Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
749
result(s) for
"Singh, Dharmendra"
Sort by:
Concepts and techniques of graph neural network
\"This book will aim to provide stepwise discussion; exhaustive literature review; detailed analysis and discussion; rigorous experimentation results, application-oriented approach that will be demonstrated with respect to applications of Graph Neural Network (GNN). It will be written to develop the understanding of concepts and techniques on GNN and to establish the familiarity of different real applications in various domains for GNN. Moreover, it will also cover the prevailing challenges and opportunities\"-- Provided by publisher.
Book
Personality matters: does an individual's personality affect adoption and continued use of green banking channels?
PurposeTechnology has revolutionized banking, and “green banking” has been the most recent phenomenon to have caught the financial world's attention. In this paper, the authors look at how personality traits of individuals influence their adoption and continued use of green banking channels. The authors also propose a comprehensive model integrating the “big five” personality traits (conscientiousness, agreeableness, extraversion, openness and neuroticism) into the Technology Acceptance Model (TAM), along with expectation confirmation theory. The integrated proposed model is used in this longitudinal study to predict the continued use of green banking channels once adopted.Design/methodology/approachThe authors collected data during two time periods about 24 weeks apart from 826 green banking channel users from different regions in India. The data were analyzed using Structural Equation Modeling.FindingsThe authors found that traits of agreeableness, conscientiousness and extraversion favor an individual adopting green banking channels, while conscientiousness and openness were only associated with its perceived usefulness (PU).Research limitations/implicationsThe results offer valuable insights for understanding the adoption and use behavior of people regarding green banking channels. This study would help develop effective segmentation strategies for promoting green banking channels.Originality/valueBy incorporating the big five, along with TAM and Expectation Confirmation Model (ECM), coupled with “trust” as an additional construct, we believe that our study enlarges the boundaries of Information Technology (IT) theories, especially in the context of green banking channels. This study also contributes to advancing the personality theory by exploring how personality traits significantly relate to adopting and using green banking channels.
Journal Article
A systematic review on diabetic retinopathy detection and classification based on deep learning techniques using fundus images
Diabetic retinopathy (DR) is the leading cause of visual impairment globally. It occurs due to long-term diabetes with fluctuating blood glucose levels. It has become a significant concern for people in the working age group as it can lead to vision loss in the future. Manual examination of fundus images is time-consuming and requires much effort and expertise to determine the severity of the retinopathy. To diagnose and evaluate the disease, deep learning-based technologies have been used, which analyze blood vessels, microaneurysms, exudates, macula, optic discs, and hemorrhages also used for initial detection and grading of DR. This study examines the fundamentals of diabetes, its prevalence, complications, and treatment strategies that use artificial intelligence methods such as machine learning (ML), deep learning (DL), and federated learning (FL). The research covers future studies, performance assessments, biomarkers, screening methods, and current datasets. Various neural network designs, including recurrent neural networks (RNNs), generative adversarial networks (GANs), and applications of ML, DL, and FL in the processing of fundus images, such as convolutional neural networks (CNNs) and their variations, are thoroughly examined. The potential research methods, such as developing DL models and incorporating heterogeneous data sources, are also outlined. Finally, the challenges and future directions of this research are discussed.
Journal Article
Genome wide transcriptome analysis reveals vital role of heat responsive genes in regulatory mechanisms of lentil (Lens culinaris Medikus)
The present study reports the role of morphological, physiological and reproductive attributes viz. membrane stability index (MSI), osmolytes accumulations, antioxidants activities and pollen germination for heat stress tolerance in contrasting genotypes. Heat stress increased proline and glycine betaine (GPX) contents, induced superoxide dismutase (SOD), ascorbate peroxidase (APX) and glutathione peroxidase (GPX) activities and resulted in higher MSI in PDL-2 (tolerant) compared to JL-3 (sensitive).
In vitro
pollen germination of tolerant genotype was higher than sensitive one under heat stress.
In vivo
stressed pollens of tolerant genotype germinated well on stressed stigma of sensitive genotype, while stressed pollens of sensitive genotype did not germinate on stressed stigma of tolerant genotype.
De novo
transcriptome analysis of both the genotypes showed that number of contigs ranged from 90,267 to 104,424 for all the samples with N
50
ranging from 1,755 to 1,844 bp under heat stress and control conditions. Based on assembled unigenes, 194,178 high-quality Single Nucleotide Polymorphisms (SNPs), 141,050 microsatellites and 7,388 Insertion-deletions (Indels) were detected. Expression of 10 genes was evaluated using quantitative Real Time Polymerase Chain Reaction (RT-qPCR). Comparison of differentially expressed genes (DEGs) under different combinations of heat stress has led to the identification of candidate DEGs and pathways. Changes in expression of physiological and pollen phenotyping related genes were also reaffirmed through transcriptome data. Cell wall and secondary metabolite pathways are found to be majorly affected under heat stress. The findings need further analysis to determine genetic mechanism involved in heat tolerance of lentil.
Journal Article
Enhancement of Detection of Diabetic Retinopathy Using Harris Hawks Optimization with Deep Learning Model
In today’s world, diabetic retinopathy is a very severe health issue, which is affecting many humans of different age groups. Due to the high levels of blood sugar, the minuscule blood vessels in the retina may get damaged in no time and further may lead to retinal detachment and even sometimes lead to glaucoma blindness. If diabetic retinopathy can be diagnosed at the early stages, then many of the affected people will not be losing their vision and also human lives can be saved. Several machine learning and deep learning methods have been applied on the available data sets of diabetic retinopathy, but they were unable to provide the better results in terms of accuracy in preprocessing and optimizing the classification and feature extraction process. To overcome the issues like feature extraction and optimization in the existing systems, we have considered the Diabetic Retinopathy Debrecen Data Set from the UCI machine learning repository and designed a deep learning model with principal component analysis (PCA) for dimensionality reduction, and to extract the most important features, Harris hawks optimization algorithm is used further to optimize the classification and feature extraction process. The results shown by the deep learning model with respect to specificity, precision, accuracy, and recall are very much satisfactory compared to the existing systems.
Journal Article
Glycine betaine modulates chromium (VI)-induced morpho-physiological and biochemical responses to mitigate chromium toxicity in chickpea (Cicer arietinum L.) cultivars
Chromium (Cr) accumulation in crops reduces yield. Here, we grew two chickpea cultivars, Pusa 2085 (Cr-tolerant) and Pusa Green 112 (Cr-sensitive), in hydroponic and pot conditions under different Cr treatments: 0 and 120 µM Cr and 120 µM Cr + 100 mM glycine betaine (GB). For plants grown in the hydroponic media, we evaluated root morphological attributes and plasma membrane integrity via Evans blue uptake. We also estimated H
+
-ATPase activity in the roots and leaves of both cultivars. Plants in pots under conditions similar to those of the hydroponic setup were used to measure growth traits, oxidative stress, chlorophyll contents, enzymatic activities, proline levels, and nutrient elements at the seedling stage. Traits such as Cr uptake in different plant parts after 42 days and grain yield after 140 days of growth were also evaluated. In both cultivars, plant growth traits, chlorophyll contents, enzymatic activities, nutrient contents, and grain yield were significantly reduced under Cr stress, whereas oxidative stress and proline levels were increased compared to the control levels. Further, Cr uptake was remarkably decreased in the roots and leaves of Cr-tolerant than in Cr-sensitive cultivars. Application of GB led to improved root growth and morpho-physiological attributes and reduced oxidative stress along with reduced loss in plasma membrane integrity and subsequently increase in H
+
-ATPase activity. An increment in these parameters shows that the exogenous application of GB improves the Cr stress tolerance in chickpea plants.
Journal Article
Distinct environmental parameters influence the abundance of living benthic foraminifera morphogroups in the southeastern Arabian Sea
The ambient environmental parameters have a great bearing on the morphology of living flora and fauna. In this study, we tested this hypothesis on one of the most dominant groups of living unicellular marine microorganism, benthic foraminifera, in the dynamic region of the southeastern Arabian Sea. The living benthic foraminifera from 43 surface samples collected between 25 and 2980 m of water depth were segregated into eight morphogroups (tapered/cylindrical, flattened-ovoid, biconvex, planoconvex, flattened-tapered, spherical, rounded-trochospiral, and rounded-planispiral). We report that the high organic carbon availability is combined with deficiency of oxygen results in benthic foraminifera with low surface area to volume ratio and mostly consists of tapered/cylindrical, flattened-ovoid forms, with a preference for infaunal habitat. However, the tests of the living benthic foraminifera thriving in the oxygen-rich bottom waters have a high surface area to volume ratio, commonly reported as epifaunal, consisting of biconvex and planoconvex forms. Additionally, we also report that the abundance of other morphogroups, namely flattened-tapered, spherical, rounded-trochospiral, and rounded-planispiral, is also controlled by the distinct environmental parameters. We suggest that the living benthic foraminifera are an excellent indicator of the ambient environmental parameters and can be used to reconstruct paleoenvironments.
Journal Article
Age and entrepreneurship: Mapping the scientific coverage and future research directions
Researchers’ interest in studying the relationship between age and entrepreneurship has mushroomed in the last decade. While over a hundred articles are published and indexed in the Scopus database alone with varying and fragmented results, there has been a lack of effort in reviewing, integrating, and classifying the literature. This article offers a framework-based systematic review of 174 articles to comprehend the relationship and influencing factors related to an individual's age and entrepreneurship. Bibliographic coupling is used to identify the prominent clusters in the literature on this topic and the most influential articles. Also, the TCCM review framework is adopted to provide a comprehensive insight into dominant theories applied, contexts (geographic regions and industries) incorporated, characteristics (antecedents, consequences, mediating and moderating variables, and their relationships) investigated, and research methods employed in age and entrepreneurship research over the last fifteen (2007–2022). Though the literature covers an array of industries, to better understand the age-entrepreneurship correlation, we need to investigate the new-age technologically driven business sectors further to expand our knowledge. Furthermore, we detect that the Theory of Planned Behavior mostly dominates the literature, with other theories trivially employed. Finally, we apply the TCCM framework to suggest fertile areas for future research.
Journal Article
Privacy-preserving detection and classification of diabetic retinopathy using federated learning with FedDEO optimization
Diabetic retinopathy (DR) is a major cause of blindness among adults worldwide. Detecting and classifying DR early is essential for timely treatment and prevention of vision loss. This study introduces a new approach to identify and classify DR by using federated learning (FL) environment and Federated differential evolution optimization (FedDEO). FL enables collaborative learning across multiple decentralized devices while maintaining data privacy. FedDEO optimization enhances the model's performance by fine-tuning hyperparameters in a distributed manner. The research achieves state-of-the-art accuracy in DR classification using the MESSIDOR dataset for training and testing. The findings suggest that integrating FedDEO optimization within the FL framework can significantly improve DR detection, offering a scalable and privacy-preserving solution for ophthalmic healthcare. The FedDEO algorithm optimizes hyperparameters, including learning rates and batch sizes, to enhance model performance. The experiments show that FedDEO works effectively for the MESSIDOR dataset to achieve a high classification accuracy, specificity, recall, and F1-Measure of 96.98%, 98.12%, 97.12%, and 98.00% while preserving privacy. The results demonstrate that implementing these algorithms in an FL environment significantly improves privacy and performance compared to other approaches. Specifically, the proposed technique outperforms others in terms of accuracy, specificity, recall, and F1 score when applied to categorizing retinal images.
Journal Article
Addressing Binary Classification over Class Imbalanced Clinical Datasets Using Computationally Intelligent Techniques
Nowadays, healthcare is the prime need of every human being in the world, and clinical datasets play an important role in developing an intelligent healthcare system for monitoring the health of people. Mostly, the real-world datasets are inherently class imbalanced, clinical datasets also suffer from this imbalance problem, and the imbalanced class distributions pose several issues in the training of classifiers. Consequently, classifiers suffer from low accuracy, precision, recall, and a high degree of misclassification, etc. We performed a brief literature review on the class imbalanced learning scenario. This study carries the empirical performance evaluation of six classifiers, namely Decision Tree, k-Nearest Neighbor, Logistic regression, Artificial Neural Network, Support Vector Machine, and Gaussian Naïve Bayes, over five imbalanced clinical datasets, Breast Cancer Disease, Coronary Heart Disease, Indian Liver Patient, Pima Indians Diabetes Database, and Coronary Kidney Disease, with respect to seven different class balancing techniques, namely Undersampling, Random oversampling, SMOTE, ADASYN, SVM-SMOTE, SMOTEEN, and SMOTETOMEK. In addition to this, the appropriate explanations for the superiority of the classifiers as well as data-balancing techniques are also explored. Furthermore, we discuss the possible recommendations on how to tackle the class imbalanced datasets while training the different supervised machine learning methods. Result analysis demonstrates that SMOTEEN balancing method often performed better over all the other six data-balancing techniques with all six classifiers and for all five clinical datasets. Except for SMOTEEN, all other six balancing techniques almost had equal performance but moderately lesser performance than SMOTEEN.
Journal Article