Changing Consumer Behavior through Ambient Displays in Smart Cafeterias and Detecting Anomalous Reporting Behavior in Wireless Sensor

Food availability and food waste are significant global problems which can be mitigated through the use of sensor networks. Current methods of monitoring food waste require manual data collection and are implemented infrequently, providing imprecise information. The use of sensors to automate food waste measurement allows constant monitoring, provides a better dataset for analysis, and enables real-time feedback, which can be used to affect behavioral change in consumers. The data from such networks can be used to drive ambient displays designed to educate a target audience, and ultimately reduce the amount of waste generated. We present WASTE REDUCE, a system for automating the measurement of food waste and affecting behavioral change. The challenges and results of deploying such a system are presented. To assess the benefits of using WASTE REDUCE, two case studies are conducted. The first study evaluates three different displays, and the second reevaluates one of these displays in a separate location. These studies confirm that the combination of automated monitoring and ambient feedback can reduce food waste for targeted groups.;Each sensor in WASTE REDUCE has the potential to malfunction. This risk exists for all sensor networks because they comprise a collection of interconnected, but independent, sensors. Regardless of the scope of failure, it is important to identify and correct problems as they occur to maintain a healthy and reliable network. This requires a framework that can monitor a network and identify problems in real- time so that personnel can be notified of a malfunction immediately. We present a framework that includes two approaches for monitoring individual sensors in a network and identifying reporting anomalies. The first approach is static and relies on configuration parameters from a user to define expected reporting behavior for each sensor. The second is dynamic and automatically updates the expected reporting behavior based on observed reporting patterns. The system notifies personnel of possible malfunctions based on expected reporting behavior. We present empirical evaluations of the framework using the Intelligent RiverRTM system [49], which is larger and more established than WASTE REDUCE, and compare the two approaches.