Refine
Year of publication
- 2019 (15) (remove)
Document Type
- Conference Proceeding (8)
- Article (3)
- Report (3)
- Other Publications (1)
Keywords
- AAL (2)
- Activity monitoring (1)
- Ambient assisted living (1)
- Artefaktkorrektur (1)
- Atmung (2)
- Automotive (1)
- Bewegung (1)
- Biomedical Signal Capturing (1)
- Drowsiness (1)
- E-Health (1)
- ECG (2)
- EEG (1)
- EKG (1)
- EMG (1)
- Freistellungssemesterbericht (3)
- Herzfrequenz (1)
- Illuminance (1)
- IoT (1)
- Multinomial logistic regression (1)
- Müdigkeitserkennung (1)
- Posture tracking (1)
- Schlafanalyse (3)
- Schlafphasenerkennung (1)
- Sleep (1)
- Sleep latency (1)
- Sleep quality (1)
- Sleep study (2)
- Sleep/Wake states (1)
- Stress (1)
- Telemedicine (1)
Institute
- Fakultät Informatik (15) (remove)
The cornerstone of cognitive systems is environment awareness which enables agile and adaptive use of channel resources. Whitespace prediction based on learning the statistics of the wireless traffic has proven to be a powerful tool to achieve such awareness. In this paper, we propose a novel Hidden Markov Model (HMM) based spectrum learning and prediction approach which accurately estimates the exact length of the whitespace in WiFi channels within the shared industrial scientific medical ISM) bands. We show that extending the number of hidden states and formulating the prediction problem as a maximum likelihood (ML) classification leads to a substantial increase in the prediction horizon compared to classical approaches that predict the immediate (short-term) future. We verify the proposed algorithm through simulations which utilize a model for WiFi traffic based on extensive measurement campaigns.
The Industrial Internet of Things (IIoT) will leverage on wireless network technologies to integrate in a seamless manner Cyber-Physical Systems into existing information systems. In this context, the 6TiSCH architecture, proposed by IETF, represents the current leading standardization effort to enable timed and reliable data communication within IPv6 networks for industrial applications. In wireless networks, Link Quality Estimation (LQE) is a crucial task to select the best routes for data forwarding, regardless of unpredictable time varying conditions. Although, many solutions for LQE have been proposed in literature, the majority of them are not designed specifically for 6TiSCH networks. In this paper, we analyze the performance of existing LQE strategies on 6TiSCH networks.
First, we run a set of simulations to measure the performance of one existing LQE strategy in 6TiSCH. Our simulations show that such strategy can result in measurements with low accuracy due to the 6TiSCH default timeslot allocation strategy. Consequently, we propose an extension of the 6TiSCH Minimal Configuration that allocates specific timeslots for the transmission of probing messages to mitigate the problem. The proposed methodology is demonstrated to effectively reduce the LQE error.
Fatigue and drowsiness are responsible for a significant percentage of road traffic accidents. There are several approaches to monitor the driver’s drowsiness, ranging from the driver’s steering behavior to analysis of the driver, e.g. eye tracking, blinking, yawning or electrocardiogram (ECG). This paper describes the development of a low-cost ECG sensor to derive heart rate variability (HRV) data for the drowsiness detection. The work includes the hardware and the software design. The hardware has been implemented on a printed circuit board (PCB) designed so that the board can be used as an extension shield for an Arduino. The PCB contains a double, inverted ECG channel including low-pass filtering and provides two analog outputs to the Arduino, that combined them and performs the analog-to-digital conversion. The digital ECG signal is transferred to an NVidia embedded PC where the processing takes place, including QRS-complex, heart rate and HRV detection as well as visualization features. The compact resulting sensor provides good results in the extraction of the main ECG parameters. The sensor is being used in a larger frame, where facial-recognition-based drowsiness detection is combined with ECG-based detection to improve the recognition rate under unfavorable light or occlusion conditions.
A significant proportion of road traffic accidents are due to inattentiveness or fatigue at the wheel. Approaches to monitoring the driver's condition range from eye tracking and driving behavior analysis to yawn and blink detection and ECG measurement. This work describes the development of a mobile system for the measurement and processing of ECG data. The aim of the signal processing is to quantify the driver’s fatigue with the heartrate variability (HRV). The work includes the hardware and software design of the sensor. First, the development of low-noise electronics including AD conversion is described. Then the software signal processing with QRS complex detection and plotting front end is explained. The resulting sensor is compact, low-cost and provides a good signal for HRV extraction.
This document presents an algorithm for a non-obtrusive recognition of Sleep/Wake states using signals derived from ECG, respiration, and body movement captured while lying in a bed. As a core mathematical base of system data analytics, multinomial logistic regression techniques were chosen. Derived parameters of the three signals are used as the input for the proposed method. The overall achieved accuracy rate is 84% for Wake/Sleep stages, with Cohen’s kappa value 0.46. The presented algorithm should support experts in analyzing sleep quality in more detail. The results confirm the potential of this method and disclose several ways for its improvement.
The number of home office workers sitting for many hours is increasing. The sensor chair is tracking users’ sitting behavior which the help of pressure sensors and tries to avoid wrong postures which may cause diseases. The system provides live monitoring of the pressure distribution via web interface, as well as sitting posture prediction in real time. Posture analysis is realized through machine learning algorithm using a decision tree classifier that is compared to a random forest. Data acquisition and aggregation for the learning process happens with a mobile app adding users biometrical data and the taken sitting posture as label. The sensor chair is able to differentiate between an arched back, a neutral posture or a laid back position taken on the chair. The classifier achieves an accuracy of 97.4% on our test set and is comparable to the performance of the random forest with 98.9%.
The goal of the presented project is to develop the concept of home ehealth centers for barrier-free and cross-border telemedicine. AAL technologies are already present on the market but there is still a gap to close until they can be used for ordinary patient needs. The general idea needs to be accompanied by new services, which should be brought together in order to provide a full coverage of service for the users. Sleep and stress were chosen as predominant diseases for a detailed study within this project because of their widespread influence in the population. The executed scientific study of available home devices analyzing sleep has provided the necessary to select appropriate devices. The first choice for the project implementation is the device EMFIT QS+. This equipment provides a part of a complete system that a home telemedical hospital can provide at a level of precision and communication with internal and/or external health services.