Browse Items (16481 total)
Sort by:
-
Deep Learning for Stock Market Index Price Movement Forecasting Using Improved Technical Analysis
Equity market forecasting is difficult due to the high explosive nature of stock data and its impact on investor's stock investment and finance. The stock market serves as an indicator for forecasting the growth of the economy. Because of the nonlinear nature, it becomes a difficult job to predict the equity market. But the use of different methods of deep learning has become a vital source of prediction. These approaches employ time-series stock data for deep learning algorithm training and help to predict their future behavior. In this research, deep learning methods are evaluated on the India NIFTY 50 index, a benchmark Indian equity market, by performing a technical data augmentation approach. This paper presents a Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), and the three variants of Gated Recurrent Unit (GRU) to analyze the model results. The proposed three GRU variants technique is evaluated on two sets of technical indicator datasets of the NIFTY 50 index (namely TA1 and TA2) and compared to the RNN and LSTM models. The experimental outcomes show that the GRU variant1 (GRU1) with TA1 provided the lowest value of Mean Square Error (MSE=0.023) and Root Mean Square Error (RMSE= 0.152) compared with existing methods. In conclusion, the NIFTY 50 index experiments with technical indicator datasetTA1 were more efficient by GRU. Hence, TA1 can be used to construct a robust predictive model in forecasting the stock index movements. 2021. All Rights Reserved. -
Generalized Vertex Induced Connected Subsets of a Graph
Vol.2 (May), 61-68 -
On Πk – connectivity of some product graphs
Vol. 21, No.2, 70 - 79 ISSN 13105132 -
PBIB Designs and association schemes arising from some connected dominating sets
Vol.4 (5) : 225-232 !SSN 2252-1512 -
Enhancing Glaucoma Detection in Fundus Images: A ResNet based Segmentation and Advanced ML Algorithms with Duck Pack Optimizer
Untreated glaucoma, a chronic eye illness, can cause irreversible vision loss if not caught early. The condition begins with abnormalities in the eye's drainage flow, leading to a rise in intraocular pressure. As the disease progresses, the optic nerve head deteriorates, resulting in vision loss. Ophthalmologists need extensive training and expertise to interpret findings accurately during medical follow-ups to examine the retina. To address this challenge, deep learning-based algorithms have been developed to screen for and diagnose glaucoma using images of the optic nerve, retinal structures, and retinal fundus. This research explores the use of classification and segmentation algorithms based on ResNet to identify glaucoma in fundus images. We fine-tuned the classifier using the DuckPack optimizer and employed XGBoost, LightGBM, and CatBoost algorithms for classification. The results were promising. The segmentation model based on ResNet effectively extracted features, aiding the classification models in accurately identifying glaucoma. All three algorithms performed admirably, though further fine-tuning is needed to determine the best one. Enhancing the model's performance was straightforward after using the DuckPack optimizer for fine-tuning. This study highlights the promising applications of deep learning and sophisticated machine learning algorithms in glaucoma detection. Its findings could inform the development of future diagnostic tools. The Author(s) 2025. -
Biogenic Synthesis of Zinc Oxide Nanoparticles using Coffea arabica Fruit Peel Extract for Electrochemical Detection and Photocatalytic Degradation of Methylene blue Dye
Methylene blue is an ecologically toxic, carcinogenic, and mutagenic dye. Due to extensive industrial use, a significant quantity of effluent containing methylene blue dye is released into a water source. It may cause toxicity to humans and aquatic fauna. Therefore, detecting and removing MB dye from the effluent is essential. For this goal, we synthesized dual application zinc oxide nanoparticles using coffee fruit (Coffea arabica) peel biomass as a reducing agent. SEM scans revealed spherical nanoparticles. The EDX spectral data indicated the existence of zinc and oxygen elements. The X-ray diffraction pattern exhibited crystallinity of ZnO. Under optimized conditions, the electrochemical impedance spectroscopy (EIS), cyclic voltammetry, and Differential Pulse Voltammetry (DPV) study was studied for the detection of MB, an impressively low detection limit (LOD) of 0.01771 ?M was recorded, The photocatalytic efficacy of ZnO nanoparticles demonstrated a significant 92.43% degradation of methylene blue under UV light. So, Coffea arabica biomass may play a vital role in synthesizing eco-friendly ZnO nanomaterials for environmental remediation applications. 2026 Elsevier B.V. -
Numerical and ANN analysis of MWCNTCuOFe?O?H?O nanofluid flow under magnetic dipole influence
The choice of coolants in automobiles, power plants, electrical appliances etc. is basically dependent on the fluids thermal characteristics. Thus, the better thermal characteristics of MWCNT (Multiwalled Carbon Nanotubes) helps in modeling an efficient coolant. Further, the flow of fluid is controlled with a magnetic dipole that creates a magnetic field around it. Since ferrite particles respond better to magnetic field, the base fluid for this study is considered to be ferrofluid formed by suspending Fe3O4 in H2O. In order to ensure stability of this combination, CuO nanoparticles are suspended into the ferrofluid along with the MWCNT that possess higher thermal conductivity. Thus, the ternary nanofluid formed with the composition MWCNT?CuO?Fe3O4?H2O is assumed to flow in the presence of exponential heat source/sink. The theoretical model describing such a particular flow is designed by partial differential equation and these equations are further transferred to ordinary differential equation with the help of apt transformation. The numerical solution obtained for this system and the outcomes are analyzed graphically which indicates that the upsurge in the velocity power index enhances the velocity and the temperature profiles of the ternary nanofluid. Furthermore, as the space between the magnetic dipole and the origin expands, the nanofluid flows faster whereas the temperature of the nanofluid diminishes. Also, An Artificial Neural Network model is applied to check the correlation between the parameter and observed that output data and targeted data are strongly co-related with each other. Akadiai KiadZrt 2025. -
Detection and Classification of Potholes in Indian Roads Using Wavelet Based Energy Modules
Maintenance of roads is one the major challenge in the developed countries. The well maintained roads always indicates the economy of the whole country. The heavy use of roads, environmental conditions and maintenance is not performed regularly that leads the formation of potholes which causes the accidents and unwanted traffics. The paper discuss about the detection of potholes based on wavelet energy field. The proposed method mainly includes three phases (A)Wavelet energy filed is constructed in order to detect the image by using geometric criteria and morphological processing (B)Extracting Region of intersect by edge based segmentation technique (C)Classifying the potholes using Neural Network. 2019 IEEE. -
A Novel Approach for Detection and Recognition of Traffic Signs for Automatic Driver Assistance System Under Cluttered Background
Traffic sign detection and recognition is a core phase of Driver Assistance and Monitoring System. This paper focuses on the development of an intelligent driver assistance system there by achieving road safty. In this paper a novel system is proposed to detect and classify traffic signs such as warning and compulsory signs even for occluded and angular tilt images using Support Vector Machines. Exhaustive experiments are performed in order to demonstrate the efficiency of proposed method. 2019, Springer Nature Singapore Pte Ltd. -
Indian Road Lanes Detection Based on Regression and clustering using Video Processing Techniques
Detecting the road lanes from moving vehicle is a difficult and challenging task because of road lane markings with poor quality, occlusion created by traffic and poor road constructions. If the driver is not maintaining the road lanes properly, the proposed system detects the road lanes and gives the alarm to the driver so that driver can take the corrective actions there by we can avoid the accidents. The paper mainly focusses on detection of road lanes from sequence of image taken from the video from moving vehicle. The Methodology mainly consisting of lane segments merging and fitting using clustering and weighted regression techniques to fit the curve in the place of group of lane segments and curve fitting separately. 2021, Springer Nature Singapore Pte Ltd. -
The Design of Driver Fatigue Detection Based on Eye Blinking and Mouth Yawing
In modern era, the Intelligent Transportation System (ITS) is very essential for the betterment of transport management, autonomous vehicles and especially for safe driving. The statistics suggest that the major severe accidents occur because of drivers drowsiness. The main objective of this work is to give the alert alarm when the driver is falling asleep. In the proposed study, the driver's face is detected using the Viola Jones algorithm, and a novel approach to detecting eye blinks using template matching and a similarity measure. For effective eye tracking, the normalized correlation coefficient is calculated. The correlation score is used to identify eye blinks since a blink causes a significant change in the correlation score. In tracking of mouth yawing finding the darkest region between the lips. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Polypyrrole functionalized MoS2 for sensitive and simultaneous determination of heavy metal ions in water
Assessing heavy metal ion (HMI) contamination to sustain drinking water hygiene is a challenge. Conventional approaches are appealing for the detection of HMIs but electrochemical approaches can resolve the limitations of these approaches, such as tedious sample preparation, high cost, time consuming and the need for trained professionals. Here, an electrochemical approach is developed using a nano-sphered polypyrrole (PPy) functionalized with MoS2 (PPy/MoS2) by square wave anodic stripping voltammetry for the detection of HMIs. The developed sensor can detect Pb2+ with a limit of detection of 0.03 nM and a sensitivity of 36.42 ?A nM?1. Additionally, the PPy/MoS2 sensor was employed for the simultaneous detection of HMIs of Cd2+, Pb2+, Cu2+ and Hg2+. The reproducibility, stability and anti-interference studies confirm that the sensor can be used to monitor HMI contamination of water. 2025 The Royal Society of Chemistry. -
Polypyrrole functionalized MoS2 for sensitive and simultaneous determination of heavy metal ions in water
Assessing heavy metal ion (HMI) contamination to sustain drinking water hygiene is a challenge. Conventional approaches are appealing for the detection of HMIs but electrochemical approaches can resolve the limitations of these approaches, such as tedious sample preparation, high cost, time consuming and the need for trained professionals. Here, an electrochemical approach is developed using a nano-sphered polypyrrole (PPy) functionalized with MoS2 (PPy/MoS2) by square wave anodic stripping voltammetry for the detection of HMIs. The developed sensor can detect Pb2+ with a limit of detection of 0.03 nM and a sensitivity of 36.42 ?A nM?1. Additionally, the PPy/MoS2 sensor was employed for the simultaneous detection of HMIs of Cd2+, Pb2+, Cu2+ and Hg2+. The reproducibility, stability and anti-interference studies confirm that the sensor can be used to monitor HMI contamination of water. 2025 The Royal Society of Chemistry. -
Molecular docking study, and ADMET analysis for the synthesized novel Zn(II) complexes as potential SARS-CoV-2 inhibitors
A new SARS-CoV-2 virus and its variants including omicron created a pandemic situation and caused more deaths in worldwide prompted many researchers to explore potential drug candidates. In this connection, we explored the first-of-its-kind report on computational studies such as molecular docking, and ADMET properties of Zn(II) complexes. The studies revealed the novel zinc complexes have high binding affinities with the SARS-CoV-2 spike glycoprotein (6vxx) alpha variant (7EKF), beta variant (7ekg), gamma variant (7EKC), delta variant (7V8B), and the omicron variant (7T9J). Molecular docking results of RMSD for SARS-CoV-2 beta variant (7ekg) and gamma variant (7EKC) are within excellent chemical stability in their protein-ligand complex state and should be effective in the biological system. ADME studies provided the better results with no adverse effect of toxicity related AMES along with absence of hepatotoxicity and skin sensitization when compared to Molnupiravir drug and it has a greater hepatotoxicity. This study could open further exploration of these novel zinc complexes for SARS-CoV-2 inhibition. (2024) DergiPark. -
Heat transfer enhancement in the boundary layer flow of hybrid nanofluids due to variable viscosity and natural convection
The aim of the current work is to explore how heat transfer can be enhanced by variations in the basic properties of fluids in the presence of free convection with the aid of suspended hybrid nanofluids. Also, the influence of the Laurentz force on the flow is considered. The mathematical equations are converted into a pair of self-similarity equations by applying appropriate transformations. The reduced similarity equivalences are then solved numerically by Runge-Kutta-Fehlberg 45 th -order method. To gain better perception of the problem, the flow and energy transfer characteristics are explored for distinct values of significant factors such as variable viscosity, convection, magnetic field, and volume fraction. The results acquired are in good agreement with previously published results. The noteworthy finding is that the thermal conductivity is greater in hybrid nanofluid than that of a regular nanofluid in the presence of specified factors. The boundary layer thickness of both hybrid nanofluid and normal nanofluid diminishes due to decrease in variable viscosity. The fluid flow and temperature of the hybrid nanofluid and normal nanofluid increases as there is a rise in volume fraction. 2019 -
3D flow and heat transfer of micropolar fluid suspended with mixture of nanoparticles (Ag-CuO/H2O) driven by an exponentially stretching surface
Purpose: The purpose of this paper is to discuss the 3D micropolar hybrid (Ag-CuO/H2O) nanofluid past rapid moving surface, where porous medium has been considered. Design/methodology/approach: The model of problem was represented by highly partial differential equations which were deduced by using suitable approximations (boundary layer). Then, the governing model was converted into five combined ordinary differential equations applying proper similarity transformations. Therefore, the eminent iterative RungeKuttaFehlberg method (RKF45) has been applied to solve the resulting equations. Findings: Higher values of vortex viscosity, spin gradient viscosity and micro-inertia density parameters are reduced in horizontal direction, whereas opposite behaviour is noticed for vertical direction. Originality/value: The work has not been done in the area of hybrid micropolar nanofluid. Hence, this article culminates to probe how to improve the thermal conduction and fluid flow in 3D boundary layer flow of micropolar mixture of nanoparticles driven by rapidly moving plate with convective boundary condition. 2020, Emerald Publishing Limited. -
Sensitivity analysis of thermal optimisation within conical gap between the cone and the surface of disk with particle deposition
This work examines the thermal and flow characteristics of TiO2+AgBr+GO/EG trihybrid nanofluid in the conical gap that exists between a disc and a cone. Effect of thermophoresis and particle deposition are examined to perceive the mass dissipation change on the surface. The governing equations of the problem are in the form of partial differential equations which are converted to nonlinear ordinary differential equations by applying proper scaling similarity transformations, and then the resultant equations are approximated numerically by using RKF45 technique. The interesting part of this research is to discuss the impact of various pertinent parameters on three cases namely: (1) rotating cone/disk (2) rotating cone/stationary disk and (3) stationary cone/rotating disk. The flow field, heat and mass transfer rates were analysed using graphical representations. Additionally, sensitivity analysis is performed on derived rate of heat transfer as a response function for input factors for different parameters. From the graph, it is perceived that flow field increases significantly with increase in the values of Reynolds numbers for both cone and disk rotations. Also, it is seen that temperature upsurges significantly for ascendent values of solid volume fraction of nanoparticles. It is also noticed that the sensitivity of the Nusselt number towards n is more for all the values of source/sink and for middle level values of n. Akadiai KiadZrt 2024. -
Series solutions for an unsteady flow and heat transfer of a rotating dusty fluid with radiation effect
A theoretical analysis of free convective MHD flow of an unsteady rotating dusty fluid under the influence of hall current and radiation effect is carried out. The fluid flow is considered in the porous media under the influence of periodic pressure gradient and the fluid is assumed to be viscous, incompressible and electrically conducting with uniform distribution of dust particles. The governing partial differential equations are solved analytically using perturbation technique and the expressions for skin-friction is also derived. Further the effect of various pertinent parameter like magnetic parameter, rotation parameter and Hall current parameter on velocity of both fluid and dust phases are depicted graphically and the effect of radiation parameter, Grashof number and Prandtl number on temperature profile is also discussed in detail. 2017, Univerzita Komenskeho. All rights reserved. -
Mixed convection in the stagnation-point flow over a vertical stretching sheet in the presence of thermal radiation
An unsteady two-dimensional stagnation-point mixed convection flow of a viscous, incompressible dusty fluid towards a vertical stretching sheet has been examined. The stretching velocity and the free stream velocity are assumed to vary linearly with the distance from the stagnation point. The problem is analyzed using similarity solutions. The similarity ordinary differential equations were then solved numerical by using the RKF-45 method. The effects of various physical parameters on the velocity profile and skin-friction coefficient are also discussed in this paper. Some important findings reported in this work reveal that the effect of radiation has a significant impact on controlling the rate of heat transfer in the boundary layer region.