台灣養殖業已經佔了非常重的比重，但養殖漁業發展均已產量提高為主要目的，但產業結構的重大關鍵是勞動人力短缺與從業人員老齡化，在飼養上方式則仍以傳統經驗的養殖方式，造成水質循環生態破壞常見的是水產養殖造成養殖水質優養化，讓使水中的含氧量減少，棲息的魚群窒息死亡，自然生態無法平衡，對周邊水域環境與生態會產生相當的危害與衝擊。低機械化及自動化使整體產業鏈智慧化程度有限，無法有效、穩定提升產能與品質，這也使得飼養過程中的相關生產與環境紀錄難以全面性建立，不利於建構生長管理或追蹤追溯體系。
政府提供檢測水質優養化的指標為卡爾森指數(Carlson Trophic State Index , CTSI)，必須計算水質的總磷量、葉綠素a、透明度，但在養殖業者中，取得總磷量及葉綠素a並不容易，必須購買昂貴的儀器，或者採樣給檢測中心代辦，無論如何皆是價格昂貴，費時而無法即時得知，導致大多數業者並無法明確解決水質優養化問題。
我們提供的系統可以幫助業者掌握水質狀況，提供即時監控pH、溫度、導電度、濁度、氧化還原，實現各項感測器功能整合，使養殖業者能夠一目瞭然，並能夠利用現有的感測器預估卡爾森指數，取代必須採樣的水質參數(透明度、葉綠素a、總磷)，使養殖業者容易判斷水質優養化發生程度，並能依照不同生物環境，找出養殖水與水質優養化發生關係，依循關係的變化，使業者容易尋找出不同生物臨界值，如此一來，就能幫助魚場管理人員做危機處理，提升妨害效益及反應效率，避免水資源過度替換、節省檢測成本昂貴費用及藥物濫用，才能達成穩定成長及永續發展。

However, deterioration of water quality and biological diseases are some of major factors that affect the number and growth of fish. To deal with those problems, fish farms often increase the rate of circulation of fresh water. As the result, excessive pumping underground water, not only leads to increase of costs, but also land subsidence. In addition, most of Taiwan’s aquaculture farms relied on their experience to decide on when to exchange water in their ponds. This is often not very effective in terms of increase the quality and quantity of their products.
To represent the water quality, Carlson Trophic State Index (CTSI) is most commonly used index by many countries’ Environmental Protection Agency. In order to get a CTSI, water need to be sent to lab to measure its Secchi Depth (SD), Chlorophyll-a (Chl-a), and total Phosphorus (TP). Therefore, it is impossible to provide a real-time CTSI of water quality to assist aquaculture farms. To estimate the CTSI value in real-time, we explore the possibility of using Multivariate Adaptive Regression Splines (MARS) model with variables (i.e., Total Dissolved Solids (TDS), Electric Conductivity (EC), pH, and Temperature) observed by water sensors.
In this paper, we propose a Real-Time Monitoring System for Aquaculture to assistance the aquaculture industries by monitor water quality in their fish ponds. The water quality is observed by number of sensors. The observed results are transmitted wirelessly to our system for further analysis to provide the water quality index such as CTSI. Our experiment results showed our system has high accuracy of predicted CTSI value with estimation error less then 4%. Based on our estimated CTSI, aquaculture farmers no longer need guess when to change water for their fish ponds. With our proposed system, aquaculture industries can monitor the degree of water eutrophication in real-time, reduce the waste of water resource, and increase their fish growth.

[1] T. V. Suslow. "Oxidation-Reduction Potential for Water Disinfection Monitoring, Control, and Documentation," in University Of California Division Of Agriculture And Natural Resources, 2004.
[2] V. H. Smith. "Eutrophication of Freshwater and Coastal Marine Ecosystems: A Global Problem," Environmental Science and Pollution Research, vol.10, no.2, pp.126-139, 2003.
[3] L. Yu and W. Li. "Cause Analysis Eutrophication of Water Sources in Winter," IEEE International Conference on Computer Distributed Control and Intelligent Environmental Monitoring, 2011.
[4] V. H. Smith and D. W. Schindler. "Eutrophication Science: Where Do We Go From Here?" in Trends in ecology & evolution, vol.24, pp.201-207, 2009.
[5] Z. Andrea, B. Nicola, C. Angelo, V. Lorenzo, and Z. Michele. "Internet of Things for Smart Cities," IEEE Internet of Things Journal, vol.1, no.1, 2014.
[6] X. Chen, X. Liu, and P. Xu. "IoT-Based Air Pollution Monitoring and Forecasting System," IEEE International Conference on Computer and Computational Sciences, 2015.
[7] G. Nader and B. Kamel. "Small Satellite and Multi-Sensor Network for Real Time Control and Analysis of Lakes Surface Waters," Recent Advances in Space Technologies, 2013.
[8] F. Halal, P. Pedrocca, and T. Hirose. "Remote-Sensing Based Adaptive Path Planning for an Aquatic Platform to Monitor Water Quality," IEEE International Symposium on Robotic and Sensors Environments, 2014.
[9] S. Vashi and J. Ram. "Internet of Things (Iot): A Vision, Architectural Elements, and Security Issues," IEEE International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), 2017.
[10] Z. Morteza and L. Hadi. "A Survey on Centralised and Distributed Clustering Routing Algorithms for WSNs," IEEE 81st Vehicular Technology Conference (VTC Spring), 2015.
[11] S. M. Saad, A. R. M. Saad, A. M. Y. Kamarudin, A. Zakaria, and A. Y. M. Shakaff. "Indoor Air Quality Monitoring System Using Wireless Sensor Network (WSN) with Web Interface," IEEE International Conference on Electrical, Electronic and System Engineering, 2013.
[12] S. N. Kumar and M. S. Chandra. "Wireless Sensor Network Based Home Monitoring System for Wellness Determination of Elderly," IEEE Sensors Journal, vol.12, no.6, 2012.
[13] M. R. Kannan, D. M. Kaimal, and M. V. Ramesh. "Efficient Patient Monitoring for Multiple Patients Using WSN," Mobile Network, Communication and its Applications (MNCAPPS), 2012.
[14] N. Nidal, A. Asmaa, K. Lutful, and B. Samir. "An Efficient Wireless Sensor Network-based Water Quality Monitoring System," Computer Systems and Applications (AICCSA), 2013.
[15] A. Alkandari , M. Alnasheet, Y. Alabduljader, and S. M. Moein. "Water Monitoring System Using Wireless Sensor Network (WSN): Case Study of Kuwait Beaches," Digital Information Processing and Communications (ICDIPC), 2012.
[16] G. Valkanas, A. Kotsifakos, D. Gunopulos, I. Galpin, A. J. G. Gray, A. A. A. Fernandes, and N. W. Paton. "Deploying In-Network Data Analysis Techniques in Sensor Networks," IEEE 12th International Conference on Mobile Data Management, 2011.
[17] L. Li and B. Fan. "Analysis of Data Fusion in Wireless Sensor Networks," IEEE　International Conference on Electronics, Communications and Control, 2011.
[18] G. R. Abuaitah and B. Wang. "Data-Centric Anomalies in Sensor Network Deployments: Analysis and Detection," IEEE 9th International Conference on Mobile Ad-Hoc and Sensor Systems (MASS), 2012.
[19] B. Liu, O. Dousse, P. Nain, and D. Towsley. "Dynamic Coverage of Mobile Sensor Networks," IEEE Transactions on Parallel and Distributed Systems, vol. 24, pp. 301-311, 2013.
[20] A. Manjeshwar and D.P. Agrawal. "TEEN: A Routing Protocol for Enhanced Efficiency in Wireless Sensor Networks," IEEE 15th International Symposium on Parallel and Distributed Processing, 2015.
[21] M. M. Zanjireh, H. Larijani, and W. O. Popoola. "Energy Based Analytical Modelling of ANCH Clustering Algorithm for Wireless Sensor Networks," International Journal on Advances in Networks and Services, vol. 7, no. 3&4, pp. 173-182, 2014.
[22] S. Fedor and M. Collier. "On the Problem of Energy Efficiency of Multi-Hop vs One-Hop Routing in Wireless Sensor Networks," IEEE 21st International Conference on Advanced Information Networking and Applications Workshops, 2007.
[23] 植根法律網：水體透明度測定方法,Available : http://www.rootlaw.com.tw/LawArticle.aspx?LawID=A040300081013500-0870611.
[24] 植根法律網：水中葉綠素a檢測方法-丙酮萃取/螢光分析法，Available : http://www.rootlaw.com.tw/LawArticle.aspx?LawID=A040300081047700-0990515.
[25] 植根法律網：水中磷檢測方法-維生素丙比色法，Available : http://www.rootlaw.com.tw/LawArticle.aspx?LawID=A040300081031500-0830309.
[26] J. H. Friedman. "Multivariate Adaptive Regression Splines," The annals of statistics, vol.19, no.1, pp.1-141, 1991.
[27] W. Zhang and A. T. C. Goh. "Multivariate Adaptive Regression Splines and Neural Network Models for Prediction of Pile Drivability," Geoscience Frontiers, vol.7, no.1, pp45-52, 2016.
[28] G. Nieto and P. José. "Using Evolutionary Multivariate Adaptive Regression Splines Approach to Evaluate The Eutrophication in The Pozón De La Dolores Lake (Northern Spain)," Ecological Engineering, vol.94, pp136-151, 2016.