Sequence Imputation using Machine Learning with Early Stopping Mechanism

In today's world, humans need data from every situation, even from conditions where humans cannot directly extract data or from places that are hazardous for human beings. Wireless sensor networks or WSNs can solve this problem. They gather the required information using their sensors and provide the human race with the necessary data. Missing data are unavoidable in WSN, due to issues such as network communication outage, sensor maintenance or failure, etc. A complete informed and accurate data can help make the right decision. Just getting the missing data is not essential; it is also crucial to get this information as quickly as possible. A sequence imputation model with an encoder-decoder model is used to identify the missing values in the sensor network. It uses SSIM, with LSTM, attention layer and an early stopping layer, which gives comparable results in the minimum time by taking into consideration the past and the future information. The training and testing data is the subset of the hourly dataset of PM2.5 data of the US Embassy in Beijing. This model was able to produce accurate values keeping in mind the time.