Browse Items (16488 total)
Sort by:
-
Ear Recognition Using ResNet50
Deep learning techniques have become increasingly common in biometrics over the last decade. However, due to a lack of large ear datasets, deep learning models in ear biometrics are limited. To address this drawback, researchers use transfer learning based on various pre-trained models. Conventional machine learning algorithms using traditional feature extraction techniques produce low recognition results for the unconstrained ear dataset AWE. In this paper, an ear recognition model based on the ResNet-50 pretrained architecture outperforms traditional methods in terms of recognition accuracy in AWE dataset. A new feature level fusion of ResNet50 and GLBP feature is also experimented to improve the recognition accuracy compared to traditional features. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Ear Recognition Using Rank Level Fusion of Classifiers Outputs
An individuals authentication plays a vital role in our daily life. In the last decade, biometric-based authentication has become more prevalent than traditional approaches like passwords and pins. Ear recognition has gained attention in the biometric community in recent years. Researchers defined several features for the identification of a person from ear image. The features play a vital role in the success of classification models. This paper considers an ensemble of features for designing a new classification model. The features are assessed in isolation as well as through feature-level fusion. Subsequently, a rank-level fusion for classification is introduced. The experiments are conducted on both constrained and unconstrained ear datasets. The results are promising and open up new possibilities in machine learning-based ear recognition 2023, International journal of online and biomedical engineering.All Rights Reserved. -
Ear Recognition Using Pretrained Convolutional Neural Networks
Ear biometrics, which involves the identification of a person from an ear image, is challenging under unconstrained image capturing scenarios. Studies in Ear biometrics reported that the Convolutional Neural Network is a better alternative to classical machine learning with handcrafted features. Two major concerns in CNN are the requirement of enormous computing resources and large datasets for training. The pretrained network concept helps to use CNN with smaller datasets and is less demanding on hardware. In this paper, three pre-trained CNN models, AlexNet, VGG16, and ResNet50 are used for ear recognition. The fully connected classification layers of the nets are trained with AWE, an unconstrained ear dataset. Alternatively, the CNN layers output (the CNN features) are extracted, and an SVM classification model is built. To improve the classification accuracy, the training dataset size is increased through data augmentation. Data augmentation improved the classification accuracy drastically. The results show that ResNet50, with the fully connected classification layer, results in higher accuracy. 2021, Springer Nature Switzerland AG. -
Eagle Strategy Arithmetic Optimisation Algorithm with Optimal Deep Convolutional Forest Based FinTech Application for Hyper-automation
Hyper automation is the group of approaches and software companies utilised to automate manual procedures. Financial Technology (FinTech) was processed as a distinctive classification that highly inspects the financial technology sector from a broader group of functions for enterprises with utilise of Information Technology (IT) application. Financial crisis prediction (FCP) is the most essential FinTech technique, defining institutions financial status. This study proposes an Eagle Strategy Arithmetic Optimisation Algorithm with Optimal Deep Convolutional Forest (ESAOA-ODCF) based FinTech Application for Hyperautomation. The ESAOA-ODCF technique has achieved exceptional performance with maximum accu y of 98.61%, and F score of 98.59%. Extensive experimental research revealed that the ESAOA-ODCF model beat more modern, cutting-edge approaches in terms of overall performance. 2023 Informa UK Limited, trading as Taylor & Francis Group. -
E-shopping orientation, trust and impulse buying in the online context a study based on female members of Generation Z in India
A large number of studies have attempted to understand consumer behaviour in the online context. One construct that has been of particular interest to marketers, retailers and researchers, is impulse buying behaviour. The number of studies attempting to understand the drivers of impulsive purchases has been on a rise. The current pandemic also saw a rise in impulsive purchases and the interest in the construct was renewed. The current study is based on the S-O-R model and evaluates the relationship between e-shopping orientation, trust and impulse buying behaviour. The findings are based on data collected from female members of Generation Z and suggest that frequent visits to e-retail stores and increased patronage can increase the level of trust in the retail partner and influence the number of impulsive purchases. The findings are particularly significant for retailers looking to drive sales through impulsive purchases. In addition, the findings provide empirical support for the application of the S-O-R model to online retail context. Copyright 2024 Inderscience Enterprises Ltd. -
E-service quality-impact on customer satisfaction
The paper aims to determine the impact of e-service quality on customer satisfaction. The study utilised data from 252 customers of private and public banks in India through questionnaires. It was found that the e-service quality has significant impact on customer satisfaction in public sector banks as well as private sector banks. 2019 SERSC. -
E-Mentoring PhD Scholars for Successful Research and Publication: A Qualitative Study
With advancements in digital communication, e-mentoring has become an essential tool in higher education, bridging geographical gaps and facilitating real-time interactions between mentors and scholars. The study attempts to examine the merits of e-mentoring for PhD scholars in their research and publication journey. The present study employed qualitative phenomenological approach and collected data through in-depth semi structured interviews. Through word-of-mouth approach researchers reached out to 8 PhD scholars, who used more tele and video conferencing platform to reach out to their supervisors and other resource persons. A valid interview guide has been used to collect the data. Study employed narrative thematic analysis technique to interpret the data. Findings revealed that, e-mentoring positively supported the research scholars in successfully completing their research and publication work and found it saved time, travel cost, and reduced anxiety. Future researchers may focus on application of e-mentoring in distance education.. 2026 by IGI Global Scientific Publishing. All rights reserved. -
E-Learning Recommender System for Deaf and Hard of Hearing Learners
People with disabilities, including deaf and hard of hearing (DHH), face numerous resources online and need support to choose the right learning materials according to their preferences in communication and learning style. Content recommendation engines may help the DHH learners by suggesting the best possible matching resources to find out the suitable learning materials according to the preferences of learners. Content recommenders that use tag-based clustering techniques reduce the search space by filtering learning objects that match users search keywords at the first level and then present the learning objects with the specified accessibility preferences in terms of communication and learning style in the next level. This chapter presents a detailed study focusing on the tag-based content recommender systems in the e-Learning domain that support learners with sensory impairment, especially DHH learners. 2025 selection and editorial matter, Urmila Shrawankar and Prerna Mishra; individual chapters, the contributors. -
E-learning During COVID-19Challenges and Opportunities of the Education Institutions
As part of the COVID-19 lockdown, educational institutions were closed and adopted e-learning to keep the learning process going. Due to the COVID-19 pandemic, e-learning has become a required component of all educational institutions such as schools, colleges, and universities worldwide. This pandemic has thrown the offline teaching process into chaos. This chapter discusses the concept and role of e-learning during the pandemic and various challenges and opportunities of e-learning encountered by educational institutions. Three broad challenges identified in e-learning are inaccessibility, self-inefficacy, and technical incompetency. E-learning opportunities are no geographic barriers, flexibility, creativity, and critical learning incorporation increased utilization of online resources and reinforced distance learning. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
E-leadership, psychological contract and real-time performance management: Remotely working professionals
Using the model of E- Leadership in Virtual teams (Avolio et al.), this paper examines impact of Psychological Contract, mediated by E-leadership, on Real-time Performance Management of Remotely working professionals. Following a quantitative research method, data was collected from 57 remotely working professional across the world. Significant positive relationships were found among Leadership Effectiveness of E-leaders, Relational Psychological Contract and Efficiency of RPM. The results confirm the interaction of the given variables in Avolio's Model of E-leadership, highlighting technological aspects of human interactions and ways to optimise them. The results underline several important managerial implications for effective leadership, fulfilling psychological contract and effective performance management, of a type of workforce that is only virtually available. 2019 SCMS Group of Educational Institutions. All rights reserved. -
E-government and e-governance: Driving digital transformation in public administration
E-Governance is crucial for enhancing government efficiency, transparency, and accessibility by digitizing public services and processes. This article explores the pivotal role of e-Government and e-Governance in transforming public administration through digital technologies. It examines how governments worldwide are leveraging information and communication technologies (ICTs) to improve the efficiency, transparency, and accessibility of public services. The study addresses key challenges such as the digital divide, cybersecurity, and the adoption of emerging technologies like artificial intelligence (AI) and blockchain in governance. Through a comprehensive review of e-Government initiatives and their impact on public sector efficiency, this paper offers solutions and recommendations for policymakers and highlights the broader implications for both academia and industry. Future research directions are also proposed to advance the understanding of digital governance frameworks in a rapidly evolving technological landscape. 2025, IGI Global Scientific Publishing. -
E-governance service quality and effective e-governance: A qualitative evaluation of telecentres of Karnataka /
Asian Journal of Research in Social Sciences and Humanities, Vol. 7, Issue 3, pp. 1272-1288, ISSN: 2249-7315. -
E-governance diffusion in the telecenters of Karnataka-a gender analysis
E-governance is the interaction between a government and its citizens to deliver services in an efficient manner by means of information technology and telecommunication. The current study takes into account three aspects namely-economical, governance and services that impact the e-governance diffusion in the telecenters set up at the hobli level of Karnataka state. A framework is created with these aspects and validated through the present study. The study explores whether gender differentials exist in the e-governance diffusion process. The research adds up to the literature in establishing that gender differentials disappear when the e-governance is in the stage of maturity. One-way ANOVA is used to identify the gender differentials in e-governance diffusion through the NadaKacheri centres of Karnataka. The study proposes policy changes by the government to render better services and governance to the citizens. 2017 Inderscience Enterprises Ltd. -
E-governance diffusion in the telecenters of Karnataka - a gender analysis /
International Journal of Business Information Systems, Vol.24, Issue 4, pp.452-468, ISSN: 1746-0980 (Print), 1746-0980 (Online). -
E-Development and Sustainable Management Education for Effective Leadership and Sustainable Society
Electronic development is the process of systematic evolution for mankind and society at large that ensures the overall progress of the electronic mode of learning, education, healthcare, society, and corporate governance. The main objective of the chapter was to address the impacts of e-development and sustainable management education for effective leadership that leads to constructing a sustainable society. The required data were collected both from primary and secondary sources. Primary data were collected from 120 respondents. The secondary data sources included official websites. The study is empirical and various statistical tools like mean, standard deviation, and t-test were executed for data analysis. The results of the research study were indicated the high degree and low degree of contribution from e-development and sustainable management education are not significant between effective leadership and sustainable society. E-development can be effective for creating a sustainable society with the goal setting of improving effective leadership skills. Copyright 2022, IGI Global. -
E-Commerce in Indian Retail Industry: Its Proliferation and Performance
The growth of the e-commerce industry in India has seen a multitude of growth since the growth of netizens in India has reached its peak post the demonetization in Indian economy. Research in e-commerce acts as a catalyst for studies in the field of digital innovation. The developments made by India in the field of e-commerce are notable by the world. India has made extensive use of the advancement in the field of technology. Recent years have seen a transformation in the way Indian shops and exchanges grew from cash mode payments to digital mode of service delivery and payments. This research is focused on studying the parameters that have acted as impetus in the expansion of e-commerce in the Indian retail sector. 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
E-Commerce data analytics using web scraping
Some companies, like Twitter and others, provide an application programming interface (API) to fetch the information. If the API is not available, we will have to search other websites to get the data in a structured format. The primary way to get data from a web page is through web scraping. The basic idea of web scraping is to pull data from a website and convert it into a format that can be used for analysis. In this paper, we will discuss the simple explanation of how we can use Beautiful Soup to scratch data into Python and later save the extracted data in an Excel spreadsheet and do the spreadsheet analysis later. We will pull data from the Flipkart website to know the cell phone name, cell phone price, cell phone rating, and cell phone specification. 2023 Scrivener Publishing LLC. -
E-Commerce and Consumer Trust Impact of Industry 4.0 on MSME Sales and Business Practices in India
The role of Industry 4.0 in business practices and consumer preference is gaining high importance in Indias MSME economy. This study examines if e-commerce implementation has influenced MSMEs sales volume, which encouraged them to shift from offline to online business. This study suggests global regulatory norms to promote e-commerce practices in consumer markets. In order to study this issue, data from 407 respondents were collected and processed using advanced statistical software IBM SPSS and AMOS, paying special attention to the inter-relation between Industry 4.0 interventions and consumer behavior. Advanced statistical software, including Structural Equation Modeling and path analysis, describe how Industry 4.0 influences company practices, consumer confidence, and sales in the MSME economy. Advanced research demonstrates high inter-relation between Industry 4.0-initiated improvement and consumer confidence, and they demonstrate insights into complexity about how technological innovations influence corporate operations and consumer attitudes. Findings of this study demand stringent regulations that enhance effective standards and consumer psycho-logical well-being in e-commerce. This study contributes to the building block of effective utilization of e-commerce in Indias fast-evolving industry, and it stresses the top priority for comprehensive frameworks that address the challenges emerging from advanced technologies. Firms can navigate complexity in e-commerce interactions better by acknowledging the implications and establishing trust. Lastly, this study highlights the key role of e-commerce in shaping consumer behavior and demands global regulatory norms to make e-commerce practices in consumer markets effective and sustainable. Findings provide a road map to policymakers and firms to frame and implement policies that enhance customer confidence and encourage long-term prosperity in the MSME economy. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Dysgraphia Disorder Detection and Classification Using Deep Learning Technique
Dysgraphia, a neurological condition, impedes childrens acquisition of standard writing abilities, leading to subpar written expression. Inadequate or underdeveloped writing proficiency can adversely affect a childs educational progress and self-esteem. To address this issue, our study involved compiling a novel dataset of handwritten operations and extracting an array of features to encapsulate the various dimensions of handwriting characteristics. This research presents the Rotational Region Convolutional Neural Network (R2CNN) as a novel approach to tackle this issue. The R2CNN framework integrates a multitask refinement network for accurate tilted box detection and a text region proposal network (Text RPN) to identify potential text areas. To address the imbalance in the training categories and mitigate the overpopulation problem through feature elimination, a balance parameter is incorporated into the loss function. This research focused on identifying dysgraphia by analyzing these extracted features, which included both handwriting and geometric elements. The feature-learning stage of deep transfer learning effectively extracts and applies characteristics to identify dysgraphia. Research findings indicate that this study can use handwritten images to detect dysgraphia in children. The results of the data-gathering process show that this investigation can leverage samples of handwritten text to recognize dysgraphia among young individuals. The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025. -
Dynamics of the Dadras-Momeni System in the Frame of the Caputo-Fabrizio Fractional Derivative
Investigation of chaos in dynamical systems is one of the most fascinating issues that has received a lot of attention across a variety of scientific domains. One such dynamical system which generates two, three, and four-scroll chaotic attractors with a single parameter change, is the novel Dadras-Momeni system. In this study, we have analyzed the Dadras-Momeni system in the frame of the Caputo-Fabrizio fractional derivative. Theoretical aspects such as boundedness, existence, and uniqueness of solutions are presented. A detailed analysis is presented regarding the stability of points of equilibrium. To regulate chaos in this fractional-order system with unpredictable dynamics, a sliding mode controller is developed and the global stability of the system with control law is established. Later, we introduced uncertainties and external disturbances to the controlled system, and the condition of global stability is derived. To perform numerical simulation we have identified certain values of the parameters where the system exhibits chaotic behavior. Then the theoretical claims about the influence of the controller on the system are established with the help of numerical simulations. 2023 Taylor & Francis Group, LLC.