本論文模擬智慧農業(Digital Agriculture)中之智慧漁場(Intelligent fish farm)環境，利用架設物聯網感測器蒐集漁場中之水質環境資料，並以收集資料進行分佈值變數之預處理及分析。首先，以物聯網感測器置入模擬漁場環境水缸，測定水中總溶解固體(Total Dissolved Solids)、導電度(Electrical conductivity)、氫離子濃度指數(pH)、氧化還原電位(Oxidation-Reduction Potential)與攝氏溫度(The degree Celsius)，依據固定時間透過無線網路(Wi-Fi)傳輸資料至雲端，而收集資料經過預處理，再進行資料型態轉換為分佈值變數。其次，使用符號相似傳播算法(the Symbol Affinity Propagation)將分佈變量進行比較，通過將其轉換為分位函數並計算新的負歐氏距離矩陣。這個相似度矩陣衡量了新的分布變量之間的相似度。通過更新相似度和優選度，符號相似傳播算法生成具有特定群組數量的簇。這種分析有助於識別大規模數據之間的相關性，並在後續的預測參考中提供幫助。最後，利用具有指定分群數的直覺模糊集增強多樣本相似傳播算法作與研究中收集到巨量資料作為基礎，開發一種直覺模糊鄰近傳播分群，藉由使用直覺模糊集作為濾波器來更新相似度，分析巨量資料間之關聯性，用以輔助後續預測參考。

This thesis simulates the environment of an intelligent fish farm in digital agriculture by setting up IoT sensors to collect water quality data in the fish farm. The collected data is preprocessed and analyzed using distribution variable transformation. Firstly, IoT sensors are placed in a simulated fish tank environment to measure Total Dissolved Solids, Electrical Conductivity, pH, Oxidation-Reduction Potential, and Celsius temperature. Data is transmitted to the cloud via Wi-Fi at fixed intervals, and the collected data is preprocessed and converted into distribution variables. Secondly, the Symbol Affinity Propagation algorithm is employed to compare the distributional variables by transforming them into quantile functions and calculating the new Euclidean distance matrix. This similarity matrix measures the similarity between new distributional variables. By updating the similarity and preference, the Symbol Affinity Propagation algorithm generates clusters with a specific number of groups. This analysis helps identify correlations among large-scale data and assists in subsequent predictive references. Finally, this research develop an Intuitionistic fuzzy set Enhanced Multiple Exemplars Affinity Propagation algorithm with Specified K Clusters. It utilizes the collected large-scale data as the base and employs Intuitionistic fuzzy set as filters to update similarity. This approach overcomes the issue of the algorithm identifying excessive clustering situations where values are similar but differ significantly.

摘要.................................................. i
Abstract.............................................. iii
Acknowledgements...................................... v
Table of contents..................................... vi
List of Tables........................................ viii
List of Figures....................................... ix
Chapter 1 Introduction................................ 1
1.1 Review of Digital Agriculture................. 1
1.2 Review of Intelligent fish farm............... 3
1.3 Sensors....................................... 5
1.4 Review of the Internet of Things (IoT)........ 6
1.5 Review of Big Data............................ 8
1.6 Review of the Symbolic Data Analysis (SDA).... 11
1.7 Review of Clustering.......................... 12
1.8 Review of Intuitionistic Fuzzy Set (IFS)...... 14
1.9 Motivations and Contributions................. 16
1.10 Organization of This Thesis................... 18
Chapter 2 Mathematical Background..................... 19
2.1 Cumulative Density Function (CDF)............. 19
2.2 AP............................................ 21
2.3 Multiple Exemplars Affinity Propagation with Specified K Clusters
............................................ 24
2.4 IFS......................................... 30
Chapter 3 Sensors, IoT, Platform Building and Data Visualization
............................................ 32
3.1 System Architecture......................... 32
3.2 Sensors..................................... 37
3.3 IoT......................................... 40
3.4 ELK Big Data Platform....................... 42
3.5 Thingspeak and MATLAB....................... 52
3.6 Visualization of Data....................... 53
3.7 Discussion and Conclude Remarks............. 81
Chapter 4 The DAP and K-MEAP for Water Quality Data Analysis
............................................ 83
4.1 Detail of DAP............................... 83
4.2 Detail of D-K-MEAP.......................... 87
4.3 Results of DAP and D-K-MEAP................. 90
4.4 Discussion and Conclude Remarks............. 94
Chapter 5 IFS Enhanced K-MEAP for Water Quality Data Analysis
............................................ 96
5.1 Detail of IFS-D-K-MEAP...................... 96
5.2 Result of IFS-D-K-MEAP...................... 104
5.3 Discussion and Conclude Remarks............. 109
Chapter 6 Conclusion and Future Works............... 111
6.1 Conclusion.................................. 111
6.2 Future Works................................ 113
References.......................................... 115
Extended Abstract................................... 123

[1]S. A. Bhat and N. -F. Huang, "Big Data and AI Revolution in Precision Agriculture: Survey and Challenges," in IEEE Access, vol. 9, pp. 110209-110222, 2021, DOI: 10.1109/ACCESS.2021.3102227.
[2]W. -C. Hu, L. -B. Chen, B. -K. Huang and H. -M. Lin, "A Computer Vision-Based Intelligent Fish Feeding System Using Deep Learning Techniques for Aquaculture," in IEEE Sensors Journal, vol. 22, no. 7, pp. 7185-7194, 1 April1, 2022, DOI: 10.1109/JSEN.2022.3151777.
[3]"IEEE Standard for Sensor Performance Parameter Definitions," in IEEE Std 2700-2014, pp.1-69, 12 Aug. 2014, DOI: 10.1109/IEEESTD.2014.6880296.
[4]E. Diday, "Explanatory Tools for Machine Learning in the Symbolic Data Analysis Framework," in Advances in Data Science: Symbolic, Complex, and Network Data, Wiley, 2020, ch. 1, pp. 1-30, DOI: 10.1002/9781119695110.ch1.
[5]B.J. Frey and D. Dueck, "Clustering by Passing Messages between Data Points," in Science, Feb. 2007. DOI: 10.1126/science.1136800
[6]C. -D. Wang, J. -H. Lai, C. Y. Suen and J. -Y. Zhu, "Multi-Exemplar Affinity Propagation," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 9, pp. 2223-2237, Sept. 2013, doi: 10.1109/TPAMI.2013.28.
[7]J. M. Keller, M. R. Gray, and J. A. Givens, "A Fuzzy K-nearest Neighbor Algorithm," in IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-15, no. 4, Jul.-Aug. 1985, pp. 580-585, DOI: 10.1109/TSMC.1985.6313426.
[8]X. Zhang, W. Wang, K. Nørvåg and M. Sebag, "K-AP: Generating Specified K Clusters by Efficient Affinity Propagation," 2010 IEEE International Conference on Data Mining, Sydney, NSW, Australia, 2010, pp. 1187-1192, DOI: 10.1109/ICDM.2010.107.
[9]Y. Wang and L. Chen, "K-MEAP: Generating Specified K Clusters with Multiple Exemplars by Efficient Affinity Propagation," 2014 IEEE International Conference on Data Mining, Shenzhen, China, 2014, pp. 1091-1096, DOI: 10.1109/ICDM.2014.54.
[10]A. H. Nuttall, "Numerical Evaluation of Cumulative Probability Distribution Functions Directly from Characteristic Functions," in Proceedings of the IEEE, vol. 57, no. 11, Nov. 1969, pp. 2071-2072, DOI: 10.1109/PROC.1969.7468.
[11]L. Billard, "Symbolic Data Analysis: What Is It?," in Compstat 2006 - Proceedings in Computational Statistics, 2006, pp. 261-269, 2006.
[12]P C Mahalanobis, "On the Generalized Distance in Statistics," Proceedings of the National Institute of Sciences of India, 2, 49–55, 1936, India, 1936.
[13]H. -H. Bock and E. Diday, Analysis of Symbolic Data, 2000.
[14]P. Bertrand and F. Goupil, "Descriptive Statistics for Symbolic Data," in Analysis of Symbolic Data, pp. 106-124, 2000.
[15]L. Billard, "Dependencies and Variation, Components of Symbolic Interval-Valued Data," in Data Analysis and Classification. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg, 2023. DOI: 10.1007/978-3-540-73560-1_1
[16]F. d. A. T. de Carvalho and Y. Lechevallier, "Dynamic Clustering of Interval-Valued Data Based on Adaptive Quadratic Distances," in IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, vol. 39, no. 6, pp. 1295-1306, Nov. 2009, doi: 10.1109/TSMCA.2009.2030167.
[17]"Cloud service platform," thingspeak.com.
[18]"Environmental Protection Administration Environmental Resource Database," erdb.epa.gov.tw.
[19]K. Joslyn and J. Lipor, "A Supervised Learning Approach to Water Quality Parameter Prediction and Fault Detection," in 2018 IEEE International Conference on Big Data, pp. 2511-2514, 2018. DOI: 10.1109/BigData.2018.8622628.
[20]X. Zhang, W. Wang, K. Nørvåg, and M. Sebag, "K-AP: Generating Specified K Clusters by Efficient Affinity Propagation," in 2010 IEEE International Conference on Data Mining, pp. 1187-1192, 2010 DOI: 10.1109/ICDM.2010.107.
[21]G. Kang, J. Z. Gao, and G. Xie, "Data-Driven Water Quality Analysis and Prediction: A Survey," in 2017 IEEE Third International Conference on Big Data Computing Service and Applications, pp. 224-232, 2017 DOI: 10.1109/BigDataService.2017.40.
[22]C. Qi, S. Huang, and X. Wang, "Monitoring Water Quality Parameters of Taihu Lake Based on Remote Sensing Images and LSTM-RNN," in IEEE Access, vol. 8, pp. 188068-188081, 2020 DOI: 10.1109/ACCESS.2020.3030878.
[23]Akash, O.M., Ahmad, S.S.S., Azmi, M.S., Alkouri, A.U.M., “Affinity Propagation Based on Intuitionistic Fuzzy Similarity Measure.” In Intelligent and Interactive Computing. Lecture Notes in Networks and Systems, vol 67. Springer, Singapore. 2019 DOI:10.1007/978-981-13-6031-2_30
[24]S. Singh, A. H. Ganie, (2021)"Applications of picture fuzzy similarity measures in pattern recognition, clustering, and MADM", Expert Systems with Applications, Vol 168, 114264, ISSN 0957-4174, 2021 DOI:10.1016/j.eswa.2020.114264.
[25]H. Zhao and Z. Xu, "Intuitionistic Fuzzy Multi-Attribute Decision Making with Ideal-point-based Method and Correlation Measure," Journal of Intelligent & Fuzzy Systems, vol. 30, no. 2, pp. 747-757, 2016 DOI: 10.3233/IFS-151795
[26]E. Szmidt and J. Kacprzyk, "Distances between intuitionistic fuzzy sets," in Fuzzy Sets Syst, vol. 114, no. 3, pp. 505-518, 2019, DOI:10.1016/S0165-0114(98)00244-9
[27]P. Grzegorzewski, "Distances between intuitionistic fuzzy sets and/or interval-valued fuzzy sets based on the Hausdorff metric," in Fuzzy Sets Systems, vol. 148, no. 2, 2004, pp. 319-328, DOI: 10.1016/j.fss.2003.08.005
[28]R. R. Yager, "On the measure of fuzziness and negation part I: membership in the unit interval," On The Measure of Fuzziness and Negation Part I: Membership in the Unit Interval, International Journal of General Systems, 5:4, 221-229, 1979 DOI: 10.1080/03081077908547452
[29]Z. Xu, “Intuitionistic Fuzzy Aggregation Techniques”, Springer, German, 2012.
[30]K. T. Atanassov, "Intuitionistic fuzzy sets," in Fuzzy Sets and Systems, vol. 20, no. 1, pp. 87-96. 1986 DOI:10.1016/S0165-0114(86)80034-3
[31]L. A. Zadeh, "Fuzzy sets," in Information and Control, vol. 8, no. 3, pp. 338-353, 1965 DOI:10.1016/S0019-9958(65)90241-X
[32]K. -P. Lin, "A Novel Evolutionary Kernel Intuitionistic Fuzzy C -means Clustering Algorithm," in IEEE Transactions on Fuzzy Systems, vol. 22, no. 5, pp. 1074-1087, 2014 doi: 10.1109/TFUZZ.2013.2280141.
[33]Q. M. D. Lohani, R. Solanki and P. K. Muhuri, "Novel Adaptive Clustering Algorithms Based on a Probabilistic Similarity Measure Over Atanassov Intuitionistic Fuzzy Set," in IEEE Transactions on Fuzzy Systems, vol. 26, no. 6, pp. 3715-3729, 2018 doi: 10.1109/TFUZZ.2018.2848245.
[34]H. Liao, X. Mi, Z. Xu, J. Xu and F. Herrera, "Intuitionistic Fuzzy Analytic Network Process," in IEEE Transactions on Fuzzy Systems, vol. 26, no. 5, pp. 2578-2590, 2018, doi: 10.1109/TFUZZ.2017.2788881.
[35]F. Zhao, Z. Zeng, H. Liu, R. Lan and J. Fan, "Semisupervised Approach to Surrogate-Assisted Multiobjective Kernel Intuitionistic Fuzzy Clustering Algorithm for Color Image Segmentation," in IEEE Transactions on Fuzzy Systems, vol. 28, no. 6, pp. 1023-1034, 2020 DOI: 10.1109/TFUZZ.2020.2973121.
[36]Y. Zhang, Y. Wang and S. Wang, "Improvement of Collaborative Filtering Recommendation Algorithm Based on Intuitionistic Fuzzy Reasoning Under Missing Data," in IEEE Access, vol. 8, pp. 51324-51332, 2020, doi: 10.1109/ACCESS.2020.2980624.
[37]L. Pan, X. Gao, Y. Deng and K. H. Cheong, "Constrained Pythagorean Fuzzy Sets and Its Similarity Measure," in IEEE Transactions on Fuzzy Systems, vol. 30, no. 4, pp. 1102-1113, 2022 doi: 10.1109/TFUZZ.2021.3052559.
[38]Y. Wang, Y. Lei, Y. Lei and X. Fan, "Multi-factor high-order intuitionistic fuzzy time series forecasting model," in Journal of Systems Engineering and Electronics, vol. 27, no. 5, pp. 1054-1062, 2016 doi: 10.21629/JSEE.2016.05.13.
[39]F. Yang, Z. Liu, X. Bai and Y. Zhang, "An Improved Intuitionistic Fuzzy C-Means for Ship Segmentation in Infrared Images," in IEEE Transactions on Fuzzy Systems, vol. 30, no. 2, pp. 332-344, 2022 doi: 10.1109/TFUZZ.2020.3037972.
[40]J. Wang, H. Zhang and Z. Zhang, "Fuzzy multi-criteria decision-making approach with incomplete information based on evidential reasoning," in Journal of Systems Engineering and Electronics, vol. 21, no. 4, pp. 604-608, 2010 doi: 10.3969/j.issn.1004-4132.2010.04.012.
[41]C. -L. Fan, Y. Song, Q. Fu, L. Lei and X. Wang, "New Operators for Aggregating Intuitionistic Fuzzy Information with Their Application in Decision Making," in IEEE Access, vol. 6, pp. 27214-27238, 2018, doi: 10.1109/ACCESS.2018.2832206.
[42]K. Guo, "Knowledge Measure for Atanassov's Intuitionistic Fuzzy Sets," in IEEE Transactions on Fuzzy Systems, vol. 24, no. 5, pp. 1072-1078, 2016 doi: 10.1109/TFUZZ.2015.2501434.
[43]S. Das, D. Guha and R. Mesiar, "Information Measures in the Intuitionistic Fuzzy Framework and Their Relationships," in IEEE Transactions on Fuzzy Systems, vol. 26, no. 3, pp. 1626-1637, 2016 doi: 10.1109/TFUZZ.2017.2738603.
[44]S. N. Swamy and S. R. Kota, "An Empirical Study on System Level Aspects of Internet of Things (IoT)," in IEEE Access, vol. 8, pp. 188082-188134, , 2020 doi: 10.1109/ACCESS.2020.3029847.
[45]Z. Wan, Z. Zhang, R. Yin and G. Yu, "KFIML: Kubernetes-Based Fog Computing IoT Platform for Online Machine Learning," in IEEE Internet of Things Journal, vol. 9, no. 19, pp. 19463-19476, 2022 doi: 10.1109/JIOT.2022.3168085.
[46]D. Wu, H. Wang, H. Mohammed and R. Seidu, "Quality Risk Analysis for Sustainable Smart Water Supply Using Data Perception," in IEEE Transactions on Sustainable Computing, vol. 5, no. 3, pp. 377-388, 2020 doi: 10.1109/TSUSC.2019.2929953.
[47]M. Kumar, T. Singh, M. K. Maurya, A. Shivhare, A. Raut and P. K. Singh, "Quality Assessment and Monitoring of River Water Using IoT Infrastructure," in IEEE Internet of Things Journal, vol. 10, no. 12, pp. 10280-10290, 2023, doi: 10.1109/JIOT.2023.3238123.
[48]A. O. Al-Sulttani, M. Al-Mukhtar, A. B. Roomi, A. A. Farooque, K. M. Khedher and Z. M. Yaseen, "Proposition of New Ensemble Data-Intelligence Models for Surface Water Quality Prediction," in IEEE Access, vol. 9, pp. 108527-108541, 2021 doi: 10.1109/ACCESS.2021.3100490.
[49]N. A. P. Rostam, N. H. A. H. Malim, R. Abdullah, A. L. Ahmad, B. S. Ooi and D. J. C. Chan, "A Complete Proposed Framework for Coastal Water Quality Monitoring System with Algae Predictive Model," in IEEE Access, vol. 9, pp. 108249-108265, 2021 doi: 10.1109/ACCESS.2021.3102044.
[50]S. I. Abba et al., "Hybrid Machine Learning Ensemble Techniques for Modeling Dissolved Oxygen Concentration," in IEEE Access, vol. 8, pp. 157218-157237, 2020 doi: 10.1109/ACCESS.2020.3017743.
[51]C. W. Wu, "Study on K-meap Clustering and Wasserstein GAN for Distributional-valued Variable of IoT," Master's thesis, Dept. of Information Engineering, National Formosa University, 2019. https://hdl.handle.net/11296/x57t5e.