publications

2022

1. An Intelligent Clinical Decision Support System for a Rapid Intrapartum Cardiotocography Interpretation

   Kizito Nkurikiyeyezu, and Ayako Kasai

   In U.S - Africa Frontiers of Science, Engineering, and Medicine symposium, 2022
2. Book chapter

   Toward the Prediction of Environmental Thermal Comfort Sensation Using Wearables

   Tahera Hossain, Kizito Nkurikiyeyezu, Yusuke Kawasaki, and 1 more author

   In , Jun 2022

   Abs

   Thermal comfort is a state of mind in which one is satisfied with the thermal environment that is crucial to human well-being, safety, and productivity in everyday life. Indoor environmental thermal comfort levels usually change due to performing different activities in different situations. Computer systems that can understand these comfort indicators can help to support and increase human wellbeing. This paper considers a simple wristwatch-like device equipped with various sensors to collect autonomic nervous system activity data. This study offers a preliminary assessment of a physiologically regulated thermal comfort provision based on Pulse Rate Variability (PRV) to see if we could predict the comfort of a hot environment (risk of heatstroke, higher dissatisfaction/more difficult to cope than cold). Therefore, we focus on collecting data in varying temperatures and humidity levels for different work conditions i.e., reading, typewriting, and gymnastics focusing on hot thermal conditions to predict human-environmental thermal comfort using multiple machine learning models. Our results show an average accuracy above 95% with five different machine learning models.

3. Journal

   Leveraging artificial intelligence and data science techniques in harmonizing, sharing, accessing and analyzing SARS-COV-2/COVID-19 data in Rwanda (LAISDAR Project): study design and rationale

   Aurore Nishimwe, Charles Ruranga, Clarisse Musanabaganwa, and 20 more authors

   BMC Medical Informatics and Decision Making, Jun 2022

   Abs

   Since the outbreak of COVID-19 pandemic in Rwanda, a vast amount of SARS-COV-2/COVID-19-related data have been collected including COVID-19 testing and hospital routine care data. Unfortunately, those data are fragmented in silos with different data structures or formats and cannot be used to improve understanding of the disease, monitor its progress, and generate evidence to guide prevention measures. The objective of this project is to leverage the artificial intelligence (AI) and data science techniques in harmonizing datasets to support Rwandan government needs in monitoring and predicting the COVID-19 burden, including the hospital admissions and overall infection rates.

2021

1. tiny Talk

   Offline Prediction of Cholera in Rural Communal Tap Waters Using Edge AI inference

   Marvin Ogore, Kizito Nkurikiyeyezu, and Jimmy Nsenga

   In tinyML EMEA Tech. Forum 2021, Jun 2021

   Abs

   Africa accounts for 54% of the world disease burden due to lack of access to safe drinking water, with the majority of rural area populations or endemic zones getting access to water through potentially unsafe community tap waters. Unfortunately the expensive laboratory processes and resources used in water processing centers to detect water-borne diseases like cholera cannot be massively deployed on all those taps to guarantee safe water for everyone, anywhere at any time. Thanks to the Internet of Things (IoT) and Artificial Intelligence (AI), the prediction of water-bone cholera can be done by monitoring water’s physicochemical patterns. However, related state of the art IoT/AI solutions rely on a cloud-centric architecture with edge sensors sending collected water data to the cloud for inferencing. Unfortunately, all time internet connectivity is not guaranteed in rural areas and low latency detection is mandatory to not delay the consumption. This paper presents a prototyping design and development of an offline edge AI rapid water-bone cholera detector kit pluggable into existing taps to lower the cost of mass deployment.

2. Book chapter

   ExerSense: Real-Time Physical Exercise Segmentation, Classification, and Counting Algorithm Using an IMU Sensor

   Shun Ishii, Kizito Nkurikiyeyezu, Mika Luimula, and 2 more authors

   In Activity and Behavior Computing, Jun 2021

   Abs PDF

   Even though it is well known that physical exercises have numerous emotional and physical health benefits, maintaining a regular exercise routine is quite challenging. Fortunately, there exist technologies that promote physical activity. Nonetheless, almost all of these technologies only target a narrow set of physical activities (e.g., either running or walking but not both) and are only applicable either in indoor or in outdoor environments, but do not work well in both environments. This paper introduces a real-time segmentation and classification algorithm that recog-nizes physical exercises and that works well in both indoor and outdoor environments. The proposed algorithm achieves a 95% classification accuracy for five indoor and outdoor exercises, including segmentation error. This accuracy is similar or better than previous works that handled only indoor workouts and those use a vision-based approach. Moreover, while comparable machine learning-based approaches need a lot of training data, the proposed correlation-based method needs one sample of motion data of each target exercises.

3. Book chapter

   Classification of Eating Behaviors in Unconstrained Environments

   Kizito Nkurikiyeyezu, Haruka Kamachi, Takumi Kondo, and 3 more authors

   In Communications in Computer and Information Science, Jun 2021

   Abs HTML

   Obesity and its numerous devastating consequences are on the rise globally. While widespread tactics to fight against obesity often focus on healthy eating, how the food is consumed is oftentimes overlooked even though convincing evidence attests that merely eating slowly and properly chewing one’s meal significantly reduces obesity. This research introduces a method that recognizes common human actions during mealtime—namely, food chewing, food swallowing, drink swallowing, and talking. The proposed system is unobtrusive. It uses a cheap and small bone conduction microphone to collect intra-body sound and a smartphone that provides feedback in real-time. Our proposed approach achieves similar performances (Accuracy = 97.5%, Specificity = 98.0%, Precision = 83.8%, Recall = 91.7%, F1 score = 87.2%, and MCC = 0.85) as those achieved by the most recent state of the art models even though our system uses modest machine learning models.

2020

1. Journal

   Effect of Person-specific Biometrics in Improving Generic Stress Predictive Models

   Kizito Nkurikiyeyezu, Anna Yokokubo, and Guillaume Lopez

   Sensors and Materials, Feb 2020

   Abs

   Because stress is subjective and is expressed differently from one person to another, generic stress prediction models (i.e., models that predict the stress of any person) perform crudely. Only person-specific ones (i.e., models that predict the stress of a preordained person) yield reliable predictions, but they are not adaptable and costly to deploy in real-world environments. For illustration, in an office environment, a stress monitoring system that uses person-specific models would require collecting new data and training a new model for every employee. Moreover, once deployed, the models would deteriorate and need expensive periodic upgrades because stress is dynamic and depends on unforeseeable factors. We propose a simple, yet practical and costeffective calibration technique that derives an accurate and personalized stress prediction model from physiological samples collected from a large population. We validate our approach on two stress datasets. The results show that our technique performs much better than a generic model. For instance, a generic model achieved only a 42.5%±19.9% accuracy. However, with only 100 calibration samples, we raised its accuracy to 95.2%±0.5%. We also propose a blueprint for a stress monitoring system based on our strategy, and we debate its merits and limitation. Finally, we made public our source code and the relevant datasets to allow other researchers to replicate our findings.

2. Ph.D. thesis

   Affect-Aware Intelligent Thermal Comfort Environments

   Kizito Nkurikiyeyezu

   Aoyama Gakuin University, Mar 2020

   Abs HTML PDF

   Despite almost a century of research on thermal comfort, its provision is still based on fundamentally flawed assumptions, achieves a lackluster performance, and requires excessive energy to operate. Indeed, the leading thermal comfort model\backslashtextemdash the PMV model\backslashtextemdash is inaccurate because it was inferred from highly controlled experiments; thus, it is oblivious of important real-life factors that influence thermal comfort. The successor to the PMV model\backslashtextemdash the adaptation model\backslashtextemdash has assumptions that are at odds with social norms and business etiquette. Furthermore, the adaptation model has very permissive comfort zones to the extent that it may lead to thermal discomfort primary because winter cold waves, long hot summers and heatwaves push the adaptation beyond human’s physiological adaptations limits. Finally, while existing personalized approaches allow the users to manually set their thermal preferences, hand-operated control leads to rebound and overshoot. Consequently, it is often suggested that an optimum personalized thermal comfort approach needs to automatically estimate and provide thermal comfort with little or no user interaction. This thesis proposes a novel technique that provides an energy-efficient and personalized thermal comfort based on the fluctuations in heartbeat patterns. Indeed, humans have thermoregulation processes that maintain their core temperature at a specific constant. Thermoregulation involves massive changes in blood circulation. For instance, in hot conditions, blood circulation to the skin significantly increases in order to enhance heat dissipation through the skin. Conversely, in cold environments, blood circulation is restricted in order to reduce heat dissipation. As a result, this thesis hypothesizes that heart rate variability~(HRV) would be an accurate and genuine indicator of thermal comfort. The proposed approach has two main advantages. First, unlike existing personalized approaches\backslashtextemdash which are manually controlled or depend on predetermine settings\backslashtextemdash the proposed approach is self-adaptive. It uses the estimated thermal comfort and creates a duplex communication between the personal thermal comfort actuators (e.g., air conditioning units, chair warmers, and a neck cooler) and its users in order to provide a real-time thermal comfort that reflects each individual’s thermal expectations. Secondly, a few parts of the body (e.g., head, wrists, and feet) are mostly responsible for one’s overall thermal comfort. That being so, the proposed approach\backslashtextemdash unlike e.g., air conditioning units which cool or warm an entire room, including its walls and furniture, and regardless of the number of people present\backslashtextemdash would be energy-efficient because it would make it possible to create a microclimate comfort zone around a person and to channel the comfort only to the parts of the body that are most sensitive to thermal comfort. The research conducted in this thesis confirms these hypotheses. In summary, it was observed that indoor thermal conditions influence people’s heart rate variability and that it is possible to reliably (with an accuracy }\textgreater}95\backslash%) predict the subjects’ thermal comfort. These results led to the development of a prototype of a thermal comfort provision system that infers an individual’s thermal comfort from a photoplethysmogram (PPG) signal recorded on a wrist. Nevertheless, because thermal comfort is expressed differently from one person to another, the proposed approach would only work if person-specif machine learning models were developed for each user of the system. Such limitations would be costly for large scale development. Hence, an algorithm that mitigates this limitation was developed. The thesis also investigates the interplay between thermal comfort and stress and concludes with the suggestion that, although both thermal comfort and stress affect a person’s HRV, thermal comfort and stress have different etiologies and physiological responses. Ergo, their effect on a person’s HRV is perhaps non-overlapping and that the two can be distinguished by, e.g., a machine learning model. Finally, the thesis coins the concept of \backslashenquote{affect-aware thermal comfort} as a 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 adjusts itself in order to satisfy their implicit and explicit needs (in terms of, e.g., thermal comfort, ventilation, well-being, and productivity) and in a sustainable way (in terms of e.g., heating, ventilation and cooling efficiency, and lighting).

3. Journal

   Effect of Person-specific Biometrics in Improving Generic Stress Predictive Models

   Kizito Nkurikiyeyezu, Anna Yokokubo, and Guillaume Lopez

   Sensors and Materials, Feb 2020

   Abs HTML PDF

   Because stress is subjective and is expressed differently from one person to another, generic stress prediction models (i.e., models that predict the stress of any person) perform crudely. Only person-specific ones (i.e., models that predict the stress of a preordained person) yield reliable predictions, but they are not adaptable and costly to deploy in real-world environments. For illustration, in an office environment, a stress monitoring system that uses person-specific models would require collecting new data and training a new model for every employee. Moreover, once deployed, the models would deteriorate and need expensive periodic upgrades because stress is dynamic and depends on unforeseeable factors. We propose a simple, yet practical and costeffective calibration technique that derives an accurate and personalized stress prediction model from physiological samples collected from a large population. We validate our approach on two stress datasets. The results show that our technique performs much better than a generic model. For instance, a generic model achieved only a 42.5%±19.9% accuracy. However, with only 100 calibration samples, we raised its accuracy to 95.2%±0.5%. We also propose a blueprint for a stress monitoring system based on our strategy, and we debate its merits and limitation. Finally, we made public our source code and the relevant datasets to allow other researchers to replicate our findings.

4. Journal

   Model for Thermal Comfort and Energy Saving Based on Individual Sensation Estimation

   Guillaume Lopez, Takuya Aoki, Kizito Nkurikiyeyezu, and 1 more author

   Sensors and Materials, Feb 2020

   Abs HTML

   In office spaces, the ratio of energy consumption of air conditioning and lighting for maintaining the environment comfort is about 70%. On the other hand, many people claim being dissatisfied with the temperature of the air conditioning. Therefore, there is concern about work efficiency reduction caused by the current air conditioning control. In this research, we propose an automatic control system that improves both energy saving and thermal comfort of all indoor users by quantifying individual differences in thermal comfort from vital information, on the basis of which the optimal settings of both air conditioning and wearable systems that can directly heat and cool individuals are determined. Various environments were simulated with different room sizes, numbers of users in a room, and heating/cooling conditions. The simulation results demonstrated the efficiency of the proposed system for both energy saving and comfort maximization.

2019

1. ACII

   Affect-aware thermal comfort provision in intelligent buildings

   Kizito Nkurikiyeyezu, Anna Yokokubo, and Guillaume Lopez

   In 2019 8th International Conference on Affective Computing and Intelligent Interaction, Sep 2019

   Abs HTML PDF

   Predominant thermal comfort provision technologies are energy-hungry, and yet they perform crudely because they overlook the requisite precursors to thermal comfort. They also fail to exclusively cool or heat the parts of the body (e.g., the wrist, the feet, and the head) that influence the most a person’s thermal comfort satisfaction. Instead, they waste energy by heating or cooling the whole room. This research investigates the influence of neck-coolers on people’s thermal comfort perception and proposes an effective method that delivers thermal comfort depending on people’s heart rate variability (HRV). Moreover, because thermal comfort is idiosyncratic and depends on unforeseeable circumstances, only person-specific thermal comfort models are adequate for this task. Unfortunately, using person-specific models would be costly and inflexible for deployment in, e.g., a smart building because a system that uses person-specific models would require collecting extensive training data from each person in the building. As a compromise, we devise a hybrid, cost-effective, yet satisfactory technique that derives a personalized person-specific-like model from samples collected from a large population. For example, it was possible to double the accuracy of a generic model (from 47.77% to 96.11%) using only 400 person-specific calibration samples. Finally, we propose a practical implementation of a real-time thermal comfort provision system that uses this strategy and highlighted its advantages and limitations.

2. Symposium

   Optimization Method of Thermal Comfort and Energy Saving Based on Individual Sensation Estimation

   Takuya Aoki, Kizito Nkurikiyeyezu, Guillaume Lopez, and 1 more author

   Multimedia, Distributes, Cooperative, and Mobile Symposium, Sep 2019

   Abs

   In office-occupied spaces, the ratio of energy consumption by air-conditioning and lighting that maintains the environment comfort accounts for about 70%. On the other hand, many people claim being dissatisfied with the temperature of the air conditioning. Therefore, there is concern about the work efficiency reduction caused by current air-conditioning control. In this research, we propose an automatic control system that both improves the energy saving and the thermal comfort of all indoor users by quantifying individual differences in thermal comfort from biological information, base on which optimal settings of both air- conditioning system and wearable system that can directly heat and cool individuals. Simulation results in various environments demonstrated the efficacy of proposed system for both energy saving and comfort maximization. 1.

3. Conference

   Importance of individual differences in physiological-based stress recognition models

   Kizito Nkurikiyeyezu, Anna Yokokubo, and Guillaume Lopez

   In Proceedings - 2019 15th International Conference on Intelligent Environments, IE 2019, Jun 2019

   Abs HTML

   Stress is well-researched. Still, despite the potential economic and health benefits of a system that continuously monitor people’s stress, there exists no mainstream real-world stress monitoring system. The most reliable methods use a fusion of multi-modal signals. However, these methods are both obtrusive and privacy-invasive. On the contrary, the most practical ones are often based on physiological signals. Nevertheless, while these methods may perform exceptionally well in research field trials, their results are yet to be incorporated in any practical, real-world stress recognition system. This paper argues that many of the published physiological based machine learning stress recognition models may not be practical to be used in real-world settings. The analysis conducted using electrodermal activity (EDA) and heart rate variability (HRV) seems to indicate that physiological-based stress recognition machine learning models perform well when tested on known users. However, they exhibit a high generalization error when tested on unknown users; thus cannot be used in real-world settings without significant tuning. Furthermore, while our results are not conclusive, we showed that it could be possible to design stress recognition system that is based on generic stress recognition models and further tune these models by incorporating the physiological fingerprints of new unseen users.

4. Conference

   Thermal comfort and stress recognition in office environment

   Kizito Nkurikiyeyezu, Kana Shoji, Anna Yokokubo, and 1 more author

   In HEALTHINF 2019 - 12th International Conference on Health Informatics, Proceedings; Part of 12th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2019, Feb 2019

   Abs HTML

   Work stress and thermal discomfort are some of the hurdles that office workers face every day. Office workers experience a periodic work stress because work is long and mentally challenging. At the same time, current thermal comfort provision technologies are inefficient and consume a large amount of energy. In our previous works, we proposed an efficient thermal comfort provision system that is based on a person’s heart rate variability (HRV). However, because work stress can also affect the person’s HRV, this paper investigates the possibility to distinguish HRV changes that are due to thermal discomfort from changes that emanate from work stress. We conducted experiments on subjects taking Advanced Trail Making Test (ATMT) and observed that stress alters HRV and that it is possible to distinguish stressed and non-stressed subjects with a 100% accuracy. We validated our method on the multimodal SWELL knowledge work (SWELL-KW) stress dataset and achieved similar results (99.25% accuracy and 99.75% average recall). Further analysis suggests that, although both thermal comfort and work stress affect HRV, their effect is perhaps non-overlapping, and that the two can be distinguished with a near-perfect accuracy. These results indicate that it could be possible to design an automatic and unobtrusive system that delivers thermal comfort and predicts work stress based on people’s HRV.

2018

1. Journal

   Heart rate variability as a predictive biomarker of thermal comfort

   Kizito N. Nkurikiyeyezu, Yuta Suzuki, and Guillaume F. Lopez

   Journal of Ambient Intelligence and Humanized Computing, Aug 2018

   Abs HTML PDF

   Thermal comfort is an assessment of one’s satisfaction with the surroundings; yet, most mechanisms that are used to provide thermal comfort are based on approaches that preclude physiological, psychological and personal psychophysics that are precursors to thermal comfort. This leads to many people feeling either cold or hot in an environment that was supposed to be thermally comfortable to most users. To address this problem, this paper proposes to use heart rate variability (HRV) as an alternative indicator of thermal comfort status. Since HRV is linked to homeostasis, we conjectured that people’s thermal comfort could be more accurately estimated based on their heart rate variability (HRV). To test our hypothesis, we analyzed statistical, spectral, and nonlinear HRV indices of 17 human subjects doing light office work in a cold, a neutral, and a hot environment. The resulting HRV indices were used as inputs to machine learning classification algorithms. We observed that HRV is distinctively different depending on the thermal environment and that it is possible to reliably predict each subject’s thermal state (cold, neutral, and hot) with up to a 93.7% accuracy. The result of this study suggests that it could be possible to design automatic real-time thermal comfort controllers based on people’s HRV.

2. Journal

   Conceptual Design of a Collective Energy-Efficient Physiologically-Controlled System for Thermal Comfort Delivery in an Office Environment

   Kizito Nkurikiyeyezu, Yuta Suzuki, Pierre Maret, and 2 more authors

   SICE Journal of Control, Measurement, and System Integration, Jul 2018

   Abs HTML PDF

   Despite their high energy consumption, office thermal comfort delivery mechanisms perform poorly. The recently enacted environmental protection policies, which require a significant cutback in greenhouse gas emission, can only exacerbate this situation because, given the limitations of current thermal comfort provision technologies, a reduc- tion in energy would translate into an increased thermal discomfort in offices. Hence, this dilemma entails alternative thermal comfort delivery systems that provide higher quality thermal comfort at lower energy. This paper proposes to use physiologically-controlled thermal comfort controllers to achieve this. It also discusses advantages of this novel ap- proach, highlights potential unobtrusive thermal comfort biomarkers, and presents the necessary steps in designing such systems. Finally, the paper briefly discusses some of our preliminary results that show the feasibility of such a system.

3. Journal

   Development and evaluation of a low-energy consumption wearable wrist warming device

   Guillaume Lopez, Takahiro Tokuda, Manami Oshima, and 3 more authors

   International Journal of Automation Technology, Nov 2018

   Abs HTML PDF

   Today in Japan, comfortable lifestyle and environment realized by abundant electric power is being questioned by energy consumption reduction policies called “cool biz” in summer, and “warm biz” in winter. One reason of these policies is the bad energy consumption efficiency of current air-conditioning systems that cool or warm indirectly human body. Several researches have been investigating the effect of direct human body cooling and warming. However, most proposed solutions focus on direct head or neck cooling, using ice to cool a water circulating system, such temperature during use cannot be controlled accurately nor adapted to user and environment conditions. Recently, a Japanese research team developed a portable system using Peltier elements that can both cool and warm neck. Though cooling was demonstrated to affect positively both physiological and psychological state in summer heat environment, in cold climate it could be confirmed for only neck warming but not feet and hands. In our objective of developing effective energy saving technology for direct temperature-conditioning of human body, and in order to reduce the discomfort caused by body chillness, we have proposed and developed a Peltier element based wrist-mounted wearable device that directly warms human body. A first experimental study showed how wrist warming rhythm affects hyperthermic sensation. Then, we verified whether the thermal sensation of the body, including the extremities, is improved by changing the position where the wrist is warmed.

4. Conference

   Development of a Wearable Thermo-Conditioning Device Controlled by Human Factors Based Thermal Comfort Estimation

   Guillaume Lopez, Kazuto Takahashi, Kizito Nkurikiyeyezu, and 1 more author

   In Proceedings - 2018 12th France-Japan and 10th Europe-Asia Congress on Mechatronics, Mecatronics 2018, Sep 2018

   Abs HTML

   Today in Japan, comfortable lifestyle and environment realized by abundant electric power is being questioned by energy consumption reduction policies called "cool biz" in summer, and "warm biz" in winter. One reason of these policies is the bad energy consumption efficiency of current airconditioning systems that cool or warm indirectly human body. Several researches have been investigating the effect of direct human body cooling and warming. However, most proposed solutions focus on direct head or neck cooling, using ice to cool a water circulating system, such temperature during use cannot be controlled accurately nor adapted to user and environment conditions. If the system can automatically perform the optimum warming and cooling operation, it becomes also possible to present an optimum thermal cooling environment for children and physically handicapped persons who have difficulties to control cooling/warming operation by their own will. In our objective of developing effective energy saving technology for direct thermal conditioning of human body, we have proposed and developed a Peltier element based neck-mounted wearable device that directly cools or warms human body based on estimation of user’s thermal sensation by biological information. The thermal sensation estimation algorithm was tested in an environment where the thermal sensation of Cold, Neutral, and Hot can be obtained. Obtained thermal sensation estimation was in accordance with the subjective thermal sensation from each subject. However, temperature range while wearing the device was 28 to 38°C, when ideal cooling/warming function is 20 to 40°C.

5. Journal

   Development and evaluation of a low-energy consumption wearable wrist warming device

   Guillaume Lopez, Takahiro Tokuda, Manami Oshima, and 3 more authors

   International Journal of Automation Technology, Nov 2018

   Abs HTML

   Today in Japan, comfortable lifestyle and environment realized by abundant electric power is being questioned by energy consumption reduction policies called “cool biz” in summer, and “warm biz” in winter. One reason of these policies is the bad energy consumption efficiency of current air-conditioning systems that cool or warm indirectly human body. Several researches have been investigating the effect of direct human body cooling and warming. However, most proposed solutions focus on direct head or neck cooling, using ice to cool a water circulating system, such temperature during use cannot be controlled accurately nor adapted to user and environment conditions. Recently, a Japanese research team developed a portable system using Peltier elements that can both cool and warm neck. Though cooling was demonstrated to affect positively both physiological and psychological state in summer heat environment, in cold climate it could be confirmed for only neck warming but not feet and hands. In our objective of developing effective energy saving technology for direct temperature-conditioning of human body, and in order to reduce the discomfort caused by body chillness, we have proposed and developed a Peltier element based wrist-mounted wearable device that directly warms human body. A first experimental study showed how wrist warming rhythm affects hyperthermic sensation. Then, we verified whether the thermal sensation of the body, including the extremities, is improved by changing the position where the wrist is warmed.

6. Book Chapter

   Toward a Real-Time and Physiologically Controlled Thermal Comfort Provision in Office Buildings

   Kizito Nkurikiyeyezu, and Guillaume Lopez

   In The 14th International Conference on Intelligent Environments, Jun 2018

   Abs

   Thermal comfort is, by definition, a personal and subjective psychological sensation. Still, its provision in office buildings relies on underperforming and energyhungry Heating Ventilation and Air Conditioning (HVAC) units that preclude people’s personal preferences. This leads to people reporting a high discontent with the built environment. This study provides a preliminary evaluation of a physiologically controlled thermal comfort provision based on Pulse Rate Variability (PRV). The study is based on a premise that thermally uncomfortable environments affect temperature homeostasis in humans. This change in homeostasis is indirectly detected by e.g. the variability of the heart’s beat-to-beat intervals. We experimented on a user sitting in two thermal environments (cold and neutral) to estimate PRV via a photoplethysmogram (PPG) signal recorded on his wrist. The result of the experiment shows that it is possible to predict the user’s thermal state in real-time with an accuracy exceeding 90%. Hence, the paper constitutes a prima facie evidence of the possibility of designing real-time physiologically controlled thermal conditioning systems.

7. Conference

   Smartphone Application Usage Prediction Using Cellular Network Traffic

   Naoto Mizumura, Kizito Nkurikiyeyezu, Hiroki Ishizuka, and 2 more authors

   2018 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2018, Jun 2018

   Abs

   The exponential rise of cellular network traffic demand due to an increased use of hand-held devices requires optimized methods to plan and deliver the necessary network bandwidth. In this paper, we propose to use cellular network traffic generated by smartphone applications to predict which applications the user is likely to be using. We conducted two experiments to assert such feasibility. In one controlled experiment required the users to use applications according to heuristic application usage guidelines. In the other experiment, the subjects were encouraged to use their phone as they normally would. In all cases, we recorded the session time, the uplink and downlink traffic and which applications are running. We subsequently used machine learning algorithms to assess the feasibility of predicting the running applications. We achieved 99% accuracy in the controlled traffic experiment. However, the performance was much lower in the arbitrary traffic monitoring experiment. This preliminary analysis may suggest that it could be possible for cellular network providers to predict what application users are running based on their real-time network usage. This would be in turn used for cellular network optimization and planning.

8. Symposium

   Méthode adaptative et personnalisée d’optimisation d’énergie et du confort thermique en temps réel

   Kizito Nkurikiyeyezu, and Guillaume Lopez

   Jun 2018

2017

1. Conference

   Heart rate variability as an indicator of thermal comfort state

   Kizito N. Nkurikiyeyezu, Yuta Suzuki, Yoshito Tobe, and 2 more authors

   In 2017 56th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2017, Sep 2017

   Abs HTML

   Thermal comfort is a personal assessment of one’s satisfaction with the surroundings. Yet, most thermal comfort delivery mechanisms preclude physiological and psychological precursors to thermal comfort. Accordingly, many people feel either cold or hot in an environment that is supposedly thermally comfortable to most people. To address this issue, this paper proposes to use people’s heart rate variability (HRV) as an alternative indicator of thermal comfort. Since HRV is linked to homeostasis, we hypothesize that it could be used to predict people’s thermal comfort status. To test our hypothesis, we analyzed statistical, spectral, and nonlinear HRV indices of 17 human subjects doing light office work in a cold, a neutral, and a hot environment. The resulting HRV indices were used as inputs to machine learning classification algorithms. We observed that HRV is distinctively altered depending on the thermal environment and that it is possible to steadfastly predict each subject’s thermal environment (cold, neutral, and hot) with up to a 93.7% prediction accuracy. The result of this study implies that it could be possible to design automatic real-Time thermal comfort controllers based on people’s HRV.

2015

1. Journal

   Toolkits for Real Time Digital Audio Signal Processing Teaching Laboratory

   Kizito Nkurikiyeyezu, Faustin Ahishakiye, Cyprien Nsengimana, and 1 more author

   Journal of Signal and Information Processing, Sep 2015

   Abs HTML

   This paper describes an audio digital signal-processing toolkit that the authors develop to supplement a lecture course on digital signal processing (DSP) taught at the department of Electrical and Electronics Engineering at the University of Rwanda. In engineering education, laboratory work is a very important component for a holistic learning experience. However, even though today there is an increasing availability of programmable DSP hardware that students can largely benefit from, many poorly endowed universities cannot afford a costly full-fledged DSP laboratory. To help remedy this problem, the authors have developed C#.NET toolkits, which can be used for real-time digital audio signal processing laboratory. These toolkits can be used with any managed languages, like Visual Basic, C#, F# and managed C++. They provide frequently used modules for digital audio processing such as filtering, equalization, spectrum analysis, audio playback, and sound effects. It is anticipated that by creating a flexible and reusable components, students will not only learn fundamentals of DSP but also get an insight into the practicability of what they have learned in the classroom.