根據定義，情緒是受到某種刺激所產生的身心激動狀態。現代人在忙碌的工作下，常常累積許多壓力，當一個人累積過多壓力後，常常因為沒有適當的宣洩壓力，而將這個刺激表現在情緒上，往往造成同事、同學間的口角，引起許多誤會。情緒會引起如交感神經、副交感神經和心率的變化的生理反應及如開懷大笑、愁眉苦臉等表情反應。為了能夠辨別情緒，本研究主要建立一套量測系統，透過ZigBee無線傳輸來傳送所量測到的生理參數，並分析之。
雖然臉部表情來辨識情緒有一定的可行性，但一個經過訓練的人可能做出假的表情來造成系統誤判，最直接的方式就是測量生理訊號，生理反應源自自律神經系統，沒有辦法造假，所以本系統採用生理訊號分析來取代臉部表情辨識。而最能夠代表情緒的生理參數就是心電圖訊號，利用無線傳輸將收集到的ECG訊號送到電腦端作心率變異率(HRV)分析，再藉由這些參數的趨勢來判斷目前處於正面情緒或是負面情緒；另外也使用最近鄰居(KNN)分類器來將參數作分類，並與SAM量表作比較。若是準確率高，就可以使用本系統達到情緒辨識的目的，擺脫使用問卷來判斷情緒的方法。

By definition, emotion is an excited state generated by some kind of physical and mental stimulation. Under the busy works in modern time, a lot of people accumulate heavy pressure. When a person accumulated too much pressure, and no proper manner to vent pressure, it may be presented on emotional responses, and often resulting in a quarrel with colleagues or students. Finally, it may also lead to a lot of misunderstanding. The emotion will cause physiological and expression responses. The physiological responses are such as sympathetic, parasympathetic and heart rate (HR) changes. The expression responses are such as laughing face, frown, etc. In order to identify emotions, this study establishes a measurement system of physiological parameters and transmit the measured data through ZigBee wireless transmission systems and then analyzing the physiological parameters.
Although face recognition authentication has some viability, a trained person may make a false expression, and cause the system’s recognition error. The most direct way is to measure physiological signals. As the physiological responses are originated from Autonomic Nervous System (ANS), it is impossible to fake. Therefore, the system uses the physiological signal analysis instead of the facial expression recognition. Furthermore, the most suitable physiological parameter to represent emotional responses is the ECG signal. By using wireless transmission, it can transmit the measured ECG signal to the PC for heart rate variability (HRV) analysis. And then we use these parameters to determine the current trend of positive emotions or negative emotions. In addition, we also use the nearest neighbor (KNN) classifier to classify other parameters and compare with the SAM scale. If it has high accuracy, you can use this system instead of questionnaires to recognize the emotional responses.

[1] L. Byungsung, et al., "Classification of Facial Expression Using SVM for Emotion Care Service System," in Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, 2008. SNPD '08. Ninth ACIS International Conference on, pp. 8-12, 2008.
[2] W. Kiing-Ing, "Real-time heart rate variability detection on sensor node," in Sensors Applications Symposium, 2009. SAS 2009. IEEE, pp. 184-187, 2009.
[3] R. R. D. Fletcher, K.; Goodwin, M.S.; Eydgahi, H.; Wilder-Smith, O.; Fernholz, D.; Kuboyama, Y.; Hedman, E.B.; Ming-Zher Poh; Picard, R.W.; , "iCalm: Wearable Sensor and Network Architecture for Wirelessly Communicating and Logging Autonomic Activity " Information Technology in Biomedicine, IEEE Transactions on vol. 14, pp. 215 - 223, 2010.
[4] J. Jiehui, et al., "A Mobile Monitoring System of Blood Pressure for Underserved in China by Information and Communication Technology Service," Information Technology in Biomedicine, IEEE Transactions on, vol. 14, pp. 748-757, 2010.
[5] S. Yu-Cheng, et al., "Wireless ECG detection system with low-power analog front-end circuit and bio-processing ZigBee firmware," in Circuits and Systems (ISCAS), Proceedings of 2010 IEEE International Symposium on, pp. 1216-1219, 2010.
[6] K. Seong Hoon, et al., "UPnP-ZigBee internetworking architecture mirroring a multi-hop ZigBee network topology," Consumer Electronics, IEEE Transactions on, vol. 55, pp. 1286-1294, 2009.
[7] P. J. Lang, Bradley, M.M., Cuthbert, B.N., "International Affective Picture System (IAPS): Instruction Manual and Affective Ratings," echnical Report A-4. The Center for Research in Psychophysiology,Gainesville, Florida., 1999.
[8] M. M. B. Peter J. Lang, Bruce N. Cuthbert, "International Affective Picture System(IAPS) : Affective ratings of pictures and instruction manual," NIMH Center for the Study of Emotion & Attention University of Florida, 2008.
[9] B. Sabatinelli D., M.M., Fitzsimmons J., and Lang, P.J., "Parallel amygdala and inferotemporal activation reflect emotional intensity and fear relevance," niversity of Florida Neuroimage, 2005.
[10] M. K. Greenwald, Cook, E.W.I., Lang, P.J., "Affective judgment and psychophysiological response: dimensional covariation in the evaluation of pictorial stimuli.," J. Psychophysiol., pp. 51–64, 1989.
[11] W. A. S. P. Gomez, and B. Danuser., "Respiratory response during affective picture viewing," Biological Psychology 67, pp. 359-373, 2004.
[12] J. P. Saul, "BEAT-TO-BEAT VARIATIONS OF HEART-RATE REFLECT MODULATION OF CARDIAC AUTONOMIC OUTFLOW," News in Physiological Sciences, vol. 5, pp. 32-37, Feb 1990.
[13] A. Luttmann, et al., "Joint analysis of spectrum and amplitude (JASA) of electrogram applied for the indication of muscular fatigue among surgeons in urology.," in Advanced in Occupation Ergonomic and saefty., pp. 523 - 528, 1996.
[14] W. Wanqing and L. Jungtae, "Improvement of HRV methodology for positive/negative emotion assessment," in Collaborative Computing: Networking, Applications and Worksharing, 2009. CollaborateCom 2009. 5th International Conference on, pp. 1-6, 2009.
[15] R. McCraty, et al., "THE EFFECTS OF EMOTIONS ON SHORT-TERM POWER SPECTRUM ANALYSIS OF HEART-RATE-VARIABILITY," American Journal of Cardiology, vol. 76, pp. 1089-&, Nov 1995.
[16] H. H. So and K. L. Chan, "Development of QRS detection method for real-time ambulatory cardiac monitor," in Engineering in Medicine and Biology Society, 1997. Proceedings of the 19th Annual International Conference of the IEEE, pp. 289-292, 1997.
[17] K. F. Tan, et al., "Detection of the QRS complex, P wave and T wave in electrocardiogram," in Advances in Medical Signal and Information Processing, 2000. First International Conference on (IEE Conf. Publ. No. 476), pp. 41-47, 2000.
[18] D. Fradkin and P. Kantor, "Methods for learning classifier combinations: no clear winner," presented at the Proceedings of the 2005 ACM symposium on Applied computing, Santa Fe, New Mexico, 2005.
[19] S. D. Kreibig, "Autonomic nervous system activity in emotion: A review," Biological Psychology, vol. 84, pp. 394-421, 2010.