Fixed-lag particle filter for continuous context discovery using Indian Buffet Process

Exploiting context from stream data in pervasive environments remains a challenge. We aim to extract proximal context from Bluetooth stream data, using an incremental, Bayesian nonparametric framework that estimates the number of contexts automatically. Unlike current approaches that can only provide final proximal grouping, our method provides proximal grouping and membership of users over time. Additionally, it provides an efficient online inference. We construct co-location matrix over time using Bluetooth data. A Poisson-exponential model is used to factorize this matrix into a factor matrix, interpreted as proximal groups, and a coefficient matrix that indicates factor usage. The coefficient matrix follows the Indian Buffet Process prior, which estimates the number of factors automatically. The non-negativity and sparsity of factors are enforced by using the exponential distribution to generate the factors. We propose a fixed-lag particle filter algorithm to process data incrementally. We compare the incremental inference (particle filter) with full batch inference (Gibbs sampling) in terms of normalized factorization error and execution time. The normalized error obtained through our incremental inference is comparable to that of full batch inference, whilst the execution time is more than 100 times faster. The discovered factors have similar meaning to the results of the popular Louvain method for community detection.