"On applying Deep Learning Techniques to Sensor Data for Gesture Recognition"

The continuous increasing use of sensors on Internet of Things (IoT) devices has led to the production of a huge amount of data. This  data is used in training machine learning models, to improve the quality of offered services. However, users are often reluctant to use their data to train the above models. There is a need for an architecture that protects the privacy of users’ data as well as the results of the trained models. The proposed solution is the use of Differential Privacy in conjunction with Blockchain in the weights of the trained models. By accomplishing this goal, it will be possible to improve the quality of services, as users will feel more secure using their data in training these models.