Refine
Year of publication
Document Type
- Conference Proceeding (874) (remove)
Conference Type
- Konferenzartikel (682)
- Konferenz-Abstract (131)
- Sonstiges (34)
- Konferenz-Poster (22)
- Konferenzband (8)
Language
- English (874) (remove)
Has Fulltext
- no (874) (remove)
Keywords
- RoboCup (32)
- Gamification (11)
- Machine Learning (11)
- injury (10)
- Biomechanik (9)
- Kommunikation (9)
- Assistive Technology (8)
- TRIZ (8)
- Deep Leaning (7)
- Additive Manufacturing (6)
Institute
- Fakultät Elektrotechnik und Informationstechnik (E+I) (bis 03/2019) (288)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (187)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (177)
- Fakultät Wirtschaft (W) (126)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (103)
- Fakultät Medien und Informationswesen (M+I) (bis 21.04.2021) (94)
- IMLA - Institute for Machine Learning and Analytics (45)
- ACI - Affective and Cognitive Institute (38)
- INES - Institut für nachhaltige Energiesysteme (37)
- Fakultät Medien (M) (ab 22.04.2021) (25)
Open Access
- Closed Access (375)
- Open Access (305)
- Closed (182)
- Bronze (86)
- Diamond (17)
- Hybrid (5)
- Grün (4)
- Gold (3)
During the day-to-day exploitation of localization systems in mines, the technical staff tends to incorrectly rearrange radio equipment: positions of devices may not be accurately marked on a map or their positions may not correspond to the truth. This situation may lead to positioning inaccuracies and errors in the operation of the localization system.This paper presents two Bayesian algorithms for the automatic corrections of positions of the equipment on the map using trajectories restored by the inertial measurement units mounted to mobile objects, like pedestrians and vehicles. As a basis, a predefined map of the mine represented as undirected weighted graph was used as input. The algorithms were implemented using the Simultaneous Localization and Mapping (SLAM) approach.The results prove that both methods are capable to detect misplacement of access points and to provide corresponding corrections. The discrete Bayesian filter outperforms the unscented Kalman filter, which, however, requires more computational power.
This paper presents an extended version of a previously published Bayesian algorithm for the automatic correction of the positions of the equipment on the map with simultaneous mobile object trajectory localization (SLAM) in underground mine environment represented by undirected graph. The proposed extended SLAM algorithm requires much less preliminary data on possible equipment positions and uses an additional resample move algorithm to significantly improve the overall performance.
In medical applications wireless technologies are not widely spread. Today they are mainly used in non latency-critical applications where reliability can be guaranteed through retransmission protocols and error correction mechanisms. By using retransmission protocols within the disturbed shared wireless channel latency will increase. Therefore retransmission protocols are not sufficient for removing latency-critical wired connections within operating rooms such as foot switches. Todays research aims to improve reliability through the physical characteristics of the wireless channel by using diversity methods and more robust modulation. In this paper an Architecture for building up a reliable network is presented. The Architecture offers the possibility for devices with different reliability, latency and energy consumption requirements to participate. Furthermore reliability, latency and energy consumption are scalable for every single participant.
In this paper, we describe a first publicly available fine-grained product recognition dataset based on leaflet images. Using advertisement leaflets, collected over several years from different European retailers, we provide a total of 41.6k manually annotated product images in 832 classes. Further, we investigate three different approaches for this fine-grained product classification task, Classification by Image, by Text, as well as by Image and Text. The approach "Classification by Text" uses the text extracted directly from the leaflet product images. We show, that the combination of image and text as input improves the classification of visual difficult to distinguish products. The final model leads to an accuracy of 96.4% with a Top-3 score of 99.2%. We release our code at https://github.com/ladwigd/Leaflet-Product-Classification.
New frontiers of supraventricular tachycardia and atrial flutter evaluation and catheter ablation
(2012)
Radiofrequency catheter ablation (RFCA) has revolutionized treatment for tachyarrhythmias and has become first-line therapy for some tachycardias. Although developed in the 1980s and widely applied in the 1990s, the technique is still in development. Transesophageal atrial pacing (TAP) can used for initiation and termination of supraventricular tachycardia (SVT).
Methods: The paroxysmal SVT include a wide spectrum of disorders including, in descending order of frequency, atrial flutter, atrioventricular (AV) nodal reentry, Wolff-Parkinson-White syndrome, and atrial tachycardia. While not life-threatening in most cases, they may cause important symptoms, such as palpitations, chest discomfort, breathlessness, anxiety, and syncope, which significantly impair quality of life. Medical therapy has variable efficacy, and most patients are not rendered free of symptoms. Research over the past several decades has revealed fundamental mechanisms involved in the initiation and maintenance of all of these arrhythmias. Knowledge of mechanisms has in turn led to highly effective surgical and catheter-based treatments. The supraventricular arrhythmias and their treatment are described in this report. SVT initiation was analysed with programmed TAP in 49 patients with palpitations (age 47 ± 17 years, 24 females, 25 males).
Results: In comparison to antiarrhythmic drug therapy the radiofrequency catheter ablation in patients suffering from atrial flutter, atrioventricular nodal reentry, atrioventricular reentry and atrial tachycardia is the better choice in most cases. TAP SVT initiation was possible in 23 patients before RFCA. Atrial cycle length of SVT was 320 ± 59 ms. We initiated AV nodal reentrant tachycardia (AVNRT, n=15), atrial tachycardia (AT, n=6) and AV reentrant tachycardia with Kent pathway conduction (AVRT, n=2) before RFCA.
Conclusions: Radiofrequency catheter ablation is a successful and safe method to cure most patients with paroxysmal supraventricular tachycardias. TAP allowed initiation and termination of SVT especially in outpatients.
Active safety systems for advanced driver assistance systems act within a complex, dynamic traffic environment featuring various sensor systems which detect the vehicles’ surroundings and interior. This paper describes the recent progress towards a performance evaluation of car-to-car communication (C2C) for active safety systems - in particular for crash constellation prediction. The methodology introduced in this work is designed to evaluate the impact of different sensors on the accuracy of a crash constellation prediction algorithm. The benefit of C2C communication (viewed as a virtual sensor) within a sensor data fusion architecture for pre-crash collision prediction is explored. Therefore, a simulation environment for accident scenarios analysis reproducing real-world sensor behaviour, is designed and implemented. Performance evaluation results show that C2C increases confidence in the estimated position of the oncoming vehicle. With C2C enhancement the given accuracy in time-to-collision (TTC) estimation is achievable about 110 ms earlier for moderate velocities at TTC range of [0.5s..0.2s]. The uncertainty in the vehicle position prediction at the time of collision can be reduced about half by integrating C2C communication into the sensor data fusion.
ECG simulators, available on the market, imitate the electric activity of the heart in a simplified manner. Thus, they are suitable for education purposes but not really for testing algorithms to recognize complex arrhythmias needed for pacemakers and implantable defibrillators. Especially certain discrimination between various morphologies of atrial and ventricular fibrillation needs simulators providing native electrograms of different patients’ heart rhythm events. This explains the necessity to develop an ECG simulator providing high-resolution native intracardiac and surface electrograms of in-vivo rhythm events. In this paper we demonstrate an approach for an ECG simulator based on a consumer multichannel soundcard and a corresponding software application for a laptop computer. This Live-ECG Simulator is able to handle invasive electrogram recordings from electrophysiological studies and send the data to a modified external soundcard for subsequent digital to analog conversion. The hardware is completed with an electronic circuit providing level adjustment to adapt the output amplitude to the input conditions of several cardiac implants.