Browse Items (16481 total)
Sort by:
-
Advancing Road Safety through Driver Drowsiness Detection Using Deep Learning Model
Driver drowsiness poses a significant threat to public safety, contributing to numerous road accidents and fatalities annually. Drowsy drivers exhibit characteristic changes in facial expressions and behaviors, including eye closure, head nodding, and yawning. These indicators can be detected through various techniques, including image processing, computer vision, and machine learning. This research investigates a promising approach: utilizing a ResNet-101 deep convolutional neural network (CNN) for driver drowsiness detection based on eye, head, and mouth states. The model was trained on a vast dataset of 2.2 million images, covering diverse driving conditions. Despite achieving a 69% accuracy, suggesting real-world potential, computational limitations restricted training to only a quarter of the data. This necessitates further research with larger datasets and increased resources to enhance accuracy and robustness. 2024 IEEE. -
Advancing Predictive Analytics in E-Learning Platform: The Dominance of Blended Models in Enrollment Forecasts
The rapid expansion of e-learning platforms has revolutionized the landscape of education, particularly highlighting the significance of online courses in contemporary learning environments. This research focuses on Udemy, a prominent online learning platform, and aims to enhance the predictability of course enrollments within its IT & Software category. The study's central purpose is to leverage advanced machine learning techniques to predict course subscriber numbers, a crucial indicator of a course's popularity and success. Employing an extensive dataset from (Kaggle DB)Udemy, encompassing various course attributes such as ratings, reviews, and pricing, the study explores multiple machine learning models. These include Linear Regression, Decision Tree, Random Forest, Gradient Boosting, and K-Nearest Neighbors Regression. A key innovation of this research is the application of ensemble methods, particularly a blended model approach, to integrate predictions from multiple models, thereby enhancing accuracy and reliability. The findings of this study are significant. The ensemble approach, notably the blended model, outperforms individual predictive models in accuracy. Among the single models, Gradient Boosting Regression shows the highest effectiveness in forecasting enrollments. The research highlights the vital role of course characteristics, including ratings and reviews, in determining course popularity. This study contributes to the field of e-learning by introducing a novel, data-driven approach to predict course enrollments. It offers valuable insights for educators, course creators, and platform developers, emphasizing the potential of machine learning in optimizing content strategy and marketing efforts in the digital education domain. The application of ensemble machine learning methods presents a new horizon in educational analytics, paving the way for more nuanced and effective strategies in online education delivery and promotion. 2024 IEEE. -
Advancing precision medicine: Uncovering biomarkers and strategies to mitigate immune-related adverse events in immune checkpoint inhibitors therapy
Immune-related adverse events (irAEs) can have a major influence on patient outcomes, but their usage is frequently confounded by immune checkpoint inhibitors (ICIs), which have revolutionized cancer treatment by increasing anti-tumor immunity. With a focus on immunological dysregulation and the resulting tissue-specific toxicities, this review clarifies the fundamental processes of irAEs. We look at contemporary clinical treatment techniques to lessen the impact of these adverse events, such as the application of immunosuppressants and patient monitoring procedures. Additionally, it is emphasized how future research is necessary to find predictive biomarkers that can forecast the development of irAEs, allowing for early intervention and individualized therapy methods. In order to improve the therapeutic index of ICIs, we also examine the crucial balance between optimizing anti-tumor activity and reducing immunotoxicity. This study aims to further the existing discussion on enhancing the safety and effectiveness of ICI medicines, which will eventually improve cancer patient care, by pointing out possible research avenues. 2025 The Authors -
Advancing Nutrient Removal and Resource Recovery Through Artificial Intelligence: A Comprehensive Analysis and Future Perspectives
The increasing difficulties associated with effectively controlling wastewater treatment operations while simultaneously satisfying the imperatives of nutrient removal and resource recovery have necessitated the use of advanced technology. This book chapter provides a comprehensive analysis of the use of artificial intelligence (AI) methods within this complex context. Utilizing a vast array of scholarly investigations and real-world implementations, this study explores the intricate domain of wastewater treatment, providing a comprehensive understanding of how artificial intelligence algorithms are used to enhance the efficiency of nutrient removal procedures and expedite the recovery of valuable resources. This chapter presents a thorough examination of the impact of artificial intelligence (AI) on sustainable innovations in wastewater treatment facilities. It accomplishes this through a comprehensive analysis of relevant data and the inclusion of real-world case studies. The findings of this research highlight the transformative effect of AI on conventional approaches to wastewater treatment, enabling the adoption of environmentally friendly and resource-efficient practices. The integration of artificial intelligence (AI) with wastewater management offers a fascinating story that highlights the shifting paradigm in the field of environmental engineering and the efficient exploitation of resources. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Advancing Intrusion Detection Using Deep Learning: A Hybrid Approach
Intrusion detection systems (IDSs) are vital for securing networks against evolving cyberthreats. Traditional machine learning models often struggle with complex network traffic and imbalanced attack patterns. This study proposes an advanced ensemble model integrating ANN, LSTM, random forest, and LightGBM to enhance detection accuracy and robustness. Evaluations on the KDD99 dataset demonstrate that the ensemble model outperforms standalone ANN-LSTM models, achieving 92.4% accuracy, 97.4% precision, 87.1% recall, and a 91.9% F1 score. Hybrid models also showed significant improvements, with Nadam optimization yielding an F1 score of 93.10% for ANN-LSTM-random forest and Adam optimization achieving 93.30% for ANN-LSTM-LightGBM. By addressing data imbalance and improving attack pattern detection, this approach provides a scalable, efficient solution for real-time intrusion detection with superior performance. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Advancing Interpretable Machine Learning: Principles, Challenges, and Practical Insights
[No abstract available] -
Advancing Image Security Through Deep Learning and Cryptography in Healthcare and Industry
Securing electronic health records (EHRs) in the Internet of Medical Things (IoMT) ecosystem is a key concern in healthcare due to the sector's differed environment. As the evolution of technology continues, ensuring the confidentiality, integrity, and accessibility of EHRs becomes more and more challenging. To enhance the confidentiality of healthcare picture data, this study explores the combined use of deep learning and cryptography methods. Through the utilization of weight analysis for improving encryption strength and the combination of chaotic systems to generate undetectable encryption patterns, it explores how deep neural networks can be modified for use in encryption. It also provides a survey of the present scenario of deep learning-based image detection of anomalies methods in working environments, such as network typologies, supervision levels, and assessment norms. Techniques in cryptography provide an effective means to protect confidential medical picture data while it's being transmitted and stored. Deep learning, on the other hand, has the ability to entirely change cryptography by providing robust encryption, resolution augmentation, and detection capabilities for medical image security. The paper outlines future research approaches to overcome these problems and tackles the opportunities and obstacles in medical image cryptography and industrial picture anomaly detection. Through this work, picture privacy in the healthcare and industrial sectors is advanced, opening the door to enhanced privacy, integrity, and availability of vital image data by overcoming the gap between deep learning and cryptography. 2024 IEEE. -
Advancing Healthcare Decision Support: Leveraging Fuzzy DEMATEL for Delivering Quality Care
Healthcare Decision Support Systems (DSS) play a pivotal contribution in modern healthcare, aiding in informed decision-making and the distribution of high-quality care. To optimize the systems, it is critical to recognize and prioritize the enablers that provide to their successful establishment and operation. This study presents a comprehensive analysis of 10 key enablers essential for the development and deployment of healthcare DSS for quality care. Utilizing Fuzzy DEMATEL (Decision-Making Trial and Evaluation Laboratory), a powerful methodology for discovering complex interdependencies among factors, we systematically evaluate the relationships among these enablers. The enablers, ranging from data integration and clinical collaboration to privacy safeguards and continuous improvement mechanisms, are scrutinized through the lens of Fuzzy DEMATEL, which accommodates the inherent uncertainties and ambiguities within healthcare data. The findings from the study shed light on the strength and direction of the relationships among the enablers, unveiling critical factors that exert substantial influence and those that are most susceptible to external changes. By applying Fuzzy DEMATEL, this study backs to a deeper understanding of the multifaceted nature of healthcare DSS development, offering insights to guide decision-makers, healthcare practitioners, and system developers in their pursuit of improved DSS that enhance the quality of healthcare delivery. The Author(s), under exclusive license to Springer Nature Switzerland AG 2025. -
Advancing Gold Market Predictions: Integrating Machine Learning and Economic Indicators in the Gold Nexus Predictor (GNP)
This study employs advanced machine learning algorithms to predict gold prices, using a comprehensive dataset from Bloomberg. The Gold Nexus Predictor (GNP), a key innovation, integrates historical data and economic indicators through advanced feature engineering. Methodologies include exploratory data analysis, model training with various algorithms like Linear regression, Random Forest, Ada Boost, SVM, and ARIMA, and evaluation using metrics like MSC, MAPE, and RMSE. The study's philosophical foundation emphasizes rationalism in economic forecasting and ethical model use. This research offers significant insights for investors and policymakers, enhancing understanding and decision-making in the gold market. 2024 IEEE. -
Advancing equity in digital classrooms: A personalized learning framework for higher education institutions
Since the introduction of technology-enabled education systems, personalizing the learning process has become more regarded as a promising methodology for revolutionizing the academe. Acknowledging the difference in the learning capability of students across various levels of the academic segment, a personalized learning approach is of paramount importance, especially when teachers cannot efficiently monitor each student (e.g., during emergency remote education). This chapter focused on the necessity for higher education institutions that offer courses from various streams to adopt a personalized learning initiative as a means of offering better online education services. For the successful creation of a personalized online learning experience, this chapter likewise developed a framework that provides a step-by-step guide to educational institutions in moving in this direction. As online education is a trend for future learning, this blueprint could be valuable as well in the post-pandemic era. 2022, IGI Global. All rights reserved. -
Advancing energy production and storage: Polypyrrole/V2O5/MnO2 composite as a high-performance electrocatalyst
The rise in energy needs in our society has enhanced the requirement for energy production and storage studies. The electrocatalytic hydrogen evolution reaction and supercapattery studies pave the way for producing and storing energy effectively. There is a lot of ongoing work on synthesizing efficient electrocatalysts for such energy related applications. In this study, polypyrrole/V2O5/MnO2 electrocatalyst is synthesized, and various characterization techniques have been utilized for analyzing the formation of the composite. The N2 adsorption-desorption analysis demonstrates the average surface area of the polymer composite as 136.3 m2/g. The high average surface area value suggests the availability of surface active sites on the synthesized polymer composite for energy production and storage. The polypyrrole/V2O5/MnO2 electrocatalyst shows an overpotential of 192 mV and a specific capacity of 1736.1C/g. The synthesized catalyst is used for fabricating an asymmetric supercapacitor, which demonstrates an energy density of 46.8 Wh/kg and a power density of 714.2 W/kg. Polypyrrole/V2O5/MnO2 electrocatalyst is proven to be a competent material for supplementing the energy requirements of our society. 2025 Hydrogen Energy Publications LLC -
Advancing Credit Card Fraud Detection Through Explainable Machine Learning Methods
The world of finance has experienced a significant shift in the way money flows, due to the advancements in technologies such as online banking, card payments, and QR-based payment systems. These innovative banking payment facilities are offered by ensuring the safety of the transaction and ensuring that only the authorized customer can access and utilize these banking services. Credit card fraud is innovative way to cheat the user of the card. Government all over the word encouraging to the people for the uses of digital money. This research work focuses on analyzing the machine learning database by using a labelled dataset to classify legitimate and fraudulent business transactions with explainable AI. This study is based on decision tree, logistic regression, support vector machine and random forest machine learning techniques. 2024 IEEE. -
Advancing Collaborative AI Learning Through the Convergence of Blockchain Technology and Federated Learning
Artificial intelligence (AI) has revolutionized multiple sectors through its growth and diversification, notably with the concept of collaborative learning. Among these advancements, federated learning (FL) emerges as a significant decentralized learning approach; however, it is not without its issues. To address the challenges of trust and security in FL, this paper introduces a novel blockchain-based decentralized collaborative learning system and a decentralized asynchronous collaborative learning algorithm for the AI-based industrial Internet environment. We developed a chaincode middleware to bridge blockchain network and AI training for secure, trustworthy and efficient federated learning and presented a refined directed acyclic graph (DAG) consensus mechanism to reduce stale models impact, ensuring efficient learning. Our solutions effectiveness was demonstrated through application on an energy conversion prediction dataset from hydroelectric power generation, validating the practical applicability of our proposed system. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Advancing Climate Services in South Asia: The SARCI Framework for Actionable Climate Information and Regional Capacity Building
South Asia, home to over a quarter of the global population, faces escalating climate risks that demand scientifically credible and actionable information. However, existing global climate models exhibit persistent temperature and precipitation biasesvariables central to impact assessmentsreaching up to 25% and 100% of their mean values, respectively, over this region, thereby limiting their reliability for climate-informed long-term planning. To address these limitations, we introduce the South Asia Regional Climate Information (SARCI) frameworka regionally optimized framework designed to deliver credible, high-fidelity climate information for South Asia. The framework features a customized atmospheric model, based on NCAR CESM/ CAM, with targeted improvements in deep convection, landatmosphere interactions, and gravity wave dynamicsprocesses linked to major regional biases. These enhancements are guided by empirical understanding of regional climate behavior and refined through rigorous model tuning to achieve regional improvements without compromising global performance. The customized model substantially improves simulations of temperature and precipitation, along with a more realistic representation of regional circulation. The framework further incorporates a synthesized lower-boundary forcing component derived from skill-based CMIP models, adjusted to reduce biases in its low-frequency variability. A statistical downscaling module then refines the projections to a quarter-degree resolution, providing fine-scale, policy-relevant regional climate information. The SARCI framework demonstrates how regional optimization, coproduction, and institutional capacity building can deliver credible, policy-relevant climate information for South Asia, with broader relevance for other regions of the Global South facing similar challenges. 2026 American Meteorological Society. -
Advancing climate justice: Aligning the strategies with SDGs
The Sustainable Development Goals (SDGs), a collection of universal objectives focused on sustainable development, were established by the UN in 2015 in view of its 2030 Agenda for a sustainable future. The SDGs tackle urgent environmental problems related to the Anthropocene like climate change and pertinent socioeconomic complexities. Human-made climate change is a serious worldwide concern that threatens the accomplishment of all SDGs, including SDG 13, a specific climate target. However, an alignment of these goals with climate justice is crucial to address the challenges faced by the vulnerable and marginalized strata of society. Justice is a highly acclaimed value of human survival and international collaborative efforts. The application of a justice perspective to the discussions of climate change and SDGs will provide more significance to the claims. In light of the above, this chapter explores SDGs and related strategies for advancing the cause of climate justice. 2025 by IGI Global Scientific Publishing. All rights reserved. -
Advancing Climate Finance for Sustainable Future: Integrating Human Capital, Climate Neutrality, and Emerging Technologies
The Intergovernmental Panel on Climate Change (IPCC) laid the scientific groundwork for the widespread agreement that, in the medium and long terms, development and inclusive growth are seriously threatened by climate change caused by humans. The importance of sustainable development and the pressing need to address climate change cannot be underscored in the rapidly evolving global setting. A key tool for reaching carbon neutrality and greening sustainable economic growth is Climate Finance, which is centered on eco-friendly investments and activities. By supporting renewable energy sources like solar and wind power, climate finance assists nations in lowering their greenhouse gas emissions. It also aids in community adaptation to the effects of climate change. Combining human capital and emerging technologies such as blockchain, Artificial Intelligence (AI) with climate finance is an additional opportunity to boost migration prospects and ease transitions in adaptation processes. Furthermore, in addition to addressing concerns about the potentially negative effects of some climate policies on development prospects and economic growth, an integrated policy package incorporating the scaling up of low-carbon and climate-resilient infrastructure, sustainable finance, and carbon pricing could also help achieve the goals of the UN Sustainable Development Goals (SDGs) and the Paris Agreement. In order to solve urgent environmental issues and achieve sustainable development goals, climate finance must improve. This chapter explores the need of climate finance and human capital with evolving technologies. Further, it analyzes the synergy of climate finance with climate neutrality and challenges and barriers in the achievement of sustainability. Furthermore, a need for a regulatory framework for achieving climate neutrality in terms of climate finance is discussed. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Advancing Building Damage Classification Accuracy through Machine Learning-Based Model Design using High Resolution Remote Sensing Images
The ability to evaluate the damage to buildings both accurately and precisely is essential for disaster recovery, planning, and rescue services. This paper proposes a new approach based on integrating machine learning algorithms in building damage classification. To achieve higher precision in classifying the level of building damage, this research proposes a new technique that employs machine learning strategies. The researchers were able to train the model to be able to differentiate the different levels of building damage and the feature extraction was performed through machine learning. The model effectively extracts and learns multiple complex signals which represent different degrees of damage from a well picked database which include several degrees of damage. In a single pass, the Siamese U-Net can perform feature extraction and similarity measurement between two different images. The efficiency and effectiveness of the Siamese U-net model can be increased by reducing inference time, thus increasing its ability to deliver faster predictions while also improving its accuracy. The suggested Enhanced U-Net (EU-Net) could greatly increase the accuracy of building-level classification. As it turned out, the results are very promising and reach beyond traditional approaches with bringing more sample opportunities of machine learning integration in the building damage assessment context. Additionally, this study believes that the accuracy of building damage classification can be further enhanced demonstrating the usefulness of machine learning in disaster management. 2025 World Scientific Publishing Company. -
Advancing Brain Tumor Segmentation in MRI Scans: Hybrid Attention-Residual UNET with Transformer Blocks
Accurate segmentation of brain tumors is vital for effective treatment planning, disease diagnosis, and monitoring treatment outcomes. Post-surgical monitoring, particularly for recurring tumors, relies on MRI scans, presenting challenges in segmenting small residual tumors due to surgical artifacts. This emphasizes the need for a robust model with superior feature extraction capabilities for precise segmentation in both pre-and post-operative scenarios. The study introduces the Hybrid Attention-Residual UNET with Transformer Blocks (HART-UNet), enhancing the U-Net architecture with a spatial self-attention module, deep residual connections, and RESNET50 weights. Trained on BRATS20 and validated on Kaggle LGG and BTC_ postop datasets, HART-UNet outperforms established models (UNET, Attention UNET, UNET++, and RESNET 50), achieving Dice Coefficients of 0.96, 0.97, and 0.88, respectively. These results underscore the models superior segmentation performance, marking a significant advancement in brain tumor analysis across pre-and post-operative MRI scans. 2024 by the authors of this article. -
Advancing Brain Tumor Recurrence Prediction: Integrating AI andAdvanced Imaging Technologies forEnhanced Prognosis
Integrating artificial intelligence (AI) and advanced imaging technologies in medical diagnostics is revolutionizing brain tumor recurrence prediction. This study aims to develop a precise prognosis model following Gamma Knife radiation therapy by utilizing state-of-the-art architectures such as EfficientNetV2 and Vision Transformers (ViTs), alongside transfer learning. The research identifies complex patterns and features in brain tumor images by leveraging pre-trained models on large-scale image datasets, enabling more accurate and reliable recurrence predictions. EfficientNetV2 and Vision Transformers (ViTs) produced prediction accuracy of 98.1% and 94.85%, respectively. The studys comprehensive development lifecycle includes dataset collection, preparation, model training, and evaluation, with rigorous testing to ensure performance and clinical relevance. Successful implementation of the proposed model will significantly enhance clinical decision-making, providing critical insights into patient prognosis and treatment strategies. By improving the prediction of tumor recurrence, this research advances neuro-oncology, enhances patient outcomes, and personalizes treatment plans. This approach enhances training efficiency and generalization to unseen data, ultimately increasing the clinical utility of the predictive model in real-world healthcare settings. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Advancing Brain Tumor Detection with Deep Learning and Machine Learning: A Performance Analysis of Different Deep Learning Models
The current study examines the difficulty of employing a deep learning architecture to diagnose brain tumors quickly and effectively. Our study is built upon a dataset of 253 MRI pictures that have been carefully categorized by medical experts as either positive (Yes) or negative (No) for brain tumors. To guarantee the robustness of model performance, the dataset is carefully divided into training and validation subsets, with 70% set aside for training and 30% for validation. We analyze the diagnostic performance of several machine learning models, including K-Nearest Neighbors (KNNs), Recurrent Neural Networks (RNNs), Support Vector Machines (SVMs), Convolutional Neural Networks (CNNs), and Artificial Neural Networks (ANNs). When these algorithms are applied to MRI scans, brain tumors can be quickly detected, and the increased accuracy makes patient treatment easier. The findings of this study could lead to a rapid and accurate diagnosis of brain tumors, which would greatly enhance patient care and treatment. The results also show how deep learning frameworks can transform medical image processing and diagnosis. This work offers a thorough review of recent findings and techniques for MRI scan-based deep learning-based brain tumor detection. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.