Browse Items (16488 total)
Sort by:
-
Machine learning based Unique Perfume Flavour Creation Using Quantitative Structure-Activity Relationship (QSAR)
Artificial intelligence played a vital role in brings revolutionary changes in the field of perfumery. It is much evident with events including the success of Philyra, exhibitions showcasing the ideas of this concept. Machine learning made it user friendly and more comfortable for the users by means of suggestive interaction. Machine learning also benefited the perfumers in helping them to choose the best combinations and likely successful outcomes. With growing concern about a healthy lifestyle, the thoughts about having an artificial intelligence to predict the user friendliness could be a huge success. This definitely would require a huge database comprising a large detail about diseases and the causes and combinational results of the various chemicals used in perfumery. This system may not be a completely successful one but would be reliable to a better extent. It would gain a positive response from various governmental health departments and would be encouraged by the consumers. Also, another possible development would be Artificial intelligence that is able to predict how long a perfume can last. This would let the consumer choose the one that suits the need. Through this idea we could now get a clear idea about the progress that we have made till this day. Further we can also be driven into vague ideas about how the future of Artificial intelligence would likely grow into. Machine learning and deep learning is a major pillar of artificial intelligence with larger application. Coming to our domain of discussion, artificial intelligence changed the way that things were in the past centuries about fragrance. This article proposed Quantitative structure-activity relationship (QSAR) method is used to predict the best perfume flavour. The proposed system also reduces mean absolute error (MAE). The proposed QSAR is also reducing the chemical composition and increase the perfume quality. 2021 IEEE. -
Machine Learning Classifiers for Credit Risk Analysis
The modern world is a place of global commerce. Since globalization became popular, entrepreneurs of small and medium enterprises to large ones have looked up to banks, which have existed in various forms since antiquity, as their pillars of support. The risk of granting loans in various forms has significantly increased as a consequence of this, the businesses face financing difficulties. Credit Risk Analysis is a major aspect of approving the loan application that is done by analyzing different types of data. The goal is to minimize the risk of approving the loan for the Individuals or businesses who might not pay back on time. This research paper addresses this challenge by applying various machine learning classifiers to the German credit risk dataset. By evaluating and comparing the accuracy of these models to identify the most effective classifier for credit risk analysis. Furthermore, it proposes a contributory approach that combines the strengths of multiple classifiers to enhance the decision-making process for loan approvals. By leveraging ensemble learning techniques, such as the Voting Ensemble model, the aim is to improve the accuracy and reliability of credit risk analysis. Additionally, it explores tailored feature engineering techniques that focus on selecting and engineering informative features specific to credit risk analysis. 2024 Sudiksha et al., licensed to EAI. -
Machine Learning Enabled Financial Statements in Assessing a Business's Performance
Machine Learning Enabled Financial Statements (MLEFS) revolutionize corporate performance analysis. This study examines MLEFS's dramatic effects using data gathering, model creation, interpretability, deployment, and ethics. We found that MLEFS accurately predicts crucial financial measures, helping investors, lenders, and financial analysts make better judgments. The study emphasizes the importance of financial measures like Return on Assets (ROA) in supporting financial theories and models. The research also stresses interpretability and ethics, promoting responsible machine learning in finance. Future trends include enhanced interpretability, strong ethical frameworks, real-time analysis, big data integration, regulatory adaption, and industrial acceptance. This study opens the door to data-driven financial analysis and decision-making, improving strategic planning, risk reduction, and investor trust. 2024 IEEE. -
Machine Learning for Early Detection of Chronic Diseases: A Case Study in Diabetes Prediction
Early detection of chronic diseases like diabetes is very important for early treatment and effective management. This chapter describes a machine learning (ML) solution for predicting diabetes risk from clinical structured data and a case study is constructed on the PIMA Indian Diabetes dataset. The solution caters to the entire ML pipeline: problem formulation, preprocessing of data, feature selection (FS), model training, validation, and deployment issues. Different preprocessing techniques including missing value imputation, detection of outliers, and feature normalization were used for improving data quality. FS techniques like correlation analysis, recursive feature elimination, and selection based on domain knowledge were utilized to decrease the dimensionality of the data as well as model interpretability. Extensive comparison was conducted among widely used classification models like logistic regression (LR), random forest, support vector machine, and XGBoost. It was suggested to adopt a stacked ensemble model of LR, RF, SVM, and XGBoost that achieved better performance in terms of accuracy, precision, recall, and F1-score. The findings confirm the tremendous potential of ML to enable early diabetes diagnosis as an unobtrusive, data-driven, and scalable decision-making supporting system for physicians. This is the groundwork for the further development of clinically applicable artificial intelligence-based prediction models within real-world healthcare settings. 2026 Walter de Gruyter GmbH, Berlin/Boston, Genthiner Stra 13, 10785 Berlin. -
Machine learning for healthcare
Machine learning currently drives healthcare innovation, enabling novelty in solving complex medical problems. This chapter will present an in-depth critical review of various machine learning techniques applicable in healthcare in general, focusing on practical applications and recent advancements. It will further discuss supervised and unsupervised learning to semi-supervised learning methods, thereby detailing their uses for disease prediction, segmentation of patients, and image analysis in medical science. Among the most important areas in ML includes data preprocessing and feature engineering issues in health-care datasets. This further includes treatments for missing data, dimensionality reduction, and class imbalance. This chapter also discusses extensive case studies with state-of-the-art approaches that give insight into how the ML approach is changing health care decision-making, increasing diagnostic precision, and improving patient outcomes. Interpretability, scalability, and the mitigation of bias are further discussed as some of the challenges in the implementation of ML in healthcare. Ethical considerations regarding the need to develop responsible AI in healthcare and regulatory compliance are also discussed. It aims to serve as a handbook for researchers, practitioners, and policy analysts operating at the intersection between ML and healthcare. 2026 -
Machine Learning for Mental Health: A Sentiment Analysis Approach for Detecting Depressive Tendencies on LinkedIn During Layoffs Using RoBERTa
In the present corporate set-up, layoffs are an unfortunate yet common occurrence. Such occurrences lead to loss of job security and can have direconsequences on an individual's mental health, leading to depression. Depression was a global health concern well before the current downsizing came into the picture. These trying times have acted as a catalyst for this illness that affects not just mental health but all aspects of an individuals life. The study investigates the use of sentiment analysis on LinkedIn data to identify and examine depressive tendencies among victims of layoffs. Web-scraped information was taken from LinkedIn profiles of individuals affected directly or indirectly by layoffs. RoBERTa, a transformers model, is used to classify people as depressed or not by evaluating sentiment and emotional cues. A comparison between four machine learning algorithms- Decision Tree, Logistic Regression, SVM, and Nae Bayes is drawn to check their ability to detect depression. The SVM classifier performed best with an accuracy of 95.59% and 83.52% with the CountVectorizer and TF-IDF feature selection methods, respectively. Sentiment analysis aids in this research by examining the melancholic undertones in the words and phrases used in texts authored by people affected by layoffs directly or indirectly. The knowledge gained from this research can significantly affect corporate initiatives, mental health services, and human resource practices during such challenging times. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Machine Learning for Smart School Selection and Admissions
Choosing the best school for their kid is an important choice that parents must make, and it is sometimes stressful and unsure. Machine learning is a potential way to improve and streamline the admissions and school selection process in the current digital era. This study investigates the use of machine learning methods in the context of selective admissions and smart school selection. We propose a user-friendly, web-based tool in the early phases of our study that helps parents and guardians locate the ideal school for their kid by using machine learning algorithms. To provide individualized school recommendations, the platform gathers and analyses a range of data, such as extracurricular activity participation, academic achievement, regional preferences, and school reputation. This makes choosing a school easier and supports parents in making wise choices. This paper's second section explores the technical details of the machine learning techniques used, going into the nuances of feature selection, data preparation, and model assessment. We also draw attention to the difficulties and moral issues - such as maintaining impartiality and avoiding bias - that come with using machine learning to school selection. 2023 IEEE. -
Machine Learning in Cyber Threats Intelligent System
Cybercriminals disrupt services, exfiltrate sensitive data, and exploit victim machines and networks to perform malicious activities against organizations. A malicious adversary seeks to steal, destroy, or compromise business assets that have a specific financial, reputational, or intellectual value. As a result, organizations are complementing their perimeter defenses with threat intelligence platforms to address these security challenges and eliminate security blind spots for their systems. Any type of information useful for identifying, assessing, monitoring, and responding to cyber threats is considered cyber threat intelligence. Organizations can benefit from increased visibility into cyber threats and policy violations. An organizations threat intelligence allows them to prevent or mitigate various types of cyberattacks. The use of machine learning and artificial intelligence is a key component of cybersecurity conflict, which together allows attackers and defenders to function at new speeds and scales. In spear-phishing attacks, relatively frivolous machine learning algorithms have been used to overwhelming effect as adversarial artificial intelligence. This chapter discusses the various cyber threats, cyber security attack types, publicly available datasets for research work, and machine learning techniques in cyber-physical systems. 2024 selection and editorial matter, S. Vijayalakshmi, P. Durgadevi, Lija Jacob, Balamurugan Balusamy, and Parma Nand; individual chapters, the contributors. -
Machine Learning in Financial Distress: A Scoping Review
Predicting financial distress is crucial for stakeholders, policymakers, governments, and management in decision-making processes. Researchers have developed various prediction models encompassing both traditional and machine-learning approaches. Notably, recent attention has shifted towards employing machine learning models to address the limitations of traditional methods. This study seeks to offer insights into current trends, identify gaps, and suggest future research directions using machine learning models for financial distress prediction, employing the PRISMA Extension for Scoping Reviews methodology. To achieve this, a comprehensive search was conducted across three databasesScience Direct, EBSCO, and ProQuestspanning from 2020 to 2023, identifying 34 relevant articles for analysis. The findings underscore the prevalent use of Support Vector Machine in financial distress prediction, followed by the Random Forest Classifier and Artificial Neural Network, with little attention paid to other models. Furthermore, the study underscores the necessity for more research in developing countries, noting the predominance of studies from developed nations. While machine learning models hold promise for enhancing the accuracy and efficiency of financial distress prediction, additional research is imperative to evaluate their effectiveness and applicability across diverse contexts. This scoping review aims to furnish researchers, policymakers, and institutions with valuable insights and policy recommendations, shedding light on underexplored machine-learning techniques. 2024, Iquz Galaxy Publisher. All rights reserved. -
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. -
Machine Learning in Investment Analysis-Enhancing or Replacing Human Judgment
Machine Learning (ML) involvement in investment analysis is quickly revolutionizing the investment-based decisions through becoming highly accurate, quick, and embracing increased data processing capabilities. This paper is to research on whether ML is complementary or a possible replacement to human financial judgment. We run experiments over 1.2 million financial transactions between 150 firms comparing old style analyst recommendations and ML-models, including XGBoost, LSTM and Random Forest. The findings indicate that ML models outperformed prediction capability by 19.6 percent and lowered the volatility of the portfolios by 14.3 percent in 5-year investment. Also, the ML-Aided decision-making was better than human (only) approaches in 78 percent of the cases in markets with high volatility or that involved trading in complicated assets. The qualitative variables like regulatory policy changes and investor sentiment however were too difficult to decipher under the leadership of ML only. Our results indicate that ML supports rather than supers the human judgement and thus demonstrates a hybrid paradigm of decision making that resolves computational exactitude with context sensitive understanding in the modern investment scenarios. 2025 IEEE. -
Machine learning in smart agriculture
Agriculture is the cultivation of the soil, the growth of crops and the raising of livestock. Agriculture is critical to the economic development of a country. Farming generates nearly 58% of a country's primary income. Previously, cultivators had accepted conventional farming practices. Because these methods were imprecise, they produced less and took longer time. Precise farming boosts productivity by precisely determining which steps must be completed at what time. Precision farming entails forecasting the weather, analyzing soil, recommending crops for cultivation and calculating the amount of fertilizer and pesticides that must be used. Precise farming uses advanced technologies such as IoT, data mining, data analytics, and machine learning (ML) to collect data, train systems and predict outcomes. Precision farming employs technology to reduce manual labor and boost productivity. Farmers have recently faced several difficulties, such as crop failure due to insufficient rainfall, soil infertility and so on. The proposed work in determining the soil, managing crops and harvesting efficiently can solve the problems caused by environmental changes. It guides a person's farming strategy to produce better results through a proper prediction process. The goal of this research is to assist an individual in efficiently cultivating crops, resulting in high productivity at a low cost. It also assists in estimating the total cost of cultivation and forecasting the likely economic barriers. This would help a person plan activities prior to cultivation, resulting in an integrated farming solution. 2023 River Publishers. All rights reserved. -
Machine learning insights into mental health risk factors associated with climate change: Impact on schoolchildren's cognitive abilities
In this chapter, we use machine learning techniques to investigate how the effects of climate change and certain risk factors for mental health affect students' cognitive skills in the classroom. The mental health of at-risk populations, especially students, must be considered in light of the fact that the world's environment is changing significantly. Using state-of-the-art machine learning algorithms, we analyze large datasets that include environmental variables, socio-economic characteristics, and markers of mental health among school-aged persons. We are primarily interested in identifying key relationships and trends that might help us understand the complex relationship between climate change and cognitive health in this population. In order to uncover complex insights, the chapter takes a holistic approach by combining feature selection, model training, and interpretability analysis. The cognitive capacities of school-aged children may be significantly impacted by some climate- related stresses, according to preliminary results. The findings add to our knowledge of the interconnected webs of environmental shifts, psychological susceptibilities, and cognitive consequences. Educators, legislators, and healthcare providers can benefit from this study's use of machine learning insights into the possible effects of climate change on students' mental health. It also paves the way for the creation of tailored treatments and adaptive techniques to deal with the highlighted dangers, fostering resilience and prosperity in the face of a changing environment. 2024, IGI Global. All rights reserved. -
Machine Learning Insights into Mobile Phone Usage and Its Effects on Student Health and Academic Achievement
The research intends to find how students' health and academic performance are affected by their smartphone use. Considering how widely smartphones are used among students, it is important to know how they could affect health and learning results. This study aims to create prediction models that can spot trends and links between smartphone usage, health ratings, and academic achievement, thereby offering insightful information for teachers and legislators to encourage better and more efficient use among their charges. Data on students' mobile phone use, health evaluations, and academic achievement were gathered for the study. Preprocessing of the dataset helped to translate categorical variables into numerical forms and manage missing values. Trained and assessed were many machine learning models: Random Forest, SVM, Decision Tree, Gradient Boosting, Logistic Regression, AdaBoost, and K-Nearest Neighbors (KNN). The models' performance was evaluated in line with their accuracy in influencing performance effects and health ratings. Predictive accuracy was improved by use of feature engineering and model optimization methods. With 63.33% of accuracy for estimating health ratings, the SVM model was most successful in capturing the link between smartphone usage and health results. With an accuracy of 50%, logistic regression performed very well in forecasting performance effect, therefore stressing important linear connections between consumption habits and academic success. Random Forest and Decision Tree models were less successful for performance impact even if they showed strong performance in health forecasts. These results highlight the need of customized treatments to reduce the detrimental consequences of too high mobile phone use on students' academic performance and health. 2024 IEEE. -
Machine Learning Insights into Predicting Crude Oil Prices
This research paper delves into the complexities of crude oil, highlighting its extraction, composition, and transformation into valuable derivatives. Examining the pricing dynamics, it explores the intricate interplay of social and economic factors that shape crude oil's value, emphasizing its critical role in global energy and industrial sectors. A forecasting model is introduced, focusing on key factors - heating oil, SPX, GPNY, and EU DOL EX - utilizing five machine learning models. Historical data reveals the efficacy of conventional models, particularly Random Forest, in predicting crude oil prices, enhanced by feature engineering techniques. The paper concludes by suggesting avenues for further exploration, offering valuable insights for readers in this dynamic research domain. 2024 IEEE. -
Machine Learning Integration for Enhanced Solar Power Generation Forecasting
This paper reviews the advancements in machine learning techniques for enhanced solar power generation forecasting. Solar energy, a potent alternative to traditional energy sources, is inherently intermittent due to its weather-dependent nature. Accurate forecasting of photovoltaic power generation (PVPG) is paramount for the stability and reliability of power systems. The review delves into a deep learning framework that leverages the long short-term memory (LSTM) network for precise PVPG forecasting. A novel approach, the physics-constrained LSTM (PCLSTM), is introduced, addressing the limitations of conventional machine learning algorithms that rely heavily on vast data. The PC-LSTM model showcases superior forecasting capabilities, especially with sparse data, outperforming standard LSTM and other traditional methods. Furthermore, the paper examines a comprehensive study from Morocco, comparing six machine learning algorithms for solar energy production forecasting. The study underscores the Artificial Neural Network (ANN) as the most effective predictive model, offering optimal parameters for real-world applications. Such advancements not only bolster the accuracy of solar energy forecasting but also pave the way for sustainable energy solutions, emphasizing the integration of these findings in practical applications like predictive maintenance of PV power plants. The Authors, published by EDP Sciences, 2024. -
Machine Learning Methods for Online Education Case
Online education has become a popular choice for learners of all ages and backgrounds due to its accessibility and flexibility. However, providing personalized learning experiences for a diverse range of students in online education can be challenging. Machine learning methods can be used to provide personalized learning experiences and improve student engagement in online education. In this case study, We're going to do some research on machine learning. methods in an online education platform. The platform provides courses in various subjects and is designed to be accessible to students from all over the world. The platform collects data on student behavior, such as the courses they enroll in, the time they spend on each course, and their performance on assignments and quizzes. We will explore several machine learning methods that can be applied to this data, including clustering, classification, and recommendation systems. Clustering algorithms can be used to group students based on their learning behavior and preferences, allowing instructors to provide personalized feedback and course recommendations. Classification algorithms can be used to predict student success in a particular course, allowing instructors to intervene and provide additional support if needed. Recommendation systems can be used to suggest courses to students based on their interests and past behavior. We will also discuss the potential benefits and challenges of using machine learning methods in online education. Benefits include increased student engagement, improved learning outcomes, and more efficient use of resources. Challenges include ensuring data privacy and security, preventing algorithmic bias, and maintaining transparency and fairness in the decision-making process. Overall, machine learning methods have the potential to transform online education by providing personalized learning experiences and improving student outcomes. By leveraging the vast amounts of data generated by online education platforms, we can create more effective and efficient learning experiences that meet the needs of students from diverse backgrounds and learning styles. 2023 IEEE. -
Machine Learning Methods leveraging ADFA-LD Dataset for Anomaly Detection in Linux Host Systems
Advancement in network technology and revolution in the global internet transformed the overall Information Technology (IT) infrastructure and its usage. In the era of the Internet of Things (IoT) and the Internet of Everything (IoE), most everyday gadgets and electronic devices are IT-enabled and can be connected over the internet. With the advancements in IT technologies, operating systems also evolved to leverage these advancements. Today's operating systems are more user-friendly and feature-rich to support current IT requirements and provide sophisticated functionalities. On the one hand, these features enabled operating systems accomplish all current requirements, but on the other hand, these modern operating systems increased their attack surface considerably. Intrusion detection systems play a significant role in providing security against the broad spectrum of attacks on host systems. Intrusion detection systems based on anomaly detection have become a prominent research area among diverse areas of cyber security. The traditional approaches for anomaly detection are inadequate to discover the operating system level anomalies. The advancement and research in Machine Learning (ML) based anomaly detection open new opportunities to tackle this challenge. The dataset plays a significant role in ML-based system efficacy. The Australian Defence Force Academy Linux Dataset (ADFA-LD) comprises thousands of normal and attack processes system call traces for the Linux platform. It is the benchmark dataset used for dynamic approach-based anomaly detection. This paper provided a comprehensive and structured study of various research works based on the ADFA-LD for host-based anomaly detection and presented a comparative analysis. 2022 IEEE. -
Machine Learning Methods to Identify Aggressive Behavior in Social Media
With the more usage of Internet and online social media, platforms creep with lot of cybercrimes. Texts in the online platforms and chat rooms are aggressive. In few instances, people target and humiliate them with the text. It affects victim mental health. Therefore, there is a need of detecting the abuse words in the text. In this paper, a study of machine learning methods is done to identify the aggressive behavior. Accuracy can be improved by incorporating additional features. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Machine Learning Model Enabled with Data Optimisation for Prediction of Coronary Heart Disease
Cardiovascular disorders remain leading cause for mortality worldwide, necessitating robust early risk assessment. Although machine learning models show promise, most rely on conventional preprocessing, which lacks model portability across datasets. We propose an integrated preprocessing pipeline enhancing model generalizability. Our methodology standardises features solely based on training statistics and then transforms test data identically to prevent leakage. We handle class imbalance through synchronised oversampling, enabling consistent performance despite distribution shifts. This framework was evaluated on an open-source dataset of clinical parameters from an African cohort using classifiers like support vector machines and gradient boosting. All models achieved upto 80% accuracy. Remarkably, evaluating the identical models on five external European and Asian datasets maintains 80% - 86% accuracy. Our reproducible data conditioning strategy enables precise and transportable heart disease risk prediction, overcoming population variability. The framework provides the flexibility to readily retrain models on new data or update risk algorithms for clinical implementation in diverse locales. Our work accelerates the safe translation of machine learning to guide cardiovascular screening worldwide. 2024 IEEE.