Position Matters: Sensor Placement for SittingPosture Classification. Kappattanavar, A. M.; da Cruz, H. F.; Arnrich, B.; Böttinger, E. (2020).
Prolonged sitting behavior and postures that cause strain on the spine and muscles have been reported to increase the probability of low back pain. To address this issue, many commercially available sensors already provide feedback about whether a person is 'slouching' or 'not slouching'. However, they do not provide information on a person's posture, which would give insights into the strain caused by a specific posture. Hence, in this pilot study, we attempt to find the optimum number of inertial measurement unit sensors required and the best locations to place them using six mock postures. Data is collected from these sensors and features are extracted. The number of features are reduced and the best features are selected using the Recursive Feature Elimination method with Cross-Validation. The reduced number of features is then trained and tested on Logistic Regression, Support Vector Machine and Hierarchical Model. Among the three models, the Support Vector Machine algorithm had the highest accuracy of 93.68%, obtained for the thoracic, hip and sacral region sensor combinations. While these findings will be validated in a larger study in an uncontrolled environment, this pilot study quantitatively highlights the importance of sensor placement in shaping discriminative performance in sitting posture classification tasks.
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.
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.
Self-prediction of seizures in drug resistance epilepsy using digital phenotyping: a concept study. Moontaha, Sidratul; Steckhan, Nico; Kappattanavar, Arpita; Surges, Rainer; Arnrich, Bert (2020). (Vol. 14)
Drug-resistance is a prevalent condition in children and adult patients with epilepsy. The quality of life of these patients is profoundly affected by the unpredictability of seizure occurrence. Some of these patients are capable of reporting self-prediction of their seizures by observing their affectivity. Some patients report no signs of feeling premonitory symptoms, prodromes, or aura. In this paper, we propose a concept study that will provide objective information to self-predict seizures for both the patient groups. We will develop a model using digital phenotyping which takes both ecological momentary assessment and data from sensor technology into consideration. This method will be able to provide a feedback of their premonitory symptoms so that a pre-emptive therapy can be associated to reduce seizure frequency or eliminate seizure occurrence.
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, Markus Clemens; Granacher, Urs; Arnrich, Bert in MDPI Sensors (2020). 20(18)
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 usinggold 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.
Will You Be My Quarantine: A Computer Vision and Inertial Sensor Based Home Exercise System. Albert, Justin; Zhou, Lin; Gloeckner, Pawel; Trautmann, Justin; Ihde, Lisa; Eilers, Justus; Kamal, Mohammed; Arnrich, Bert (2020). (Vol. 14)
The quarantine situation inflicted by the COVID-19 pandemic has left many people around the world isolated at home. Despite the large variety of mobile device-based self exercise tools for training plans, activity recognition or repetition counts, it remains challenging for an inexperienced person to perform fitness workouts or learn a new sport with the correct movements at home. As a proof of concept, a home exercise system has been developed in this contribution. The system takes computer vision and inertial sensor data recorded for the same type of exercise as two independent inputs, and processes the data from both sources into the same representations on the levels of raw inertial measurement unit (IMU) data and 3D movement trajectories. Moreover, a Key Performance Indicator (KPI) dashboard was developed for data import and visualization. The usability of the system was investigated with an example use case where the learner equipped with IMUs performed a kick movement and was able to compare it to that from a coach in the video.
Prototypical System to Detect Anxiety Manifestations by Acoustic Patterns in Patients with Dementia. Hernandez, Netzahualcoyotl; Garcia-Constantino, Matias; Beltran, Jessica; Hecker, Pascal; Favela, Jesus; Cleland, Ian; Lopez, Hussein; Arnrich, Bert; McChesney, Ian in EAI Endorsed Transactions on Pervasive Health and Technology (2020). 5(19)
INTRODUCTION: Dementia is a syndrome characterised by a decline in memory, language, and problem-solving that affects the ability of patients to perform everyday activities. Patients with dementia tend to experience episodes of anxiety and remain for extended periods, which affects their quality of life. OBJECTIVES: To design AnxiDetector, a system capable of detecting patterns of sounds associated before and during the manifestation of anxiety in patients with dementia. METHODS: We conducted a non-participatory observation of 70 diagnosed patients in-situ, and conducted semi-structured interviews with four caregivers at a residential centre. Using the findings from our observation and caregiver interviews, we developed the AnxiDetector prototype and tested this in an experimental setting where we defined nine classes of audio to represent two groups of sounds: (i) Disturbance which includes audio files that characterise sounds that trigger anxiety in patients with dementia, and (ii) Expression which includes audio files that characterise sounds expressed by the patients during episodes of anxiety. We conducted two experimental classifications of sounds using (i) a Neural Network model trained and (ii) a Support Vector Machine model. The first evaluation consists of a binary discriminating between the two groups of sounds; the second evaluation discriminates the nine classes of audio. The audio resources were retrieved from publicly available datasets. RESULTS: The qualitative results present the views of the caregivers on the adoption of AnxiDetector. The quantitative results from our binary discrimination show a classification accuracy of 98.1% and 99.2% for the Deep Neural Network and Support Vector Machine models, respectively. When classifying the nine classes of sound, our model shows a classification accuracy of 92.2%. Whereas, the Support Vector Machine model yielded an overall classification accuracy of 93.0%. CONCLUSION: In this paper, we presented the outcomes from an observational study in-site at a residential care centre, qualitative findings from interviews with caregivers, the design of AnxiDetector, and preliminary qualitative results of a methodology devised to detect relevant acoustic events associated with anxiety in patients with dementia. We conclude by signalling future plans to conduct in-situ validation of the effectiveness of AnxiDetector for anxiety detection.
IMU-Based Movement Trajectory Heatmaps for Human Activity Recognition. Konak, Orhan; Wegner, Pit; Arnrich, Bert in Sensors (Switzerland) (2020). 20(24) 1–15.
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.
HYPE: Predicting Blood Pressure from Photoplethysmograms in a Hypertensive Population. Morassi Sasso, Ariane; Datta, Suparno; Jeitler, Michael; Steckhan, Nico; Kessler, Christian S.; Michalsen, Andreas; Arnrich, Bert; Böttinger, Erwin M. Michalowski, R. Moskovitch (eds.) (2020). (Vol. 12299)
The state of the art for monitoring hypertension relies on measuring blood pressure (BP) using uncomfortable cuff-based devices. Hence, for increased adherence in monitoring, a better way of measuring BP is needed. That could be achieved through comfortable wearables that contain photoplethysmography (PPG) sensors. There have been several studies showing the possibility of statistically estimating systolic and diastolic BP (SBP/DBP) from PPG signals. However, they are either based on measurements of healthy subjects or on patients on (ICUs). Thus, there is a lack of studies with patients out of the normal range of BP and with daily life monitoring out of the ICUs. To address this, we created a dataset (HYPE) composed of data from hypertensive subjects that executed a stress test and had 24-h monitoring. We then trained and compared machine learning (ML) models to predict BP. We evaluated handcrafted feature extraction approaches vs image representation ones and compared different ML algorithms for both. Moreover, in order to evaluate the models in a different scenario, we used an openly available set from a stress test with healthy subjects (EVAL). The best results for our HYPE dataset were in the stress test and had a mean absolute error (MAE) in mmHg of 8.79 (±3.17) for SBP and 6.37 (±2.62) for DBP; for our EVAL dataset it was 14.74 (±4.06) and 7.12 (±2.32) respectively. Although having tested a range of signal processing and ML techniques, we were not able to reproduce the small error ranges claimed in the literature. The mixed results suggest a need for more comparative studies with subjects out of the intensive care and across all ranges of blood pressure. Until then, the clinical relevance of PPG-based predictions in daily life should remain an open question.
