Master thesis proposal: Deep learning for detection of coffee berry disease
Climate change brings along problems for farmers around the world. Assisting
agriculture using AI to make farming more resilient may become an important
step towards adapting to the new normal. Limiting the uncertainties and risks
in food production can substantially improve the situation for many farmers,
and increases the availability and robustness of food supplies. Deep learning
is one of the most important tools in the AI toolbox, and has shown impressive
results on many tasks on data of different modalities, not the least for
Coffee berry disease (CBD) affects Arabica coffee plants, and is caused by
the fungus Colletotrichum kahawae. CBD is one major factor hindering coffee
production on the African continent. The spread of CBD is highly dependent on
rainfall, temperature, and humidity, and has been affected by climate change.
In this master thesis , you will develop and train predictive models for
detecting coffee berry disease using computer vision and deep learning. The
work will include training models using images of infected and uninfected
plants and berries. Techniques will include convolutional neural networks,
transfer learning, domain adaptation, and few-shot learning. You will work in
close collaboration with our deep learning research group and experts in
agriculture from Mpendakazi Agribusiness in Tanzania. The work requires
students with an excellent skill set within machine learning, image
processing, and statistical inference. You will be expected to start out with
a literature study, and then start with simpler models and eventually extend
or develop upon more advanced solutions. As this is a master thesis project
with a research organization, we will help you reach a high level of research
excellence, and a successful project may result in writing a joint research
paper in addition to the master thesis.
J. Arun Pandian, V. Dhilip Kumar, Oana Geman, Mihaela Hnatiuc, Muhammad
Arif, and K. Kanchanadevi. Plant Disease Detection Using Deep
Convolutional Neural Network.
https: // www. google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=&ved=2ahUKEwj3iILp75P6AhVIposKHVayBoQFnoECAsQAQ&url=https: // www. mdpi.com/2076-3417/12/14/6982/pdf&usg=AOvVaw1tQg7vl
Jahnavi Kolli; Dhara Mohana Vamsi; V. M. Manikandan. Plant Disease
Detection using Convolutional Neural Network.
https: // ieeexplore.ieee.org/document/9673493
Experience of implementing machine learning models.
Courses in mathematical statistics, probability theory or similar.
Programming skills. Preferably with some experience of relevant frameworks
such as Pytorch, Keras, or Tensorflow.
Supervisor: Olof Mogren (firstname.lastname@example.org) and Aleksis Pirinen
Start date: Spring 2023
Location: Gothenburg or Lund
Credits: 30 ECTS
RISE Center for Applied AI Research connects AI research within RISE
Research Institutes of Sweden. We are around 60 researchers working on machine
learning related tasks within different fields including natural language
processing, computer vision and network analysis.
RISE is Sweden's research institute. Through our international
collaboration programmes with industry, academia and the public sector, we
ensure the competitiveness of the Swedish business community on an
international level and contribute to a sustainable society. Our 2,800
employees engage in and support all types of innovation processes.
The Deep Learning Research Group is connected to RISE Center for Applied
AI Research working on modern AI and machine learning. We have solid expertise
in the field of deep learning, computer vision, federated learning,
uncertainty quantification, and privacy-preserving machine learning.
Keywords: machine learning, deep learning, computer vision, climate
change, smart agriculture
Welcome with your application!
If you have questions, please contact email@example.com. We will interview
suitable candidates as applications are received. Please send in your
application as soon as possible. Last day of application is 30th of November.
Note that all applications for this position must go through our recruitment
system Varbi. We do not accept applications by email.
Göteborg eller Lund
Visstidsanställning 3-6 månader
Student - examensarbete/praktik
Skicka in din ansökan