由於現今節能減碳的議題越來越被重視，一般家庭也能希望更明確的瞭解家庭中用電的資訊，為達到將傳統電表資訊轉換為人們可以容易得知的數位資訊，智慧電表(Smart Meter)開始廣泛的被使用。
目前智慧電表的型態有兩種，一種為測量家庭總電量之電表，另一種則針對個別插座進行量測。前者雖然安裝方便，卻無法詳細得知家庭電器使用與電量之關係；後者雖可明確得知個別電器用電量，但因為一般家庭家電數量相當多，因此在安裝上有其困難度，並且也較難得知家庭總用電量。
為此，本研究提出利用監督式學習建立並行式多方電器辨識系統，其利用電流感測器以及電壓感測器搭配微處理器設計成一個低成本之智慧電表，透過智慧電表所讀取到的電能資訊，進行模糊、電能特徵擷取之後，使用監督式學習的方法之一的支援向量機來進行不同電器的電能特徵分類，用以歸納出不同電器的分類特性並建立分類模型，最後藉由監督波形的變換擷取出電器運作波形後，使用支援向量機對波形所擷取出來之電能特徵進行判斷，便可於總電源端辨識出電器，改善當前智慧電表的缺陷。

Due to recent attention toward power management and energy conservation, residents want to know the power consumption and related information of each appliance at home. For the purpose of translating traditional power meter readings into digital form for ease of displaying power consumption information to residents, the Smart Meter is widely used.
There are now two types of Smart Meters, one meter measures the total power consumption of the residence while the other measures the power consumption in each power outlets individually. The first meter may be easier in installation, but cannot accurately display the relationship between the appliances and their power consumptions. The latter meter can accurately measure the power consumption by each appliance, but since the number of appliances in each residence is numerous, installation is difficult and harder to find the total power usage within the residence.
Therefore, this study proposes a parallel multi-appliance recognition system using supervised learning method. This study designs a low-cost Smart Meter with current sensors, voltage sensors and microcontrollers to measure the power information. Using the power information read from the power meter, the fuzzy and power features are extracted. Then one of the supervised learning methods, Support Vector Machine is used to identify the appliances by their power features. It summarizes the classification of different appliances and establishes the classification model. Finally, this system polls the variation of power wave forms and extracts the wave form of the appliances in use. The wave form is used to get the power feature and let Support Vector Machine identify the appliance. Hence, it can recognize the appliances just by the power outlet readings in the residence and improve defects within the Smart Meter.

[1] H.S. Cho, T. Yamazaki and M. Hahn, "Determining location of appliances from multi-hop tree structures of power strip type smart meters", IEEE Trans. on Consumer Electronics, Vol. 55, No. 4, pp. 2314-2322, November 2009.
[2] M. Saguan, 「Advanced Metering: summary and conclusion」, Proceedings of the Smart metering workshop organized by Florence school of regulation, pp. 1-12,Feb 2009.
[3] C. Bennett, D. Highfill, 「Networking AMI Smart Meters」, Proceedings of the IEEE Energy2030 conference, pp. 1-8, Nov 2008.
[4] Y. M. Huang, M. Y. Hsieh, H. C. Chao, S. H. Hung, and J. H. Park, 「Pervasive, Secure Access to a Hierarchical Sensor-Based Healthcare Monitoring Architecture in Wireless Heterogeneous Networks」, IEEE Journal on Selected Area in Communications, Vol. 27, No. 4, pp.400-302, May 2009.
[5] C. F. Lai, Y. M. Huang, J. H. Park, and H. C. Chao, 「Adaptive Body Posture Analysis Using Collaborative Multi-Sensors for Elderly Falling Detection」, IEEE Journal on Intelligent System , Vol.25, No.2, pp.20-30, March 2010.
[6] H. C. Huang, Y. M. Huang ,and J. W. Ding, 「An implementation of battery-aware wireless sensor network using ZigBee for multimedia service」, Proceedings of the IEEE International Conference on Consumer and Electronics, pp. 369-370, February 2006.
[7] M. Y. Hsieh, Y. M. Huang, and H. C. Chao, 「Adaptive security design with malicious node detection in cluster-based sensor networks」, Journal on Computer Communications , Vol. 30, no. 11-12, pp. 2385-2400, September 2007.
[8] H.S. Cho, T. Kato, T. Yamazaki, and M. Hahn, 「Simple and Robust Method for Detecting the Electric Appliances Using Markers and Programmable Logic Devices」, Proceedings of the IEEE 13th International Symposium on Consumer Electronic, pp. 334-338, May 2009.
[9] H.Serra, J.Correia, A.J. Gano, A.M. de Campos, and I.Teixeira, 「Domestic Power Consumption Measurement and Automatic Home Appliance Detection」, Proceedings of the IEEE International Workshop on Intelligent Signal Processing, pp.128–132, September 2005.
[10] M. Ito, R. Uda, S. Ichimura, K. Tago, T. Hoshi, and Yutaka Matsushita, 「A Method of Appliance Detection Based on Features of Power Waveform」, Proceedings of the International Symposium on Applications and the Internet, pp. 291-294, August 2004.
[11] J. Heo, C.S. Hong, S.B. Kang, and S.S. Jeon, 「Design and Implementation of Control Mechanism for Standby Power Reduction」, IEEE Trans. Consumer Electronics, Vol. 54, No. 1, pp. 179–185, February 2008.
[12] 「Smart Meter of joseph-tech」, http://www.joseph-tech.com.tw/download/EZ-D_Catalog_tw.pdf, retrieved on July 2011.
[13] S. Park, H. Kim, H. Moon, J. Heo, and S.Yoon, 「Concurrent Simulation Platform for Energy-Aware Smart Metering Systems,」 IEEE Trans. Consumer Electron., vol. 56, no. 3, pp. 1918-1926, Aug. 2010.
[14] Y. Yingcong, L. Binqiao, G. Jing, and S. Yehui, 「A Design of Smart Energy-saving Power Module」, Proceedings of the IEEE Conference on Industrial Electronics and Applications , pp. 898 – 902, June 2010.
[15] M. Jahn, M. Jentsch, CR. Prause, F.Pramudianto, A, Al-Akkad, and R. Reiners, 「The Energy Aware Smart Home」, Proceedings of the International Conference on Future Information Technology, pp 1–8, May 2010.
[16] 「hydra」, http://www.hydramiddleware.eu/news.php, retrieved on July 2011.
[17] D.M. Han and J.H. Lim, 「Smart home energy management system using IEEE 802.15.4 and zigbee」, IEEE Trans. Consumer Electronics, vol.56, no. 3, pp. 1403-1410, August 2010.
[18] D.M. Han and J.H. Lim, 「Design and implementation of smart home energy management systems based on ZigBee,」 IEEE Trans. Consumer Electronics, Vol. 56, Issue 3, 2010, pp. 1417 – 1425, August 2010.
[19] Y.S. Son, T. Pulkkinen; K.D. Moon, and C. Kim; 「Home energy management system based on power line communication,」 IEEE Trans. Consumer Electronics, Vol. 56, no. 3, pp. 1380 -1386, February 2010.
[20] 「Google Meter」, http://www.google.org/powermeter/, retrieved on July 2011.
[21] 「Greenbox」, http://getgreenbox.com/, retrieved on July 2011.
[22] 「The Power Tab」, http://www.energy-aware.com/our-products/ihd/, retrieved on July 2011.
[23] 「John La Grou plugs smart power outlets」, http://www.ted.com/talks/john_la_grou_plugs_smart_power_outlets_1.html, retrieved on July 2011.
[24] M. Ito, R. Uda, S. Ichimura, K. Tago, T. Hoshi, and Y. Matsushita, 「A method of appliance detection based on features of power waveform」, Proceedings of the International Symposium on Applications and the Internet, pp. 291–294, August 2004.
[25] H.Y. Lam, G.S.K. Fung, and W.K. Lee, 「A Novel Method to Construct Taxonomy of Electrical Appliances Based on Load Signatures」, IEEE Trans. Consumer Electronics, vol. 53, no. 2, pp. 654-660, May 2007.
[26] A.G. Ruzzelli, G.M.P. O'Hare, A. Schoofs, and C. Nicolas, 「Real-Time Recognition and Profiling of Appliances through a Single Electricity Sensor, In Seventh Annual IEEE Communications Society Conference on Sensor」, Proceedings of the IEEE Communications Society Conference on Sensor Mesh and Ad Hoc Communications and Networks , pp.1-9, June 2010.
[27] M. Akbar and D. Z. A. Khan, 「Modified nonintrusive appliance load monitoring for nonlinear devices」, Proceedings of the IEEE International Multitopic Conference, pp. 1-5, December 2007.
[28] W. Frawley, G. Piatetsky-Shapiro ,and C. Matheus, 「Knowledge Discovery in Databases: An Overview」 , AAAI/MIT Press, 1991.
[29] D. Hand, H. Mannila, amd P. Smyth, 「Principles of Data Mining」, Massachusetts Institute of Technology, 2001.
[30] 「ACS714ELCTR-20A-T」, http://www.ictradenet.com/ACS714ELCTR-20A-T/, retrieved on July 2011.
[31] 「Basic Usage of ACS714」, http://www.allegromicro.com/en/Products/Part_Numbers/0714/0714.pdf, retrieved on July 2011.
[32] 「STM3210E-LK」, http://www.st.com, retrieved on July 2011.
[33] 「Power Factor」, http://en.wikipedia.org/wiki/Power_factor, retrieved on July 2011.
[34] 「資訊熵」, http://zh.wikipedia.org/wiki/%E7%86%B5_(%E4%BF%A1%E6%81%AF%E8%AE%BA), retrieved on July 2011.
[35] 「Support Vector Machine」, http://en.wikipedia.org/wiki/Support_vector_machine, retrieve on July 2011.
[36] M. Aizerman, E. Braverman, and L. Rozonoer , 「Theoretical foundations of the potential function method in pattern recognition learning」, Automation and Remote Control 25: 821–837
[37] 「libsvm」, http://www.csie.ntu.edu.tw/~cjlin/libsvm/, retrieved on July 2011.