台灣的農業在經濟中起著重要作用。由於人口爆炸，可用於農業的土地急劇減少。通過選擇適當的作物和種植模式來利用可用土地是非常必要的。可以通過分析來自工廠狀態的數據來完成預測。機器學習是一種技術，通過該技術，可以基於通過對過去的輸入數據及其輸出行為進行訓練而準備的模型來預測結果。
在台灣，火龍果的正常生產期為6月至10月。經過這段時間後，陽光不充足，溫度低。它經常無法順利開花。只要11月到4月可以生產紅火龍果，價格就會翻倍。目前透過火龍果植物生長環境相關參數收集當作機器學習的輸入，來預測每一批火龍果花苞產出時間。未來可以透過補光技術，利用光感應來調節火龍果的生長周期。光補償技術的使用可以促進火龍果的早花期，提高開花質量，從而達到提高年產量的效果。我們選擇了五種機器學習算法來比較預測精度。並將獲得的結果與實際結果進行比較以計算精度，並且確定導致最大精度的算法。

Taiwan's agriculture plays an important role in the economy. Due to the population explosion, the land available for agriculture has decreased drastically. It is essential to utilize the available land by selecting the appropriate crop and planting pattern. The prediction can be done by analyzing the data from the state of the plant. Machine learning is a technique by which a result can be predicted based on a model prepared by training past input data and its output behavior.
In Taiwan, the normal production period of dragon fruit is from June to October. After this period of time, the sun is not enough and the temperature is low. It often fails to bloom smoothly. As long as the red dragon fruit can be produced from November to April, the price will double. At present, the collection of parameters related to the growth environment of the dragon fruit plant is used as an input to machine learning to predict the production time of each batch of dragon fruit. In the future, light-sensing can be used to adjust the growth cycle of dragon fruit through light-filling technology. The use of light compensation technology can promote the early flowering period of dragon fruit and improve the flowering quality, so as to achieve the effect of increasing annual output. We chose five machine learning algorithms to compare prediction accuracy. The results obtained are compared to the actual results to calculate the accuracy and determine the algorithm that results in the greatest precision.

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 work-------------------------------------4
2.1 Basic Concepts of Machine Learning---------------------4
2.2 Types of Machine Learning Algorithms-------------------5
2.2.1 Supervised Learning----------------------------------5
2.2.2 Unsupervised Learning--------------------------------6
2.2.3 Semi-Supervised Learning-----------------------------7
2.2.4 Reinforcement Learning-------------------------------7
2.2.5 Comparison of Machine Learning Algorithm Types-------8
2.3 Classification and Regression in Supervised Learning---8
2.3.1 Classification---------------------------------------9
2.3.2 Regression-------------------------------------------9
2.4 Common Regression Algorithm Under Supervised Learning--10
2.4.1 Multiple Linear Regression---------------------------10
2.4.2 Decision Tree Regression-----------------------------10
2.4.3 Support Vector Machine (SVM)-SVR---------------------12
2.4.4 Random Forest----------------------------------------13
2.4.5 K-Nearest Neighbors----------------------------------14
2.5 Related Works of Machine Learning Application in Agriculture--14
2.5.1 Crop Yield Prediction--------------------------------15
2.5.2 Soil Moisture Prediction-----------------------------16
2.5.3 Crop Disease Prediction------------------------------16
Chapter 3 System Design------------------------------------18
3.1 Data Collection System---------------------------------18
3.1.1 Hardware-related Components of Sensor Hubs-----------19
3.1.2 Sensor Hubs transmission protocol-Lora and LoraWAN---23
3.1.3 Data Collection System Architecture------------------27
3.2 Machine Learning Prediction System---------------------29
3.2.1 Raw Data---------------------------------------------31
3.2.2 Preprocess in Python---------------------------------31
3.2.3 Prediction Using Machine Learning Algorithms---------32
3.2.4 Prediction Parameters--------------------------------33
3.2.5 Evaluate Model Performance---------------------------34
3.3 Data Display Platform----------------------------------37
Chapter 4 Experiment and Result----------------------------41
4.1 Data Collection Environment----------------------------41
4.2 Feature Selection--------------------------------------44
4.3 Set model Parameters and Evaluate Model----------------46
Chapter 5 Conclusion and Future Works----------------------57
References-------------------------------------------------59

[1]Ericsson, “Ericsson mobility report,” White thesis, 2015.
[2]LoRa Alliance, “LoRaWAN specification,” Jul. 2016, Available: http://lora-alliance.org
[3]“Semtek,” [Online]. Available: https://www.semtech.com/technology/lora/what-is-lora
[4]SA AgroFly, High Precision Forecast with Agro Drones (UAV), 2016.
[5]A. Raorane, R. Kulkarni, "Data Mining: An effective tool for yield estimation in the agricultural sector", International Journal of Emerging Trends and Technology in Computer Science, vol. 1, no. 2, pp. 75-79, 2012.
[6]D. Ramesh, B. Vardhan, "Data mining techniques and applications to agricultural yield data", International Journal of Advanced Research in Computer and Communication Engineering, vol. 2, no. 9, pp. 3477-3480, 2013.
[7]“Supervised learning” [Online]. Available: https://en.wikipedia.org/wiki/Supervised_learning
[8]“3 Examples of Supervised Learning” [Online]. Available:
https://simplicable.com/new/supervised-learning
[9]“Unsupervised learning” [Online]. Available:
https://en.wikipedia.org/wiki/Unsupervised_learning
[10]“An easy introduction to unsupervised learning with 4 basic techniques” [Online]. Available:https://towardsdatascience.com/an-easy-introduction-to-unsupervised-learning-with-4-basic-techniques-897cb81979fd
[11]“Semi-supervised learning” [Online]. Available:
https://en.wikipedia.org/wiki/Semi-supervised_learning
[12]“Semi-Supervised Machine Learning” [Online]. Available:
https://en.wikipedia.org/wiki/Reinforcement_learning
[13]“Reinforcement learning” [Online]. Available:
https://en.wikipedia.org/wiki/Reinforcement_learning
[14]“Reinforcement learning” [Online]. Available:
https://www.chessprogramming.org/Reinforcement_Learning
[15]“Machine Learning Algorithms Comparison” [Online]. Available:
https://medium.com/fintechexplained/machine-learning-algorithm-comparison-f14ce372b855
[16]“Machine Learning Algorithm - Backbone of emerging technologies” [Online]. Available:https://www.techleer.com/articles/203-machine-learning-algorithm-backbone-of-emerging technologies/?fbclid=IwAR3E2OwgQkSfza_aL_Tl4SfOufpKOD6zl1LPKMbBGa6Jq9Smz91qFueLoII
[17]“Statistical classification” [Online]. Available:
https://en.wikipedia.org/wiki/Statistical_classification
[18]“Classification - Machine Learning” [Online]. Available:
https://www.simplilearn.com/classification-machine-learning-tutorial
[19]“Regression in Machine Learning” [Online]. Available:
https://medium.com/datadriveninvestor/regression-in-machine-learning-296caae933ec
[20]“Regression - Machine Learning” [Online]. Available:
https://www.simplilearn.com/regression-machine-learning-tutorial
[21]“Multiple linear regression” [Online]. Available:
https://en.wikiversity.org/wiki/Multiple_linear_regression
[22]“Multiple Linear Regression Example” [Online]. Available:
https://ismayc.github.io/teaching/sample_problems/mlr.html
[23]“Decision tree learning” [Online]. Available:
https://en.wikipedia.org/wiki/Decision_tree_learning
[24]“CLASSIFICATION AND REGRESSION TREES” [Online]. Available:
https://www.oreilly.com/library/view/making-sense-of/9780470074718/ch7-sec020.html
[25]“Support-vector machine” [Online]. Available:
https://en.wikipedia.org/wiki/Support-vector_machine
[26]“Support Vector Machine - Regression (SVR)” [Online]. Available:
https://www.saedsayad.com/support_vector_machine_reg.htm
[27]“Random forest” [Online]. Available:
https://en.wikipedia.org/wiki/Random_forest
[28]C. Jennings, D. Wu, J. Terpenny, "Forecasting obsolescence risk and product life cycle with machine learning", IEEE TRansactions on Components Packaging and Manufacturing Technology, vol. 6, no. 9, pp. 1428-1439, 2016.
[29]W. Lin, Z. Wu, L. Lin, A. Wen, J. Li, "An ensemble random forest algorithm for insurance big data analysis", IEEE Access, vol. 5, pp. 16568-16575, 2017.
[30]“k-nearest neighbors algorithm” [Online]. Available:
https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm
[31]“K-Nearest Neighbors Algorithm for Regression” [Online]. Available:
https://www.analyticsvidhya.com/blog/2018/08/k-nearest-neighbor-introduction-regression-python/
[32]S. Bhanumathi , M. Vineeth , N. Rohit “Crop Yield Prediction and Efficient use of Fertilizers” 2019 International Conference on Communication and Signal Processing (ICCSP) ,2019.
[33]Niketa Gandhi et al., "Rice Crop Yield Forecasting of Tropical Wet and Dry Climatic Zone of India Using Data Mining Techniques", IEEE International Conference on Advances in Computer Applications (ICACA), 2016.
[34]K. E. Eswari, L. Vinitha, "Crop Yield Prediction in Tamil Nadu Using Baysian Network", International Journal of Intellectual Advancements and Research in Engineering Computations, vol. 6, no. 2, ISSN 2348-2079.
[35]Anna Chlingaryana, Salah Sukkarieha, Brett Whelanb, "Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review" in Computers and Electronics in Agriculture, Elisver, vol. 151, no. 2018, pp. 61-69, 2018.
[36]Dakshayini Patil et al., "Rice Crop Yield Prediction using Data Mining Techniques:An Overview", International Journal of Advanced Research in Computer Science and Software Engineering, vol. 7, no. 5, May 2017.
[37]Shikha Prakash ,Animesh Sharma ,Sitanshu Shekhar Sahu “Soil Moisture Prediction Using Machine Learning”, 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), pp.1-6, 2018.
[38]N Hemageetha, "A survey on application of data mining techniques to analyze the soil for agricultural purpose", Computing for Sustainable Global Development (INDIAcom) 3rd International Conference on IEEE, 2016.
[39]Luca Pasolli, Claudia Notarnicola, Lorenzo Bruzzone, "Estimating soil moisture with the support vector regression technique", IEEE geoscience and remote sensing letters, vol. 8, no. 6, November 2011.
[40]Daniel L Elliott, Russell E. Valentine, "Recurrent neural networks for moisture content prediction in seed corn dryer buildings", Tools with Artificial Intelligence (ICTAI) 23rd IEEE International Conference on IEEE, 2011.
[41]Supriya S. Shinde ; Mayura Kulkarni “Review Thesis on Prediction of Crop Disease Using IoT and Machine Learning”,2017 International Conference on Transforming Engineering Education (ICTEE), pp.1-4, 2017.
[42]D. Ashourloo, H. Aghighi, A. Matkan, M. Mobasheri, A. Rad, "An Investigation Into Machine Learning Regression Techniques for the Leaf Rust Disease Detection Using Hyperspectral Measurement", IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 9, no. 9, pp. 4344-4351, Sept 2016.
[43]J. Zhang, R. Pu, L. Yuan, W. Huang, C. Nie, G. Yang, "Integrating Remotely Sensed and Meteorological Observations to Forecast Wheat Powdery Mildew at a Regional Scale", IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 7, no. 11, pp. 4328-4339, Nov 2014.
[44]N. Schor, A. Bechar, T. Ignat, A. Dombrovsky, Y. Elad, S. Berman, "Robotic Disease Detection in Greenhouses: Combined Detection of Powdery Mildew and Tomato Spotted Wilt Virus", IEEE Robotics and Automation Letters, vol. 1, no. 1, pp. 354-360, Jan 2016.
[45]“LinkIt 7697,” [Online]. Available: https://labs.mediatek.com/en/platform/linkit-7697
[46]“Gemtek,” [Online]. Available: https://www.gemteks.com/en/products/lora-iot
[47]Alexandru Lavric; Valentin Popa “Internet of Things and LoRa™ Low-Power Wide-Area Networks: A survey”, 2017 International Symposium on Signals, Circuits and Systems (ISSCS), pp.1-5, 2017.
[48]Usman Raza; Parag Kulkarni; Mahesh Sooriyabandara “Low Power Wide Area Networks: An Overview”, IEEE Communications Surveys & Tutorials, vol.19, no.2, pp.855-873, 2017.
[49]“Modbus” [Online]. Available: https://en.wikipedia.org/wiki/Modbus
[50]“Supervised vs. Unsupervised Learning” [Online]. Available:
https://towardsdatascience.com/supervised-vs-unsupervised-learning-14f68e32ea8d
[51]“Model Fit: Underfitting vs. Overfitting” [Online]. Available:
https://docs.aws.amazon.com/machine-learning/latest/dg/model-fit-underfitting-vs-overfitting.html
[52]“Cross-validation (statistics)” [Online]. Available:
https://en.wikipedia.org/wiki/Cross-validation_(statistics)
[53]“[Day29] Machine Learning: Cross Validation!” [Online]. Available:
https://ithelp.ithome.com.tw/articles/10197461