The semantic gap between keyword queries and search intents behind them motivates intensive studies on keyword query interpretation, which aims to interpret a keyword query to structured queries (a.k.a. patterns) representing most possibly relevant search intents. However, there still lacks of study on an important issue: how to guarantee the patterns are "reliable", which means the structured queries can be evaluated as really existing results. In this paper, we regard the reliability as a new metric for ranking patterns, and present a keyword query interpretation approach to find both reliable and relevant pattern trees on an arbitrary summary graph of underlying data. Specifically, we firstly propose a reliability estimation model to measure how possibly a pattern tree can be evaluated as a nonempty result set by statistics under reasonable assumptions. Secondly, we develop constrained top-k search algorithms that guarantee to return the optimal pattern trees for a specific keyword query. Moreover, to improve the efficiency of online search, we also design elaborate indexes, search heuristics and pruning strategies. Lastly, we perform comprehensive experiments on two real-world datasets, DBpedia and Yago, with both QALD-9 queries and random queries. The observations indicate our approach improves the accuracy and overall quality of top-k results significantly.

The road accidents are a common cause to the injury and death of people. As reported by The American National Highway Traffic Safety Administration (NHTSA), the drivers drowsiness accounts for nearly 100,000 accidents per year in the United States. Thus, we present a novel drivers drowsiness detection system in this paper using the techniques of deep learning(DL), mobile computing, wearable device and Electroencephalography (EEG). We employ the deep learning architecture designed by ourselves that can be easily implemented on the mobile phone to detect the drowsiness with a high accuracy. The EEG signal we use is only single channel that can be easily obtained by the wearable device. The EEG signal collector is designed and made by ourselves, which is like a hair band that makes the driver easier and more comfortable to wear it. The whole system mainly consists of two parts: one is the hardware consisting of EEG headband and sensor, the other is software consisting of Android application and web platform. The app contains the fine trained model to make real-time prediction based on the EEG signal and alert the driver, while sending the data to the backend synchronously. The web platform provides an interface for the monitor to observe the condition of the driver. Our system achieved an accuracy of 97.09% detecting the drivers drowsiness, which surpasses the SOTA methods. The model's size and predict latency are also within a smaller scale than present models that make it more applicable to mobile and embedded system.