More about HKUST
Adaptive Temporal Radio Maps for Indoor Location Estimation
------------------------------------------------------------------ Seminar on Data Mining for Pervasive Computing ------------------------------------------------------------------ Speaker: Jie YIN and Xiaoyong CHAI Department of Computer Science Hong Kong University of Science & Technology Date: Monday, 28 February 2005 Time: 4:00 pm - 5:00 pm Venue: Lecture Theatre F (Leung Yat Sing Lecture Theatre, near lifts nos. 25/26) The Hong Kong University of Science & Technology ------------------------------------------------------------------------- This talk consists of two conference presentations to be given at the 3rd Annual IEEE International Conference on Pervasive Computing and Communications (IEEE Percom 2005) in Hawaii USA, March 2005. It should serve as a good overview of our research activities in data mining for pervasive computing. ------------------------------------------------------------------------ First Presentation (30 min): =========================== Title: "Adaptive Temporal Radio Maps for Indoor Location Estimation" Speaker: Jie YIN, (http://cse.hkust.edu.hk/~yinjie) Abstract: We present a novel method to adapt the temporal radio maps for indoor location estimation by offsetting the varying environmental factors using data mining techniques and reference points. Environmental variations, which cause the signals to change from time to time even at the same location, present a challenging task for indoor location estimation in the IEEE 802.11b infrastructure. In such a dynamic environment, the radio maps obtained in one time period may not be applicable in other time periods. To solve this problem, we apply a regression analysis to learn the temporal predictive relationship between the signal-strength values received by sparsely located reference points and that received by the mobile device. This temporal prediction model can then be used for online localization based on the newly observed signal strength values at the client side and the reference points. We show that this technique can effectively accommodate the variations of signal-strength values over different time periods without the need to rebuild the radio maps repeatedly. This is joint work with Professors Qiang Yang and Lionel Ni. Biography: Jie Yin is currently a Ph. D. student in the Department of Computer Science, HKUST. Her research interests include artificial intelligence and pervasive computing. Currently she is working on learning and recognizing human behaviors from sensory data in pervasive environments. Second Presentation (30 min): ============================= Title: "Reducing the Calibration Effort for Location Estimation Using Unlabeled Samples" Speaker: Xiaoyong CHAI (http://cse.hkust.edu.hk/~carnamel) Abstract: WLAN location estimation based on 802.11 signal strength is becoming increasingly prevalent in today's pervasive computing applications. As an alternative to the well established deterministic approaches, probabilistic location determination techniques show good performance and become more and more popular. However, in order for these techniques to achieve a high level of accuracy, adequate training samples should be collected offline for calibration. As a result, a great amount of manual effort is incurred. In this work, we aim to solve the problem by reducing both the sampling time and the number of locations sampled in constructing the radio map. A learning algorithm is proposed to build location estimation systems based on a small fraction of the calibration data traditional techniques require and a collection of user traces that can be cheaply obtained. Our experiments show that unlabeled user traces can be used to compensate the effects of reducing calibration effort and even improve the system performance. Consequently, manual effort can be significantly reduced while a high level of accuracy is still achieved. This is joint work with Professor Qiang Yang. Biography: Xiaoyong Chai is currently an MPhil student at the Department of Computer Science, the Hong Kong University of Science and Technology. He received his bachelor degree in Computer Science from Fudan University, Shanghai, China in 2002. His research interests include location-aware computing and human behavior recognition.