Browse Items (16481 total)
Sort by:
-
Deploying Deep Learning in Real-Time for Lung Cancer Diagnosis via Medical Imaging
In this research, deep learning models were used to diagnose lung cancer automatically using hospital image data. A dataset with 3,400 lung cancer images from online repositories and hospital archives was used for model training and evaluation. After preprocessing and feature extraction, various deep learning architectures such as VGG-16, CNN, ResNet and RNN were adopted in this study. The VGG-16 model had the highest accuracy rate of 96.86%, showing strong performance. This rate of accuracy is actually higher than their accuracy of 91%. These results serve to highlight the impressive accuracy achieved by our study relative to prior research. By accurately and effectively altering lung cancer diagnosis into a process entirely reliant on algorithms, deep learning models show promise for their potential. Diagnostic tools should be able to catch cancer early and accurately, identify the present type and classification for tumors. For all its promise, limitations such as dataset size and generalizability mean that clinical trials will be needed for further validation. Focus should turn toward this as the direction of future research in order to enhance model robustness and applicability against challenges. This research allows us to better the well-being of patients and reduce the burden of lung cancer through timely intervention and personalized treatment strategies by making use of advanced techniques in medical diagnostics. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Deploying a Multi-Model Forecasting System for Bitcoin Prices: Bridging Statistical Forecasting and Deep Learning Innovations
In this study, we investigate and compare several forecasting models for predicting Bitcoin market prices using historical data sourced from Nasdaq Data Link (formerly Quandl) spanning from 2016 to 2025. Our analysis evaluates traditional time series methods - such as ARIMA and Holt Winters exponential smoothing - alongside modern machine learning and deep learning techniques including LSTM, Prophet, XGBoost, SVR, Random Forest, and GRU. Performance was assessed via metrics such as RMSE, MAE, MAPE, sMAPE, directional accuracy, and R-squared. Our experiments reveal that while classical methods (e.g., ARIMA and Holt Winters) exhibit large estimation errors and limited explanatory capacity, advanced neural network architectures - particularly the GRU - demonstrate superior accuracy with an RMSE of 2,505.84, MAE of 1,760.93, MAPE of 2.79%, and an R-squared of 0.99. The best-performing model (GRU) was deployed as a web application on PythonAnywhere, providing real-time forecasts through an interactive dashboard. This deployment not only validates the predictive efficacy of the GRU model but also offers a practical tool for investors and financial analysts to monitor and predict Bitcoin price movements using reliable Nasdaq data. 2025 IEEE. -
Deployable Solution for Real-Time Children Face Emotion Prediction System
Nowadays, many parents struggle to comprehend their children's emotions, which can hinder the creation of a nurturing environment. While numerous models focus on predicting adult emotions, there is a lack of standardised datasets for studying children's emotions. To address this gap, our work attempts to establish a comprehensive children's emotion dataset that can facilitate the study of emotions across various pose orientations. Furthermore, we propose an efficient and deployable system for real-time children's emotion prediction. An effective face detector with deep architecture is designed to handle all pose orientations from key image frames. Optimal features are then selected by re-ranking the features using a hybrid feature selection mechanism. The emotion category is declared by carefully analysing sequences of emotion identification from these features. This system holds promise for educational institutions and healthcare facilities, offering insights into children's behaviour through emotional analysis. Through experimental comparisons with three state-of-the-art emotion prediction models, we observed that our proposed system consistently outperforms existing models. Hence, we strongly recommend the adoption of our proposed system. With its achievement of state-of-the-art results in children's facial emotion recognition, it offers a practical solution for real-time deployment across diverse settings. The Author(s), under exclusive license to Springer Nature Switzerland AG 2025. -
Depletion studies in the interstellar medium
We report interstellar Si depletion and dust-phase column densities of Si along 131 Galactic sight lines using previously reported gas-phase Si II column densities, after correcting for the differences in oscillator strengths. With our large sample, we could reproduce the previously reported correlations between depletion of Si and average density of hydrogen along the line of sight () as well as molecular fraction of hydrogen (f(H2). We have also studied the variation of amount of Si incorporated in dust with respect to different extinction parameters. With the limitations we have with the quality of data, we could find a strong relation between the Si dust and extinction. While we cannot predict the density dependent distribution of size of Si grains, we discuss about the large depletion fraction of Si and the bigger size of the silicate grains. 2013 AIP Publishing LLC. -
Depiction ofNifty Midcap Index Efficiency Using ARIMA
In recent years, the desirability of midcaps in Indian stock markets has received considerable attention from researchers, academicians, and financial analysts due to expectation of multi-bagger returns. The present study is undertaken to determine the market efficiency of Indian stock market using Nifty Midcap Index at High Frequency. The market efficiency of Nifty Midcap Index is determined using ARIMA technique. The fitted ARIMA model had a MASE value close to one. Hence, the findings suggest that the Nifty Midcap Index is inefficient. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Dependence of Eigen frequency on the output performance of a piezoelectric nano sensor: A comparative study
Energy harvesting is an approach to generating electricity that uses the energy of the local environment directly. Instead of relying on batteries or power generated elsewhere, the world needs a new generation of energy-producing products. Generation or accumulation and energy consumption must be balanced when designing such a system. Before implementation into the real world, simulations are available for optimizing device designs, comparing them, predicting them, and formulating methodologies. In this comparative study, using a finite element simulation software COMSOL Multiphysics, an Eigen frequency analysis is performed to validate the relationship between Eigen frequency and output voltage and also shows how much the selection of a piezo electric base material depends on the natural frequency, excitation frequency, and output voltage relationship. A piezoelectric sensor is constructed with an initial base material and using material sweeps, another six materials are added and switched for the purpose. After applying allowable stress and frequency analysis, measured the output electric potential for the first five eigenmodes. Selecting seven different piezo electric base materials that possess unique properties from traditional lead zirconate titanate (PZT) to upcoming polymer material polyvinylidene fluoride (PVDF), there reveals the role of selecting suitable energy harvesting medium in generating proper output. From the experimented materials, zinc oxide (ZnO), aluminum nitride (AlN), and PVDF are found to be reliable towards the resonance concept and attaining optimum electric potential. Thus, our study strongly supports previous works carried out by the researchers regarding the effect of various piezo electric base materials on output response. 2023 -
Dependence between Sugar Industry Specific Factors and Sugar Companies Share Prices: Evidence from India
We assess the effects of sugar industry-specific macroeconomic factors on share prices of sugar companies in India using quantile regression approach from January 2001 to December 2017. We detect grounds to affirm the dependence between sugar industry specific macroeconomic factors and sugar companies share prices. The results indicate that the change in sugarcane cultivation area has both positive and negative effect on the share prices of sugar companies. Further, it shows that the impact of sugar production on share prices of sugar companies varies across the different quantiles except an insignificant effect on two companies for all quantiles. Moreover, most of the companies share prices are highly and positively influenced by sugar import. The study pointed out that the risk of sugar industry specific macroeconomic factors noticed in the sugar companies share prices is heterogenous. Indian Institute of Finance Vol. XXXVI No. 4, December 2022. -
Denial of Service Attacks in the Internet of Things
A DoS attack is the most severe attack on IoT and creates a crucial challenge for the detection and mitigation of such attacks. A DoS attack occurs at multiple layers of the IoT protocol stack and exploiting the protocol vulnerabilities disrupts communication. Traditional mechanisms employ single-layer detection of DoS attacks, which individually detect and mitigate attacks. However, it is essential to establish a general framework for detecting DoS attacks in a real-time environment and coping with diversified applications. This can be achieved by fetching attack features of multiple layers to create a pool of numerous attacks and then designing a system that detects the attack when fed with specific attack features. This chapter comprehensively analyzes the research gap in the DoS attack detection techniques proposed. Secondly, we offer a two-stage framework for DoS attack detection, comprising Fuzzy Rule Manager and Neural Network (NN), to detect cross-layer DoS attacks in real time. The Input Data Type (IDT) is derived using a fuzzy rule manager that can identify the type of input dataset as usual or attack in real time. This IDT is passed to the NN along with the real-time dataset to increase detection accuracy and decrease false alarms. 2024 selection and editorial matter, Vinay Chowdary, Abhinav Sharma, Naveen Kumar and Vivek Kaundal; individual chapters, the contributors. -
Denial of Desire Depictions of Elderly Intimacy in Malayalam Cinema
[No abstract available] -
Demystifying the Metaverse Era: The Enabling Technologies and Industry Use Cases
Metaverse can be called a 3D shared virtual space that is hyper realistic, immer-sive, instinctive, and interactive. Through metaverse, people try to visualize life in the manner that do not exist in the real world. The potential and promising digital technologies turn out to be a huge enabler of the metaverse dream. This chapter is to delineate the various versatile metaverse applications, implementation technol-ogies, and use cases (individual as well as industrial). 2025 Scrivener Publishing LLC. -
Demystifying the 5G-Advanced communication paradigm
With the massive surge in the increasing number of connected wireless devices, the demand for wireless data bandwidth keeps growing exponentially. Further on, in the beginning, many people were using only one computer. Today everyone has his own computer. But in the days ahead, there will be many digital devices to cogently and cognitively identify and deliver real-time and real-world services to a person. That is the world is tending towards a multi-device communication and computing era. Visualizing and realizing context-aware applications mandate for device computing. That is, devices have to be empowered to be computational, communicative, sensitive, vision-enabled, perceptive, decision-making, intelligently responsive, and action-taking. Leading research analysts and market watchers have forecast that there will be billions of IoT devices and trillions of IoT sensors in the years to unfold. Connecting them to instinctively share their unique capabilities and data with one another as well as with nearby and faraway cloud data platforms demands pioneering and powerful communication capabilities. With this projected growth in mind, the cellular industry looks for advanced wireless communication technologies. to other frequency bands that could possibly be utilized in the development of new 5G wireless technologies. This chapter is dedicated to telling all about the unique capabilities and use cases of 5G Advanced releases (Releases 17 and 18). Let us start with release 17 and then jump into the 18th release. 5G is all set to empower consumers and businesses to realise and use advanced applications and it allows a large number of devices to connect and exchange data faster than ever before. 2025 -
Demystifying Data Justice: Legal Response To India's Privacy And Security Standards: Challenges In Cloud Computing
Data is the new oil of this economy. Cloud Computing acts in the capacity of storing databases, in operational analytics, networking and intelligence. Indian cloud computing market is valued at 2.2 billion dollars, which is said to scale by 30 percent in 2022. It's therefore pertinent to understand Indian's data protection landscape in the light of Personal Data Protection Bill, 2018 to answer the questions of ownership, controlling, processing of data in order to reflect upon the liability, obligations, and compliances by intermediaries, dispute resolution forums, data portability and indemnification. The authors will explore by means of doctrinal method, the challenges posed on the content regulatory mechanism for the internet architecture which paves responsibility of data classification into lawful and unlawful, with the exception of section 79 of Information Technology Act. The authors will further examine the encryption standard tools exhibiting data security and the obstacles created by the 40-bit limit encryption standard as part of the DoT's telecom licensing conditions and section 84A IT Act, 2008, to provide suggestions towards pragmatic delimitation. Cloud computing being the next growth frontier of the IT industry, makes it more evident to enable cloud forensics in entrusting with investigations and establishing confidence within the end-users. Goal 16 of SDG's deal with Promote just, peaceful and inclusive societies. The Electrochemical Society -
Demystifying artificial intelligence and customer engagement: A bibliometric review using TCCM framework
Artificial intelligence (AI) has grabbed the attention of the extent of literature and customer engagement of many business organizations in the past decade, especially with the advancement of machine learning and deep learning. However, despite the great potential of AI to solve customer problems and engage customers, there are still many issues related to practical uses and lack of knowledge to create value through customer engagement. In this context, the present study aims to full fill the gap by providing a critical literature review based on 53 A* and A categories of Australian Business Deans Council (ABDC) journals (2011-2023) by highlighting the benefits, challenges, framework, and future research directions in theory, context, characteristic and methodology (TCCM) areas. These findings contribute to both theoretical and managerial perspectives for developing a future novel theory and new forms of management practices. 2024, IGI Global. All rights reserved. -
Demography-Based Hybrid Recommender System for Movie Recommendations
Recommender systems have been explored with different research techniques including content-based filtering and collaborative filtering. The main issue is with the cold start problem of how recommendations have to be suggested to a new user in the platform. There is a need for a system which has the ability to recommend items similar to the users demographic category by considering the collaborative interactions of similar categories of users. The proposed hybrid model solves the cold start problem using collaborative, demography, and content-based approaches. The base algorithm for the hybrid model SVDpp produced a root mean squared error (RMSE) of 0.92 on the test data. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Demographic Variables Influence on Work Engagement of Nurses and Doctors in Hospitals.
It has been foreseen that the healthcare sector in India will be at par with the IT services as well as education in terms of revenue, and would largely contribute to the countrys economy. The health-care industry is presently worth $ 7 Billion dollars (USD), and is predicted to grow at the rate of 13% every year. At this pace, work levels in hospitals have increased, and an employees contribution towards work has decreased. The psychological connection of employees towards their work has gained critical importance; as organizations find that their employees are not giving their best in these times when the demand is on its rise. Work engagement is a positive-fulfilling work-related state of mind characterized by vigor, dedication and absorption, where vigor being high energy levels and mental resilience, dedication being a state of mind where an individual is strongly involved in ones work, and absorption is characterized by engrossment and concentration towards ones work. Literature review on work engagement from the last decade has focused on the relationship of engagement with job satisfaction, employee turnover, performance, and other human resource related constructs. A sample of 372 respondents comprising of doctors and nurses form 20 hospitals (corporate, government and private/trust) of 150 beds and above. Respondents were chosen by using judgmental sampling technique. The variables under investigation were Work engagement and eight demographic characteristics of the respondents. Utrecht Work engagement scale (UWES), by Wilmar Schaufeli and Arnold Baker, (2003), and based on the objectives the eight demographics were included. Fourteen hypotheses were tested and the major findings were that the overall work engagement for doctors was significantly high, and for nurses it was found to be moderate. Significant difference on work engagement levels on doctors was found across gender, educational qualification, age of the respondents, marital status, number of children, and types of hospitals. No significant difference on work engagement levels was found across work experience for doctors. Significant difference on work engagement levels on nurses was found across educational qualification, age of the respondents, work experience, marital status, number of children, and type of hospitals for nurses. No significant difference on work engagement levels was found across gender for nurses. Implications suggested that hospitals develop a flexible training, and therapeutic program for men and women to manage stress customized to their requirement. Focus should be given on encouraging employees to continue higher education. Younger and less experienced employees should be encouraged to interact with senior staff as their sharing of ideas and thoughts would be beneficial to both older and younger employees. Hospitals should imbibe values and ethics which are based on compassion, love for mankind and development of society through good leadership which would inspire them to go that extra mile. Key words: Work engagement, Demographic influence, Doctors, Nurses. -
Demographic Determinants of Fire-Safety Behavior in High-Rise Residential Buildings: A Survey-Based Behavioral Analysis from Bengaluru, India
This study explores the role of demographic and experience-based parameters for fire safety behavior among residents of high-rise residential apartment buildings in the city of Bengaluru, a metropolitan capital in India. Data were gathered through a questionnaire-based survey among 262 residents. Multiple regression analysis was used to assess the correlation among demographic parameters and behavioral responses during evacuation. The results show that age (R2 = 0.154, p = 0.004), presence of vulnerable household members (R2 = 0.137, p = 0.022), and prior fire experience (R2 = 0.157, p = 0.004) are statistically significant predictors of fire-safety behavior. In contrast, gender (R2 = 0.117, p = 0.073), educational qualifications (R2 = 0.109, p = 0.136), and chronic health conditions (R2 = 0.121, p = 0.500) do not exhibit significant associations. Cross-tabulation analysis further indicates that residents who have received fire-safety training prioritize immediate evacuation, whereas untrained residents display delay behaviors. By providing empirical behavioral evidence from an Indian metropolitan context, this study highlights the demographic heterogeneity in evacuation behavior and supports the integration of behavioral realism into performance-based fire safety design for high-rise residential buildings. (2026), (Dr D. Pylarinos). All rights reserved. -
Demographic constructs and savings behavior of adult people /
Journal of Emerging Technologies And Innovative Research, Vol.6, Issue 3, pp.409-412, ISSN No: 2349-5162. -
Demographic characteristics influencing financial wellbeing: amultigroup analysis
Purpose: The study attempts to understand the factors impacting the financial wellbeing of IT employees in India using confirmatory factor analysis (CFA). It utilizes well-established survey instruments to assess the impact of financial literacy, financial behaviour and financial stress on financial wellbeing. The study also attempts to understand the role of demographic factors (age, gender, monthly income, job category and work experience) in determining financial wellbeing through multigroup analysis. Design/methodology/approach: Structured equation modelling (SEM) is used to study the link between the determinants. The study also attempts to understand the role of demographic factors (age, gender, monthly income, job category and work experience) in determining financial wellbeing through multigroup analysis. Data used for the analysis covers 237 employees working in the IT sector. Findings: While financial literacy and financial behaviour have a significant positive impact on financial wellbeing, financial stress has a significant negative impact. Financial behaviour and financial stress were found to have a mediating role in the relationship between financial literacy and financial wellbeing. The demographic variables significantly moderate the relationship between the factors leading to financial wellbeing. Originality/value: The results show the need for financial wellbeing programs to focus on enhancing financial knowledge and improving financial planning. Further, it suggests offering customized financial wellbeing programs based on the employee's demographic characteristics rather than following a one program, fits all approach. 2021, Emerald Publishing Limited. -
Democratising Intelligent Farming Solutions to Develop Sustainable Agricultural Practices
In this chapter, the transformative potential of democratising intelligent farming solutions is discussed, primarily in the context of the sustainable farming. Technologies including the Internet of Things (IoT), global positioning systems (GPS), Unmanned Aerial Vehicles (UAVs), computer vision, and artificial intelligence (AI) have redefined farming activities. Such advances have allowed decision-making and optimised resource utilisation to be driven by real-time data. The democratisation of AI tools are meant to make AI-driven agriculture accessible to all. As such, this chapter discusses the interplay of bottom-up and top-down approaches, highlighting their roles in promoting the accessibility of AI tools and their benefits to farmers. The integration of such AI tools would transform contemporary agriculture into agriculture 4.0. This revolution would be characterised by real-time data, predictive analytics, and precision farming techniques. Further, the integration of technology such as wireless networks and the global navigation satellite system (GNSS) increases precision and the ability to monitor farming activities. The idea of democratising intelligent farming solutions is meant to herald agriculture 4.0, which would improve crop quality, climate resilience of crops, and the income of farmers. It would also improve broader macroeconomic aspects by promoting education and information and communication technology (ICT) skills and potentially reducing income inequality gap while promoting socio-economic well-being. 2025 selection and editorial matter, Sirisha Potluri, Suneeta Satpathy, Santi Swarup Basa, and Antonio Zuorro; individual chapters, the contributors. All rights reserved. -
Democracy in the age of AI: Ethical and legal considerations
Democracy is an age-old idea. Although it originated in Ancient Greek Polis Athens, it took almost 20 centuries to become a globally preferred political system of governance. In the aftermath of the Second World War, many countries became independent and democratic affirming the role and strength of people in the governance of country. Democracy revolves around the values like human rights, free choice, freedom, equality, and decision-making. However, with the latest technological advancements in the area of artificial intelligence (AI), there are serious concerns with regard to the smooth functioning of democracy as many biased involvements are officially reported. The virtual world and AI systems are used for targeting the efficiency of democracy. The chapter, in this perspective, critically examines the role of AI in democracy and enlists certain ethical values and legal principles for AI's effective incorporation into the dynamics of politics and democracy. 2025 by IGI Global Scientific Publishing. All rights reserved.