Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. We show how to extract and label a person’s activities and signiď¬...
We present an approach to teach incrementally human gestures to a humanoid robot. The learning process consists of first projecting the movement data in a latent space and encodin...
In the near future, we will see dramatic changes in computing and networking hardware. A large number of devices (e.g., phones, PDAs, even small household appliances) will become c...
We investigate the problem of maximizing the lifetime of wireless ad hoc and sensor networks. Being battery powered, nodes in such networks have to perform their intended task und...
Traditional Markov network structure learning algorithms perform a search for globally useful features. However, these algorithms are often slow and prone to finding local optima d...