Endometriosis is a chronic disease that affects a considerable percentage of women of reproductive age and is characterized by the presence of endometrial tissue outside the uterine cavity, leading to symptoms such as...
详细信息
ISBN:
(数字)9798331522216
ISBN:
(纸本)9798331522223
Endometriosis is a chronic disease that affects a considerable percentage of women of reproductive age and is characterized by the presence of endometrial tissue outside the uterine cavity, leading to symptoms such as pelvic pain and dysmenorrhea. The aim of this study is to develop a predictive model for the classification of endometriosis using four machine learning algorithms: Random Forest, LASSO, SVM, and Naive Bayes. For this purpose, a dataset from the Global Health Data Exchange was utilized, consisting of 1,000 cases of patients with endometriosis. The methodology included data cleaning and preprocessing, as well as the evaluation of each algorithm's performance using four metrics: precision, recall, F1-Score, and accuracy. The findings revealed that the Random Forest algorithm was the most effective in identifying endometriosis, outperforming the other algorithms with a precision of 0.99 for the “endometriosis” class and an overall accuracy of 0.98.
Cardiovascular diseases continue to be the primary cause of death worldwide, responsible for around 31% of all deaths each year, as reported by the World Health Organization (WHO). Although significant progress has be...
详细信息
ISBN:
(数字)9798331505745
ISBN:
(纸本)9798331505752
Cardiovascular diseases continue to be the primary cause of death worldwide, responsible for around 31% of all deaths each year, as reported by the World Health Organization (WHO). Although significant progress has been made in their diagnosis and treatment, heart disease remains highly prevalent. It has risen significantly due to unhealthy dietary habits and reduced physical activity. Predicting heart diseases using patient-related data, such as blood pressure, cholesterol levels, and other health metrics, has emerged as one of the most complex tasks for human analysts in modern times. As a result, there is a growing global demand for timely and accurate predictive models in identifying heart disease in healthcare industry, predominantly in the field of cardiology. In this paper, an intelligent heart disease prediction using ant colony optimization using machine learning algorithms is proposed. It includes two phases namely: 1) Feature Selection and 2) Classification. Ant Colony Optimization (ACO) is used to reduce the redundancy in feature selection from the large data set and helps to upgrade the performance of the classifier in the next stage. Then, we exploit the different classification algorithms such as K-Nearest Neighbors (KNN), Support Vector machine (SVM), Decision Tree (DT), Random Forest (RF) and XGBoost (XGB). These algorithms are chosen for their ability to deliver high accuracy, computational efficiency, and optimized memory usage, making them well-suited for this application. Furthermore, performance of the machine learning algorithms has been evaluated using accuracy, precision, F 1 score, recall and support parameters. The results illustrate that the amalgamation of the ACO algorithm and SVM classifier has the utmost performance for use in heart disease estimation.
Customer satisfaction in the airline industry is influenced by demographic, service-related, and operational factors. As competition grows and passenger expectations evolve, understanding these determinants is crucial...
详细信息
ISBN:
(数字)9798331531935
ISBN:
(纸本)9798331531942
Customer satisfaction in the airline industry is influenced by demographic, service-related, and operational factors. As competition grows and passenger expectations evolve, understanding these determinants is crucial for improving service quality and loyalty. This study uses machine learning algorithms to analyze key drivers of customer satisfaction and derive actionable insights. It employs techniques such as Logistic Regression, Gaussian Naive Bayes, Gradient Boosting, K-Nearest Neighbors, and Random Forest classifiers. Among these, Gradient Boosting and Random Forest achieved the highest predictive accuracy, with AUC scores of 0.99 and 0.9937. A strong correlation (0.97) between departure and arrival delays highlights the importance of punctuality. Inflight services like entertainment and legroom, especially on long-haul flights, significantly enhance satisfaction. Demographic analysis shows passengers aged 40+ report higher satisfaction, emphasizing the need for tailored service strategies, while younger passengers (20-40) show lower satisfaction, indicating a need for personalized engagement. These findings provide a data-driven foundation for improving airline operations and service delivery. Future research should integrate real-time data for more adaptive service improvements.
In the area of farming, parts of the soil are of special note as it has to do with growing crops and provision of food for consumption. Soil analysis is also important in crop rating since it reflects some important I...
详细信息
ISBN:
(数字)9798331527549
ISBN:
(纸本)9798331527556
In the area of farming, parts of the soil are of special note as it has to do with growing crops and provision of food for consumption. Soil analysis is also important in crop rating since it reflects some important Indices of the soils such as nutrients, pH, and texture which all affect plants' growing condition. Farmers are able to utilize this strategy in order to plant the right sorts of crops on their area of land, hence gaining scope in the yield and resources consumed. This paper showcases the application of advanced machine learning algorithms to optimize crop recommendations based on essential climatic, geographic, and eco-spatial parameters. In such techniques, depending on humidity, temperature and rainfall, certain patterns and relations are established and the best crops are recommended. For the purpose of generating predictive models that recommend the growth of specific crops in specific regions with the aim of increasing agricultural productivity, the system deploys the algorithms of Gradient Boosting, XGBoost, and LightGBM.
The Actual Takeoff Weight (ATOW) is a significant and critical aircraft performance parameter that has a huge impact on not only fuel consumption and derived gaseous emissions but also on flight trajectory prediction....
详细信息
ISBN:
(数字)9798331534738
ISBN:
(纸本)9798331534745
The Actual Takeoff Weight (ATOW) is a significant and critical aircraft performance parameter that has a huge impact on not only fuel consumption and derived gaseous emissions but also on flight trajectory prediction. Aircraft mass data, including Actual Takeoff Weight, is typically considered sensitive information by airlines due to its reliance on factors such as passenger and cargo loads, as well as operational strategies and as such have a competitive meaning. As a result, this data is generally not disclosed to researchers or entities outside the operating airline. Automatic Dependent Surveillance-Broadcast (ADS-B) technology offers precise, up-to-the-minute data on aircraft velocity and acceleration. This information is publicly accessible and not exclusively controlled by any particular airline. This study demonstrates the potential of machine learning algorithms, which using relevant ADS-B data, can predict the Actual Takeoff Weight of the aircraft with high accuracy.
An Internet of Things (IoT)-based motor damage diagnosis and predictive maintenance system using machinelearning (ML) for on-time motor health diagnostics. Critical information consisting of to a temperature, vibrati...
详细信息
ISBN:
(数字)9798331544607
ISBN:
(纸本)9798331544614
An Internet of Things (IoT)-based motor damage diagnosis and predictive maintenance system using machinelearning (ML) for on-time motor health diagnostics. Critical information consisting of to a temperature, vibration, and RPM sensor data is retrieved from the sensors and assessed using a pre-learned machinelearning model. The model analyzes and classifies the sensor data as either a “Good Product” or “Failure Product.” The system performs the vital task of failure identification, facilitating prompt system amelioration. Each sensor is connected to a central ESP-32 microcontroller which serves as the system's brain by gathering and sending the sensor data to a web server in real-time for further computation. Employed with the system is Random Forest, a classifying machinelearning model that scans data to extract new patterns such as excessive vibration, overheating, and irregular changes in RPM. These sharp changes are also known as clear signs of deteriorating health of the machine. In addition to the web interface, email notification helps telemonitor system condition for most recent changes in motor health. Remediating an issue on time helps avoid device standstill and expensive damages. The life of the instrumented device is prolonged with the AI powered system controlling timely maintenance, optimizing operations. With this solution, industrial environments are more efficient as they enhance decision making and maintenance tactics since the solution is proactive, flexible, and scalable.
Diabetes is a chronic metabolic condition characterized by elevated blood glucose levels, posing significant health and economic challenges globally. This study aimed to evaluate the performance of Random Forest and D...
详细信息
ISBN:
(数字)9798331506995
ISBN:
(纸本)9798331507008
Diabetes is a chronic metabolic condition characterized by elevated blood glucose levels, posing significant health and economic challenges globally. This study aimed to evaluate the performance of Random Forest and Decision Tree algorithms in classifying diabetes, addressing the increasing prevalence of the disease and the necessity for accurate diagnostic tools. Both algorithms were applied to a dataset containing 100,000 entries sourced from Kaggle. The study employed systematic preprocessing steps, including normalization and feature selection, to optimize data quality. The dataset was split into training (80 % ) and testing (20 % ) subsets, ensuring robust evaluation. Random Forest and Decision Tree algorithms were implemented with carefully tuned parameters to maximize performance, and their outputs were assessed using metrics such as accuracy, precision, sensitivity, and specificity. Results revealed that Random Forest achieved a higher accuracy of 96%, outperforming Decision Tree's 95%, with superior sensitivity and specificity. These findings highlight Random Forest's effectiveness in capturing complex patterns and reducing overfitting, which is consistent with prior studies on medical data classification. This research underscores the importance of algorithm selection and data preprocessing in improving diabetes classification. Future studies should explore ensemble methods and diverse datasets to enhance generalizability and predictive accuracy, offering valuable insights for healthcare applications.
Breast cancer is still a major global health issue, and early detection is important for better patient outcomes. This research discusses the use of machine learning algorithms for predicting breast cancer through the...
详细信息
ISBN:
(数字)9798331509859
ISBN:
(纸本)9798331509866
Breast cancer is still a major global health issue, and early detection is important for better patient outcomes. This research discusses the use of machine learning algorithms for predicting breast cancer through the Orange data mining software. We utilized a comprehensive dataset containing various breast cancer features to develop and evaluate multiple machinelearning models. The Orange tool facilitated data preprocessing, feature selection, model training, and performance evaluation. Our analysis compared the efficacy of several algorithms, in-cluding random forests, support vector machines, KNN, Gradient Boosting and neural networks. The study highlights the potential of orange tool for machinelearning in enhancing breast cancer detection and diagnosis, potentially aiding healthcare profession-als in making more informed decisions. Furthermore, the user-friendly interface of the Orange tool showcases its utility in medical research and potential for wider adoption in clinical settings. For this paper, we consulted the Wisconsin dataset. The findings reveal that SVM models, particularly those utilizing ensemble methods like bagging and boosting with RBF kernels, significantly outperform traditional classifiers in both small and large datasets. In contrast, while Neural Networks demonstrated competitive accuracy, they often faced challenges related to overfitting and computational demands. Feature selection techniques were identified as crucial for enhancing model performance, allowing for more efficient training processes.
Network Intrusion Detection Systems (NIDS) play crucial role for maintaining the security of modern network infrastructures. With the increasing sophistication of cyber-attacks, traditional signature-based methods hav...
详细信息
ISBN:
(数字)9798331509934
ISBN:
(纸本)9798331509941
Network Intrusion Detection Systems (NIDS) play crucial role for maintaining the security of modern network infrastructures. With the increasing sophistication of cyber-attacks, traditional signature-based methods have become insufficient. machinelearning (ML) techniques offer a promising alternative, providing the ability to detect novel threats by learning from network traffic patterns. This article provides a comparative analysis of different ML algorithms applied to NIDS, evaluating their performance based on key metrics such as accuracy, precision, recall, and Fl-score.
One of the main causes of cancer-related deaths is lung cancer, and increasing survival rates requires early detection. The use of sophisticated machinelearning (ML) algorithms to improve the identification of lung c...
详细信息
ISBN:
(数字)9798331512248
ISBN:
(纸本)9798331512255
One of the main causes of cancer-related deaths is lung cancer, and increasing survival rates requires early detection. The use of sophisticated machinelearning (ML) algorithms to improve the identification of lung cancer from chest X-rays and CT images is investigated in this study. Vision Transformers (ViT), Reinforcement learning (RL), Generative Adversarial Networks (GANs), Meta-learning, and Ensemble learning are some of the state-of-the-art methods we use. Compared to conventional CNNs, By capturing long-range dependencies in medical pictures, Vision Transformers (ViT) can improve accuracy by up to 85–96% compared to typical CNN models, especially when it comes to feature extraction and categorization. The optimization of diagnostic workflows using Reinforcement learning (RL) results in a 90% improvement in decision-making efficiency and adaptive learning capabilities, which greatly enhance real-time picture analysis. Training datasets can be enhanced with Generative Adversarial Networks (GANs), which create realistic synthetic images and increase model generalization by 90–97%. This is crucial in situations where data is scarce or unbalanced. For uncommon or underrepresented cancer cases, meta-learning improves classification accuracy by 90% by allowing models to learn from sparsely labeled data. Ensemble learning reduces bias and variation by combining many models using approaches like XGBoost, Bagging, and Stacking, increasing total accuracy by 80–95%. When compared to conventional methods, key performance indicators including precision, recall, and F1 score demonstrate significant gains, with sensitivity rising by up to 90% and specificity improving by 85%. These cutting-edge algorithms greatly improve the detection of lung cancer, facilitating quicker and more precise diagnoses and assisting clinicians in making decisions that will benefit patients.
暂无评论