Browse Items (3095 total)
Sort by:
-
PM2.5 Prediction Models: A Systematic and Comparative Review
Airborne particulate matter (PM) is an amalgam of liquid droplets found in air and microscopic solid particles. The particles differ in size, shape, and chemical composition. PM has a significant impact on climate and precipitation and adversely affects human health as it can infiltrate the lungs and enter the cardiovascular system. This article explores the various PM2.5 prediction models proposed to date to predict a region's particulate matter (PM2.5) concentration. As prediction techniques evolve rapidly, this study aims to assess the various methodologies proposed for predicting PM2.5 concentration in different regions according to the factors that influence it. Various machine learning, deep learning, and statistical models have been proposed to predict hourly or daily PM2.5 concentrations in the air. The previously proposed models were compared using the RMSE, MAE, and R2 scores as the evaluation metrics. Since most of these models were region-specific and mostly used different parameters for the prediction, the comparison highlighted the need for a generalized model that could be fine-tuned based on the parameters of a particular region. Thus, this review points to the need for a high-accuracy generalized prediction model for PM2.5 that adapts to the diverse parameters region-wise. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Disease Identification from Illegible Medical Prescriptions Using OCR and NLP Techniques
Medical prescriptions that are challenging to interpret present significant issues for the healthcare industry because they increase the possibility of errors in patient care and medication administration. This study presents an efficient workflow that uses Optical Character Recognition (OCR) technology, specifically, Tesseract OCR, along with a preprocessing step to extract text from handwritten prescriptions. The preprocessing stage uses grayscale conversion, noise reduction, and contrast enhancement to increase the accuracy of OCR. Significant results from experiments on a publicly accessible dataset show that preprocessing greatly improves performance, lowering the error rate from 34.7 to 18.3% and raising average accuracy from 65.3 to 81.7%. The enhanced accuracy outweighs the modest increase in processing time (from 0.8 to 1.2s), emphasizing the potential of using these techniques in practical healthcare applications. The studys findings also demonstrated the successful analysis of the text using Natural Language Processing (NLP) and Clinical Bidirectional Encoder Representations from Transformers (ClinicalBERT) techniques by identifying four distinct diseases, Common Cold, Diabetes Mellitus, Bronchitis, and disease caused by Anemia, as validated by a medical professional. This demonstrates the systems potential to improve health care processes by automatically digitizing handwritten prescriptions. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
New Empirical Equation for Fundamental Time Period of RC Moment-Resisting Frame Buildings Using Machine Learning Algorithms
The fundamental time period of reinforced concrete (RC) buildings is a critical parameter in structural engineering, influencing their dynamic behavior and response to seismic and wind loads. This study aims to propose a new empirical formula for estimating the fundamental time period of RC buildings through regression analysis. Leveraging the SAP2000 API with VBA code, a dataset comprising 200 two-dimensional RC building models was rapidly generated, allowing for efficient exploration of various building configurations. Modal analysis was conducted for each model to determine the fundamental time period, and regression analysis was performed using both multiple linear regression and curve estimation regression techniques. The input parameters included total building height and base dimensions, while the output variable was the fundamental time period obtained from SAP2000 results. Multiple linear regression yielded two best-fit models, while curve estimation regression produced logarithmic and exponential models. The proposed models were compared with the fundamental time period values obtained from SAP2000 results and those calculated using the formula specified in the Indian Standards (IS) code. Further the results obtained are used to develop a machine learning model that can be used to estimate the time period of RC structures for a given height. The model is chosen after estimating the coefficient of regression for various individual machine learning algorithms and ensemble algorithms. This research contributes to the advancement of structural engineering by providing a systematic approach to developing empirical formulas tailored to RC buildings. The proposed formula, enabled by the automation capabilities of the SAP2000 API, offers a more accurate and reliable method for estimating the fundamental time period, facilitating improved seismic design and analysis practices. Further validation and verification of the formulas performance using additional datasets and real-world case studies are recommended to enhance its applicability and robustness. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Bridging Signs to Sentences: Enhancing Sign Language Interpretation
This paper mainly focuses on bridging the gap between sign language recognition (SLR) and sentence formation by integrating the recognition of different signs or machine learning models with large language models (LLMs), which results in contributing and enhancing the communication of the deaf community. There are around 466million deaf individuals worldwide, where they primarily rely on Sign language for communication. Current SLR technologies have certain limitations that deal with difficulty in sentence formation and high processing requirements. This papers dataset consists of 36 classes, where 26 of them are alphabets, and the rest 9 are numbers, each consisting of 500 images. Therefore, a total of 18,000 images are present in the dataset for accurate prediction of sign languages. MediaPipe, developed by Google, is used as a tool for feature extraction by identifying 21 hand landmarks. The features extracted are then passed onto an ML model (like a Random Forest), and then the result of this model is passed on to an LLM (here, Groqs Gemma-7b-it) that forms a sentence based on the predictions. The ML model achieved a high accuracy of 99.54% and the LLMs achieved an accuracy of 93.75%. With the combination of sign language recognition and advanced modeling, this work helps to bridge signs to sentences, providing to the deaf community. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Transforming Finance into an AI-Driven, Data-Centric, and Analytics-Focused Function: Implications for Organizational Impact
The financial function within organizations is evolving from a traditional cost-center role to a strategic partner powered by artificial intelligence (AI), data analytics, and advanced technologies. This transformation is reshaping how financial professionals analyze data, predict trends, and support decision-making. By leveraging AI, finance teams can automate repetitive tasks, enhance data accuracy, and deliver actionable insights in real-time. Integrating predictive and prescriptive analytics further empowers organizations to forecast financial outcomes, optimize resource allocation, and mitigate risks with precision. This shift to an AI-driven, data-centric finance model fosters agility, innovation, and enhanced collaboration across departments. It aligns financial strategies with organizational goals, improving operational efficiency and driving sustainable growth. However, the transition demands investments in digital infrastructure, a redefinition of roles, and an upskilling of personnel to handle complex analytics tools. The implications for organizational impact include enhanced competitiveness, informed decision-making, and a stronger ability to navigate an increasingly volatile economic landscape. This chapter explores these transformations, their challenges, and the opportunities they unlock for organizations aiming to thrive in a data-dominated era. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Deep Learning-Based Consolidated Disease Classification in Health Data Management
Healthcare data management is critical for ensuring comprehensive and high-quality medical treatment. Sensitive patient data management has a potential new option thanks to blockchain technology. However, existing blockchain-based healthcare data management systems face challenges in scalability, integration, and regulatory compliance. To address these issues, a novel blockchain-based healthcare data management system has been proposed to provide a secure, decentralized, and interoperable platform for managing sensitive patients medical information. Proposed approach involves collecting comprehensive health measurements from patients using wearable sensors and ensuring the security and integrity of patient data through robust user verification protocols. Artificial Neural Networks (ANNs) are employed to consolidate disease symptoms, enhancing the efficiency and accuracy of data analysis. The results and comparative analysis showcase the efficiency of the proposed method in terms of precision, accuracy, recall, search accuracy and F1-score. The accuracy of the proposed method is improved by 12.9%, 6.07%, and 14.28% when related to the existing ACTION-EHR, BSDMF, and BlockMedCare techniques respectively. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
The Quantum Shift inMachine Learning
Quantum machine learning (QML) leverages the power of quantum computing to extensively enhance the performance of simple ML algorithms. This kind of enhancement efficiently avoids complicated high-dimensional and computationally expensive applications. Following exciting discoveries of some key algorithms such as Grovers and Shors algorithm, QML came up with advanced models such as quantum neural networks (QNNs), quantum support vector machines (QSVMs), and quantum deep architecture. The discussed models give better results in data processing, pattern recognition, and optimization in comparison to their classical variants. This survey discusses the most important developments in QML with focus on Quantum Fourier Transform for encoding the data. Applications of QML in quantum chemistry, secure distributed computing, and high-dimensional data analysis are shown. It will present new breakthroughs and continue to challenge practical, scalable QML solutions toward mapping out the course toward quantum advantage in machine learning tasks. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Harnessing Machine Learning toOptimize Social Media Marketing
Machine learning (ML) has transformed the way digital advertising is done and analyzed by social media data. This paper explores ML in targeted advertising, including techniques such as supervised learning, neural networks, and NLP. While ML improves campaign precision and consumer engagement, it also presents challenges such as algorithmic bias, data privacy concerns, and computational scalability. This study is a synthesis of existing research and explores real-world applications, providing a critical analysis of MLs capacity to optimize social media advertising. It argues that while ML may provide exceptional possibilities for customization and engagement, its success can only be ensured through appropriate ethical practices, transparency, and innovation in technology. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Leveraging Machine Learning for Epidermal Ailment Detection
Skin disorders are common across the globe, often proving to be difficult to diagnose because of coexisting signs and symptoms. In this paper, we study the feasibility of using machine learning (ML) techniques for automatic skin disease detection. We look at the emerging patterns in fundamental studies within the scope of focus that deals with image processing for feature extraction and employing classification methods for disease detection. We focus on feature extraction and the classification of images. One of the major strengths is the ML-based approach with better access and usability and higher chances of them being detected at an early stage. In addition, we consider some of the drawbacks and problems of these methods, including biased data and lack of sufficient professional oversight. We also consider other aspects, whereby one of them is further analysis of the requirement in the case of the absence of the adequate data, standard models, and unambiguous explanations of the inner processes. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Financial Inclusion as a Tool for Social Equity: A Focus on the Elderly and Underprivileged
Financial inclusion is a key element in reducing poverty and promoting economic growth, particularly for vulnerable groups such as the elderly and the poor. This article explores the multiple barriers that these groups face in accessing financial services, including economic constraints, discrimination, and lack of identification and credit history. The report highlights the special challenges that older people face due to limited mobility and digital literacy. The study emphasizes the importance of a multi-faceted policy approach to improving financial inclusion, including developing simplified financial products, expanding financial literacy programs, and working with NGOs. The paper focuses on effective strategies and proposes interventions aimed at empowering these populations and improving their access to financial resources, ultimately supporting economic stability and reducing inequality. The findings highlight the need for policymakers and financial institutions to work together to address systemic barriers that impede the financial autonomy of vulnerable groups. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Development ofNew Fidelity Theorems inQuantum Communication
Fidelity estimates the closeness or degree of overlap between a pair of unknown quantum systems. In quantum information processing study, a primary task is to estimate the fidelity of a pure states pair in a 2-dimensional Hilbert space or between a mixed state, ?, and pure state existing in N dimensional Hilbert space while transmitting them through noisy environments. This paper suggests two theorems to estimate fidelity while proving and justifying them numerically. The first theorem computes fidelity between pure states and the second estimates fidelity between mixed and pure states. The mathematical basis of the theorems confirms accuracy in estimation while dealing with single- and multiqubit system environments. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Managing Retail Credit Default Risk Using Artificial Intelligence and Machine Learning: Ethical Considerations and Challenges
Credit risk management is an integral aspect of financial stability of financial institutions. The determinants of credit default behavior help in identifying types of credit risk based upon customers habits or actions such as purchasing behavior, spending patterns, social interactions, and moral hazard. The awareness on such behavioral factors helps in getting a complete picture in analyzing the credit worthiness of any individual. The onset of artificial intelligence (AI) and machine learning (ML) has remodeled the methodologies of credit risk assessment. Training and developing learning models to predict the borrowers behavior evolved along with AI and ML, developing advanced mechanisms for managing credit default risks. Using risk modeling to determine behavioral scoring enables the banks to acquire creditworthy retail borrowers, alongside its inherent demerits of the models. This study is focused on the employment of AI and ML techniques along with qualitative determinants in managing credit risk, drawing attention to the advantages and disadvantages and applications and implications for the financial service providers. The paper examines contemporary literature on modern methods of credit risk management and sheds light on the technological accuracy of credit risk calculations and automated decision-making processes alongside methods to alleviate biases. The study also outlines the sequential phases of the conventional models along with the regulatory and ethical considerations of AI-ML-driven credit risk assessment. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Efficacy of AI for Three-Dimensional Point Cloud Semantic Segmentation of Heritage Data for XR Environments
In heritage documentation, three-dimensional (3D) models created using Scan-to-BIM processes are essential for interpreting and presenting historic structures. Point cloud data derived from 3D laser scanning and photogrammetry facilitate realistic digital models used for immersive experiences. For this, raw point clouds, which are unstructured, are processed, semantically classified, and segmented to create parametric architectural objects in modeling platforms. Three-Dimensional Point Cloud Semantic Segmentation (3DPCSS) refers to segmenting point clouds into classes like walls, columns, etc. Automating 3DPCSS using Artificial Intelligence (AI) has gained importance in current research activities because of its versatility and efficiency over manual segmentation. However, implementing it solely with AI presents various operational and conceptual challenges, particularly for XR models in digital heritage. Automated segmentation often fails to capture the unique characteristics and intricate geometries, leading to misrepresentations or oversimplifications. Selecting an appropriate algorithmic framework for automating 3DPCSS is essential to address this gap. This paper aims to understand the efficacy of AI algorithms in recent research for 3DPCSS, particularly those tailored for 3D modeling. A study of Dwarakadesh Haveli, Ahmedabad, India, highlights the workflow and challenges of integrating point clouds into 3D models. The findings indicate the need for a detailed approach tailored to the projects specific characteristics, emphasizing the importance of systematic algorithm ensemble experimentation to refine segmentation, leading to the development of 3D parametric objects. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Technological Interventions in Unpaid Care Work and Gender Dynamics
Unpaid care work, frequently centered on women, is an important yet neglected component of the world economy. This study strives to address the potential and flexibility that technology brings in curbing gender disparities, along with the bodily burden associated with unpaid care work. An examination is made for smart home devices, telehealth solutions, and caregiving applications that will further be evaluated for their effectiveness in minimizing the time and effort invested in unpaid care responsibilities. Through existing theoretical frameworks, empirical evidence, and case studies, this paper aims to determine how technological innovation can more effectively redistribute care work between genders and enhance the economic value of unpaid care to further improve gender equality. For instance, in Japan, smart home appliances such as automated pill dispensers and remote monitoring devices have become crucial solutions to a caregiving burden largely imposed on women. Telemedicine services similar to these have transported rural India from its unfavorable health care situation, thereby significantly shortening the time women spend on activities related to health care. Caregiver applications have assisted in the United States in achieving an equal distribution of caregiver responsibilities between male and female caregivers. Sophisticated robotic assistants in South Korea may fill gaps in the workforce while tending to older populations; thus, potentially minimizing housework hours for women. The education systems operating online across Sub-Saharan Africa enable girls to juggle learning with caring effectively and hence strike long-lasting gender parity. Such socio-economic advantages were purely garnered through wearable health monitors in Europe that eased family members burdens while experiencing economic benefits at a broader level. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Improving the Accuracy of Cardiovascular Disease Classification Using CardioAugmentNet Technique
Cardiovascular disease is the leading cause of death and mortality worldwide. Thus, early diagnosis of CVDs is crucial since the disease can be managed with optimal care. In the current study, we consider CardioAugmentNet, which is a CNN model augmented with data augmentation strategies for the classification of several cardiovascular pathologies in ECG images. A proposed method was designed to provide a robust algorithm for the detection of irregular heart rhythms, myocardial infarction and other cardiac diseases. The model is trained and tested on the dataset of ECG images from individuals with various prevalent cardiovascular diseases as well as normal hearts. Therefore, the CardioAugmentNet state-of-the-art model classifies different cardiac abnormalities with high accuracy, suggesting that it can be used in clinical practice. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Mobilizing Automated Vehicles: Harmonizing the Intersection of Technological Innovations and Legal Regulations
There will be significant shifts in transportation with the introduction of autonomous vehicles (AVs), which will increase efficiency, safety, and environmental friendliness. But these technologies can only be used to their full potential if technological breakthroughs are seamlessly integrated with strong legal regulations. The article delves into the ways in which technological advances and legal frameworks meet, highlighting how important regulatory measures are for ensuring the secure use of AVs. In addition, the article delves into the current legal framework around AVs, drawing attention to the difficulties caused by inconsistent regulations and the necessity for flexible rules that can stay up with the fast-paced advancements in technology. The purpose of this article is to examine current policies and case studies to shed light on how to effectively integrate technology advancements with legal requirements to create conditions that are favorable to the broad use of autonomous vehicles. The results highlight the need for manufacturers, lawmakers, and the general public to work together for the sake of society's safety and well-being during the shift to autonomous transportation. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Evaluating Technostress: Work-Life Balance and Well-Being in Varied Work Contexts
In the contemporary digital landscape, the phenomenon of technostress, defined as stress induced by technology usage, has emerged as a crucial factor influencing work-life balance and employee well-being. This study will explore the impact of technostress in varied work modes such as traditional office-based, remote, and hybrid models. Employing a quantitative approach, the researcher conducted surveys on a representative sample of employees across multiple industries. The results indicate that technostress adversely influences work-life balance and well-being, and the difference in various work modes is observable. Further, it has also been observed that there are significant differences in technostress and well-being concerning the various work modes; working from home comes out to be a positive option, which is related to lesser levels of technostress and higher outcomes of well-being. The present study shows how organisational interventions may be implemented in mitigating technostress-inducing effects: induction of digital literacy, instillation of appropriate communication policies, and embedding of supportive work culture. Essentially, an intervention could help organisations improve well-being 0f employees and achieve better work-life balance in a digital environment. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Detection andDealing ofMulticollinearity Using aNew RidgeEstimator
The Ordinary Least Square (OLS) method is a widely used technique for estimating regression coefficients that describe the relationship between the independent variables and the dependent variable. The regression estimates obtained using this approach give a poor result in the presence of multicollinearity. Ridge regression is employed to address this problem. A ridge estimator, also called a biasing constant, plays a notable role in the parameter estimation of ridge regression. In this paper, we introduced a new ridge estimator and studied its properties. A comparative study of the proposed estimator with some of the existing ridge estimators under extreme multicollinearity has been illustrated by using a simulation technique. The estimator developed in this paper seems to perform better than all the other estimators because of the smaller ratio of average mean square error. The performance of the proposed estimator is analysed and verified using real-life data. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Autoregressive Model with Students t-Errors
This paper examines a first-order autoregressive model that incorporates students t-distributed errors. The estimation procedure is developed using the maximum likelihood method, with the solutions demonstrated using a simulation approach. As the estimating equations were not in a closed-form expression, we obtained the parameter estimates using the NewtonRaphson method. For a finite sample size, a parametric bootstrap procedure for the unit root test has been illustrated. To demonstrate the applications of the proposed model, a time series of quarterly GDP percentage changes are analyzed. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Leveraging Machine Learning and Streamlit for Real-Time Stock Analysis and Prediction
This paper introduces StockNavigator, an interactive web application developed using Streamlit, designed to offer a comprehensive solution for stock performance analysis, real-time stock price monitoring, and stock price prediction. Users can compare the performance of multiple stocks over a specified period, visualize data through various chart types, and gain insights into stock trends and relative returns. The proposed models user-friendly interface allows investors to make informed data-driven decisions, regardless of whether them being seasoned traders or beginners. This article demonstrates the effectiveness of using modern machine learning models like Prophet in the domain of financial forecasting and highlights the flexibility of Python-based frameworks for developing interactive, data-centric web applications. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.