A5073414196- Context-Aware Activity Recognition Systems
- Neurogenetic and Muscular Disorders Research
- Cerebral Palsy and Movement Disorders
- Human Pose and Action Recognition
- Gait Recognition and Analysis
- Hereditary Neurological Disorders
- Balance, Gait, and Falls Prevention
- Non-Invasive Vital Sign Monitoring
- Anomaly Detection Techniques and Applications
- Robotic Locomotion and Control
- Sports Performance and Training
- Sports injuries and prevention
- Hyperglycemia and glycemic control in critically ill and hospitalized patients
- Ultrasound and Cavitation Phenomena
- Heart Rate Variability and Autonomic Control
- Lower Extremity Biomechanics and Pathologies
- Green IT and Sustainability
- Smart Grid Security and Resilience
- Innovative Energy Harvesting Technologies
- Advanced X-ray Imaging Techniques
- Tactile and Sensory Interactions
- Ultrasound and Hyperthermia Applications
- Video Surveillance and Tracking Methods
- Mechanical Engineering and Vibrations Research
- Structural Health Monitoring Techniques
Fraunhofer Institute for Integrated Circuits
2022
Friedrich-Alexander-Universität Erlangen-Nürnberg
2016-2020
Imperial College London
2014-2017
NIHR Imperial Biomedical Research Centre
2014
New smart technologies and the internet of things increasingly play a key role in healthcare wellness, contributing to development novel concepts. These enable comprehensive view an individual’s movement mobility, potentially supporting healthy living as well complementing medical diagnostics monitoring therapeutic outcomes. This overview article specifically addresses shoes, which are becoming one such technology within future health things, since ability walk defines large aspects quality...
Machine learning is a promising approach to evaluate human movement based on wearable sensor data. A representative dataset for training data-driven models crucial ensure that the model generalizes well unseen However, acquisition of sufficient data time-consuming and often infeasible. We present method create realistic inertial with corresponding biomechanical variables by 2D walking running simulations. augmented measured simulated convolutional neural networks estimate sagittal plane...
Robust gait segmentation is the basis for mobile analysis. A range of methods have been applied and evaluated healthy pathological bouts. However, a unified evaluation in Parkinson’s disease (PD) missing. In this paper, we compare four prevalent order to reveal their strengths drawbacks processing. We considered peak detection from event-based methods, two variations dynamic time warping template matching hierarchical hidden Markov models (hHMMs) machine learning methods. To evaluate...
In this paper we present a smart soccer shoe that uses textile pressure sensing matrices to detect and analyze the interaction between players' foot ball. We describe sensor system consists of two 3 × 4 one sampled at over 500Hz with low power electronics allows continuous operation (incl. wireless transmission) for 8 hours using small 800mA/h Li-Po battery. show how relevant parameters shot analysis such as contact speed angles can be reliably derived from signals. To ensure reliable ground...
The correct treatment of diabetes is vital to a patient's health: Staying within defined blood glucose levels prevents dangerous short- and long-term effects on the body. Mobile devices informing patients about their future could enable them take counter-measures prevent hypo or hyper periods. Previous work addressed this challenge by predicting using regression models. However, these approaches required physiological model, representing human body's response insulin intake, are not directly...
Abstract Wearable sensor systems are of increasing interest in clinical gait analysis. However, little information about dynamics patients under free living conditions is available, due to the challenges integrating such unobtrusively into a patient’s everyday live. To address this limitation, new, fully integrated low power insoles proposed, target applications particularly home-monitoring scenarios. The combine inertial as well pressure sensors and feature wireless synchronization acquire...
Hereditary spastic paraplegia (HSP) causes progressive spasticity and weakness of the lower limbs. As neurologic examination clinical Spastic Paraplegia Rating Scale (SPRS) are subject to potential patient-dependent clinician-dependent bias, instrumented gait analysis bears objectively quantify impaired gait. The aim this study was investigate cyclicity parameters by application a mobile system in cross-sectional cohort patients with HSP longitudinal fast progressing subcohort.Using wearable...
Severely damaged historical documents are extremely fragile. In many cases, their secrets remain concealed beneath cover. Recently, non-invasive digitization approaches based on 3-D scanning have demonstrated the ability to recover single pages or letters without need open manuscripts. This can even be achieved using conventional micro-CTs for synchrotron hardware. However, not all manuscripts may suited such techniques due material and X-ray properties. order recommend which inks best a...
Activity monitoring using wearables is becoming ubiquitous, although accurate cycle level analysis, such as step-counting and gait are limited by a lack of realistic labeled datasets. The effort required to obtain annotate datasets massive, therefore we propose smart annotation pipeline which reduces the number events needing manual adjustment 14%. For scenarios dominated walking, this low 8%. consists three approaches, namely edge detection pressure data, local cyclicity estimation,...
Although ski jumping is a widely investigated sport, competitions and training sessions are rarely supported by state-of-the-art technology. Supporting technologies could focus on continuous velocity determination visualization for as well an analysis of the development jump length sessions. In literature, there several approaches analysis. However, majority these aim biomechanical instead support system frequent use. They do not fulfill requirements unobtrusiveness usability that necessary...
Visually impaired people find navigating within unfamiliar environments challenging. Many smart systems have been proposed to help blind in these difficult, often dangerous, situations. However, some of them are uncomfortable, difficult obtain or simply too expensive. In this paper, a low-cost wearable system for visually was implemented which allows detect and locate obstacles their locality. The consists two main hardware components, laser pointer ($12) an android phone, making our...
Cyclic signals are an intrinsic part of daily life, such as human motion and heart activity. The detailed analysis them is important for clinical applications pathological gait sports performance analysis. Labeled training data algorithms that analyze these cyclic come at a high annotation cost due to only limited annotations available under laboratory conditions or requiring manual segmentation the less restricted conditions. This paper presents smart method reduces this labeling...
Hereditary spastic paraplegias (HSP) represents a group of orphan neurodegenerative diseases with gait disturbance as the predominant clinical feature. Due to its rarity, research within this field is still limited. Aside from analysis using established scales, has been employed enhance understanding mechanisms behind disease. However, state art systems are often large, immobile and expensive. To overcome these limitations, paper presents first clinically relevant mobile system for HSP...
The monitoring of patients within a natural, home environment is important in order to close knowledge gaps the treatment and care neurodegenerative diseases, such as quantifying daily fluctuation Parkinson's patients' symptoms. combination machine learning algorithms wearable sensors for gait analysis becoming capable achieving this. However, these require large, labelled, realistic datasets training. Most systems used ground truth labelling are restricted laboratory environment, well being...
Ultrasound-driven microbubble (MB) activity is used in therapeutic applications such as blood clot dissolution and targeted drug delivery. The safety performance of these technologies are linked to the type distribution MB activities produced within area, but controlling monitoring vivo real time has proven be difficult. As pulses often milliseconds long, currently requires a separate transducer passive reception mode. Here, we present simple, inexpensive, integrated setup, which focused...
Gait analysis provides a quantitative method to assess disease progression or intervention effect on gait disorders. While mobile enables continuous monitoring in free living conditions, state of the art for diseases such as hereditary spastic paraplegia (HSP) is currently limited motion capture systems which are large and expensive. The challenge with HSP its heterogeneous nature rarity, leading wide range ages, severity patterns well small patient numbers. We propose sensor-based solution,...
In this paper we use foot-mounted inertial measurement units (IMU) as a mobile solution to measure the gait of 21 HSP patients while performing 4 by 10 m walk at self-selected pace. Two algorithms common other analysis solutions, hidden Markov model (HMM) and dynamic time warping (DTW), were applied these signals in order investigate their effectiveness when faced with heterogeneous nature range foot strike techniques gait, sometimes even lacking heel strike. Using nested cross validation...
Wearables are becoming mainstream technology, however there is still room for improvement in the sports domain of this field. Monitoring performance and collecting large scale data high interest among athletes - amateurs professionals alike. The current state-of-the art wearable solutions analysis able to provide individual statistics user, they have shortcomings certain aspects, such as isolating visualizing important information beyond statistics. This workshop focuses on application...
The evaluation of trajectory reconstruction the human body obtained by foot-mounted Inertial Pedestrian Dead-Reckoning (IPDR) methods has usually been carried out in controlled environments, with very few participants and limited to walking. In this study, a pipeline for using IPDR system is proposed evaluated two large datasets containing activities that involve walking, jogging, running, as well movements such side backward strides, sitting, standing. First, stride segmentation addressed...
The possibilities for wearable health care technology to improve the quality of life chronic disease patients has been increasing within recent years. For instance, unobtrusive cardiac monitoring can be applied people suffering from a disorder autonomic nervous system (ANS) which show significantly lower heart rate variability (HRV) than healthy people. Although work presented solutions analyze this relationship, they did not perform it during daily situations. that reason, presents...
Recent studies showed that Parkinson's disease (PD) patients improved their gait parameters while walking with rhythmic auditory stimulation (RAS). They achieved a longer stride length, reduced time variability and higher speed. Combining RAS mobile analysis would allow continuous monitoring of effects in natural environments. This paper proposes solution for home-based assessment by combining training system data acquisition. Existing datasets were used to investigate the cadence PD propose...
European Network of Living Lab's effective member.Objectives 1.To develop an innovative solution that would enable healthrelated behaviour changes, increase motivation, promote physical activity and reduce prolonged sedentary time in users, thanks to persuasive ubiquitous computing techniques.2. To be validated by SPORTIS Lab.Following aim involve society the innovation process, ObesiTIC will end-users (children teenagers) combined with development application final product, order suit...
This paper discusses a metering concept design based on equipment cheaper and smaller than laptop able to meet the requirements of power measurements that need relatively high frequency, simultaneous sampling. Its size cost make it useful when developing hardware for smart grid systems. Non-active is term used describe both distortion reactive power. In conventional theory, apparent power, S, non-active Q, are RMS voltages line currents. A novel general theory was proposed recently give...