Refine
Year of publication
- 2020 (139) (remove)
Document Type
- Conference Proceeding (47)
- Article (36)
- Report (14)
- Part of a Book (12)
- Book (6)
- Other Publications (6)
- Doctoral Thesis (4)
- Master's Thesis (4)
- Journal (Complete Issue of a Journal) (4)
- Bachelor Thesis (3)
Keywords
- 3D ship detection (1)
- Accelerometers (1)
- Accessible Tourism (1)
- Actions (1)
- Adaptive (1)
- Adivasi (1)
- Agiles Lehren (1)
- Agiles Management (1)
- Apnoe (1)
- Architektur (1)
Institute
- Fakultät Architektur und Gestaltung (4)
- Fakultät Bauingenieurwesen (9)
- Fakultät Elektrotechnik und Informationstechnik (1)
- Fakultät Informatik (20)
- Fakultät Maschinenbau (5)
- Fakultät Wirtschafts-, Kultur- und Rechtswissenschaften (13)
- Institut für Angewandte Forschung - IAF (4)
- Institut für Naturwissenschaften und Mathematik - INM (2)
- Institut für Optische Systeme - IOS (8)
- Institut für Strategische Innovation und Technologiemanagement - IST (10)
Globalization has increased the number of road trips and vehicles. The result has been an intensification of traffic accidents, which are becoming one of the most important causes of death worldwide. Traffic accidents are often due to human error, the probability of which increases when the cognitive ability of the driver decreases. Cognitive capacity is closely related to the driver’s mental state, as well as other external factors such as the CO2 concentration inside the vehicle. The objective of this work is to analyze how these elements affect driving. We have conducted an experiment with 50 drivers who have driven for 25 min using a driving simulator. These drivers completed a survey at the start and end of the experiment to obtain information about their mental state. In addition, during the test, their stress level was monitored using biometric sensors and the state of the environment (temperature, humidity and CO2 level) was recorded. The results of the experiment show that the initial level of stress and tiredness of the driver can have a strong impact on stress, driving behavior and fatigue produced by the driving test. Other elements such as sadness and the conditions of the interior of the vehicle also cause impaired driving and affect compliance with traffic regulations.
In previous studies, we used a method for detecting stress that was based exclusively on heart rate and ECG for differentiation between such situations as mental stress, physical activity, relaxation, and rest. As a response of the heart to these situations, we observed different behavior in the Root Mean Square of the Successive differences heartbeats (RMSSD). This study aims to analyze Virtual Reality via a virtual reality headset as an effective stressor for future works. The value of the Root Mean Square of the Successive Differences is an important marker for the parasympathetic effector on the heart and can provide information about stress. For these measurements, the RR interval was collected using a breast belt. In these studies, we can observe the Root Mean Square of the successive differences heartbeats. Additional sensors for the analysis were not used. We conducted experiments with ten subjects that had to drive a simulator for 25 minutes using monitors and 25 minutes using virtual reality headset. Before starting and after finishing each simulation, the subjects had to complete a survey in which they had to describe their mental state. The experiment results show that driving using virtual reality headset has some influence on the heart rate and RMSSD, but it does not significantly increase the stress of driving.
In modern fruit processing technology, non-destructive quality measuring techniques aresought for determining and controlling changes in the optical, structural, and chemical properties of theproducts. In this context, changes inside the product can be measured during processing. Especiallyfor industrial use, fast, precise, but robust methods are particularly important to obtain high-qualityproducts. In this work, a newly developed multi-spectral imaging system was implemented andadapted for drying processes. Further it was investigated if the system could be used to link changesin the surface spectral reflectance during mango drying with changes in moisture content andcontents of chemical components. This was achieved by recovering the spectral reflectance frommulti-spectral image data and comparing the spectral changes with changes of the total soluble solids(TSS), pH-value and the relative moisture contentxwbof the products. In a first step, the camera wasmodified to be used in drying, then the changes in the spectra and quality criteria during mangodrying were measured. For this, mango slices were dried at air temperatures of 40–80◦C and relativeair humidities of 5%–30%. Samples were analyzed and pictures were taken with the multi-spectralimaging system. The quality criteria were then predicted from spectral data. It could be shown thatthe newly developed multi-spectral imaging system can be used for quality control in fruit drying.There are strong indications as well, that it can be employed for the prediction of chemical qualitycriteria of mangoes during drying. This way, quality changes can be monitored inline during theprocess using only one single measuring device.
What drives entrepreneurial action to create a lasting impact? The creation of new ventures that aim at having an impact beyond their financial performance face additional challenges: achieving economic sustainability and at the same time addressing social or environmental issues. Little is known on how these new hybrid organizations, aiming for multiple impact dimensions, manage to be congruent with their blended values. A dataset of 4,125 early-stage ventures is used to gain insights into how blended values are converted into financial, social and environmental impacts, giving shape to different types of hybrid organizations. Our findings suggest new hybrid organizations might opt to sacrifice financial impact to achieve social impact, yet this is not the case when they aim to generate environmental or sustainable impact. Therefore, the tensions and sacrifices related to holding blended values are not homogeneous across all types of new hybrid organizations.
Three-dimensional ship localization with only one camera is a challenging task due to the loss of depth information caused by perspective projection. In this paper, we propose a method to measure distances based on the assumption that ships lie on a flat surface. This assumption allows to recover depth from a single image using the principle of inverse perspective. For the 3D ship detection task, we use a hybrid approach that combines image detection with a convolutional neural network, camera geometry and inverse perspective. Furthermore, a novel calculation of object height is introduced. Experiments show that the monocular distance computation works well in comparison to a Velodyne lidar. Due to its robustness, this could be an easy-to-use baseline method for detection tasks in navigation systems.
Mapping of tree seedlings is useful for tasks ranging from monitoring natural succession and regeneration to effective silvicultural management. Development of methods that are both accurate and cost-effective is especially important considering the dramatic increase in tree planting that is required globally to mitigate the impacts of climate change. The combination of high-resolution imagery from unmanned aerial vehicles and object detection by convolutional neural networks (CNNs) is one promising approach. However, unbiased assessments of these models and methods to integrate them into geospatial workflows are lacking. In this study, we present a method for rapid, large-scale mapping of young conifer seedlings using CNNs applied to RGB orthomosaic imagery. Importantly, we provide an unbiased assessment of model performance by using two well-characterised trial sites together containing over 30,000 seedlings to assemble datasets with a high level of completeness. Our results showed CNN-based models trained on two sites detected seedlings with sensitivities of 99.5% and 98.8%. False positives due to tall weeds at one site and naturally regenerating seedlings of the same species led to slightly lower precision of 98.5% and 96.7%. A model trained on examples from both sites had 99.4% sensitivity and precision of 97%, showing applicability across sites. Additional testing showed that the CNN model was able to detect 68.7% of obscured seedlings missed during the initial annotation of the imagery but present in the field data. Finally, we demonstrate the potential to use a form of weakly supervised training and a tile-based processing chain to enhance the accuracy and efficiency of CNNs applied to large, high-resolution orthomosaics.
This paper presents the goals, service design approach, and the results of the project “Accessible Tourism around Lake Constance”, which is currently run by different universities, industrial partners and selected hotels in Switzerland, Germany and Austria. In the 1st phase, interviews with different persons with disabilities and elderly persons have been conducted to identify the barriers and pains faced by tourists who want to spend their holidays in the region of Lake Constance as well as possible assistive technologies that help to overcome these barriers. The analysis of the interviews shows that one third of the pains and barriers are due to missing, insufficient, wrong or inaccessible information about the
accessibility of the accommodation, surroundings, and points of interests during the planning phase of the holidays. Digital assistive technologies hence play a
major role in bridging this information gap. In the 2nd phase so-called Hotel-Living-Labs (HLL) have been established where the identified assistive technologies
can be evaluated. Based on these HLLs an overall service for accessible holidays has been designed and developed. In the last phase, this service has been implemented
based on the HLLs as well as the identified assistive technologies and is currently field tested with tourists with disabilities from the three participated countries.
Im vorliegenden Beitrag wird der Einfluss der Modellierung des Kellergeschosses auf die Querkraft und die Verformungen von im Kellergeschoss eingespannten Stahlbeton‐Aussteifungswänden untersucht. Der Querkraftverlauf der Wand und die Verschiebung am Kopf der Wand werden mit den entsprechenden, am vereinfachten Kragwandmodell ermittelten Werten verglichen, bei dem die Wand auf Höhe der Kellerdecke voll eingespannt ist und die Weiterleitung der Schnittkräfte im Kellergeschoss nicht näher betrachtet wird. Für die Berücksichtigung des Kellergeschosses wird zunächst eine gelenkige Festhaltung durch die Kellerdecke und die Bodenplatte betrachtet, wodurch sich eine unrealistisch große Wandquerkraft im Kellergeschoss ergibt. Danach wird ein verfeinertes Modell mit Teileinspannung in der Bodenplatte und nachgiebiger Halterung durch die Kellerdecke untersucht. Es werden Empfehlungswerte für die Federkonstante der Drehfeder auf Höhe der Bodenplatte und der horizontalen Translationsfeder auf Höhe der Kellerdecke angegeben, die in der Praxis Anwendung finden können. Es wird besonders der Frage nachgegangen, welche Einflüsse die Berücksichtigung des Kellergeschosses bei der Erdbebenbemessung der Aussteifungswände hat. Dabei wird einerseits die Systemsteifigkeit, von der die Erdbebenersatzlasten abhängen, und andererseits die mögliche Verschiebungsduktilität, von der der mögliche Verhaltensbeiwert q abhängt, betrachtet.
Location-aware mobile devices are becoming increasingly popular and GPS sensors are built into nearly every portable unit with computational capabilities. At the same time, the emergence of location-aware virtual services and ideas calls for new efficient spatial real-time queries. Communication latency in mobile environments interacting with high decentralization and the need of scalability in high-density systems with immense client counts leads to major challenges. In this paper we describe a decentralized architecture for continuous range queries in settings in which both, the requested and the requesting clients, are mobile. While prior works commonly use a request-response approach we provide a stream-based adaptive grid solution dealing with arbitrary high client counts and improving communication latency that meets given hard real-time constraints.
Die Nibelungenbrücke Worms
(2020)
The transformation to an Industry 4.0, which is in general seen as a solution to increasing market challenges, is forcing companies to radically change their way of thinking and to be open to new forms of cooperation. In this context, the opening-up of the innovation process is widely seen as a necessity to meet these challenges, especially for small and medium enterprises (SMEs). The aim of the study therefore is to analyze how cooperation today can be characterized, how this character has changed since the establishment of the term Industry 4.0 at Hanover Fair in 2011 and which cooperation strategies have proven successful. The analysis consists of a quantitative, secondary data analysis that includes country-specific data from 35 European countries of 2010 and 2016 collected by the European Commission and the OECD. The research, focusing on the secondary sector, shows that multinational enterprises MNEs still tend to cooperate more than SMEs, with a slight overall trend towards protectionism. Nevertheless, there is a clear tendency towards the opening-up of SMEs. In this regard, especially universities, competitors and suppliers have become increasingly attractive as cooperation partners for SMEs.
At present, the majority of the proposed Deep Learning (DL) methods provide point predictions without quantifying the model's uncertainty. However, a quantification of the reliability of automated image analysis is essential, in particular in medicine when physicians rely on the results for making critical treatment decisions. In this work, we provide an entire framework to diagnose ischemic stroke patients incorporating Bayesian uncertainty into the analysis procedure. We present a Bayesian Convolutional Neural Network (CNN) yielding a probability for a stroke lesion on 2D Magnetic Resonance (MR) images with corresponding uncertainty information about the reliability of the prediction. For patient-level diagnoses, different aggregation methods are proposed and evaluated, which combine the individual image-level predictions. Those methods take advantage of the uncertainty in the image predictions and report model uncertainty at the patient-level. In a cohort of 511 patients, our Bayesian CNN achieved an accuracy of 95.33% at the image-level representing a significant improvement of 2% over a non-Bayesian counterpart. The best patient aggregation method yielded 95.89% of accuracy. Integrating uncertainty information about image predictions in aggregation models resulted in higher uncertainty measures to false patient classifications, which enabled to filter critical patient diagnoses that are supposed to be closer examined by a medical doctor. We therefore recommend using Bayesian approaches not only for improved image-level prediction and uncertainty estimation but also for the detection of uncertain aggregations at the patient-level.
Probabilistic Deep Learning
(2020)
Probabilistic Deep Learning is a hands-on guide to the principles that support neural networks. Learn to improve network performance with the right distribution for different data types, and discover Bayesian variants that can state their own uncertainty to increase accuracy. This book provides easy-to-apply code and uses popular frameworks to keep you focused on practical applications.
Deep neural networks (DNNs) are known for their high prediction performance, especially in perceptual tasks such as object recognition or autonomous driving. Still, DNNs are prone to yield unreliable predictions when encountering completely new situations without indicating their uncertainty. Bayesian variants of DNNs (BDNNs), such as MC dropout BDNNs, do provide uncertainty measures. However, BDNNs are slow during test time because they rely on a sampling approach. Here we present a single shot MC dropout approximation that preserves the advantages of BDNNs without being slower than a DNN. Our approach is to analytically approximate for each layer in a fully connected network the expected value and the variance of the MC dropout signal. We evaluate our approach on different benchmark datasets and a simulated toy example. We demonstrate that our single shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BDNNs.