我們提出一項綜合了行人推測航行法與相遇資訊的室內定位技術。裝置相遇可以透過近距離電磁波原理的通訊介面做為鄰近感測的機制。我們以條件隨機域(CRFs)為基礎，加上相遇時交換的軌跡與鄰近資訊， 相較於之前常用的顆粒過濾法，降低了演算的複雜度。實驗數據顯示我們不但減少運算能力的需求，更擴充了室內可定位的範圍。

This thesis proposes a new indoor localization techniques that fuses pedestrian dead reckoning with encounter information. Encounter is detected by proximity sensing using short-range radio frequency(RF) also used for communication. Our work builds on conditional random fields(CRFs) for the lower computational complexity than the traditional particle filtering by incorporating information exchanged from the encounter, including the trajectory and proximity. Experimental results show that
we further lower the complexity and expand location coverage.

1 Introduction . . . . . . . . . . . . . . . . . . 1
1.1 Motivation . . . . . . . . . . . . . . . . . 1
1.2 Contributions . . . . . . . . . . . . . . . . 2
2 Related Work . . . . . . . . . . . . . . . . . . 3
2.1 Non-Encounter Systems . . . . . . . . . . . . 3
2.1.1 Inertial Sensing . . . . . . . . . . . . 3
2.1.2 Fingerprinting . . . . . . . . . . . . . 4
2.1.3 RF Interference . . . . . . . . . . . . . 4
2.1.4 RF Ranging . . . . . . . . . . . . . . . 4
2.1.5 Optical . . . . . . . . . . . . . . . . . 5
2.1.6 Acoustic . . . . . . . . . . . . . . . . 5
2.1.7 Ground Vibrations . . . . . . . . . . . . 5
2.2 Encounter-Based Systems . . . . . . . . . . . 5
3 Background Theory . . . . . . . . . . . . . . . . 7
3.1 Basic Probability Theory. . . . . . . . . . . 7
3.1.1 Terminology . . . . . . . . . . . . . . . 7
3.1.2 Probability . . . . . . . . . . . . . . . 8
3.1.3 Conditional Probability . . . . . . . . . 9
3.1.4 Bayes Theorem . . . . . . . . . . . . . . 9
3.2 Probability Distribution. . . . . . . . . . . 10
3.2.1 Random Variables. . . . . . . . . . . . . 10
3.2.2 Expected Value. . . . . . . . . . . . . . 12
3.2.3 Variance and Standard Deviation . . . . . 13
3.2.4 Gaussian Distribution . . . . . . . . . . 13
3.3 Graphical Models. . . . . . . . . . . . . . . 15
3.3.1 Models . . . . . . . . . . . . . . . . . 15
3.3.2 Graphical Models . . . . . . . . . . . . 15
3.3.3 Factors . . . . . . . . . . . . . . . . . 16
3.3.4 Directed Graphical Models . . . . . . . . 17
3.3.5 Undirected Graphical Models . . . . . . . 19
3.4 Conditional Random Fields . . . . . . . . . . 20
3.4.1 Maximum Entropy Model . . . . . . . . . . 20
3.4.2 Conditional Random Fields . . . . . . . . 25
3.4.3 Viterbi Algorithm . . . . . . . . . . . . 26
4 Collaborative Conditional Random Fields . . . . . 29
4.1 System Overview . . . . . . . . . . . . . . . 29
4.2 Observations and Constraints . . . . . . . . 31
4.3 Merging Mechanism . . . . . . . . . . . . . . 31
4.4 Inference . . . . . . . . . . . . . . . . . . 33
5 System Implementation . . . . . . . . . . . . . . 38
5.1 Observations, States, and Constraints . . . . 38
5.2 Feature Functions . . . . . . . . . . . . . . 40
5.3 Encounter Information . . . . . . . . . . . . 41
5.4 Inference . . . . . . . . . . . . . . . . . . 44
6 Evaluation. . . . . . . . . . . . . . . . . . . . 45
6.1 Design of Experiments . . . . . . . . . . . . 45
6.1.1 Experimental Environments . . . . . . . . 45
6.1.2 Metrics . . . . . . . . . . . . . . . . . 45
6.1.3 Competitors . . . . . . . . . . . . . . . 48
6.2 Results . . . . . . . . . . . . . . . . . . . 48
6.2.1 Accuracy. . . . . . . . . . . . . . . . . 48
6.2.2 Convergence Distance. . . . . . . . . . . 53
6.2.3 Time Complexity . . . . . . . . . . . . . 55
6.2.4 Sample Rates . . . . . . . . . . . . . . 57
7 Conclusions and Future Work . . . . . . . . . . . 58
7.1 Conclusions . . . . . . . . . . . . . . . . . 58
7.2 Future Work . . . . . . . . . . . . . . . . . 59

[1] ADIB, F., AND KATABI, D. See through walls with WiFi!, vol. 43. ACM, 2013.
[2] BAHL, P., AND PADMANABHAN, V. N. RADAR: An in-building RF-based user location and tracking system. In INFOCOM 2000. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies. Proceedings. IEEE (2000), vol. 2, Ieee, pp. 775–784.
[3] BEAUREGARD, S., AND HAAS, H. Pedestrian dead reckoning: A basis for personal positioning. In Proceedings of the 3rd Workshop on Positioning, Navigation and Communication (2006), pp. 27–35.
[4] BEAUREGARD, S., KLEPAL, M., ET AL. Indoor PDR performance enhancement using minimal map information and particle filters. In Position, Location and Navigation Symposium, 2008 IEEE/ION (2008), IEEE, pp. 141–147.
[5] BERGER, A. L., PIETRA, V. J. D., AND PIETRA, S. A. D. A maximum entropy approach to natural language processing. Computational linguistics 22, 1 (1996), 39–71.
[6] BERTSEKAS, D. P. Constrained optimization and Lagrange multiplier methods. Academic press, 2014.
[7] BLUETOOTHSIG. Covered core package version 4.0, 2010.
[8] CHAN, L.-W., CHIANG, J.-R., CHEN, Y.-C., KE, C.-N., HSU, J., AND CHU, H.-H. Collaborative localization: Enhancing WiFi-based position estimation with neighborhood links in clusters. In Pervasive Computing. Springer, 2006, pp. 50–66.
[9] CHANG, C.-M. Cooperative tracking using encounter information by particle filter.
[10] CHANG, H.-L., TIAN, J.-B., LAI, T.-T., CHU, H.-H., AND HUANG, P. Spinning beacons for precise indoor localization. In Proceedings of the 6th ACM conference on Embedded network sensor systems (2008), ACM, pp. 127–140.
[11] COLLIN, J., MEZENTSEV, O., LACHAPELLE, G., ET AL. Indoor positioning system using accelerometry and high accuracy heading sensors. In Proc. of ION GPS/GNSS 2003 Conference (2003), pp. 9–12.
[12] DE MOIVRE, A. The doctrine of chances: or, A method of calculating the probabilities of events in play, vol. 1. Chelsea Publishing Company, 1756.
[13] EVENNOU, F., AND MARX, F. Advanced integration of WiFi and inertial navigation systems for indoor mobile positioning. Eurasip journal on applied signal processing 2006 (2006), 164–164.
[14] FELDMANN, S., KYAMAKYA, K., ZAPATER, A., AND LUE, Z. An indoor Bluetooth-based positioning system: Concept, implementation and experimental evaluation. In International Conference on Wireless Networks (2003), pp. 109–113.
[15] HE, T., HUANG, C., BLUM, B. M., STANKOVIC, J. A., AND ABDELZAHER, T. Rangefree localization schemes for large scale sensor networks. In Proceedings of the 9th annual international conference on Mobile computing and networking (2003), ACM, pp. 81–95.
[16] HOUSE, S., CONNELL, S., MILLIGAN, I., AUSTIN, D., HAYES, T. L., AND CHIANG, P.Indoor localization using pedestrian dead reckoning updated with RFID-based fiducials. In Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of
the IEEE (2011), IEEE, pp. 7598–7601.
[17] JAYNES, E. T. Information theory and statistical mechanics. Physical review 106, 4 (1957),620.
[18] JAYNES, E. T. Information theory and statistical mechanics. ii. Physical review 108, 2 (1957),171.
[19] JUDGEROY, J. O., DAVIS, B., AND ÕUNPUU, S. Step length reductions in advanced age: the role of ankle and hip kinetics. The Journals of Gerontology Series A: Biological Sciences and Medical Sciences 51, 6 (1996), M303–M312.
[20] JUN, J., GU, Y., CHENG, L., LU, B., SUN, J., ZHU, T., AND NIU, J. Social-loc: Improving indoor localization with social sensing. In Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems (2013), ACM, p. 14.
[21] JUNG, S.-Y., HANN, S., AND PARK, C.-S. TDOA-based optical wireless indoor localization using LED ceiling lamps. Consumer Electronics, IEEE Transactions on 57, 4 (2011), 1592–1597.
[22] KLEPAL, M., BEAUREGARD, S., ET AL. A backtracking particle filter for fusing building plans with PDR displacement estimates. In Positioning, Navigation and Communication, 2008.WPNC 2008. 5th Workshop on (2008), IEEE, pp. 207–212.
[23] LAFFERTY, J., MCCALLUM, A., AND PEREIRA, F. C. Conditional random fields: Probabilistic models for segmenting and labeling sequence data.
[24] LEE, J. H., SHIN, B., KIM, C., KIM, J., LEE, S., AND LEE, T. Real time adaptive step length estimation for smartphone user. In Control, Automation and Systems (ICCAS), 2013 13th International Conference on (2013), IEEE, pp. 382–385.
[25] LI, L., HU, P., PENG, C., SHEN, G., AND ZHAO, F. Epsilon: A visible light based positioning system. In 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI 14) (2014), USENIX Association, pp. 331–343.
[26] LI, Y.-T., CHEN, G., AND SUN, M.-T. An indoor collaborative pedestrian dead reckoning system. In Parallel Processing (ICPP), 2013 42nd International Conference on (2013), IEEE, pp. 923–930.
[27] MIRSHEKARI, M., PAN, S., BANNIS, A., LAM, Y. P. M., ZHANG, P., AND NOH, H. Y. Step-level person localization through sparse sensing of structural vibration. In Proceedings of the 14th International Conference on Information Processing in Sensor Networks (2015), ACM,
pp. 376–377.
[28] RAI, A., CHINTALAPUDI, K. K., PADMANABHAN, V. N., AND SEN, R. Zee: zero-effort crowdsourcing for indoor localization. In Proceedings of the 18th annual international conference on Mobile computing and networking (2012), ACM, pp. 293–304.
[29] RATNAPARKHI, A. Maximum entropy models for natural language ambiguity resolution. PhD thesis, University of Pennsylvania, 1998.
[30] RUIZ, A. R. J., GRANJA, F. S., HONORATO, J. C. P., AND ROSAS, J. I. G. Accurate pedestrian indoor navigation by tightly coupling foot-mounted IMU and RFID measurements. Instrumentation and Measurement, IEEE Transactions on 61, 1 (2012), 178–189.
[31] SERTATIL, C., ALTINKAYA, M. A., AND RAOOF, K. A novel acoustic indoor localization system employing CDMA. Digital Signal Processing 22, 3 (2012), 506–517.
[32] SHANNON, C. E. A mathematical theory of communication. ACM SIGMOBILE Mobile Computing and Communications Review 5, 1 (2001), 3–55.
[33] SHIN, S., PARK, C., KIM, J., HONG, H., AND LEE, J. Adaptive step length estimation algorithm using low-cost mems inertial sensors. In Sensors Applications Symposium, 2007. SAS’07. IEEE (2007), IEEE, pp. 1–5.
[34] TARZIA, S. P., DINDA, P. A., DICK, R. P., AND MEMIK, G. Indoor localization without infrastructure using the acoustic background spectrum. In Proceedings of the 9th international conference on Mobile systems, applications, and services (2011), ACM, pp. 155–168.
[35] VITERBI, A. J. Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. Information Theory, IEEE Transactions on 13, 2 (1967), 260–269.
[36] XIAO, Z., WEN, H., MARKHAM, A., AND TRIGONI, N. Lightweight map matching for indoor localisation using conditional random fields. In Information Processing in Sensor Networks, IPSN-14 Proceedings of the 13th International Symposium on (2014), IEEE, pp. 131–142.
[37] YOUSSEF, M., AND AGRAWALA, A. The Horus WLAN location determination system. In Proceedings of the 3rd international conference on Mobile systems, applications, and services(2005), ACM, pp. 205–218.