在農業方面，農民的經驗非常寶貴，但卻難以取代和傳承。對許多農業國家來說，缺乏大量的人力資源也是一個嚴重的問題，也因為人力資源的考量，導致農民的事業規模無法擴大或增加產值。其中對於有機作物而言，灌溉是最關鍵的步驟之一，但也是一項勞動相對密集的工作。如何有效利用自動控制系統來解決人力不足的問題，是這個系統最主要的目的。
本論文提供了一種基於機器學習的智能灌溉系統，該系統使用LoRa P2P模式來建構LoRa網路，此系統能夠自動學習農業專家和農民對溫室有機農作物的灌溉經驗。首先系統會根據訓練後的灌溉模型結合環境數據（如氣溫/濕度，土壤溫度/濕度，光照強度等）計算每次農作物需要灌溉的水量，然後利用無線長距離低功耗的LoRa P2P網路自動灌溉作物進行灌溉。在LoRaWAN 網路內使用的是非同步傳輸 (asynchronous communication), 是使用 random access 常見的 ALOHA method，並不適合即時的自動控制。我們使用LoRa P2P網路來實現自動灌溉系統，這是一種主從式的關係也是基於TDM (Time-Division Multiplexing)的MAC協議。我們的實驗結果顯示，我們所提出的智慧灌溉系統非常適合現代農業，不僅能優化農民澆水的方式也能更大幅度的縮減人力的需求。我們也提供了手機應用程式來觀看相關的環境數據跟操作此控制系統。

In agriculture, the experience of farmers is very valuable but difficult to replace and pass on. The lack of working power is also a serious problem for many agriculture countries. For organic crops, the irrigation is one of the most critical steps but also a very labor intensive work. How to effectively use the automatic control system to solve the problem of insufficient manpower is the most important purpose of this system.
This thesis provides a machine learning-based smart irrigation system with LoRa P2P networks to automatically learn the irrigation experiences from expert farmers for greenhouse organic crops. The proposed system will firstly calculate the amount of water for each irrigation based on the trained irrigation model combined with the environment data, such as air temperature/humidity, soil temperate/humidity, light intensity, etc., and then irrigate the crops automatically via the long-distance and low-power wireless LoRa P2P networks. The MAC protocol of LoRaWAN is Aloha based (random access) and may not be suitable for real-time automatically control. We implement the automatic irrigation system with LoRa P2P network which is a master-slave and TDM-based MAC protocol. Experimental results show that the proposed smart irrigation system is very suitable for modern agriculture. Not only can optimize the way farmers water their plants, but also can reduce the need for manpower. We also provide a mobile application to view relevant environmental data and operate this control system.

Abstract I
中文摘要 II
Table of Contents III
List of Figures IV
List of Tables V
Chapter 1 Introduction 1
Chapter 2 Related Works 5
2.1 LoRa and LoRaWAN 5
2.1.1 LoRa 5
2.1.2 LoRaWAN 6
2.2 Linear Regression 9
2.2.1 Simple Linear Regression 9
2.2.2 Multiple Linear Regression 10
2.3 Automation Control System 12
Chapter 3 System Design 13
3.1 System Architecture 13
3.2 Sensor Hub 14
3.2.1 Modbus 14
3.2.2 Sensors 15
3.3 Gateway 19
3.3.1 Raw Data Processing 19
3.3.2 Rules Engine 20
3.4 LoRa P2P 21
3.4.1 Slave to Master 21
3.4.2 Master to Slave 23
3.4.3 LoRa P2P Security 24
3.4.4 LoRa P2P Water Meter 25
3.5 Controller 29
3.5.1 LoRa P2P Solenoid Valve 29
Chapter 4 Experiment and Result 31
4.1 Hardware Device 31
4.2 Data Platform 32
4.2.1 Website 32
4.2.2 Mobile Application 34
4.3 Automatic Generation Rules System 36
4.4 Automatic Control System 43
Chapter 5 Conclusion and Future Works 45
References 47

[1] “M2M”, https://en.wikipedia.org/wiki/Machine_to_machine, accessed: 2019-7-22
[2] “TDM,” https://en.wikipedia.org/wiki/TDM, accessed: 2019-7-22
[3] “LoRa,” http://www.semtech.com/technology/lora, accessed: 2019-7-22
[4] “LoRaWAN,” http://www.lora-alliance.org/, accessed: 2019-7-22
[5] LoRa Alliance, “LoRaWAN specification,” http://lora-alliance.org, accessed: 2019-7-22
[6] “Semtek,” https://www.semtech.com/technology/lora/what-is-lora, accessed: 2019-7-22
[7] “Device Classes,” https://www.coursehero.com/file/p34b3ta/Device-Classes-Not-All-Nodes-Are-Created-Equal-End-devices-serve-different/, accessed: 2019-7-22
[8] “Simple linear regression”, http://en.wikipedia.org/wiki/Simple_linear_regression
[9] N. Hemageetha, "A survey on application of data mining techniques to analyze the soil for agricultural purpose," in 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom), pp. 3112-3117, Mar 2016.
[10] S. Prakash, A. Sharma and S. S. Sahu, "Soil Moisture Prediction Using Machine Learning," in 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), pp. 1-6, Apr 2018.
[11] “Linear Regression,” https://nthu-datalab.github.io/ml/labs/04-2_Regression/04-2_Regression.html, accessed: 2019-7-22
[12] “Multiple linear regression,” http://www.stat.yale.edu/Courses/1997-98/101/linmult.htm/, accessed: 2019-7-22
[13] Luminto and Harlili, "Weather analysis to predict rice cultivation time using multiple linear regression to escalate farmer's exchange rate," in 2017 International Conference on Advanced Informatics, Concepts, Theory, and Applications (ICAICTA), pp. 1-4, Aug 2017.
[14] S. Nagini, T. V. R. Kanth and B. V. Kiranmayee, "Agriculture yield prediction using predictive analytic techniques," in 2016 2nd International Conference on Contemporary Computing and Informatics (IC3I), pp. 783-788, Dec 2016.
[15] L. Dan, C. Xin, H. Chongwei and J. Liangliang, "Intelligent Agriculture Greenhouse Environment Monitoring System Based on IOT Technology," in 2015 International Conference on Intelligent Transportation, Big Data and Smart City, pp. 487-490, Dec 2015.
[16] S. B. Saraf and D. H. Gawali, "IoT based smart irrigation monitoring and controlling system," in 2017 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT), pp. 815-819, May 2017.
[17] D. Trancă, F. Stancu, R. Rughinis and D. Rosner, "SiloSense: ZigBee-based wireless measurement system architecture for agriculture parameter monitoring," in 2017 4th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 0330-0335, Apr 2017.
[18] “ZigBee,” http://www.zigbee.org/, accessed: 2019-7-22
[19] C. Yoon, M. Huh, S. Kang, J. Park and C. Lee, "Implement smart farm with IoT technology," in 2018 20th International Conference on Advanced Communication Technology (ICACT), pp. 749-752, Feb 2018.
[20] D. Davcev, K. Mitreski, S. Trajkovic, V. Nikolovski and N. Koteli, "IoT agriculture system based on LoRaWAN," in 2018 14th IEEE International Workshop on Factory Communication Systems (WFCS), pp. 1-4, June 2018.
[21] D. Ilie-Ablachim, G. C. Pătru, I. Florea and D. Rosner, "Monitoring device for culture substrate growth parameters for precision agriculture: Acronym: MoniSen," in 2016 15th RoEduNet Conference: Networking in Education and Research, pp. 1-7, Sep 2016.
[22] D. A. Pramuditya, A. N. Jati and F. Azmi, "Kufarm: A Modified Platform of Automation Planting System," in 2018 5th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), pp. 208-213, Sep 2018.
[23] R. Jauhari, A. N. Jati and F. Azmi, "Mechanical design of CNC for general farming automation," in 2017 5th International Conference on Instrumentation, Control, and Automation (ICA), pp. 47-50, Aug 2017.
[24] M. I. Sani, S. Siregar, A. P. Kumiawan, R. Jauhari and C. N. Mandalahi, "Web-based monitoring and control system for aeroponics growing chamber," in 2016 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC), pp. 162-168, Sep 2016.
[25] X. Fan, Y. Wang, C. Wu and H. Liu, "Research of Soil Moisture Content Forecast Model Based on Reference Evapotranspiration in Neighboring Periods," in 2018 7th International Conference on Agro-geoinformatics (Agro-geoinformatics), pp. 1-6, Aug 2018.
[26] H. Nie, L. Yang, X. Li, L. Ren, J. Xu and Y. Feng, "Spatial Prediction of Soil Moisture Content in Winter Wheat Based on Machine Learning Model," in 2018 26th International Conference on Geoinformatics, pp. 1-6, June 2018.
[27] “Modbus,” http://en.wikipedia.org/wiki/Modbus, accessed: 2019-7-22
[28] “LinkIt 7697,” [Online]. https://labs.mediatek.com/en/platform/linkit-7697, accessed: 2019-7-22
[29] “RS-485,” https://zh.wikipedia.org/wiki/EIA-485, accessed: 2019-7-22
[30] “MEC-10,” http://www.infwin.com/manage_zheqin/ewebeditor5_5/attachment/20170718114523993.pdf, accessed: 2019-7-22
[31] “RS-GZ-N01,” http://save.jnrsmcu.com/%E8%8B%B1%E6%96%87%E8%B5%84%E6%96%99/Light%20intensity%20transmitter%EF%BC%88Type485%E3%80%810-65535lux%EF%BC%89.pdf, accessed: 2019-7-22
[32] “Raspberry Pi3,” https://www.raspberrypi.org/products/raspberry-pi-3-model-b/, accessed: 2019-7-22
[33] Acsip, “EK-S76SXB,” http://www.acsip.com.tw/index.php?action=products-detail&fid1=21&fid2=&fid3=&id=73, accessed: 2019-7-22
[34] “The LoRa P2P water meter,” http://en.ems.com.tw/, accessed: 2019-7-22