Honey bee conservation using deep learning
Honey bee colony assessment is usually carried out via the laborious manual task of counting and classifying comb cells. Beekeepers perform this task many times throughout the year to asses the colony’s strength and to track its development. As you can imagine, this is an extremely time-consuming and error-prone task.
Thiago da Silva Alves and Jean Metz share their experience with the development of a tool for automatic honeybee colony assessment, the DeepBee.
DeepBee is a tool that encapsulates an image classification pipeline using classical image processing methods and state-of-the-art deep learning and Deep Neural Networks (DNN) for image segmentation and classification. To get to the final solution, they compared 13 distinct DNN architectures and chose the best model based on several metrics. They discuss the steps taken from image collection to the delivery of the final solution, highlighting the mistakes we have done during the process, the hurdles we overtook, and the lessons learned. The project has been developed at the Polytechnic Institute of Bragança.
Thiago da Silva Alves loves to dive deep to create solutions for real problems. In the last three years, during his bachelor in Computer Science, he specialised in Computer Vision, Machine Learning and different applications using Deep Neural Networks. Throughout his master’s in Information Systems, he founded an Artificial Intelligence student group with his supervisors and helped to grow an AI community in his University.
Currently, Thiago works at the Belgian company JArchitects as a Machine Learning Engineer and a junior Consultant. In his free time, he likes to blog, participate in conferences, and exchange experiences about AI with his friends.
Jean Metz started his career in academia, first as a PhD student and later as Adjunct Professor at a Federal University, where he co-created and led the Computational Intelligence Research Group. Since day one, he focused his research on Machine Learning and its applications. After a few years of academic life, he decided to make a career move and landed at the software industry. Now, he can apply his knowledge and skills on more tangible problems.
He has been working as a consultant in Belgium for a few years, where he has helped companies to implement intelligent applications. In the journey, he acquired skills that helped him to design and deliver solutions that create value from data using Machine Learning.
Currently, he is consulting for KBC bank in Belgium. This time, the focus is on Conversational AI and the delivery of a complete data-driven and machine learning backed chatbot platform.