Advances in corneal imaging have generated vast datasets, making it challenging to extract clinically relevant insights. Machine Learning (ML) provides ophthalmologists with essential tools for keratoconus (KC) detect...
详细信息
ISBN:
(数字)9798331542726
ISBN:
(纸本)9798331542733
Advances in corneal imaging have generated vast datasets, making it challenging to extract clinically relevant insights. Machine Learning (ML) provides ophthalmologists with essential tools for keratoconus (KC) detection and clinical decision-making. However, effective Exploratory Data Analysis (EDA) remains crucial for identifying trends, forming hypotheses, and selecting key parameters to build robust ML models. This paper presents a comprehensive EDA framework that fosters collaboration between AI specialists and clinicians to enable early KC detection. Using statistical and visual techniques alongside expert input, a clinical dataset with 79 features from 2,491 cases is pre-processed, analyzed, and effectively prepared for ML modelling. The analysis identified a key subset of features–just 6.3% of the original dataset–which was used to develop and evaluate the classification performance of several ML models. Among them, the Random Forest model achieved 99.6% accuracy, surpassing previous studies and demonstrating the effectiveness of the proposed EDA framework.
Accurate keratoconus (KC) staging is vital for improving patient care and guiding clinical decision making. Choosing the right Machine Learning (ML) algorithm is key to effectively tackling this challenge and ensuring...
详细信息
ISBN:
(数字)9798331542726
ISBN:
(纸本)9798331542733
Accurate keratoconus (KC) staging is vital for improving patient care and guiding clinical decision making. Choosing the right Machine Learning (ML) algorithm is key to effectively tackling this challenge and ensuring optimal performance. This paper presents a detailed comparison of eight ML algorithms commonly used in KC detection, based on a clinical dataset collected by the authors over the past decade. The study investigates each algorithm's effectiveness in distinguishing KC severity stages. Results showed that ensemble learning algorithms outperformed other approaches, with Random Forest (RF) emerging as the top-performing model, achieving the highest validation accuracy of 98.82%. When tested on unseen data, the RF model maintained a comparable accuracy of 98%, demonstrating its robustness, and generalizability in accurately distinguishing between different stages of KC severity.
This paper presents an Internet of Things (IoT) platform that integrates humanoid robots to enhance Type 1 Diabetes Management (T1DM) in children. By leveraging advancements in IoT, robotic coaching, and artificial in...
详细信息
ISBN:
(数字)9798331542726
ISBN:
(纸本)9798331542733
This paper presents an Internet of Things (IoT) platform that integrates humanoid robots to enhance Type 1 Diabetes Management (T1DM) in children. By leveraging advancements in IoT, robotic coaching, and artificial intelligence (AI), the platform improves remote diabetes care delivery. The robot wirelessly collects biometric measurements from various patient devices, along with data on diet, physical activity, insulin intake, and overall well-being through interactive dialogues. This information is transmitted to a remote smart disease management hub for analysis, where AI algorithms generate personalized feedback, which is then relayed back to patients through the robotic interface at home. A fully functional platform has been successfully tested in a pilot clinical study, demonstrating a patient satisfaction rate exceeding 86%, with 91% of participants expressing a positive perception of the robot as a new medical device in T1DM. These findings underscore the transformative potential of robotic technology in diabetes care as it evolves and becomes more accessible.
Background and objective : Accurate staging of keratoconus (KC) is crucial for timely intervention and improving patient quality of life. Unlike prior studies that relied on traditional base machine learning (ML) mode...
详细信息
Background and objective : Accurate staging of keratoconus (KC) is crucial for timely intervention and improving patient quality of life. Unlike prior studies that relied on traditional base machine learning (ML) models, this paper proposes a more advanced two-stage ensemble learning model, co-developed with ophthalmologists, designed to automate KC severity detection and track disease progression with improved *** : A clinical dataset collected from Pentacam corneal tomography devices serves as a comprehensive source of corneal data. Following extensive pre-processing, key Pentacam indices strongly correlated with KC severity staging are identified and clinically validated through a rigorous feature selection process. These selected indices are used to train, optimize, and validate a two-stage ensemble learner that combines the strengths of four top-performing base ML models—Random Forest (RF), Gradient Boost (GB), Decision Tree (DT), and Support Vector Machine (SVM)—for KC severity classification. Three of these base learners are stacked to leverage their complementary strengths, with their predictions aggregated into a new feature matrix. This matrix is then passed as input to the fourth model, a meta-classifier, which generates the final classification *** : Experimental evaluation of the proposed two-way ensemble learning model achieved superior performance compared to previous studies. This approach achieved an overall validation accuracy of 99.41%, a precision of 99.43%, and a sensitivity of 99.41%. The F1 and F2 scores were 99.42% and 99.41%, respectively. The classification quality, measured by Matthew's Correlation Coefficient (MCC), also attained a value of 0.993. Additionally, the model was tested with unseen data, achieving an accuracy of 99%, highlighting its remarkable consistency, robustness, and generalizability in distinguishing between the distinct KC severity stages (0–4).Conclusion : The proposed model, developed in co
In today’s digital landscape, affordable Programmable Logic Controllers (PLCs) for industrial automation and applied engineering education are essential, as traditional setups are often too costly for many institutio...
详细信息
In today’s digital landscape, affordable Programmable Logic Controllers (PLCs) for industrial automation and applied engineering education are essential, as traditional setups are often too costly for many institutions and individuals. In this paper, a cost-effective, modular PLC lab was designed and developed to enable hands-on learning in industrial automation. The lab accommodates ten pairs of trainees, allowing for simultaneous experimentation using modular simulation kits tailored for various applications, such as traffic light systems, elevators, and automated filling systems. Trainees can prepare, test, and verify their code on these kits in real-time, enhancing their hands-on experience with programmable logic controllers. Each kit offers a set of features, including an integrated input/output interface that supports a variety of input types (e.g., switches, sensors, and push buttons) and output options (e.g., lights, motors, and actuators). This well-rounded setup is specifically designed to meet the educational and training objectives of the lab, promoting an interactive learning environment that develops essential automation skills and builds trainee confidence in applying PLC technology across real-world scenarios. • Offers a cost-effective PLC solution for industrial automation and engineering education, addressing the high cost of traditional systems. • Provides a scalable PLC lab setup developed to facilitate hands-on learning and practical experience in industrial automation, enabling simultaneous experimentation and collaborative learning. • Aligns with educational objectives, fostering an interactive, hands-on environment that builds essential automation skills, by enabling real-code preparation, testing and verification.
暂无评论