AC-Skin: Facial Acne Detection-Based on Intelligent Learning and Large Data Collection of Internet of Things (IoT) for Smart Skincare

Artificial intelligence (AI) is considered an extremely hot research area of computing technology in the current era, and deep learning (DL) method analysis is one of the powerful tools that helps in complex environments while detecting and recognizing facial features and extracting prior knowledge, which is required for biomedical investigation. Currently, this technology faces a few problems in the adequation of medical data collection by means of autonomous. The role of the Internet of Things (IoT) is critical in this process; a successful integration is a challenging prospect recently with the application of DL in skin diagnosis, especially facial acne and severity impacts, which has become a new paradigm in the domain of dermatology. In this article, the classification of facial acne using AI-enabled DL techniques, especially convolutional neural networks (CNNs) is addressed, which aims to summarize the characteristics of the level of severity and the status of skin damage. In addition, this article addresses the procedure of large data collection from different sources of the Internet via associating the IoT, such as ESP 32 connect cameras for collecting real-time multimedia data. With the use of CNN and IoT, this article provides a new paradigm for intelligent learning in terms of the detection and recognition of facial acne and the level of skin severity metrics. To manage this technological collaboration, this article presents a design of close loop architecture, namely AC-Skin, a solution for self-learning infrastructure that mainly focuses on the key aspects and influencing factors of disease diagnosis for smart-skincare developments.