Browse Items (3095 total)
Sort by:
-
A Fuzzy AHP Approach to Evaluation of Value Addition in the Indian Medical Equipment Supply Chain
The research delineates the risks within the supply chain that impede firms from achieving optimal value-added ratios. A comprehensive inventory of medical equipment crucial to healthcare is identified, and manufacturing and order fulfilment durations are ascertained through non-participatory observation. Employing these durations, the value-added ratio is computed for each piece of medical equipment to assess the firms performance. The study divulges that the average value-added ratio for hospital laboratory equipment is alarmingly low, signifying the prevalence of non-value-added activities resulting in augmented costs and protracted turnaround times. Furthermore, hospital diagnostic and surgical equipment, although exhibiting higher value-added ratios in comparison with laboratory equipment, still evince an average value-added ratio below fifty per cent, underscoring that over half of the activities along this supply chain are non-value-added. These findings accentuate the necessity of addressing these issues to bolster the value addition within the Indian medical equipment supply chain. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Evaluating Sentiment Classification Models for Bollywood Movies
The rise in popularity of Bollywood cinema, fueled by streaming services such as Netflix and Amazon Prime, has increased the global availability of Hindi-language films. This study investigates the sentiment analysis of Bollywood movie reviews using a dataset of 1,698 movies released between 2005 and 2017. The research examines three main dimensions: confusion matrix, evaluation metric, and random forest model. The results highlight the model's ability to accurately predict emotions, especially when detecting neutral and positive emotions. Challenges in identifying negative emotions persist. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Machine Learning Models for SMS Spam Detection
With the increasing reliance on mobile communication, detecting spam messages sent via Short Messaging Service (SMS) has become more important. This advent has created a new era for spam in peoples lives, one that calls for quick attention and automatization in categorizing messages. This study analyzes three machine learning algorithmsLogistic Regression, Naive Bayes, and Decision Tree resulting in the binary classification of SMS messages into either spam or not spam (ham). To achieve effective spam detection, the study highlights the significance of feature engineering, model selection, and evaluation metrics such as accuracy, precision, recall, and F1-score. The research challenges, including unbalanced data, changing spam strategies, and the requirement for scalable solutions, are handled in this study. During experimentation, it was observed that Logistic Regression increased performance by 98.07% accuracy. The results also showed the advantages and disadvantages of each model, providing guidance on which strategy, is best for SMS spam filtering apps in the real world. This analysis aims to give readers a thorough grasp of existing approaches and how they might be used to improve the effectiveness and security of mobile communication systems. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Machine Learning in Intrusion Detection: A Comprehensive Analysis
Intrusion detection systems (IDS) are employed to investigate anomalous behavior in a network system, which monitors a network system for suspicious behavior, which is essential for maintaining network security. Improving accuracy in intrusion detection is necessary to lower false alarms and boost detection rates. Support Vector Machine (SVMLinear and Quadratic), Long Short-Term Memory (LSTM), and k-nearest neighbors (kNN), machine learning techniques for intrusion detection in network environments, are compared in this research. The effectiveness of SVM, which is well-known for its resilience in high-dimensional environments, in differentiating between normal and malicious behavior is examined. Straightforward yet powerful algorithms, namely KNN and LSTM, are analyzed to see how well they can adjust to different types of intrusions. Regarding detection accuracy, false positive rates, and response times, the experimental results on a benchmark intrusion detection dataset highlight the advantages and disadvantages of the models considered for the study. This study suggests incorporating machine-learning approaches into real-time intrusion detection systems to improve network security and lessen cyber risks. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Design of Heart Rate Monitoring System Using Visual Simulation Tool
In this research paper, a wireless heart rate and temperature monitoring system using Packet Tracer is proposed and put into operation. A wearable bracelet with sensors that can track temperature and heart rate in real time is integrated into the system. The patient and the attending physician receive the gathered data wirelessly for in-depth health monitoring and analysis. This system is used to provide a practical and effective way to track vital signs in real-time, especially temperature and heart rate. The system's functionality and performance can be thoroughly evaluated and validated in a controlled environment thanks to this simulation. Additionally, the system includes functions for data analysis and visualization to help medical professionals make well-informed decisions. To increase the accuracy and accessibility of heart rate monitoring, which would eventually enhance patient outcomes and general wellbeing, the proposed initiative aims to address these challenges. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Dynamic Scheduling of Scientific Workflows with Budget-Constraints in the Cloud
This research presents a novel approach to dynamic scheduling in cloud computing environments, directing on budget-constrained workflows and towards optimizing makespan, Quality of Service (QoS) metrics, and energy efficiency. Exploiting the Task Duplication Scheduling Algorithm (TDSA) and Salp Swarm Algorithm (SSA) which is influenced by the motion patterns of marine life forms, the proposed Enhanced Salp Swarm Algorithm (ESSA) algorithm dynamically assigns tasks to cloud resources while bearing budget curbs. The algorithm seeks to reduce makespan, guaranteeing efficient completion of workflows, at the same time boosting the QoS metric resource utilization. Moreover, the incorporation of energy-efficient scheduling techniques further donates to the sustainability of cloud environment operations. By constructing a mathematical representation which captures the trade-off between makespan, resource utilization, and budget constraints, the mechanism productively balances competing objectives to reach optimal scheduling outcomes. Through substantial experimentation with 5 Scientific Workflows, the success and efficiency of the suggested methodology are assessed, exhibiting its potential to significantly improve the performance of budget-restricted workflow in cloud environments while boosting workflows makespan (up to 9%) and improving asset usage (up to 5%) and energy efficiency (up to 10.5%). This research presents to advancing the latest in dynamic scheduling techniques for cloud environment, benefitting practical solutions for real-world deployment and operation. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Blockchain Technology in Higher Education: Opportunities, Applications, and Network Security Challenges
Blockchain technology has garnered attention beyond its origins in cryptocurrency, positioning itself as a robust solution to the security and administrative hurdles faced by higher education establishments. This paper delves into how the decentralized nature and unchangeable ledger of blockchain could enhance the management of academic records, bolster data security, and streamline administrative processes in institutions. In the contemporary era of digitization, higher education increasingly depends on digital platforms for record-keeping, offering advantages like accessibility and efficiency, yet also presenting susceptibilities to cyber threats. Conventional centralized databases are prone to tampering, breaches, and unauthorized entry, jeopardizing the confidentiality of student information. Blockchain emerges as a feasible remedy by furnishing cryptographic security that ensures the immutability and openness of data. This research scrutinizes blockchains potential to elevate the security of academic records, diminish fraud, and refine administrative workflows within establishments. It scrutinizes real-life cases and practical applications of blockchain to assess their efficacy in safeguarding student data and upholding academic honesty. Moreover, it tackles the challenges and apprehensions related to implementation that are vital for the successful integration by educational institutions. By addressing these issues, the research aids in elucidating how blockchain could enhance the record-keeping processes in higher education. It showcases blockchains capability to authenticate educational accomplishments adequately, thus safeguarding the reputation of institutions and fostering confidence in academic qualifications. Ultimately, this research pinpoints blockchain as an indispensable technology for modernizing school management and preserving the validity of educational information in an increasingly digital landscape. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Risk Analysis Using Ensemble Learning Model for Smart Energy Sustainability in Indian Cities
Analyzing risks involved in smart energy sustainability entails identifying, assessing, and mitigating diverse types of risks that include financial, operational, and environmental factors that can affect the dependability, efficiency, and ecological friendliness of energy systems in smart cities. The study uses a high-frequency dataset from smart meters in Mathura and Bareilly districts in India collected over 2 years from May 2019 to October 2021 which contains millions of data points. To forecast energy consumption patterns and reveal possible risks we used machine learning models like linear regression, random forest, gradient boosting, and extra tree classifier. By using several machine learning algorithms such as multiple linear regression (MLR), classification trees (CTs), random forests (RFs), and support vector machines (SVMs) this paper developed an empirical model to establish an interrelationship between district heating systems investments influence on the performance improvement variables for sustainable development goals. Notably, the ensemble learning approach had a remarkable precision rate of 94.69% indicating its importance in forecasting and managing demand for power. Moreover, the findings provide insights that could help policymakers and service providers improve urban energy sustainability and efficiency. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Developing an Advanced Cybersecurity Framework and Blueprint: A Contemporary Approach to Counter Hacking Through Reverse Engineering Techniques
Recently many of the world's most secure networks have been breached by hackers, resulting in damage, information theft, data corruption, and threats to both national and international security. Protection experts are now doubting the dependability and efficacy of the current protection measures against hacking assaults in light of this dire situation. This research will use a variety of accepted practice models, global standards, information security frameworks, and best practices to achieve this goal of developing a framework and blueprint for a specialized hacking countermeasure. The deliverable outcome is a technical and administrative hacking countermeasure framework and blueprint because the study will concentrate on technological management practices in addition to hacking countermeasure techniques and tools. The framework and the blueprint were validated and authorized, and the effectiveness and reliability of the study deliverable outcome were confirmed using questionnaire and interview surveys, finding that it fully met the established objectives and scope of work. Furthermore, the validation has demonstrated that the introduced solutions for the Defense-in-Breadth and the deception and concealment strategies can further improve the hacker countermeasure and the development of SNORT rules, the construction of a prototype, and the execution of live testing with the ultimate goal of closing the security gap created by hacker countermeasures in the present defense-in-depth-based security models. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Enhancing Learning and Societal Innovation with Cyber-Physical Systems: Education and Society
Cyber-Physical Systems (CPS) are evolving rapidly and can significantly impact education and society. In this paper, we explore the various technologies and applications of CPS in the context of education and social concerns. Through the integration of computation, networking, and physical processes, CPS can enhance educational experiences, foster social inclusion, and address societal challenges. Using CPS in education allows for intelligent learning environments, personalized learning experiences, and real-time feedback systems that meet the diverse needs of students and encourage them to engage in their learning. With real-time monitoring and response systems, CPS can help develop smart communities, improve accessibility for disabled individuals, and enhance public safety. This paper provides a comprehensive analysis of CPS technologies and their applications, highlighting their transformative potential in education and society, motivating further research and policy development. The implementation of CPS can transform education and society, but enhanced security measures must accompany their implementation. Integrating CPS in real-world applications requires safeguarding sensitive data and safeguarding against cyber-threats. This collaboration ensures that diverse perspectives are considered, leading to more comprehensive solutions that address the multifaceted challenges of CPS deployment. It also enhances the effectiveness and sustainability of CPS applications by combining different expertise. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Nutrition Analysis: A Data-Driven Approach for Optimizing Individual Dietary Choices
Maintaining good health, avoiding illnesses, and controlling ailments like diabetes, heart disease, and obesity all depend on proper diet. With the use of nutrition analysis, people can better understand their dietary requirements and choose foods that will support a healthy lifestyle. The goal of this studys data-driven approach to nutrition analysis is to maximize each persons dietary selections. Individualized recommendations are made for balanced nutrition by utilizing top-of-the-machine learning techniques to examine food patterns, nutrient consumption, and health effects. Food items are categorized based on their nutritional characteristics, and potential health effects are predicted using algorithms like Gradient Boosting, Multi-Layer Perceptron (MLP), Random Forest, Support Vector Classifier (SVC), Gaussian Nae Bayes (GNB), Decision Tree, Stochastic Gradient Descent (SGD), Linear Discriminant Analysis (LDA), and K-Nearest Neighbors (KNN). These models evaluated the relationship between dietary practices and nutritional needs. The final outcome is a comprehensive system that enables people to make knowledgeable food choices and optimize their nutrition in a way that promotes their overall health. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Comprehensive Analysis of Canine Parvovirus Outbreaks: Predictive Modeling and Evaluation Metrics
This paper addresses the persistent threat of Canine Parvovirus (CPV) to canine health, exploring a spectrum of outcomes from recovery to fatalities. Employing a fusion of machine learning techniques and comprehensive evaluation metrics, we present a robust analysis of CPV outbreaks. Our methodology involves the development of a deep learning-based predictive model designed to anticipate CPV case outcomes based on symptoms and diverse contributing factors, with performance monitoring through visualization techniques. The study delves into the intricacies of a dataset featuring diverse features such as age, breed, symptoms, treatment, and geographic location. Through meticulous preprocessing and feature encoding, we establish a powerful deep learning model proficient in discerning intricate patterns within the data. Model evaluation encompasses key metrics, including accuracy, precision, recall, F1-score, confusion matrix, Cohens Kappa, and Matthews Correlation Coefficient, providing a comprehensive assessment of predictive capabilities. Our findings highlight the models proficiency in anticipating CPV outcomes, suggesting potential enhancements in decision-making within veterinary practice. Insights derived from this research contribute to the refinement of CPV diagnosis, treatment, and prevention strategies, ultimately benefiting the well-being of canine companions. The projects results demonstrate the efficacy of the proposed models in forecasting the prevalence and survival rate of the CPV virus in dogs using basic parameters. This approach eliminates the need for costly and time-consuming laboratory tests, typically requiring 1224h for results, showcasing a practical and efficient solution for CPV management. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Prioritizing Risks in AI-Enabled EdTech Platforms: An Analytic Hierarchy Process Approach
Artificial intelligence (AI) has revolutionized educational technology (EdTech) platforms, offering innovative tools and personalized learning experiences. However, the integration of AI into EdTech also introduces significant risks that must be addressed. This study aims to systematically prioritize and evaluate these risks using the Analytic Hierarchy Process (AHP), a structured multi-criteria decision-making tool. Key risks identified include data privacy and security concerns, algorithmic bias and fairness issues, technical reliability and compatibility challenges, personalization and overreliance on AI, accessibility and equity risks, ethical and privacy concerns, operational and financial risks, governance and regulatory compliance risks, and the black box problem of lack of transparency in AI decision-making processes. Through an extensive literature review and expert inputs, the study employs the AHP methodology to capture the diverse dimensions of risk and determine their relative importance. The findings highlight technical reliability and compatibility (27.43%), the black box problem (17.31%), ethical concerns (17.29%), and personalization and overreliance on AI (17.25%) as the top-ranked risks. By identifying critical risk areas, this research informs the establishment of effective risk management strategies, ensuring the responsible and sustainable adoption of AI in EdTech platforms. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Prioritizing Risks in AI-Enabled EdTech Platforms: An Analytic Hierarchy Process Approach
Artificial intelligence (AI) has revolutionized educational technology (EdTech) platforms, offering innovative tools and personalized learning experiences. However, the integration of AI into EdTech also introduces significant risks that must be addressed. This study aims to systematically prioritize and evaluate these risks using the Analytic Hierarchy Process (AHP), a structured multi-criteria decision-making tool. Key risks identified include data privacy and security concerns, algorithmic bias and fairness issues, technical reliability and compatibility challenges, personalization and overreliance on AI, accessibility and equity risks, ethical and privacy concerns, operational and financial risks, governance and regulatory compliance risks, and the black box problem of lack of transparency in AI decision-making processes. Through an extensive literature review and expert inputs, the study employs the AHP methodology to capture the diverse dimensions of risk and determine their relative importance. The findings highlight technical reliability and compatibility (27.43%), the black box problem (17.31%), ethical concerns (17.29%), and personalization and overreliance on AI (17.25%) as the top-ranked risks. By identifying critical risk areas, this research informs the establishment of effective risk management strategies, ensuring the responsible and sustainable adoption of AI in EdTech platforms. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Comparative Performance Analysis of Segmentation Methods in Cervigram Images
One of the most common cancers of the lower female reproductive tract is cervical cancer and it is a major contributor of mortality in developing nations. Screening tests include image analysis of pap smear and colposcope pictures. In image analysis, machine learning techniques can be employed to analyze and interpret images of the cervix through segmentation and extraction of characteristics for the classification of cervix images. K-means algorithm and Gaussian mixture model are popular segmentation algorithms used in cervix region-of-interest extraction. In the context of deep network learning, segmentation means the use of deep convolution networks to accurately identify different objects or regions in an image. R-CNN and Deeplab architectures are among the most frequently employed models in deep learning for automated cervix image processing. In this paper, we have systematically reviewed machine and deep learning models popularly employed in cervical cancer identification through colposcope images. Four carefully chosen models were deployed, and their performance was comparatively analyzed. This research can be a foundation for scientists looking to develop new models for the classification and segmentation of cervical cancer. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Artificial Intelligence: Economic Impact, Labor Productivity, and Policy Implications
Artificial intelligence (AI) is a transformative technology that changes automation and cognitive functions traditionally performed by humans. This research examines the various economic effects of AI, emphasizing its ability to enhance productivity and disrupt labor markets. AI, while it may have automated tasks, has also created new job opportunities and transformed existing roles. The rise of AI has led to significant economic disturbances, especially in terms of unemployment. Today, businesses are more inclined toward AI rather than a human workforce because it is more cost-effective and time-effective. This tendency is evident not only in the financial sector but also in education and e-commerce where the use of artificial intelligence has significantly improved service quality and productivity. However, this transition also presents challenges like joblessness and an educated workforce that rightly deserves strong policy frameworks that put ethical guidelines, global cooperation, and optimistic breakthroughs first while tackling social inequalities. In spite of advancements, further experiential research is required to grasp the consequences of these policy approaches completely. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Bridging Sustainable Innovation: Developing a Regulatory Sandbox Model for FinTech Products
The evolution of the regulatory sandboxes in the world and its impact on the rapidly growing FinTech sector in the world is explored in this study, while comparing the successful sandboxes from around the world, relatively modified sandboxes for India is proposed. With the FinTech sector witnessing significant growth in recent years, the paper highlights the risks of scams and frauds, emphasizing the need for regulatory sandboxes to mitigate these challenges before introducing the product into the market. By comparing successful models of the United Kingdom and Singapore, the research identifies gaps in the existing Indian framework and proposes a tailored regulatory sandbox model. The modified model adds feasibility and sustainability assessments, which ensures a balanced approach to innovation, consumer protection, and financial stability. It explains the different eligibility criteria required to be met at each stage of the pilot testing as per Indian policies and explained the benefits of such tailored sandbox to the regulators, firms as well as the users of FinTech products. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Enhancing Pneumonia Diagnosis with Convolutional Neural Networks: A Comprehensive Evaluation
Pneumonia, a significant health concern globally, presents unique challenges in diagnosis and treatment due to its diverse ethology and impact on respiratory function. The potential of augmentation techniques and Convolutional Neural Networks, for automated pneumonia detection is explored in this study. Employing a transfer learning approach with VGG16, DenseNet, and our proposed model achieves outstanding accuracy (95%) and robust performance metrics. The research explores augmentation techniques to enhance the precision and accuracy of the model, emphasizing the importance of data augmentation in improving classification accuracy. A comparative analysis with related models highlights advancements in automated pneumonia detection, showcasing the efficacy of our proposed model. The models ability to correctly identify pneumonia from chest X-ray pictures is demonstrated by the results, suggesting that medical image analysis could benefit from practical implementation of this model. Future directions include expanding the dataset, exploring alternative architectures, and integrating explanation techniques to enhance model interpretability. This research contributes to the advancement of artificial intelligence in healthcare, offering a promising approach for accurate and efficient pneumonia diagnosis, thus addressing critical challenges in respiratory medicine. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
On C-Perfection of Modular Product of Graphs
A graph G is said to be C-perfect if, for all induced subgraphs H of G, the induced cycle independence number is equal to its corresponding induce cycle covering number, where every vertex in H belongs to at least one cycle in H. This article deals with the study on C-perfection of modular product of graphs. Through this article, we study various structural properties of C-perfect modular product of graphs and also characterize them. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Analysing Twitter User Behaviour with Process Mining: A Study on Activity Patterns
Social media sites provide a platform to share the information. People share their views and interests. Social media data provides information on user, activity, network, and content. Researchers anticipate a lot of information from social media data. It covers the activities of user, people connected to them, and their likes and dislikes. If users data is processed keenly, one can easily understand a users behaviour with his actions and predicts the next action of the user. It also helps in describing the relations among the users. This study illustrated the process mining algorithms to uncover the insights of Twitter users data. The model depicts the overall process flow of Twitter user activities. Behavioural patterns like common sequences, repeated user actions, direct relations, and rare interactions are analysed. The models performance is assessed with the metrics like fitness, precision, and simplicity to choose the best model for the dataset. Inductive miner outperformed well with other algorithms. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.