Information and communication technologies for agriculture theme II : data / / edited by Dionysis D. Bochtis [and four others]

• Record Nr.: UNINA9910552715003321
• Pubbl/distr/stampa: Cham, Switzerland : , : Springer, , [2022]; ©2022
• ISBN: 3-030-84148-0
• Descrizione fisica: 1 online resource (296 pages)
• Collana: Springer Optimization and Its Applications ; ; v.183
• Disciplina: 630.2085
• Soggetti: Agricultural informatics; Enginyeria agronòmica; Innovacions agrícoles; Internet de les coses; Aplicacions industrials; Congressos; Llibres electrònics
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Nota di bibliografia: Includes bibliographical references.
• Nota di contenuto: Intro -- Preface -- Contents -- Part I: Data Technologies -- You Got Data Now What: Building the Right Solution for the Problem -- 1 Introduction -- 2 Sensors and Their Readings -- 3 Networks of Sensors -- 3.1 In-Field Crop Production -- 3.2 Intensive Crop Production -- 3.3 Intensive Animal Production -- 4 Using Machine Learning -- 5 Remaining Challenges and Opportunities -- References -- Data Fusion and Its Applications in Agriculture -- 1 Introduction -- 2 Data Fusion -- 2.1 Introduction -- 2.2 The ``Whys´´ and ``Wherefores´´ of Information Fusion -- 2.3 Information Fusion: Methods, Techniques, and Algorithms -- 2.4 Models of Data Fusion -- Architectures and Performance Aspects -- Data Alignment and Fusion of Attributes -- 2.5 Applications of Information Fusion in Agriculture -- Remote Sensing Image Preprocessing -- Restoration and Denoising -- Pixel-based Classification -- Spectral Feature Classification -- Classification with Spatial Information -- Target Recognition -- Scene Understanding -- 2.6 Data Mining and Artificial Intelligence in Agriculture -- Yield ; Prediction -- Disease Detection -- Weed Detection -- Species Recognition -- 3 Conclusions and Future Challenges -- References -- Machine Learning Technology and Its Current Implementation in Agriculture -- 1 Introduction -- 2 Machine Learning Versus Conventional Programming -- 3 Fundamental Features of Machine Learning -- 4 Types of Machine Learning Methods -- 4.1 Supervised Learning -- Regression -- Classification -- 4.2 Unsupervised Learning -- Clustering -- Dimensionality Reduction -- Association -- 4.3 Reinforcement Learning -- Classification -- Control -- 4.4 Recommender Systems (Active Learning) -- Content-based -- Collaborative Filtering -- 5 Families of Machine Learning Algorithms -- 5.1 Regression -- 5.2 Regularization -- 5.3 Bayesian -- 5.4 Instance-based -- 5.5 Decision Tree.; 5.6 Ensemble -- 5.7 Clustering -- 5.8 Dimensionality Reduction -- 5.9 Association Rule -- 5.10 Artificial Neural Networks -- 5.11 Deep Neural Networks -- 6 Machine Learning in Agriculture -- 6.1 Yield Prediction -- 6.2 Crop Disease Detection -- 6.3 Weed Detection -- 6.4 Quality Assessment -- 7 Summary of the Basic Aspects of the Reviewed Studies -- 8 Conclusions -- References -- Part II: Applications -- Application Possibilities of IoT-based Management Systems in Agriculture -- 1 Introduction -- 1.1 Data Acquisition and Management in Agriculture -- 2 Methodology -- 3 Progression and Evaluation of the System -- 3.1 The Main Characteristics Based on the Literature -- 3.2 Determining the Possibilities from a Practical Standpoint -- Data Acquisition Systems -- Data Management Methods and Applications -- Data Utilization -- 4 Discussion -- 5 Conclusions -- References -- Plant Species Detection Using Image Processing and Deep Learning: A Mobile-Based Application -- 1 Introduction -- 2 Background Research -- 2.1 Deep Learning -- 3 Methodology -- 3.1 Dataset and Data Preparation -- Background Removal -- Data Augmentation -- 4 Software Development and Analysis -- 5 Detailed Design and Software Implementation -- 5.1 Developing Convolutional Neural Network -- 5.2 Online Classification System App -- 6 Testing and Evaluation -- 7 Discussion and Future Work -- 8 Conclusions -- References -- Computer Vision-based Detection and Tracking in the Olive Sorting Pipeline -- 1 Introduction -- 1.1 Industrial Sorters -- 2 Problem Description -- 2.1 Related Work -- 3 The Proposed Olive Separation Approach -- 3.1 Image Binarization -- 3.2 Distance Transform -- 3.3 Watershed Transform -- 3.4 Centroid Extraction -- 3.5 Multiple Object Tracking -- 4 The Unscented Kalman Filter -- 4.1 Prediction Phase of the UKF -- 4.2 Update Phase of the UKF.; 5 The Kuhn-Munkres (Hungarian) Algorithm -- 6 Results -- 6.1 Sample Collection -- 6.2 Simulation Design -- 6.3 Results Using Kalman Filtering -- 7 Evaluation of the Results -- 8 Conclusions -- References -- Integrating Spatial with Qualitative Data to Monitor Land Use Intensity: Evidence from Arable Land - Animal Husbandry Systems -- 1 Introduction -- 1.1 Land Use Intensity and Farming Systems -- 1.2 Land Use/Land Cover (LULC) Extraction -- 2 Methodology -- 2.1 Study Area -- 2.2 Materials and Methods -- Timeline of Changes -- Remote Sensing Data -- 2.3 Participatory Workshop -- 3 Results and Discussion -- 3.1 Image Processing -- 3.2 Land Cover Type Extraction and Change Detection -- 3.3 Land Conversions -- 3.4 Results from Qualitative Methods -- 3.5 Comparison and Synthesis of Results -- 3.6 Farming Systems and Land Use Intensity -- 4 Conclusion: Ways Forward in Integrating Qualitative Data in Land Use Intensity -- References -- Air drill Seeder Distributor Head Evaluation: A Comparison between Laboratory Tests and Computational Fluid Dynamics Simulatio... -- 1 Introduction -- 2 Materials and Methods -- 2.1 Tested Model ; Description -- 2.2 Description of Distributor Head´s Test Bench -- 2.3 Experiment Design -- 2.4 Numerical Simulations -- Air-Seeds Mixture Flow -- Air Flow -- Particles Trajectory -- Discrete Phase Model Setup -- 3 Results -- 3.1 Experimental Results -- 3.2 Numerical Results -- 3.3 Validation of the Numerical Model -- 4 Conclusions and Perspectives -- References -- Part III: Value Chain -- Data-Based Agricultural Business Continuity Management Policies -- 1 Introduction -- 2 Motivation -- 2.1 Business Intelligence Tools as Business Continuity Solutions in the Modern Era -- 2.2 Business Continuity and Big Data Challenges in the Agricultural Domain -- 2.3 Research Steps -- 3 Tools and Methods -- 3.1 Formulation of Datasets.; 3.2 Business Intelligence Multidimensional Data Models - Preliminary Concepts -- 3.3 Business Process Modelling Notation (BPMN) for Supporting Business Decisions Based on Multidimensional Data -- 3.4 A Robust Machine Learning Agricultural Business Continuity Classifier -- 4 Results -- 4.1 The Multidimensional Data Models for Supporting Agricultural Business Continuity Management Decisions -- Model 1: The Criticality Levels Multidimensional Model -- Model 2: The Risks/Hazards Multidimensional Model -- 4.2 Machine Learning Predictive Analytics Based on the Proposed Multidimensional Schemas -- Data Preprocessing -- Risk Exposure Classification Based on Decision Tree Induction -- Boosting the Risk Exposure classifier´s Predictive Power with the 10-Fold Cross-Validation and the Random Forest Techniques -- 5 Discussion -- 6 Conclusions -- References -- Soybean Price Trend Forecast Using Deep Learning Techniques Based on Prices and Text Sentiments -- 1 Introduction -- 2 Related Work -- 2.1 Price Prediction of Agricultural Commodities -- 2.2 Deep Learning for Price Trend Prediction -- 2.3 Deep Learning for Text Sentiment Analysis -- 3 Methodology -- 4 Results -- 4.1 Models Considering Only Prices -- 4.2 Models Considering Only Text Sentiments -- 4.3 Ensemble Model Considering Prices and Text Sentiments -- 5 Discussion -- 5.1 Benefits of Deep Learning for Agricultural Price Prediction -- 5.2 Adaptation and Uses for Other Products -- 6 Conclusions -- References -- Use of Unsupervised Machine Learning for Agricultural Supply Chain Data Labeling -- 1 Introduction -- 2 Unsupervised Machine Learning in Agriculture -- 3 Methodology -- 4 Results -- 5 Discussion -- 5.1 Training Time for Each Model -- 5.2 Implementation Difficulties -- 5.3 Benefits for SC Traceability -- 5.4 Adaptation to Other SCs -- 6 Conclusions -- References.