Literature Review on Transfer Learning for Human Activity Recognition Using Mobile and Wearable Devices with Environmental Technology.Hernandez, Netzahualcoyotl; Lundström, Jens; Favela, Jesus; McChesney, Ian; Arnrich, Bert in SN Computer Science (2020). 1(2) 66.
Self-prediction of seizures in drug resistance epilepsy using digital phenotyping: a concept study.Moontaha, Sidratul; Steckhan, Nico; Kappattanavar, Arpita; Surges, Rainer; Arnrich, Bert in Pervasive Health (2020).
Federated Learning in a Medical Context: A Systematic Literature Review.Pfitzner, Bjarne; Steckhan, Nico; Arnrich, Bert in ACM Transactions on Internet Technology (TOIT) Special Issue on Security and Privacy of Medical Data for Smart Healthcare (2020).
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. On the other hand, 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.
Tangle Ledger for Decentralized Learning.Schmid, R.; Pfitzner, B.; Beilharz, J.; Arnrich, B.; Polze, A. (2020). 852-859.
Federated learning has the potential to make machine learning applicable to highly privacy-sensitive domains and distributed datasets. In some scenarios, however, a central server for aggregating the partial learning results is not available. In fully decentralized learning, a network of peer-to-peer nodes collaborates to form a consensus on a global model without a trusted aggregating party. Often, the network consists of Internet of Things (IoT) and Edge computing nodes.Previous approaches for decentralized learning map the gradient batching and averaging algorithm from traditional federated learning to blockchain architectures. In an open network of participating nodes, the threat of adversarial nodes introducing poisoned models into the network increases compared to a federated learning scenario which is controlled by a single authority. Hence, the decentralized architecture must additionally include a machine learning-aware fault tolerance mechanism to address the increased attack surface.We propose a tangle architecture for decentralized learning, where the validity of model updates is checked as part of the basic consensus. We provide an experimental evaluation of the proposed architecture, showing that it performs well in both model convergence and model poisoning protection.
Validation of an IMU Gait Analysis Algorithm for Gait Monitoring in Daily Life Situations.Zhou, Lin; Tunca, Can; Fischer, Eric; Brahms, Clemens Markus; Ersoy, Cem; Granacher, Urs; Arnrich, Bert (2020).
Gait is an essential function for humans, and gait patterns in daily life provide meaningful information about a person’s cognitive and physical health conditions. Inertial measurement units (IMUs) have emerged as a promising tool for low-cost, unobtrusive gait analysis. However, large varieties of IMU gait analysis algorithms and the lack of consensus for their validation make it difficult for researchers to assess the reliability of the algorithms for specific use cases. In daily life,individuals adapt their gait patterns in response to changes in the environment, making it necessary for IMU gait analysis algorithms to provide accurate measurements despite these gait variations. In this paper, we reviewed common types of IMU gait analysis algorithms and appropriate analysis methods to evaluate the accuracy of gait parameters extracted from IMU measurements. We then evaluated stride lengths and stride times calculated from a comprehensive double integration based IMU gait analysis algorithm using an optoelectric walkway as gold standard. In total, 729 strides from five healthy subjects and three different walking patterns were analyzed. Correlation analyses and Bland-Altman plots showed that this method is accurate and robust against large variations in walking patterns (stride length: correlation coefficient (r) was 0.99, root mean square error (RMSE) was 3% and average limits of agreement (LoA) was 6%; stride time: r was 0.95, RMSE was 4% and average LoA was 7%), making it suitable for gait evaluation in daily life situations. Due to the small sample size, our preliminary findings should be verified in future studies.
How We Found Our IMU: Guidelines to IMU Selection and a Comparison of Seven IMUs for Pervasive Healthcare Applications.Zhou, Lin; Fischer, Eric; Tunca, Can; Brahms, Clemens Markus; Ersoy, Cem; Granacher, Urs; Arnrich, Bert in Sensors (2020).
Evaluation of the Pose Tracking Performance of the Azure Kinect and Kinect v2 for Gait Analysis in Comparison with a Gold Standard: A Pilot Study.Albert, Justin; Owolabi, Victor; Gebel, Arnd; Brahms, Clemens Markus; Granacher, Urs; Arnrich, Bert in Sensors (2020).
Gait analysis is an important tool for the early detection of neurological diseases and for the assessment of risk of falling in elderly people. The availability of low-cost camera hardware on the market today and recent advances in Machine Learning enable a wide range of clinical and health-related applications, such as patient monitoring or exercise recognition at home. In this study, we evaluated the motion tracking performance of the latest generation of the Microsoft Kinect camera, Azure Kinect, compared to its predecessor Kinect v2 in terms of treadmill walking using a gold standard Vicon multi-camera motion capturing system and the 39 marker Plug-in Gait model. Five young and healthy subjects walked on a treadmill at three different velocities while data were recorded simultaneously with all three camera systems. An easy-to-administer camera calibration method developed here was used to spatially align the 3D skeleton data from both Kinect cameras and the Vicon system. With this calibration, the spatial agreement of joint positions between the two Kinect cameras and the reference system was evaluated. In addition, we compared the accuracy of certain spatio-temporal gait parameters, i.e., step length, step time, step width, and stride time calculated from the Kinect data, with the gold standard system. Our results showed that the improved hardware and the motion tracking algorithm of the Azure Kinect camera led to a significantly higher accuracy of the spatial gait parameters than the predecessor Kinect v2, while no significant differences were found between the temporal parameters. Furthermore, we explain in detail how this experimental setup could be used to continuously monitor the progress during gait rehabilitation in older people.
Position Matters: Sensor Placement for SittingPosture Classification.Kappattanavar, A. M.; da Cruz, H. F.; Arnrich, B.; Böttinger, E. in IEEE International Conference on Healthcare Informatics (2020).
Constrained expectation maximisation algorithm for estimating ARMA models in state space representation.Galka, Andreas; Moontaha, Sidratul; SIniatchkin, Siniatchkin in EURASIP Journal on Advances in Signal Processing 2020.1 (2020). 1-37.
SVD Square-root Iterated Extended Kalman Filter for Modeling of Epileptic Seizure Count Time Series with External Inputs.Moontaha, Sidratul; Galka, Andreas; Siniatchkin, Michael; Scharlach, Sascha; von Spiczak, Sarah; Stephani, Ulrich; May, Theodor; Meurer, Thomas in 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (2019).
Bewertung von Therapieeffekten bei Epilepsie: Eine vergleichende Analyse zwischen Cox-Stuart-Berechnung und Zustandsraum-Modellierung.Scharlach, Sascha; Moontaha, Sirdatul; von Spiczak, Sarah; Stephani, Ulrich; Siniatchkin, Michael; May, Theodor; Galka, Andreas; Meurer, Thomas in 11. Gemeinsame Jahrestagung der Deutschen und Österreichischen Gesellschaft für Epileptologie sowie der Schweizerischen Epilepsie-Liga (2019).
An Exploratory Study to Detect Temporal Orientation Using Bluetooth's sensor.Netzahualcoyotl, Hernandez; Demiray, Burcu; Arnrich, Bert; Favela, Jesus in 13th EAI International Conference on Pervasive Computing Technologies for Healthcare (2019). 292-297.
A multi-site study on walkability, data sharing and privacy perception using mobile sensing data gathered from the mk-sense platform.Hernández, N; Arnrich, Bert; Favela, J; Ersoy, C; Demiray, Burcu; Fontecha, J in Journal of Ambient Intelligence and Humanized Computing (2019). 10 2199-2211.
Analysis of the effects of medication for the treatment of epilepsy by ensemble Iterative Extended Kalman Filtering.Moontaha, Sidratul; Galka, Andreas; Meurer, Thomas; Siniatchkin, Michael in 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (2018).
Evaluation der Therapieeffekte antikonvulsiver Medikamente bei Kindern mit strukturell bedingter Epilepsie mittels Zustandsraum-Modellierung.Moontaha, Sidratul; von Spiczak, Sarah; Scharlach, Sascha; Doege, Corinna; Boor, Rainer; May, Theodor; Stephani, Ulrich; Siniatchkin, Michael; Galka, Andreas in 43. Jahrestagung der Gesellschaft für Neuropädiatrie (2017). 1-45.
Starting from the situation 15 years ago with a great gap between the low symbolic complexity on the one hand and the high numeric complexity of coding in Geometric Algebra on the other hand, this paper reviews some applications showing, that, in the meantime, this gap could be closed, especially for CPUs. Today, the use of Geometric Algebra in engineering applications relies heavily on the availability of software solutions for the new heterogeneous computing architectures. While most of the Geometric Algebra tools are restricted to CPU focused programming languages, in this paper, we introduce the new Gaalop (Geometric Algebra algorithms optimizer) Precompiler for heterogeneous systems (CPUs, GPUs, FPGAs, DSPs ...) based on the programming language C++ AMP (Accelerated Massive Parallelism) of the HSA (Heterogeneous System Architecture) Foundation. As a proof-of-concept we present a raytracing application together with some computing details and first performance results.
Prof. Dr. Bert Arnrich Professor for Digital Health - Connected Healthcare Room: G-2.1.14 Tel.: +49-(0)331 5509-4850 E-Mail: bert.arnrich(at)hpi.de
Campus III, Haus G2 Room: G-2.1.22 Tel.: +49-(0)331 5509-4850 Fax: +49-(0)331 5509-4849 E-Mail: office-arnrich(at)hpi.de
Campus III Building G2 Rudolf-Breitscheid-Straße 187 14482 Potsdam, Germany