CAFFEINE Dataset

<p>The CAFFEINE dataset contains non-intrusive sensor data (time series) and labels (coffee type for each time series, and actuator activation status at each time step)&nbsp;for 130 coffees. Eight&nbsp;sensors are placed along the&nbsp;power chain of the coffee making process (1 current sensor, 1 voltage sensor, 3 accelerometers, 2 temperature sensors, 1 coffee level sensor), producing signals originated by 5 sources (heating coil, infuser translation motor, grinder, vibration pump, (electronics)), sampled at 6250 Hz.</p> <p>The dataset comes with reading scripts and instructions for Python and MATLAB users.</p> <p>Intended uses for this dataset include <strong>blind source separation</strong>&nbsp;(multi-label clustering and signal decomposition), <strong>classification</strong>, as well as <strong>regression</strong>&nbsp;(multivariate time series forecasting), <strong>parameter identification</strong> and <strong>model synthesis</strong>.</p>