| Titre : | Predict Plant Diseases and Crop Health Analysis Using IA and IOT |
| Auteurs : | Jamila Mammeri, Auteur ; Dalila Hattab, Directeur de thèse |
| Editeur : | Biskra [Algérie] : Faculté des Sciences Exactes et des Sciences de la Nature et de la Vie, Université Mohamed Khider, 2023 |
| Format : | 1 vol. (190 p.) / ill., couv. ill. en coul / 30 cm |
| Langues: | Anglais |
| Mots-clés: | plant diseases, sensors, CNN, IoT, IA,Deep learning, precision agriculture, climate change. |
| Résumé : |
This project focuses on the development of an IoT-based monitoring system for precision agriculture, specifically targeting epidemic disease control. The proposed agricultural monitoring system offers environmental monitoring services to maintain an optimal crop-growing environment and enables early prediction of conditions that may lead to disease outbreaks. A wireless sensor network is utilized to collect and store environmental and soil information in a database. Users can access real-time environmental data of their crops through any Internet-enabled device. To enhance decision-making capabilities, artificial intelligence, and prediction algorithms are implemented, creating an expert system that can emulate the judgment of human experts. This expert system issues warning messages to users before the onset of diseases, mitigating potential outbreaks. |
| Sommaire : |
Deducation i THANKS and gratitude ii Table of Contents iii List of Figures x List of Tables xv Introduction 1 1 Phase-1- Plants Diseases 4 1.1 Introduction . . . . . . . .. . . . . . 5 1.2 Plant Pathology or Phytopathology . . . . . . . . . . . . 6 1.3 Plant disease . . . . . . . . . . . . . . . . . . . . . . . 6 1.4 Symptoms[1] . . . . . . . . . . . . . . . . . . . . . . . . . 7 1.4.1 The most important symptoms of plant diseases[1] . . . . . 1.5 The aim of studying plant pathology[2] . . . . . . . . . . .. . 12 1.6 The history of plant diseases[2]. . . . . . . . . . .. . . 13 1.7 The signi…cance of plant diseases[2]. . . . . . . . . . . . . . 15 1.8 The dissemination of plant pathogens[2]. . . . . . . 15 1.9 Monitoring, examination, diagnosis and prediction[1]. . . . . . 16 iii1.9.1 Monitoring . . . . . . . . . . . . . . . . . . . . . 16 1.9.2 Examination . . . . . . . . . . . . . . . . . . . . . . .. 16 1.9.3 Diagnosis . . . . . . . . . . . . . . . . . . .. 16 1.9.4 Prediction plant disease . . . . . . . . . . . . 18 1.10 Control of plant diseases[1]. . . . . . .. . . . . 18 1.10.1 Legislative and legal methods . . . . . . . . . . . 18 1.10.2 Agricultural methods . . . . . . . . . . . . . . . . . 18 1.10.3 Vitality methods . . . . . . . . . . . . . . . . 19 1.10.4 Physical methods . . . . . . . . . . . . . . . . . . . . 19 1.10.5 Chemical methods . . . . . . . . . . . . . . . 19 1.11 Agricultural pests[1]. . . . . . . . . . . . . . . . . . 20 1.11.1 Insects . . . . . . . . . . . . 20 1.11.2 Mites (spiders) . . . . . . . . . . . . . 21 1.11.3 Caecilians (Nematoda) . . . . . . . . . . . . . . . . 22 1.11.4 Flowering plants (dodder) . . . . . . . . . . 22 1.11.5 Weeds and wild herbs . . . . . . . . . . . . 22 1.11.6 Rodents . . . . . . . . . . . . . . . . . . . . . .. . 23 1.11.7 Microorganisms . . . . . . . . . . . . . . . . . .. 24 1.12 Classi…cation of plant diseases[1] . . . . . . . . . . . . . . . . . 24 1.12.1 Fungal diseases . . . . . . . . . . . . . . . . . . . . 25 1.12.2 Bacterial diseases . . . . . . . . . . . . . 28 1.12.3 Viral diseases . . . . . . . . . . . . . . . . . . 29 1.13 Agricultural disturbances[1]. . . . . . . . . . . .. . . 30 1.13.1 The e¤ect of environmental factors on the plant in disease events . 30 1.13.2 The most important environmental factors a¤ecting plant growthand development . . . . . 1.13.3 The most important physiological diseases a¤ecting vegetable crops 33 iv1.14 The disease severity . . . . . . . . . . 37 1.15 Disease monitoring[21] . . . . . . . . . . . . . . . . . . . . 38 1.16 Percentage Scales[23] . . . . . . . . . . . . . . . . .. . 38 1.17 Computer Simulation[25] . . . . . . . . . . . . . . . . . 39 1.18 Conclusion . . . . . . . . . . . . . . . . . . . . . 40 2 PHASE-2- AI and IoT in Plant Diseases 42 2.1 Introduction . . . . . . . . . . . . 43 2.2 The objective of this work . . . . . . . . . . . 44 2.3 The related work . . . . . . . . . . . . . . . . . . . . . . . . 45 2.4 Arti…cial intelligence (AI)[40] . . . . . . . . . . . . . . . 47 2.5 Machine learning (ML)[41] . . . . . . . . . . . . . . . . 48 2.5.1 Types of Systems of Machine Learning . . . . . . .. . 48 2.6 Machine Learning Models (ML)[12] . . . . . . . . . . . 50 2.6.1 Support Vector Machine (SVM)[26] . . . . . . . 2.6.2 Naive Bayes . . . . . . . . . . . . . . . . . . . . . . 51 2.6.3 K-Nearest Neighbor (KNN) . . . . . . . . . . . .. 52 2.7 Deep learning (DL) . . . . . . . . . . . . . . . . . . . . . 52 2.7.1 Batch Normalization[43] . . . . . . . . . . . . . . . 53 2.8 Deep Learning models (DL) . . . . . . . . . . . .. . . . 54 2.8.1 Arti…cial Neural Networks (ANN)[12] . . . . . . . . . 54 2.8.2 Convolutional Neural Networks (CNN) . . . . . . . . . .. 55 2.8.3 Convolutional Neural Network Architectures[12] . . . . . . 59 2.8.4 Comparison of various classi…ers . . . . . 61 2.8.5 DCNN[49] . . . . . . . . . . . . . . . . . . 61 2.8.6 The Di¤erence between machine learning and deep learning[54] . . . 62 2.8.7 Image recognition technology based on deep learning[47] . . . . . . 62 2.8.8 Open source tools for deep learning . . . . . . 62 v2.9 Transfer Learning (TL)[12] . . . . . . . . . . . . . . . 63 2.10 Data Operations . . . . . . . . . . . . . . . . . . . . . . . . . 63 2.10.1 Data acquisition . . . . . . . . . . . . . . . . . . .. . . . 63 2.10.2 Data Pre-processing[12] . . . . . . . . . . . . . . . . 64 2.10.3 Data Analysis[34]. . . . . . . . . . . . . . . . 67 2.11 Network type[47]. . . . . . . . . . . . . . . . .. . . . . 68 2.11.1 Classi…cation network [47]. . . . . . . . 68 2.11.2 Detection network[47]. . . . . . . . . . . . . . 71 2.11.3 Segmentation network[47] . . . . . . . . . . 2.12 Evaluation indices[47]. . . . . . . . . . . . . . . . .. . . . 73 2.13 Challenges[47]. . . . . . . . . . . . . .. . . . 73 2.13.1 Small dataset size problem . . . . . . . . 73 2.13.2 Detection performance under the in‡uence of illumination and occlusion 74 2.14 Computer vision[72] . . . . . . . . . . . . . . 75 2.15 Precision agriculture[73] . . . . . . . . . . . . . . . . 75 2.15.1 The bene…ts of precision agriculture[73] . . . . . . . 75 2.15.2 Are there any challenges involved with precision agriculture ?[73] ? . 76 2.15.3 The use cases for precision agriculture[73] . . . 76 2.16 Smart Farming (SF)[74] . . . . . . . . . . . . .. . . . . . 77 2.17 Internet of Things (IoT) . . . . . . . . . . . . . . . . . . . . . 77 2.17.1 Major components of IoT based Smart Farming[78] . . . 78 2.17.2 IoT Agriculture network architecture[78] . . . . . . . . . . . . 79 2.17.3 The bene…ts of IoT[83] . . . . . . . . . .. . 81 2.17.4 Disadvantages of IoT[83] . . . . . . . . . . . . . . .82 2.18 Smart Agriculture Monitoring (SAM) . . . . . . . . . . . 82 2.19 Overview of Wireless Communication Technologies . . . . . . 83 vi2.19.1 Wireless sensors (WS)[8] . . . . . . . . . . . . . . . 85 2.20 Cloud Computing [98] . . . . . . . . . . . . . . . . . . . 86 2.20.1 Cloud computing categories[98] . . . . . . . . . . . . 86 2.20.2 Deployment Models[98] . . . . . . . . . . . . . . . . . . 87 2.20.3 Advantages of Cloud Computing[98] . . . . . . . . .. 87 2.20.4 Disadvantages of the Cloud [98] . . . . . . . . . . . . 88 2.21 AGRICULTURAL DRONES . . . . . . . . . . . . . . . . . . 88 2.22 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . 88 3 PHASE-3- REALIZATION AND IMPLEMENTATION 90 3.1 Introduction . . . . . . . . . . . . . . . . . 91 3.2 Description of the prototype . . . . . . . . . . . . . . . . . . .92 3.3 Conception of the system . . . . . . . . . . . . . . . . . .. . 93 3.4 Materials and methods . . . . . . . . . . . . . . . . . . . 94 3.5 How systems work ? . . . . . . . . . . . . . . . . . . . . . . . 96 3.6 Development of Experimental Setup[86] . . . . . . . . . . .. . 98 3.6.1 Field Sensors . . . . . . . . . . . . . . . . . . . 98 3.6.2 Microcontroller . . . . . . . . . . . . . . . . . . . . 98 3.6.3 Wireless Communication Technologies and Protocols . . . . . . . . 98 3.6.4 Field Actuators . . . . . . . . . . . . . . . . . . 98 3.7 Description Architecture IoT used[86] . . . . . . . . . . . . . . 99 3.7.1 The transmitter section (TX) . . . . . . . . . . . . . . 99 3.7.2 The receiver section (RX) . . . . . . . . . . . . .. . 99 3.7.3 Field Estimation for Deployment Sensors . . . . . . . . 101 3.8 Applications of the proposed methodology . . . . . . . . . . . 102 3.8.1 Plant and crop management . . . . . . . . . . . . . . . . 102 3.8.2 Crop disease and pest management . . . . . . . .. 103 3.8.3 Crop recommendation[106] . . . . . . . . . . . . . . . 103 vii3.8.4 Soil monitoring[8] . . . . . . . . . . 10 3.8.5 Fertilizer system . . . . . . . . . . . . . . . . . . . . 104 3.8.6 Irrigation system . . . . . . . . . . . . . . . 105 3.8.7 Weed detection. . . . . . . . . . . . . . . . . . . . . . 106 3.8.8 Advantages of the system[110] . . . . . . . . . . . . . . 106 3.9 IoT sensors . . . . . . . . . . . . . . . . . . . . . . . . . 106 3.9.1 NPK sensor . . . . . . . . . . . . . . . . . . . . . . 106 3.9.2 The DHT . . . . . . . . . . . . . . . . . . . . . . . 107 3.9.3 Soil Moisture Sensor[35] . . . . . . . . . . .. . 107 3.9.4 Rain sensor[114] . . . . . . . . . . . . . . . . . . . 108 3.9.5 Raspberry Pi[115] . . . . . . . . . . . . . 108 3.9.6 NODEMCU[35] . . . . . . . . . . . . . 110 3.10 Software and Libraries used . . . . . . . . . . .. . . . . 111 3.10.1 Python [110] . . . . . . . . . . . . . . . . . . . 111 3.10.2 TensorFlow[35] . . . . . . . . . . . . . . . . . .. 113 3.10.3 PyTorch . . . . . . . . . . . . . . . . . . . . 113 3.10.4 Scikit-learn . . . . . . . . . . . . . . . 114 3.10.5 Keras . . . . . . . . . . . . . . . . . . . 114 3.10.6 OpenCV[79] . . . . . . . . . . . . . . . . . . . . . . 114 3.11 Platforms Used . . . . . . . . . . . . . . . . . . . . 115 3.11.1 Google Colab Notebook . . . . . . . . . . . . . 115 3.11.2 Kaggle Notebook . . . . . . . . . . . . . . . . . . 115 3.12 Algorithm prediction of plant disease using sensor and camera . . . 116 3.13 Training Models [35] . . . . . . . . . . . . . . . . . .. . . 117 3.14 Dataset Description . . . . . . . . . . . . . . . . . . .. . . . 118 3.14.1 Dataset preparation . . . . . . . . . . . . 119 3.14.2 Problematic situations and indicative cases[77] . . . . . . . 120 viiiTable of contents 3.15 Analysis and Design . . . . . . . . . . . . . . . . . . 120 3.15.1 System Architecture . . . . . . . . . . . . . . . . . 120 3.15.2 Use Case Diagram . . . . . . . . . . . . . . . . 121 3.15.3 Sequence Diagram . . . . . . . . . . . . . . . . . 122 3.16 Implementation . . . . . . . . . . . . . . . . . . . 123 3.16.1 Results and Discussion . . . . . . . . . . . .. . 123 3.16.2 Plagiarism . . . . . . . . . . . . . . . 172 3.17 Conclusion . . . . . . . . . . . . . .. . . . . 172 3.18 Conclusion : . . . . . . . . . . . . . . 175 Bibliographie 177 Annexe A : Abbreviations and notation 190 i |
Disponibilité (1)
| Cote | Support | Localisation | Statut |
|---|---|---|---|
| MINF/866 | Mémoire master | bibliothèque sciences exactes | Consultable |
