Application of machine learning in agriculture

목차 (Table of Contents)

• CONTENTS
• List of contributors = xiii
• Section 1 Fundamentals of smart agriculture
• CHAPTER 1 Machine learning-based agriculture / Rijwan Khan ; Mohammad Ayoub Khan ; Mohammad Aslam Ansari ; Niharika Dhingra ; Neha Bhati = 3
• Introduction = 3
• Literature review = 6
• Deep learning in agriculture = 8
• Transfer learning for pest detection = 9
• Proposed method = 10
• Pest detection = 10
• Crop yield prediction = 13
• E-Mandi = 15
• Comparative study = 18
• Comparison between different pest detection techniques = 18
• Comparison between different crop yield prediction techniques = 18
• Results and discussions = 18
• Pest detection = 18
• Crop yield prediction = 21
• E-Mandi = 23
• Conclusion = 23
• References = 25
• CHAPTER 2 Monitoring agricultural essentials / Jhanvi P. Sarvaiya ; Aditya P. Chaudhari ; Jai Prakash Verma = 29
• Introduction = 29
• Unsupervised machine learning algorithms for agriculture = 30
• Supervised machine learning algorithms for agriculture = 33
• Artificial neural network = 33
• Linear regression = 34
• Random forest = 35
• Proposed predictive model for agriculture = 35
• Data collection devices = 36
• Data storage = 39
• Crop prediction = 39
• Real-time monitoring = 40
• Communication technology = 40
• Results and discussion = 42
• Summary = 43
• References = 44
• CHAPTER 3 Machine learning-based remote monitoring and predictive analytics system for monitoring and livestock monitoring / Nikita Goel ; Yogesh Kumar ; Sumit Kaur ; Moolchand Sharma ; Prerna Sharma = 47
• Introduction = 47
• Motivation = 49
• Background study = 50
• Techniques used = 51
• Benefits of the work = 53
• Research challenges = 54
• Role of artificial intelligence and machine learning for crop monitoring = 56
• Reported work = 56
• Comparative analysis = 60
• Conclusion = 62
• References = 63
• Section 2 Market, technology and products
• CHAPTER 4 Agricultural economics / Avinash Kumar Sharma ; Rijwan Khan ; Abhyudaya Mittal ; Aditi Tiwari ; Aashna Kapoor = 71
• Introduction = 71
• Prediction of crop price = 72
• Impact of gross domestic product = 75
• Share of agriculture in gross domestic product = 76
• Government schemes = 77
• Economical changes in traditional agriculture versus machine learning agriculture = 78
• Meteorology = 80
• Scope of agrometeorology = 82
• Agromeleorology’s relationship with agricultural sciences = 83
• Difference between meteorology and agrometeorology = 83
• Crops and animals using agrometeorology = 83
• Agrometeorology as an interdisciplinary science = 84
• Conclusion = 84
• References = 85
• CHAPTER 5 Current and prospective impacts of digital marketing on the small agricultural stakeholders in the developing countries / Abdelrahman AH ; ChunpingXia = 91
• Introduction = 91
• Definition of and types of electronic business = 93
• Digital agricultural market before, during, and what is expected after the COVID-19 pandemic in developing countries = 95
• Digital agricultural market to mitigate the negative impacts of uncertainty = 97
• Opportunities and risks of investment in the digital agricultural market industry = 98
• Market segmentation of the digital agricultural market in developing countries = 101
• A mobile banking system = 104
• Digital agricultural value chain and its stakeholders = 105
• Impacts of digital agriculture on poverty reduction, food security rates, and food losses and waste reduction in developing countries = 107
• Agricultural digitalization to achieve the sustainable development goals 2030 = 108
• Conclusion = 109
• References = 109
• CHAPTER 6 Intelligent farming system through weather forecast support and crop production / Rakesh Mohan Pujahari ; Satya Prakash Yadav ; Rijwan Khan = 113
• Introduction = 113
• Technology stack used = 114
• Internet of Things = 114
• Used algorithms = 115
• Deep neural networks = 115
• Random forest program = 115
• System-related architecture = 116
• Raspberry Pi 3 = 117
• Sensor module based on DHT 11 = 118
• Sensor for soil moisture = 118
• Sensor for sensing rainfall = 118
• Sensor BMP-180 type = 120
• Software Raspbian (Raspberry pi) = 120
• ThingSpeak = 120
• Jupyter Notebook = 121
• Weather prediction = 122
• Predicting temperature = 122
• Methodology used = 125
• Results = 125
• Conclusions = 128
• References = 128
• CHAPTER 7 Deep learning-based prediction for stand age and land utilization of rubber plantation / Indra Mahakalanda ; Piyumal Demotte ; Indika Perera ; Dulani Meedeniya ; Wasana Wijesuriya ; Lakshman Rodrigo = 131
• Introduction = 131
• Background and related work = 133
• Rubber land-use mapping and age estimation via remote sensing imagery = 133
• Supervised classification methods = 135
• Study materials = 137
• Details of the area of study = 137
• Dataset = 137
• Solution design and implementation = 138
• Model design = 138
• Data preprocessing = 138
• Supervised learning process = 141
• Model evaluation = 144
• Experimental setup = 144
• Classification performance analysis = 144
• Vegetation index analysis = 14g
• Discussion = 150
• Study contributions = 150
• Study challenges = 151
• Future research directions = 151
• Conclusion = 152
• Acknowledgment = 152
• References = 153
• Section 3 Tools and techniques
• CHAPTER 8 Modeling techniques used in smart agriculture / N. Divya ; S. Deepthi ; G. Suresh Kumaar ; S. Manoharan = 159
• Introduction = 159
• Expert system = 160
• Fuzzy framework for smart agriculture = 161
• Fuzzy system architecture = 162
• Fuzzy inference engine = 164
• Defuzzification = 169
• Conclusion = 169
• References = 169
• CHAPTER 9 Plant diseases detection using artificial intelligence / Ravi Anand ; Ritesh K. Mishra ; Rijwan Khan = 173
• Introduction = 173
• Literature survey = 174
• Recognizing plant diseases = 180
• Image acquisition = 180
• Image preprocessing = 181
• Image segmentation = 182
• Region based = 182
• Edge based = 182
• Threshold based = 183
• Feature-based clustering = 183
• Feature extraction = 183
• Image recognition = 184
• Performance measures for image recognition techniques = 185 Discussion and future work = 186
• Conclusion = 187
• References = 188
• CHAPTER 10 A deep learning-based approach for mushroom diseases classification / Nusrat Zahan ; Md. Zahid Hasan ; Mohammad Shorif Uddin ; Shakhawat Hossain ; Sk. Fahmida Islam = 191
• Introduction = 191
• Related works = 192
• Dataset description = 195
• Methods = 195
• Image augmentation = 195
• Noise removal from image = 197
• Image enhancement technique = 198
• Deep learning algorithm = 200
• GoogleNet = 203
• Result analysis and discussion = 204
• Conclusion = 209
• References = 210
• CHAPTER 11 Smart fence to protect farmland from stray animals / Roshan Jahan ; Ahkeela M. Khanum ; Manish Madhav Tripathi = 213
• Introduction = 213
• Agricultural fences = 213
• Natural repellents = 214
• Smart fence to protect farmland = 215
• Virtual fence setup using optical fiber sensor = 215
• Optical fiber cable = 216
• Types of optical fibers = 218
• Optical fiber cable as sensor = 219
• Fiber optic sensors = 220
• Types of fiber-optic sensor systems = 220
• Intrinsic type fiber optic sensors = 220
• Extrinsic type fiber-optic sensors = 220
• Classification of fiber-optic sensors on the basis of operating principles = 221
• Intensity-based fiber-optic sensor = 221
• Polarization-based fiber-optic sensor = 221
• Phase-based fiber optic sensor = 222
• Signal analysis = 223
• Gait-based analysis to differentiate walking, running, and tapping = 226
• Algorithm for classification = 230
• Results = 231
• Conclusion = 233
• References = 234
• CHAPTER 12 Enhancing crop productivity through autoencoderbased disease detection and context-aware remedy recommendation system / S. Abinaya ; M.K. Kavitha Devi = 239
• Introduction = 239
• Preliminaries = 241
• Multilayer perceptron = 241
• Stacked denoising autoencoder = 242
• Convolutional neural network = 243
• Sentiment analysis = 243
• Proposed method = 244
• Disease detection phase = 245
• Disease classification phase = 248
• Recommendation phase = 249
• Experimental valuation = 253
• Description of the dataset = 253
• Implementation details = 253
• Evaluation metric = 255
• Performance of segmentation by cascading autoencoder = 255
• Performance of classification by concise convolutional neural network = 256
• Performance of remedy recommendation stacked autoencoder (SAE) = 256
• Conclusion = 257
• References = 258
• CHAPTER 13 UrbanAgro : Utilizing advanced deep learning to support Sri Lankan urban farmers to detect and control common diseases in tomato plants / Dilsha Hettiarachchi ; Vishmanthi Fernando ; Hiruni Kegalle ; Thilina Halloluwa = 263
• Introduction = 263
• Literature review = 264
• Preprocessing = 264
• Feature extraction = 264
• Machine learning = 265
• Deep learning = 266
• Implementation = 269
• Methodology = 269
• Data collection = 269
• Image annotation = 271
• Data augmentation = 271
• Deep learning model = 272
• Model Training = 274
• Results and discussion = 274
• Comparison of our results with previous works = 279
• Conclusion = 280
• Limitations = 280
• Future directions = 280
• Acknowledgments = 281
• References = 281
• CHAPTER 14 Machine learning techniques for agricultural image recognition / Mohammad Reza Keyvanpour ; Mehrnoush Barani Shirzad = 283
• Introduction = 283
• Steps for image analysis = 284
• Machine learning strategies in agricultural image recognition = 286
• Traditional machine learning methods = 286
• Deep learning models = 291
• Applications of image processing in agriculture tasks = 292
• Soil assessment = 293
• Irrigation = 293
• Leaf analysis = 293
• Weed detection = 294
• Pest control = 295
• Disease detection = 295
• Vegetation measurement = 296
• Monitoring plant growing = 296
• Fruit/food grading = 297
• Crop yield = 297
• Flower and seed detection = 298
• Plant classification = 298
• Summary = 300
• References = 300
• Index 307