A5077369441- Balance, Gait, and Falls Prevention
- Context-Aware Activity Recognition Systems
- Non-Invasive Vital Sign Monitoring
- Complex Systems and Time Series Analysis
- Physical Activity and Health
- Cerebral Palsy and Movement Disorders
- Infant Development and Preterm Care
- Chaos control and synchronization
- Neonatal and fetal brain pathology
- Human Pose and Action Recognition
- Muscle activation and electromyography studies
- Stroke Rehabilitation and Recovery
- Time Series Analysis and Forecasting
- Gait Recognition and Analysis
- Anomaly Detection Techniques and Applications
- Medical Imaging and Analysis
- Infant Health and Development
- Neonatal Respiratory Health Research
- Explainable Artificial Intelligence (XAI)
- Neural dynamics and brain function
- Winter Sports Injuries and Performance
- Vestibular and auditory disorders
- Fractal and DNA sequence analysis
- Heart Rate Variability and Autonomic Control
- Artificial Intelligence in Healthcare
Norwegian University of Science and Technology
2015-2025
Fractal structures are found in biomedical time series from a wide range of physiological phenomena. The multifractal spectrum identifies the deviations fractal structure within periods with large and small fluctuations. present tutorial is an introduction to detrended fluctuation analysis (MFDFA) that estimates series. presents MFDFA step-by-step interactive Matlab session. All tools needed available Introduction folder at website www.ntnu.edu/inm/geri/software. introduced code boxes where...
It has been suggested that human behavior in general and cognitive performance particular emerge from coordination between multiple temporal scales. In this article, we provide quantitative support for such a theory of interaction-dominant dynamics cognition by using wavelet-based multifractal analysis accompanying multiplicative cascading process on the response series 4 different tasks: simple response, word naming, choice decision, interval estimation. Results indicated major portion...
Background: Early identification of cerebral palsy (CP) during infancy will provide opportunities for early therapies and treatments. The aim the present study was to a novel machine-learning model, Computer-based Infant Movement Assessment (CIMA) clinically feasible CP prediction based on infant video recordings. Methods: CIMA model designed assess proportion (%) risk-related movements using time–frequency decomposition movement trajectories infant’s body parts. developed tested recordings...
Early identification of cerebral palsy (CP) is important for early intervention, yet expert-based assessments do not permit widespread use, and conventional machine learning alternatives lack validity.
Real-world fall events objectively measured by body-worn sensors can improve the understanding of in older people. However, these are rare and hence challenging to capture. Therefore, FARSEEING (FAll Repository for design Smart sElf-adaptive Environments prolonging Independent livinG) consortium associated partners started build up a meta-database real-world falls.Between January 2012 December 2015 more than 300 have been recorded. This is currently largest collection data recorded with...
Physical activity is strongly linked with mental and physical health in the elderly population accurate monitoring of activities daily living (ADLs) can help improve quality life well-being. This study presents validates an inertial sensors-based classification system developed older adults as target population. The dataset was collected free-living conditions without placing constraints on way order performing ADLs. Four sensor locations (chest, lower back, wrist, thigh) were explored to...
Objectives To determine whether videos taken by parents of their infants’ spontaneous movements were in accordance with required standards the In-Motion-App, and could be remotely scored a trained General Movement Assessment (GMA) observer. Additionally, to assess feasibility using home-based video recordings for automated tracking movements, examine parents’ perceptions experiences taking homes. Design The study was multi-centre prospective observational study. Setting Parents/families...
Automatic fall detection will promote independent living and reduce the consequences of falls in elderly by ensuring people can confidently live safely at home for linger. In laboratory studies inertial sensor technology has been shown capable distinguishing from normal activities. However less than 7% fall-detection algorithm have used data recorded real life. The FARSEEING project compiled a database life people, to gain new knowledge about events develop algorithms combat problems...
Despite frequent use of exergames in intervention studies to improve physical function older adults, we lack knowledge about the movements performed during exergaming. This causes difficulties for interpreting results and drawing conclusions efficacy exercise specific functions important elderly population. The aim current study was investigate whether game level affect adults' stepping upper body while playing exergames. A 3D-motion capture experiment with 20 (12 women 8 men; age range...
Early prediction of cerebral palsy (CP) using the General Movement Assessment (GMA) during fidgety movements (FM) period has been recommended as standard care in high-risk infants. The aim this study was to determine accuracy GMA, alone or combination with neonatal imaging, predicting (CP).Infants increased risk perinatal brain injury were prospectively enrolled from 2009-2014 multi-center, observational study. FM classified by two certified GMA observers blinded clinical history. Abnormal...
Assessment of spontaneous movements can predict the long-term developmental disorders in high-risk infants. In order to develop algorithms for automated prediction later disorders, highly precise localization segments and joints by infant pose estimation is required. Four types convolutional neural networks were trained evaluated on a novel dataset, covering large variation 1 424 videos from clinical international community. The performance was as deviation between estimated keypoint...
Early detection of Cerebral Palsy (CP) is crucial for effective intervention and monitoring. This paper tests the reliability applicability Explainable AI (XAI) methods using a deep learning method that predicts CP by analyzing skeletal data extracted from video recordings infant movements. Specifically, we use XAI evaluation metrics — namely faithfulness stability to quantitatively assess Class Activation Mapping (CAM) Gradient-weighted (Grad-CAM) in this specific medical application. We...
Age and age-related diseases have been suggested to decrease entropy of human gait kinematics, which is thought make older adults more susceptible falls. In this study we introduce a new measure, called phase-dependent generalized multiscale (PGME), test whether measure improves fall-risk prediction in community-dwelling adults. PGME can assess changes the stability dynamics that result from kinematic events such as heel strike toe-off. was assessed for trunk acceleration 30 seconds walking...
The popularity of using wearable inertial sensors for physical activity classification has dramatically increased in the last decade due to their versatility, low form factor, and power requirements. Consequently, various systems have been developed automatically classify daily life activities. However, scope implementation such is limited laboratory-based investigations. Furthermore, these are not directly comparable, large diversity design (e.g., number sensors, placement data collection...
The present study compares phase-dependent measures of local dynamic stability daily life walking with 35 conventional gait features in their ability to discriminate between community-dwelling older fallers and nonfallers. reanalyzes 3D-acceleration data 3-day activity from 39 people who reported less than 2 falls during one year 31 two or more falls. Phase-dependent was defined for initial perturbation at 0%, 20%, 40%, 60%, 80% the step cycle. A partial least square discriminant analysis...
Physical activity monitoring algorithms are often developed using conditions that do not represent real-life activities, the target population, or labelled to a high enough resolution capture true detail of human movement. We have designed semi-structured supervised laboratory-based protocol and an unsupervised free-living recorded 20 older adults performing both protocols while wearing up 12 body-worn sensors. Subjects' movements were synchronised cameras (≥25 fps), deployed in laboratory...
Extensive test batteries are often needed to obtain a comprehensive picture of person’s functional status. Many not suitable for active and healthy adults due ceiling effects, or require lot space, time, training. The Community Balance Mobility Scale (CBMS) is considered gold standard this population, but the complex, as well time- resource intensive. There strong need faster, yet sensitive robust physical function in seniors. We sought investigate whether an instrumented Timed Up Go (iTUG)...