Michal Muszynski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Michal Muszynski has a total of 54 co-authors. Here are the top co-authors by number of shared publications:
- Thomas Brunschwiler
IBM Research Europe, Zurich, Switzerland
4 shared publications - Jonas Weiss
IBM Research Europe, Switzerland
3 shared publications - Leimin Tian
Faculty of Engineering, Monash University, Melbourne, Australia
3 shared publications - Adam Ivankay
IBM Research - Europe, Zurich, Switzerland
2 shared publications - Christian F. Clarenbach
Faculty of Medicine, University of Zurich, Zurich, Switzerland
2 shared publications - Dario Kohlbrenner
HP2 Laboratory, INSERM, Grenoble Alpes University, CHU Grenoble Alpes, Grenoble, France
2 shared publications
Latest Publications
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 814-817
HRAI 2025: The 1st Workshop on Holistic and Responsible Affective Intelligence
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 814-817
Open AccessHRAI 2025: The 1st Workshop on Holistic and Responsible Affective Intelligence
- Open Access
- 1 December 2024
- Published by Taylor & Francis in International Journal of Chronic Obstructive Pulmonary Disease
- Vol. ume 19, 2739-2750
Hybrid Virtual Coaching and Telemonitoring in COPD Management: The CAir Randomised Controlled Study
Objective: To investigate the effectiveness of 12-weeks hybrid virtual coaching on health-related quality-of-life (HrQoL) in patients with stable COPD. Methods: We equipped all patients with a CAir Desk for telemonitoring, the intervention group additionally received hybrid virtual coaching through the built-in smartphone. The multimodal intervention based on the Living well with COPD programme, containing educational content, physical activity coaching, and home-based exercises. Primary outcome was HrQoL as measured by the SGRQ. Secondary outcomes were symptom burden, physical activity, functional exercise capacity, and lung function. Between-group differences were calculated using linear regression models, controlling for baseline differences. Results: We included 30 participants with COPD (13/17 women/men; 63 [9] years; FEV1 54 [22] % predicted), 24 (80%) completed the study. SGRQ improved in both groups (intervention: − 4.5 [20.1]; control: − 2.7 [7.4] points) without statistically significant or clinically relevant between-group differences (B = − 2.5 points, 95% CI = − 24.3, 19.3, p = 0.81). Physical activity increased only in the intervention group (313 [1561] vs − 364 [2399] steps) without statistically significant but clinically relevant between-group difference (B = 2147 steps, 95% CI = − 86, 4395, p = 0.06). Symptom burden decreased in both groups (− 4.2 [6.7] vs − 1.0 [2.8] points) without statistically significant but clinically relevant between-group difference (B = − 3.0 points, 95% CI = − 10.8, 5.0, p = 0.43). Conclusion: Twelve-weeks hybrid virtual coaching did not improve HrQoL more than telemonitoring only in patients with stable COPD. The intervention group improved their physical activity and symptom burden clinically relevant more than the control group.
- 1 December 2024
- Published by Taylor & Francis in International Journal of Chronic Obstructive Pulmonary Disease
- Vol. ume 19, 2739-2750
Open AccessHybrid Virtual Coaching and Telemonitoring in COPD Management: The CAir Randomised Controlled Study
Objective: To investigate the effectiveness of 12-weeks hybrid virtual coaching on health-related quality-of-life (HrQoL) in patients with stable COPD. Methods: We equipped all patients with a CAir Desk for telemonitoring, the intervention group additionally received hybrid virtual coaching through the built-in smartphone. The multimodal intervention based on the Living well with COPD programme, containing educational content, physical activity coaching, and home-based exercises. Primary outcome was HrQoL as measured by the SGRQ. Secondary outcomes were symptom burden, physical activity, functional exercise capacity, and lung function. Between-group differences were calculated using linear regression models, controlling for baseline differences. Results: We included 30 participants with COPD (13/17 women/men; 63 [9] years; FEV1 54 [22] % predicted), 24 (80%) completed the study. SGRQ improved in both groups (intervention: − 4.5 [20.1]; control: − 2.7 [7.4] points) without statistically significant or clinically relevant between-group differences (B = − 2.5 points, 95% CI = − 24.3, 19.3, p = 0.81). Physical activity increased only in the intervention group (313 [1561] vs − 364 [2399] steps) without statistically significant but clinically relevant between-group difference (B = 2147 steps, 95% CI = − 86, 4395, p = 0.06). Symptom burden decreased in both groups (− 4.2 [6.7] vs − 1.0 [2.8] points) without statistically significant but clinically relevant between-group difference (B = − 3.0 points, 95% CI = − 10.8, 5.0, p = 0.43). Conclusion: Twelve-weeks hybrid virtual coaching did not improve HrQoL more than telemonitoring only in patients with stable COPD. The intervention group improved their physical activity and symptom burden clinically relevant more than the control group.
- Open Access
- 21 March 2024
- Published by MDPI AG in Proceedings
- Vol. 97 (1) , 67
HyperTaste Lab—A Notebook with a Machine Learning Pipeline for Chemical Sensor Arrays
The cross-sensitivity of materials in low-selective sensor arrays, namely e-noses and e-tongues, results in a convoluted sensor array response, which renders traditional analytical methods for data processing ineffective. Machine learning approaches can help discover the latent information in such data, and various data processing methods, including unsupervised and supervised techniques, have been proposed to calibrate those devices. In this study, we demonstrate HyperTaste Lab—a notebook with a machine learning pipeline for potentiometric sensor arrays. The ability of the notebook to process raw data produced by model sensor arrays comprising cross-sensitive and/or ion-selective electrodes is demonstrated for the characterization of drinking water and consumer beverages. We describe the modular data processing and machine learning framework that can be applied by sensor researchers to accommodate different signal modalities and perform various downstream tasks, such as the verification of a product’s originality, the estimation of ion concentrations, and the quantitative prediction of sensory descriptors.
- 21 March 2024
- Published by MDPI AG in Proceedings
- Vol. 97 (1) , 67
Open AccessHyperTaste Lab—A Notebook with a Machine Learning Pipeline for Chemical Sensor Arrays
The cross-sensitivity of materials in low-selective sensor arrays, namely e-noses and e-tongues, results in a convoluted sensor array response, which renders traditional analytical methods for data processing ineffective. Machine learning approaches can help discover the latent information in such data, and various data processing methods, including unsupervised and supervised techniques, have been proposed to calibrate those devices. In this study, we demonstrate HyperTaste Lab—a notebook with a machine learning pipeline for potentiometric sensor arrays. The ability of the notebook to process raw data produced by model sensor arrays comprising cross-sensitive and/or ion-selective electrodes is demonstrated for the characterization of drinking water and consumer beverages. We describe the modular data processing and machine learning framework that can be applied by sensor researchers to accommodate different signal modalities and perform various downstream tasks, such as the verification of a product’s originality, the estimation of ion concentrations, and the quantitative prediction of sensory descriptors.
- Open Access
- 22 January 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Symposium Series
- Vol. 2 (1) , 40-45
Sustainable Inference of Remote Sensing Data by Recursive Semantic Segmentation – a Flood Extent Mapping Study
In times of climate change and large machine learning models with petabytes of training data, the demand for responsible AI methodologies is more pressing than ever. This is in-particular true for the vast amount of remote sensing data. Its value to explore and inform about earth processes is of paramount importance, especially in times of global warming. Thus, it is nearly ironic that such applications can be the cause of substantial green-house-gas emissions, through energy demands from compute and communication systems. Thus, this study aims at reducing the data transfer between data centers while maintaining near-real time insights from remote sensing data. A recursive inference approach is introduced consisting of three steps: i) Data pyramid preparation in the host data center (sequence of upscaled raster data). ii) The transfer of low-resolution images to the service data center, where a deep-learning model performs a semantic segmentation task, including an uncertainty estimation. Images of higher resolution are then requested and segmented in a recursive fashion, in areas of high uncertainty only. iii) Finally, the merging of the predictions at different resolutions is performed to result in the final pixel-wise segmentation at scale. The method is demonstrated on synthetic and real-world data for a flood mapping task. A U-Net encoder-decoder model is used for the semantic segmentation task, using Monte-Carlo dropout to result in the uncertainty map. The proof-of-concept demonstrated a 35-38% performance gain per transferred pixel compared to high-resolution image segmentation only. Further, we perform a scaling study to estimate the true potential of the recursive inference approach, indicating the potential to reduce a data transfer by up to 98%, considering four hierarchy levels in the data pyramid. With this study, we hope to have contributed a small but important step towards sustainable machine learning.
- 22 January 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Symposium Series
- Vol. 2 (1) , 40-45
Open AccessSustainable Inference of Remote Sensing Data by Recursive Semantic Segmentation – a Flood Extent Mapping Study
In times of climate change and large machine learning models with petabytes of training data, the demand for responsible AI methodologies is more pressing than ever. This is in-particular true for the vast amount of remote sensing data. Its value to explore and inform about earth processes is of paramount importance, especially in times of global warming. Thus, it is nearly ironic that such applications can be the cause of substantial green-house-gas emissions, through energy demands from compute and communication systems. Thus, this study aims at reducing the data transfer between data centers while maintaining near-real time insights from remote sensing data. A recursive inference approach is introduced consisting of three steps: i) Data pyramid preparation in the host data center (sequence of upscaled raster data). ii) The transfer of low-resolution images to the service data center, where a deep-learning model performs a semantic segmentation task, including an uncertainty estimation. Images of higher resolution are then requested and segmented in a recursive fashion, in areas of high uncertainty only. iii) Finally, the merging of the predictions at different resolutions is performed to result in the final pixel-wise segmentation at scale. The method is demonstrated on synthetic and real-world data for a flood mapping task. A U-Net encoder-decoder model is used for the semantic segmentation task, using Monte-Carlo dropout to result in the uncertainty map. The proof-of-concept demonstrated a 35-38% performance gain per transferred pixel compared to high-resolution image segmentation only. Further, we perform a scaling study to estimate the true potential of the recursive inference approach, indicating the potential to reduce a data transfer by up to 98%, considering four hierarchy levels in the data pyramid. With this study, we hope to have contributed a small but important step towards sustainable machine learning.
- Open Access
- 9 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 84-93
Breathing New Life into COPD Assessment: Multisensory Home-monitoring for Predicting Severity
- 9 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 84-93
Open AccessBreathing New Life into COPD Assessment: Multisensory Home-monitoring for Predicting Severity
- Open Access
- 9 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 814-815
4th International Workshop on Multimodal Affect and Aesthetic Experience
“Aesthetic experience” corresponds to the inner state of a person exposed to the form and content of artistic objects. Quantifying and interpreting the aesthetic experience of people in various contexts contribute towards a) creating context, and b) better understanding people’s affective reactions to aesthetic stimuli. Focusing on different types of artistic content, such as movie, music, literature, urban art, ancient artwork, and modern interactive technology, the 4th international workshop on Multimodal Affect and Aesthetic Experience (MAAE) aims to enhance interdisciplinary collaboration among researchers from affective computing, aesthetics, human-robot/computer interaction, digital archaeology and art, culture, ethics, and addictive games.
- 9 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 814-815
Open Access4th International Workshop on Multimodal Affect and Aesthetic Experience
“Aesthetic experience” corresponds to the inner state of a person exposed to the form and content of artistic objects. Quantifying and interpreting the aesthetic experience of people in various contexts contribute towards a) creating context, and b) better understanding people’s affective reactions to aesthetic stimuli. Focusing on different types of artistic content, such as movie, music, literature, urban art, ancient artwork, and modern interactive technology, the 4th international workshop on Multimodal Affect and Aesthetic Experience (MAAE) aims to enhance interdisciplinary collaboration among researchers from affective computing, aesthetics, human-robot/computer interaction, digital archaeology and art, culture, ethics, and addictive games.
- 16 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
Flood Mapping Using Sentinel-1 Images and Lightweight U-Nets Trained on Synthesized Events
Floods cause loss of lives and multi-billion dollar damages every year. When these events strike, automated tools using remote sensing for quick mapping of the affected areas are critical for planning rescue activities and assessing impact. The most recent techniques to map floods are based on semantic segmentation and deep learning, which require large datasets and ground truth for training, that are difficult to get. To overcome this challenge, we propose an effective method for synthesizing patches of synthetic aperture radar images containing open-land flooded areas. With bi-temporal image acquisitions, we replace portions of land areas in the second acquisition with water pixels borrowed from permanent water bodies. Spatial patterns derived from elevation data help guide the process. With this approach, we build a large dataset with pre and post-event Sentinel-1-based VH-polarized radar intensity images to train deep neural networks to map real-life floods. In a case study, we employ an established U-Net architecture and show that a model version with less than 2% of the number of original parameters achieves almost identical flood detection accuracy. This allows for faster processing and is a clear advantage from an operational perspective. For comparison, we provide empirical segmentation results of four flood cases. F1 scores agree between 0.80 and 0.90 when compared to reference flood maps from the Copernicus service. This confirms that the approach is valuable for mapping areas affected by floods, e.g. during or immediately after catastrophic events, even in areas that were not included during the model training.
- 16 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
Flood Mapping Using Sentinel-1 Images and Lightweight U-Nets Trained on Synthesized Events
Floods cause loss of lives and multi-billion dollar damages every year. When these events strike, automated tools using remote sensing for quick mapping of the affected areas are critical for planning rescue activities and assessing impact. The most recent techniques to map floods are based on semantic segmentation and deep learning, which require large datasets and ground truth for training, that are difficult to get. To overcome this challenge, we propose an effective method for synthesizing patches of synthetic aperture radar images containing open-land flooded areas. With bi-temporal image acquisitions, we replace portions of land areas in the second acquisition with water pixels borrowed from permanent water bodies. Spatial patterns derived from elevation data help guide the process. With this approach, we build a large dataset with pre and post-event Sentinel-1-based VH-polarized radar intensity images to train deep neural networks to map real-life floods. In a case study, we employ an established U-Net architecture and show that a model version with less than 2% of the number of original parameters achieves almost identical flood detection accuracy. This allows for faster processing and is a clear advantage from an operational perspective. For comparison, we provide empirical segmentation results of four flood cases. F1 scores agree between 0.80 and 0.90 when compared to reference flood maps from the Copernicus service. This confirms that the approach is valuable for mapping areas affected by floods, e.g. during or immediately after catastrophic events, even in areas that were not included during the model training.
- Open Access
Multimodal Remote Home Monitoring of Lung Transplant Recipients during COVID-19 Vaccinations: Usability Pilot Study of the COVIDA Desk Incorporating Wearable Devices
Background and Objectives: Remote patient monitoring (RPM) of vital signs and symptoms for lung transplant recipients (LTRs) has become increasingly relevant in many situations. Nevertheless, RPM research integrating multisensory home monitoring in LTRs is scarce. We developed a novel multisensory home monitoring device and tested it in the context of COVID-19 vaccinations. We hypothesize that multisensory RPM and smartphone-based questionnaire feedback on signs and symptoms will be well accepted among LTRs. To assess the usability and acceptability of a remote monitoring system consisting of wearable devices, including home spirometry and a smartphone-based questionnaire application for symptom and vital sign monitoring using wearable devices, during the first and second SARS-CoV-2 vaccination. Materials and Methods: Observational usability pilot study for six weeks of home monitoring with the COVIDA Desk for LTRs. During the first week after the vaccination, intensive monitoring was performed by recording data on physical activity, spirometry, temperature, pulse oximetry and self-reported symptoms, signs and additional measurements. During the subsequent days, the number of monitoring assessments was reduced. LTRs reported on their perceptions of the usability of the monitoring device through a purpose-designed questionnaire. Results: Ten LTRs planning to receive the first COVID-19 vaccinations were recruited. For the intensive monitoring study phase, LTRs recorded symptoms, signs and additional measurements. The most frequent adverse events reported were local pain, fatigue, sleep disturbance and headache. The duration of these symptoms was 5–8 days post-vaccination. Adherence to the main monitoring devices was high. LTRs rated usability as high. The majority were willing to continue monitoring. Conclusions: The COVIDA Desk showed favorable technical performance and was well accepted by the LTRs during the vaccination phase of the pandemic. The feasibility of the RPM system deployment was proven by the rapid recruitment uptake, technical performance (i.e., low number of errors), favorable user experience questionnaires and detailed individual user feedback.
Open AccessMultimodal Remote Home Monitoring of Lung Transplant Recipients during COVID-19 Vaccinations: Usability Pilot Study of the COVIDA Desk Incorporating Wearable Devices
Background and Objectives: Remote patient monitoring (RPM) of vital signs and symptoms for lung transplant recipients (LTRs) has become increasingly relevant in many situations. Nevertheless, RPM research integrating multisensory home monitoring in LTRs is scarce. We developed a novel multisensory home monitoring device and tested it in the context of COVID-19 vaccinations. We hypothesize that multisensory RPM and smartphone-based questionnaire feedback on signs and symptoms will be well accepted among LTRs. To assess the usability and acceptability of a remote monitoring system consisting of wearable devices, including home spirometry and a smartphone-based questionnaire application for symptom and vital sign monitoring using wearable devices, during the first and second SARS-CoV-2 vaccination. Materials and Methods: Observational usability pilot study for six weeks of home monitoring with the COVIDA Desk for LTRs. During the first week after the vaccination, intensive monitoring was performed by recording data on physical activity, spirometry, temperature, pulse oximetry and self-reported symptoms, signs and additional measurements. During the subsequent days, the number of monitoring assessments was reduced. LTRs reported on their perceptions of the usability of the monitoring device through a purpose-designed questionnaire. Results: Ten LTRs planning to receive the first COVID-19 vaccinations were recruited. For the intensive monitoring study phase, LTRs recorded symptoms, signs and additional measurements. The most frequent adverse events reported were local pain, fatigue, sleep disturbance and headache. The duration of these symptoms was 5–8 days post-vaccination. Adherence to the main monitoring devices was high. LTRs rated usability as high. The majority were willing to continue monitoring. Conclusions: The COVIDA Desk showed favorable technical performance and was well accepted by the LTRs during the vaccination phase of the pandemic. The feasibility of the RPM system deployment was proven by the rapid recruitment uptake, technical performance (i.e., low number of errors), favorable user experience questionnaires and detailed individual user feedback.
- Open Access
- 7 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 52-60
Impact of aesthetic movie highlights on semantics and emotions: a preliminary analysis
Aesthetic highlight detection is a challenge for understanding affective processes underlying emotional movie experience. Aesthetic highlights in movies are scenes with aesthetic values and attributes in terms of form and content. Deep understanding of human emotions while watching movies and automatic recognition of emotions evoked by watching movies are critically important for a wide range of applications, such as affective content creation, analysis, and summarization. Many empirical studies on emotions have formulated theory-driven and data-driven models to uncover the underlying mechanism of emotions using discrete ad dimensional paradigms. Nevertheless, these approaches to emotions do not fully reveal all underlying processes of emotional experience. Recent neuroscience findings has led to the development of multi-process frameworks that aim to characterize emotions as a multi-componential phenomena. In particular, multi-process frameworks can be useful to study emotional movie experience. In this work, we carry out statistical analysis of the componential paradigm on emotions while watching aesthetic highlights in full-length movies. We focus on the effect of the aesthetic highlights on intensity of emotional movie experience. We explore occurrence frequency of different semantic categories involved in constructing different types of the aesthetic highlights. Moreover, we investigate the applicability of machine learning classifiers in predicting the aesthetic highlights from movie scene semantics based features.
- 7 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 52-60
Open AccessImpact of aesthetic movie highlights on semantics and emotions: a preliminary analysis
Aesthetic highlight detection is a challenge for understanding affective processes underlying emotional movie experience. Aesthetic highlights in movies are scenes with aesthetic values and attributes in terms of form and content. Deep understanding of human emotions while watching movies and automatic recognition of emotions evoked by watching movies are critically important for a wide range of applications, such as affective content creation, analysis, and summarization. Many empirical studies on emotions have formulated theory-driven and data-driven models to uncover the underlying mechanism of emotions using discrete ad dimensional paradigms. Nevertheless, these approaches to emotions do not fully reveal all underlying processes of emotional experience. Recent neuroscience findings has led to the development of multi-process frameworks that aim to characterize emotions as a multi-componential phenomena. In particular, multi-process frameworks can be useful to study emotional movie experience. In this work, we carry out statistical analysis of the componential paradigm on emotions while watching aesthetic highlights in full-length movies. We focus on the effect of the aesthetic highlights on intensity of emotional movie experience. We explore occurrence frequency of different semantic categories involved in constructing different types of the aesthetic highlights. Moreover, we investigate the applicability of machine learning classifiers in predicting the aesthetic highlights from movie scene semantics based features.
- 27 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 12 (1) , 36-52
Recognizing Induced Emotions of Movie Audiences from Multimodal Information
Recognizing emotional reactions of movie audiences to affective movie content is a challenging task in affective computing. Previous research on induced emotion recognition has mainly focused on using audiovisual movie content. Nevertheless, the relationship between the perceptions of the affective movie content (perceived emotions) and the emotions evoked in the audiences (induced emotions) is unexplored. In this work, we studied the relationship between perceived and induced emotions of movie audiences. Moreover, we investigated multimodal modelling approaches to predict movie induced emotions from movie content based features, as well as physiological and behavioral reactions of movie audiences. To carry out analysis of induced and perceived emotions, we first extended an existing database for movie affect analysis by annotating perceived emotions in a crowd-sourced manner. We find that perceived and induced emotions are not always consistent with each other. In addition, we show that perceived emotions, movie dialogues and aesthetic highlights are discriminative for movie induced emotion recognition besides spectators? physiological and behavioral reactions. Also, our experiments revealed that induced emotion recognition could benefit from including temporal information and performing multimodal fusion. Moreover, our work deeply investigated the gap between affective content analysis and induced emotion recognition by gaining insight into the relationships between aesthetic highlights, induced emotions and perceived emotions.
- 27 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 12 (1) , 36-52
Recognizing Induced Emotions of Movie Audiences from Multimodal Information
Recognizing emotional reactions of movie audiences to affective movie content is a challenging task in affective computing. Previous research on induced emotion recognition has mainly focused on using audiovisual movie content. Nevertheless, the relationship between the perceptions of the affective movie content (perceived emotions) and the emotions evoked in the audiences (induced emotions) is unexplored. In this work, we studied the relationship between perceived and induced emotions of movie audiences. Moreover, we investigated multimodal modelling approaches to predict movie induced emotions from movie content based features, as well as physiological and behavioral reactions of movie audiences. To carry out analysis of induced and perceived emotions, we first extended an existing database for movie affect analysis by annotating perceived emotions in a crowd-sourced manner. We find that perceived and induced emotions are not always consistent with each other. In addition, we show that perceived emotions, movie dialogues and aesthetic highlights are discriminative for movie induced emotion recognition besides spectators? physiological and behavioral reactions. Also, our experiments revealed that induced emotion recognition could benefit from including temporal information and performing multimodal fusion. Moreover, our work deeply investigated the gap between affective content analysis and induced emotion recognition by gaining insight into the relationships between aesthetic highlights, induced emotions and perceived emotions.