Connected health solutions such as an EEG headset or health patch capture enormous amounts of data. How do you turn that into meaningful information and actionable insights? Count on imec to develop the algorithms that make your application truly smart.
Turning raw data into reliable results
Imec develops a lot of algorithms that accurately characterize – often in real time – the collected mass of raw data. It’s a crucial step towards your development of clinical-grade connected health solutions.
These data analysis algorithms perform different data processing steps: from cleaning up noisy data to signal quality prediction. This last function is particularly important in neurotechnology applications, where users need to assess the reliability of the data before starting the procedure.
Extracting actionable insights
Once you have these filtered and reliable data sets, you can mine them for deeper meanings. For example:
- What does the output of several body movement sensors tell us about the revalidation process of a patient?
- How do someone’s skin conductance, skin temperature and acceleration (movement) relate to his stress level?
- Can we derive someone’s emotional state from his EEG readings?
It’s this layer of algorithms that opens the door towards advanced connected health applications that combine unobtrusive monitoring with reliable feedback – encouraging healthy behaviors and lifestyle choices.
Co-designing of algorithms and devices
If we want to integrate medical wearables seamlessly into our active lives, we need to make sure that they:
- don’t rely on a connection to the cloud, but can perform their basic functions off-line
- can get by for hours, days or even weeks on a limited power budget.
That’s why imec, driven by its vision of edge AI, devotes special attention to the co-optimization of device hardware and algorithms – resulting in exceptionally efficient solutions.
Want to join our research? Need an experienced partner to speed up your development?
Publications & Conferences on innovative algorithms
- Schiavone et al. "The Double Layer Methodology and the Validation of Eigenbehavior Techniques Applied to Lifestyle Modeling", BioMed Research International , (2017)
- Grossekathofer et al. "Automated detection of stereotypical motor movements in autism spectrum disorder using recurrence quantification analysis", Frontiers in Neuroinformatics, (2017)
- Smets et al. "Comparing Task-induced Psychophysiological Responses Between Persons with Stress-related Complaints and Healthy Controls: a Methodological Pilot Study", Helath Science Reports, (2018)
- Smets et al. "Large-Scale Wearable Data Reveal Digital Phenotypes for Stress Detection", npj Digital Medicine, (2018)
- Zhai et al. "Ambulatory Smoking Habits Investigation based on Physiology and Context (ASSIST) using wearable sensors and mobile phones: protocol for an observational study", BMJ Open, (2019)
- Simoes-Capela et al. "Towards quantifying the psychopathology of Eating Disorders from the Autonomic Nervous System perspective: a methodological approach", Frontiers in Neuroinformatics, (2019)
- Witteveen et al. "Comparison of a pragmatic and regression approach for wearable EEG signal quality assessment", IEEE Journal of Biomedical and Health Informatics, (2019)
- Blanko-Almazan et al. "Wearable Bioimpedance Measurement for Respiratory Monitoring During Inspiratory Loading", IEEE Access, (2019)
- Steenkiste et al. "Automated Sleep Apnea Detection in Raw Respiratory Signals using Long Short-Term Memory Neural Networks ", IEEE Journal of Biomedical and Health Informatics, (2019)
- Zhang et al. "Motion Artifacts Reduction for Wrist-Worn PPG Devices based on Different Wavelengths", MDPI Sensors, (2019)
- Altini et al. "Cardiorespiratory fitness estimation in free-living using wearable sensors", Artificial Intelligence in Medicine, (2016)
- Altini et al. "Cardiorespiratory fitness estimation using wearable sensors: Laboratory and free-living analysis of context-specific submaximal heart rates", Journal of Applied Physiology, (2016)
- Altini et al. "Estimating Oxygen Uptake During Nonsteady-State Activities and Transitions Using Wearable Sensors", IEEE Journal of Biomedical and Health Informatics, (2016)