Smart Home-Healthcare for Skin Lesions Classification with IoT Based Data Collection Device.

Skin lesions or malignancies have been a source of worry for many individuals in recent years. The underline reason behind it mainly the diet and environmental pollution. Yet many individuals are unaware of the issue and, more importantly, many people do not want to visit a hospital for diagnostic or therapeutic purposes. So, we have come up with a pipeline to diagnose skin lesions at home. Firstly, we proposed a IoT base data collection device which is accessible by patient to capture skin lesions image. This IoT device will encrypt and send the collected image towards a cloud storage; then it will decrypt the image send to the computer assisted diagnosis system. In CAD, we have implemented ensemble classifier. Ensemble classifier created depending on four deep learning classifiers namely VGG16, DenseNet201, Inception V3 and Efficient B7; whereas encryption and decryption performed in order to secure a patient data from unauthorized access. For skin lesions classification, we have used "HAM10000" dataset where 7 kind of skin lesions data included; Although DenseNet201 performed well, the ensemble model provides the highest accuracy with 87.22\% as well as its test loss/error is lower than others with 0.4131.