Refine
Year of publication
Document Type
- Article (218) (remove)
Language
- English (218) (remove)
Keywords
- (Strict) sign-regularity (1)
- 1D-CNN (1)
- 3D urban planning (1)
- AAL (2)
- Aboriginal people (1)
- Abstract interpretation (1)
- Accelerometer calibration (1)
- Accelerometer sensor (1)
- Accelerometers (1)
- Actuators (1)
Institute
- Fakultät Architektur und Gestaltung (1)
- Fakultät Bauingenieurwesen (11)
- Fakultät Elektrotechnik und Informationstechnik (1)
- Fakultät Informatik (7)
- Fakultät Maschinenbau (3)
- Fakultät Wirtschafts-, Kultur- und Rechtswissenschaften (27)
- Institut für Angewandte Forschung - IAF (30)
- Institut für Optische Systeme - IOS (9)
- Institut für Strategische Innovation und Technologiemanagement - IST (6)
- Institut für Systemdynamik - ISD (27)
This study investigates the application of Force Sensing Resistor (FSR) sensors and machine learning algorithms for non-invasive body position monitoring during sleep. Although reliable, traditional methods like Polysomnography (PSG) are invasive and unsuited for extended home-based monitoring. Our approach utilizes FSR sensors placed beneath the mattress to detect body positions effectively. We employed machine learning techniques, specifically Random Forest (RF), K-Nearest Neighbors (KNN), and XGBoost algorithms, to analyze the sensor data. The models were trained and tested using data from a controlled study with 15 subjects assuming various sleep positions. The performance of these models was evaluated based on accuracy and confusion matrices. The results indicate XGBoost as the most effective model for this application, followed by RF and KNN, offering promising avenues for home-based sleep monitoring systems.
The massive use of patient data for the training of artificial intelligence algorithms is common nowadays in medicine. In this scientific work, a statistical analysis of one of the most used datasets for the training of artificial intelligence models for the detection of sleep disorders is performed: sleep health heart study 2. This study focuses on determining whether the gender and age of the patients have a relevant influence to consider working with differentiated datasets based on these variables for the training of artificial intelligence models.
Accurate monitoring of a patient's heart rate is a key element in the medical observation and health monitoring. In particular, its importance extends to the identification of sleep-related disorders. Various methods have been established that involve sensor-based recording of physiological signals followed by automated examination and analysis. This study attempts to evaluate the efficacy of a non-invasive HR monitoring framework based on an accelerometer sensor specifically during sleep. To achieve this goal, the motion induced by thoracic movements during cardiac contractions is captured by a device installed under the mattress. Signal filtering techniques and heart rate estimation using the symlets6 wavelet are part of the implemented computational framework described in this article. Subsequent analysis indicates the potential applicability of this system in the prognostic domain, with an average error margin of approximately 3 beats per minute. The results obtained represent a promising advancement in non-invasive heart rate monitoring during sleep, with potential implications for improved diagnosis and management of cardiovascular and sleep-related disorders.
This paper compares two popular scripting implementations for hardware prototyping: Python scripts exe- cut from User-Space and C-based Linux-Driver processes executed from Kernel-Space, which can provide information to researchers when considering one or another in their implementations. Conclusions exhibit that deploying software scripts in the kernel space makes it possible to grant a certain quality of sensor information using a Raspberry Pi without the need for advanced real-time operational systems.
A post-growth economy is a comparatively new paradigm in the tourism discourse. The aim of this article is to find out the commonalities between this concept and Māori tourism and in which way the latter can contribute to a post-growth economy. A qualitative mixed method approach, including in-depth-interviews, participant observation, and secondary analysis is applied. The results show that there is a lot of overlap between Māori tourism and a post-growth economy. Differences are visible, as well, regarding the value approach of Māori tourism and the indicator approach of a post-growth economy. Especially the social innovation created in Aotearoa New Zealand at the instigation of Māori groups of granting legal personhood to parts of nature may serve as a driver for a form of tourism that is in line with the idea of a post-growth economy.
This paper applies the concept of Soja’s Thirdspace to the phenomenon of Lazgi dance and tourism in Uzbekistan. In doing so it analyses the different levels of perception (including Firstspace and Secondspace) of Lazgi and tourism via an autoethnographic lens. Complemented by expert interviews, the interaction of Lazgi and tourism is examined and characteristics of the Lazgisphere (world of Lazgi) in Uzbekistan are distilled. The results show that Lazgi is often directly or indirectly connected with tourism in Uzbekistan, but even more so serves to reaffirm national identity.
While driving, stress is caused by situations in which the driver estimates their ability to manage the driving demands as insufficient or loses the capability to handle the situation. This leads to increased numbers of driver mistakes and traffic violations. Additional stressing factors are time pressure, road conditions, or dislike for driving. Therefore, stress affects driver and road safety. Stress is classified into two categories depending on its duration and the effects on the body and psyche: short-term eustress and constantly present distress, which causes degenerative effects. In this work, we focus on distress. Wearable sensors are handy tools for collecting biosignals like heart rate, activity, etc. Easy installation and non-intrusive nature make them convenient for calculating stress. This study focuses on the investigation of stress and its implications. Specifically, the research conducts an analysis of stress within a select group of individuals from both Spain and Germany. The primary objective is to examine the influence of recognized psychological factors, including personality traits such as neuroticism, extroversion, psychoticism, stress and road safety. The estimation of stress levels was accomplished through the collection of physiological parameters (R-R intervals) using a Polar H10 chest strap. We observed that personality traits, such as extroversion, exhibited similar trends during relaxation, with an average heart rate 6% higher in Spain and 3% higher in Germany. However, while driving, introverts, on average, experienced more stress, with rates 4% and 1% lower than extroverts in Spain and Germany, respectively.
Study design:
Retrospective, mono-centric cohort research study.
Objectives:
The purpose of this study is to validate a novel artificial intelligence (AI)-based algorithm against human-generated ground truth for radiographic parameters of adolescent idiopathic scoliosis (AIS).
Methods:
An AI-algorithm was developed that is capable of detecting anatomical structures of interest (clavicles, cervical, thoracic, lumbar spine and sacrum) and calculate essential radiographic parameters in AP spine X-rays fully automatically. The evaluated parameters included T1-tilt, clavicle angle (CA), coronal balance (CB), lumbar modifier, and Cobb angles in the proximal thoracic (C-PT), thoracic, and thoracolumbar regions. Measurements from 2 experienced physicians on 100 preoperative AP full spine X-rays of AIS patients were used as ground truth and to evaluate inter-rater and intra-rater reliability. The agreement between human raters and AI was compared by means of single measure Intra-class Correlation Coefficients (ICC; absolute agreement; .75 rated as excellent), mean error and additional statistical metrics.
Results:
The comparison between human raters resulted in excellent ICC values for intra- (range: .97-1) and inter-rater (.85-.99) reliability. The algorithm was able to determine all parameters in 100% of images with excellent ICC values (.78-.98). Consistently with the human raters, ICC values were typically smallest for C-PT (eg, rater 1A vs AI: .78, mean error: 4.7°) and largest for CB (.96, -.5 mm) as well as CA (.98, .2°).
Conclusions:
The AI-algorithm shows excellent reliability and agreement with human raters for coronal parameters in preoperative full spine images. The reliability and speed offered by the AI-algorithm could contribute to the efficient analysis of large datasets (eg, registry studies) and measurements in clinical practice.
In the last decade, both sustainability and business models for sustainability have increased in importance. Sustainability issues have become the focus of discussion. These issues are interlinked and often negatively impact each other. They are complex and include socio-ecological dilemmas, exist in almost every aspect of our society (economic, environmental, social), and are hard to formulate. They may have multiple, incompatible solutions, competing objectives, and open timeframes. Previous research has not developed satisfactory ways to comprehend and solve problems of this nature. Life Cycle Assessment (LCA) the widely used method to assess sustainable development has reached its limitation to achieve sustainable social goals. System Dynamics (SD) is a valuable methodology that enhances understanding of the structure and internal dynamic behaviours of large, complex, and dynamic systems, leading to improved decision-making. It offers a philosophy and set of tools for modelling, analysing, and simulating dynamic systems. This research applied system dynamics methods in conjunction with simulation software to assess the potential impact of a solution on environmental, social, and economic aspects of a complex system, aims to gain insights into the system's behaviour and identify the potential consequences of interventions or policy changes across multiple dimensions. This paper responds to the urgent need for a new business model by presenting a concept for an adapted dynamic business modelling for sustainability (aDBMfS) using system dynamics. Case studies in the smartphone industry are applied.
“Crowd contamination”?
(2023)
Misconduct allegations have been found to not only affect the alleged firm but also other, unalleged firms in form of reputational and financial spillover effects. It has remained unexplored, however, how the number of prior allegations against other firms matters for an individual firm currently facing an allegation. Building on behavioral decision theory, we argue that the relationship between allegation prevalence among other firms and investor reaction to a focal allegation is inverted U-shaped. The inverted U-shaped effect is theorized to emerge from the combination of two effects: In the absence of prior allegations against other firms, investors fail to anticipate the focal allegation, and hence react particularly negatively (“anticipation effect”). In the case of many prior allegations against other firms, investors also react particularly negatively because investors perceive the focal allegation as more warranted (“evaluation effect”). The multi-industry, empirical analysis of 8,802 misconduct allegations against US firms between 2007 and 2017 provides support for our predicted, inverted U-shaped effect. Our study complements recent misconduct research on spillover effects by highlighting that not only a current allegation against an individual firm can “contaminate” other, unalleged firms but that also prior allegations against other firms can “contaminate” investor reaction to a focal allegation against an individual firm.