Refine
Year of publication
Document Type
- Conference Proceeding (50)
- Master's Thesis (34)
- Report (17)
- Article (9)
- Bachelor Thesis (3)
- Doctoral Thesis (3)
- Other Publications (3)
- Working Paper (2)
Language
- English (63)
- German (56)
- Multiple languages (2)
Keywords
- .NET Remoting (1)
- 2 D environment Laser data (1)
- AAL (2)
- ADO.NET (1)
- ASP.NET (1)
- Accelerometers (1)
- Active Server Pages (1)
- ActiveX Data Objects (ADO) (1)
- Activity monitoring (1)
- Agenten-Plattform (1)
Institute
- Fakultät Informatik (121) (remove)
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.
Sleep quality and in general, behavior in bed can be detected using a sleep state analysis. These results can help a subject to regulate sleep and recognize different sleeping disorders. In this work, a sensor grid for pressure and movement detection supporting sleep phase analysis is proposed. In comparison to the leading standard measuring system, which is Polysomnography (PSG), the system proposed in this project is a non-invasive sleep monitoring device. For continuous analysis or home use, the PSG or wearable Actigraphy devices tends to be uncomfortable. Besides this fact, they are also very expensive. The system represented in this work classifies respiration and body movement with only one type of sensor and also in a non-invasive way. The sensor used is a pressure sensor. This sensor is low cost and can be used for commercial proposes. The system was tested by carrying out an experiment that recorded the sleep process of a subject. These recordings showed the potential for classification of breathing rate and body movements. Although previous researches show the use of pressure sensors in recognizing posture and breathing, they have been mostly used by positioning the sensors between the mattress and bedsheet. This project however, shows an innovative way to position the sensors under the mattress.
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%.