Browse Items (3095 total)
Sort by:
-
Real-World Breast Cancer Imaging DataLLM Led Analytics for Insights and Evidence Generation
Breast cancer remains one of the most prevalent and deadly forms of cancer worldwide, affecting individuals across all ages and sexes. In recent years, artificial intelligence (AI) and machine learning (ML) have emerged as transformative tools in the field of medical diagnostics, offering the potential to enhance the detection, diagnosis, and prediction of breast cancer. Despite these advancements, challenges remain, including the need for large, diverse datasets to train robust models, the integration of AI tools into clinical workflows, and addressing ethical concerns related to AI in healthcare. This paper explores the application of Large Language Models (LLMs) using embeddings in breast cancer management, focusing on its ability to analyze medical data, including imaging, histopathology datasets to identify patterns that may be imperceptible to human experts. Datasets from real-world setting have been secured for analysis across multiple models. Convolutional Neural Network (CNN) model and custom-built large language model are employed to demonstrate the precision and accuracy of Generative AI techniques and observed that custom-built LLM with 98.44% outperforms the traditional AI approaches such as CNN with 61.72%. Future studies can further establish how these models can assist in stratifying patients based on risk, thereby enabling personalized treatment plans that can reduce overtreatment and improve quality of life. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
A Comparative Study on IOT Security Using Machine Learning Techniques
This increased reliance on networks has made the security of IoT devices a highly burning issue. Among the sea of threats, the threats associated with DDoS attacks are at a high level since they do damage to the functionality of devices and unavailability of networks. Detection and mitigation of DDoS attacks will demand IoT environments based on powerful classification algorithms. This paper evaluates the performances of three prominent algorithms: Decision Tree, Random Forest, and Histogram-Based Gradient Boosting for the classification of DDoS attack traffic within IoT networks. An IoT-23 dataset comprising a subset of attacks, including DDoS, is used herein for the purpose of achieving high classification accuracy to ensure a reliable evaluation of attacks. The results clearly show that all three algorithms are pretty good in terms of detection performance, and Histogram-Based Gradient Boosting is the best in terms of generalization accuracy. These results open new perspectives for the implementation of machine learning, generally, and Histogram-Based Gradient Boosting, specifically, directed to improving security in IoT networks against DDoS attacks, which is an extremely promising result when working within the light of some insights for future research and development within this critical area of security. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
A Review on Development and Properties of Ultra-High-Performance Concrete
This study presents a review of literature on ultra-high-performance concrete that brings in information regarding the preparation of UHPC, mix design of UHPC on the basis of various particle packing density models, microstructural analysis, durability studies, and strength characteristics. A data base is collected to study the performance, mechanical strength and durability of UHPC from various research works. UHPC can found to be a long-term solution for present day challenges that is faced in construction industry when conventional concrete is used and makes this concrete a novel concept in concrete technology. The advantages of UHPC are: less porosity, high abrasion resistance, greater mechanical properties, high packing density, and improvement in fatigue behavior though the cost of UHPC is high. The non-availability of a standard code for mix design of UHPC makes it difficult to arrive at consistent and comparable mix. The cost of UHPC can be controlled with the use of naturally available materials and utilizing agricultural and industrial waste materials in UHPC. From the data collected, it is observed that the binder content can be optimized and cement which is residual in UHPC can be replaced by industrial residue like fly ash, GGBS, glass powder, etc. and thereby brings down the cost without compromising on the strength and performance. The information shared in this paper will help the contractors, consultants, engineers, industry stakeholders and researchers to alleviate the confusions regarding the use of UHPC in construction industry and to encourage research to make this concrete construction-industry friendly. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Impact of the Internet on Human Life a Data-Driven Analysis Using Machine Learning and Statistical Correlations
These days Internet is became an essential part of human life and affects various domains which includes education, business, social interactions, mental health. It pushes the society ahead through increasing innovations, amplifying learning techniques, connecting people across the globe and access to vast resources which makes it a valuable tool in this modern society. But it comes with problems such as Internet addiction, sleeping disorders, health complications. This abstract discusses about dual impact of Internet uses, focusing on its significant benefits and possible dangers. Hence, there is need to manage use of Internet so one can make use of its benefits at the same time reducing the affects which are caused by Internet on human life. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Indian Stock Market Prediction Using Neural Networks: A Comparative Analysis
Predicting stock prices remains a challenging problem due to the highly dynamic and nonlinear nature of financial markets. Traditional statistical models like ARIMA and GARCH often fail to capture the complexities inherent in stock market data. This paper investigates the use of deep learning techniques, focusing on Convolutional Neural Networks (CNNs) and a hybrid CNN-LSTM ensemble model for stock price prediction in the Indian stock market. The CNN model efficiently extracts temporal patterns from sequential data, while the CNN-LSTM ensemble leverages temporal dependencies for improved long-term prediction accuracy. Historical data from Tata motors, spanning over two decades, was used to train and evaluate the models. Experimental results highlight the CNN-LSTM ensemble's superior performance in capturing volatile trends and long-term dependencies, with a notable decrease in test loss compared to standalone CNN. This study underscores the effectiveness of hybrid deep learning architectures in enhancing prediction reliability, paving the way for more adaptive and robust financial forecasting systems. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Path Planning of KR6 R900 Vision Sensor Assisted KUKA Industrial Robot for Pick and Place Application
In this paper, a new multi-objective functions comprising of squared values of joint jerk, acceleration, torque rate and total travel time subjected to kinematic and dynamic constraints have been formulated for achieving optimal trajectory for industrial applications. Then four different multi-objective optimization algorithmsthe multi-objective particle swarm optimization technique (MOPSO), the multi-objective genetic algorithm (MOGA), non-dominated sorting genetic algorithm-II (NSGA-II) and the proposed multi-objective enhanced teaching learning-based optimization (MOETLBO)have been utilized to obtain the optimal solution for trajectory planning. Finally, the experimental validation of the proposed technique and the summarization of simulation results have been done as a comparative study of the four different metaheuristic techniques for pick and place application of KR6 R900 KUKA industrial manipulator. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Dreamscapes and Virtual Realms: Exploring VRs Impact on Dream Patterns
In recent years, psychologists have been exploring the impacts of virtual reality on mental health, discovering its potential toward curing diseases and therapeutic tools for many such mental conditions. In conventional exposure therapy, the ability of patients to successfully visualize particular feared stimuli is a prerequisite for imaginal exposures. On the flip side, various VR-related tasks have been conducted to test the impact on dreams. This study examines the impact of VR on dreams and analyze the changes in its patterns. By reviewing the recent papers, we concluded that the potential harm caused by VR is well established, with negative side effects reported since the early 1990s. Seven of these twenty-three studies either did not report global incorporation rates or failed to provide sufficient data to determine them. The side effect profile associated with the clinical use of VR and AR remains largely unknown; therefore, we systematically reviewed available evidence of their adverse effects. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Leveraging Big Data and AI for Optimizing Health Insurance Claims and Risk Assessment in Healthcare Financing
This research elucidates the transformative potential of big data analytics and artificial intelligence in optimizing health insurance claims and risk assessment by employing an empirically robust framework encompassing reliability and validity metrics, Heterotrait-Monotrait Ratio (HTMT) analysis, and bootstrapping to unravel the intricate interdependencies among constructs such as AI model accuracy, claims processing efficiency, cost efficiency, data quality, fraud detection accuracy, system usability, and user trust interface, thereby advancing a comprehensive understanding of the systemic synergies that enhance predictive precision, operational scalability, and equitable resource allocation within the healthcare financing paradigm. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Deep Learning for Uncovering of Fraud: A Design for Automated Financial Protection
Leveraging the unparalleled adaptability and hierarchical feature stratification capabilities of deep learning, this study constructs a sophisticated framework for fraud detection, seamlessly integrating convolution and recurrent neural architectures with advanced anomaly detection algorithms to decode complex, nonlinear transactional patterns within heterogeneous financial datasets, thereby enabling real-time fraud identification while addressing pivotal challenges of algorithmic interpretability, adversarial resilience, regulatory compliance, scalability, and data confidentiality, ultimately redefining the paradigm of automated financial security in an increasingly digitized global economy. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Smart Healthcare Systems and Artificial Intelligence: Leveraging Data-Driven Solutions in Healthcare
Smart healthcare systems, powered by artificial intelligence (AI), enables drastic shift in healthcare sector. The benefits of data-driven solutions anchored in advanced disease diagnosis, efficient administrative records management, and operational efficiency. AI algorithms, including machine learning and deep learning, enable real-time data analysis from diverse sources such as Internet of medical Things (IoMT), wearable devices, and medical imaging. This facilitates early disease detection, personalized treatment plans, and predictive analytics, leading to improved health outcomes. Additionally, AI-powered systems optimize resource management, reduce human error, and streamline administrative tasks. While challenges such as data privacy, integration complexities, and ethical concerns exist, the potential of smart healthcare systems to revolutionize healthcare delivery is undeniable. This study explores the role of AI in advancing smart healthcare, focusing on the integration of data-driven technologies to create a more efficient, accessible, and patient-centered healthcare ecosystem. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
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. -
Designing of a Human-Centric Autonomous Fish-Feeding Robot: Advancing Aquaculture Sustainability Through Enhanced HumanRobot Interaction
The increasing need for sustainable and efficient aquaculture practices due to rising global seafood consumption and challenges such as labor shortages, environmental degradation, and inefficiencies in manual feeding methods highlights the crucial requirement for an autonomous fish-feeding robot. Service robots are usually designed as a mechatronic design issue focused on implementing essential technological functions, frequently neglecting the significance of intuitive operation and usability. Using the double diamond design framework, this study details the development of a human-centered autonomous fish-feeding robot for fish farming. The goal was to make it more user-friendly and sustainable. The project began the discovery phase to gather insights into aquaculture difficulties and find potential for innovation in fish-feeding procedures. Around 38 small- and medium-sized fish farmers from Andhra Pradesh, Tamil Nadu, and Odisha were interviewed to gather their needs for fish farm feeding systems. In the Define phase, the focus shifted to developing a system that optimizes feeding efficiency while considering environmental factors and user requirements. During the development process, the team utilized iterative design and prototyping, incorporating modern technology such as AI for accurate feed distribution and sensors for evaluating water quality and fish health. User comments played a vital role in enhancing the robots usability and functionality. The Deliver phase concentrated on deploying the robot in simulation environments using ROS AND GAZEBO for the technical feasibility test, assessing its influence on operational efficiency and waste reduction, and advocating for sustainable aquaculture methods. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Integrating SMOTE and Heterogeneous Ensemble Methods for Online FraudDetection
In the continuous evolving digital era, the escalation of online fraud demands a robust and efficient mechanism for its detection and prevention. In the recent years there has been a significant increase in the online bank transactions. The research delves into the integration of different machine learning algorithms and to enhance the models adaptability, Synthetic Minority Oversampling Technique (SMOTE) has been utilized. The approach addresses the challenges of data imbalance and also strengthens the overall detection performance. Through an extensive literature review the study highlights the limitations in the existing issues in online financial fraud. The proposed model employs a heterogeneous ensemble model consisting of K-Nearest Neighbors (KNN), Random Forest, and XGBoost. KNN functions as an anomaly detector, identifying irregularities in transactional data. Simultaneously, Random Forest assesses feature significance and detects intricate patterns, contributing to a comprehensive understanding of fraudulent activity. XGBoost, known for its computational efficiency, ensures real-time responsiveness by adapting to emerging fraud tactics. The system also introduces a soft voting mechanism that seamlessly integrates individual algorithm predictions, resulting in a robust and highly accurate ensemble fraud detection system. Validation on an authentic bank fraud dataset underscores the framework's prowess, showcasing superior fraud detection capabilities and a significant reduction in false positives. The purpose of adopting this approach is to enhance the financial security and safeguard the consumers assets. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
A Fuzzy Logic Approach for Prioritizing Customer Retention Strategies in OTT Video Platforms
The emergence of over-the-top (OTT) video platforms has significantly transformed the way people consume content and the entire media landscape. The significant growth of OTT video platforms in recent years, amidst fierce competition and changing consumer preferences, has posed a challenge for the platforms in retaining customers. Elevated churn rates in the OTT video platforms have prompted them to focus on customer retention. OTT platforms implemented different strategies to retain customers. The customer retention strategies are identified through a literature review and unstructured interviews with industry experts. This paper presents a novel approach to prioritize customer retention strategies using a fuzzy analytic hierarchy process (fuzzy AHP). The fuzzy AHP analysis results show that content strategy is the most significant, followed by pricing, customer experience, and platform extension. This paper provides actionable insights for OTT platform managers, helping them enhance user satisfaction and retain customers. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Prioritizing Risks in IoT-Enabled EdTech Platforms: A Fuzzy AHP Approach to Maximize User Satisfaction
The integration of the Internet of Things (IoT) in educational technology (EdTech) platforms offers personalized, adaptive learning but introduces significant risks. This study identifies and prioritizes these risks using the Analytic Hierarchy Process (AHP) and fuzzy AHP techniques. Seven industry experts provided input, complemented by a comprehensive literature review. The analysis reveals ethical considerations (30.17%) and data privacy/security (29.22%) as top concerns, followed by regulatory compliance (12.91%), high implementation costs (10.99%), and technical expertise requirements (8.37%). Surprisingly, scalability concerns (1.70%) and data accuracy/reliability (2.63%) rank lower. These findings emphasize the need for a human-centric approach in IoT-enhanced EdTech deployment, focusing on responsible implementation and regulatory adherence. The study provides valuable insights for EdTech companies and educational institutions, guiding strategic decision-making to enhance user satisfaction and ensure sustainable development of IoT-enhanced educational platforms. Future research could explore more advanced mathematical models and context-specific challenges to refine risk prioritization strategies. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
A Study on Impact of Dopants on Piezoelectric Parameters of Aluminium Nitride
Doping is a critical in piezoelectric base materials used as sensors or energy harvesters. It has a significant effect in determining the output parameters of an energy harvester. This paper studies the effect and impact on piezoelectric properties when materials are co doped and singly doped by considering some common dopants found in the literature. From the study, the elastic constant and c/a ratio are found to be decreasing and all other lattice parameters such as piezoelectric stress coefficient, electromechanical coupling constant, Born effective charge etc. are increasing, although some discrepancies are there. Scandium, magnesium, Lithium and its co-dopants are mainly considered for the study. Another factor that should be considered is doping concentration. Excessive doping with scandium (Sc) has been demonstrated to reduce the coercive field (Ec), enabling ferroelectric switching in AlScN thin films. The critical factor for achieving ferroelectric switching lies in sufficiently lowering the energy barrier between the two polarization states made of the wurtzite structure. This can be accomplished either by increasing the proportion of the non-Group-III metal or through strain engineering. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Artificial Intelligence: A Catalyst for Change in the Indian Automobile Industry
AI is becoming a major game-changer economically and technologically across various sectors in the world. The Indian automotive industry is one such area of development. This paper discusses AIs impact on Indian automotive sector right from supply chain management, boost in production, smart AI systems through predictive maintenance, customization capabilities and development of autonomous vehicles. The Indian automotive industry is one such industry that greatly adds to the countrys GDP and employment, but at the same time presents challenges in terms of infrastructure, logistics and changing consumer needs that AI can address. With the advent of campaigns like Make in India and Digital India, India seeks to position itself as one of the leading figures in international production, and for this, the adoption of AI measures seems of strategic importance as this will facilitate productivity growth, competitiveness and meeting the aims of sustainable development (Aggarwal et al. in J Technol Forecast Soc Change 170, 2021 [1]; Chui et al. in AI adoption and economic growth: The case of India. McKinsey Global Institute, 2022 [6]). Through case studies of Indian companies and new startups using AI technologies, this research focuses on how AI can tackle complex supply chains, cut production costs and satisfy consumer expectations for going green, safety and personalization. At the same time, AI usage in India has its own challenges such as expensive introduction, lack of skilled labour, protection of personal data and strict rules. This paper posits that given the necessary assistance from the state, together with the cooperation of the industry and investment in AI specialists, the Indian auto industry is able to use AI for scaling in a competitive environment and to become part of Indias economy in a larger context. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Performance Evaluation of CPU and GPU Processors Using Advanced Data Analysis Techniques
The modern industry is developing advanced CPU and GPU processors. The standard efficiency difference between the Intel Core i5 and 11th Gen with Nvidia GTX3050 processors is being discussed in this article. However, the reduction factor between these processors is determined to be as 2.5. Various data visualization techniques were applied to give a comprehensive analysis of the performance of CPU and GPU-based processors for execution of intensive tasks. The results were analyzed to understand the various performance parameters related to their functioning and efficiency. A model was proposed for enhancing the performance and throughput of the processor by easing the internal communication process between the CPU and the GPU by converting from electrical signals to light signals, though being faced with many challenges in the current time, holds a large scope of further research in the pursuit of higher computational efficiency. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Machine-Learning Based Sleep Pattern Analysis Using Linear Regression Algorithm
This article is investigating the connection between sleep patterns and concentration spans among university students while exploring the potential influence of MyersBriggs Type Indicator (MBTI) personality types on these aspects. The primary objective is to understand how sleep duration affects students ability to maintain focus and how their personality traits might interact with this relationship. Data was collected from university students aged 1619 using a multiple-choice form. The key variables analyzed were age, MBTI personality types, sleep duration, concentration span, and effective study ranking. Pearson's correlation was employed to examine these relationships. Additionally, a linear regression model was developed to predict concentration span based on sleep hours. The findings revealed a strong positive correlation 0.758 between sleep duration and concentration span, suggesting that increased sleep is associated with longer concentration spans. A moderate positive relationship 0.249 was also observed between concentration span and effective study ranking. However, the analysis showed a negligible relationship ? 0.008 between MBTI personality types and concentration span, indicating that within the context of this study, personality type does not significantly influence concentration span. This research emphasizes the critical role of sleep in academic settings and challenges the assumption that personality types significantly impact concentration span and sleep patterns. The linear regression model developed provides a predictive tool for understanding the impact of sleep on concentration, underscoring the importance of adequate sleep for academic success. This research is contributing to the broader understanding of factors influencing student performance and offers practical insights for optimizing study habits and educational strategies. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Chronic Disease Diagnosis Using Multi-modal Transfer Learning Model
Chronic diseases are on rise in recent times and symptoms of these disorders need to be detected at an early stage. Traditional methods in handling these risks are quite resource intensive and costly with less accuracy. This paper explores transfer learning to address the challenge of limited data in diagnosing chronic diseases like chronic kidney disease, breast cancer, hepatitis, and Alzheimers. We propose a multi-modal framework utilizing pre-trained models: image recognition for medical images and natural language processing for textual data. Transfer learning aims to improve diagnostic accuracy and reduce training time, enabling development of adaptable tools for various chronic diseases. The implementation results show the performance of the model is promising generating an accuracy rate of 94%. Also the model gave a mean accuracy of 93.3% when tested with different chronic disorders. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.