Region Formation for Efficient Offline Location Prediction
As low-power devices continue to be integrated into daily life, we are presented with the challenge of deciding when it's beneficial for these devices to interrupt us. Predicting a user's movements provides valuable insight to solve this problem. Here, the authors present a new approach for offline location prediction for low-power devices, representing a user's mobility patterns as an optimal set of geographical regions. Their approach yielded a 27 percent increase in precision and a 13 percent increase in recall over standard time- and place-based approaches against GPS data for hundreds of users. Their approach requires minimal additional cost and opens up potential for further development.
- 원문이 없습니다.
NDSL에서는 해당 원문을 복사서비스하고 있습니다. 위의 원문복사신청 또는 장바구니 담기를 통하여 원문복사서비스 이용이 가능합니다.
- 이 논문과 함께 출판된 논문 + 더보기