@article{ZieglerPfitznerSchulzetal.2022, author = {Ziegler, Joceline and Pfitzner, Bjarne and Schulz, Heinrich and Saalbach, Axel and Arnrich, Bert}, title = {Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data}, series = {Sensors}, volume = {22}, journal = {Sensors}, edition = {14}, publisher = {MDPI}, address = {Basel, Schweiz}, issn = {1424-8220}, doi = {10.3390/s22145195}, pages = {25}, year = {2022}, abstract = {Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.940.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated R{\´e}nyi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}�∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.940.94 for ε=6�=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.760.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.}, language = {en} } @techreport{DoellnerFriedrichArnrichetal.2022, author = {D{\"o}llner, J{\"u}rgen Roland Friedrich and Friedrich, Tobias and Arnrich, Bert and Hirschfeld, Robert and Lippert, Christoph and Meinel, Christoph}, title = {Abschlussbericht KI-Labor ITSE}, doi = {10.25932/publishup-57860}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-578604}, pages = {60}, year = {2022}, abstract = {Der Abschlussbericht beschreibt Aufgaben und Ergebnisse des KI-Labors "ITSE". Gegenstand des KI-Labors bildeten Methodik, Technik und Ausbildung in der IT-Systemtechnik zur Analyse, Planung und Konstruktion KI-basierter, komplexer IT-Systeme.}, language = {de} } @misc{HeckerSteckhanEybenetal.2022, author = {Hecker, Pascal and Steckhan, Nico and Eyben, Florian and Schuller, Bj{\"o}rn Wolfgang and Arnrich, Bert}, title = {Voice Analysis for Neurological Disorder Recognition - A Systematic Review and Perspective on Emerging Trends}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {13}, doi = {10.25932/publishup-58101}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-581019}, pages = {16}, year = {2022}, abstract = {Quantifying neurological disorders from voice is a rapidly growing field of research and holds promise for unobtrusive and large-scale disorder monitoring. The data recording setup and data analysis pipelines are both crucial aspects to effectively obtain relevant information from participants. Therefore, we performed a systematic review to provide a high-level overview of practices across various neurological disorders and highlight emerging trends. PRISMA-based literature searches were conducted through PubMed, Web of Science, and IEEE Xplore to identify publications in which original (i.e., newly recorded) datasets were collected. Disorders of interest were psychiatric as well as neurodegenerative disorders, such as bipolar disorder, depression, and stress, as well as amyotrophic lateral sclerosis amyotrophic lateral sclerosis, Alzheimer's, and Parkinson's disease, and speech impairments (aphasia, dysarthria, and dysphonia). Of the 43 retrieved studies, Parkinson's disease is represented most prominently with 19 discovered datasets. Free speech and read speech tasks are most commonly used across disorders. Besides popular feature extraction toolkits, many studies utilise custom-built feature sets. Correlations of acoustic features with psychiatric and neurodegenerative disorders are presented. In terms of analysis, statistical analysis for significance of individual features is commonly used, as well as predictive modeling approaches, especially with support vector machines and a small number of artificial neural networks. An emerging trend and recommendation for future studies is to collect data in everyday life to facilitate longitudinal data collection and to capture the behavior of participants more naturally. Another emerging trend is to record additional modalities to voice, which can potentially increase analytical performance.}, language = {en} } @misc{ZieglerPfitznerSchulzetal.2022, author = {Ziegler, Joceline and Pfitzner, Bjarne and Schulz, Heinrich and Saalbach, Axel and Arnrich, Bert}, title = {Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data}, series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {14}, doi = {10.25932/publishup-58132}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-581322}, pages = {25}, year = {2022}, abstract = {Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.940.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated R{\´e}nyi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}�∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.940.94 for ε=6�=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.760.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.}, language = {en} } @article{HeckerSteckhanEybenetal.2022, author = {Hecker, Pascal and Steckhan, Nico and Eyben, Florian and Schuller, Bj{\"o}rn Wolfgang and Arnrich, Bert}, title = {Voice Analysis for Neurological Disorder Recognition - A Systematic Review and Perspective on Emerging Trends}, series = {Frontiers in Digital Health}, journal = {Frontiers in Digital Health}, publisher = {Frontiers Media SA}, address = {Lausanne, Schweiz}, issn = {2673-253X}, doi = {10.3389/fdgth.2022.842301}, pages = {16}, year = {2022}, abstract = {Quantifying neurological disorders from voice is a rapidly growing field of research and holds promise for unobtrusive and large-scale disorder monitoring. The data recording setup and data analysis pipelines are both crucial aspects to effectively obtain relevant information from participants. Therefore, we performed a systematic review to provide a high-level overview of practices across various neurological disorders and highlight emerging trends. PRISMA-based literature searches were conducted through PubMed, Web of Science, and IEEE Xplore to identify publications in which original (i.e., newly recorded) datasets were collected. Disorders of interest were psychiatric as well as neurodegenerative disorders, such as bipolar disorder, depression, and stress, as well as amyotrophic lateral sclerosis amyotrophic lateral sclerosis, Alzheimer's, and Parkinson's disease, and speech impairments (aphasia, dysarthria, and dysphonia). Of the 43 retrieved studies, Parkinson's disease is represented most prominently with 19 discovered datasets. Free speech and read speech tasks are most commonly used across disorders. Besides popular feature extraction toolkits, many studies utilise custom-built feature sets. Correlations of acoustic features with psychiatric and neurodegenerative disorders are presented. In terms of analysis, statistical analysis for significance of individual features is commonly used, as well as predictive modeling approaches, especially with support vector machines and a small number of artificial neural networks. An emerging trend and recommendation for future studies is to collect data in everyday life to facilitate longitudinal data collection and to capture the behavior of participants more naturally. Another emerging trend is to record additional modalities to voice, which can potentially increase analytical performance.}, language = {en} } @article{PfitznerSteckhanArnrich2021, author = {Pfitzner, Bjarne and Steckhan, Nico and Arnrich, Bert}, title = {Federated learning in a medical context}, series = {ACM transactions on internet technology : TOIT / Association for Computing}, volume = {21}, journal = {ACM transactions on internet technology : TOIT / Association for Computing}, number = {2}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1533-5399}, doi = {10.1145/3412357}, pages = {1 -- 31}, year = {2021}, abstract = {Data privacy is a very important issue. Especially in fields like medicine, it is paramount to abide by the existing privacy regulations to preserve patients' anonymity. However, data is required for research and training machine learning models that could help gain insight into complex correlations or personalised treatments that may otherwise stay undiscovered. Those models generally scale with the amount of data available, but the current situation often prohibits building large databases across sites. So it would be beneficial to be able to combine similar or related data from different sites all over the world while still preserving data privacy. Federated learning has been proposed as a solution for this, because it relies on the sharing of machine learning models, instead of the raw data itself. That means private data never leaves the site or device it was collected on. Federated learning is an emerging research area, and many domains have been identified for the application of those methods. This systematic literature review provides an extensive look at the concept of and research into federated learning and its applicability for confidential healthcare datasets.}, language = {en} } @article{KappattanavarHeckerMoontahaetal.2023, author = {Kappattanavar, Arpita Mallikarjuna and Hecker, Pascal and Moontaha, Sidratul and Steckhan, Nico and Arnrich, Bert}, title = {Food choices after cognitive load}, series = {Sensors}, volume = {23}, journal = {Sensors}, number = {14}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s23146597}, pages = {22}, year = {2023}, abstract = {Psychology and nutritional science research has highlighted the impact of negative emotions and cognitive load on calorie consumption behaviour using subjective questionnaires. Isolated studies in other domains objectively assess cognitive load without considering its effects on eating behaviour. This study aims to explore the potential for developing an integrated eating behaviour assistant system that incorporates cognitive load factors. Two experimental sessions were conducted using custom-developed experimentation software to induce different stimuli. During these sessions, we collected 30 h of physiological, food consumption, and affective states questionnaires data to automatically detect cognitive load and analyse its effect on food choice. Utilising grid search optimisation and leave-one-subject-out cross-validation, a support vector machine model achieved a mean classification accuracy of 85.12\% for the two cognitive load tasks using eight relevant features. Statistical analysis was performed on calorie consumption and questionnaire data. Furthermore, 75\% of the subjects with higher negative affect significantly increased consumption of specific foods after high-cognitive-load tasks. These findings offer insights into the intricate relationship between cognitive load, affective states, and food choice, paving the way for an eating behaviour assistant system to manage food choices during cognitive load. Future research should enhance system capabilities and explore real-world applications.}, language = {en} } @article{GaertnerSchneiderArnrichetal.2023, author = {G{\"a}rtner, Thomas and Schneider, Juliana and Arnrich, Bert and Konigorski, Stefan}, title = {Comparison of Bayesian Networks, G-estimation and linear models to estimate causal treatment effects in aggregated N-of-1 trials with carry-over effects}, series = {BMC Medical Research Methodology}, volume = {23}, journal = {BMC Medical Research Methodology}, number = {1}, publisher = {BMC}, address = {London}, issn = {1471-2288}, doi = {10.1186/s12874-023-02012-5}, pages = {12}, year = {2023}, abstract = {Background The aggregation of a series of N-of-1 trials presents an innovative and efficient study design, as an alternative to traditional randomized clinical trials. Challenges for the statistical analysis arise when there is carry-over or complex dependencies of the treatment effect of interest. Methods In this study, we evaluate and compare methods for the analysis of aggregated N-of-1 trials in different scenarios with carry-over and complex dependencies of treatment effects on covariates. For this, we simulate data of a series of N-of-1 trials for Chronic Nonspecific Low Back Pain based on assumed causal relationships parameterized by directed acyclic graphs. In addition to existing statistical methods such as regression models, Bayesian Networks, and G-estimation, we introduce a carry-over adjusted parametric model (COAPM). Results The results show that all evaluated existing models have a good performance when there is no carry-over and no treatment dependence. When there is carry-over, COAPM yields unbiased and more efficient estimates while all other methods show some bias in the estimation. When there is known treatment dependence, all approaches that are capable to model it yield unbiased estimates. Finally, the efficiency of all methods decreases slightly when there are missing values, and the bias in the estimates can also increase. Conclusions This study presents a systematic evaluation of existing and novel approaches for the statistical analysis of a series of N-of-1 trials. We derive practical recommendations which methods may be best in which scenarios.}, language = {en} } @article{MoontahaSchumannArnrich2023, author = {Moontaha, Sidratul and Schumann, Franziska Elisabeth Friederike and Arnrich, Bert}, title = {Online learning for wearable EEG-Based emotion classification}, series = {Sensors}, volume = {23}, journal = {Sensors}, number = {5}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {10.3390/s23052387}, pages = {23}, year = {2023}, abstract = {Giving emotional intelligence to machines can facilitate the early detection and prediction of mental diseases and symptoms. Electroencephalography (EEG)-based emotion recognition is widely applied because it measures electrical correlates directly from the brain rather than indirect measurement of other physiological responses initiated by the brain. Therefore, we used non-invasive and portable EEG sensors to develop a real-time emotion classification pipeline. The pipeline trains different binary classifiers for Valence and Arousal dimensions from an incoming EEG data stream achieving a 23.9\% (Arousal) and 25.8\% (Valence) higher F1-Score on the state-of-art AMIGOS dataset than previous work. Afterward, the pipeline was applied to the curated dataset from 15 participants using two consumer-grade EEG devices while watching 16 short emotional videos in a controlled environment. Mean F1-Scores of 87\% (Arousal) and 82\% (Valence) were achieved for an immediate label setting. Additionally, the pipeline proved to be fast enough to achieve predictions in real-time in a live scenario with delayed labels while continuously being updated. The significant discrepancy from the readily available labels on the classification scores leads to future work to include more data. Thereafter, the pipeline is ready to be used for real-time applications of emotion classification.}, language = {en} } @misc{ZhouFischerTuncaetal.2020, author = {Zhou, Lin and Fischer, Eric and Tunca, Can and Brahms, Clemens Markus and Ersoy, Cem and Granacher, Urs and Arnrich, Bert}, title = {How We Found Our IMU}, series = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, journal = {Postprints der Universit{\"a}t Potsdam : Reihe der Digital Engineering Fakult{\"a}t}, number = {2}, doi = {10.25932/publishup-48162}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-481628}, pages = {31}, year = {2020}, abstract = {Inertial measurement units (IMUs) are commonly used for localization or movement tracking in pervasive healthcare-related studies, and gait analysis is one of the most often studied topics using IMUs. The increasing variety of commercially available IMU devices offers convenience by combining the sensor modalities and simplifies the data collection procedures. However, selecting the most suitable IMU device for a certain use case is increasingly challenging. In this study, guidelines for IMU selection are proposed. In particular, seven IMUs were compared in terms of their specifications, data collection procedures, and raw data quality. Data collected from the IMUs were then analyzed by a gait analysis algorithm. The difference in accuracy of the calculated gait parameters between the IMUs could be used to retrace the issues in raw data, such as acceleration range or sensor calibration. Based on our algorithm, we were able to identify the best-suited IMUs for our needs. This study provides an overview of how to select the IMUs based on the area of study with concrete examples, and gives insights into the features of seven commercial IMUs using real data.}, language = {en} }