Refine
Year of publication
Document Type
- Conference Proceeding (1253) (remove)
Conference Type
- Konferenzartikel (950)
- Konferenz-Abstract (156)
- Konferenzband (77)
- Sonstiges (42)
- Konferenz-Poster (32)
Language
- English (934)
- German (317)
- Multiple languages (1)
- Russian (1)
Keywords
- Mikroelektronik (62)
- RoboCup (32)
- Gamification (12)
- Machine Learning (12)
- injury (10)
- Biomechanik (9)
- Finite-Elemente-Methode (9)
- Kommunikation (9)
- Assistive Technology (8)
- Produktion (8)
Institute
- Fakultät Elektrotechnik und Informationstechnik (E+I) (bis 03/2019) (453)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (286)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (213)
- Fakultät Wirtschaft (W) (164)
- Fakultät Medien und Informationswesen (M+I) (bis 21.04.2021) (120)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (113)
- INES - Institut für nachhaltige Energiesysteme (59)
- IMLA - Institute for Machine Learning and Analytics (46)
- ACI - Affective and Cognitive Institute (40)
- Fakultät Medien (M) (ab 22.04.2021) (33)
Open Access
- Open Access (560)
- Closed Access (456)
- Closed (223)
- Bronze (214)
- Diamond (29)
- Grün (13)
- Gold (6)
- Hybrid (6)
This study aimed to compare a simplified calculation of the knee abduction moment with the traditional inverse dynamics calculation when athletes perform fake-cut maneuvers with different complexities. In the simplified calculation, we multiply the force vector with its lever arm to the knee, projected onto the local coordinate system of the proximal thigh, hence neglecting the inertial contributions from distal segments. We found very strong ranking consistency using Spearman’s rank correlation coefficient when using the simplified method compared to the traditional calculation. Independent of the tasks, the simplified method resulted in higher moments than the inverse dynamics. This was caused by ignoring the moment caused by segment linear acceleration generating a counteracting moment by about 7%. An alternative to the complex calculations of inverse dynamics can be used to investigate the contributions of the GRF magnitude and its lever arm to the knee.
Smart Home-/Smart-Building-Anwendungen sind ein stetig wachsender Markt. Smart Gardening ist ein Beispiel dafür, Nutzern mehr Komfort und eine bessere Lebensqualität zu Hause oder in Bürogebäuden zu ermöglichen. Im Rahmen dieses Beitrags wird die Entwicklung eines Indoor-Smart-Gardening-Systems mit dem Fokus auf energieautarkes Arbeiten vorgestellt. Herzstück des Systems ist ein 3D-gedruckter Blumentopf für einzelne Pflanzen mit integrierter Elektronik zum Monitoring der wichtigsten Pflanzenparameter und einem integrierten Wasserreservoir mit Tauchpumpe für das automatisierte Bewässern der Pflanze. Energy Harvesting per Solarzellen ermöglicht ein energieautarkes Arbeiten des Blumentopfes. Eine selbstentwickelte Low-Power-Funkschnittstelle im Blumentopf und ein externes Gateway ermöglichen die drahtlose Vernetzung mehrerer Pflanzen. Das Gateway dient zur Auswertung der Pflanzenparameter, der Ansteuerung der im Netzwerk vorhandenen Blumentöpfe und als Benutzerinterface.
This paper presents a practice and science orientated education approach for freshman students of interdisciplinary bachelor engineering degree programs. This approach is meant to enhance the motivation and success of freshman students during their whole study. The education approach is called Fit4PracSis (Fit for Practice and Sciences) It was started to develop, set up and establish an education approach, which is building a relationship to students' future profession and to scientific working during the introductory study phase. The freshman students will be trained early in important skills, which are necessary for achieving the final degree successfully and handling of future business and research activities.
This paper presents the competence-, business- and research-orientated education approach Fit4PracSis (= Fit for Practice and Sciences). Fit4PracSis is designed for freshman students in interdisciplinary engineering degree programs. It is an education concept, which is establishing a relationship to the future profession and scientific work during the introductory study phase. The freshman students will be early trained in important skills, which are necessary for the successful achievement of the final degree and the future business and research activities.
Der Entwurf und die Realisierung gedruckter Schaltungen oder Elektronikkomponenten stellt ein intensives Thema der Forschung dar. Forschungsgruppen beschäftigen sich zunehmend mit der Entwicklung von gedruckten Energy Harvestern, weil diese kostengünstig und einfach herstellbar sind. Das Energy Harvesting (EH) oder auch das ”Mikro Energy Harvesting“ (MEH) bezeichnet die Gewinnung von elektrischer Energie aus der Umgebung, um elektronische Verbraucher zu versorgen, kontinuierliche Leistungen zu erzeugen, das System energieeffizienter zu machen, sowie die Energiespeicherung im Mikrowattbereich zu gewährleisten. Energy Harvesting-Systeme stellen eine Alternative gegenüber der Energieversorgung autarker Low-Power-Elektronik mit Batterien dar. Das Energiemanagement solcher EH-Systeme ist jedoch eine Herausforderung aufgrund der Energieverfügbarkeit und der im Zeitablauf nicht konstanten Verlustleistung. Dieser Beitrag gibt einen Überblick über die derzeit existierenden ultra low-power Energiemanagement Schaltungen für Energy Harvester. Dabei wird insbesondere der Fokus auf gedruckte Energy Harvester gelegt. Es soll aufgezeigt werden, welche Aspekte der vorgestellten Energieversorgungsschaltungen bei der Entwicklung eines Energieversorgungschips für gedruckte Energy Harvester berüucksichtigt werden sollen.
The following paper presents the results of a feasibility study about Bluetooth Low Energy (BLE) based wireless sensors. The development of industrial wireless sensors leads to important demands for the wireless technologies like a low energy consumption and a resource saving simple protocol stack. Bluetooth Low Energy (BLE) is a rather new wireless standard which will completely fulfill these fundamental requirements. A self-designed BLE sensor system has been used to explore the common applicability of BLE for wireless sensor systems. The evaluation results of various analyses with the BLE sensor system are now presented in this paper.
During the last ten years the development of wireless sensing applications has become more and more attractive. A major reason for this trend is the large quantity of available wireless technologies. The progressing demand on wireless technologies is mainly driven through development from the industrial wireless sensors market. Especially requirements like low energy consumption, a resource saving simple protocol stack and short timing delays between different states of the wireless transceivers are very important for wireless sensors. Bluetooth Low Energy (BLE) is a rather new wireless standard in addition to the traditional Bluetooth standard (Basis rate and enhanced data rate, BR/EDR) [1]. The BLE will completely fulfill these fundamental requirements. First BLE transceiver chips and modules are available and have been tested and implemented in products. In this paper the performance analysis results of a BLE sensor system which is based on the TI transceiver CC2540F [5] will be presented. The results can be taken for further important investigations like lifetime calculations or BLE simulation models.
Smart Home or Smart Building applications are a growing market. An increasing challenge is to design energy efficient Smart Home applications to achieve sustainable and green homes. Using the example of the development of an Indoor Smart Gardening system with wireless monitoring and automated watering this paper is discussing in particular the design issue of energy autonomous working sensors and actuators for home automation. Most important part of the presented Smart Gardening system is a 3D printed smart flower pot for single plants. The smart flower pot has integrated a water reservoir for automated plant irrigation and an electronic for monitoring important plant parameters and the water level of the water reservoir. Energy harvesting with solar cells enables energy autonomous working of the flower pot. A low-power wireless interface also integrated in the flowerpot and an external gateway based on a Raspberry Pi 3 enables wireless networking of multiple of those flower pots. The gateway is used for evaluating the plant parameters and as a user interface. Particularly the architecture of the energy autonomous wireless flower pot will be considered, because fully energy autonomous sensors and actuators for home automation could not be implemented without special concepts for the energy supply and the overall electronic.
Mit zunehmend komplexer werdenden Schaltungen wachsen auch die Anforderungen an die Entwicklung einer entsprechenden Leiterplatte. Mit der BOARD-Station von MENTOR-Graphics können professionelle Leiterplatten entwickelt werden.
Im Rahmen dreier Entwicklungsprojekte an der Fachhochschule Offenburg wurden mehrere aufwendige Layoutentwürfe mit der BOARD-Station in verschiedenen Diplomarbeiten durchgeführt. Im Folgenden wird über die dabei gewonnenen Erfahrungen berichtet.
Recently, RobustBench (Croce et al. 2020) has become a widely recognized benchmark for the adversarial robustness of image
classification networks. In it’s most commonly reported sub-task, RobustBench evaluates and ranks the adversarial robustness of trained neural networks on CIFAR10 under AutoAttack (Croce and Hein 2020b) with l∞ perturbations limited to ϵ = 8/255. With leading scores of the currently best performing models of around 60% of the baseline, it is fair to characterize this benchmark to be quite challenging. Despite it’s general acceptance in recent literature, we aim to foster discussion about the suitability of RobustBench as a key indicator for robustness which could be generalized to practical applications. Our line of argumentation against this is two-fold and supported by excessive experiments presented in this paper: We argue that I) the alternation of data by AutoAttack with l∞, ϵ = 8/255 is unrealistically strong, resulting in close to perfect detection rates of adversarial samples even by simple detection algorithms and human observers.
We also show that other attack methods are much harder to detect while achieving similar success rates. II) That results on low resolution data sets like CIFAR10 do not generalize well to higher resolution images as gradient based attacks appear to become even more detectable with increasing resolutions.
Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. However, current CNN approaches largely remain vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system while being quasi-imperceptible to the human eye. In recent years, various approaches have been proposed to defend CNNs against such attacks, for example by model hardening or by adding explicit defence mechanisms. Thereby, a small “detector” is included in the network and trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations. In this work, we propose a simple and light-weight detector, which leverages recent findings on the relation between networks’ local intrinsic dimensionality (LID) and adversarial attacks. Based on a re-interpretation of the LID measure and several simple adaptations, we surpass the state-of-the-art on adversarial detection by a significant m argin and reach almost perfect results in terms of F1-score for several networks and datasets. Sources available at: https://github.com/adverML/multiLID
Recently, adversarial attacks on image classification networks by the AutoAttack (Croce and Hein, 2020b) framework have drawn a lot of attention. While AutoAttack has shown a very high attack success rate, most defense approaches are focusing on network hardening and robustness enhancements, like adversarial training. This way, the currently best-reported method can withstand about 66% of adversarial examples on CIFAR10. In this paper, we investigate the spatial and frequency domain properties of AutoAttack and propose an alternative defense. Instead of hardening a network, we detect adversarial attacks during inference, rejecting manipulated inputs. Based on a rather simple and fast analysis in the frequency domain, we introduce two different detection algorithms. First, a black box detector that only operates on the input images and achieves a detection accuracy of 100% on the AutoAttack CIFAR10 benchmark and 99.3% on ImageNet, for epsilon = 8/255 in both cases. Second, a whitebox detector using an analysis of CNN feature maps, leading to a detection rate of also 100% and 98.7% on the same benchmarks.
Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality
(2023)
Diffusion models recently have been successfully applied for the visual synthesis of strikingly realistic appearing images. This raises strong concerns about their potential for malicious purposes. In this paper, we propose using the lightweight multi Local Intrinsic Dimensionality (multiLID), which has been originally developed in context of the detection of adversarial examples, for the automatic detection of synthetic images and the identification of the according generator networks. In contrast to many existing detection approaches, which often only work for GAN-generated images, the proposed method provides close to perfect detection results in many realistic use cases. Extensive experiments on known and newly created datasets demonstrate that the proposed multiLID approach exhibits superiority in diffusion detection and model identification.Since the empirical evaluations of recent publications on the detection of generated images are often mainly focused on the "LSUN-Bedroom" dataset, we further establish a comprehensive benchmark for the detection of diffusion-generated images, including samples from several diffusion models with different image sizes.The code for our experiments is provided at https://github.com/deepfake-study/deepfake-multiLID.
Cardiac resynchronization therapy with biventricular pacing is an established therapy for heart failure patients with electrical left ventricular desynchronization. The aim of this study was to evaluate left atrial conduction delay, intra left atrial conduction delay, left ventricular conduction delay and intra left ventricular conduction delay in heart failure patients using novel signal averaging transesophageal left heart ECG software.
Methods: 8 heart failure patients with dilated cardiomyopathy (DCM), age 68 ± 9 years, New York Heart Association (NYHA) class 2.9 ± 0.2, 24.8 ± 6.7 % left ventricular ejection fraction, 188.8 ± 15.5 ms QRS duration and 8 heart failure patients with ischaemic cardiomyopathy (ICM), age 67 ± 8 years, NYHA class 2.9 ± 0.3, 32.5 ± 7.4 % left ventricular ejection fraction and 167.6 ± 19.4 ms QRS duration were analysed with transesophageal and transthoracic ECG by Bard LabDuo EP system and novel National Intruments LabView signal averaging ECG software.
Results: The electrical left atrial conduction delay was 71.3 ± 17.6 ms in ICM versus 72.3 ± 12.4 ms in DCM, intra left atrial conduction delay 66.8 ± 8.6 ms in ICM versus 63.4 ± 10.9 ms in DCM and left cardiac AV delay 180.5 ± 32.6 ms in ICM versus 152.4 ± 30.4 ms in DCM. The electrical left ventricular conduction delay was 40.9 ± 7.5 ms in ICM versus 42.6 ± 17 ms in DCM and intra left ventricular conduction delay 105.6 ± 19.3 ms in ICM versus 128.3 ± 24.1 ms in DCM.
Conclusions: Left heart signal averaging ECG can be utilized to analyse left atrial conduction delay, intra left atrial conduction delay, left ventricular conduction delay and intra left ventricular conduction delay to improve patient selection for cardiac resynchronization therapy.