Generating a Personalised Sensor Data Generation System for the Fusion of Adversarial Networks and Behavioural Matter-of-Fact Mapping

Generative models such as Generative Adversarial Networks and Variational Self-Encoders have been shown to generate highly simulated synthetic data with incredible results in areas such as text, images, and audio. However, to date there is no proven method for generating sensor data for mobile terminals. This is because sensor-generated data is high-dimensional, high-complexity, and contains a lot of noise and variations, which makes it difficult for generative models to learn realistic distributions from this data. In addition, different users acquiring sensor data for the same action will also have different features, which makes it more challenging to generate fine-grained sensor data. In order to solve the above problems, we propose a personalised sensor data generation system for fusion of generative adversarial networks and behavioural matter-of-fact mapping, which creatively introduces matter-of-fact mapping and aims to reduce the probability of occurrence of situations that do not conform to the matter-of-fact logic in the personalised sensor data set by utilising matter-of-fact logic and temporal relationships originated from matter-of-fact mapping, and thus improve the accuracy of user behavioural sensor data generation. The results demonstrate that the sensor data generated by the method proposed in this paper achieves 90% accuracy under the behavioural action recognition task and generates personalised sensor data for a long period of time through the designed state transfer template.