A5034531247- Context-Aware Activity Recognition Systems
- Digital Mental Health Interventions
- Cardiac Arrest and Resuscitation
- Mental Health Research Topics
- Simulation-Based Education in Healthcare
- Intensive Care Unit Cognitive Disorders
- IoT and Edge/Fog Computing
- Robotics and Automated Systems
- Innovative Human-Technology Interaction
- Web Data Mining and Analysis
- IoT-based Smart Home Systems
- AI in Service Interactions
- Bipolar Disorder and Treatment
- Water Quality Monitoring Technologies
- Psychiatric care and mental health services
- Data Quality and Management
- Personal Information Management and User Behavior
- Sports Analytics and Performance
- Speech and Audio Processing
- Gaze Tracking and Assistive Technology
- Technology Use by Older Adults
- Biomedical and Engineering Education
- Treatment of Major Depression
- Healthcare Decision-Making and Restraints
- Hand Gesture Recognition Systems
German Research Centre for Artificial Intelligence
2013-2024
UMIT - Private Universität für Gesundheitswissenschaften, Medizinische Informatik und Technik
2008
In this paper we demonstrate how smart phone sensors, specifically inertial sensors and GPS traces, can be used as an objective "measurement device" for aiding psychiatric diagnosis. a trial with 12 bipolar disorder patients conducted over total (summed all patients) of 1000 days (on average weeks per patient) have achieved state change detection precision/recall 96%/94% recognition accuracy 80%. The describes the data collection, which was medical in real life every day environment rural...
In this work a Smart-Watch application, that is able to monitor the frequency and depth of Cardiopulmonary Resuscitation (CPR) provide interactive corrective feedback described. We have evaluated system with total 41 subjects who had undertaken single episode CPR training several years previously. This was part First Aid course for lay people, commonly accessed in population. The evaluation conducted by measuring participant competence using "gold standard" [10], namely compression depth....
This Special Interest Group (SIG) explores the transformative impact of Generative Artificial Intelligence (GenAI) on Human-Computer Interaction (HCI) research processes. The theme here is to answer "question zero": when use and refrain from using AI tools during cycle? discussion guided by five phases commonly used in HCI: planning, prototyping, data collection, analysis synthesis, dissemination communication. We investigate how GenAI accelerates project cycles, enhances reproducibility,...
This paper outlines the design and implementation of a mobile galvanic skin response (GSR) measurement system applied to feet. The comprises an off-the-shelf node featuring acceleration GSR sensors with customized firmware phone Android application. app
In this work, we show how a smart-phone worn unobtrusively in nurse’s coat pocket can be used to document the patient care activities performed during regular morning routine. The main contribution is how, taking into account certain domain specific boundary conditions, single sensor
We present a study comparing the effect of real-time wearable feedback with traditional training methods for cardiopulmonary resuscitation (CPR). The aim is to ensure that students can deliver CPR right compression speed and depth. On side, we test two systems: one based on combination visual tactile information smart-watch audio Google Glass. In trial 50 subjects (23 trainee nurses 27 novices,) compare those modalities standard human teaching used in nurse training. While single session...
Capabilities of smartphones can be utilised to monitor a range aspects users’ behaviour. This has potential affect number areas where behaviour is considered relevant information. Most notably, healthcare in general and mental health particular are excellent candidates uti
We present the first phase of a project for monitoring elderly people suffering from dementia in dasiareal lifepsila environment an dasiaassisted livingpsila flat associated with nursing home. Based on requirements derived discussions staff system consists UBISENSE location location, sound-system vocal interaction, and TECO dasiaParticlespsila sensor nodes mounted under beds sleep monitoring. In this paper we introduce background project, describe some initial data collected deployment period.
Capabilities of smartphones can be utilised to monitor a range aspects users' behaviour. This has potential affect number areas where behaviour is considered relevant information. Most notably, healthcare in general and mental health particular are excellent candidates utilise capabilities smartphones, since disorders typically have strong component. especially true for bipolar disorder, mobility activity the patients an indicator episode (depressive or manic). In this work we report on...
Background Bipolar disorder is characterized by depressive and manic episodes, each with its own specific outcomes. To guarantee the best therapy it important necessary to assess episodes of disease exact degree severity at an early stage. Methods During a time period 12 weeks, 9 patients suffering from bipolar were provided commercially available smartphone in order collect behavioral patterns phone's internal sensors. These sensors included acceleration, GPS-traces, phone-call behavior...
We present the first phase of a project for monitoring elderly people suffering from dementia in 'real life' environment an 'assisted living' flat associated with nursing home. Based on requirements derived discussions staff system consists UBISENSE l
We compare the performance of a smart phone based state and change detection system to self-assessment show that automatic is much closer objective psychiatric diagnosis. Our work on large, real life dataset collected with 9 patients total 800 days data. It consists sensor data, daily questionnaire filled out by validated standardized scale tests.
Human health is closely associated with their daily behavior and environment. However, keeping a healthy lifestyle still challenging for most people as it difficult to recognize living behaviors identify surrounding situations take appropriate action. activity recognition promising approach building model of users, by which users can get feedback about habits be encouraged develop healthier lifestyle. In this paper, we present smart light wearable badge six kinds sensors, including an...
Education is the Achilles heel of successful resuscitation in cardiac arrest. Therefore, we aim to contribute educational efficiency by providing a novel augmented-reality (AR) guided interactive cardiopulmonary (CPR) "trainer". For this trainer, mixed reality smart glass, Microsoft HoloLens, and CPR manikin covered with pressure sensors were used. To introduce procedure learner, an application intractable virtual teacher model was designed. The teaching scenario consists two main parts,...
Medical procedures such as venipuncture and cannulation are essential for nurses require precise skills. Learning this skill, in turn, is a challenge educators due to the number of teachers per class complexity task. The study aims help students with skill acquisition alleviate educator's workload by integrating generative AI methods provide real-time feedback on medical cannulation.
In this paper we introduce two real-world examples of successful deployments ubiquitous monitoring technology in mental care: one related to elderly dementia patients at a nursing home and the diagnosis manic depressive episodes bipolar disorder patients. We will elaborate most relevant challenges that had be dealt with solutions helped us overcome them.
In this paper we introduce two real-world examples of suc- cessful deployments ubiquitous monitoring technology in mental care: one related to elderly dementia patients at a nursing home and the diagnosis manic depressive episodes bipolar dis- order patients. We will e
This paper presents a novel beverage intake monitoring system that can accurately recognize kinds and freshness. By mounting carbon electrodes on the commercial cup, measures electrochemical impedance spectrum of fluid in cup. We studied frequency sensitivity regarding distinct beverages importance features like amplitude, phase, real imaginary components for classification. The results show from low-frequency domain (100 Hz to 1000 Hz) provide more meaningful information classification than...
Monitoring of human activities is an essential capability many smart systems. In recent years much progress has been achieved. One the key remaining challenges availability labeled training data, in particular taking into account degree variability activities. A possible solution to leverage large scale online data repositories. This previously attempted with image and sound as both microphones cameras are widely used sensing modalities. this paper, we describe a first step towards use...
This paper investigates the problem of recognizing activities and dynamic ad-hoc collaboration involving multiple users. Thus, we consider people performing various predominantly physical, compound in a smart environment (which includes personal/wearable devices). In this case, being "compound" means that activity can be decomposed into primitive (atomic) actions are executed by individual We investigate how noisy recognition atomic users used to identify instances cooperation at level...
Human health is closely associated with their daily behavior and environment. However, keeping a healthy lifestyle still challenging for most people as it difficult to recognize living behaviors identify surrounding situations take appropriate action. activity recognition promising approach building model of users, by which users can get feedback about habits be encouraged develop healthier lifestyle. In this paper, we present smart light wearable badge six kinds sensors, including an...