Advanced Machine Learning for Industrial Applications (AMaLIA) | Aug. 2023 – Dec. 2026
AMaLIA develops advanced AI and machine learning techniques for timely, high-impact industrial applications. The project is supported by the National Science Foundation (NSF) through the Center for Big Learning (CBL). As a Postdoctoral Researcher, I serve as Co-PI across multiple work packages.

ANSE: AI-Native Software Engineering | Jan. 2026 – Oct. 2026
ANSE is developing an AI-native method for software development built around human–AI collaboration, in which generative AI proposes solutions and a symbolic reasoning layer verifies them. The project is run by Tampere University (GPT-Lab) and the University of Jyväskylä and funded by Business Finland. As a part-time Postdoctoral Research Fellow, I worked on adapting time-series AI models to generative AI contexts.

Generative Artificial Intelligence in Business Support (GENT) | Feb. 2025 – Dec. 2025
GENT brought generative AI and large language model expertise to companies in the Satakunta region. As a part-time Postdoctoral Researcher at Tampere University (GPT-Lab), I developed methods to support regional companies and increase AI adoption.

H2TRAIN | Feb. 2024 – Jan. 2025
The EU-funded H2TRAIN project advanced digital health and lifestyle technologies through innovative biosensors. I developed novel AI algorithms for anomaly detection.

Untangling People Flow | Feb. 2024 – Jan. 2025
The project studied how data from physical spaces can be integrated into digital twins. I collaborated with researchers to develop new methods for this data integration.

Haltian Carbon Handprint Research Program | Feb. 2024 – Jan. 2025
The program helped Haltian and its global customers reduce their carbon footprint by putting the carbon handprint practice into use. As Principal Scientist, I developed concepts and services built on AI-driven real-time anomaly detection and optimization to improve operational efficiency.

Brain Neural-Like Analysis of Multimodal Data | Dec. 2022 – Dec. 2023
Funded by the Foundation for Economic Education, this project applied brain-inspired neural analysis to multimodal data. I led the research, developing a robust multimodal data description framework and intelligent decision-making strategies for real-time modelling in complex multisensory environments.

Mental Health and Productivity Boosting in the Workplace (Mad@Work) | Sep. 2021 – Sep. 2023
This ITEA Smart Health project focused on detecting and mitigating poor mental health conditions, such as work stress and burnout, before they result in a diagnosed disorder. It involved 19 partners from 5 countries. I developed stress detection algorithms for different work settings.

Co-Botics: Intelligent Cooperating Robots and Humans (Phase 1 and Phase 2) | Aug. 2017 – Aug. 2020
The project applied advanced machine learning and pattern recognition to enable shared intelligent cooperation between robots and humans. It received €230,000 in funding from Business Finland, with support from the NSF-funded Center for Visual and Decision Informatics (CVDI). I developed a novel multimodal technique with smart decision strategies.

Virpa-D | Aug. 2018 – Aug. 2019
Virpa-D explored how activity-based environments will be realized in the future workplace and how they promote well-being at work. More than 30 companies with their subcontractors and five research institutes took part in the four Virpa projects. I developed a machine learning-based satisfaction index for working spaces.

Noise-Specific Speech Denoising | Sep. 2013 – Jun. 2015
The project improved speech denoising for telecommunication systems using speaker- and noise-specific algorithms. It was supported by Türk Telekom and carried out at the Vision and Pattern Analysis Lab at Sabanci University. We proposed and developed a method called “Recognize and Separate”, which adapts to the environment by identifying the noise in an audio signal and then removing it.

Audio Source Recognition | Sep. 2014 – May 2015
Funded by Sensornet in the Netherlands, this project enhanced an audio noise source identification system using a one-class classifier. I developed a real-time machine learning model that classifies audio events as target or outlier. The work formed a core part of my MS thesis.

Sentiment Analysis of Review Text | Sep. 2013 – Mar. 2014
Undertaken as a machine learning challenge during my coursework at Sabanci University, this project scored tweets by polarity on a scale from −1 (very negative) to +1 (very positive). I experimented with a range of classifiers and regression algorithms to address the problem.

Facility Monitoring and Management (FMM) | Aug. 2011 – Apr. 2012
During my undergraduate studies at FAST NUCES, I developed the FMM system, which allows remote control of electronic equipment via mobile phones. I presented it at Imperial College London in 2012 during the London International Youth Science Forum.