動態情境模型於智慧家庭之設計與研究

情境感知系統在辨識使用者行為和提供生活服務協助的智慧家庭中扮演著關鍵角色，這類研究領域採用的方法十分多元，包含以邏輯規格為基礎和以機器學習方法為基礎的技術。然而，欲建構一個能讓使用者理解，且機器可互換資訊、進而重複使用的模型，需要運用具有語意描述能力和領域經驗知識的方法。本體論因富含語意關係而適用於建構此類模型，但在擴充性或適應性方面，卻因內容由專家預設，而不足以完整描述外在的動態環境。因此，本研究將提出一種動態情境模型的設計方法，利用學習方法適應不同的環境及使用者習慣，達成修改及擴充情境模型的目標。首先使用正規表達知識的本體論來建立家庭環境中各種基礎概念之間的關係，以提供個人本體論的應用與擴充。其次應用本體論推理和信任值計算於感測器偵測到的觸發事件，完成行為辨識的任務。接著過濾行為紀錄中的不重要資訊，並評估是否需要更改行為本體論中各物品的相關權重。最後實際演化符合個人化特色的本體論內容，並在未知行為出現時，透過使用者的標籤動作，完成本體論模型的行為知識擴充。

關鍵字

本體論演化；情境模型；行為辨識；機器學習；情境感知

並列摘要

A context-aware system plays an important role in recognizing user’s activities and providing assistive services in smart homes. There has been a lot of research that aims at fulfilling the requirements in this topic, including specification-based and learning-based methods. Furthermore, constructing a model with understandability and reusability is necessary, which makes information exchangeable between components. Therefore, we first use ontology as the model base because of its rich semantic structure in describing the different relationships between domain concepts. Second, we combine the model with a machine learning approach, merging patterns, to enhance the limitation that knowledge must be defined by expert beforehand. After fusing these two methods, the model indeed improves the power on adaptability and scalability, making it suitable for dynamic environment adaptation and personal preference accommodation.

並列關鍵字

ontology evolution ； context model ； activity recognition ； machine learning ； context-awareness

參考文獻

[1] M. Weiser, “The computer for the 21st century,” Scientific American, vol. 265, no. 3, pp. 94–104, 1991.

[3] V. Bellotti and K. Edwards, “Intelligibility and accountability: human considerations in context-aware systems,” Human–Computer Interaction, vol. 16, no. 2–4, pp. 193–212, 2001.

[7] K. L. Courtney, “Privacy and senior willingness to adopt smart home information technology in residential care facilities,” Methods of Information in Medicine, vol. 47, no. 1, pp. 76–81, 2008.

[8] K. Henricksen and J. Indulska, “Modelling and using imperfect context information,” in Proceedings of the Second IEEE Annual Conference on Pervasive Computing and Communications Workshops, pp. 33–37, 2004.

[9] L. Atallah and G.-Z. Yang, “The use of pervasive sensing for behaviour profiling—a survey,” Pervasive and Mobile Computing, vol. 5, no. 5, pp. 447–464, 2009.

國際替代計量

動態情境模型於智慧家庭之設計與研究

未授權

主題瀏覽