Browse Items (16481 total)
Sort by:
-
Deep vs. Shallow: A Comparative Study of Machine Learning and Deep Learning Approaches for Fake Health News Detection
Internet explosion and penetration have amplified the fake news problem that existed even before Internet penetration. This becomes more of a concern, if the news is health-related. To address this issue, this research proposes Content Based Models (CBM) and Feature Based Models (FBM). The difference between the two models lies in the input provided. The CBM only takes news content as the input, whereas the FBM along with the content also takes two readability features as the input. Under each category, the performance of five traditional machine learning techniques: - Decision Tree, Random Forest, Support Vector Machine, AdaBoost-Decision Tree and AdaBoost-Random Forest is compared with two hybrid Deep Learning approaches, namely CNN-LSTM and CNN-BiLSTM. The Fake News Healthcare dataset comprising 9581 articles was utilized for the study. Easy Data Augmentation technique is used to balance this highly imbalanced dataset. The experimental results demonstrate that Feature Based Models perform better than Content Based Models. Among the proposed FBM, the Hybrid CNN - LSTM model had a F1 score of 97.09% and AdaBoost-Random Forest had a F1 Score of 98.9%. Thus, Adaboost-Random Forest under FBM is the best-performing model for the classification of fake news. 2013 IEEE. -
Effect of Organizational Culture during Crises on adoption of virtual classrooms: An extension of UTAUT model
This study aims to understand the impact of organizational culture in the context of obligatory adoption of a virtual classroom (VC) during the COVID pandemic. The academic crisis created by the pandemic resulted in obligatory adoption of VCs, without being mandated by top management. Organizational culture was tested by this crisis, and thus created a unique opportunity to examine adoption. This research examines Organizational Culture during Crises (OCC) as an antecedent to the Unified Theory of Acceptance and Use of Technology (UTAUT) model to evaluate the factors that determine the intention to adopt a virtual classroom across multiple disciplines by the faculty of a reputed Indian university. Data collected from a sample of 353 respondents was analyzed to test the research model using Structural Equation Modeling (SEM). The findings of the study reveal that OCC plays a positive and significant role in determining the intention of faculties to adopt a virtual classroom. We also found that OCC also significantly influences performance expectancy, effort expectancy, facilitating conditions and social influence. The results imply proper framing of policies by top management of Higher Education Institutions (HEI) for the smooth adoption of virtual classrooms by faculty when confronted by crises. 2021 The Author(s). Published with license by Taylor & Francis Group, LLC. -
Smart People Counting System by Enhancing Accuracy and Affordability with YOLOv5 and Cloud-Based Integration
Considering that all moving objects are humans, much of the work in data is based on recognizing and tracking moving objects. In this work, we present a method for counting peoples faces. Even though we use the face mask, the deep learning-based YOLOv5 algorithm and Faster R-CNN allow us to recognize the face. We do a very good job of counting people. To make the calculation more accurate, we introduced a new type of intelligent small scale computing system consisting of cheaper hardware and user-friendly cloud computing software. These findings show that intelligent computing systems can realize human vision. Additionally, by combining inexpensive hardware with cloud-based software, the planning process becomes more transparent and cost-effective. Finally, the web application allows users to view the number of authorized and unauthorized users. Based on the results obtained from this method, the deep learning YOLOv5 algorithm is used to identify and match human images to increase security, and thanks to cloud storage, users can easily view all calculated results, increasing the accuracy by 98.53%. Owing to the truth that most of the secure watches cannot be able to check each and each individual The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Search and analysis of giant radio galaxies with associated nuclei (SAGAN): III. New insights into giant radio quasars
Giant radio quasars (GRQs) are radio-loud active galactic nuclei (AGN) that propel megaparsec-scale jets. In order to understand GRQs and their properties, we have compiled all known GRQs (the GRQ catalogue) and a subset of small (size < 700 kpc) radio quasars (SRQs) from the literature. In the process, we have found ten new Fanaroff-Riley type-II GRQs in the redshift range of 0.66 < z < 1.72, which we include in the GRQ catalogue. Using the above samples, we have carried out a systematic comparative study of GRQs and SRQs using optical and radio data. Our results show that the GRQs and SRQs statistically have similar spectral index and black hole mass distributions. However, SRQs have a higher radio core power, core dominance factor, total radio power, jet kinetic power, and Eddington ratio compared to GRQs. On the other hand, when compared to giant radio galaxies (GRGs), GRQs have a higher black hole mass and Eddington ratio. The high core dominance factor of SRQs is an indicator of them lying closer to the line of sight than GRQs. We also find a correlation between the accretion disc luminosity and the radio core and jet power of GRQs, which provides evidence for disc-jet coupling. Lastly, we find the distributions of Eddington ratios of GRGs and GRQs to be bi-modal, similar to that found in small radio galaxies (SRGs) and SRQs, which indicates that size is not strongly dependent on the accretion state. Using all of this, we provide a basic model for the growth of SRQs to GRQs. ESO 2022. -
Wearable Smart Technologies: Changing the Future of Healthcare
Wearable smart technologies are the innovative solutions for the issues of healthcare services. In this chapter, a review of the innovative wearable healthcare devices and applications has been done. Wearable devices are used for supervision and illness control. These innovative wearable technologies can straightforwardly affect the medical dynamic, can upgrade the quality of treatment for patients, and can reduce the expenses incurred in it. The large health record generated by the wearable devices provides an opportunity for data analysts to apply machine learning techniques for prediction on the data generated by sensors. Today's wearable smart technologies are capable of being integrated into eyeglasses, cloths, shoes, belts, watches, etc. Sensors can be inserted in these objects to be worn. The advanced forms of wearable technologies can be attached to the skin of the wearer. A smartphone is mainly utilized to collect data and communicate it to a server situated at a remote area for greater capacity and investigation. Maximum innovations related to wearable technologies are still in the prototyping phase. The study covers almost every aspect of wearable technologies, which could be helpful in the future for innovation and research in this area. 2024 selection and editorial matter, Ankur Beohar, Ribu Mathew, Abhishek Kumar Upadhyay, and Santosh Kumar Vishvakarma -individual chapters, the contributors. All rights reserved. -
Impact of Work from Home During COVID-19 Scenario
In view of the recent situation, COVID-19 has spread across the world, and every country has to enforce a lockdown to prevent the virus from transmitting further. The worldwide COVID-19 outbreak has led to a large number of professionals work from their homes. Almost all the sectors like IT, academics, government, business, etc. are implementing work from home for safety of their employees and sincerely obeying the social distancing norms. Work from home can be beneficial and fruitful in terms of travel expenses, saving time commuting, working on ones own agenda, etc. But it can also be a pain and take a toll on mental well-being as you are living a quarantined life with little to no social life, which can also impact an individuals efficiency. There are so many barriers to work from home (WFH), like unavailability of resources, poor network connectivity, using digital platform and latest software for non-IT professionals, lack of proper infrastructure, etc. Our chapter focuses on every aspects of WFH during the COVID-19 lockdown period so that well-suited policies and practices can be designed to cope with the issues and hence transforming future of organizations by shifting the tradition of work from office to work from home. 2024 Apple Academic Press, Inc. All rights reserved. -
Strength and durability properties of geopolymer paver blocks made with fly ash and brick kiln rice husk ash
In India the generation of agro waste rice husk ash is abundant. The utilization of rice husk ash in development of geopolymer binders can be suitable to alleviate the environmental problems associated with disposal of rice husk ash. Further, the utilization of rice husk ash generated from the stacks of brick kilns has not been addressed in past, particularly in development of geopolymer binders. This study proposes development of geopolymer paver (GEOPAV) blocks utilizing brick kiln rice husk ash (BKRHA). It presents fresh, mechanical and durability properties of GEOPAV blocks blended with fly ash, BKRHA, natural aggregates, NaOH and Na2SiO3 solution, and cured in both sundry and room temperature conditions. Microstructural analysis using scanning electron microscope (SEM) and X-ray diffraction (XRD) was adopted to study the influence of BKRHA on hardened properties of GEOPAV blocks. The results show that addition of BKRHA reduce the workability of GEOPAV mixes due to micro porous surface with honeycombed structure of BKRHA particles. The addition of BKRHA showed negligible improvement in compressive strength of GEOPAV blocks. However, the major advantage was observed with improved split tensile strength and flexural strength for GEOPAV blocks with BKRHA. Further, the durability properties in terms of resistance to acid and frost attack was significantly improved with the addition of BKRHA in GEOPAV blocks. Such improvements can be attributed to high amounts of amorphous silica in BKRHA which contribute towards dissolution and formation of polymeric gel, and thereby serve as a binder to enhance the geopolymer matrix making it dense. Finally, all the developed GEOPAV blocks satisfy the IS 156582021 specification requirements and perform much better when compared to commercially available paver blocks. 2021 The Authors -
Performance analysis of different classifier for remote sensing application
The classification of remotely sensed data on thematic map is a challenging task from very long time and it is also a goal of todays remote sensing because of complexity level of earth surface and selection of suitable classification technique. Hence selection of best classification technique in remote sensing will give better result. Classification of remotely sensed data is an important task within the domain of remote sensing and it is outlined as processing technique that uses a systematic approach to group the pixels into different classes. In this study, we have classified the multispectral data of Udupi district, Karnataka, India using different classifier including Support Vector Machine (SVM), Maximum Likelihood, Minimum Distance and Mahalanobis Distance classifier. The data of dimension 3980x3201 pixels are collected from a Landsat-3 satellite. Performance of the each classifier is compared by conducting accuracy assessment test and Kappa analysis. The obtained results shows that SVM will give accuracy of 95.35% and kappa value of 0.9408 respectively when compared other classifier, hence effectiveness of SVM is a good choice for classifying remotely sensed data. BEIESP. -
Land Use/Land Cover (LULC) Change Classification for Change Detection Analysis of Remotely Sensed Data Using Machine Learning-Based Random Forest Classifier
Land Use and Land Cover (LULC) classification is critical for monitoring and managing natural resources and urban development. This study focuses on LULC classification for change detection analysis of remotely sensed data using a machine learning-based Random Forest classifier. The research aims to provide a detailed analysis of LULC changes between 2010 and 2020. The Random Forest classifier is chosen for its robustness and high accuracy in handling complex datasets. The classifier achieved a classification accuracy of 86.56% for the 2010 data and 88.42% for the 2020 data, demonstrating an improvement in classification performance over the decade. The results indicate significant LULC changes, highlighting areas of urban expansion, deforestation, and agricultural transformation. These findings highlight the importance of continuous monitoring and provide valuable insights for policymakers and environmental managers. The study demonstrates the effectiveness of using advanced machine-learning techniques for accurate LULC classification and change detection in remotely sensed data. 2025 by the authors. -
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. -
Optimized uplink scheduling model through novel feedback architecture for wimax network
Broadband Wireless Access has drawn the fine attention due to the wide range of data requirement and user mobility all the time. Moreover, WiMAX provides the best QoE (Quality of Experience) which is based on the IEEE 802.16 standards; this includes several services such as data, video and audio. However, in order to provide the effective and smooth experience i.e. QoS scheduling plays one of the critical part. In past several mechanism has been proposed for effective scheduling however, through the research it is observed that it can be furthermore improvised hence in this we propose a mechanism named as OUS (Optimized Uplink Scheduling) which helps in improvising the QoS. In here, we have proposed a novel feedback architecture and proposed optimized scheduling which helps in computing the bandwidth request this in terms helps in reducing the delay as well as jitter. Moreover, the performance evaluation is performed through extensive simulation by varying the different SS and frequency and the results analysis confirms that our mechanism performs way better than the existing algorithm. BEIESP. -
Adaptive uplink scheduling model for WiMAX network using evolutionary computing model
The increased usage of smart phones has led to increase usage an internet based application services. These application requires different quality of service (QoS) and bandwidth requirement. WiMAX is an efficient network to provision high bandwidth connectivity and coverage to end user. To meet QoS requirement the exiting model used adaptive model selection scheme. However, these model induce bandwidth wastage as it does not considers any feedback information for scheduling. This work present an Adaptive Uplink Scheduling (AUS) by optimizing MAC layer using Multi-Objective Genetic Algorithm (MOGA). The MAC scheduler use feedback information from both physical layer and application layer. Further, to meet QoS requirement of application and utilize bandwidth efficiently this paper presented an adaptive modulation selection scheme based on user application requirement using MOGA. Our model provides application level based QoS provisioning for WiMAX network. Experiment are conducted to evaluate performance of AUS over exiting model. The overall result attained shows AUS model attain good performance in term of throughput, successful packet transmission and packet collision. 2019 Institute of Advanced Engineering and Science. All rights reserved. -
Evalutionary compting model for QoS provisioning in WiMAX
In recent time wireless technology is adopted widely for connecting remote user over network. WiMAX is an attractive technology for provisioning high data rate connectivity and coverage. QoS is a required parameter for analyzing the system performance. Before allocation of the bandwidth in the network, physical layer information is required for improving QoS performance. Many modulation techniques are used in WiMAX network. An adaptive approach is required for selection of modulation scheme to maximize network performance. Physical layer information is used for selection of modulation scheme. An adaptive genetic based scheduling is proposed in this paper for improved QoS. Experiments are conducted to evaluate performance of proposed approach in term of throughput, successful transmission and packet collision over existing approach. The outcome shows significant performance over existing approach. 2017 IEEE. -
A new facile synthesis of (2S,5S)-5-hydroxypipecolic acid hydrochloride
A simple and efficient synthesis of (2S,5S)-5-Hydroxypipecolic acid hydrochloride is reported. The key features of the synthesis involve the asymmetric reduction of ketone using (S)-CBS oxazaborolidine and the use of commercially available methyl pyroglutamate as a starting material.. 2022 Taylor & Francis Group, LLC. -
Convolutional Neural Networks for Automated Detection and Classification of Plasmodium Species in Thin Blood Smear Images
There has been a continued transmission of malaria throughout the world due to protozoan parasites from the Plasmodium species. As for treatment and control, it is very important to make correct and more efficient diagnostic. In order to observe the efficiency of the proposed approach, This Research built a Convolutional Neural Network (CNN) model for Automated detection and classification on thin blood smear images of Plasmodium species. This model was built on a corpus of 27558 images, included five Plasmodium species. Our CNN model got an overall accuracy of 96% for the cheating detection with an F 1score of 0.94. In the detection of the presence of malaria parasites the test accuracy conducted was as follows: 8%. Species-specific classification accuracies were: P. falciparum (95.7%), P. vivax (94.9%), P. ovale (93.2%), P. malaria (92.8%) and P. Knowles (91, 5%). As for the model SL was found to have sensitivity of 97.3% And the specificity in this case is 9 6. 1 %. The proposed CNN-based approach provides a sound and fully automated solution for malarial parasite detection and species determination, which could lead to better diagnostic performances in day-to-day practices. 2024 IEEE. -
Integration of sustainability in business through finance
[No abstract available] -
Consumers Perspective Toward Fintech Disruption in Financial ServicesA Structural Equation Modeling Approach
For nearly a decade, banks have faced an unprecedented array of challenges, with shrinking revenues and intense pressure from consumers and regulators. Compounding this tough environment is a powerful new force that has emerged to challenge banks, financial technology (FinTech) firms. These innovative start-ups are striving to take a share of financial services customers, products, and revenue. Financial Consumer Demands for Tomorrows Digital Bank, investigated what consumers value from their main financial service provider and how well banks are meeting consumers needs. The study revealed a demand for value-added services that supplement traditional banking products, while also solidifying the importance of seamless, anytime/anywhere, omni-channel service channels. This study is such an attempt to analyze the consumer perspective based on the Fintech Disruption in Financial Services in Pune city among 150 respondents. The tools used for this study are ANOVA, regression analysis, and structural equation modeling (SEM). Hence, this study concludes that financial institutions have a lot on their plate: emerging competitors, shifting demographics, rising customer expectations, and changing regulations. Technology offers solutions, allowing financial institutions to cut costs and become more efficient at what they do. 2025 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Mathematical and prosodic analysis of intonation in Malayalam
This study investigates the intonation patterns of Malayalam, a language spoken in Kerala, India, using polynomial regression and Kernel Density Estimation. Malayalam has distinct pitch modulation patterns across genders and question types, with variations in acoustic features, syllables, and stress structures. We examine the mean pitch characteristics of different question types and analyze the correlation between stress patterns and syllable structure counts in the language. Additionally, we perform clustering analysis on Malayalam words to highlight similarities and diversities in acoustic features, which helps us understand the phonetic diversity within the language. Our analysis shows that the overlap of KDE curves in the feature space allows us to analyze the linguistic factors that influence variability in Malayalam speech. This suggests a need for further research on regions where syllable complexity and phonological patterns are notably concentrated. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025. -
Artificial intelligence in education: A pathway to achieving SDG 4
Artificial Intelligence (AI) has emerged as a transformative force in education, offering innovative solutions to some of the most pressing challenges in the global education system. As the world strives to achieve the United Nations Sustainable Development Goals (SDGs), particularly SDG 4 (Quality Education), AI offers significant potential to enhance educational access, equity, and quality. This chapter explores the intersection of AI and education with a focus on how AI can contribute to the achievement of SDG 4. The chapter examines the role of AI in personalizing learning, promoting equity and inclusion, enhancing teacher effectiveness, and fostering global collaboration for sustainability. AI's ability to deliver personalized learning experiences is one of its most significant contributions to education. Through adaptive learning platforms and intelligent tutoring systems, AI can tailor educational content to meet the unique needs of individual students, ensuring that learning is accessible and engaging for all. 2026, IGI Global Scientific Publishing. All rights reserved. -
Data-Driven Decision Making in the VUCA Context: Harnessing Data for Informed Decisions
Data-driven decision making (DDDM) has evolved from being a strategic advantage to a necessity for organizations aiming to thrive in the dynamic business contexts. It is about using data as a tool to enhance strategic thinking, scenario planning, and adaptation in rapidly changing environments. It involves leveraging data and analytics to navigate the challenges of volatility, uncertainty, complexity, and ambiguity. By embracing DDDM, organizations can enhance their decision-making processes, gain a competitive edge, and navigate the challenges of volatility, uncertainty, complexity, and ambiguity with greater confidence. However, successful implementation requires addressing challenges, fostering a data-driven culture, and continually adapting best practices to meet the evolving demands of the VUCA environment. This chapter discusses how organizations leverage DDDM in VUCA context to support effective and rapid decision making aligned with organizations vision. Particularly, it would offer insights to transit from volatility to vision, uncertainty to understanding, complexity to clarity, and ambiguity to agility. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.