近年科技的演進與行動通訊時代的來臨，漸漸的取代人們傳統的思維，智慧型手機與平板電腦等科技產物如雨後春筍般的成長，越來越被人們所接受，公共場所也逐漸提供無線網路裝置，方便人們透過行動裝置上網服務。傳統人們透過空間平面圖，尋找目前位置或欲前往的目的地，然而隨著智慧型裝置的普及帶來了科技創新應用，將可藉由透過無線網路與智慧型裝置進行定位的計算，取得目前所位於的室內空間位置，在室內空間定位中，環境便是首要考量因素，避免因空間格局的變化，降低了室內定位的準確性，考量空間變化與定位準確性如何兩者兼具，便是本研究所進行探討的議題。
研究環境中藉由佈建數個參考點，利用NFC進行參考點資料讀取，環境中使用者提供參考點當下資訊，參考點便可計算出一學習曲線，透過參考點的學習，當環境的變動下便可自動學習，得到一可靠的參考點資訊。並利用感測器進行定位修正計算，當每次定位之間的時間，使用者移動了位置，此時便可透過感測器的資訊進行位置修正。
於本研究中提出一結合參考點學習方式，計算出可靠的參考點資訊與感測器的修正方式，制訂出一套透過無線網路定位系統學習機制，研究環境中，於外在環境的改變下，參考點的學習次數，透過傳統統計方式需150次以上的學習次數，研究方法只需100次便可達到學習目的，縮短了學習次數，加速參考點學習，提升學習效率。研究環境使用三台AP定位下，平均定位誤差由1.61m改善至1.46m，提升了9.3%定位準確率，因此可提升使用者對於定位系統的滿意度與使用率。

With the technology evolvement in recent years, the era of mobile communication has gradually changed how people think traditionally. The users of technological products such as smart phones and tablet PCs are emerging such that there are more and more wireless network connections available in public premises allowing people to use their mobile devices to go online. In the past people are used to finding out their current positions or destinations through space plan diagram. However, with the popularization of smart devices, now the current position in indoor space can be located based on the positioning calculation by wireless network devices and smart devices. The most important factor of the indoor space positioning is the environment factor. The issue to be investigated in this study is how to prevent the changes in space pattern from reducing the accuracy of indoor positioning.
Several reference points have been installed in the research environment, and the NFC mechanism has been used to readout the data of these reference points. If people in this environment are willing to provide current information of reference points, a learning curve can be calculated for each reference point. The automatic learning of reference point under environmental change will lead to the reliable information of reference point. The sensor has been used for the correction calculation of positioning. If the user’s position has been moved during the interval of every positioning, the information obtained by the sensor can be used for position correction.
In this study a learning approach based on reference point has been introduced in order to calculate the reliable reference point data and the sensor correction approach, and development a positioning system learning mechanism through wireless network connection. Due the change in external environment, the traditional statistical approach will require more than 150 times of learning for the reference points, while the method proposed in this study will only require 100 times of learning to achieve the learning objective. This indicates that the reference point learning has been accelerated, and the learning efficiency has been improved. By using three units of AP for positioning in the environment of this research, the average positioning error has been improved from 1.61 m to 1.46 m with the positioning accuracy enhancement of 9.3%, thus improving the user satisfaction and usage rate of positioning system.

[1] Y. Geng, J. He, H. Deng and K. Pahlavan, "Modeling the effect of human
body on TOA ranging for indoor human tracking with wrist mounted sensor,"
Proceedings of the International Symposium on Wireless Personal Multimedia
Communications, pp.1-6, 2013.
[2] G. Amin and S. Stavros, "A hybrid TDoA-ToA localization method,"
Proceedings of the International Conference on Telecommunications, pp.1-4,
2013.
[3] J.Y. Yoon, J.W. Kim, W.H. Lee and D.S. Eom, "A TDoA-based localization
using precise time-synchronization," Proceedings of the International
Conference on Advanced Communication Technology, pp.1266-1271, 2012.
[4] K. Enda, M.H. Kabir, F. Ono and R. Kohno, "High accuracy tag tracking
system based on TDOA in medical network," Proceedings of the International
Symposium on Medical Information and Communication Technology, pp.1-4,
2012.
[5] N. Ngoc, L. Thu and Y. Shin, "A new approach for positioning based on AOA
measurements," Proceedings of the International Conference on Computing,
Management and Telecommunications, pp.208-211, 2013.
[6] J.R. Jiang, C.M. Lin, F.Y. Lin and S.T. Huang, "ALRD: AoA localization with
RSSI differences of directional antennas for wireless sensor networks,"
Proceedings of the International Conference on Information Society,
pp.304-309, 2012.
[7] P.K. Sahu, E.H.K. Wu and J. Sahoo, "DuRT: Dual RSSI trend based
localization for wireless sensor networks," Sensors Journal, vol.13, no.8,
pp.3115-3123, 2013.
[8] J.Y. Wang, C.P. Chen, T.S. Lin, C.L. Chuang, T.Y. Lai and J.A. Jiang,
"High-precision RSSI-based indoor localization using a transmission power
adjustment strategy for wireless sensor networks," Proceedings of the
International Conference on High Performance Computing and
Communication, pp.1634-1638, 2012.
[9] C. Liu, D. Fang, Z. Yang, X. Chen, W. Wang, T. Xing, N. An and L. Cai,
"RDL: A novel approach for passive object localization in WSN based on
RSSI," Proceedings of the IEEE International Conference on Communications,
pp.586-590, 2012.
[10] H. Zhang, J. Zhang and H. Wu, "An adaptive localization algorithm based on
RSSI in wireless sensor networks," Proceedings of the International
Conference on Cloud Computing and Intelligent Systems, pp.1133-1136, 2012.
[11] Y. Yu, J. He, O. Wang, F. Liu and C. Xu, "A query-driven indoor location
system based on smartphone," Proceedings of the First IEEE Workshop on
Enabling Technologies for Smartphone and Internet of Things, pp.25-29,
2012.
[12] S. Boonsriwai and A. Apavatjrut, “Indoor WIFI localization on mobile
devices,” Proceedings of the International Conference on Electrical
Engineering/Electronics, Computer, Telecommunications and Information
Technology, pp.1-5, 2013.
[13] R.W. Ouyang, A.K.S. Wong and K.T. Woo, "GPS localization accuracy
improvement by fusing terrestrial TOA measurements," Proceedings of the
IEEE International Conference on Communication, pp.1-5, 2010.
[14] H. Kim, C. Park, Y. Cho, C. Shin, J. Park and D Park, "A study on a
ratiometric GPS iteration algorithm for indoor localization," Proceedings of
the International Conference on Computing and Convergence Technology,
pp.32-35, 2012.
[15] Z. Li, Z. Zhou, C. He and X. Huang, "Advances in RFID-ILA: The past,
present and future of RFID-based indoor location algorithms," Proceedings of
the Chinese Control and Decision Conference, pp.3830-3835, 2012.
[16] J.L. Brchan, L. Zhao, J. Wu, R.E. Williams and L.C. Perez, "A real-time RFID
localization experiment using propagation models," Proceedings of the IEEE
International Conference on RFID, pp.141-148, 2012.
[17] N. Mair and Q.H. Mahmoud, "A collaborative Bluetooth-based approach to
localization of mobile devices," Proceedings of the International Conference
on Collaborative Computing: Networking, Applications and Worksharing,
pp.14-17, 2012.
[18] Y. He, Y. Liu, X. Shen, L. Mo and G. Dai, "Noninteractive localization of
wireless camera sensors with mobile beacon," Proceedings of the IEEE
Transactions on Mobile Computing, pp.333-345, 2013.
[19] J. Larranaga, L. Muguira, J.M Lopez-Garde and J.I. Vazquez, "An
environment adaptive ZigBee-based indoor positioning algorithm,"
Proceedings of the International Conference on Indoor Positioning and
Indoor Navigation, pp.1-8, 2010.
[20] H.Q. Zhang, X.W. Shi, L.G. Cao and G.H. Deng, "A new indoor location
technology using back propagation neural network and improved centroid
algorithm," Proceedings of the Chinese Control Conference, pp.5460-5463,
2012.
[21] M. Youssef, M.A. Yosef and M. El-Derini, "GAC: Energy-efficient hybrid
GPS-accelerometer-compass GSM localization," Proceedings of the IEEE Global Telecommunications Conference, pp.6-10, 2010.
[22] J.S. Leu and H.J. Tzeng, "Received signal strength fingerprint and footprint
assisted indoor positioning based on ambient Wi-Fi signals," Proceedings of
the IEEE Vehicular Technology Conference, pp.1-5, 2012.