近年來，隨著老人援助需求的增長，健康照護系統的開發漸漸地朝向具備舒適度、隱私及智慧化的方向發展，並以提升老年人的生活品質為宗旨。在本論文中，基於隱私問題的考量，我們採用低解析度的紅外線陣列感測器做為健康照護系統的開發，此紅外線感測器是由 16 × 4 的熱電堆陣列感測器所組成，可視角為 60˚ × 16.4˚，在陣列感測器之中，每個像素可取得所測得的溫度資訊以產生紅外線溫度影像，最後利用溫度影像實現定位及跌倒偵測的應用。
在系統之中，我們使用兩顆紅外線陣列感測器，布置在房間不同位置的牆上，以不同角度擷取人體在空間上的資訊。在前處理的部分，利用人體與環境溫度差異的特性，人體前景的影像可藉由將紅外線影像與背景溫度模型相減而得到，此背景模型會隨著背景溫度的變化更新。在定位方面，我們利用前景區域的溫度，計算出人體對應到每個感測器的方位角(AOA)，並藉由AOA定位法估測出人體位置，接著經由回歸模型修正估測位置的誤差，最後，我們的定位演算法可達到13.39公分的平均距離誤差。
除了定位之外，我們利用感測器擷取跌倒動作的特徵，實現跌倒偵測的演算法，在系統中，兩個感測器會同時捕捉人體的動作，我們會選擇前景面積較大的感測器資料去做特徵擷取的動作，其中擷取的特徵包含了7種特徵，最後利用這些特徵建立k-近鄰演算法(k-NN)的模型，進行跌倒偵測的分類。為了評估跌倒偵測的分類效果，我們使用80個跌倒動作及80個正常動作，並以10次交叉驗證(10-fold cross-validation)來選擇最佳的特徵集合與k-NN模型的k值，最後的分類結果達到95.25%的敏感度，90.75%的特異度及93%的準確度。

As the need of the elderly assistance increases, the healthcare monitoring systems are designed for improving the quality of life. The development strategy is aimed at comfortability, privacy, and intelligence. In this thesis, a low resolution privacy preserved infrared array sensor are adopted. The sensor is composed of a 16×4 thermopile array with the corresponding 60˚×16.4˚ field of view. To capture the infrared image, each pixel of infrared sensor contains the temperature value seen by the sensor. By using the infrared array sensors, our healthcare monitoring system is developed for the applications of tracking and fall detection.
In our system, two infrared sensors are attached to the wall at different places and are used for capturing the three dimensional image information. Before the tracking process, the foreground of human body is determined by subtracting the image with the background model using the temperature difference characteristic. The background model would update with the background temperature adaptively. Using the temperature value within the foreground region, the angle of arrival (AOA) from each sensor is obtained. The location is then estimated by the AOA based positioning algorithm. The estimated position is passed to the regression model to reduce the positioning error. As a result, the mean error of our tracking algorithm is 13.39 cm.
In addition to the tracking application, the fall detection algorithm is implemented by extracting the features from the falling action. Two sensors would capture the action at the same time. The sensor with larger foreground region is chosen for the feature extraction process, in which 7 features are included. These extracted features are applied to the k-nearest neighbor (k-NN) classification model for the fall detection. To build the k-NN model, 80 fall actions and 80 normal actions are collected from five subjects for estimating the performance. Using the 10-fold cross-validation method, the k value of k-NN model and the feature selection are determined by scanning the k value and every possible combination of feature subsets. Finally, 95.25% sensitivity, 90.75% specificity and 93% accuracy are achieved in our fall detection system.

[1] Microelectronic Integrated Systems, ”16x4 IR array,” MLX90620 datasheet, Sept. 2012.
[2] M. Inc. (2013, April) MLX90620 for smart and green HVAC. [Online]. Available:
http://www.melexis.com/Assets/MLX90620-for-smart-and-green-HVAC-6256.aspx
[3] W.-T. Tang, C.-M. Hu, and C.-Y. Hsu, “A mobile phone based homecare management
system on the cloud,” in IEEE International Conference on Biomedical Engineering and
Informatics (BMEI), vol. 6, Oct 2010, pp. 2442–2445.
[4] C.-C. Shih, K.-Y. Chou, H.-C. Keh, Y.-C. Cheng, P.-Y. Yu, and N.-C. Huang, “Building
long-distance health care network using minimized portable sensors and active alert sys-
tem,” in IEEE International Conference on Network-Based Information Systems (NBiS),
Sept 2013, pp. 401–404.
[5] B. Najafi, K. Aminian, F. Loew, Y. Blanc, and P. Robert, “Measurement of stand-sit and
sit-stand transitions using a miniature gyroscope and its application in fall risk evaluation
in the elderly,” IEEE Transactions on Biomedical Engineering, vol. 49, no. 8, pp. 843–
851, Aug 2002.
[6] J. Hwang, J. Kang, Y. Jang, and H. Kim, “Development of novel algorithm and real-time
monitoring ambulatory system using bluetooth module for fall detection in the elderly,”
in IEEE Annual International Conference on Engineering in Medicine and Biology So-
ciety (IEMBS), vol. 1, Sept 2004, pp. 2204–2207.
[7] J. Zheng, G. Zhang, and T. Wu, “Design of automatic fall detector for elderly based
on triaxial accelerometer,” in IEEE International Conference on Bioinformatics and
Biomedical Engineering (ICBBE), June 2009, pp. 1–4.
[8] S. Sim, H. Jeon, G. Chung, S. Kim, S. Kwon, W. Lee, and K. Park, “Fall detection
algorithm for the elderly using acceleration sensors on the shoes,” in IEEE Annual In-
ternational Conference on Engineering in Medicine and Biology Society (EMBC), Aug
2011, pp. 4935–4938.
[9] C.-F. Lai, S.-Y. Chang, H.-C. Chao, and Y.-M. Huang, “Detection of cognitive injured
body region using multiple triaxial accelerometers for elderly falling,” IEEE Sensors
Journal, vol. 11, no. 3, pp. 763–770, March 2011.
[10] S. Erdogan, T. Bilgin, and J. Cho, “Fall detection by using k-nearest neighbor algorithm
on wsn data,” in IEEE GLOBECOM Workshops (GC Wkshps), Dec 2010, pp. 2054–
2058.
[11] W.-C. Cheng and D.-M. Jhan, “Triaxial accelerometer-based fall detection method using
a self-constructing cascade-adaboost-svm classifier,” IEEE Journal of Biomedical and
Health Informatics, vol. 17, no. 2, pp. 411–419, March 2013.
[12] G. Qian, B. Peng, and J. Zhang, “Gesture recognition using video and floor pressure
data,” in IEEE International Conference on Image Processing (ICIP), Sept 2012, pp.
173–176.
[13] Y. Li, Z. Zeng, M. Popescu, and K. Ho, “Acoustic fall detection using a circular micro-
phone array,” in IEEE Annual International Conference on Engineering in Medicine and
Biology Society (EMBC), Aug 2010, pp. 2242–2245.
[14] X. Zhuang, J. Huang, G. Potamianos, and M. Hasegawa-Johnson, “Acoustic fall de-
tection using gaussian mixture models and gmm supervectors,” in IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP), April 2009, pp. 69–
72.
[15] C. Doukas and I. Maglogiannis, “Advanced patient or elder fall detection based on move-
ment and sound data,” in IEEE Second International Conference on Pervasive Comput-
ing Technologies for Healthcare, Jan 2008, pp. 103–107.
[16] G. Diraco, A. Leone, and P. Siciliano, “An active vision system for fall detection and
posture recognition in elderly healthcare,” in IEEE Design, Automation Test in Europe
Conference and Exhibition (DATE), March 2010, pp. 1536–1541.
[17] C.-L. Liu, C.-H. Lee, and P.-M. Lin, “A fall detection system using k-nearest neighbor
classifier,” Expert Systems with Applications, vol. 37, no. 10, pp. 7174 – 7181, 2010.
[18] V. Vaidehi, K. Ganapathy, K. Mohan, A. Aldrin, and K. Nirmal, “Video based auto-
matic fall detection in indoor environment,” in IEEE International Conference on Recent
Trends in Information Technology (ICRTIT), June 2011, pp. 1016–1020.
[19] J. Kemper and H. Linde, “Challenges of passive infrared indoor localization,” in IEEE
5th Workshop on Positioning, Navigation and Communication (WPNC), March 2008,
pp. 63–70.
[20] W. Yu, Z. Wang, and L. Jin, “The experiment study on infrared radiation spectrum of
human body,” in IEEE-EMBS International Conference on Biomedical and Health In-
formatics (BHI), Jan 2012, pp. 752–754.
[21] M. Kuki, H. Nakajima, N. Tsuchiya, and Y. Hata, “Human movement trajectory record-
ing for home alone by thermopile array sensor,” in IEEE International Conference on
Systems, Man, and Cybernetics (SMC), Oct 2012, pp. 2042–2047.
[22] M. Popescu, B. Hotrabhavananda, M. Moore, and M. Skubic, “Vampir- an automatic
fall detection system using a vertical pir sensor array,” in IEEE International Conference
on Pervasive Computing Technologies for Healthcare (PervasiveHealth), May 2012, pp.
163–166.
[23] X. Luo, T. Liu, J. Liu, X. Guo, and G. Wang, “Design and implementation of a dis-
tributed fall detection system based on wireless sensor networks,” EURASIP Journal on
Wireless Communications and Networking, vol. 2012, no. 1, pp. 1–13, 2012.
[24] X. Qinlan and C. Hong, “Image denoising based on adaptive filtering and multi-frame
averaging filtering,” in IEEE International Conference on Artificial Intelligence and
Computational Intelligence (AICI), vol. 3, Nov 2009, pp. 523–526.
[25] X. Ping and J. Robinson, “Supervised object-based temporal filtering for enhancement
of moving facial images,” in IEEE Conference on Electrical and Computer Engineering,
vol. 1, May 1998, pp. 453–456.
[26] Y. Liu, L. Wang, J. Liu, and Y. Di, “A study of human skin and surface temperatures in
stable and unstable thermal environments,” Journal of Thermal Biology, vol. 38, no. 7,
pp. 440 – 448, 2013.
[27] Y. Benezeth, B. Emile, and C. Rosenberger, “Comparative study on foreground detection
algorithms for human detection,” in IEEE Fourth International Conference on Image and
Graphics (ICIG), Aug 2007, pp. 661–666.
[28] H.-M. Chen, P.-H. Chen, K.-L. Yeh, W.-H. Fang, M.-C. Shie, and F. Lai, “Center of
mass-based adaptive fast block motion estimation,” Journal on Image and Video Pro-
cessing, vol. 2007, no. 1, pp. 2–2, 2007.
[29] M. Haque et al., “A least square approach for tdoa/aoa wireless location in wcdma sys-
tem,” in IEEE International Conference on Computer and Information Technology (IC-
CIT), 2008, pp. 686–690.
[30] S. Tao, M. Kudo, H. Nonaka, and J. Toyama, “Recording the activities of daily living
based on person localization using an infrared ceiling sensor network,” in IEEE Interna-
tional Conference on Granular Computing (GrC), 2011, pp. 647–652.
[31] S. Zhang and X. Pan, “A novel text classification based on mahalanobis distance,”
in IEEE International Conference on Computer Research and Development (ICCRD),
vol. 3, 2011, pp. 156–158.
[32] F. Gu, D. Liu, and X. Wang, “Semi-supervised weighted distance metric learning for knn
classification,” in IEEE International Conference on Computer, Mechatronics, Control
and Electronic Engineering (CMCE), vol. 6, Aug 2010, pp. 406–409.
[33] M. Popescu and S. Coupland, “A fuzzy logic system for acoustic fall detection.” in AAAI
Fall Symposium AI in Eldercare: New Solutions to Old Problem, 2008, pp. 78–83.
[34] G. Wu, “Distinguishing fall activities from normal activities by velocity characteristics,”
Journal of Biomechanics, vol. 33, no. 11, pp. 1497–1500, 2000.
[35] K. Yang, H. Wang, G. Dai, S. Hu, Y. Zhang, and J. Xu, “Determining the repeat number
of cross-validation,” in IEEE International Conference on Biomedical Engineering and
Informatics (BMEI), vol. 3, Oct 2011, pp. 1706–1710.
[36] T. Liu, X. Guo, and G. Wang, “Elderly-falling detection using distributed direction-
sensitive pyroelectric infrared sensor arrays,” Multidimensional Systems and Signal Pro-
cessing, vol. 23, no. 4, pp. 451–467, 2012.
[37] E. Auvinet, F. Multon, A. Saint-Arnaud, J. Rousseau, and J. Meunier, “Fall detection
with multiple cameras: An occlusion-resistant method based on 3-d silhouette vertical
distribution,” IEEE Transactions on Information Technology in Biomedicine, vol. 15,
no. 2, pp. 290–300, March 2011.
[38] B. Aguiar, T. Rocha, J. Silva, and I. Sousa, “Accelerometer-based fall detection for
smartphones,” in IEEE International Symposium on Medical Measurements and Appli-
cations (MeMeA), June 2014, pp. 1–6.
[39] M. Yu, Y. Yu, A. Rhuma, S. Naqvi, L. Wang, and J. Chambers, “An online one class
support vector machine-based person-specific fall detection system for monitoring an
elderly individual in a room environment,” IEEE Journal of Biomedical and Health In-
formatics, vol. 17, no. 6, pp. 1002–1014, Nov 2013.
[40] M. Dumitrache and S. Pasca, “Fall detection algorithm based on triaxial accelerometer
data,” in IEEE E-Health and Bioengineering Conference (EHB), Nov 2013, pp. 1–4.