臺灣博碩士論文加值系統

現有的基於非影像的植物疾病偵測依賴於對環境條件的時間域分析。這些方法適用於鬆散控制的開放式農田。然而，蘭花疾病在基於物聯網（IoT）的智能溫室中並不常見，這些溫室的環境條件受到了良好的控制。在這樣緊密監管的環境中，現有的時間域分析解決方案不足以偵測罕見發生的蘭花疾病事件。我們觀察到，在這種被良好控制的溫室內，溫度和濕度對於蘭花真菌的影響在時間域內不易明顯顯示，這也是我們在時間域的調查所指出的。為了應對這一個挑戰，我們提出了 OrchidTalk，一個基於物聯網的深度學習平台，它使用連續小波轉換（CWT）濾波器進行時間頻域分析，以偵測蘭花疾病。經由一個複雜的過程，我們選擇了帶有四個導數的高斯小波作為 CWT 的母小波，用於數據提取階段。所得到的特徵被用作 Orchid-3D 模型（三維 ConvLSTM）的輸入，該模型在偵測蘭花疾病方面顯著優於之前提出的 Orchid-1D （CNN 和 LSTM）和 Orchid-2D（二維 ConvLSTM）模型。對於偵測罕見發生 0.2% 的患病蘭花植株事件，OrchidTalk 實現了 0.902 的召回率，0.92 的精確度，0.99 的準確率和 0.911 的 F1-score。據我們所知，這代表了在良好控制的溫室中實現的最高預測性能。

Existing non-image-based solutions for detecting plant diseases rely on time domain analysis of environmental conditions. These solutions are suitable for loosely controlled open farm fields. Conversely, orchid diseases are infrequent events in Internet of Things (IoT)-based smart greenhouses, where environmental conditions are well-controlled. Within such tightly regulated environments, existing time domain analysis solutions are inadequate for detecting rare orchid disease events. We observed that the influence of temperature and humidity on orchid fungus within the well-controlled greenhouse is not readily apparent, as indicated by our investigation in the time domain. In order to address this challenge, we propose OrchidTalk, an IoT-based deep learning platform, which employs a time-frequency domain analysis using the Continuous Wavelet Transform (CWT) filter, for the purpose of detecting orchid diseases. Through a non-trivial process, we select the Gaussian wavelet with four derivatives to serve as the mother wavelet of the CWT in the data extraction phase. The resulting features are used as inputs to the Orchid-3D model (three-dimension ConvLSTM), which significantly outperforms the previously proposed Orchid-1D (CNN and LSTM) and Orchid-2D (two-dimension ConvLSTM) models. For the rare event detection of 0.2% of sick orchid plants, OrchidTalk achieves a recall of 0.902, precision of 0.92, accuracy of 0.99, and an F1-score of 0.911. To the best of our knowledge, this represents the highest prediction performance achieved for a well-controlled greenhouse.

誌 謝i
摘 要ii
Abstractiv
目 錄vi
圖片目錄viii
表格目錄x
第一章 緒論1
第二章 相關研究5
第三章 資料收集與特徵提取9
第四章 深度學習模型19
第五章 性能評估26
5.1時間域與時頻域的比較26
5.2母小波的選擇27
5.3AI 模型的表現30
第六章 結論36
參考文獻38

[1] "HARK Orchideen - Diseases on Phalaenopsis and other orchids," [Online]. Available: https://www.hark-orchideen.com/diseases/. [Accessed 15 7 2023].
[2] Tsai, Cheng-Feng and Huang, Chih-Hung and Wu, Fu-Hsing and Lin, Chuen-Horng and Lee, Chia-Hwa and Yu, Shyr-Shen and Chan, Yung-Kuan and Jan, Fuh-Jyh, "Intelligent image analysis recognizes important orchid viral diseases," Frontiers in Plant Science, vol. 13, p. 1051348, 2022.
[3] Tuhid, Nurul Hidayah and Abdullah, Noor Ezan and Khairi, N.M and Saaid, M.F. and M.S.B, Shahrizam and Hashim, Hadzli, "A statistical approach for orchid disease identification using RGB color," 2012 IEEE Control and System Graduate Research Colloquium, pp. 382-385, 2012.
[4] Lin, Yi-Bing and Liu, Chun-You and Chen, Wen-Liang and Chang, Chia-Hui and Ng, Fung-Ling and Yang, Krista and Hsung, Jerry, "IoT-based Strawberry Disease Detection with Wall-mounted Monitoring Cameras," IEEE Internet of Things Journal, 2023.
[5] Morkeliūnė, Armina, Neringa Rasiukevičiūtė, and Alma Valiuškaitė, "Meteorological Conditions in a Temperate Climate for Colletotrichum acutatum, Strawberry Pathogen Distribution and Susceptibility of Different Cultivars to Anthracnose," Agriculture, vol. 11, no. 1, p. 80, 2021.
[6] ElBeheiry, Nabila and Balog, Robert S., "Technologies Driving the Shift to Smart Farming: A Review," IEEE Sensors Journal, 2022.
[7] Chen, Wen-Liang and Lin, Yi-Bing and Lin, Yun-Wei and Chen, Robert and Liao, Jyun-Kai and Ng, Fung-Ling and Chan, Yuan-Yao and Liu, You-Cheng and Wang, Chin-Cheng and Chiu, Cheng-Hsun and Yen, Tai-Hsiang, "AgriTalk: IoT for Precision Soil Farming of Turmeric Cultivation," IEEE Internet of Things Journal, vol. 6, no. 3, pp. 5209-5223, 2019.
[8] Chen, Wen-Liang and Lin, Yi-Bing and Ng, Fung-Ling and Liu, Chun-You and Lin, Yun-Wei, "RiceTalk: Rice Blast Detection Using Internet of Things and Artificial Intelligence Technologies," IEEE Internet of Things Journal, vol. 7, no. 2, pp. 1001-1010, 2019.
[9] Lin, Yi-Bing and Lin, Yun-Wei and Kao, Ling-Han, "Anomaly Detection for Electric Energy Consumption in Smart Farms," IEEE Transactions on AgriFood Electronics, 2023.
[10] Golhani, Kamlesh and Balasundram, Siva K and Vadamalai, Ganesan and Pradhan, Biswajeet, "A review of neural networks in plant disease detection using hyperspectral data," Information Processing in Agriculture, vol. 5, no. 3, pp. 354-371, 2018.
[11] Liu, Zhiyan and Bashir, Rab Nawaz and Iqbal, Salman and Shahid, Malik Muhammad Ali and Tausif, Muhammad and Umer, Qasim, "Internet of Things (IoT) and Machine Learning Model of Plant Disease Prediction–Blister Blight for Tea Plant," IEEE Access, vol. 10, pp. 44934-44944, 2022.
[12] Li, Manzhou and Cheng, Siyu and Cui, Jingyi and Li, Changxiang and Li, Zeyu and Zhou, Chang and Lv, Chunli, "High-Performance Plant Pest and Disease Detection Based on Model Ensemble with Inception Module and Cluster Algorithm," Plants, vol. 12, no. 1, p. 200, 2023.
[13] Amin, Muhammad and Ullah, Khalil and Asif, Muhammad and Waheed, Abdul and Haq, Sana Ul and Zareei, Mahdi and Biswal, Rajesh Roshan, "ECG-Based Driver’s Stress Detection Using Deep Transfer Learning and Fuzzy Logic Approaches," IEEE Access, vol. 10, pp. 29788-29809, 2022.
[14] Tseng, Li-Ming and Tseng, Vincent S, "Predicting Ventricular Fibrillation Through Deep Learning," IEEE Access, vol. 8, pp. 221886-221896, 2020.
[15] Wang, Tao, Changhua Lu, Yining Sun, Mei Yang, Chun Liu, and Chunsheng Ou, "Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network," Entropy, vol. 23, no. 1, p. 119, 2021.
[16] Srivastava, Shikha and Kadooka, Chris and Uchida, Janice Y, "Fusarium species as pathogen on orchids," Microbiological research, vol. 207, pp. 188-195, 2018.
[17] Prasad, Akhilesh and Maan, Jeetendrasingh and Verma, Sandeep Kumar, "Wavelet transforms associated with the index Whittaker transform," Mathematical Methods in the Applied Sciences, vol. 44, no. 13, pp. 10734-10752, 2021.