Kizito Nkurikiyeyezu

Imagine how a wonderful world it would be if mundane household items had emotional intelligence, empathy, and the ability to adapt their functionality according to their users’ emotions? While such a futuristic world might seem far-fetched and appears to belong to the next episode of an exaggerated plot of a Futurama reboot, a vibrant research group at MIT is busy developing intelligent machines that exhibit innate emotional abilities.

Mymodest research—which pales in comparison to that conducted by the smarter than me folks at the UC Berkeley’s Center for the Built Environment— focuses on affect-aware intelligent environments and pioneers research on intelligent and energy-efficient air-conditioning systems that self-adjust depending on people’s heart rate variability (HRV). In particular, my Ph.D. thesis proposed a novel thermal comfort provision system that estimates people’s thermal comfort level from the variation in their physiological signals (e.g., heart rate variability) due to their bodies’ response to the surrounding environment and uses appropriate constrained optimization algorithms to provide an efficient and personalized thermal comfort at the lowest energy. This approach not only provides higher quality thermal comfort but also significantly reduces the amount of energy required for thermal comfort provision.

My research also investigates the interplay between thermal comfort and stress. The recent result suggests that, although both thermal comfort and stress affect a person’s heart rate variability (HRV), thermal comfort and stress have different etiologies and physiological responses. Ergo, their effect on a person’s HRV is perhaps non-overlapping and the two can be distinguished by, e.g., a machine learning model. Nevertheless, because human affects (e.g., stress and thermal comfort) are expressed differently from one person to another, the proposed approach would only work if person-specific machine learning models were developed for each user of the system. Such limitations would be confining and costly for large-scale deployment. Consequently, I developed an efficient algorithm that mitigates these limitations and I laid the groundwork of an “affect-aware thermal comfort” system complementary to the existing thermal comfort provision methods. An affect-aware system would estimate in real-time the affects (e.g., thermal comfort, stress, and emotion) of its users and automatically adjust itself in order to satisfy the user’s implicit and explicit needs (in terms of, e.g., thermal comfort, ventilation, well-being, and productivity) in a sustainable way (in terms of e.g., heating, ventilation, and cooling efficiency, and lighting).

This website will serve as a vehicle to disseminate my research to the mass. The blog will also help me keep up with the ever evolving technology space, will hopefully help me hone my writing skills, and, occasionally— when the stoic in me gives up— I might even use this blog to express my frustration with my C++ compiler. Finally, since we live in a highly litigious world, it goes without saying that, unless strictly expressed otherwise, all views expressed on this blog are my own and do not necessarily reflect those of my former, current or future employers and any of my associates!

selected publications

  1. Ph.D. thesis
    Affect-Aware Intelligent Thermal Comfort Environments
    Nkurikiyeyezu, Kizito
    2020
  2. ACII
    Affect-aware thermal comfort provision in intelligent buildings
    Nkurikiyeyezu, Kizito, Yokokubo, Anna, and Lopez, Guillaume
    In 2019 8th International Conference on Affective Computing and Intelligent Interaction 2019
  3. Journal
    Effect of Person-specific Biometrics in Improving Generic Stress Predictive Models
    Nkurikiyeyezu, Kizito, Yokokubo, Anna, and Lopez, Guillaume
    Sensors and Materials 2020
  4. Journal
    Heart rate variability as a predictive biomarker of thermal comfort
    Nkurikiyeyezu, Kizito N., Suzuki, Yuta, and Lopez, Guillaume F.
    Journal of Ambient Intelligence and Humanized Computing 2018
  5. Journal
    Conceptual Design of a Collective Energy-Efficient Physiologically-Controlled System for Thermal Comfort Delivery in an Office Environment
    Nkurikiyeyezu, Kizito, Suzuki, Yuta, Maret, Pierre, Lopez, Guillaume, and Itao, Kiyoshi
    SICE Journal of Control, Measurement, and System Integration 2018
  6. Journal
    Development and evaluation of a low-energy consumption wearable wrist warming device
    Lopez, Guillaume, Tokuda, Takahiro, Oshima, Manami, Nkurikiyeyezu, Kizito, Isoyama, Naoya, and Itao, Kiyoshi
    International Journal of Automation Technology 2018
  7. Book chapter
    Classification of Eating Behaviors in Unconstrained Environments
    Nkurikiyeyezu, Kizito, Kamachi, Haruka, Kondo, Takumi, Jain, Archit, Yokokubo, Anna, and Lopez, Guillaume
    2021