研究生: |
SETYA WIDYAWAN PRAKOSA SETYA WIDYAWAN PRAKOSA |
---|---|
論文名稱: |
智慧農業框架構建研究 Study on the Construction of Smart Farming Frameworks |
指導教授: |
呂政修
Jenq-Shiou Leu |
口試委員: |
呂政修
Jenq-Shiou Leu 魏宏宇 Hung-Yu Wei 周承復 Cheng-Fu Chou 曾建超 Chien-Chao Tseng 林丁丙 Ding-Bing Lin 衛信文 Hsin-Wen Wei 方文賢 Wen-Hsien Fang 鄭瑞光 Ray-Guang Cheng 阮聖彰 Shanq-Jang Ruan |
學位類別: |
博士 Doctor |
系所名稱: |
電資學院 - 電子工程系 Department of Electronic and Computer Engineering |
論文出版年: | 2023 |
畢業學年度: | 111 |
語文別: | 英文 |
論文頁數: | 77 |
中文關鍵詞: | smart farming 、Internet of Things (IoT) 、deep learning 、compression technique 、pruning filters 、PCENet 、SCANet 、accuracy 、inference time |
外文關鍵詞: | smart farming, Internet of Things (IoT), deep learning, compression technique, pruning filters, PCENet, SCANet, accuracy, inference time |
相關次數: | 點閱:318 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
Smart farming is becoming an essential approach to solve several issues in the agricultural area including how to create precise agriculture schemes, how to efficiently manage the resources such as workers, fertilizers, or the land itself, and possibly for monitoring the farm as the surveillance approach. Since in the recent years, the interest of younger generation for being farmers is getting declined. Therefore, the smart farming application can be a buzzword and possibly an approach to attract many generations to get involved in growing our food.
In this dissertation, the study on the construction of smart farming application is presented. As we know that some recent applications are constructed based on the Internet of Things (IoT) paradigm. Thus, the approach of the IoT is studied in this dissertation particularly for the construction of the smart farming framework using LoRa protocol. The study for the deployment of the scheme was conducted in the Indonesian rural area. The objective was to have an idea related to the factors affecting the performance of the scheme such as the data latency and the possible range of the proposed approach.
Secondly, we proposed a scheme using deep learning to classify the cocoa bean images retrieved from the Indonesian agriculture industry. The classification is based on the Indonesian export standard. To have an accurate classification we proposed structure called Progressive Contextual Excitation Network (PCENet) and Selective Context Adaptation Network (SCANet). From the study, we found that both proposed schemes can achieve accuracy of 86.8% and 88.7% which outperform the other well-known architectures.
Eventually, to deploy the proposed models, we conducted an experiment for compressing the proposed structure. The compression technique was done using pruning filters. The objective of the compression technique study is to give an insight how we can deploy the proposed models and accelerate the current models. Therefore, it can be possible for the deployment into a cheap and more affordable hardware such as the deployment into the Jetson Nano as an edge computing platform. From our study, we can possibly accelerate the PCENet model from 9.9 FPS to 16.7 FPS and 2.9 to 5.3 FPS for the SCANet model.
Smart farming is becoming an essential approach to solve several issues in the agricultural area including how to create precise agriculture schemes, how to efficiently manage the resources such as workers, fertilizers, or the land itself, and possibly for monitoring the farm as the surveillance approach. Since in the recent years, the interest of younger generation for being farmers is getting declined. Therefore, the smart farming application can be a buzzword and possibly an approach to attract many generations to get involved in growing our food.
In this dissertation, the study on the construction of smart farming application is presented. As we know that some recent applications are constructed based on the Internet of Things (IoT) paradigm. Thus, the approach of the IoT is studied in this dissertation particularly for the construction of the smart farming framework using LoRa protocol. The study for the deployment of the scheme was conducted in the Indonesian rural area. The objective was to have an idea related to the factors affecting the performance of the scheme such as the data latency and the possible range of the proposed approach.
Secondly, we proposed a scheme using deep learning to classify the cocoa bean images retrieved from the Indonesian agriculture industry. The classification is based on the Indonesian export standard. To have an accurate classification we proposed structure called Progressive Contextual Excitation Network (PCENet) and Selective Context Adaptation Network (SCANet). From the study, we found that both proposed schemes can achieve accuracy of 86.8% and 88.7% which outperform the other well-known architectures.
Eventually, to deploy the proposed models, we conducted an experiment for compressing the proposed structure. The compression technique was done using pruning filters. The objective of the compression technique study is to give an insight how we can deploy the proposed models and accelerate the current models. Therefore, it can be possible for the deployment into a cheap and more affordable hardware such as the deployment into the Jetson Nano as an edge computing platform. From our study, we can possibly accelerate the PCENet model from 9.9 FPS to 16.7 FPS and 2.9 to 5.3 FPS for the SCANet model.
[1] N. Ahmed, D. De and I. Hussain, "Internet of Things (IoT) for Smart Precision Agriculture and Farming in Rural Areas," in IEEE Internet of Things Journal, vol. 5, no. 6, pp. 4890-4899, Dec. 2018, doi: 10.1109/JIOT.2018.2879579.
[2] M. Salah Uddin, M. Fatin Istiaq, M Rasadin, M. Ruhel Talukder, “Freshwater shrimp farm monitoring system for Bangladesh based on internet of things.” Engineering Reports. 2020. https://doi.org/10.1002/eng2.12184
[3] R. Rayhana, G. Xiao and Z. Liu, "Internet of Things Empowered Smart Greenhouse Farming," in IEEE Journal of Radio Frequency Identification, vol. 4, no. 3, pp. 195-211, Sept. 2020, doi: 10.1109/JRFID.2020.2984391.
[4] N. G. Rezk, E. ED. Hemdan, AF. Attia, A. El-Sayed, M. A. El-Rashidy, “An efficient IoT based smart farming system using machine learning algorithms.” Multimed Tools Appl 80, 773–797, 2021, https://doi.org/10.1007/s11042-020-09740-6
[5] V. Saiz-Rubio, and F. Rovira-Más, "From Smart Farming towards Agriculture 5.0: A Review on Crop Data Management" Agronomy 10, no. 2: 207, 2020, https://doi.org/10.3390/agronomy10020207.
[6] V. Tenrisanna and K. Kasim, “Livestock farming income analysis of farm households in Indonesia.” In the 3rd International Conference of Animal Science and Technology. IOP Conf. Ser.: Earth Environ. Sci. 3-4 November 2020, Makassar, Indonesia, doi:10.1088/1755-1315/788/1/012218
[7] H. Toiba, T. W. Nugroho, D. Retnoningsih, and M. S. Rahman, “Food system transformation and its impact on smallholder farmers’ income and food security in Indonesia.” Cogent Economics & Finance, 8:1, 2020, doi: 10.1080/23322039.2020.1854412.
[8] H. Azadi, P. Ho, and L. Hasfiati. “Agricultural Land Conversion Drivers: A Comparison between Less Developed, Developing and Developed Countries.” Land Degradation & Development 22, no. 6 (2010): 596–604. https://doi.org/10.1002/ldr.1037.
[9] M. Rondhi, P. A. Pratiwi, V. T. Handini, A. F. Sunartomo, and S. A. Budiman, "Agricultural Land Conversion, Land Economic Value, and Sustainable Agriculture: A Case Study in East Java, Indonesia" Land 7, no. 4: 148, 2018, https://doi.org/10.3390/land7040148
[10] K. M. A. Rahman, and D. Zhang, "Effects of Fertilizer Broadcasting on the Excessive Use of Inorganic Fertilizers and Environmental Sustainability" Sustainability, 10, no. 3: 759, 2018, https://doi.org/10.3390/su10030759
[11] E. Soetarto, D. Nurdinawati, R. Sita, M. Sihaloho, and T. Budiarto, "Agriculture and the regeneration problem: Rural youth, employment, and the future of farming." In Rural Socio-Economic Transformation: Agrarian, Ecology, Communication and Community Development Perspectives, pp. 35-44. CRC Press, 2019.
[12] Badan Pusat Statistik. “Jumlah Pendapatan Setelah Pajak Menurut Golongan Rumah Tangga.” Badan Pusat Statistik. Accessed June 10, 2022. https://www.bps.go.id/indikator/indikator/view_data/0000/data/681/website_104/1.
[13] Pertanian, Kementrian. “Youth Entrepreneur and Employment Support Services (YESS).” Kementerian Pertanian. Accessed July 6, 2022. https://yesskementan.org/profile.
[14] Agriculture, Executive Yuan, R.O.C.(Taiwan), Council of. “Council of Agriculture, Executive Yuan, R.O.C.(Taiwan).” Overview-Council of Agriculture, Executive Yuan, R.O.C.(Taiwan). Accessed July 7, 2022. https://eng.coa.gov.tw/ws.php?id=9501.
[15] C. Abbott, “On Average, U.S. Farmers Are Aging, but a Quarter of Them Are Newcomers – Food and Environment Reporting Network.” On average, U.S. farmers are aging, but a quarter of them are newcomers – Food and Environment Reporting Network. Accessed July 7, 2022. https://thefern.org/ag_insider/on-average-u-s-farmers-are-aging-but-a-quarter-of-them-are-newcomers/#:~:text=For%20four%20decades%2C%20the%20average,years%2C%20says%20the%202017%20census.
[16] V. Akre, A. Rajan, J. Ahamed, A. Al Amri and S. Al Daisi, "Smart Digital Marketing of Financial Services to Millennial Generation using emerging technological tools and buyer persona," 2019 Sixth HCT Information Technology Trends (ITT), 2019, pp. 120-125, doi: 10.1109/ITT48889.2019.9075106.
[17] M. I. H. bin Ismail and N. M. Thamrin, "IoT implementation for indoor vertical farming watering system," 2017 International Conference on Electrical, Electronics and System Engineering (ICEESE), 2017, pp. 89-94, doi: 10.1109/ICEESE.2017.8298388.
[18] S. W. Prakosa, M. Faisal, Y. Adhitya, J.-S. Leu, M. Koppen, and C. Avian, “Design and Implementation of LoRa Based IoT Scheme for Indonesian Rural Area,” Electronics, Vol. 10, Issue 1, pp. 1–12, 77, Jan. 2021
[19] Y. Adhitya, S. W. Prakosa, M. Koppen and J.-S. Leu, “Feature Extraction for Cocoa Bean Digital Image Classification Prediction for Smart Farming Application,” Agronomy, Vol. 10, Issue 11, pp. 1–16, 1642. Oct. 2020
[20] W. -L. Chen et al., "AgriTalk: IoT for Precision Soil Farming of Turmeric Cultivation," in IEEE Internet of Things Journal, vol. 6, no. 3, pp. 5209-5223, June 2019, doi: 10.1109/JIOT.2019.2899128.
[21] M. I. Alipio, A. E. M. D. Cruz, J. D. A. Doria, and R. S. Fruto, “A smart hydroponics farming system using exact inference in bayesian network,” in 2017 IEEE 6th Global Conference on Consumer Electronics, Oct 2017.
[22] Semtech, “Revolutionising smart agriculture using semtech’s LoRa technology.” Semtech, White Paper; 2017. [Online]. Available: www.semtech.com/uploads/technology/LoRa/WP-SEMTECH-LORA-SMART-AGRICULTURE.pdf (accessed on 5th of July 2022)
[23] Semtech SX1276. Available online: https://www.semtech.com/products/wireless-rf/lora-transceivers/sx1276 (accessed on 5th of July 2022)
[24] Dragino Lora IoT Kit. Available online: https://www.dragino.com/ (accessed on 7th of July 2022).
[25] DHT11 Datasheet. Available online: https://www.mouser.com/datasheet/2/758/ DHT11-Technical-Data-Sheet-Translated-Version-1143054.pdf. (accessed on 7th of July 2022)
[26] G. Hristov, D. Kinaneva, G. Georgiev, P. Zahariev and P. Kyuchukov, "An overview of the use of Unmanned Aerial Vehicles for Precision Agriculture," 2020 International Conference on Biomedical Innovations and Applications (BIA), 2020, pp. 137-140, doi: 10.1109/BIA50171.2020.9244519.
[27] R. G. de Luna, E. P. Dadios and A. A. Bandala, "Automated Image Capturing System for Deep Learning-based Tomato Plant Leaf Disease Detection and Recognition," TENCON 2018 - 2018 IEEE Region 10 Conference, 2018, pp. 1414-1419, doi: 10.1109/TENCON.2018.8650088.
[28] M. H. Saleem, J. Potgieter, and K. M. Arif, "Plant Disease Detection and Classification by Deep Learning" Plants 8, no. 11: 468, 2019 https://doi.org/10.3390/plants8110468
[29] A. Jihen, B. Bouaziz, A. A. Algergawy, “Deep Learning-Based Approach for Banana Leaf Diseases Classification.” In Datenbanksysteme für Business, Technologie und Web (BTW 2017)-Workshopband, Gesellschaft für Informatik e.V., Bonn, Germany, 2017
[30] A. Sirohi, A. Malik, “A hybrid model for the classification of sunflower diseases using deep learning.” In Proceedings of the 2021 2nd International Conference on Intelligent Engineering and Management (ICIEM), London, UK, 28–30 April 2021.
[31] N. Kussul, M. Lavreniuk, S. Skakun and A. Shelestov, "Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data," in IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 5, pp. 778-782, May 2017, doi: 10.1109/LGRS.2017.2681128.
[32] D. Mohapatra, B. Choudhury, B. Sabat, “An Automated System for Fruit Gradation and Aberration Localisation using Deep Learning.” In Proceedings of the 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India, 19–20 March 2021.
[33] A. Milioto, P. Lottes, C. Stachniss, “Real-time blob-wise sugar beets vs weeds classification for monitoring fields using convolutional neural networks.” In Proceedings of the International Conference on Unmanned Aerial Vehicles in Geomatics, Bonn, Germany, 6–7 April 2017.
[34] R. A. Priyadharshini, S. Arivazhagan, M. Arun, A. Mirnalini, “Maize leaf disease classification using deep convolutional neural networks.” Neural Comput. Appl. 31, 8887–8895, 2019, https://doi.org/10.1007/s00521-019-04228-3
[35] A. Waheed, M. Goyal, D. Gupta, A. Khanna, A. E. Hassanien, H. M. Pandey, “An optimized dense convolutional neural network model for disease recognition and classification in corn leaf.” Comput. Electron. Agric. 175, 105456, 2020, https://doi.org/10.1016/j.compag.2020.105456
[36] H. Yu, J. Liu, C. Chen, A. A. Heidari, Q. Zhang, H. Chen, M. Mafarja, H. Turabieh, “Corn Leaf Diseases Diagnosis Based on K-Means Clustering and Deep Learning.” IEEE Access 9, 143824–143835, 2021, https://doi.org/10.1109/-ACCESS.2021.3120379
[37] A. D. Andrushia, A. T. Patricia, “Artificial bee colony optimization (ABC) for grape leaves disease detection.” Evol. Syst. 11, 105–117, 2020, https://doi.org/10.1007/s12530-019-09289-2
[38] A. Adeel, M. A. Khan, T. Akram, A. Sharif, M. Yasmin, T. Saba, K. Javed, “Entropy‐controlled deep features selection framework for grape leaf diseases recognition.” Expert Syst, 2020, https://doi.org/10.1111/exsy.12569
[39] B. Liu, Y. Zhang, D.-J. He, Y. Li, “Identification of apple leaf diseases based on deep convolutional neural networks.” Symmetry (Basel). 10, 2018, https://doi.org/10.3390/sym10010011
[40] Y. Zhong, M. Zhao, “Research on deep learning in apple leaf disease recognition.” Comput. Electron. Agric. 168, 105146, 2020, https://doi.org/10.1016/-j.compag.2019.105146
[41] A. J. Mantau, I. W. Widayat, J.-S. Leu and M. Koppen, “A Human-Detection Method Based on YOLOv5 and Transfer Learning Using Thermal Image Data from UAV Perspective for Surveillance System,” Drones, Vol. 6, Issue 10, pp. 1–12, 290, Oct. 2022.
[42] H.-Y. Hsieh, S.-A. Huang, J.-S. Leu, “Implementing a Real-Time Image Captioning Service for Scene Identification Using Embedded System,” Multimedia Tools and Applications (MTAP), Springer, Vol. 80, Issue 8, pp. 12525 - 12537, Mar. 2021.
[43] J.-C. Tsai, J.-S. Leu, S. W. Prakosa, L.-C. Hsiao, P.-C. Huang, S.-Y. Yang and Y.-T. Huang, “Design and Implementation of an Internet of Healthcare Things System for Respiratory Diseases,” Wireless Personal Communications(WPC), Springer, Vol. 117, Issue 2, pp. 337–353, Mar. 2021
[44] C. Vallati, A. Virdis, E. Mingozzi, and G. Stea, “Mobile-edge computing come home connecting things in future smart homes using LTE device-to-device communications,” IEEE Consum. Electron. Mag., vol. 5, no. 4, pp. 77–83, Oct. 2016.
[45] G. Jia, G. Han, H. Rao, and L. Shu, “Edge computing-based intelligent manhole cover management system for smart cities,” IEEE Internet Things J., vol. 5, no. 3, pp. 1648–1656, Jun. 2018.
[46] N. G. Rezk, E. E. D. Hemdan, A. F. Attia, A. E. Sayed, and M. A. E. Rashidy, “An efficient IoT based smart farming system using machine learning algorithms.” Multimed Tools Appl 80, 773–797. 2021. https://doi.org/10.1007/s11042-020-09740-6.
[47] A. Menshchikov, D. Shadrin, V. Prutyanov, D. Lopatkin, S. Sosnin, E. Tsykunov, E. Iakovlev, and A. Somov , "Real-Time Detection of Hogweed: UAV Platform Empowered by Deep Learning," in IEEE Transactions on Computers, vol. 70, no. 8, pp. 1175-1188, 1 Aug. 2021, doi: 10.1109/TC.2021.3059819.
[48] P. Joshi, D. Das, V. Udutalapally, M. K. Pradhan and S. Misra, "RiceBioS: Identification of Biotic Stress in Rice Crops Using Edge-as-a-Service," in IEEE Sensors Journal, vol. 22, no. 5, pp. 4616-4624, 1 March1, 2022, doi: 10.1109/JSEN.2022.3143950
[49] S. W. Prakosa, J. S. Leu, and Z. H. Chen, “Improving the accuracy of pruned network using knowledge distillation,” Pattern Analysis and Applications, vol. 24, no. 2, pp. 819–830, May 2021, doi: 10.1007/s10044-020-00940-2.