposed an ensemble CNN, LSTM architecture for sentiment analysis. For comparison of the proposed system, LSTM alone also tested for similar dataset. LSTM was given an accuracy of 91% and the proposed ensemble framework with LSTM and CNN was given an accuracy of 93%. The experiments showed that the proposed model achieved better accuracy when compared to conventional techniques. 2022 IEEE. -
Loan Default Prediction Using Machine Learning Techniques and Deep Learning ANN Model
Loan default prediction is a critical task in the financial sector, aimed at assessing the creditworthiness of borrowers and minimizing potential losses for lending institutions. Online loans continue to reach the public spotlight as Internet technology develops, and this trend is expected to continue in the foreseeable future. In this paper, the authors proposed loan default loan prediction system based on ML and DL models. This work makes use of the information on loan defaults provided by Lending Club. The dataset is preprocessed by applying various data preprocessing techniques and preprocessed dataset is generated. Later, we proposed four ML algorithms decision tree, random forest, logistic regression, K-NN and Feed forward neural network. The experimental results shown that proposed feed forward neural network achieved good accuracy for loan default prediction with an accuracy of 99%. 2023 IEEE. -
Role of AI in Computational Risk Modeling of Financial Stability and Portfolio Risk: A New Perspective
The need to assess climate change-related risks and their impact on the financial stability of banks is imperative. Innovations in technology, especially AI andML algorithms, have improved the efficiency and accuracy of risk analysis models. The obstacle for banks is assessing the climate risk exposure due to their lending portfolio. The climate data are uncertain and unavailable, and the granularity of the data is questionable. To overcome these issues, in this chapter, a hybrid risk predictive model is proposed. It uses a combination of ResNet-50 (to analyze and quantify spatial image data) and CoViaR (risk prediction) models. Using the ResNet-50 model, a climate change risk score is developed from images and feature extraction, which is correlated with the emission volume of the borrower firms. Then, using the proposed model, the impact of climate change-related risk on the lending portfolio is evaluated to understand the financial stability of banks through capital. 2025, Bentham Books imprint. -
An Efficient Approach for Gene Selection through Parallel Bio-Inspired Algorithms and Shapley Value Analysis
The fast development of microarray technology has significantly assisted in the use of gene expression analysis to forecast cancer subtypes. Analyzing high-dimensional microarray data is still challenging, as existing hybrid methods cannot find highly discriminative genes. This study aims to use Shapley value analysis and hybrid bio-inspired algorithms to develop a scalable, parallel gene selection technique to increase computing efficiency and classification accuracy in high-dimensional microarray data. This study used hybrid feature selection approaches inspired by bio-organisms to create a scalable parallel gene selection system. The dataset size is initially enlarged by Adaptive Synthetic Sampling (ADASYN). They use the Recursive Feature Elimination (RFE) approach to extract features and determine their Shapley values. In addition, the Whale Optimization Algorithm (WOA) works to determine which genes are most important. After that, Machine Learning (ML) techniques assist in classifying the chosen characteristics. According to the experiment results, the suggested strategy surpasses standard gene selection techniques with the same datasets, employing improved classification accuracy and reducing computing time. K-NN achieved an accuracy of 85.44%, while LR showed improved results with an accuracy of 91.72%. RF further increased accuracy to 94.69%. SVM demonstrated exceptional performance, reaching an accuracy of 97.63%. Ultimately, XGBoost excelled among all models with the highest accuracy of 98.49%, highlighting its robust ability to classify SRBCT samples effectively based on gene expression data. 2025, Ayandegan Institute of Higher Education. All rights reserved. -
An Extensive Time Series Analysis of Covid-19 Data Sets on the Indian States
Pandemic influenza coronavirus is causing a great loss to mankind. It is creating a chaos on the global economy. Fight against this unseen enemy is affecting all the sectors of the global economy. Mankind is quivering with fear and scared to do something. This study gives a detailed presentation of the current position of virus escalation in India. Sentiment analytics from Twitter data is evaluated on sentiment, emotions and fear opinions are analyzed in the study. The analysis is on red, orange and green zones in several states of India and also gave a comprehensive interpretation on various phases of lockdown. Confirmed, active, recovered and deceased cases in all states are modeled to predict the increase of number of cases. Textual, geographical and graphical analytics are extensively described in the research study. Time series analysis is broadly elaborated as a case study till July 22, 2020, forecasting the impact of virus on Maharashtra, Kerala, Gujarat, Delhi and Tamil Nadu. This study will favor the administrative system to control the disease spread across the nation. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Natural convection of a binary liquid in cylindrical porous annuli/rectangular porous enclosures with cross-diffusion effects under local thermal non-equilibrium state
The present article reports an analytical study of the double diffusive natural convection (DDNC) in cylindrical porous annuli (CPA) and rectangular porous enclosures (RPE), which are handled in a unified way using the curvature parameter, saturated by a binary liquid under the assumption of local thermal non-equilibrium (LTNE) state. The buoyancy forces (thermal and solutal) driving the flow are assumed to be induced by the maintenance of constant and uniform heat and mass fluxes applied along the vertical (radial) walls and insulation of both horizontal walls of the annuli/rectangular enclosures. The Darcy-Boussinesq equations with LTNE assumption between the fluid and solid phases are employed to model the problem of DDNC in a binary liquid-saturated porous medium with cross-diffusion effects. The analytical results are obtained by employing the Oseen-linearization transformation technique in the study. The influence of various dimensionless parameters on heat and mass transports of the system are depicted using the Nusselt and Sherwood numbers and isotherms plots, and the obtained results are analysed with the physical explanation. Special attention is given to understand the effect of LTNE parameter and cross-diffusion parameters on heat and mass transports of the system. Different aspect ratio values are chosen to obtain the results of three types of CPA/RPE (shallow, square and tall). Among these CPA/RPE, maximum and minimum heat and mass transports are achieved in the cases of shallow and tall CPA/RPE, respectively. The results of the pure thermal convection problem is obtained at the zero value of buoyancy ratio and solute Rayleigh number. The increasing value of N magnifies the heat and mass transports in the system due to the augmented buoyancy effect resulted from the thermal and solutal gradients. The increase of solid inner cylinder radius, by fixing its volume, makes the annulus slender which yields to decrease the heat and mass transports in the system. The effects of LTNE parameter and cross-diffusion parameters on heat and mass transports of the system are clearly brought out. The results of LTE model are obtained at the infinite value of ratio of porosity modified thermal conductivities, ?, as a particular case of the present model. From the study, we conclude that the shallow porous annulus and tall rectangular enclosure are best suited in the design of heat removal and heat storage systems, respectively. 2021 -
A study of the natural convection of water- AA 7075 nanoliquids in low-porosity cylindrical annuli using a local thermal non-equilibrium model
Natural convection in nanoliquid-saturated porous cylindrical annuli due to uniform heat and mass influxes from the solid cylinder and effluxes from the outer hollow cylinder is investigated analytically. The Darcy model and the modified version of the Buongiorno two-phase model are used, and local thermal non-equilibrium between the phases is assumed. A nanoliquid-saturated porous medium made up of glass balls with a dilute concentration of AA7075 alloy nanoparticles well-dispersed in water is considered. Out of three types of annuli considered, shallow annuli provide the best heat transport and tall annuli show the worst performance. The presence of a dilute concentration of nanoparticles significantly enhances the heat transport in the system. Of nine nanoparticle shapes considered, lamina-shaped nanoparticles enhance heat transport the most. Heat transport is enhanced in the case of heat-and-mass-driven convection compared to the case of purely heat-driven convection. The results for a rectangular enclosure are obtained as a particular case of the present study. Two asymptotic routes that take us to the results of thermal equilibrium are shown. The vanishing limit of the concentration Rayleigh number yields the result for a single-phase model. Results for the base-liquid-saturated porous medium form a limiting case of the present study. We conclude that a shallow cylindrical annulus saturated with water-AA7075 lamina-shaped alloy nanoparticles is best suited for heat transfer due to its high effective thermal conductivity in comparison with that of other shaped nanoparticles and a tall rectangular enclosure saturated by water is best suited for heat storage applications. 2021 Author(s). -
Theoretical Prediction of the Number of Bénard Cells in Low-Porosity Cylindrical/Rectangular Enclosures Saturated by a Fast Chemically Reacting Fluid
Many applications including chemical engineering and meteorology require the study of a chemically driven convection in cylindrical, as well as rectangular enclosures. The present paper reports a unified analysis of a chemically driven convection in densely packed porous cylindrical/rectangular enclosures saturated by a chemically reactive binary fluid mixture. Employing the degeneracy technique and the single-term Galerkin method involving Bessel functions in a linear stability analysis, an analytical expression for the critical Rayleigh number, (Formula presented.), was obtained. An analytical expression for the number of cells that manifest in a given enclosure, at the onset of convection, was derived from (Formula presented.). The connection between the stabilizing and destabilizing effects of various parameters and the size or the number of Bénard cells that manifest are described in detail. The results depicted that the chemical parameters related to the heat of reaction destabilize and the parameter depending inversely on the rate of the chemical reaction stabilizes the system. In the latter case, a greater number of smaller cells were formed in the system compared to the former case. Hence, we concluded that the chemically reactive fluid advances the onset of convection compared to the chemically non-reactive fluid. The results of a similar problem in rectangular enclosures of infinite horizontal extent and chemically non-reactive liquid-saturated porous medium were recovered as limiting cases. Thus, the present model presents a unified analysis of six individual problems. 2023 by the authors. -
Linear and weakly non-linear stability analyses of Rayleigh-Bard convection in a water-saturated porous medium with different shapes of copper nanoparticles
The Rayleigh-Bard convection of a nanoliquid-saturated porous medium confined in a very shallow enclosure is investigated theoretically using the modified Buongiorno - Brinkman model. In the study, the chosen nanoliquid-saturated porous medium is assumed to be made up of water well dispersed with copper(Cu) nanoparticles of five different shapes saturating in a 30% reinforced polycarbonate glass fiber(GF) porous material of high porosity and its effective thermophysical properties are calculated using the phenomenological laws or mixture theory. Two kinds of boundary conditions, viz., stress-free and rigid, are employed and the analytical solution is obtained in both cases. On the other hand, Rayleigh-Bard convection in a very shallow domain of height 5mm and width 5cm filled with water-liquid and bounded by the rigid boundaries is simulated. The simulation results are then compared with the analytical results in the case of rigid boundaries. We found that the analytical results are in good agreement with those of the simulation results and this validates results of the present study. Linear and weakly non-linear stability analyses are performed to find the onset and the heat transport of the system. The effects of various parameters on the onset and heat transport of the system are depicted graphically and the physical explanation is provided for all observed results in the study. We found that the addition of dilute concentration of nanoparticles advances the onset and thereby enhances the heat transport in the system. Among five different shapes of copper nanoparticles, maximum and minimum heat transports are observed in the cases of blade and spherical shaped nanoparticles, respectively. The porous medium parameters: Brinkman number and porous parameter, show a stabilizing effect in the system. The existence of subcritical motions is also predicted for the system. The results of the Khanafer-Vafai-Lightstone(KVL) single-phase model, nanoliquid, base liquid and base liquid-saturated porous medium are obtained as limiting cases of the present study. Since nanoparticles and porous medium, respectively, show a destabilizing and stabilizing nature of influence in the system, the present work has possible applications in both heat removal and heat retainment systems. 2022, The Author(s), under exclusive licence to SocietItaliana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature. -
Natural convection of water-copper nanoliquids confined in low-porosity cylindrical annuli
Natural convection in cylindrical porous annuli saturated by a nanoliquid whose inner and outer vertical radial walls are respectively subjected to uniform heat and mass influxes and out fluxes is studied analytically using the modified Buongiorno-Darcy model (MBDM) and the Oseen-linearization technique. Nanoliquid-saturated porous medium made up of water as base liquid, copper nanoparticles of five different shapes, viz., spheres, bricks, cylinders, platelets and blades, and glass balls porous material is considered as working medium for investigation. The thermophysical properties of nanoliquid -saturated porous medium is modeled using phenomenological laws and mixture theory. The effect of various parameters and individual effects of five different shapes of copper nanoparticles on velocity, temperature and heat transport are found. From the study, it is clear that the addition of a dilute concentration of nanoparticles increases the effective thermal conductivity of the system and thereby increases the velocity and the heat transport, and decreases the temperature. In other words, the heat transport is more in the case of heat and mass driven convection compared to purely heat-driven convection. Among the five different shapes of nanoparticles, blade-shaped nanoparticles facilitate the transport of maximum temperature compared to all other shapes. Maximum heat transport is achieved in a shallow cylindrical annulus compared to square and tall circular annuli. The increase of the inner solid cylinder's radius is to decrease heat transport. The results of the KVL single-phase model are obtained from the present study by setting to zero the value of the nanoparticles concentration Rayleigh number. Also, neglecting the curvature effect in the present problem, we obtain the results of the rectangular enclosure problem. 2020 The Physical Society of the Republic of China (Taiwan) -
Study of rotating Bard-Brinkman convection of Newtonian liquids and nanoliquids in enclosures
Taylor-Bard convection of water and water-based nanoliquids confined in three different types of high porosity rectangular enclosures, viz., shallow, square and tall, is studied analytically using both infinitesimal and finite amplitude stability analyses. We make use of the modified-Buongiorno-Brinkman model(MBBM) for the governing equations concerning nanoliquid-saturated porous enclosures bounded by rigid-rigid boundaries and obtain analytical results. Among three types of enclosures, maximum and minimum heat transfers are observed in tall and shallow enclosures respectively. Water well dispersed with a dilute concentration of single-walled carbon nanotubes(SWCNTs) is considered as a working medium. The water-SWCNTs is able to flow in the porous medium because the medium is loosely-packed with porosity in the range 0.5 ? ? ? 1. In addition to this, the maximum volume fraction of nanoparticles considered in the system is 6% and thus this does not alter the fluidity of the system. We found from the study that the presence of low concentration(volume fraction-0.06) of SWCNTs in a water-saturated porous medium effectively improves the heat transport of the system due to its high thermal conductivity and large surface area. Due to the presence of a porous medium, however, the onset of convection gets delayed and heat transport in nanoliquids gets substantially reduced in a Bard-Brinkman configuration resulting from the weak thermal conductivity of the porous medium. Thus the porous medium acts as the heat storage system. Also, in a rotating frame of reference the heat transport gets reduced and rotation serves as an external mechanism of regulating heat transport in the system. The nonlinear dynamics of the system is studied using the 6-mode Lorenz model. Chaotic motion in the system is studied using the maximum Lyapunov exponent(MLE). The Hofp-bifurcation point of the system along with the MLE is used to investigate periodic, nearly periodic and mildly chaotic behaviors of the system. 2020 -
Achievenment motivation and self esteem among handicapped children
How the children with handicap perceive themselves and their self esteem levels are important yet not much focussed aspect in disability research. If we have a correct evaluation of their motivational level and self esteem it may help us to modify their training interventions and also would make them feel more satisfied and confident. So we planned to study achievement motivation and self esteem levels of handicapped children. The Objective of the study is that to to compare achievement motivation of physically handicapped to that of non-handicapped school children, and to compare self esteem of physically handicapped to that of non-handicapped school children. Methodology 40 physically handicapped school students and 40 age, gender and education matched non handicapped students were included in the study. Handicapped children of other categories like sensory disability, visual impairment, hearing impairment and speech impairment were excluded. Achievement motivation questionnaire was used to measure the motivational behaviour and Rosenberg self-esteem scale was applied by asking the respondents to reflect on their current feelings. Results and Conclusions Achievement motivation and self esteem were observed to be significantly lower in physically handicapped students compared to healthy controls. Significant gender difference in favour of females was observed i.e., self esteem and achievement motivation was significantly higher in females of both the groups compared to males. The study emphasizes need for interventions to improve self esteem and motivation levels of handicapped children. -
A Hybrid Approach Against Black Hole Attackers Using Dynamic Threshold Value and Node Credibility
Detecting black hole attackers is tedious in Vehicular Ad Hoc Networks due to vehicles' high mobility. The main consequence faced because of these attackers is an increase in the number of dropped packets which converts secure and fastest paths to compromised ones. Since these attackers can act individually and collaboratively as a group, early detection of these attackers must be feasible to preserve the network's performance. The majority of current methods rely on predetermined threshold and trust score values, which are ineffective in accurately identifying black hole attackers. Hence, this paper proposes a hybrid approach using dynamic threshold value and node credibility for early detection of black hole attackers. RSUs periodically compute the dynamic threshold value and categorize the vehicles into categories 1, 2, and 3. Vehicles classified as Category 1 are legitimate, whereas Category 3 vehicles are attackers. Vehicles in Category 2 are suspicious, requiring further analysis using node credibility values to identify attackers. It is protected against single, multiple, and collaborative black hole attackers. The NS2 simulation results demonstrate that the suggested method is optimal concerning PDR, Throughput, Delay, and Packet Loss Ratio compared to recent techniques. Since the proposed scheme efficiently identifies the attackers, it has 89.67% PDR, which is higher when compared to other schemes. 2013 IEEE. -
Role of employee value proposition in creating employer brand value for employee attraction and retention
Employee Value Proposition is a set of associations and offerings provided by an organisation in return for the skills, capabilities and experiences an employee brings to the organisation. Employee newlineexpectations from the employer is now shifted from monetary to more intrinsic values like rewards, recognition, and flexible work. newlineUnderstanding the value proposition is vital to devise appropriate human resource strategies for employee attraction and retention. Human resource managers have realised that the communicating the value propositions to the employees is as important as devising them. This has led human newlineresource managers to collaborate with marketing team to develop right newlinecommunicating strategies to build a lucrative employer brand to attract right talent into the organisation. Previous studies lack focus on dual outcomes of employer brand. The current study develops an employer brand for internal employees and potential employees. Although the value proposition components remain same for both category of employees, the order of preference differs. The study has used structured questionnaire to newlineunderstand the order of preference of value proportion components for internal and potential employees among generation X, Y and Z. The findings assist human resource managers to use the developed framework newlineto identify the value proposition preferred and develop and communicate the Employee Value Proposition accordingly. The theoretical contribution includes proposing differentiated Employer Brand framework for internal and potential employees. -
A Cognitive Workload-Aware Machine Learning Model for Performance Enhancement in Cyber-Physical Systems
Cyber-Physical Systems increasingly demand seamless coordination between human operators and autonomous processes, which increases the complexity. High cognitive workload in those environments amounts to a degradation of performance, decision fatigue, and increased susceptibility to system failure and cyber threats. To address these challenges, we propose a Neuro-inspired Cognitive Workload Optimizer (NCO), a novel machine-learning-based model for the monitoring, prediction, and optimization of cognitive workload for CPS performance improvement. The NCO framework employs neuro-inspired deep learning techniques, with LSTM networks coupled with an attention mechanism for assessing workload patterns dynamically in time. The adaptive operation of the system depends on executing a contextual analysis of system data and operator interaction metrics, whereby NCO recognizes fluctuations in workload and adjusts the operations of the system in real-time to maintain an optimal state for cognitive functioning. Thus, the model implements an adaptive feedback loop that prioritizes task distribution, resource allocation, and security management based on cognitive load estimations. In this way, CPS environments are hereby enabled to proactively mitigate operator overloads, minimize latencies, and enhance accuracy in decision-making, all while ensuring this is happening under dynamic conditions ensuring robust system performance. Experimental results on simulated CPS datasets indicate that NCO can reduce workloads peaks by 35%, improve system throughput by 28%, and provide better anomaly detection performance in conditions of high stress. The NeuroCPS-Optimizer thus opens up a new paradigm for cognitive-aware CPS management, ensuring that human and machine components are kept within safe and efficient bounds. This research thereby advances the creation of resilient and intelligent CPS that can self-adjust and sustain performance levels in complex and demanding environments. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Multivariate Forecasting of Co2 Emissions Using Hybrid Machine Learning Models Based on Energy Consumption and Renewable Adoption
The study presents a machine learning approach to predict carbon dioxide (CO2) emissions by analysing key factors such as energy consumption, renewable energy adoption, and economic growth (GDP). Traditional forecasting methods struggle to capture the complex and nonlinear patterns of emissions. To overcome the limitations and improve the accuracy, research combines classical statistical models like ARIMA and VAR with advance techniques, including deep learning (LSTM) and ensemble methods (XGBoost, stacking). The models are trained on a global dataset of energy and economic records. The results shows that the hybrid models, particularly the LSTM + XGBoost and stacked approaches, have outperformed the traditional methods by obtaining a lower Root Mean Square Error (RMSE) and a higher coefficient of determination (R2). Apart from advancing environmental data science, the research offers a solid predictive framework to support policy initiatives related to the Sustainable Development Goals, specifically SDG 7 (Affordable and Clean Energy) and SDG 13 (Climate Action). 2025 IEEE. -
Gestational diabetes prediction using hybrid probabilistic machine learning models
[No abstract available] -
Nonlinear steady Darcy-Bard convection problem: Revisit using the heatlines approach
The classical problem of Darcy-Bard convection(DBC) in enclosures is revisited using the method of heatlines to have a better perspective of the problem. General aspect ratio is chosen in the analysis which helps in obtaining the results of four different types of enclosures, viz., tall, square, shallow and very shallow. Three different water saturated porous media(WSPM) and their actual thermophysical properties are used in the computation of the results. The method of heatlines facilitates the observation of fluid and heat flow lines in order to have a good understanding of the dynamics. The neo-classical approach not only accurately predicts the critical Darcy-Rayleigh and wave numbers but also picturizes the heat flow of the problem in the most natural way. The Galerkin method is used in the paper for the normal and convective modes of convection yields accurate analytical results in the heatlines formulation. Theoretical expression to calculate the number of Bard cells that form in the system at onset is obtained by linear theory, and ranges of aspect ratio at which unicellular, two-cellular and multicellular convection are possible are determined and documented. The weakly non-linear stability analysis is performed to determine the heat transport. Among four considered enclosures, maximum heat transport is achieved in the case of a square enclosure. Out of three chosen WSPM, the water-saturated glass balls porous medium and the water-saturated aluminium-foam porous medium show most stable and least stable behaviours. Results obtained from the heatlines approach are validated by comparing with the results of the classical DBC problem in the case of a very shallow enclosure. From the study, we conclude that the square enclosure with water-saturated aluminium-foam porous medium has possible application in heat removal systems. 2025 The Physical Society of the Republic of China (Taiwan)