2023

Federated Learning for Activity Recognition: A System Level Perspective. Kalabakov, Stefan; Jovanovski, Borche; Denkovski, Daniel; Rakovic, Valentin; Pfitzner, Bjarne; Konak, Orhan; Arnrich, Bert; Gjoreski, Hristijan in IEEE Access (2023). 11 64442–64457.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
The past decade has seen substantial growth in the prevalence and capabilities of wearable devices. For instance, recent human activity recognition (HAR) research has explored using wearable devices in applications such as remote monitoring of patients, detection of gait abnormalities, and cognitive disease identification. However, data collection poses a major challenge in developing HAR systems, especially because of the need to store data at a central location. This raises privacy concerns and makes continuous data collection difficult and expensive due to the high cost of transferring data from a user’s wearable device to a central repository. Considering this, we explore the adoption of federated learning (FL) as a potential solution to address the privacy and cost issues associated with data collection in HAR. More specifically, we investigate the performance and behavioral differences between FL and deep learning (DL) HAR models, under various conditions relevant to real-world deployments. Namely, we explore the differences between the two types of models when (i) using data from different sensor placements, (ii) having access to users with data from heterogeneous sensor placements, (iii) considering bandwidth efficiency, and (iv) dealing with data with incorrect labels. Our results show that FL models suffer from a consistent performance deficit in comparison to their DL counterparts, but achieve these results with much better bandwidth efficiency. Furthermore, we observe that FL models exhibit very similar responses to those of DL models when exposed to data from heterogeneous sensor placements. Finally, we show that the FL models are more robust to data with incorrect labels than their centralized DL counterparts.
@article{kalabakov2023federated, abstract = {The past decade has seen substantial growth in the prevalence and capabilities of wearable devices. For instance, recent human activity recognition (HAR) research has explored using wearable devices in applications such as remote monitoring of patients, detection of gait abnormalities, and cognitive disease identification. However, data collection poses a major challenge in developing HAR systems, especially because of the need to store data at a central location. This raises privacy concerns and makes continuous data collection difficult and expensive due to the high cost of transferring data from a user’s wearable device to a central repository. Considering this, we explore the adoption of federated learning (FL) as a potential solution to address the privacy and cost issues associated with data collection in HAR. More specifically, we investigate the performance and behavioral differences between FL and deep learning (DL) HAR models, under various conditions relevant to real-world deployments. Namely, we explore the differences between the two types of models when (i) using data from different sensor placements, (ii) having access to users with data from heterogeneous sensor placements, (iii) considering bandwidth efficiency, and (iv) dealing with data with incorrect labels. Our results show that FL models suffer from a consistent performance deficit in comparison to their DL counterparts, but achieve these results with much better bandwidth efficiency. Furthermore, we observe that FL models exhibit very similar responses to those of DL models when exposed to data from heterogeneous sensor placements. Finally, we show that the FL models are more robust to data with incorrect labels than their centralized DL counterparts.}, author = {Kalabakov, Stefan and Jovanovski, Borche and Denkovski, Daniel and Rakovic, Valentin and Pfitzner, Bjarne and Konak, Orhan and Arnrich, Bert and Gjoreski, Hristijan}, journal = {IEEE Access}, keywords = {bertarnrich bjarnepfitzner orhankonak stefankalabakov widehealth}, pages = {64442-64457}, title = {Federated Learning for Activity Recognition: A System Level Perspective}, volume = 11, year = 2023 }

HARE: Unifying the Human Activity Recognition Engineering Workflow. Konak, Orhan; van de Water, Robin; Döring, Valentin; Fiedler, Tobias; Liebe, Lucas; Masopust, Leander; Postnov, Kirill; Sauerwald, Franz; Treykorn, Felix; Wischmann, Alexander; Gjoreski, Hristijan; Luštrek, Mitja; Arnrich, Bert in Sensors (2023). 23(23)
[ BibTeX ] [ URL ] [ DOI ]
 
@article{s23239571, author = {Konak, Orhan and van de Water, Robin and Döring, Valentin and Fiedler, Tobias and Liebe, Lucas and Masopust, Leander and Postnov, Kirill and Sauerwald, Franz and Treykorn, Felix and Wischmann, Alexander and Gjoreski, Hristijan and Luštrek, Mitja and Arnrich, Bert}, journal = {Sensors}, keywords = {bertarnrich orhankonak robinvandewater widehealth}, number = 23, title = {HARE: Unifying the Human Activity Recognition Engineering Workflow}, volume = 23, year = 2023 }

Overcoming Data Scarcity in Human Activity Recognition. Konak, Orhan; Liebe, Lucas; Postnov, Kirill; Sauerwald, Franz; Gjoreski, Hristijan; Luštrek, Mitja; Arnrich, Bert in IEEE EMBC 2023 (2023).
[ BibTeX ]
 
@article{konak2023overcoming, author = {Konak, Orhan and Liebe, Lucas and Postnov, Kirill and Sauerwald, Franz and Gjoreski, Hristijan and Luštrek, Mitja and Arnrich, Bert}, booktitle = {IEEE EMBC 2023}, keywords = {bertarnrich orhankonak widehealth}, organization = {IEEE EMBC}, title = {Overcoming Data Scarcity in Human Activity Recognition}, year = 2023 }

A Real-time Human Pose Estimation Approach for Optimal Sensor Placement in Sensor-based Human Activity Recognition. Konak, Orhan; Wischmann, Alexander; van De Water, Robin; Arnrich, Bert (2023). 1–6.
[ BibTeX ]
 
@inproceedings{konak2023real, author = {Konak, Orhan and Wischmann, Alexander and van De Water, Robin and Arnrich, Bert}, booktitle = {Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence}, keywords = {bertarnrich orhankonak robinvandewater}, pages = {1–6}, title = {A Real-time Human Pose Estimation Approach for Optimal Sensor Placement in Sensor-based Human Activity Recognition}, year = 2023 }

SONAR, a nursing activity dataset with inertial sensors. Konak, Orhan; Döring, Valentin; Fiedler, Tobias; Liebe, Lucas; Masopust, Leander; Postnov, Kirill; Sauerwald, Franz; Treykorn, Felix; Wischmann, Alexander; Kalabakov, Stefan; others in Scientific Data (2023). 10(1) 727.
[ BibTeX ]
 
@article{konak2023sonar, author = {Konak, Orhan and D{ö}ring, Valentin and Fiedler, Tobias and Liebe, Lucas and Masopust, Leander and Postnov, Kirill and Sauerwald, Franz and Treykorn, Felix and Wischmann, Alexander and Kalabakov, Stefan and others}, journal = {Scientific Data}, keywords = {bertarnrich orhankonak stefankalabakov widehealth}, number = 1, pages = 727, publisher = {Nature Publishing Group UK London}, title = {SONAR, a nursing activity dataset with inertial sensors}, volume = 10, year = 2023 }

2022

Unsupervised Activity Recognition Using Trajectory Heatmaps from Inertial Measurement Unit Data. Konak., Orhan; Wegner., Pit; Albert., Justin; Arnrich., Bert (2022). 304–312.
[ BibTeX ] [ URL ] [ DOI ]
 
@conference{icaart22, author = {Konak., Orhan and Wegner., Pit and Albert., Justin and Arnrich., Bert}, booktitle = {Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,}, keywords = {bertarnrich justinalbert orhankonak}, organization = {INSTICC}, pages = {304-312}, publisher = {SciTePress}, title = {Unsupervised Activity Recognition Using Trajectory Heatmaps from Inertial Measurement Unit Data}, year = 2022 }

2020

IMU-Based Movement Trajectory Heatmaps for Human Activity Recognition. Konak, Orhan; Wegner, Pit; Arnrich, Bert in Sensors (Switzerland) (2020). 20(24) 1–15.
[ Abstract ] [ BibTeX ] [ URL ] [ DOI ]
 
Recent trends in ubiquitous computing have led to a proliferation of studies that focus on human activity recognition (HAR) utilizing inertial sensor data that consist of acceleration, orientation and angular velocity. However, the performances of such approaches are limited by the amount of annotated training data, especially in fields where annotating data is highly time-consuming and requires specialized professionals, such as in healthcare. In image classification, this limitation has been mitigated by powerful oversampling techniques such as data augmentation. Using this technique, this work evaluates to what extent transforming inertial sensor data into movement trajectories and into 2D heatmap images can be advantageous for HAR when data are scarce. A convolutional long short-term memory (ConvLSTM) network that incorporates spatiotemporal correlations was used to classify the heatmap images. Evaluation was carried out on Deep Inertial Poser (DIP), a known dataset composed of inertial sensor data. The results obtained suggest that for datasets with large numbers of subjects, using state-of-the-art methods remains the best alternative. However, a performance advantage was achieved for small datasets, which is usually the case in healthcare. Moreover, movement trajectories provide a visual representation of human activities, which can help researchers to better interpret and analyze motion patterns.
@article{Konak2020, abstract = {Recent trends in ubiquitous computing have led to a proliferation of studies that focus on human activity recognition (HAR) utilizing inertial sensor data that consist of acceleration, orientation and angular velocity. However, the performances of such approaches are limited by the amount of annotated training data, especially in fields where annotating data is highly time-consuming and requires specialized professionals, such as in healthcare. In image classification, this limitation has been mitigated by powerful oversampling techniques such as data augmentation. Using this technique, this work evaluates to what extent transforming inertial sensor data into movement trajectories and into 2D heatmap images can be advantageous for HAR when data are scarce. A convolutional long short-term memory (ConvLSTM) network that incorporates spatiotemporal correlations was used to classify the heatmap images. Evaluation was carried out on Deep Inertial Poser (DIP), a known dataset composed of inertial sensor data. The results obtained suggest that for datasets with large numbers of subjects, using state-of-the-art methods remains the best alternative. However, a performance advantage was achieved for small datasets, which is usually the case in healthcare. Moreover, movement trajectories provide a visual representation of human activities, which can help researchers to better interpret and analyze motion patterns.}, author = {Konak, Orhan and Wegner, Pit and Arnrich, Bert}, journal = {Sensors (Switzerland)}, keywords = {bertarnrich orhankonak}, number = 24, pages = {1–15}, title = {IMU-Based Movement Trajectory Heatmaps for Human Activity Recognition}, volume = 20, year = 2020 }

2019

An Information and Communication Platform Supporting Analytics for Elderly Care. Konak, Orhan; Freitas Da Cruz, Harry; Thiele, Marvin; Golla, David; Schapranow, Matthieu-P. (2019).
[ BibTeX ]
 
@inproceedings{konak2019information, author = {Konak, Orhan and Freitas Da Cruz, Harry and Thiele, Marvin and Golla, David and Schapranow, Matthieu-P.}, booktitle = {5th International Conference on Information for Ageing Well, Communication Technologies e Health}, keywords = {orhankonak}, title = {An Information and Communication Platform Supporting Analytics for Elderly Care}, year = 2019 }

MORPHER – A Platform to Support Modeling of Outcome and Risk Prediction in Health Research. Freitas da Cruz, Harry; Bergner, Benjamin; Konak, Orhan; Schneider, Frederic; Bode, Philipp; Lempert, Conrad; Schapranow, Matthieu-P. (2019).
[ BibTeX ]
 
@conference{freitasdacruz2019morpher, author = {Freitas da Cruz, Harry and Bergner, Benjamin and Konak, Orhan and Schneider, Frederic and Bode, Philipp and Lempert, Conrad and Schapranow, Matthieu-P.}, booktitle = {Proceedings of the 19th IEEE International Conference on Bioinformatics and Biomedicine}, keywords = {orhankonak}, title = {MORPHER – A Platform to Support Modeling of Outcome and Risk Prediction in Health Research}, year = 2019 }