International Journal
-
Project
SkinSavvy2: Augmented Skin Lesion Diagnosis and Personalized Medical Consultation System
The shortage of medical personnel and the busy lives of modern people have increased the desire for the self-diagnosis of diseases, and the latest large-scale language models and image recognition technologies have the potential to meet this demand. In particular, skin-related diseases are one of the areas where symptoms are visually distinguishable, making self-diagnosis and care possible. In this paper, we propose a system that classifies diseases through images of skin diseases and combines them with individual conditions such as age, skin type, and gender for self-diagnosis. First, we design the latest deep learning model-based skin disease classifier that can classify six types of skin diseases using the HAM10000 dataset and generate prompts by combining the personal information input. By utilizing the Generative Pre-trained Transformer (GPT) model, the system generates personalized care methods based on these prompts. We measured the accuracy of the classification model of the proposed system and validated the effectiveness of the proposed method through user evaluations. https://doi.org/10.3390/electronics14050969
-
Project
Development of a Success Prediction Model for Crowdfunding Based on Machine Learning Reflecting ESG Information
This study aims to develop a success prediction model for crowdfunding by integrating ESG (Environmental, Social, and Governance) factors using machine learning techniques. Crowdfunding, a modern financing method conducted through online platforms, has become a popular avenue for raising funds, particularly for creative projects, startups, and social enterprises. Incorporating ESG factors into crowdfunding success prediction models is crucial, as these factors represent environmental responsibility, social accountability, and ethical governance, which are increasingly important to investors and sponsors. To achieve the research objectives, this study employed advanced machine learning algorithms, including XGBoost, LightGBM, AdaBoost, CatBoost, and NGBoost, to analyze data from a prominent reward-based crowdfunding platform in Korea, 'Wadiz.' Text mining techniques were used to quantify unstructured ESG-related data, and the predictive performance of models including ESG factors was compared with models excluding them. The results demonstrated that prediction accuracy significantly improved when ESG factors were incorporated. Among the ESG dimensions, environmental information contributed the highest prediction performance, followed by social activity information and governance information. The findings of this study contribute to academia by expanding the understanding of non-financial factors in crowdfunding success prediction and integrating ESG elements into machine learning models. This research also provides practical implications by offering insights for platform operators, project creators, and investors to improve decision-making processes through the strategic use of ESG factors. The proposed model enhances crowdfunding platforms' reliability and success rates, supports project makers in designing impactful campaigns, and aids investors in making sustainable and data-driven investment decisions. This study advances theoretical understanding and provides actionable strategies for enhancing the effectiveness of crowdfunding in practice. https://ieeexplore.ieee.org/document/10804760
