Browse Items (16481 total)
Sort by:
-
Unveiling Patterns, Visualizations, and Trends from Patient Diabetes Data
The important role that exploratory data analysis, or EDA, plays in the context of diabetes prediction is explored in this work. EDA is used as a key component of a multimodal strategy to identify unique characteristics linked to diabetes. EDA offers insights that aid in the creation of prediction models by sifting through the complex patterns present in the medical data. The focus is on using EDA to fully grasp the data landscape while also comprehending the distinct features of diabetes. This investigation is critical to accurately categorizing people into discrete risk groups and emphasizes the use of domain-specific knowledge in enhancing diabetes prediction techniques. The research suggests using specific EDA techniques to gain deep insights and lead proactive responses. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Harnessing Insights for Optimizing Healthcare: Disease Prediction and Beyond
This study offers a novel method for developing classification approaches for disease prediction. Exploratory analysis and meticulous data preprocessing were conducted to understand the relationships between symptoms and illnesses. The research involved assessing various machine learning models, including the random forest classifier, through cross-validation techniques, resulting in the identification of a high-performing model with an impressive accuracy rate. In addition, this study incorporates data visualization techniques to gain insights into symptomdisease connections. The studys focus on data visualization and optimization strategies in health demonstrates the potential to transform healthcare by providing precise diagnoses and predicting diseases, ultimately improving patient outcomes. This research underscores the efficacy of data-driven techniques and their integration into recommendation and disease prediction systems, emphasizing the significance of data visualization and optimization strategies in health. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
A Comprehensive Analysis of the Impact of Demographic, Socioeconomic Factors, and Social Media Advertisements on Consumers Online Shopping Behavior
This research comprehensively explores the intricate relationship between social media, demographic factors, socioeconomic status, and online shopping behavior. It investigates how various elements, such as brand, quality, price, and reviews, intersect to influence consumers virtual shopping experiences. Recognizing the diversity among consumer populations, the study considers demographic traits like age, gender, and socioeconomic status. It identifies a research gap concerning the moderating effects of these factors on virtual shopping behavior and the influence of different advertisement sources. The research proposes a methodology involving machine learning approaches to address these gaps. Using a dataset collected from 331 respondents in Kolkata, the study employs statistical tests and machine learning models to analyze the correlations and predict online shopping behavior. The results underscore the importance of understanding consumer behavior in the evolving e-commerce landscape. Logistic Regression emerges as the most accurate algorithm for predicting online shopping decisions. Additionally, the research investigates the reasons limiting consumers use of online shopping platforms, providing practical insights for tailored marketing strategies. These findings empower businesses to adapt their marketing strategies to the evolving landscape of consumer behavior. Overall, the study enhances our understanding of the multifaceted variables shaping customers decisions in online marketplaces. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Data-Driven Strategies for Twitter Engagement: Hashtag Recommendations and API Insights
Twitter is a great way to connect with people worldwide, and one of the best ways to do that is by using hashtags. A hashtag is a keyword or phrase attached to a particular topic, and users can use it to find related tweets. Using a hashtag relevant to the needs or for business can increase the tweets visibility and make it easier for people to see the content they want. It can hugely help content creators who want to increase engagement and influence their tweets. This research introduces TagMate, a hashtag recommender system for Twitter that offers significant benefits. By accessing the tweets using Twitter API and after analyzing and performing algorithms, recommendations for hashtags can be obtained. The Twitter API allows access to various information about the account, including followers, tweets, content, etc. This information can be used to generate recommendations for hashtags related to the business. The system will generate hashtags according to the tweet and recommend trending or popular hashtags to increase their reach or engagement on the Twitter platform. Using the API, a dashboard can be created showing which hashtags are being used most frequently and which are most popular. This information can help create more relevant and engaging tweets, attracting more followers and interest. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Optimizing Healthcare: Enhancing Disease Management with Recommendation Systems
This paper explores a data-driven disease recommendation system for medical professionals based on symptoms. The technology examines symptom patterns to recommend diseases from large datasets by utilizing collaborative filtering and data analytics. To provide individualized disease recommendations based on symptom severity, it goes through data preprocessing and uses techniques like collaborative filtering and cosine similarity. Even if the technology is promising, disease predictions might be strengthened. It seeks to support early disease prediction and offer patients and healthcare professionals individualized guidance. This system demonstrates the potential of technology in healthcare decision-making using a basic Tkinter application. More improvements are anticipated as a result of data-driven approach advancements, which will improve patient care and optimize healthcare procedures. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Harnessing the Power of Cloud Computing for Advanced Business and Economic Research
Cloud computing has surfaced as a significant influence in the domain of business and economic research. Its ability to deliver vast computational resources, scalable storage, and unparalleled accessibility has revolutionized the way researchers analyze complex datasets, conduct simulations, and collaborate on ground-breaking projects. This paper delves into the myriad ways cloud computing is empowering researchers to unlock unprecedented economic insights. This research article delves into the key dimensions of leveraging cloud computing for advanced business and economic research. It investigates the scalability and flexibility of cloud-based infrastructure, enabling researchers to process and analyze extensive datasets, conduct complex simulations, and implement machine learning algorithms for predictive modeling. Moreover, the cloud facilitates real-time collaboration and data sharing, fostering a global research community that transcends geographical boundaries. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Bridging the Gap: Exploring Blockchains Role in Enhancing Financial Inclusion in the Indian Context
In recent years, the concept of financial inclusion has gained prominence as a crucial element in both economic and societal progress. This study investigates how blockchain technology could enhance financial accessibility in the unique socioeconomic context of India. Through an extensive analysis of a variety of blockchain applications, such as decentralized banking, digital identity verification, and transparent transaction procedures, this paper investigates the feasibility of utilizing blockchain technology to enhance inclusive financial systems. It closely examines the obstacles to blockchain adoption in India, such as governmental regulations, public sentiment, and the limitations of the countrys technology infrastructure. In order to raise awareness and encourage adoption, it also examines how to include blockchain education initiatives. This study adds to the discussion on financial inclusion and blockchain technology by fusing theoretical knowledge with real-world applications. Additionally, it offers a way to apply blockchain technology to advance inclusive economic growth in India. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Novel Hybrid Machine-Learning Algorithms for Resource Optimization in Cloud
The resource optimization process in the cloud is crucial and can be achieved through the ideal Load Balancing (LB) mechanism. The cloud undergoes several challenges with resource optimization due to poor LB mechanism, where its Virtual Machines (VMs) are either overloaded or idle. The main aim of this experimental-based research is to enhance the LB mechanism of the cloud by implementing and comparing the performance of novel hybrid LB algorithms RLFCFS and RLSJF to optimize the resources. The RLFCFS and RLSJF novel LB algorithms are designed by combining the Reinforcement Learning (RL) technique with the heuristic FCFS and SJF algorithms. The proposed algorithms improve resource optimization in terms of cost and time by facilitating enhanced LB mechanism through RL intelligence mechanism. The performance of RLFCFS and RLSJF LB algorithms is compared with respect to the average (avg.) load managed by the VMs and the avg. percentage (perc.) of deviation observed against the expected load in each experimental stage. The experimental throughput conveys that the RLFCFS LB algorithm managed an aggregate avg. load of 968.77 tasks against the RLSJF LB algorithm, which managed 999.08 tasks aggregately across all experimental stages. Concerning the avg. perc. of deviation, the RLFCFS LB algorithm deviated by 63.44% against the ideal expected load to manage against the RLSJF LB algorithm, which deviated by 64.60%. This shows that the RLFCFS LB algorithm gave better resource optimization results than the RLSJF LB algorithm. Lastly, these results are mathematically validated using the Simple Linear Regression model. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
The Role of Artificial Intelligence in Simulating, Automating, and Analyzing Business Operations
Business processes have been transformed with the advent of artificial intelligence. However, to efficiently utilize the technology and to close the gap, we reviewed the literature to find these solutions in this work. We ensured that styles worked because they allowed for extensions and replication. In these studies, we correlated patterns that assisted with task automation and helped analysts create, expand, or re-engineer business processes with the confidence to make judgments. The authors used various AI methods, including swarm intelligence, Bayesian networks, and K-means. Our analysis gives data on the approaches and issues being dealt with and indicates potential future directions. Processes for predictive business future planning and activity prediction are examples of monitoring jobs that are becoming less significant as new technologies allow for the intelligent automation of company processes. Deep learning models are used in recent work on this subject to encapsulate historical event information without further processing. The data context, which includes the dependence of conditions and particular traits, might also have an impact on the anticipated data, even though it was not taken into account in earlier research. We present a novel encoding strategy for state data, encompassing non-existent, multi-character private, and regular event states. We present the transformer and LSTM deep learning models, two new deep learning models, and two popular deep learning models. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Sign Language Recognition Using Hand Gestures
In everyday interactions between humans and computers, recognizing hand gestures plays a crucial role as it offers a natural and easy way to control and communicate with various applications. This article delves into a detailed exploration of how MobileNet architecture can enhance the accuracy and efficiency of hand gesture detection systems. The aim is to address the limitations found in traditional models by leveraging the optimization and computational efficiency offered by MobileNet. To understand the significance of incorporating MobileNet architecture, the article begins by examining previous research methods used in hand gesture recognition. By conducting a thorough review of existing literature, the study identifies areas where improvements can be made. It then introduces a novel approach that utilizes MobileNet architecture to elevate the precision and effectiveness of hand gesture detection. This approach is tested using a well-established dataset of American Sign Language movements, providing a reliable foundation for training and evaluating the model. This work delves into the technical aspects of implementing the MobileNet-based hand gesture detection system. It explains how the model framework integrates MobileNet architecture and discusses the preprocessing techniques employed for image analysis. The experimental and analytical work conducted during the project is highlighted, emphasizing the iterative process of refining and optimizing the model to achieve optimal performance. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Unlocking Insights into Mental Well-Being: A Deep Learning Approach to Depression Detection
Depression, a prevalent global mental health disorder, poses significant challenges for timely diagnosis and effective intervention. Our research leverages the power of deep learning to develop a novel approach to depression detection, with the ultimate goal of enhancing early diagnosis and improving mental well-being. To evaluate the effectiveness of our method, we carried out an examination on a sizable dataset consisting of real-world data from individuals with and without diagnosed depression. The report discusses the performance metrics to examine the proposed technique effectiveness in depression detection. Additionally, this proposed work emphasizes the ethical and privacy considerations surrounding mental health data. The findings of this research indicate promising results in early depression detection, offering the potential to revolutionize mental health care by facilitating timely interventions. We discuss the implications of our approach in terms of supporting mental health professionals, improving mental health care accessibility, and addressing the pressing global mental health crisis. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Enhancing Mobile Application Security Through Android Threat Classification
The Android application market has grown significantly, offering customers an ever-growing range of features to suit a variety of purposes. Users are exchanging more and more sensitive data thanks to the widespread usage of mobile applications, therefore safeguarding personal information is crucial. But this boom has also opened the door for a corresponding rise in cybersecurity risks, especially for malware and adware that target mobile devices. It is imperative to categorise mobile applications into distinct groups such as malware, adware, and benign in order to fortify the mobile ecosystem. This project's primary objective is to create and apply cutting-edge machine learning algorithms that can precisely categorise mobile apps into groups including adware, malware, and benign apps. This will necessitate investigating various machine learning strategies and ensemble methods to improve classification accuracy and robustness. Multiple machine learning models were developed based on feature importance, utilizing various machine learning techniques. The evaluation metrics showcase the effectiveness of the final model, especially the Tuned XGBoost model. While achieving a high overall accuracy of 92.51%, the findings highlight the importance of considering diverse features beyond traditional flow-based ones, providing a more robust and complete perspective on mobile network security. 2025 The Authors. Published by Elsevier B.V. -
A novel stable feature selection algorithm for machine learning based intrusion detection system
The advent of new technologies like artificial intelligence, and big data has influenced many cyber attackers to launch their attacks on the network. Hence researchers have already proposed Intrusion Detection Systems by incorporating machine learning as well. Building an effective IDS is still a challenging task because of low accuracy. Managing high dimensional data is another major problem that occurs in IDS. Hence in this paper, an efficient Machine Learning based Intrusion Detection System is developed by means of a novel stable feature selection strategy called IV-RFE. The proposed methodology aims to select only the relevant features that contribute to the attack, which is purely based on relative variance, and weight factor in combination with RFE. This methodology increases the performance in terms of accuracy and maintains a stable set of features. Previous studies only focussed on the feature selection strategy and their performance. The feature stability also has to be considered which is an equally important metric, especially in the field of Intrusion Detection Systems. Hence in the current study, an efficient ML based IDS is proposed which selects only the relevant and stable features. Experimental results also revealed that the proposed IV-RFE outperformed well for three attacks with respect to accuracy and stability metrics also. The results show that stability is also an important indicator in selecting the features in the field of Intrusion Detection Systems. 2025 The Authors. Published by Elsevier B.V. -
EM-ACO-ARM: An Enhanced Multiple Ant Colony Optimization Algorithm for Adaptive Resource Management in Cloud Environment
Ant Colony Optimization (ACO) is an intelligent algorithm ensuring optimal resource management in cloud environments. This paper proposes an enhanced version of the ACO algorithm called Enhanced Multiple Ant Colony Optimization for Adaptive Resource Management (EM-ACO-ARM). Our approach uses multiple ant colonies undergoing several iterations of optimizations to find the optimal Virtual Machine (VM) and adapt to the convergence uncertain-ties, unlike a single ant colony in the existing ACO, which can hinder Quality of Service (QoS)-based performance parameters. We conducted experiments in a cloud-simulated environment to evaluate EM-ACO-ARM in two phases. In the first phase, we computed real-time Montage tasks using the existing ACO algorithm on VMs across ten scenarios. To ensure an unbiased comparison, the same cloud configuration was maintained in the second phase, and the same tasks were computed using the proposed EM-ACO-ARM algorithm in all ten scenarios. The experimental results demonstrate that EM-ACO-ARM improves Execution Cost and Execution Time, leading to a 14.73% increase in Resource Utilization. This ultimately improves the management of cloud resources. Additionally, a stability evaluation was conducted using regression models, and it outputted EM-ACO-ARM to provide more stability than the existing ACO algorithm. The cloud can provide better QoS with the proposed EM-ACO-ARM algorithm while abiding by Service Level Agreements. 2025 The Authors. Published by Elsevier B.V. -
An Energy, Mobility and Obstacle Aware Clustering based Intelligent Routing Protocol for FANET
The use of Flying Adhoc Networks (FANETs), also known as Unmanned Aerial Vehicles (UAVs), has increased in recent years. However, the fast movement of UAVs can lead to unreliable links and inefficient data transmission. To address this issue, the Intelligent-based Energy and Mobility-aware Clustering (IEMC) protocol has been developed, utilizing Battle Royale Optimization (BRO) for Cluster Head (CH) selection and a Deep Q-Learning (DQL)-based fast dynamic hello interval algorithm for path maintenance. Despite these advancements, FANETs still face challenges due to environmental obstacles affecting communication routes. To solve these issues, this article proposes an Intelligent-based Energy, Mobility, and Obstacle-aware Clustering (IEMOC) protocol for FANET routing. This protocol uses an intelligent Bezier route selection technique to deal with obstacles obstructing the paths of FANET nodes and a speed-based mobility prediction technique to reduce the impact of mobility during transmission. If link failure occurs due to an obstacle in the network, the IEMOC protocol selects an optimal alternative routing path via neighboring nodes based on its mobility awareness factor, link duration, network connectivity, and route availability, recovering the failed route without initiating the route discovery process. The effectiveness of the IEMOC protocol is validated through performance evaluations using the Network Simulator (NS)-2.35, and simulation results demonstrate that the IEMOC protocol outperforms conventional routing protocols in FANETs. 2025 The Authors. Published by Elsevier B.V. -
Integrating Diverse Approaches in Medical Image Analysis: PAA-CNN and Feature Extraction Fusion for Classiation of Psychological Disorders using Anatomical Scans
A psychological disorder is a condition that impacts a persons behavior. Due to the contemporary way of life, a large number of individuals suffer from disorders like stress, depression, and other similar ones. These might turn into severe issues that would signiantly impact a persons quality of life. We present a sample framework that uses an Anatomical scan captured along with fMRI. Anatomical scans were used to extract characteristics, which were then utilized to classify using a random forest classir. In a follow-up experiment, CNN is applied to features obtained from the piecewise aggregate approximation method for multi-class classiation of psychological disorders. This method performs noticeably better than the conventional feature extraction techniques, and with this approach, obtained an accuracy of up to 79%. Combining several approaches may boost the classiation and prediction accuracy of medical data. 2025 The Authors. Published by Elsevier B.V. -
Enhancing Kannada Handwritten Text Processing: A Deep Learning Approach to Optimized Recognition and Segmentation
Digitalization ensures that information is available in diverse regional languages, empowering more cultures and perspectives to be heard and understood. One of the regional languages considered for empowering information access is the Handwritten Kannada document. Extracting text from these documents requires overcoming several obstacles, such as deciphering diverse handwriting styles, accommodating inconsistencies in character size, and the presence of multiple touches between characters. The present paper explored recognizing and segmenting Kannada handwritten characters using a deep learning model, specifically YOLOv8. While YOLOv8 is primarily known for real-time object detection, the paper suggests its potential for character detection tasks. The model achieved a promising mean Average Precision (mAP) of 96.8% at a threshold of 0.5 on a hybrid dataset consisting of 2476 images and 95.0% on character segmentation. This experiment adds to the growing body of research exploring YOLOv8s capabilities beyond traditional real-time object detection and instance segmentation. 2025 The Authors. Published by Elsevier B.V. -
A Novel Approach towards Key-point based Real-time Children Emotion Prediction
Emotion prediction is crucial in mental healthcare. It is vital in children as it aids in managing behavioral issues and early identification of emotional distress that can lead to helpful mental health support. The research uniquely centres on children's emotional expressions, addressing a gap in existing emotion detection studies, which often focus on adults. By specifically tailoring the model to recognize subtle expressions unique to children, the study contributes valuable insights into child psychology and emotion recognition. To address this gap, this work attempts to establish a comprehensive children's emotion dataset that can facilitate the study of emotions across various pose orientation. The approach introduces advanced key-point detection techniques that capture a higher density of facial landmarks, allowing for more nuanced analysis of emotional expressions. This fine-grained detection enables the identification of subtle changes that are critical in interpreting children's emotions. An effective face detector with deep architecture is designed to handle all pose orientations from key image frames. Optimal features are then chosen by re-ranking the features using a hybrid feature selection mechanism. The emotion category is revealed by careful analysis of sequences of emotion identification from these features and is not based on a single frame. This framework holds promise for educational institutions and healthcare facilities, offering insights into children's behavior through emotion analysis. Through experimental analysis and comparisons with three existing SOTA emotion prediction models, it is observed that the proposed system consistently outperforms existing models by exhibiting an accuracy of 77.7 on average. Overall, this study recommended that the proposed model is suitable for children's emotion prediction. 2025 The Author(s). -
Forecasting Flight Delays with a Multilayered Memory Fusion Network
One of the biggest worldwide sectors is aviation, hence delays in flight services not only perturb customers but also result in large losses for airlines. Forecasting these delays is still difficult because of the erratic character of elements like climate. Accurate projections are challenging even using accepted analytical methods. This work employs sophisticated deep learning methods to enhance the forecast of aircraft delays - more especially, those resulting from weather-related causes.We investigate their effect on aircraft delays using datasets from both the United States and India, including meteorological fluctuations. Built on a Multilayered Memory Fusion Network, the model captures intricate temporal patterns in the data by merging Bidirectional LSTM (Bi-LSTM) and Long Short-Term Memory (LSTM). This network generates more accurate forecasts and is meant to effectively manage several factors. For the United States dataset, the proposed network attained a Mean Absolute Error (MAE) score of 72.41 and Root Mean Square Error (RMSE) scores of 118.87 and 11.83 and 21.82 for India respectively. Our deep learning methodology clearly predicts flight delays as these performance measures are far better than those attained by conventional machine learning techniques, including linear regression. By using these cutting-edge algorithms, the research provides a more accurate way to forecast flight delays, hence perhaps lowering passenger discontent and airline financial losses. 2025 The Author(s). -
Comparative Analysis of Composite Column Capacity Estimation in International Codes
The primary function of a building, bridge or any structural system is to transmit loads safely from the superstructure to the foundation. The columns play a critical role in this function, and any inaccuracies in load prediction can lead to catastrophic damage. Hence, the evaluation of a column's strength assumes considerable importance. Upon this premise, this research aimed to investigate the strength prediction of M40 grade concrete columns subjected to uniaxial compression loading. The experimental loading capacities of various columns were compared with the evaluated loads as per the Indian Standard code (IS 456:2000), British Standard (BS 8110-1:1997), American Concrete Institute (ACI 318-14) and European Standard (EN 1994-1-1 (2004)). It was observed that the partial safety factors and design philosophies in these codes were different. The experimental results suggested that the load-carrying capacities experimentally determined of the tested columns compare well with the capacities recommended by the IS code and the BS code for columns. In contrast, the other two codes have vastly different column capacity assessments due to higher partial safety factors. It is concluded that all four codes have evolved based on different design philosophies and, hence, have varying partial safety factors. Thus, a direct code comparison is not appropriate. The Authors, published by EDP Sciences, 2025.