Today, the rapid development of industrial zones leads to an increased incidence of skin diseases because of polluted air. According to a report by the American Cancer Society, it is estimated that in 2022 there will be about 100,000 people suffering from skin cancer and more than 7600 of these people will not survive. In the context that doctors at provincial hospitals and health facilities are overloaded, doctors at lower levels lack experience, and having a tool to support doctors in the process of diagnosing skin diseases quickly and accurately is essential. Along with the strong development of artificial intelligence technologies, many solutions to support the diagnosis of skin diseases have been researched and developed. In this paper, a combination of one Deep Learning model (DenseNet, InceptionNet, ResNet, etc) with Soft-Attention, which unsupervisedly extract a heat map of main skin lesions. Furthermore, personal information including age and gender are also used. It is worth noting that a new loss function that takes into account the data imbalance is also proposed. Experimental results on data set HAM10000 show that using InceptionResNetV2 with Soft-Attention and the new loss function gives 90 percent accuracy, mean of precision, F1-score, recall, and AUC of 0.81, 0.81, 0.82, and 0.99, respectively. Besides, using MobileNetV3Large combined with Soft-Attention and the new loss function, even though the number of parameters is 11 times less and the number of hidden layers is 4 times less, it achieves an accuracy of 0.86 and 30 times faster diagnosis than InceptionResNetV2.

Motivated by the increasing interest in clinical studies focused on infant movements and poses, this research addresses the limited emphasis on speed and efficiency in existing 2D and 3D pose estimation methods, particularly concerning infant datasets. The scarcity of publicly available infant data poses a significant challenge. In response, we aim to develop a lightweight pose estimation model tailored for edge devices and CPUs. Drawing inspiration from the OpenPose-2016 approach, we refine the algorithm’s architecture, focusing on 2D image training. The resulting model, with 4.09 million parameters, features a single-branch structure. During execution, it achieves an algorithmic complexity of 8.97 giga floating-point operations per second (GFLOPS), enabling operation at approximately 23 frames per second on a Core i5-10400f processor.Notably, this approach balances compact dimensions with superior performance on our self-collected infant dataset. We anticipate that this pragmatic methodology establishes a robust foundation, addressing the need for speed and efficiency in infant pose estimation and providing favorable conditions for future research in this application.