臺灣博碩士論文加值系統

在以往電腦效能較差的時代，雖然已有人工智慧的提出，但由於運算量過大導致電腦無法負荷故發展速度非常緩慢，然而近年電腦效能進步，人工智慧的發展越發蓬勃，現在也常將人工智慧用於進行圖片辨識，改變以往辨識圖片時需要根據需求而開發不同演算法的情況。在這個時代中，物聯網與人工智慧都是科技發展的主流之一，本論文將人工智慧及物聯網結合至自動販賣系統上，並以售票機模擬販賣機形式，藉由深度學習所訓練的圖片辨識系統辨識客戶的年齡及性別資料，再透過低功耗廣域物聯網將資料送到伺服器做匯集統整，藉以分析客戶族群以及商品販賣情形，並可以透過監測端監測當前售票機的狀況。

In the era of poor computer performance, although artificial intelligence has been proposed, the development speed is very slow because the computer is unable to load due to the large amount of computation. However, in recent years, the computer performance has improved, and the development of artificial intelligence has become more vigorous. Artificial intelligence is often used now. It is used for image recognition, and it is necessary to develop different algorithms according to requirements when changing the past identification pictures. In this era, the Internet of Things and artificial intelligence are one of the mainstream of technological development. This thesis combines artificial intelligence and the Internet of Things into the vending system, then simulated vending machine with ticket vending machine. The image recognition system identifies the age and gender data of the customer, and then sends the data to the server through the low-power wide-area Internet of Things to collect and analyze the customer group and the merchandise sales situation, and can monitor the current ticket vending machine through the monitoring terminal situation.

摘要..............................i
Abstract..........................ii
誌謝..............................iii
目錄..............................iv
表目錄............................vi
圖目錄............................vii
第1章 緒論......................1
1.1 研究背景......................1
1.2 研究目的及研究方法............1
第2章 背景知識與相關研究........2
2.1 LoRa介紹......................2
2.1.1 LoRa技術....................2
2.1.2 LoRaWAN介紹.................3
2.1.3 LoRaWAN設備分類.............4
2.1.4 LoRaWAN設備認證.............5
2.2 PCANet簡介....................7
2.3 CNN簡介.......................8
2.4 進程間通訊簡介................10
2.4.1 進程間通訊................11
2.4.2 命名管道介紹..............12
第3章 系統架構..................14
3.1 系統架構......................14
3.2 售票機架構....................15
3.2.1 售票機硬體架構............15
3.2.2 售票機軟體架構............15
3.3 物聯網伺服器架構..............18
3.4 監測介面架構..................19
第4章 系統整合與實作結果........20
4.1 售票機整合與實現..............20
4.1.1 硬體元件介紹與整合........20
4.1.2 軟體整合..................22
4.2 LoRaWAN伺服器實現.............33
4.3 監測介面實現..................37
4.4 系統測試......................39
4.4.1 LoRa傳輸距離測試..........39
4.4.2 系統負荷測試..............43
第5章 結論與未來展望............44
5.1 結論..........................44
5.2 未來展望......................44
參考文獻..........................45
附錄..............................47
Extended Abstract.................48

[1]A. Ramzan, S. Rehman, Aqib Perwaiz, "RFID Technology: Beyond Cash-Based Methods in Vending Machine", 2017 2nd International Conference on Control and Robotics Engineering (ICCRE), pp. 189-193, 2017.
[2]G C. Wenshan, H. Yanqun, L. Minyang, "Influential Factors of Vending Machine Interface to Enhance the Interaction Performance", 2015 8th International Conference on Intelligent Computation Technology and Automation (ICICTA), pp. 486-489, 2015.
[3] S M S. Arifin, M. Syai'in, J. Endrasmono, S T. Sarena, L. Subiyanto, L. Subiyanto, L. Subiyanto, L. Subiyanto, A. Wahidin, A. Soeprijanto, "Smart vending machine based on SMS gateway for general transactions", 2017 15th International Conference on Quality in Research (QiR) : International Symposium on Electrical and Computer Engineering, pp. 34-39, 2017.
[4]G. Nemoto, K. Hiraishi, "Modeling and optimization of item changes in vending machines", 2017 11th Asian Control Conference (ASCC), pp. 19-24, 2017.
[5]R. Gruen, E. Liang, "NuiVend - Next Generation Vending Machine", 2016 International Conference on Computational Science and Computational Intelligence (CSCI), pp. 545-548, 2016.
[6]物聯網重點技術LPWAN解析，6大主要技術、各家優勢與主要產業發展、商業模式與智慧城市應用, 資料取至
http://www.techbang.com/posts/49656-internet-of-things-technologies-lpwan-analysis-6-home-advantage-and-industrial-development-of-major-technology-business-models-and-application-of-intelligent-cities
[7]LoRa無線網路技術創始人談IoT未來關鍵趨勢 資料取至
http://www.ithome.com.tw/people/108349
[8]LoRa：長距離低功耗物聯網傳輸技術 資料取至 https://read01.com/5xzLQE.html
[9]G. Margelis, R. Piechocki, D. Kaleshi, P. Thomas, "Low Throughput Networks for the IoT: Lessons learned from industrial implementations," in Proceedings of IEEE 2nd World Forum on Internet of Things (WF-IoT), pp. 181-186, Milan, 14-16 Dec. 2015.
[10]P. Neumann, J. Montavont and T. Noël, "Indoor deployment of low-power wide area networks (LPWAN): A LoRaWAN case study," 2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), New York, NY, 2016, pp. 1-8.
[11]J. Petajajarvi, K. Mikhaylov, A. Roivainen, T. Hanninen, M. Pettissalo "On the Coverage of LPWANs: Range Evaluation and Channel Attenuation Model for LoRa Technology," in Proceedings of 14th International Conference on ITS Telecommunications (ITST), pp. 55-59, Copenhagen, 2-4 Dec. 2015.
[12]Lora Alliance [Online]. 資料取至Available: https://www.lora-alliance.org/
[13]J. Petajajarvi, K. Mikhaylov, A. Roivainen, T. Hanninen, and M. Pettissalo, “On the coverage of LPWANs: Range evaluation and channel attenuation model for LoRa technology,” in Proc. 14th Int. Conf. ITS Telecommun. (ITST), Copenhagen, Denmark, Dec. 2015, pp. 55–59.
[14]Wixted, A.J. Kinnaird, P. Larijani, H. Tait, A. Ahmadinia, A. Strachan, N. Evaluation of LoRa and LoRaWAN for wireless sensor networks. In Proceedings of the 2016 IEEE SENSORS, Glasgow, UK, 30 October–3 November 2016; pp. 1–3..
[15]A. Augustin, J. Yi, T. Clausen, W. M. Townsley, "A study of LoRa: Long range & low power networks for the Internet of Things", Sensors, vol. 16, no. 9, pp. 1466, 2016.
[16]J. Petäjäjärvi, K. Mikhaylov, M. Hämäläinen, J. Iinatti, "Evaluation of LoRa LPWAN technology for remote health and wellbeing monitoring", 2016 10th International Symposium on Medical Information and Communication Technology, pp. 1-5, 2016
[17]T. Chan, K. Jia, S. Gao, J. Lu, Z. Zeng, Y. Ma, PCANet: A Simple Deep Learning Baseline for Image Classification? arXiv Prepr, pp. 1-15, 2014
[18]Wikipedia, “主成分分析”, 資料取自
https://zh.wikipedia.org/wiki/%E4%B8%BB%E6%88%90%E5%88%86%E5%88%86%E6%9E%90
[19] 葛一鳴，2017，自己動手寫神經網路，大陸：人民郵電出版社，9月。
[20]MBAlib, “主成分分析法”,資料取自
http://wiki.mbalib.com/zh-tw/%E4%B8%BB%E6%88%90%E5%88%86%E5%88%86%E6%9E%90%E6%B3%95
[21]Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan, Stefan Carlsson , CNN Features off-the-shelf: an Astounding Baseline for Recognition in CVPR 2014
[22]Kanishka Nithin.D, Dr.Bagavathi Sivakumar.P, Learning of Generic Vision Features using Deep CNN, 2015 Fifth International Conference on Advances in Computing and Communications, pp. 54-57, 2015
[23]Wikipedia, “進程間通訊”, 資料取自
https://zh.wikipedia.org/wiki/%E8%A1%8C%E7%A8%8B%E9%96%93%E9%80%9A%E8%A8%8A
[24]網昱多媒體, “MQTT教學（一）：認識MQTT”, 資料取自
https://swf.com.tw/?p=1002
[25]ASUS, “VivoMini VC66”,資料取自
https://www.asus.com/tw/Mini-PCs/VivoMini-VC66/
[26]正文科技股份有限公司,"Features of IDU (indoor unit) Pico Gateway", 資料取至http://www.giotnetwork.com/img/dload/dm_Indoor-Gateway.pdf