嬰兒安全監控及音樂互動系統之研製

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：30

、訪客IP：18.117.94.221

姓名

陳日憲(Rih-Sian Chen) 查詢紙本館藏

畢業系所

資訊工程學系

論文名稱

嬰兒安全監控及音樂互動系統之研製
(The Development of a Baby Safety Monitoring and Musical Interaction System)

相關論文

★ 以Q-學習法為基礎之群體智慧演算法及其應用	★ 發展遲緩兒童之復健系統研製
★ 從認知風格角度比較教師評量與同儕互評之差異：從英語寫作到遊戲製作	★ 基於檢驗數值的糖尿病腎病變預測模型
★ 模糊類神經網路為架構之遙測影像分類器設計	★ 複合式群聚演算法
★ 身心障礙者輔具之研製	★ 指紋分類器之研究
★ 背光影像補償及色彩減量之研究	★ 類神經網路於營利事業所得稅選案之應用
★ 一個新的線上學習系統及其於稅務選案上之應用	★ 人眼追蹤系統及其於人機介面之應用
★ 結合群體智慧與自我組織映射圖的資料視覺化研究	★ 追瞳系統之研發於身障者之人機介面應用
★ 以類免疫系統為基礎之線上學習類神經模糊系統及其應用	★ 基因演算法於語音聲紋解攪拌之應用

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

[檢視]

[下載]

本電子論文使用權限為同意立即開放。
已達開放權限電子全文僅授權使用者為學術研究之目的，進行個人非營利性質之檢索、閱讀、列印。
請遵守中華民國著作權法之相關規定，切勿任意重製、散佈、改作、轉貼、播送，以免觸法。

摘要(中)

由於嬰兒尚未發展完全，常常處在危險環境中卻不自覺，因此近年來有關嬰兒監控的產品與研究有蓬勃的發展。另一方面，年輕父母重視嬰兒成長過程，他們會藉由音樂學習、聽覺刺激等方式來陪伴嬰兒成長。本論文的目標是開發一套為嬰兒設計的安全監控與音樂互動系統，提供嬰兒更安全的生活環境，並且成為嬰兒最好的玩伴。起初，系統會先偵測嬰兒的臉部資訊，然後以其臉部大小為基底，建立其肢體的感興趣區域模型(region of interest model, ROI model)。我們藉由動態背景相減法，得到各肢體ROI model的動態資訊，並且為這些動態資訊加入時間資訊，作為類神經網路的輸入特徵。本論文的類神經網路架構為：8顆輸入神經元、單隱藏層、10顆隱藏層神經元以及11顆輸出神經元。類神經網路會分類出11種類型的狀態，其中包含6種安全類狀態以及5種危險類狀態。當嬰兒處於危險狀態時，系統會立即發出警示給照護者。另一方面，嬰兒在揮動肢體的時候，系統會辨識出其揮動的肢體，利用MIDI改變音樂，與嬰兒互動。系統平台是使用Cubieboard 4嵌入式系統開發板為基底進行開發，目的在於體積小、成本低，容易應用在一般家庭環境。本論文之危險監控可以幫助照護者在進行其他工作(如：煮飯、泡奶等)時，有效地偵測危險，避免遺憾發生；音樂互動功能則是提供嬰兒探索環境的樂趣，以及刺激其聽覺能力與肢體發展。
實驗的設計上分成九種情境，每種情境都會有特定狀態種類輸出，其中五種情境為危險狀況發生的情境；四種為安全或音樂互動的情境。本論文使用混淆矩陣統計每種狀態的辨識結果，辨識之指標我們採用精確度(Precision)、召回率(Recall)，其中，精確率為86.6%、召回率85.7%。

摘要(英)

The research of baby monitor systems has been greatly growing in these years because of newborn infants are usually in hazardous environments are not conscious; On the other hand, young parents concern about the periods of babies growing up. They apply to be learning music, auditory stimulation, etc. to accompany growth of the babies. This thesis aims to develop a system to baby monitoring and musical interaction, system provide a safer living environment, and to be the best playmate for infants. The system starts from the detection of the face information of infant, then establishes limbs ROI model based on the face information. We use dynamic background subtraction algorithm to obtain dynamic information about each limb ROI model, and add some time information to this dynamic information, then the information will be the input of neural network input. Neural network architecture of this thesis is as follows: 8 input neurons, single hidden layer, 10 neurons in the hidden layer and eleven output neurons. The neural network can classify 11 types of state, which includes 6 security status, and five kinds of dangerous status. When the baby is in danger, the system will alarm the guardians immediately. On the other hand, when baby waving limbs, the system will recognize baby’s waving limb, then interact with the baby by changing music via MIDI. System develops with the basement of embedded development board－Cubieboard 4, it has the advantage of small size, low cost and easy to apply in general living environment. In this thesis, the function of danger monitoring detects dangerous events effectively, therefore, guardians can perform other tasks (such as: cooking, hot milk, and so on.) easily; The function of musical interaction can provide the babies can environment to explore for fun, stimulate their hearing ability and physical development.
The performance of the proposed system was verified by nine experimental scenarios, each scenario had specific types of output state, five of which scenario will occur dangerous events, the others are secure scenarios which include musical interaction events. This thesis computes results for each state of confusion matrix, and the results of the indicators we use Precision and Recall, the precision ratio and the recall ratio were 86.6% and 85.7%, respectively.

關鍵字(中)

★ 嬰兒
★ 音樂學習
★ 危險監控
★ 嵌入式系統

關鍵字(英)

★ baby
★ music learning
★ danger monitoring
★ embedded system

論文目次

摘要 I
ABSTRACT III
誌謝 V
目錄 VI
圖目錄 IX
表目錄 XI
第一章、緒論 1
1-1 研究動機 1
1-2 研究目的 2
1-3 論文架構 3
第二章、相關研究 4
2-1 嬰兒監控產品 4
2-2 安全監控相關文獻 7
2-3 幼兒音樂互動 8
2-3-1 幼兒聽覺能力之發展 9
2-3-2 音樂互動玩具 9
2-4 數位樂器介面 10
2-4-1 MIDI檔案格式 11
2-4-2 MIDI事件 12
第三章、系統架構 14
3-1 系統目的 14
3-2 系統流程 16
3-3 硬體架構 20
3-3-1 Cubieboard 4 21
3-3-2 QuickCam Pro 5000 22
第四章、特徵擷取 23
4-1 臉部特徵 23
4-2 嘴巴明亮度變異數 24
4-3 人臉位移量 26
4-4 動態連續時間 26
4-5 無臉之動態影像數 27
4-6 重心相鄰特徵 28
4-7 局部動態特徵 29
4-8 動態分佈區間 29
第五章、類神經網路 31
5-1 倒傳遞類神經網路 31
5-2 深度學習 38
5-2-1 深度學習工具－TensorFlow 41
5-2-2 深度學習工具－Deeplearning4j 42
5-3 交叉驗證結果比較 43
5-4 多層感知機訓練 44
5-5 多層感知機架構比較 46
第六章、實驗設計與結果 47
6-1 狀態設立與解析 47
6-2 實驗設計 48
6-3 嬰兒人臉辨識 51
6-4 有光源行為分析實驗 51
6-4-1 有光源狀態判斷結果 58
6-4-2 有光源系統分類與辨識結果比較 61
6-4-3 有光源危險警報與辨識結果 63
6-4-4 有光源音樂互動與辨識結果 65
6-5 無光源行為分析實驗 66
6-5-1 無光源狀態判斷結果 67
6-5-2 無光源系統分類與辨識結果比較 69
6-5-3 無光源危險警報與辨識結果 71
6-5-4 無光源音樂互動與辨識結果 72
第七章、結論與未來展望 74
7-1 結論 74
7-2 未來展望 75
參考文獻 76
附錄一 82

參考文獻

[1] Central Intelligence Agency: THE WORLD FACTBOOK. [Online]. Available: https://goo.gl/bjTuuq. [Accessed: 9-Jul-2016].
[2] 媽媽育兒百科：嬰兒發展，讓寶寶聽音樂好處.[Online]. Available: http://mombaby.tw/article14192.html. [Accessed: 02-Jul-2016].
[3] Babies’ brains benefit from music lessons, even before they can walk and talk. [Online]. Available: http://goo.gl/0RNZU5. [Accessed: 15-May-2016].
[4] 媽媽育兒百科：嬰兒聽音樂幫助成長和發育. [Online]. Available: http://mombaby.tw/article14403.html. [Accessed: 06-Jul-2016].
[5] Amazon: iBaby Wi-Fi Wireless Digital Baby Video Camera with Night Vision and Music Player. [Online]. Available: http://goo.gl/41C6nY. [Accessed: 03-Jul-2016].
[6] Amazon: Withings Smart Baby Monitor. [Online]. Available: http://goo.gl/XwiQLz. [Accessed: 03-Jul-2016].
[7] Amazon: Angelcare Movement and Sound Monitor for Smart Phone. [Online].Available:https://goo.gl/6GGtUS. [Accessed: 03-Jul-2016].
[8] Amazon: Baby monitor. [Online]. Available: https://goo.gl/vJiTCE. [Accessed: 1-Jul-2016].
[9] Amazon：Fosbaby Digital Video Baby Monitor by Foscam. [Online]. Available: http://goo.gl/sYjwUL. [Accessed: 03-Jul-2016].
[10] Amazon: Foscam FBM3502 Digital Video Baby Monitor, Auto Motion Tracking. [Online]. Available: http://goo.gl/Fy2z2n. [Accessed: 03-Jul-2016].
[11] Amazon: Cyber-Bay Intelligent Mini Baby Monitor. [Online]. Available: http://goo.gl/KW1V1K. [Accessed: 03-Jul-2016].
[12] Amazon: Motorola MBP8 Digital Audio Monitor. [Online]. Available: http://goo.gl/R5mXKy. [Accessed: 03-Jul-2016].
[13] Amazon: Motorola MBP36S Remote Wireless Video Baby Monitor with 3.5-Inch Color LCD Screen, Remote Camera Pan, Tilt, and Zoom. [Online]. Available: http://goo.gl/gtaALn. [Accessed: 03-Jul-2016].
[14] Amazon: Gynoii WiFi Wireless Video Baby Monitor with HD Infrared Night Vision, Two Way Audio and Time-Lapse for iPhone, iPad, Android Phones and tablets. [Online]. Available: http://goo.gl/NlM1Zg. [Accessed: 03-Jul-2016].
[15] Amazon: Snuza Baby Monitor, Hero. [Online]. Available: http://goo.gl/3i0fTr. [Accessed: 03-Jul-2016].
[16] Amazon: iBaby Monitor M6 HD Wi-Fi Wireless Digital Baby Video Camera with 360 Rotation, Night Vision, Two-way Speakers and Music Player for iPhone and Android, White. [Online]. Available: http://goo.gl/t8utm1. [Accessed: 03-Jul-2016].
[17] 宋文舉，台北榮總兒童醫學部：嬰兒猝死症. [Online]. Available: http://homepage.vghtpe.gov.tw/~ped/newpage32.htm. [Accessed: 09-Jul-2016].
[18] W. L. Ou, S. M. Yu, J. W. Chang, and C. P. Fan, “Video based vomit and facial foreign object detections for baby watch and safety,” 2013 International Conference on Orange Technologies, pp. 219-222, 2013.
[19] L. Li, Y. Chen, and Z. Li, “Yawning detection for monitoring driver fatigue based on two cameras,” 2009 12th International IEEE Conference on Intelligent Transportation Systems, pp. 1-6, 2009.
[20] 林漢威，「以表情辨識為基礎之嬰兒意外監控系統」，國立臺灣師範大學資訊工程研究所碩士論文，民國九十八年。
[21] J. Bhatt, N. D. V. Lobo, M. Shah, and G. Bebis, “Automatic recognition of a baby gesture,” 15th IEEE International Conference on Tools with Artificial Intelligence, pp. 610-615, 2003.
[22] 邵柏潤，「以肢體動作分析為基礎之新生兒意外監控系統」，國立臺灣師範大學資訊工程研究所碩士論文，民國九十八年。
[23] 蕭宛甄，「以前景物動在機率模型為基礎之嬰兒危險程度評估系統」，國立臺灣師範大學資訊工程研究所碩士論文，民國九十九年。
[24] N. Hafner, I. Mostafanezhad, V. M. Lubecke, O. Boric-Lubecke, and A. Host-Madsen, “Non-Contact Cardiopulmonary Sensing with a Baby Monitor,” 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 2300-2302, 2007.
[25] Wei Lin, R. Zhang, J. Brittelli, and C. Lehmann, “Wireless Infant Monitoring Device for the prevention of sudden infant death syndrome,” The 11th International Conference & Expo on Emerging Technologies for a Smarter World, pp. 1-4, 2014.
[26] H. Cao, L. C. Hsu, T. Ativanichayaphong, J. Sin, and J. C. Chiao, “A non-invasive and remote infant monitoring system using CO2 sensors,” 2007 IEEE Sensors, pp. 989-992, 2007.
[27] 林朱彥，「幼兒聽覺與音樂能力發展知多少」，國教之友，第六十卷第一期，37-44頁，國立台南大學國教之友社，民國九十八年。
[28] 劉英淑，「兒童發展與音樂教育」，國家圖書館研習資訊學刊，15-17頁，民國七十七年。
[29] Ebulobo：熊抱抱床邊懸掉玩具旋轉音樂盒. [Online]. Available: http://goo.gl/Oq1037. [Accessed: 27-May-2016].
[30] Toyroyal：魔術球. [Online]. Available: http://goo.gl/dlyjAz. [Accessed: 27-May-2016].
[31] 林志杰，新版MIDI玩家手冊，第三波出版社，民國八十三年。
[32] 陳幗眉，洪福財，兒童發展與輔導，初版，五南書局，台北市，民國九十八年。
[33] Cubieboard: Cubieboard4(CC-A80). [Online]. Available: http://goo.gl/IdmAoG. [Accessed: 9-Jul-2016].
[34] CNET: Logitech QuickCam Pro 5000 Specifications. [Online]. Available: http://goo.gl/5Ka80a. [Accessed: 9-Jul-2016].
[35] N. Srichumroenrattana, C. Lursinsap, and R. Lipikorn, “Facial Feature Detection Using Multiresolution Decomposition and Hillcrest-Valley Classification with Adaptive Mean Filter,” Fourth International Conference on Computer Sciences and Convergence Information Technology, pp. 697-701, 2009.
[36] 蘇木春，張孝德，機器學習：類神經網路、模糊系統以及基因演算法則，修訂二版，全華圖書，新北市，民國一百零一年。
[37] J. Schmidhuber, “Deep learning in neural networks: An overview,” Neural Networks, vol. 61, pp.85-117, 2015.
[38] Deeplearnin4j: Restricted Boltzmann Machines. [Online]. Available: http://deeplearning4j.org/restrictedboltzmannmachine. [Accessed: 29-Jul-2016].
[39] CSDN: 深度學習與受限波爾茲曼機. [Online]. Available: http://goo.gl/sNw614. [Accessed: 29-Jul-2016].
[40] CSDN: DBN. [Online]. Available: http://goo.gl/I4UGxb. [Accessed: 29-Jul-2016].
[41] Deeplearnin4j: Convolutional Networks. [Online]. Available: http://goo.gl/V9T7gG. [Accessed: 29-Jul-2016].
[42] TensorFlow: About TensorFlow. [Online]. Available: https://www.tensorflow.org/. [Accessed: 20-Jul-2016].
[43] Deeplearning4j: Quick Start Guide for Deeplearning4j. [Online]. Available: http://deeplearning4j.org/quickstart. [Accessed: 13-Jul-2016].

指導教授

蘇木春

審核日期

2016-7-28

推文