臺灣博碩士論文加值系統

隨著海洋受到環境變遷、過度捕撈與汙染，漁獲量逐漸減少，在食物短缺的情況下，水產養殖業成為未來趨勢產業。台灣過去曾產出8萬多公噸的草蝦，得到「草蝦王國」稱號，卻在幾年後受草蝦病毒及白點病毒接連影響，重創台灣養殖產業。而白蝦的引進取代草蝦，成為國內養殖重點，但仍受蝦疾病影響，近年產量平均約10,000公噸，與以往的盛況相差甚大。蝦疾病不僅帶來高死亡率，也可能因養殖業者濫用藥物產生抗藥性，使得水試所與畜試所共同執行白蝦繁殖與養殖之計畫，為了解決白蝦養殖產業的問題。
傳統養蝦模式仰賴農民經驗，蝦類病變、水質汙染及養殖技術缺乏是白蝦養殖最大的問題點。工廠化養殖解決傳統養蝦問題，卻因建置成本龐大，並非小農能夠負擔，也擔憂會被大企業給壟斷市場，在台灣多數是小農之情況下，是一大隱憂。資訊科技快速發展，各產業朝向智慧化時代前進，IoT與AI應用於水產業之養殖模式已成未來趨勢，因此本研究以白蝦養殖為例，建置物聯網水產養殖平台與深度學習預測模型，透過自動監控及預測水質狀況，更能有效進行水質管理，進而維護水產品之生長環境。

The ocean is affected by environmental changes, overfishing, and pollution. Total fish production in the capture fishery industry is gradually decreasing. The aquaculture industry has thus become the trend to address food shortages. In the past, Taiwan produced more than 80,000 tons of grass shrimp and was called the "Grass Shrimp Kingdom." However, several years later, the industry was affected by a grass shrimp virus and the white spot virus, which was a strong blow to the aquaculture industry in Taiwan. Whiteleg shrimp was introduced to replace grass shrimp and became the focus of domestic aquaculture, but it is still affected by shrimp diseases. Shrimp diseases not only cause mortality, but also may lead to drug resistance because of excessive use of pesticides. As a result, the Fisheries Research Institute and Livestock Research Institute are cooperating with the whiteleg shrimp breeding and farming plan.
With the rapid development of information technology and the technological advancement of many industries, the application of the Internet of Things and artificial intelligence in the aquaculture industry has become a trend. Therefore, in this study, whiteleg shrimp farming is used as an example to construct an IoT aquaculture platform and a deep learning predictive model. Through automatic monitoring and forecasting of water quality status, management of water quality will become more effective, and the growth environment of aquatic animals will be maintained.

摘要 I
目錄 X
圖目錄 XIII
表目錄 XV
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 4
1.3 研究流程 5
第二章 文獻探討 6
2.1 物聯網之應用 6
2.2 預測模型 7
2.2.1 統計預測模型 7
2.2.1.1 自回歸移動平均模型(ARMA) 7
2.2.1.2 自回歸整合移動平均模型(ARIMA) 7
2.2.2 類神經網路(ANN) 8
2.2.2.1 遞歸神經網路(RNN) 9
2.2.2.2 長短期記憶模型(LSTM) 10
2.3 田口方法 11
2.4 本章總結 12
第三章 研究方法 13
3.1 研究範圍 13
3.2 研究架構 14
3.2.1 了解養殖流程與辨識問題 15
3.2.2 訂定解決方案之目標 17
3.2.3 系統開發與設計 17
3.2.4 建置深度學習模型 17
3.2.4.1 商業理解 17
3.2.4.2 資料理解 17
3.2.4.3 資料準備 17
3.2.4.4 模型開發 18
3.2.4.5 評估模型 18
3.2.4.6 部署 18
3.3 系統架構 19
3.4 系統建置流程 20
3.4.1 平台架設與設計 21
3.4.2 感測器之設置規劃與連接 22
3.4.3 系統測試與修正 22
3.5 模型建置流程 22
3.5.1 模型架構 22
3.5.2 模型參數設定 23
3.5.3 損失函數 27
第四章 研究結果 28
4.1 系統開發環境 28
4.1.1 硬體設備及作業系統 28
4.1.2 網站與模型開發工具 28
4.1.3 軟體架構 29
4.2 系統活動圖 30
4.2.1 查看水質監測數據之活動圖 31
4.2.2 新增水質檢測數據之活動圖 32
4.3 使用者操作說明 33
4.3.1 首頁 33
4.3.2 查看水質監測數據 34
4.3.3 新增水質檢測數據 35
4.4 預測模型 36
4.4.1 資料集 36
4.4.2 資料清理 37
4.4.3 資料正規化(Normalization) 38
4.4.4 模型實驗結果 40
4.4.4.1 長短期記憶模型 40
4.4.4.2 遞歸神經網路 44
4.4.4.3 LSTM與RNN之比較 48
4.5 成果討論 50
第五章 結論與建議 51
5.1 研究結論 51
5.2 研究限制與未來方向 52
參考文獻 54

丁雲源（2005）。白蝦養殖發展史。水產試驗所特刊第6號，3-4。

台灣趨勢研究（2019）。台灣智慧農業現況與需求：水產養殖業篇。取自http://www.twtrend.com/share_cont.php?id=73

行政院農業委員會漁業署（2019）。民國104年(2015)漁業統計年報。取自https://www.fa.gov.tw/cht/index.aspx

行政院農業委員會漁業署（2019）。民國105年(2016)漁業統計年報。取自https://www.fa.gov.tw/cht/index.aspx

行政院農業委員會漁業署（2020）。民國106年(2017)漁業統計年報。取自https://www.fa.gov.tw/cht/index.aspx

行政院農業委員會漁業署（2020）。民國107年(2018)漁業統計年報。取自https://www.fa.gov.tw/cht/index.aspx

行政院農業委員會漁業署（2020）。民國108年(2019)漁業統計年報。取自https://www.fa.gov.tw/cht/index.aspx

行政院農業委員會（2020）。養殖水產類-甲殼類臺灣良好農業規範(TGAP)。產銷履歷農產品資訊網。取自https://taft.coa.gov.tw/lp.asp?ctNode=276&CtUnit=80&BaseDSD=7&role=C

周信佑（2018）。我國水產養殖轉型發展新契機。農業科技決策資訊平台。取自https://agritech-foresight.atri.org.tw/article/contents/1619

郭仁杰（2005）。台灣白蝦養殖產業現況。水產試驗所特刊第6號，9-17。

陳獻（2005）。白蝦養殖工廠化企業管理。水產試驗所特刊第6號，167-174。

陳心瑜（2019）。探討水產養殖業應用區塊鏈之商業模式—以台灣鯛養殖為例。國立成功大學工業與資訊管理研究所碩士論文。
 
陳煦森、鄭金華、陳紫媖（2014）。環境因子對蝦類行為生態的影響。水試專訓，47，24-27。

楊金城（2018年6月1日）投資4億！全台最大漁電共生室內養殖場今啟用。自由時報。取自https://www.ltn.com.tw/

楊明樺、鄭金華、陳紫媖（2019）。白蝦生物安全繁養殖，有效提高育成率。農政視野，330，26-31。

薛月順（2010）。臺灣「草蝦王國」的形成（1968-1988）—政府與民間扮演的角色。國史館館刊，24，139-176。

Akyol, O., Özgül, A., Düzbastılar, F. O., Şen, H., Urbina, J. M. O. d., & Ceyhan, T. (2020). Influence of some physico-chemical variables on wild fish richness beneath sea-cage fish farms in the Aegean Sea, Turkey. Journal of the Marine Biological Association of the United Kingdom, 100(7), 1171-1179.

Badii, C., Bilotta, S., Cenni, D., Difino, A., Nesi, P., Paoli, I., & Paolucci, M. (2020). High Density Real-Time Air Quality Derived Services from IoT Networks. Sensors, 20(18), 5435.

Bradley, D., Merrifield, M., Miller, K. M., Lomonico, S., Wilson, J. R., & Gleason, M. G. (2019). Opportunities to improve fisheries management through innovative technology and advanced data systems. Fish and Fisheries, 20(3), 564-583.

Burke, M., Grant, J., Filgueira, R., & Stone, T. (2021). Oceanographic processes control dissolved oxygen variability at a commercial Atlantic salmon farm Application of a real-time sensor network. Aquaculture, 533, 736143.

Cao, W., Huan, J., Liu, C., Qin, Y., & Wu, F. (2019). A combined model of dissolved oxygen prediction in the pond based on multiple-factor analysis and multi-scale feature extraction. Aquacultural Engineering, 84, 50-59.

Cao, X., Liu, Y., Wang, J., Liu, C., & Duan, D. (2020). Prediction of dissolved oxygen in pond culture water based on K-means clustering and gated recurrent unit neural network. Aquacultural Engineering, 91, 102122.

Chiang, C.-T., Chen, T.-Y., & Wu, Y.-T. (2020). Design of a Water Salinity Difference Detector for Monitoring Instantaneous Salinity Changes in Aquaculture. IEEE Sensors Journal, 20(6), 3242-3248.

FAO. (2020). The State of World Fisheries and Aquaculture 2020. Retrieved December 7, 2020 from http://www.fao.org/documents/card/en/c/ca9229en.

Francisti, J., Balogh, Z., Reichel, J., Magdin, M., Koprda, Š., & Molnár, G. (2020). Application Experiences Using IoT Devices in Education. Applied Sciences, 10(20), 7286.

Gooijer, J. G. D., & Hyndman, R. J. (2006). 25 years of time series forecasting. International Journal of Forecasting, 22(3), 443-473.

Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780.

Huan, J., Li, H., Li, M., & Chen, B. (2020). Prediction of dissolved oxygen in aquaculture based on gradient boosting decision tree and long short-term memory network: A study of Chang Zhou fishery demonstration base, China. Computers and Electronics in Agriculture, 175, 105530.

Huan, J., Li, H., Wu, F., & Cao, W. (2020). Design of water quality monitoring system for aquaculture ponds based on NB-IoT. Aquacultural Engineering, 90, 102088.

Jiang, H., Chen, X., Bian, W., Fu, L., Qin, Q., Zhong, L., & Wang, M. (2020). Comparison of bacterial communities in channel catfish Ictalurus punctatus culture ponds of an industrial ecological purification recirculating aquaculture system. Aquaculture Research, 51(6), 2432-2442.

Kautsky, N., Ronnback, P., Tedengren, M., & Troell, M. (2000). Ecosystem perspectives on management of disease in shrimp pond farming. Aquaculture, 191(1-3), 145-161.

Lai, H.-C., Ng, T. H., Ando, M., Lee, C.-T., Chen, I-T., Chuang, J.-C., Mavichak, R., Chang, S.-H., Yeh, M.-D., Chiang, Y.-A., Takeyama, H., Hamaguchi, H.-o, Lo, C.-F., Aoki, T., & Wang, H.-C. (2015). Pathogenesis of acute hepatopancreatic necrosis disease (AHPND) in shrimp. Fish & Shellfish Immunology, 47(2), 1006-1014.
LeCun,, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436-444.

Lee, C., & Wang, Y.-J. (2020). Development of a cloud-based IoT monitoring system for Fish metabolism and activity in aquaponics. Aquaculture Engineering, 90, 102067.

Leff, A., & Rayfield, J. T. (2001, September). Web-application development using the model/view/controller design pattern. Paper presented at the Proceedings Fifth IEEE International Enterprise Distributed Object Computing Conference, Seattle.

Lin, C., & Lin, Yihsu. (2007). A cooperative inventory policy with deteriorating items for a two-echelon model. European Journal of Operational Research, 178(1), 92-111.

Lin, S.-J., Chen, Y.-F., Hsu, K.-C., Chen, Y.-L., Ko, T.-P., Lo, C.-F., Wang, H.-C., & Wang, H.-C. (2019). Structural Insights to the Heterotetrameric Interaction between the Vibrio parahaemolyticus PirAvp and PirBvp Toxins and Activation of the Cry-Like Pore-Forming Domain. Toxins, 11(4), 233.

Liu, G., & Guo, J. (2019). Bidirectional LSTM with attention mechanism and convolutional layer for text classification. Neurocomputing, 337, 325-338.

Liu, H.-P., Chuang, Y.-M., Liu, C.-H., Yang, P. C., & Fuh, C.-S. (2021). Precise Measurement of Physical Activities and High-Impact Motion: Feasibility of Smart Activity Sensor System. IEEE Sensors Journal, 21(1), 568-580.

Liu, Y., Zhang, Q., Song, L., & Chen, Y. (2019). Attention-based recurrent neural networks for accurate short-term and long-term dissolved oxygen prediction. Computers and Electronics in Agriculture, 165, 104964.

Moura, P. S. D., Wasielesky, W. J., Serra, F. D. P., Braga, A., & Poersch, L. (2021). Partial seawater inclusion to improve Litopenaeus vannamei performance in low salinity biofloc systems. Aquaculture, 531, 735905.

Sagheer, A., & Kotb, M. (2019). Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing, 323, 203-213.
 
Sengupta, S., Basak, S., Saikiab, P., Paul, S., Tsalavoutis, V., Atiah, F., Ravi, V., & Peters, A. (2020). A review of deep learning with special emphasis on architectures, applications and recent trends. Knowledge-Based Systems, 194, 105596.

Sezer, O. B., Gudelek, M. U. & Ozbayoglu, A. M. (2020). Financial time series forecasting with deep learning : A systematic literature review: 2005-2019. Applied Soft Computing Journal, 90, 106181.

Tacon, A. G. J., & Metian, M. (2013). Fish Matters: Importance of Aquatic Foods in Human Nutrition and Global Food Supply. Fisheries Science, 21(1), 22-38.

WHO. (2018). Air pollution and child health: prescribing clean air. Retrieved January 12, 2021 from https://www.who.int/publications/i/item/air-pollution-and-child-health.

Wirth, R. & Hipp, J. (2000). CRISP-DM: Towards a standard process model for data mining. Proceedings of the Fourth International Conference on the Practical Application of Knowledge Discovery and Data Mining, Manchester, United Kingdom, 29-39.

Xing, Y.-F., Xu, Y.-H. Shi, M.-H., & Lian, Y.-X. (2016). The impact of PM2.5 on the human respiratory system. Journal of Thoracic Disease, 8(1), E69-E74.

Yang , X., Zhang, S., Liu, J., Gao, Q., Dong, S., & Zhou, C. (2020). Deep learning for smart fish farming: applications, opportunities and challenges. Reviews in aquaculture, 13(1), 66-90.

Yu, Q., Xie, J., Huang, M., Chen, C., Qian, D., Qin, J. G., Chen, L., Jia, Y., & Li, E. (2020). Growth and health responses to a long-term pH stress in Pacific white shrimp Litopenaeus vannamei. Aquaculture Reports, 16, 100280.

Yu, Y., Si, Y., Hu, C., & Zhang, J. (2019). A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures. Neural Computation, 31(7), 1235-1270.

Zhao , R., Yan, R., Chen, Z., Mao, K., Wang, P., & Gao, R. X. (2019). Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 115, 213-237.