| Titre : | An Enhanced Intelligent System For Palm Tree Mites Disease Forecasting |
| Auteurs : | CHAIB Aimen, Auteur ; Salim Bitam, Directeur de thèse |
| Editeur : | Biskra [Algérie] : Faculté des Sciences Exactes et des Sciences de la Nature et de la Vie, Université Mohamed Khider, 2024 |
| Format : | 1vol.(98p.) / ill., couv. ill. en coul / 30 cm |
| Langues: | Anglais |
| Mots-clés: | IOT, Deep learning, Forecasting, Data center, Boufaroua. |
| Résumé : |
Algeria’s palm plantations face significant challenges due to the spread of palm pests, most notably the mite, which causes serious damage to palm crops, as it can result in significant losses of production in dry and hot years. The insect in its spread depends on appropriate environmental conditions, making its fight a continuing challenge for farmers. In Algeria, palm is a basic agricultural crop on which the local economy relies heavily. Palms are not only a major source of dates, but also a part of the country’s cultural and agricultural heritage. However, these crops face increasing threats from agricultural pests, resulting in reduced productivity and increased costs for farmers. The fight against the mite is complicated for several reasons. First, it is difficult to detect an injury in its early stages using traditional visual examination. Infection develops rapidly, making it difficult for farmers to determine the right time to take effective control action. Secondly, controlling the spread of the insect requires the use of chemical or biological pesticides, which may be costly and difficult to apply widely. Furthermore, agricultural pests increase farmers’ operational costs, including pesticide and labour costs for their application. These increased costs adversely affect the totalprofitability of farms, increasing economic pressures on Algeria’s agricultural sector. To address these challenges, our project came as an innovative solution based on AI, IoT and software engineering. The system provides accurate and early predictions of the spread of the mite, helping farmers take appropriate preventive action in a timely manner. Data are collected from sensors scattered on farms, and analyzed using deep learning models to provide accurate predictions. Thanks to this system, farmers can reduce reliance on manual inspection and costly chemical treatments. The system contributes to improved crop management, increased productivity and reduced economic losses. This integrated solution not only improves the efficiency of pest control, but also promotes agricultural sustainability and helps sustain the local economy. |
| Sommaire : |
List of Figures 1
List of Tables 1 List of Abbreviations 1 General introduction 1 1 Overview 3 1.1 Internet of Things . . . . . . . 3 1.1.1 IoT definition . . . . . . 3 1.1.2 IoT Characteristics . . . . . . . . . 4 1.1.3 IoT Architecture . . . . .. . 5 1.2 Back-end Development . . . . . . 6 1.2.1 Back-end Development Components . . . . . . . . . 6 1.3 O. afrasiaticus -Boufaroua- 11 1.3.1 The Period of appearance of the Boufaroua . . . . . . . . . . . . . . 12 1.3.2 The weather factors of appearance of the DPM -Tolga- . . . . . . . 13 1.4 Conclusion . 16 2 Related Work 17 2.1 Date palm spider mite(Oligonychus afrasiaticus McGregor) forecasting and monitoring system . . . . . 17 2.1.1 Material and Methods . . . . . 17 2.1.2 Results . . . 18 2.2 Classification of Palm Trees Diseases using Convolution Neural Network . 20 2.2.1 Materials and Methods . . . . 21 2.3 Development and Validation of Innovative Machine Learning Models for Predicting Date Palm Mite Infestation on Fruits . . . . . . . . . . . . . . 22 2.3.1 Materials and Methods . . . . . . . 22 2.4 Relationship of Date Palm Tree Density to Dubas Bug Ommatissus lybicus Infestation in Omani Orchards . . . . . . . . . . . . 25 2.4.1 Study area . . . . . . . . . . . . . . . . 25 2.5 Design of a new Intelligent System for Early Prediction of Date palm spider mite (Boufaroua) . . . . . . . . . . . . . 27 2.5.1 Overall system architecture . . . . . . . . . . 27 2.5.2 Overall system operation . . . . . . 27 2.5.3 Methodology . . . . . . . . . . . . . 30 3 Design of the Suggested System 31 3.1 Introduction . . . . . . . . . . . . 31 3.2 Context and objective . . . . . . . . . . . . 31 3.3 Overall system architecture . .. . . . 31 3.3.1 IoT Dispositif (Station) . . . . . . . . . 32 3.3.2 Data Center and Hosted Servers . . . .. . . . 32 3.3.3 AI Models . . . . . . . . . . . . . .. . . 32 3.3.4 Mobile Application (alert system) . . . . . .. . . 32 3.4 Overall system preparation . . . . . . . . . 33 3.5 Methodology . . . . . . . 3.5.1 Data center configuration (Packtriot) . . . . . . . . . . . . . . . . . 33 3.5.2 Data center manager . . . . . . . . . . . . . . . . . . . . . . . . . . 34 3.5.3 Models development . . . . . . . . . . . . . . . . . . . . . . . . . . 35 3.5.4 Mobile application development . . . . . . . . . . . . . . . . . . . . 43 3.5.5 Hardware construction (Our stations) . . . . . . . . . . . . . . . . . 45 3.6 UML diagrams . . . . . . . . . . 46 3.6.1 Class diagrams . . . .. . . 46 3.6.2 Sequence diagrams . . . . . . . . 47 3.6.3 Use case diagram . . . . . .. . . 49 3.7 Conclusion . . . . .. . . . 49 4 Coding, Experiments and Results 50 4.1 Introduction . . . . . . . . . 50 4.2 Software tools . . . . . . . . 50 4.2.1 Programming languages, libraries and frameworks . . . . . . 50 4.2.2 Databases . . . . . . . . . . . . . . 53 4.2.3 Cloud and deployment . . . . . 53 4.3 Hardware . . . . . . . 54 4.3.1 LILYGO T-SIMA7670SA R2 ESP32 . . . . . . . . . . . . . . . . . 54 4.3.2 DHT22 sensor . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 4.3.3 Module Sensor rain water drop detector Pic Arduino FC-37 YL-83 . 56 4.3.4 Capacitive soil moisture sensor v1.2 . . . .. . . . . . . . . . 56 4.3.5 Module GPS GY-NEO6MV2 V2 . . . . . . . . . . 57 4.3.6 Solar panel 6v 0.8w and 3.7 V 2200 mAh rechargeable lithium-ion battery . . . . . . . . . .. . . . 57 4.4 Implementation . . . . . . . . . . . 57 4.4.1 Data center configuration and its UI manager and deployment . . . 57 4.4.2 AI models details and deployment . .. . . . . . . 67 4.4.3 Mobile application . . . . . .. . . . . . . . . . 78 4.4.4 Hardware implementation . . . . . . . . . . 81 4.5 Conclusion . . . . . . . . . . . . . . . . 83 General conclusion 84 Bibliography 85 Univ- |
| Type de document : | Mémoire master |
Disponibilité (1)
| Cote | Support | Localisation | Statut |
|---|---|---|---|
| MINF/894 | Mémoire master | bibliothèque sciences exactes | Consultable |
