Tymoteusz Cejrowski

Employment History

• Machine Learning Researcher

  Arrow Electronics, 2022-present

• Adjunct, Research Assistant

  Gdańsk University of Technology, 2018-2024

• Machine Learning Engineer

  Inero Software, 2021-2022

• Co-founder, Software Developer

  Smartula - Remote Beekeeping, 2019-2021

• Software Developer

  Dynatrace, 2017-2018

• Embedded Software Developer

  INFO-TECH, 2015-2017

Education

• PhD in Computer Science

  Gdańsk University of Technology, 2017-2024, with honors

• Master's in Computer Science

  Gdańsk University of Technology, 2016-2027, grade: 4.5

• Bachelor's in Robotics and Control Automation

  Gdańsk University of Technology, 2015-2019, grade: 5.0, with honors

Cejrowski Tymoteusz, and Julian Szymański. "Detection of anomalies in bee colony using transitioning state and contrastive autoencoders."

We propose a method for inferring the bee colony state using a contrastive autoencoder and an anomaly detection model. Hive's internal state is modeled with the use of an autoencoder latent vector extended with in-hive temperature dynamics. We test our methodology with a bee feeding experiment where the glucose syrup application was detected and the length of food intake was estimated.

Cejrowski Tymoteusz, and Julian Szymański. "Buzz-based honeybee colony fingerprint."

The Design-of-Experiment (DoA) approach for extracting valuable bee colony audio data is described. With proposed methods, it is possible to precisely define the most distinctive bee hours where unique colony sounds are emitted.

Cejrowski Tymoteusz, Julian Szymański, and Doina Logofătu. "Buzz-based recognition of the honeybee colony circadian rhythm."

Identification of bees circadian rhythm with a use of sound-based analysis. We use bees' buzz that have been analysed using ML algorithms, specifically Mel Frequency Cepstral Coefficients (MFCCs) features with SVM classifier. For the purpose of bees day/night definition, a dedicated electronic system has been developed.

Cejrowski Tymoteusz, et al. "Detection of the bee queen presence using sound analysis."

First work for bees sound analysis where based on acquisited signals we construct the application that is capable to detect an absence of honey bee queen. Specifically we are using SVMs and LPC coding for modeling and feature extraction.

Smartula - Remote Beekeeping

Smartula is a remote beekeeping system that allows beekeepers to monitor their hives from anywhere in the world. The system consists of a set of sensors that collect data on the hive's temperature, humidity, and sound levels, as well as a mobile app that allows beekeepers to access this data in real-time. The system also includes an AI-powered anomaly detection algorithm based on Neural Nets that can alert beekeepers to any potential issues with their hives, such as the presence of pests or diseases. LINK1, LINK2, LINK3

Makawa - printing patterns on coffee foam

Makawa is a coffee printer that uses food-safe ink to print patterns on the foam of cappuccinos and lattes. The printer is controlled via a mobile app that allows users to select from a library of pre-designed patterns or create their own custom designs. LINK1, LINK2