Crime incidents embedding using restricted Boltzmann machines
This addresses crime analysis for law enforcement by enabling detection and clustering of related incidents, though it is incremental as it builds on existing RBM methods.
The paper tackled the problem of detecting related crime series by learning latent feature embeddings from crime narratives using Gaussian-Bernoulli Restricted Boltzmann Machines, resulting in embeddings where related cases are closer and unrelated ones are farther apart in Euclidean space, as validated on hand-labeled data from the Atlanta Police Department.
We present a new approach for detecting related crime series, by unsupervised learning of the latent feature embeddings from narratives of crime record via the Gaussian-Bernoulli Restricted Boltzmann Machines (RBM). This is a drastically different approach from prior work on crime analysis, which typically considers only time and location and at most category information. After the embedding, related cases are closer to each other in the Euclidean feature space, and the unrelated cases are far apart, which is a good property can enable subsequent analysis such as detection and clustering of related cases. Experiments over several series of related crime incidents hand labeled by the Atlanta Police Department reveal the promise of our embedding methods.