Browse Items (3095 total)
Sort by:
-
A Univariate and Multivariate Time Series Analysis for the Prediction of Maize Production in India
This study examines the use of time series analysis for predicting maize production in India. The objective is to analyze the relationship between maize productions, domestic consumption, exports, and to forecast maize production using various time series models. The study employs cointegration techniques such as Johansen's test, Engle-Granger test, and Granger causality test to determine the long-term relationship between the variables. The findings exhibit that there is a bidirectional causal relationship between domestic consumption and export series and between domestic consumption and production series and that all three variables are co-integrated. To forecast maize production, the study employs both multivariate and univariate time series models. The multivariate models used are vector auto regressive and vector error correction models, while the univariate models used are ARIMA (auto regressive integrated moving averages), Holts exponential smoothing, NNAR (neural network auto regression), K-nearest neighbors (KNN), and LSTM (long short-term memory). The best forecast model is selected on the basis of a comparison of three evaluation metrics: mean absolute square error, mean absolute percentage error, and root mean square log error. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Exploring the Intersection of Engineering and Health Leveraging 3D Solutions to Tackle Complex Medical Challenges
The medical imaging industry is on the brink of becoming as tangible as the world around us, blurring the lines between the virtual and the real. From compact gadgets to fully tangible anatomical models, medicine and technology have always been intertwined, but never as closely as they are today. This section explores immersive technologies in medicine and healthcare, focusing on virtual, augmented, and mixed reality, with a particular emphasis on the groundbreaking applications of 3D technology in medicine. This integration has ushered in a new era of medical advancements, promising significant progress in diagnosis, treatment, patient care, and healthcare overall. The adoption of 3D techniques, such as magnetic resonance imaging (MRI), computed tomography (CT), ultrasound, and more, enables doctors and clinicians to view anatomical structures as if they were real-life models. This enhances clarity, precision, and conciseness while reducing the risk of medical errors. The virtual world promised by 3D technology is also expected to improve communication skills between healthcare professionals and patients, especially for young medical students. 3D printing has seen significant development in recent years, playing a critical role in various applications, including medicine. This section will focus on three key advancements in 3D printing: its combination with the internet as a delivery vehicle, its integration with medical imaging, and its use in tissue engineering and regenerative medicine. We will also delve into three-dimensional display technologies, such as monoscopic 3D displays, stereoscopic 3D displays, and autostereoscopic displays. Technology's impact is not solely measured by its failures; sometimes, the small successes can save lives that might otherwise be lost. This piece will illustrate how technology could revolutionize medicine and reveal the potential we have yet to fully realize due to fear. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Prediction of Grandiose Narcissism Using Machine Learning
The Gen-Zs have the tendency to exhibit a sense of self-importance and superiority excessively over social media. This study intends to predict Grandiose Narcissism based on Instagram usage and Fear of Missing Out (FoMO) among young adults. The study was conducted on a sample size of 300 young adults, recruited using convenient sampling, residing in the state of Assam, India. This study employed various machine learning models, including Logistic Regression, Random Forest, Support Vector Machine (SVM), Gradient Boosting, K-Nearest Neighbours (KNNs), and Gaussian Naive Bayes, to analyse the predictors of Grandiose Narcissism. Results showed that machine learning algorithms, especially KNN (90.7%) and Random Forest (88.70%) predicted Grandiose Narcissism accurately based onFoMO, Self-Esteem, PAUM. Additionally, Area Under Curve (AUC) in the range of 0.850.91 indicated that the variables in the data set are being discriminated in the context of specificity and sensitivity thoroughly. Significant influence of grandiose narcissism and FoMO on Instagram usage highlighted the role of social validation in enhancing online engagement. Future studies can include these algorithms to deduce patterns and develop real timebots to provide psychologically safe online environment. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Prediction of Crime Hotspots Using Machine-Learning Techniques
Crime prediction is critical in improving police strategies and implementing measures for crime prevention and control. In recent years, machine learning has emerged as a critical way to predictive analytics in this domain. However, few studies have thoroughly compared various machine-learning algorithms for crime prediction. This study investigates the predicting capacities of various machine learning and ensemble approaches using historical public property crime data from a large city in India. Five ensemble models, Random Forest, AdaBoost, CatBoost, Gradient Boosting Machine (GBM) and eXtreme Gradient Boosting (XGBoost) and Four machine learning models, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Nae Bayes and Decision Trees are used for crime predictive analysis in this study. The XGBoost model outperformed the other models tested, based primarily on historical crime data. XGBoost being an ensemble approachcombines multiple weak classifiers to create an effective classifier. Every weak learner concentrates on the faults made by the preceding ones, enabling the model to refine its predictions and fix errors repeatedly. When compared with other models used in the study, this resultedin higher accuracy. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Machine Learning-Based Classical Dance Mudra Recognition Model
In this research, symbolic hand mudras of the Indian traditional dance style of Bharatanatyam are recognized and categorized using deep learning techniques. The three main goals are establishing baseline datasets to identify and categorize hasta mudras, designing an automated tutoring program for prospective students, and constructing a system for recommending videos that support cultural heritage. The research achieves a real-time recognition accuracy of 85% to 95% using convolutional neural networks (CNNs) and the Mobile Net architecture. This activity greatly aids virtual learning during pandemics, worldwide cultural relations, and preserving intangible cultural assets. The three main goals of this research are to establish baseline datasets for accurate mudra identification, create an automated tutoring program for participants, and build a video recommendation system to promote cultural heritage globally. The benchmark datasets that are used to train the models are made up of high-quality photos and videos of mudras that are taken and annotated under the direction of experts. While the video recommendation system supports attempts to preserve culture and advance education, the automated tutoring system provides participants with a comprehensive virtual learning environment and tailored feedback. To ensure the survival and continued appreciation of Bharatanatyam around the world, our endeavor substantially enhances virtual education, deep learning, and cultural preservation. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Emerging Approaches in Digital Content Security: A Review of Blockchain Technology, Image Authentication, and Identity Management Systems
The rapid growth of digital media exchange and communication technologies has intensified the need for robust methods to ensure data integrity and protect intellectual property. This review paper explores various methodologies for safeguarding digital content, with a particular focus on distributed ledger technologies (DLT) and advanced image processing techniques. DLT, employed in blockchain systems, is highlighted for its ability to secure transactions and data in decentralized networks, mitigating the risks associated with centralized systems. In the realm of multimedia forensics, keypoint-based copy-move forgery detection methods, enhanced with density-based clustering and outlier removal algorithms, have shown superior performance in challenging conditions, effectively identifying forgeries even under geometric distortions and postprocessing. Additionally, the integration of speeded-up robust features (SURF) and polar complex exponential transform (PCET) in forgery detection offers resilience against various distortions, ensuring the authenticity of high-brightness regions in images. The paper also examines the evolution of digital identity management, where blockchain-based systems like BZDIMS employ zero-knowledge proof (ZKP) algorithms to enhance privacy and security. Through a comprehensive comparison of existing models, this paper demonstrates the advantages of these advanced technologies in enhancing data integrity, privacy, and the overall reliability of digital content verification systems. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
An Improved Security Framework for Vulnerable Intrusions in High Dense Fog Networks
This work presents an advanced security model to prevent vulnerable invasions through highly dense fog networks. Advantages: One of the strengths that fog computing has revealed is how beneficial its native design can be, but on the other hand, one critical aspect to keep in mind is that it brings several fresh security subjects because of its extremely dynamic and decentralized nature. The framework uses anomaly detection and secure communication protocols to identify the potential intrusion into a network. This also includes clustering fog nodes and more frequent network updates to improve security across the whole network. We evaluate our framework by implementing it in simulation experiments. We show that communication among existing trusted peers can be enhanced, whereas non-trusted sources entering the network cannot conduct attacks. Generally, this framework provides an attractive approach to improve fog networks security and renders them more attack-resistant. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
An Efficient Machine Learning Framework for Flood Forecasting
Floods, a significant natural disaster which has an impact on the whole world present major risks to ecosystems and humans, particularly in semi-arid areas with variable rainfall patterns. With the help of ICRISATs historical meteorological data and machine learning algorithms, this study has developed a customized flood prediction model for use. After evaluating and contrasting various models, including the proposed model Stacked Gradient Boosting with Random Forest (SGB-RAF), KNN, Decision Tree, Random Forest, and Linear Regression, it shows that SGB-RAF has the highest R2 score and lowest RMSE comparatively to other models. While other enhancements such as Ridge Regression and polynomial feature creation were studied, SGB-RAF remained effective. Overall, this study highlights how machine learning may improve flood prediction accuracy, which is important for disaster management and for improving the semi-arid regions adaptability to climatic variability. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Energy Efficient Smart Scheduling for Multi-path Routing Using Deep Learning
Energy efficiency is a key part of networkingit saves on cost and has an environmental impact. Multi-path routing is a well-known technique used for network traffic management to make it more efficient and reliable. Unfortunately, traditional multi-path routing techniques are oblivious to energy and suffer from poor energy utilization. This paper: An approach to efficient smart scheduling for multi-path routing with deep learning. Employing a deep learning algorithm with relevant network parameters allows us to predict the lightest path for processing in/outbound data. Simulation results demonstrate that our solution guarantees higher energy efficiency than conventional algorithms while enjoying better network performance. This solution proposes the formulation of a green and sustainable networking approach. Thus, it can be better adopted as an innovative security mechanism in many practical scenarios. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
A Systematic Review on Traffic Management System and Security Flaws: Analysis Research
The number of cars on our roads has significantly increased in recent years, surpassing the advancement of our traffic and road infrastructure. Due to the ineffective traffic management caused by this imbalance, there have been noticeable increases in traffic jams, congestion, and pollution. Addressing the problem of growing traffic has become urgent on a global scale. By using cutting-edge technology, Intelligent Transportation Systems (ITSs) provide a viable solution for addressing these issues. This research explores the development of traffic control systems as well as the cutting-edge innovations that have revolutionized this field. Furthermore, it examines various techniques based on traffic signals, primarily focusing on scrutinizing their security vulnerabilities and the measures taken to enhance system performance. The review acknowledges significant strides made in implementing security measures, assessing their effectiveness through both qualitative and quantitative metrics. Additionally, this study delves into key discoveries and explores the rationale behind lessons learned, serving as a roadmap for future research endeavors. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Enhancing Early Detection of Alzheimers Disease Through Integrated Deep Learning Models: A Multimodal Diagnostic Approach
Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline and functional impairment. Early detection is crucial for effective management and intervention. This study explores the effectiveness of an integrated deep learning approach combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to enhance the early detection of Alzheimer's disease using multimodal data. A novel deep learning model was developed and validated, integrating neuroimaging data (MRI and PET scans) with clinical data using a decision-level fusion strategy. The study utilized a dataset comprising 1000 anonymized patient records from the Alzheimers Disease Neuroimaging Initiative (ADNI). Models were assessed based on accuracy, precision, recall, F1-score, and area under the receiver operating characteristic (ROC) curve (AUC). The integrated model demonstrated superior performance with an accuracy of 95%, precision of 94%, recall of 93%, and an F1-score of 93.5%. The model's AUC was 0.97, indicating excellent diagnostic capability. The proposed deep learning approach significantly improves the early detection of Alzheimers disease by effectively analyzing complex, multimodal data. This model holds considerable potential for clinical applications, providing a robust tool for healthcare professionals to diagnose AD in its early stages. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Content-Based Product Recommendation SystemsReview
Content-based recommendation systems have become essential for improving user experiences in e-commerce and various digital platforms. This review paper examines the recent advancements in content-based recommendation systems, focusing on machine learning techniques and models used to personalise user interactions. The paper also explores the role of deep learning and hybrid approaches in increasing the accuracy and relevance of recommendations. Despite significant progress, the product recommendation systems face challenges such as capturing complex user preferences, ensuring scalability, addressing the cold start problem, and improving explainability which remains crucial and requires further research. This paper offers a comprehensive overview of current methodologies, identifies existing limitations, and suggests future directions to optimise content-based recommendation systems to provide more effective and reliable recommendations. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
FusionBotSentinel: A Framework to Mitigate Probable Social Bots Spreading False Information in Cyber Physical Systems
The escalating dissemination of fake news across social media networks has emerged as a concerning societal issue and a threat to cyber physical systems. Bots, often employed to propagate such misinformation, present a formidable challenge in their detection and elimination. Bot prediction have been pivotal in identifying and curbing these deceptive bot activities within social media networks. Twitchs live streaming content is readily scrapable and totally accessible. But quite understudied. Recent studies scrutinized these frameworks, revealing significant strides in their development while acknowledging the need for further enhancements in both predictions for proactive measures. FusionBotSentinel proposes a novel architecture that underscores the imperative for future research to concentrate on fortifying these frameworks, ensuring they are more resilient and adaptable in mitigating and predicting the spread of fake news by social bots. Another focus is on enhancing the effectiveness of deep learning models through a refined understanding of data quality with a largest dataset available and employing better hybrid techniques that bolster the generalizability and robustness helping in forecasting bot activities in combatting this escalating problem within cyber physical systems. Since bots are seen to be the source of the present problems with cyber physical systems, including privacy, security, safety, and ethical difficulties, it is necessary to recognize these gaps. Our suggested FusionBotSentinelprovides a revolutionary significance by contributing to in combatting fake news in the society by achieving up to 99% in accuracy, 98% in precision, 100% in recall, 99% in sensitivity with F1 score as 99% in social bot prediction offering 20% more efficiency when compared to the most advanced existing models proving its superiority. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
A Novel Nature-Inspired Coconut Tree Optimization Technique forEngineering Applications
Coconut tree optimization technique is a novel optimization algorithm that is motivated by the physical structure of the coconut tree. The search for optima in a feasible region is chosen between a random root and any point in a leaf. Coconut tree optimization is a pseudo meta-heuristic algorithm wherein search of solution is carried out using random as well as gradient movement with a memory stack that contains local optima. Nonlinear optimization problems consisting of equality and inequality constraints were solved using the proposed algorithm. The algorithm is validated for linear and nonlinear optimization problems. The comparative study and analysis were detailed for existing algorithms used in domain-specific physical problems. The algorithm is compared with the genetic algorithm and particle swarm optimization by considering standard test functions. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Pattern Identification and Recommender System Based on Skin Undertone in ApparelA Deep Learning Approach
The fashion industry has undergone significant transformations driven by technological advancements, shifting consumer preferences, and the rise of e-commerce. Traditional retail models have been disrupted, giving consumers unprecedented access to information and options, making personalization crucial for success. The industry has also embraced inclusivity, offering diverse clothing lines that cater to various body types, skin tones, and cultural backgrounds. Technology plays a pivotal role in this evolution, enhancing design, manufacturing, marketing, and sustainability practices. Despite these advancements, existing recommendation systems often overlook individual characteristics such as skin undertones and pattern preferences, as well as the dynamic nature of fashion trends. This study aims to address these limitations by developing a novel AI-powered recommendation system that integrates personalized factors with real-time fashion trends. The proposed system will analyze customer data, including browsing history, social media activity, and purchases, to provide accurate and tailored fashion suggestions. By incorporating individual traits and the latest trends, the research seeks to create a more effective and responsive recommendation engine, ultimately enhancing the consumer shopping experience and helping fashion brands stay competitive in a rapidly evolving market. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
AI-Based Medical Assistance forProactive Healthcare Predictions andServices
Healthcare systems must adapt to the requirements of the digital era. The proposed healthcare Artificial Intelligence (AI) assistance provides a safe and user-friendly platform for physicians, patients, and administrators to meet their specific needs. The systems architecture prioritizes user authentication and role-based access control to ensure that only authorized users have access to certain features. The technology allows patients to input their symptoms, which is the platforms cornerstone offering. The technology uses a Machine Learning (ML) model and a large medical database to properly forecast probable illnesses based on the symptoms presented. This predictive feature helps individuals make educated decisions about their health and seek medical assistance proactively. The systems creative approach extends to online consultations. Patients may seek consultations, schedule appointments, and conduct secure video chats from the comfort of their homes. This online consultation service offers a convenient and flexible option for medical treatment, especially for people with restricted mobility or wanting immediate assistance. This paper evaluates disease prediction using parameters like accuracy and confusion matrix performance. The neural network model performs better for the above parameters in comparison to the random forest and K-nearest neighbor ML models. The proposed system uses ML technology to deliver fast, accurate, and secure medical services, breaking down traditional healthcare barriers. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Cloud Job Scheduling Using Deadline-Based Task Optimisation Algorithm in Internet of Things
The cloud-based Internet of Things (IoT) gadgets are becoming increasingly significant in todays current environment. Thoroughly examining the ever-changing relationship among these two domains, this literature review sheds light on how the field of research is developing and how important both domains are to defining our digital future. The analysis delves into the various uses of cloud-based computing in conjunction with IoT devices, highlighting how these two technologies have the combined power to transform companies, improve productivity, and improve user experiences. Blending cloud-based resources with IoT has become essential for advancement, from connected houses to industrial automation. The article provides a detailed overview of the complexities involved in this merger, highlighting the importance of computing in the cloud in tackling issues like data protection, immediate analysis, and resource optimisation. This study also points out significant gaps in current understanding, highlighting the need for more investigation to fully realise the promise of cloud computing when combined with IoT devices. Essentially, this analysis of the literature highlights the critical role in determining the integration of cloud technology and IoT devices by giving a more efficient and optimal scheduling Deadline-Based Task scheduling algorithm, which has proved to have the least average waiting time of five units when compared to all the scheduling algorithms taken into consideration. The beginning of a new era characterised by connectivity and data-driven decision-making, and the key to realising the full potential of IoT applications is to comprehend and leverage the power of cloud technology. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Detection of Fungi Diseases in Tomato Leaf Using ResNet-18 Approach
Agriculture is the largest and most vital sector of our economy, providing employment to over 70% of the Indian population. In an agricultural field identification and classification of disease in a tomato plant plays a vital role. If proper care is not taken in advance with this, it causes the serious effect on the tomato plants. The plants which are affected by the disease reflect on the quality and quantity of the production as well as the economy of the country. Tomato is one of the main vegetables in India which plays an important role in providing food for public needs and its a very vulnerable plant to insects and diseases caused by different pathogens like bacteria, virus, and fungi. This paper proposes a convolutional neural network (CNN) for automatic identification of plant disease caused by fungi. The proposed model attains the results of F1 score is 91% to differentiate tomato leaves in both healthy and unhealthy conditions. Measures like a high Area Under Curve (AUC) score on the Receiver Operating Characteristic (ROC) curve, accuracy, sensitivity, and specificity show the models remarkable performance. The practical uses of this discovery for early illness detection in agriculture make it significant. With its exceptional specificity and precision, ResNet-18 serves as a potential tool for agriculture. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
A Novel Cross-Validation Fusion Model Combining Vision Transformer and DenseNet161 for Enhanced Cervical Lesion Classification
Cervical cancer is fourth most common cancer in women across the world with highest impact in low- and middle-income countries. World Health Organization sent out a call for all UN nations to work toward the elimination of cervical cancer. Deep learning and artificial intelligence have been the go-to solutions for medical image analysis for diagnosis and prognosis. This paper aims to classify lesions in a colposcope captured cervix image with help of artificial intelligence models. To further advance automated cervical lesion classification, the study proposes a novel hybrid model that combines the complementary strengths of a vision transformer and DenseNet architecture. The paper also addresses ongoing challenges, such as interference from specular reflection areas and the difficulty in distinguishing between different lesion grades due to subtle visual differences. The proposed cross-validation decision fusion strategy aims to improve the reliability and robustness of the classification process. The results of the study affirm that deep learning and fusion technologies will steer the future direction of research in medical image analysis. DenseNet model has performed with an accuracy score of 0.695, sensitivity of 0.912, specificity of 0.979 and F1 score of 0.9100. These metrics are significantly improved versions of state of the art used in this study for comparative analysis. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
A Comparative Study of Machine Learning Algorithms for Recommendation Systems
This research explores recommendation algorithms for e-commerce efficacy. From e-commerce giants like Amazon to streaming services like Netflix, recommendation algorithms are integral in giving personalized experiences to attract and retain customers. It tests KNN, K-Means, Decision Tree (Gini, Entropy), and Naive Bayes on the Amazon review dataset 2018Electronics category. Decision Trees emerged as the most accurate predictor of user preferences, suggesting the trees ability to capture complex data relationships is key for relevant product recommendations. To get a better understanding, this research also examines each algorithms power and weakness in the context of recommendation systems. It offers valuable information on how to approach the optimization of their recommendation strategies in e-commerce businesses, highlighting not only the most effective approach (Decision Trees) but also the considerations for choosing an algorithm based on its strengths and weaknesses (e.g., interpretability vs. accuracy). Ultimately, this research contributes to informing data-driven decision-making for personalized recommendations in e-commerce, paving the way for a more user-centric shopping experience. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.