Research Article
Optimizing CNN Kernel Sizes for Enhanced Melanoma Lesion Classification in Dermoscopy Images
Issue:
Volume 9, Issue 2, December 2024
Pages:
26-38
Received:
15 June 2024
Accepted:
3 July 2024
Published:
15 July 2024
Abstract: Skin cancer, particularly melanoma, presents a significant global health challenge due to its increasing incidence and mortality rates. Current diagnostic methods relying on visual inspection and histopathological examination are subjective and time-consuming, often leading to delayed diagnoses. Recent advancements in machine and deep learning, particularly convolutional neural networks (CNNs), offer a promising avenue for transforming melanoma detection by automating precise classification of dermoscopy images. This study leverages a comprehensive dataset sourced from Kaggle, comprising 10,605 images categorized into benign and malignant classes. Methodologically, a custom CNN architecture is trained and evaluated using varying kernel sizes (3x3, 5x5, 7x7) to optimize melanoma lesion classification. Results demonstrate that smaller kernel sizes, notably 3x3, consistently yield superior accuracy of 93.00% and F1-scores of 96.00%, indicating their efficacy in distinguishing between benign and malignant lesions. The CNN model exhibits robust generalization capabilities with minimal overfitting, supported by high validation accuracy throughout training epochs. Comparative analysis with related studies highlights competitive performance, suggesting potential enhancements through advanced feature selection and optimization techniques. Despite these advancements, challenges such as dataset diversity and model optimization persist, particularly concerning underrepresented darker skin tones. The study underscores the transformative potential of CNNs in enhancing diagnostic accuracy and efficiency in dermatological practice, paving the way for improved patient outcomes through early detection and intervention strategies. Future research directions include refining segmentation techniques and expanding dataset evaluations to ensure the model's applicability across diverse clinical settings. Ultimately, this research contributes to advancing melanoma diagnosis by integrating cutting-edge deep learning methodologies with clinical practice, thereby addressing current limitations and driving forward innovations in dermatological image analysis.
Abstract: Skin cancer, particularly melanoma, presents a significant global health challenge due to its increasing incidence and mortality rates. Current diagnostic methods relying on visual inspection and histopathological examination are subjective and time-consuming, often leading to delayed diagnoses. Recent advancements in machine and deep learning, par...
Show More
Research Article
Generative Artificial Intelligence: Challenges and Opportunities for Systems Developers: A Systematic Mapping of Literature
Samira Santos Caduda
,
Anderson Santos Barroso*
Issue:
Volume 9, Issue 2, December 2024
Pages:
39-47
Received:
16 July 2024
Accepted:
16 August 2024
Published:
29 September 2024
DOI:
10.11648/j.mlr.20240902.12
Downloads:
Views:
Abstract: Generative Artificial Intelligence tools have gained increasing prominence in recent years. However, the increasing use of these technologies and the functionalities they offer has sparked discussions about their impact and even raised concerns about the potential replacement of human work by automation carried out by machines. This study proposes a Systematic Literature Review to evaluate the opportunities and challenges that these technologies present to system developers in the current and future technological scenario. Aiming at state-of-the-art research to identify how Generative AIs are being applied in the context of software development and what are the latest trends and innovations in this field and how these innovations affect the opportunities and challenges for system developers. As a result, several studies were found that highlight how Generative AI has provided productivity and systems development optimized solutions in the industry, as well as promoting innovations. Studies also emphasize the need for a balance between the use of AI tools and development carried out by human participation, which must be mediated by common sense. Furthermore, the review will explore the ethical implications associated with the widespread adoption of AI technologies, addressing issues such as data privacy, decision-making transparency, and the responsibility of developers in ensuring that AI applications are used in a way that benefits society. The findings of this review will contribute to a better understanding of how generative AI is reshaping the software development landscape and provide insights for future research and development in this rapidly evolving field.
Abstract: Generative Artificial Intelligence tools have gained increasing prominence in recent years. However, the increasing use of these technologies and the functionalities they offer has sparked discussions about their impact and even raised concerns about the potential replacement of human work by automation carried out by machines. This study proposes ...
Show More
Research Article
A Machine Learning Approach to Optimal Group Formation Based on Previous Academic Performance
Issue:
Volume 9, Issue 2, December 2024
Pages:
48-52
Received:
2 September 2024
Accepted:
19 September 2024
Published:
29 September 2024
DOI:
10.11648/j.mlr.20240902.13
Downloads:
Views:
Abstract: In today’s educational institutions, student performance can vary widely due to differences in cognition, motivation, and environmental factors. These variations create challenges in achieving optimal learning outcomes. To address these challenges, Optimal Group Formation (OGF) has emerged as a promising research area. Optimal Group Formation (OGF) aims to form student groups that maximize learning efficiency based on past academic performance. Group formation problems are inherently complex and time-consuming, but their applications are extensive, spanning from manufacturing systems to educational contexts. This paper introduces a machine learning-based model designed to create optimal student groups using academic records as the primary input. The goal is to enhance overall group performance and reduce error rates by organizing students into cohesive, efficient teams. What sets this research apart is its focus on educational group formation, leveraging machine learning to improve collaborative learning outcomes. The paper also reviews prior research, emphasizing the importance of Optimal Group Formation (OGF) in various fields and its relevance in education. The model’s effectiveness is demonstrated through comparative analysis, showcasing its potential to improve group dynamics in both theoretical and lab-based courses. Ultimately, the aim is to improve educational outcomes by ensuring that student groups are optimally balanced and structured.
Abstract: In today’s educational institutions, student performance can vary widely due to differences in cognition, motivation, and environmental factors. These variations create challenges in achieving optimal learning outcomes. To address these challenges, Optimal Group Formation (OGF) has emerged as a promising research area. Optimal Group Formation (OGF)...
Show More
