Browse Items (9795 total)
Sort by:
-
Analysis and prediction of Indian stock market: a machine-learning approach
Prediction of financial stock market is a challenging task because of its volatile and non- linear nature. The presence of different factors like psychological, sentimental state, rational or irrational behaviour of investors make the stock market more dynamic. With the inculcation of algorithms based on artificial intelligence, deep learning algorithms, the prediction of movement of financial stock market is revolutionized in the recent years. The purpose of using these algorithms is to help the investors for taking decisions related to the Stock Pricing. A model has been proposed to predict the direction of movement of Indian stock market in the near future. This model makes use of historical Indian stock data of companies in nifty 50 since they came existence along with some financial and social indicators like financial news and tweets related to stocks. After pre-processing and normalization various machine learning algorithms like LSTM, support vector machines, KNearest neighbour, random forest, gradient boosting regressor are applied on this time series data to produce better accuracy and to minimize the RMSE error. This model has the ability to reduce major losses to the investors who invest in stock market. The social indicators will give an insight for predicting the direction of stock market. The LSTM network will make use of historical closing prices, tweets and trading volume. 2023, The Author(s) under exclusive licence to The Society for Reliability Engineering, Quality and Operations Management (SREQOM), India and The Division of Operation and Maintenance, Lulea University of Technology, Sweden. -
Analysis and prediction of seed quality using machine learning
The mainstay of the economy has always been agriculture, and the majority of tasks are still carried out without the use of modern technology. Currently, the ability of human intelligence to forecast seed quality is used. Because it lacks a validation method, the existing seed prediction analysis is ineffective. Here, we have tried to create a prediction model that uses machine learning algorithms to forecast seed quality, leading to high crop yield and high-quality harvests. For precise seed categorization, this model was created using convolutional neural networks and trained using the seed dataset. Using data that can be used to forecast the future, this model is used to learn about whether the seeds are of premium quality, standard quality, or regular quality. While testing data are employed in the algorithms predictive analytics, training data and validation data are used for categorization reasons. Thus, by examining the training accuracy of the convolution neural network (CNN) model and the prediction accuracy of the algorithm, the projects primary goal is to develop the best method for the more accurate prediction of seed quality. 2023 Institute of Advanced Engineering and Science. All rights reserved. -
Analysis and Prediction of Suitable Model for Coconut Production Estimates in South Indian States
The study attempts to forecast coconut production in major coconut-producing states in India. The future projections on coconut production have been calculated based on yearly data for 73 years (194950 to 202122) accessed from the database of Indiastat (2022). We have used prominent forecasting techniques for the purpose and a suitable model has been chosen based on the lowest results of MAPE. The damped linear trend has been chosen for forecasting coconut production in Karnataka whereas Differenced first-order Auto Regressive model with drift has been adopted for Kerala and Karnataka. This study has considered a large dataset compared to other existing works and has chosen states that produce coconut on a large scale in India. Along with this, this study also attempts to find which state will produce more nuts for the Indian coconut industry, which can help the concerned stakeholders to take necessary decisions. Future projections depict that Kerala will continue to be the largest producer of coconut and Karnataka will show remarkable performance in coconut production during the upcoming four years post-study period. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Analysis and predictions of spread, recovery, and death caused by COVID-19 in India
The novel coronavirus outbreak was first reported in late December 2019 and more than 7 million people were infected with this disease and over 0.40 million worldwide lost their lives. The first case was diagnosed on 30 January 2020 in India and the figure crossed 0.24 million as of 6 June 2020. This paper presents a detailed study of recently developed forecasting models and predicts the number of confirmed, recovered, and death cases in India caused by COVID-19. The correlation coefficients and multiple linear regression applied for prediction and autocorrelation and autoregression have been used to improve the accuracy. The predicted number of cases shows a good agreement with 0.9992 R-squared score to the actual values. The finding suggests that lockdown and social distancing are two important factors that can help to suppress the increasing spread rate of COVID-19. 2018 Tsinghua University Press. -
Analysis of a Fractional Stage-Structured Model With CrowleyMartin Type Functional Response by Lagrange Polynomial Based Method
The dynamics of a stage-structured predator-prey system that replicates interactions between two densities of prey and predator populations were investigated in this work. The adult predator population and the juvenile predator are the two compartments that make up the predator population in the model. The predator relies on both prey and juvenile predator, which is another element of the paradigm that can be termed cannibalism. CrowleyMartin type functional denotes the nature of the interaction between prey and adult predators, while Holling type-I functional response denotes the nature of contact between juvenile and adult predators. The concept of memory is introduced in the form of the Caputo fractional derivative to reflect the complicated dynamics of interaction among the species. As a result, the model is able to incorporate all relevant historical information about the occurrence, from its inception to the desired time, into its calculations. We have also investigated the boundedness and existence and uniqueness of solutions to the proposed model. The condition of existence and stability of various points of equilibrium are investigated. The numerical simulations are performed by using the Lagrange polynomial-based method which is novel in the field of mathematical biology. Simulations have been accomplished to examine the significance of parameters related to cannibalism, the conversion rate from prey to adult predator, harvesting of an adult predator, and growth rate of juvenile predators on the overall behavior of the system. The noteworthy performance of the fractional operator on the anticipated predator-prey models dynamical behavior is well demonstrated by numerical results. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023. -
Analysis of a magnetic field and Hall effects in nanoliquid flow under insertion of dust particles
In this study, the two-phase hydromagnetic flow of a viscous liquid through a suspension of dust and nanoparticles is considered. The influence of the Hall current is also taken into account. The similarity variables are utilized to transform the problem into one independent variable. The obtained expressions in one independent variable are solved through the RungeKuttaFehlberg scheme connected with the shooting procedure. The computed results are sketched for employing multiple values of physical constraints on the temperature and velocity of the nanofluid and dust phase. The characterization of various nanoparticles like Cu, Al2O3, TiO2, and Ag on velocities and temperatures of both phases is made through plots. A comparative analysis in the limiting approach is presented to justify the present solution methodology. The range of emerging parameters is taken as 0 ? l ? 3, 0.1 ? ?t ? 3, 0 ? m ? 2.5, 0 ? M2 ? 2, 0.1 ? ?v ? 3, 0 ? ? ? 0.4, and ?0.8 ? ? ? 0.8. From the study, it is revealed that ?t has theopposite effect on the temperature of dust and nanofluid phases. The Hall parameter mraisesthe profiles of velocities in the nanoliquid and dust phases. Also, it is found that the transverse velocities h(?) and H((?) andtemperatures ?(?) and ?p(?) rise for larger ?. 2020 Wiley Periodicals, Inc. -
Analysis of a mathematical model of the aggregation process of cellular slime mold within the frame of fractional calculus
The pivotal aim of the present study is to find the solution for a nonlinear system describing the aggregation process of cellular slime mold by using (Formula presented.) -homotopy analysis transform method. The coupled system is considered within the frame of the Caputo fractional operator. We examine three different cases with distinct values of sensitivity function (Formula presented.), (Formula presented.) and (Formula presented.) to exemplify the efficiency and applicability of the considered scheme. We capture the nature of the obtained results with respect to the fractional order, with distinct initial conditions, and illustrate them using 2D and 3D plots for particular values of the parameters. The considered scheme offers parameters, which help to adjust the convergence region, and we plotted the ?-curves to dissipate the effect in the present framework. Moreover, some simulating and important behavior of the considered model using attained results shows the prominence of the hired operator while analyzing the coupled equations and confirms the competence of the projected scheme. 2023 Informa UK Limited, trading as Taylor & Francis Group. -
Analysis of an Existing Method for Detecting Adversarial Attacks on Deep Neural Networks
Analyzes the existing method of detecting adversarial attacks on deep neural networks, proposed by researchers from Carnegie Mellon University and the Korean Institute of Advanced Technologies (KAIST) Ko, G. and Lim, G in 2021. Examines adversarial attacks, as well as the history of research on the topic. The paper considers the concepts of interpreted and not interpreted neural networks and features of methods of protection of the types of neural networks considered. The method for protecting against adversarial attacks is also considered to be applicable to both types of neural networks. An example of an attack simulation is given, which makes it possible to identify a sign showing that an attack has been committed. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Analysis of attention deficit hyperactivity disorder using various classifiers
Attention Deficit Hyperactivity Disorder (ADHD) is a neurobehavioral childhood impairment that wipes away the beauty of the individual from a very young age. Data mining classification techniques which are becoming a very important field in every sector play a vital role in the analysis and identification of these disorders. The objective of this paper is to analyze and evaluate ADHD by applying different classifiers like Nae Bayes, Bayes Net, Sequential Minimal Optimization, J48 decision tree, Random Forest, and Logistic Model Tree. The dataset employed in this paper is the first publicly obtainable dataset ADHD-200 and the instances of the dataset are classified into low, moderate, and high ADHD. The analysis of the performance metrics and therefore the results show that the Random Forest classifier offers the highest accuracy on ADHD dataset compared to alternative classifiers. With the current need to provide proper evaluation and management of this hyperactive disorder, this research would create awareness about the influence of ADHD and can help ensure the proper and timely treatment of the affected ones. Springer Nature Singapore Pte Ltd 2021. -
Analysis of benchmark image pre-processing techniques for coronary angiogram images
Coronary Artery supplies oxygenated blood and nutrients to the heart muscles. It can be narrow by the plaque deposited on the artery wall. Cardiologists and radiologists diagnose the disease through visual inspection based on x-ray images. It is a challenging part for them to identify the plaque in the artery in the given imagery. By using image processing and pattern recognition techniques, a narrowed artery can be identified. In this paper, pre-processing methods of image processing are discussed with respect to coronary angiogram image(s). In general the angiogram images are affected by device generated noise / artifacts; pre-processing techniques help to reduce the noise in the image and to enhance the quality of the image so that the region of interest is sensed. The main objective of the medical image analysis is to localize the region of interest by removing the noise. It is essential to find the structure of the artery in the angiogram image, for that preprocessing is useful. 2021 IEEE. -
Analysis of Cardiovascular Diseases Prediction Using Machine Learning Classification Algorithms
Worldwide healthcare systems have faced enormous hurdles because of the COVID-19 pandemic, especially when it comes to treating individuals who already have pre-existing disorders such as cardiovascular diseases (CVDs). Prioritizing medical therapies and resources for COVID-19 patients who are at increased risk of mortality from underlying CVDs requires early identification. In this work, we investigate how well three machine learning algorithms-, Random Forest, XGBoost, and Logistic Regression-predict death in COVID-19 patients who already have cardiovascular disease. We performed grid search and cross-validation using a dataset of clinical and demographic features of COVID-19 patients with and without CVDs to reduce overfitting and maximize model performance. Our findings show that among patients with CVDs, Logistic Regression had the best accuracy in predicting COVID-19 fatality, followed by Random Forest and Decision Tree coming in a close second. These results highlight how machine learning algorithms can help clinical professionals detect high-risk COVID-19 patients who have underlying cardiovascular diseases (CVDs), enable prompt interventions, and enhance patient outcomes. 2024 IEEE. -
Analysis of Challenges Experienced by Students with Online Classes During the COVID-19 Pandemic
In the current context of the COVID-19 pandemic, due to restrictions in mobility and the closure of schools, people had to shift to work from home. India has the worlds second-largest pool of internet users, yet half its population lacks internet access or knowledge to use digital services. The shift to online mediums for education has exposed the stark digital divide in the education system. The digitization of education proved to be a significant challenge for students who lacked the devices, internet facility, and infrastructure to support the online mode of education or lacked the training to use these devices. These challenges raise concerns about the effectiveness of the future of education, as teachers and students find it challenging to communicate, connect, and assess meaningful learning. This study was conducted at one of the universities in India using a purposive sampling method to understand the challenges faced by the students during the online study and their satisfaction level. This paper aims to draw insight from the survey into the concerns raised by students from different backgrounds while learning from their homes and the decline in the effectiveness of education. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Analysis of chromosomal aberrations and micronuclei in type 2 diabetes mellitus patients
Introduction: Type 2 diabetes mellitus is a metabolic disorder characterized by insulin resistance and disrupted insulin secretion. It is often linked to injuries, malfunction and failure of several organs in the long term. The elevated chromosomal disruptions and genetic complications in diabetic patients are due to the increased production of reactive oxygen species. Materials and Methods: The current study used chromosomal aberration assay and micronucleus assay to analyze the extent of abnormalities in the subjects. Results: The results showed increase in frequency of chromosomal aberrations in diabetic patients when compared to the control group (2.761.65 and 0.470.75 respectively). They also showed higher levels of micronuclei formation than the control participants (13.288.63 and 4.128.89 respectively). The correlation analysis indicated positive relationship between total aberrations and duration of diabetes. Conclusion: These results indicate that diabetes is associated with genomic instability and studies at a genetic level can be employed for early detection. 2020, West Asia Organization for Cancer Prevention. -
Analysis of club convergence for economies: identification and testing using development indices
This paper attempts to identify club convergence using the procedure suggested by Phillips and Sul (Phillips and Sul, Econometrica 75:17711855, 2007, Phillips and Sul, J Appl Economet 24:11531185, 2009) based on GDP per capita for 102 countries across the globe for the time period 1996 through 2015. The results indicate the presence of five clubs with four countries belonging to the non- convergent group. After identifying the clubs, the study analyzed the transitional behaviors among the clubs. Finally, to understand the determinant of the club membership, we used the ordered logit model by considering the initial level of GDP, gross capital formation, growth rate of population, and four indices, namely social, governance, sustainability, and globalization as the explanatory variables. The results suggest that the initial level of GDP per capita, gross capital formation, social, governance, sustainability, and globalization are the major factors for determining the club. 2021, The Japan Section of the Regional Science Association International. -
Analysis of determinants of voter turnout in Indian states for election years 19912019
Elections, considered the flagship to the emergence of a new government and a new era is a platform replete with exuberance and vibrancy in all forms. No election is complete without its voters who form the backbone behind the success of democracy. Democracy means elections and free and fair elections mean democracy. The present study is a focus on economic determinants of voter turnout in India since 1991 till date (2019 elections). Economics of voting is a study that encompasses analysis of both economists and political scientists in an attempt to study the economic forces influencing political outcome of the country. In this study, relevant forces determining voter turnout and their impact on political outcomes have been emphasized upon. The data are collected across regions and is characterized using panel regression. Economic factors influencing voter turnout are explored using pooled regression and fixed effect model. Results suggest that as India goes to vote, factors such as income employment influence turnout. Literacy (GER) and urban voter turnout do not influence voter turnout. Lack of efficient governance, bureaucratic loopholes, corruption, large-scale migration and others are some of the potent causes of low turnout. 2022, The Author(s), under exclusive licence to Institute for Social and Economic Change. -
Analysis of Elliptic Curve Cryptography & RSA
In todays digital world, the Internet is an essential component of communication networks. It provides a platform for quickly exchanging information among communicating parties. There is a risk of unauthorized persons gaining access to our sensitive information while it is being transmitted. Cryptography is one of the most effective and efficient strategies for protecting our data and it are utilized all around the world. The efficiency of a cryptography algorithm is determined by a number of parameters, one of which is the length of the key. For cryptography, key (public/private) is an essential part. To provide robust security, RSA takes larger key size. If we use larger key size, the processing performance will be slowed. As a result, processing speed will decrease and memory consumption will increase. Due to this, cryptographic algorithms with smaller key size and higher security are becoming more popular. Out of the cryptographic algorithms, Elliptic Curve Cryptography (ECC) provides equivalent level of safety which RSA provides, but it takes smaller key size. On the basis of key size, our work focused on, studied, and compared the efficacy in terms of security among the well-known public key cryptography algorithms, namely ECC (Elliptic Curve Cryptography) and RSA (Rivets Shamir Adelman). 2023 River Publishers. -
Analysis of error rate for various attributes to obtain the optimal decision tree
The competitiveness and computational intelligence are required to increase the gross profit of the product in a market. The classification algorithm rpart is applied on retail market dataset. The regression rpart decision tree algorithm is implemented with principal component analysis to impute data in the missing part of the dataset. The objective is to obtain an optimal tree by analysing cross validation error, standard deviation error, and number of splits and relative error of various attributes. The results of various attributes by ANOVA method are compared to choose the best optimal tree. The tree with minimum error rate is considered for the optimal tree. Copyright 2022 Inderscience Enterprises Ltd. -
Analysis of factors impacting firm performance of MSMEs: lessons learnt from COVID-19
Purpose: The micro, small and medium scale enterprises (MSMEs) faced various challenges in the ongoing COVID-19 pandemic, making it challenging to remain competitive and survive in the market. This research develops a model for MSMEs to cope with the current pandemic's operational and supply chain disruptions and similar circumstances. Design/methodology/approach: The exhaustive literature review helped in identifying the constructs, their items and five hypotheses are developed. The responses were collected from the experts working in MSMEs. Total 311 valid responses were received, and the structural equation modeling (SEM) approach was used for testing and validating the proposed model. Findings: Critical constructs identified for the study are-flexibility (FLE), collaboration (COL), risk management culture (RMC) and digitalization (DIG). The statistical analysis indicated that the four latent variables, flexibility, digitalization, risk management culture and collaboration, contribute significantly to the firm performance of MSMEs. Organizational resilience (ORS) mediates the effects of all the four latent variables on firm performance (FP) of MSMEs. Practical implications: The current study's findings will be fruitful for the manufacturing MSMEs and other firms in developing countries. It will enable them to identify the practices that significantly help in achieving the firm performance. Originality/value: The previous researches have not considered the effect of organizational resilience on the firm performance of MSMEs. This study attempts to fill this gap. 2022, Emerald Publishing Limited. -
Analysis of Fine Needle Aspiration Images by Using Hybrid Feature Selection and Various Machine Learning Classifiers
Women die of breast cancer most often worldwide. Breast tissue samples can be examined by radiologists, surgeons, and pathologists for evidence of this cancer. Fine needle aspiration cytology (FNAC) can be used to detect this cancer through a visual microscopic examination of breast tissue samples. This sample must be examined by a cytopathologist in order to determine the patient's risk of breast cancer. To determine if a tumor is malignant, the nuclei of the cells must be characterized by their chromatin texture patterns. A machine learning method is used in order to categorize FNA images into two classes, respectively Malignant and Benign. For detecting abnormalities, numerous feature collection methods and machine learning means are applied here. Using features extracted from the FNA image set, UCI machine learning datasets are used to validate the proposed approach. This paper compares three classification methodologies, namely random forests, Naive Bayes, and artificial neural networks, by examining their accuracy, specificity, precision, and sensitivity, respectively. With the ANN and PCA along with the Chi-square selection method, 99.1% of the classifiers are correctly classified. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Analysis of Flexoelectricity with Deformed Junction in Two Distinct Piezoelectric Materials Using Wave Transmission Study
Analysis of flexoelectricity in distinct piezoelectric (PE) materials bars (PZT-7A, PZT-6B) with deformed interface in stick over Silicon oxide layer is studied analytically with the help of Love-type wave vibrations. Using the numerical data for PE material, then research achieves the noteworthy fallouts of flexoelectric effect (FE) and PE. The effect of flexoelectricity is compared first between biomaterials of piezoelectric ceramics. Dispersion expressions are procured logically for together electrically unlocked/locked conditions under the influence of deformed interface in the complex form which is transcendental. Fallouts of the research identify that contexture consisting of FE has a noteworthy impact on the acquired dispersion expressions. Existence of FE displays that the unreal section of the phase velocity rises monotonically. Competitive consequences are displayed diagrammatically and ratified with published outcomes. The outcomes of the present research done on both the real and imaginary section of the wave velocity. The comparative study between the two piezo-ceramics bars helps us to understand the properties of one piezo-material over the another and as an outcomes the significance of the present study helps in structural health monitoring, bioengineering for optimizing the detection sensitivity in the smart sensors. 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.