John Martinsson
Doctoral Student at RISE Research Institutes of Sweden
Sweden
Summary
👤
Senior🎓
Top SchoolJohn Martinsson is a doctoral student and research scientist with 11 years of experience applying machine learning and deep learning to audio and visual sensing problems. Based in Sweden, he combines doctoral-level research in spectral and time-frequency analysis with practical deployments of sensor-driven soundscape monitoring to quantify biodiversity and ecosystem change. His work spans academic collaborations (including a visiting stint at Tampere University on active learning for bioacoustics) and applied research at RISE, bridging novel algorithms and real-world annotation workflows. He has a strong foundation in algorithms and probabilistic modeling from Chalmers University of Technology and prior software engineering roles that shaped robust tooling for data collection and visualization. Open to funding collaborations, he’s particularly interested in scaling continuous acoustic and visual sensor networks to make human impacts on nature measurable. A less obvious strength is his blend of deep technical expertise and hands-on experience building annotation-efficient ML pipelines that reduce labeling costs while improving ecological insight.
11 years of coding experience
1 year of employment as a software developer
Master's degree, Computer Science, Algorithms, Languages and Logic, Master's degree, Computer Science, Algorithms, Languages and Logic at Chalmers University of Technology
Stackoverflow
13reputation
8kreached
1answer
2questions
Github Skills (16)
prediction10
lstm10
convolutional-neural-networks10
recurrent-neural-networks10
classifier10
audio-classification9
diabetes9
time-frequency7
audio6
audio-processing6
discord-net6
spectrogram5
deep-learning5
machine-learning5
ecommerce4
Programming languages (3)
Github contributions (5)
johnmartinsson/differentiable-mel-spectrogram
Mar 2023 - Dec 2024
The official implementation of DMEL the method presented in the paper "DMEL: The differentiable log-Mel spectrogram as a trainable layer in neural networks".
Contributions:4 PRs, 78 pushes, 1 branch in 1 year 9 months
neural-networkspectrogramaudio-classificationaudio-processingmachine-learning
johnmartinsson/blood-glucose-prediction
Jun 2018 - Mar 2021
Blood glucose prediction using long short-term memory recurrent neural networks.
Contributions:84 commits, 37 pushes, 1 comment in 2 years 9 months
recurrent-neural-networkslstmblood-glucosediabetesprediction
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.