Ionian University
Ανάπτυξη στοχαστικών αλγορίθμων και μοντέλων μηχανικής μάθησης για την εξέλιξη πληθυσμών: εφαρμογή στον δάκο της ελιάς
Abstract
dc:descriptionIn the present dissertation, stochastic algorithms and machine learning models are developed for the prediction of population evolution and in particular for the evolution of the olive fruit fly population. The olive fruit fly is a parasitic insect that depends on the fruit of the olive tree for the perpetuation of its species, thus causing great damage, if its population remains unchecked, in the production of olive-based products, such as olive oil and table olives. The presence of the insect has been recorded in all olive-producing countries, and due to its dependence on climatic conditions (temperature, humidity) the total number of generations that arise varies from region to region. In this context, as far as stochastic algorithms are concerned, the software for simulating the temporal and spatial evolution of the population of the olive fruit fly based on real measurements in the field is initially presented. Then, the development and comparison of three models of dispersion of the olive fruit fly based on the fruiting of the olive grove is described and finally, the influence of the presence of microclimates, on the evolution of the population of the olive fruit fly, is studied, through simulation, using the aforementioned software, and how, in this context, the evolution of the olive fruit fly population is affected by the application of the usual practices of controlling the population. Continuing, in the use of machine learning methods, initially, the use of environmental conditions to predict the next olive fruit fly trap measurement, given the knowledge of the previous measurement, and a comparison of the performance of four characteristic vectors using various machine learning algorithms is examined. The development of a model for the automatic identification of the olive fruit, and therefore automatic counting, in images of the contents of the McPhail trap, which is commonly used as a method of control and an exacerbation indicator of the population of the olive fruit fly, is presented. Finally, the use of machine learning methods for the identification of microclimates, is examined, which would help to predict outbreaks of infestation of the olive fruit fly in the olive grove depending on the time of year and the climatic characteristics of each microclimate. In conclusion, conclusions are drawn about the performance of the aforementioned experiments and possible directions are pointed out that future research could focus on.
Degree
thesis:*- Grantor dc:publisher
- Ionian University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Kalamatianos-Vourov, Romanos
- Καλαματιανός-Βουρόβ, Ρωμανός
Subjects
dc:subject × 14- Δάκος της ελιάς
- Μηχανική μάθηση
- Στοχαστικοί αλγόριθμοι
- Olive fruit fly
- Machine learning
- Stochastic algorithms
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Φυσικές Επιστήμες
- Τεχνητή νοημοσύνη
- Επιστήμη ηλεκτρονικών υπολογιστών και Πληροφορική, άλλοι τομείς
- Computer and Information Sciences
- Natural Sciences
- Artificial Intelligence
- Computer and Information sciences, miscellaneous
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/50945