隨著物連網(IoT)的興起，智慧家庭領域上的研究也越來越重要，智慧家庭中管理者可以藉由收集並分析多個感測器感測的資訊來識別居民的活動，並操控各種不同類型的機器人提供居民服務，以滿足居民的需求。然而，不同類型的機器人可能因為驅動軟體不同，造成管理者的操控困難。且感測器可能因為故障、網路不穩定等因素，造成提供的資訊不可靠，目前已經有研究採用Dempster Shafer theory證據合併理論分析這些不可靠的感測器資訊，並協助管理者可靠地決策居民的活動，考慮到這些感測器需要一直開啟並感測環境資訊，能量消耗的問題也是必須要被探討的。本研究利用 OM2M 中介軟體框架，使管理者能透過瀏覽器在圖形化介面更容易地操控異質機器人，並探討開啟感測器較少的部分情況下，證據合併可能會導致辨識能力不足，接著提出一個 Markov Decision Process 模型，控制感測器開關，來解決能量消耗的問題。

With the rise of IoT (Internet of things), research in the field of smart home is becoming increasingly important by collecting and analyzing information sensed by multiple sensors, managers can identify resident's activities and operate them control various types of robots to provide residents with services to meet the needs of residents. However, different types some of the robots may be driven by different software, which makes it difficult for managers to control them. And sensors may be due to failure, network instability and other factors, resulting in unreliable information provided. At present, some studies have adopted Dempster Shafer theory to combine evidence to analyze these unreliable sensor information and assist managers to make reliable decisions about resident's activities. Considering that these sensors need to be turned on and sense environmental information all the time, the problem of energy consumption must also be discussed. This research use OM2M middleware framework, make managers can more easily through the browser in the graphical interface control heterogeneous robot, and discusses some cases start sensor less, the evidence combination may lead to a lack of recognition, then we propose a Markov Decision Process model, control sensor switch, to solve the problem of energy consumption.

[1] Y. J. Fan, Y. H. Yin, L. D. Xu, Y. Zeng and F. Wu, "IoT-Based Smart Rehabilitation System," in IEEE Transactions on Industrial Informatics, vol. 10, no. 2, pp. 1568-1577, May 2014.
[2] A. Al-Fuqaha, M. Guizani, M. Mohammadi, M. Aledhari, and M. Ayyash, "Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications," IEEE Communications Surveys & Tutorials, vol. 17, no. 4, pp. 2347-2376, 2015.
[3] Xin Hong, Chris Nugent, Maurice Mulvenna, Sally McClean, Bryan Scotney, Steven Devlin, Evidential fusion of sensor data for activity recognition in smart homes, Pervasive and Mobile Computing ,Pages 236-252,2009.
[4] ETSI. [Online]. Available: http://www.etsi.org/ (accessed July 20,2020).
[5] OneM2M. [Online]. Available: http://www.onem2m.org/ (accessed July 20,2020).
[6] OneM2M-TS-0001, "Functional Architecture", v2.10.0, [Online]. Available: http://www.OneM2M.org/images/files/deliverables/Release2/TS-0001-%20Functional_Architecture-V2_10_0.pdf (accessed July 20,2020).
[7] OpenM2M. [Online]. Available: https://wiki.eclipse.org/OM2M/one (accessed July 20,2020).
[8] ROS. "Robot Operating System", [Online]. Available: http://www.ros.org/(accessed July 20,2020).
[9] EV3. [Online]. Available: https://www.lego.com/en-us/mindstorms/about-ev3 (accessed July 20,2020).
[10] LeJOS. [Online]. Available: http://www.lejos.org/ (accessed July 20,2020).
[11] hacks4ros. [Online]. Available: http://hacks4ros.github.io/h4r_ev3_ctrl/ (accessed July 20,2020).
[12] L. Chen, J. Hoey, C. D. Nugent, D. J. Cook and Z. Yu, "Sensor-Based Activity Recognition," in IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 42, no. 6, pp. 790-808, Nov. 2012.
[13] L. Chen, C. Nugent and G. Okeyo, "An Ontology-Based Hybrid Approach to Activity Modeling for Smart Homes," in IEEE Transactions on Human-Machine Systems, vol. 44, no. 1, pp. 92-105, Feb. 2014.
[14] R. Bellman, Dynamic Programming, Princeton Landmarks in Mathematics, Princeton University Press, Princeton, NJ, USA, 2010.
[15] M. Abu Alsheikh, D. T. Hoang, D. Niyato, H. Tan and S. Lin, "Markov Decision Processes With Applications in Wireless Sensor Networks: A Survey," in IEEE Communications Surveys & Tutorials, vol. 17, no. 3, pp. 1239-1267, third quarter 2015.
[16] W. T. Scherer, S. Adams and P. A. Beling, "On the Practical Art of State Definitions for Markov Decision Process Construction," in IEEE Access, vol. 6, pp. 21115-21128, 2018.
[17] J. Zheng and A. S. Namin, "Defending SDN-based IoT Networks Against DDoS Attacks Using Markov Decision Process," 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA, pp. 4589-4592, 2018.
[18] L. Li, Z. Jin, G. Li, L. Zheng and Q. Wei, "Modeling and Analyzing the Reliability and Cost of Service Composition in the IoT: A Probabilistic Approach," 2012 IEEE 19th International Conference on Web Services, Honolulu, HI, pp. 584-591,2012.
[19] Wang, E. K., Wu, T.-Y., Chen, C.-M., Ye, Y., Zhang, Z., & Zou, F. MDPAS: Markov Decision Process Based Adaptive Security for Sensors in Internet of Things. Genetic and Evolutionary Computing, pp. 389-397,2015.
[20] X. Bai, C. Xu, Y. Ao , B. Chen and D. Du, "Learning-based Probabilistic Modeling and Verifying Driver Behavior using MDP," 2019 International Symposium on Theoretical Aspects of Software Engineering (TASE), Guilin, China, pp. 152-159, 2019.
[21] Wei-ChangShih, Dependable activity recognition in heterogeneous service-robot systems, Institute of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan, R.O.C. ,2019.
[22] ROS Bridge. [Online]. Available: http://wiki.ros.org/rosbridge_suite (accessed July 20,2020).
[23] EF-MDP model. [Online]. Available: https://github.com/ice71115/EF-MDP (accessed July 20,2020).