Improved Machine Learning Methodology for High Precision Agriculture

Treboux, Jerome; Genoud, Dominique

doi:10.1109/giots.2018.8534558

Cited by 37 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, there have been minimal attempts to analyze these records using new and emerging tools, such as data mining and machine learning. Most new researches have been focused on the implementation of robotic platforms and unmanned aerial and terrestrial vehicles to acquire remote sensing data to obtain information for decision-making related to irrigation scheduling, pest and disease detection or yield estimation, among others [3][4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Modeling of Wine Sensory Profiles and Color of Vertical Vintages of Pinot Noir Based on Chemical Fingerprinting, Weather and Management Data

Fuentes

Torrico

Tongson

et al. 2020

Sensors

View full text Add to dashboard Cite

Important wine quality traits such as sensory profile and color are the product of complex interactions between the soil, grapevine, the environment, management, and winemaking practices. Artificial intelligence (AI) and specifically machine learning (ML) could offer powerful tools to assess these complex interactions and their patterns through seasons to predict quality traits to winegrowers close to harvest and before winemaking. This study considered nine vintages (2008–2016) using near-infrared spectroscopy (NIR) of wines and corresponding weather and management information as inputs for artificial neural network (ANN) modeling of sensory profiles (Models 1 and 2 respectively). Furthermore, weather and management data were used as inputs to predict the color of wines (Model 3). Results showed high accuracy in the prediction of sensory profiles of vertical wine vintages using NIR (Model 1; R = 0.92; slope = 0.85), while better models were obtained using weather/management data for the prediction of sensory profiles (Model 2; R = 0.98; slope = 0.93) and wine color (Model 3; R = 0.99; slope = 0.98). For all models, there was no indication of overfitting as per ANN specific tests. These models may be used as powerful tools to winegrowers and winemakers close to harvest and before the winemaking process to maintain a determined wine style with high quality and acceptability by consumers.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning Modeling of Wine Sensory Profiles and Color of Vertical Vintages of Pinot Noir Based on Chemical Fingerprinting, Weather and Management Data

Fuentes

Torrico

Tongson

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…In this method, RGB images are converted to Hue Saturation Intensity (HIS) image representation. However, in the visible light spectrum, image additional features can also be characterized, and the color cooccurrence features called contrast, homogeneity, energy, and entropy can be obtained by the equations (19), (20), (21) and (22) respectively [19,20]…”

Section: Image Processing and Disease Detectionmentioning

confidence: 99%

Diseased Area Recognition and Pesticide Spraying in Farming Lands by Multicopters and Image Processing System

Pittu¹,

Gorantla²

2020

JESA

View full text Add to dashboard Cite

United Nations indexes that the world's population will increase drastically, it may increase by 20% and it will be around 970 crores by 2050. However this scenario requires 20% more food to serve this much population, but farming land is decreasing due to pollution, industrialization, and globalization. Cultivation these days is more difficult and increasing the labor cost and pesticides. Enough labor is not available, so labor charges are also increasing which reflects in expenditure for cultivation. In regular spraying system pesticides are sprayed in the whole field. This will increase pesticide costs and pollution. In this proposed system image acquiring Multicopter will move in a pre-defined path in the field is given in a Mission planner firmware. UAV while moving along the pre-defined path captures high-quality RGB pictures in the field and those captured images are tagged with a Global Positioning System (GPS). These pictures are processed by the image processing system using MATLAB software at the ground station and actual disease recognition from the database frame is done. Disease recognition is done along with the tag of the specific diseased area in the field. These tags can help the crew to identify the diseased area spot. This diseased area or plant GPS tag information is used for the creation of a path for pesticide spraying Multicopters and will spray the pesticide in a diseased area or a plant in the field. This will lead to the optimal usage of pesticides.

show abstract

“…First, opening transformation removes noise with a succession of erosion and dilation process. Then the closing process applies dilation and erosion to close small missing pixel inside the foreground objects (applied with OpenCV) [23]. These transformations fortify the foreground color and intensity, in this case, the lines of vines.…”

Section: Baseline Descriptionmentioning

confidence: 99%

High Precision Agriculture: An Application Of Improved Machine-Learning Algorithms

Treboux

Genoud

2019

2019 6th Swiss Conference on Data Science (SDS)

Self Cite

View full text Add to dashboard Cite

This paper presents the performances of machine learning algorithms on aerial images object detection for high precision agriculture. The dataset used focuses on geotagged pictures of vineyards. We demonstrate that advanced machine learning methodologies like Decision Tree Ensemble, outperform state-of-the-art image recognition algorithms generally used within the agriculture field. The innovative approach described here improve object detection and obtain an accuracy of 94.27 % which is an increase of more than 4 % compared to the state-ofthe-art. Finally, methodology and possible developments for high precision agriculture are discussed in this study.

show abstract

Improved Machine Learning Methodology for High Precision Agriculture

Cited by 37 publications

References 14 publications

Machine Learning Modeling of Wine Sensory Profiles and Color of Vertical Vintages of Pinot Noir Based on Chemical Fingerprinting, Weather and Management Data

Machine Learning Modeling of Wine Sensory Profiles and Color of Vertical Vintages of Pinot Noir Based on Chemical Fingerprinting, Weather and Management Data

Diseased Area Recognition and Pesticide Spraying in Farming Lands by Multicopters and Image Processing System

High Precision Agriculture: An Application Of Improved Machine-Learning Algorithms

Contact Info

Product

Resources

About