Browse Items (14421 total)
Sort by:
-
Data Mining-Based Variant Subset Features
A subset of accessible variants data is chosen for the learning approaches during the variant selection procedure. Itincludes the important one with the fewest dimensions and contributes the most to learner accuracy. The benefit of variant selection would be that essential information about a particular variant isnt lost, but if just a limited number of variants are needed,and the original variants are extremely varied, there tends to be a risk of information being lost since certain variants must be ignored. Dimensional reduction, also based on variant extraction, on the other hand, allows the size of the variant space to be reduced without losing information from the original variant space.Filters, wrappers, and entrenched approaches are the three categories of variant selection procedures. Wrapper strategies outperform filter methods because the variation selection procedure is suited for the classifier to be used. Wrapper techniques, on the other hand, are too expensive to use for large variant spaces due to their high computational cost;therefore each variant set must be evaluated using the trained classifier, which slows down the variant selection process. Filter techniques have a lower computing cost and are faster than wrapper procedures, but they have worse classification reliability and are better suited to high-dimensional datasets. Hybrid techniques, which combine the benefits of both filters and wrappers approaches, are now being organized. 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Data Modeling and Analysis for the Internet of Medical Things
Smart biomedical technology greatly assists in rapid disease screening and diagnosis within hospitals. One innovative device, a smart inhaler, incorporates sensors to track medication doses, usage patterns, and effectiveness. These inhalers provide valuable support to asthma sufferers, allowing for improved condition management and better patient outcomes. Asthma, a chronic respiratory disease affecting millions worldwide, causes airway constriction and swelling, resulting in breathing difficulties. Typically, medication such as inhaled corticosteroids and bronchodilators is used for management. However, medication adherence is often inadequate, leading to worsened outcomes and exacerbations. Smart inhalers aim to address this challenge by enabling users to monitor medication usage and compliance. Equipped with sensors, the inhalers track when, how much, and how frequently the prescribed medication is taken. The collected data is then transmitted to a mobile app or web portal, accessible to patients and healthcare providers. This integration facilitates medication tracking and provides personalized coaching for improved asthma control. The gathered data serves multiple purposes, including helping patients monitor their medication use and adherence. Patients can receive feedback on their treatment plan adherence and utilize the app to set medication reminders, promoting adherence and enhancing outcomes. 2024 CRC Press. -
Data Privacy
Data privacy is a private and public phenomenon and its operations have implications for the individual and the society. This understanding of privacy ceases it from being viewed as a simple technological process and highlights different factors that are associated with it. While on one hand, the right to privacy is seen as integral to the freedom of the individual, on the other hand, it is also seen as the ability to hide certain information for malpractice. This chapter delves into this existing dichotomy of data privacy and simplifies various terms and operations that have emerged in the field of study. A discussion is facilitated on the concept and its associated areas. The chapter looks at privacy regimes in different countries to note emerging developments and also presents a critique of the practice to bring forth shortcomings and enable change. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Data privacy in blockchain management scheme with Nudge Theory for banking sector
Blockchain is an emerging digital transformation technique for processing and storing information. The study explores how blockchain technology can transform the banking sector by improving efficiency, transparency, and security. The main goal is to understand how blockchain can modernize traditional banking operations and address key challenges such as fraud, high transaction costs, and slow processing times. The study uses a qualitative approach, drawing insights from existing research, real-world examples, and current trends in financial technology. Findings show that blockchain offers clear advantages, including faster and more secure transactions, reduced operational costs, and improved record-keeping. It holds strong potential in areas like payments, trade finance, and compliance. However, the paper also highlights significant obstacles such as unclear regulations, difficulties in integrating with existing systems, and technical limitations related to scalability and interoperability. Blockchain is seen as a promising solution for many of the inefficiencies in current banking practices. Still, successful implementation will require careful planning, regulatory support, and collaboration across the financial ecosystem. The study offers practical insights for banks, technology developers, and regulators, recommending a gradual and strategic approach to blockchain adoption to ensure long-term value and sustainability. 2025 by the authors; licensee Learning Gate. -
Data Reduction Techniques in Wireless Sensor Networks with AI
Due to their numerous uses in practically every part of life and their related problems, such as energy saving, a longer life cycle, and better resource usage, the research of wireless sensor networks is ongoing. Its extensive use successfully saves and processes a considerable volume of sensor data. Since the sensor nodes are frequently placed in challenging locations where less expensive resources are required for data collection and processing, this presents a new difficulty. One method for minimizing the quantity of sensor data is data reduction. A review of data reduction methods has been provided in this publication. The different data reduction approaches that have been put forth over the years have been examined, along with their advantages and disadvantages, ways in which they can be helpful, and whether or not using them in contexts with limited resources is worthwhile. 2022 IEEE. -
Data Science in the Medical Field
Data science has the potential to influence and improve fundamental services such as the healthcare sector. This book recognizes this fact by analyzing the potential uses of data science in healthcare. Every human body produces 2 TB of data each day. This information covers brain activity, stress level, heart rate, blood sugar level, and many other things. More sophisticated technology, such as data science, allows clinicians and researchers to handle such a massive volume of data to track the health of patients. The book focuses on the potential and the tools of data science to identify the signs of illness at an extremely early stage. 2025 Elsevier Inc. All rights are reserved including those for text and data mining AI training and similar technologies. -
Data science: simulating and development of outcome based teaching method
The educational researcher has a wealth of options to apply analytics to extract meaningful insights to improve teaching and learning due to the growing availability of educational data. Teaching analytics, in contrast to learning analytics, examines the quality of the classroom environment and the efficacy of the instructional methods used to improve student learning. To investigate the potential of analytics in the classroom without jeopardizing students' privacy, we suggest a data science strategy that uses simulated data using pseudocode to build test cases for educational endeavors. Hopefully, this method's findings will contribute to creating a teaching outcome model (TOM) that can be used to motivate and evaluate educator performance. In Splunk, the study's simulated methodology was carried out. Splunk is a real-time Big Data dashboard that can gather and analyze massive amounts of machine-generated data. We provide the findings as a set of visual dashboards depicting recurring themes and developments in classroom effectiveness. Our study's overarching goal is to help bolster a culture of data-informed decision-making at academic institutions by applying a scientific method to educational data. 2023 IEEE. -
Data science: the Artificial Intelligence (AI) algorithms-inspired use cases
The data science field is growing fast with the faster maturity and stability of its implementation technologies. We had been fiddling with traditional data analytics methods. But now, with Artificial Intelligence (AI), it is possible to embark on predictive and prescriptive insights generation in time. There are several data science (DS) use cases emerging with the wider adoption and adaptation of AI technologies and tools. This chapter is dedicated to illustrate various AI-inspired use cases. The Institution of Engineering and Technology 2022. -
Data Security
Corporates, industries, and governments have completely digitized their infrastructure, processes, and data or running towards completed digitalization. This data could be text files, different types of databases, accounts, and networks. The data living in the digital format needs to be preserved and also protected from unauthorized access. If this data remains open for access, any unauthorized user can destroy, encrypt, or corrupt the data, making the data unusable. There are implications of data security threats such as data breaches and data spills, beyond cost and can spell doom for the business. Hence the data needs to be protected from such threats. Data security is a mechanism through which data is protected and prevented from loss due to unauthorized access. It is a mix of practices and processes to ensure data remains protected from unauthorized use and readily accessible for authorized use. Data Security is essential for achieving data privacy in general. To define appropriate security measures, we must define the difference between a data breach and a data leak. Data security mechanisms could be data-centric such as identity and access management, encryption and tokenization, and backup and recovery. A defined data governance and compliance can also ensure data security. This chapter will explain why there is a need for data security, methods and processes to achieve data security, and touch upon some of the data security laws and regulations. We will also see a case study on how hackers exploited a vulnerability to mount a data security attack worldwide and how data security mechanisms could have prevented it. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Data Security-Based Routing in MANETs Using Key Management Mechanism
A Mobile Ad Hoc Network (MANET) is an autonomous network developed using wireless mobile nodes without the support of any kind of infrastructure. In a MANET, nodes can communicate with each other freely and dynamically. However, MANETs are prone to serious security threats that are difficult to resist using the existing security approaches. Therefore, various secure routing protocols have been developed to strengthen the security of MANETs. In this paper, a secure and energy-efficient routing protocol is proposed by using group key management. Asymmetric key cryptography is used, which involves two specialized nodes, labeled the Calculator Key (CK) and the Distribution Key (DK). These two nodes are responsible for the generation, verification, and distribution of secret keys. As a result, other nodes need not perform any kind of additional computation for building the secret keys. These nodes are selected using the energy consumption and trust values of nodes. In most of the existing routing protocols, each node is responsible for the generation and distribution of its own secret keys, which results in more energy dissemination. Moreover, if any node is compromised, security breaches should occur. When nodes other than the CK and DK are compromised, the entire networks security is not jeopardized. Extensive experiments are performed by considering the existing and the proposed protocols. Performance analyses reveal that the proposed protocol outperforms the competitive protocols. 2022 by the authors. Licensee MDPI, Basel, Switzerland. -
Data set on impact of COVID-19 on mental health of internal migrant workers in India: Corona Virus Anxiety Scale (CAS) approach
The article presents a unique dataset on mental health of internal Migrant workers in India. The dataset was constructed during the pandemic when the entire nation was the victim of stringent measures to curtail the spread of Corona Virus in the form of travel restrictions and lockdowns. We collected this data in our pursuit to submit a paper in response to call for paper in the Journal titled Migration and health. Non-availability of authentic data about the internal migrant workers triggered this effort to compile the data. We have recorded 1350 responses out of a 6897 Sample through snowball sampling method. Every respondent is said to be a referee for further driving of sample. The responses were collected between June 2 and August 30, 2020 through the telephonic interviews. Also, the consent of the respondents has been duly obtained for publication of the data without revealing their identity. The interview schedule was adopted by using Corona virus Anxiety Scale (CAS) which uses four dimension model namely Cognitive, Emotional, Behavioral and Psychological. The Interview schedule was originally designed in English but was later translated into three different languages after consulting the language experts. This article provides descriptive statistics of study variables along with socio economic factors. This dataset provides a significant platform for further research related to CAS and in assessment of mental health of vulnerable groups. 2021 -
Data visualization and toss related analysis of IPL teams and batsmen performances
Sports play a very significant role in the development of the human persona. Getting involved in games like Cricket and other various sports help us to build character, discipline, confidence and physical fitness. Indian Premier League, IPL provides the most successful form of cricket as it gives opportunities to young and talented players to show case their talents on various pitch. Decision-makers are the utmost customers for all fundamentals in the sports analytics framework. Sports analytics has been a smash hit in shaping success for many players and teams in various sports. Sports analytics and data visualization can play a crucial role in selecting the best players for a team. This paper is about the Toss Related analysis and the breadth of data visualization in supporting the decision makers for identifying inherent players for their teams. Copyright 2019 Institute of Advanced Engineering and Science. All rights reserved. -
Data visualization: Experiment to impose ddos attack and its recovery on software-defined networks
The entire network is doing paradigm shift towards the software-defined networks by separating forwarding plane from control plane. This gives a clear call to researchers for joining the ocean of software-defined networks for doing research considering its security aspects. The biggest advantage of SDN is programmability of the forwarding plane. By making the switches programmable, it can take live instructions from controllers. The versions of OpenFlow protocol and the compatibility of programmable switches with OpenFlow were the stepping stone making software-defined networks thrashed towards reality. The control plane has come up with multiple options of controllers such as NOX [2], Ryu [3], Floodlight [4], Open- DayLight [6], ONOS [7] and the list is big. The major players are Java based which keeps the doors open for enhancement of features by the contributors. However, more is expected from the practicality of P4Lang programmed switches by bringing skilled people to the industry who can actually implement programmable switches with ease. The obvious reason for delayed progress in the area of software-defined networks is the lack of awareness towards data visualization options existing as of now. The purpose of writing this chapter is to throw light upon the existing options available for data visualization in the area of SDN especially addressing the security aspect by analyzing the experiment of distributed denial of service (DDoS) attack on SDN with clarity on its usage, features, applicability and scopes for its adaptabilities in the world of networks which is going towards SDN. This chapter is a call to network researchers to join the train of SDN and push forward the SDN technology by proved results of data visualization of network and security matrices. The sections and subsections show clearly the experimental steps to implement DDoS attack on SDN and further provide solution to overcome the attack. Springer Nature Singapore Pte Ltd. 2020. -
Data- Driven Insights for Decision- Making in the Stock Market by Using Meta- Analyses
The stock market structure is complex, dynamic, and continually evolving. This makes it harder for investors to make smart decisions. Using data-driven insights to inform investment decisions has become increasingly prevalent in recent years. This research study focused on two main parameters: investors behavioral biases and initial public offering (IPO) pricing. Forty-five past studies from 2010 to 2022 were analyzed using meta-analyses. The study initially delves into the difficulties investors face in choosing suitable stock market investments. It then covers the various types of data that are available to investors. The paper proceeds to examine the techniques for analyzing stock market data. Finally, the article concludes by discussing the advantages of implementing data-based insights in investment decision-making. 2025 CRC Press. -
Data-driven behaviour finance for mutual fund investment decision making
When it comes to money and investing funds, the individual portfolio investor isn't always as logical as he feels he is, which is why there's a whole school of thought dedicated to explaining why people behave in irrational and weird ways. The primary objective of this research is to investigate the effects of five major behavioural biases on individual investor decisions in a metro city India, with a focus on mutual funds, as well as to examine how individuals make decisions to ensure that their investments generate greater returns for a better future. The statistical evidence shows that a variety of behavioural elements have a significant part in people' investment decision-making patterns, which has an impact on the population's economic situation. The purpose of this study is to illustrate how an individual's perspective, attitude, and conduct affect mutual fund investments. 2023, IGI Global. -
Data-Driven Decision Making
This book delves into contemporary business analytics techniques across sectors for critical decision-making. It combines data, mathematical and statistical models, and information technology to present alternatives for decision evaluation. Offering systematic mechanisms, it explores business contexts, factors, and relationships to foster competitiveness. Beyond managerial perspectives, it includes contributions from professionals, academics, and scholars worldwide, delivering comprehensive knowledge and skills through diverse viewpoints, cases, and applications of analytical tools. As an international business science reference, it targets professionals, academics, researchers, doctoral scholars, postgraduate students, and research organizations seeking a nuanced understanding of modern business analytics. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Data-Driven Decision Making in the VUCA Context: Harnessing Data for Informed Decisions
Data-driven decision making (DDDM) has evolved from being a strategic advantage to a necessity for organizations aiming to thrive in the dynamic business contexts. It is about using data as a tool to enhance strategic thinking, scenario planning, and adaptation in rapidly changing environments. It involves leveraging data and analytics to navigate the challenges of volatility, uncertainty, complexity, and ambiguity. By embracing DDDM, organizations can enhance their decision-making processes, gain a competitive edge, and navigate the challenges of volatility, uncertainty, complexity, and ambiguity with greater confidence. However, successful implementation requires addressing challenges, fostering a data-driven culture, and continually adapting best practices to meet the evolving demands of the VUCA environment. This chapter discusses how organizations leverage DDDM in VUCA context to support effective and rapid decision making aligned with organizations vision. Particularly, it would offer insights to transit from volatility to vision, uncertainty to understanding, complexity to clarity, and ambiguity to agility. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Data-Driven Drug Discovery Optimization for Breast Cancer Using Interpretable Machine Learning Models
Breast cancer remains one of the most prevalent malignancies worldwide, posing significant therapeutic challenges due to tumor heterogeneity and drug resistance. This study presents a reproducible, data-driven machine learning protocol for predicting drug sensitivity in breast cancer cell lines, with the dual objective of identifying potent single agents and synergistic drug combinations. Using curated datasets from the Genomics of Drug Sensitivity in Cancer (GDSC), two predictive approaches were implemented: a standalone XGBoost regressor and a hybrid Autoencoder-XGBoost pipeline. Preprocessing included label encoding, one-hot encoding, Z-score standardization, missing value imputation, and dimensionality reduction via PCA. Model evaluation demonstrated that XGBoost achieved superior performance (MSE = 1.3789, R2 = 0.8145) compared to the hybrid model (MSE = 4.0322, R2 = 0.4577). Interpretability was addressed using SHapley Additive exPlanations (SHAP), which identified TARGET_PATHWAY, DRUG_ID, TARGET, and CELL_LINE_NAME as key predictive features, aligning with established pharmacological mechanisms. Predicted synergy scores, derived from combining model outputs with DrugComb and SynergyDB data, highlighted promising drug pairs such as Bortezomib + Romidepsin and Paclitaxel + Bortezomib. These findings were further supported by PCA-based pharmacological clustering, revealing biologically relevant groupings of drugs with similar mechanisms of action. The proposed protocol provides a transparent and adaptable framework for precision oncology research, enabling both predictive accuracy and biological interpretability. By integrating rigorous preprocessing, model validation, explainability, and drug synergy analysis, this workflow offers a scalable foundation for translational drug discovery and repurposing in breast cancer treatment. 2025 JoVE Journal of Visualized Experiments. -
Data-driven education: Leveraging big data, AI, and machine learning for smarter learning environments
Big Data, artificial intelligence (AI), and machine learning are transforming education with self-paced learning, precise insights, and automated decisions. The effects these technologies have on education are transformative, especially when it comes to improving student achievement, advancing administrative operations, and personalizing the learning experience, as stated in this chapter. Big Data collects and analyzes immense volumes of data, while AI powers automation, makes predictions, automates evaluations, and enables the possibility of adaptive learning. Chatbots, recommendation engines, and tutoring systems enhance student-focused digital education. Still, integrating these technologies comes with challenges such as privacy and ethical issues, algorithm discrimination, and data security concerns. Some of the new trends are explainable AI (XAI) for ethical decision-making, blockchain and federated learning for privacy-preserving analytic systems, and verifiable credentials. In addition, XR, AI-based virtual laboratories, and neurosymbolic AI will have great consequences on the future learning environment. AI in education offers scalability and inclusivity but demands ethical regulation, governance, and resource management. This chapter recommends sustained effort in research, policy changes, and ethical integration of AI for the best possible use thereof. The education sector, by incorporating human-centered AI approaches, can create a just, sustainable future of learning that is accessible to all students around the world. 2026 Elsevier Inc. All rights reserved. -
Data-Driven Insights into Student Performance: Benchmarking Machine Learning Models for Grade Prediction using Regression and Classification Approaches
This research explores the effectiveness of 17 machine learning models in predicting student performance across Mathematics and Portuguese datasets. The primary goal of this study was to evaluate and compare regression and classification models to identify the most accurate predictors of student grades. A range of algorithms was tested, including linear models (Linear Regression, Elastic Net, Ridge, Lasso), tree-based models (Random Forest, Gradient Boosting, CatBoost, LightGBM), and advanced techniques (Neural Networks, SVM, XGBoost, Naive Bayes, SVR). The methodology involved data preprocessing, feature engineering, and splitting data into training and test sets. Base models were implemented, followed by hyperparameter tuning to optimize performance. Metrics like RMSE, MAE, MSE, R2 (for regression), and accuracy, precision, recall, F1 score (for classification) were used to assess performance. The study found that Gradient Boosting and Elastic Net consistently outperformed other models in regression tasks, achieving the highest R2 scores. For classification, Logistic Regression proved to be the most accurate, followed by Naive Bayes. These findings provide valuable insights for model selection in educational performance prediction, establishing Gradient Boosting and Logistic Regression as benchmark models. 2025 IEEE.