This paper introduces a novel approach to budgeted online active learning from finite-horizon data streams with extremely limited labeling budgets. In agricultural applications, such streams might include daily weather data over a growing season, and labels require costly measurements of weather-dependent plant characteristics. Our method integrates two key sources of prior information: a collection of preexisting expert predictors and episodic behavioral knowledge of the experts based on unlabeled data streams. Unlike previous research on online active learning with experts, our work simultaneously considers query budgets, finite horizons, and episodic knowledge, enabling effective learning in applications with severely limited labeling capacity. We demonstrate the utility of our approach through experiments on various prediction problems derived from both a realistic agricultural crop simulator and real-world data from multiple grape cultivars. The results show that our method significantly outperforms baseline expert predictions, uniform query selection, and existing approaches that consider budgets and limited horizons but neglect episodic knowledge, even under highly constrained labeling budgets.

Cold temperatures during fall and spring have the potential to cause frost damage to grapevines and other fruit plants, which can significantly decrease harvest yields. To help prevent these losses, farmers deploy expensive frost mitigation measures, such as, sprinklers, heaters, and wind machines, when they judge that damage may occur. This judgment, however, is challenging because the cold hardiness of plants changes throughout the dormancy period and it is difficult to directly measure. This has led scientists to develop cold hardiness prediction models that can be tuned to different grape cultivars based on laborious field measurement data. In this paper, we study whether deep-learning models can improve cold hardiness prediction for grapes based on data that has been collected over a 30-year time period. A key challenge is that the amount of data per cultivar is highly variable, with some cultivars having only a small amount. For this purpose, we investigate the use of multi-task learning to leverage data across cultivars in order to improve prediction performance for individual cultivars. We evaluate a number of multi-task learning approaches and show that the highest performing approach is able to significantly improve over learning for single cultivars and outperforms the current state-of-the-art scientific model for most cultivars.

"Smart Things" are commonly understood as wireless ad-hoc networked, mobile, autonomous, special purpose computing appliances, usually interacting with their environment implicitly via a variety of sensors on the input side and actuators on the output side. Such smart appliances have started to populate the "real world" with "hidden" or "invisible" services, thus building up an "invisible world" of services associated with real world objects. With the embedding of invisible technology into everyday things, however, also the intuitive perception of "invisible services" disappears. We believe that it has potential advantages to support the perception of smart appliance services via novel interactive visual experiences. For this purpose we have developed and built DigiScope, a see-through based visual real time perception system for "invisible worlds" to support interactive theater experience in mixed reality spaces. A case study is presented that demonstrates the use of DigiScope to percept the "invisible services" of our smart Internet appliance SmartCase. Opposed to previous work on mixed reality based augmentation of reality, the DigiScope approach allows for a multiuser, collaborative real time perceptual experience.