Recent developments in cloud computing and the Internet of Things have enabled smart environments, in terms of both monitoring and actuation. Unfortunately, this often results in unsustainable cloud-based solutions, whereby, in the interest of simplicity, a wealth of raw (unprocessed) data are pushed from sensor nodes to the cloud. Herein, we advocate the use of machine learning at sensor nodes to perform essential data-cleaning operations, to avoid the transmission of corrupted (often unusable) data to the cloud. Starting from a public pollution dataset, we investigate how two machine learning techniques (kNN and missForest) may be embedded on Raspberry Pi to perform data imputation, without impacting the data collection process. Our experimental results demonstrate the accuracy and computational efficiency of edge-learning methods for filling in missing data values in corrupted data series. We find that kNN and missForest correctly impute up to 40% of randomly distributed missing values, with a density distribution of values that is indistinguishable from the benchmark. We also show a trade-off analysis for the case of bursty missing values, with recoverable blocks of up to 100 samples. Computation times are shorter than sampling periods, allowing for data imputation at the edge in a timely manner.

The ease of deployment of digital technologies and the Internet of Things, gives us the opportunity to carry out large scale social studies and to collect vast amounts of data from our cities. In this work we investigate a novel way of analysing data from social sciences studies by employing machine learning and data science techniques. This enables us to maximise the insight gained from this type of studies by fusing both objective (sensor information) and subjective data (direct input from the users). The pilot study is concerned with better understanding the interactions between citizens and urban green spaces. A field experiment was carried out in Sheffield, UK, involving 1870 participants for two different time periods (7 and 30 days). With the help of a smartphone app, both objective and subjective data was collected. Location tracking was recorded as people entered any of the publicly accessible green spaces. This was complemented by textual and photographic information that users could insert spontaneously or when prompted (when entering a green space). By employing data science and machine learning techniques, we identify the main features observed by the citizens through both text and images. Furthermore, we analyse the time spent by people in parks, as well as the top interaction areas. The study allows us to gain an overview about certain patterns and the behaviour of the citizens within their surroundings and it proves the capabilities of integrating technology into large-scale social studies.