基於室內定位技術與本體進行情境感知服務之研究

The Study of Context-Aware Services Based on Domain Ontology and Indoor Location Technology

林渝翔(Yu-hsiang Lin)

指導教授 ： 陳榮靜

朝陽科技大學/資訊學院/資訊管理系/碩士(2013年)

摘要

行動智慧裝置與無線技術發展蓬勃，普及運算(Ubiquitous Computing)環境與微型應用程式提供了豐富的行動服務資源，如何提供正確且適當的服務給使用者，位置資訊是重要的參考指標之一。由於全球定位系統(Global Position System, GPS)只適用於室外定位，因此先前研究採用如紅外線、超音波、無線射頻辨識(Radio Frequency Identification, RFID)等各種無線技術發展，期望除了達到室內定位的目標之外，還能進一步結合環境資訊提供行動服務給使用者，這便是情境感知(Context-Aware)的核心概念。本研究將以室內定位的精確度、準確率與情境服務推薦為主軸探討，採用無線射頻技術(Radio Frequency Identification, RFID)，記錄目標參考元件發出的訊號強度(Received Signal Strength, RSS)作為環境特徵，並提出多組類神經網路(Neural Network)進而建構室內定位平台的方法。服務推薦方面將採用本體(Ontology)建構情境服務推薦平台，根據使用者身份、所處位置、相關環境資訊以及隱私權設定，透過後端規則引擎達到推論適當的服務，最後將行動服務推薦給使用者。

關鍵字

本體 ； 情境感知 ； 類神經網路 ； 無線射頻辨識 ； 室內定位

並列摘要

In recent years, the expanding of smart devices and wireless technologies promote the development of Ubiquitous Computing and APP. In order to provide appropriate mobile services to users, the location information is an important factor. However, Global Positioning System is only suitable to outdoor location, so previous research have used different wireless technologies for indoor location, such as Radio Frequency Identification(RFID), Infrared, etc. Our purpose is combine indoor location with services recommended. However, how to provide Context-Aware services to user is an important issue. Our research focus on the accuracy and precision of indoor location and the context services recommended. We adopt RFID to construct Indoor Location Platform. On the other hand, we adopted Ontology to construct Context Aware Services Platform, the recommended services is based on the user’s location, privacy setting and another environmental information, so that user can enjoy mobile services from services platform by pre-define rules.

並列關鍵字

Ontology ； Context-aware ； Neural Network ； RFID ； Indoor location

參考文獻

[3] A. H. Behzadan, Zeeshan Aziz, Chimay J. Anumba, Vineet R. Kamat (2008), “Ubiquitous location tracking for context-specific information delivery on construction sites,” Automation in Construction, vol. 17, no. 6, pp. 737-748

[4] H. E. Byun and K. Cheverest (2004), “Utilizing Context history to provide dynamic adaptions,” Applied Artifical Intelligence, vol. 18, no. 6, pp. 533-548

[5] M. Brunato and R. Battiti (2005), “Statistical learning theory for location fin-gerprinting in wireless LANs,” Computer Networks, vol. 47, pp. 825–845.

[6] P. Bahl and V. N. Padmanabhan (2000), “RADAR: An in-building RF-based user location and tracking system,” Proceedings of Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies, vol. 2, pp. 775-784.

[7] R. Battiti, T. L.Nhat, andA.Villani (2002), “Location-aware computing:Aneural network model for determining location in wireless LANs,” Technical Report, DIT-02–0083.