Refine
H-BRS Bibliography
- yes (2495) (remove)
Departments, institutes and facilities
- Fachbereich Informatik (979)
- Fachbereich Angewandte Naturwissenschaften (630)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (388)
- Fachbereich Ingenieurwissenschaften und Kommunikation (386)
- Fachbereich Wirtschaftswissenschaften (317)
- Institute of Visual Computing (IVC) (286)
- Institut für funktionale Gen-Analytik (IFGA) (231)
- Internationales Zentrum für Nachhaltige Entwicklung (IZNE) (126)
- Institut für Cyber Security & Privacy (ICSP) (107)
- Institut für Verbraucherinformatik (IVI) (104)
Document Type
- Article (1021)
- Conference Object (918)
- Part of a Book (189)
- Preprint (86)
- Doctoral Thesis (52)
- Report (51)
- Book (monograph, edited volume) (43)
- Master's Thesis (29)
- Working Paper (28)
- Research Data (22)
Year of publication
Language
- English (2495) (remove)
Keywords
- Virtual Reality (15)
- FPGA (14)
- Machine Learning (14)
- GC/MS (13)
- Robotics (13)
- Sustainability (11)
- virtual reality (11)
- Augmented Reality (9)
- Lignin (9)
- Social Protection (9)
Sweet sorghum (Sorghum bicolor (L.) moench), a crop that is grown by subsistence farmers in Zimbabwe was used to extract silica gel in order to assess its possible use as a raw material for the production of silica-based products. The gel was prepared from sodium silicate extracted from sweet sorghum bagasse ash by sodium hydroxide leaching. Results show that maximum yield can be obtained at pH 5 and with 3 M sodium concentration. The silica gel prepared at optimum pH 5 had a bulk density of 0.5626 g/cm3 and anestimated porosity of 71.87%. Silica gel aged over 10 h had improved moisture adsorption properties. X-ray fluorescence (XRF) determinations show that the silica content in the ash is 40.1%. Characterization of sweet sorghum ash and silica gels produced at pH 5, 7 and 8.5 by Fourier Transform Infrared spectroscopy gave absorption bands similar to those reported by other researchers.Transmission electron micrographs show that silica prepared under optimum conditions is amorphous and consisted of irregular particles. Sweet sorghum proved to be a potential low cost raw material for the production of silica gel.
The recent explosion of available audio-visual media is the new challenge for information retrieval research. Audio speech recognition systems translate spoken content to the text domain. There is a need for searching and indexing this data which possesses no logical structure. One possible way to structure it on a high level of abstraction is by finding topic boundaries. Two unsupervised topic segmentation methods were evaluated with real-world data in the course of this work. The first one, TSF, models topic shifts as fluctuations in the similarity function of the transcript. The second one, LCSeg, approaches topic changes as places with the least overlapping lexical chains. Only LCSeg performed close to a similar real-world corpus. Other reported results could not be outperformed. Topic analysis based on the repeated word usage models renders topic changes more ambiguous than expected. This issue has more impact on the segmentation quality than the state-of-the-art ASR word error rate. It could be concluded that it is advisable to develop topic segmentation algorithms with real-world data to avoid potential biases to artificial data. Unlike evaluated approaches based on word usage analysis, methods operating with local contexts can be expected to perform better through emulation of semantic dependencies.
Object detectors have improved considerably in the last years by using advanced Convolutional Neural Networks (CNNs) architectures. However, many detector hyper-parameters are not generally tuned, and they are used with values set by the detector authors. Blackbox optimization methods have gained more attention in recent years because of its ability to optimize the hyper-parameters of various machine learning algorithms and deep learning models. However, these methods are not explored in improving CNN-based object detector's hyper-parameters. In this research work, we propose the use of blackbox optimization methods such as Gaussian Process based Bayesian Optimization (BOGP), Sequential Model-based Algorithm Configuration (SMAC), and Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to tune the hyper-parameters in Faster R-CNN and Single Shot MultiBox Detector (SSD). In Faster R-CNN, tuning the input image size, prior box anchor scales and ratios using BOGP, SMAC, and CMA-ES has increased the performance around 1.5% in terms of Mean Average Precision (mAP) on PASCAL VOC. Tuning the anchor scales of SSD has increased the mAP by 3% on PASCAL VOC and marine debris datasets. On the COCO dataset with SSD, mAP improvement is observed in the medium and large objects, but mAP decreases by 1% in small objects. The experimental results show that the blackbox optimization methods have proved to increase the mAP performance by optimizing the object detectors. Moreover, it has achieved better results than the hand-tuned configurations in most of the cases.
Object detectors have improved considerably in the last years by using advanced CNN architectures. However, many detector hyper-parameters are generally manually tuned, or they are used with values set by the detector authors. Automatic Hyper-parameter optimization has not been explored in improving CNN-based object detectors hyper-parameters. In this work, we propose the use of Black-box optimization methods to tune the prior/default box scales in Faster R-CNN and SSD, using Bayesian Optimization, SMAC, and CMA-ES. We show that by tuning the input image size and prior box anchor scale on Faster R-CNN mAP increases by 2% on PASCAL VOC 2007, and by 3% with SSD. On the COCO dataset with SSD there are mAP improvement in the medium and large objects, but mAP decreases by 1% in small objects. We also perform a regression analysis to find the significant hyper-parameters to tune.
3D-Printing is an efficient method in the field of additive manufacturing. In order to optimize the properties of manufactured parts it is essential to adapt the curing behavior of the resin systems with respect to the requirements. Thus, effects of resin composition, e.g. due to different additives such as thickener and curing agents, on the curing behavior have to be known. As the resin transfers from a liquid to a solid glass the time dependent ion viscosity was measured using DEA with flat IDEX sensors. This allows for a sensitive measurement of resin changes as the ion viscosity changes two to four decades. The investigated resin systems are based on the monomers styrene and HEMA. To account for the effects of copolymerization in the calculation of the reaction kinetics it was assumed that the reaction can be considered as a homo-polymerization having a reaction order n?1. Then the measured ion viscosity curves are fitted with the solution of the reactions kinetics - the time dependent degree of conversion (DC-function) - for times exceeding the initiation phase representing the primary curing. The measured ion viscosity curves can nicely be fitted with the DC-function and the determined fit parameters distinguish distinctly between the investigated resin compositions.
The ongoing miniaturization, multi-layer structure parts and hybrid parts require methods to determine mechanical properties on a micro-scale. However, there is a gap in measuring techniques. On one hand there are the classical methods to measure hardness e.g. VICKERS, ROCKWELL, UNIVERSAL, IRHD etc having resolutions typically above 100μm. On the other hand there are well-developed AFM methods that allow for the determination of mechanical properties in the nanometer range. This paper describes an indentation technique that yields data of mechanical properties in the micrometer range between typically 5 to 50 μm. The measuring device and the data evaluation is presented. Results of micro-mechanical mapping are shown for NR-SBR rubber interfaces, a fuel tank and a part manufactured by two component injection moulding. Finally, the measured micro-mechanical stiffness is compared to the YOUNG’s modulus of the corresponding materials.
In service robotics, tasks without the involvement of objects are barely applicable, like in searching, fetching or delivering tasks. Service robots are supposed to capture efficiently object related information in real world scenes while for instance considering clutter and noise, and also being flexible and scalable to memorize a large set of objects. Besides object perception tasks like object recognition where the object’s identity is analyzed, object categorization is an important visual object perception cue that associates unknown object instances based on their e.g. appearance or shape to a corresponding category. We present a pipeline from the detection of object candidates in a domestic scene over the description to the final shape categorization of detected candidates. In order to detect object related information in cluttered domestic environments an object detection method is proposed that copes with multiple plane and object occurrences like in cluttered scenes with shelves. Further a surface reconstruction method based on Growing Neural Gas (GNG) in combination with a shape distribution-based descriptor is proposed to reflect shape characteristics of object candidates. Beneficial properties provided by the GNG such as smoothing and denoising effects support a stable description of the object candidates which also leads towards a more stable learning of categories. Based on the presented descriptor a dictionary approach combined with a supervised shape learner is presented to learn prediction models of shape categories.
Experimental results, of different shapes related to domestically appearing object shape categories such as cup, can, box, bottle, bowl, plate and ball, are shown. A classification accuracy of about 90% and a sequential execution time of lesser than two seconds for the categorization of an unknown object is achieved which proves the reasonableness of the proposed system design. Additional results are shown towards object tracking and false positive handling to enhance the robustness of the categorization. Also an initial approach towards incremental shape category learning is proposed that learns a new category based on the set of previously learned shape categories.
In this paper, we describe an approach that enables an autonomous system to infer the semantics of a command (i.e. a symbol sequence representing an action) in terms of the relations between changes in the observations and the action instances. We present a method of how to induce a theory (i.e. a semantic description) of the meaning of a command in terms of a minimal set of background knowledge. The only thing we have is a sequence of observations from which we extract what kinds of effects were caused by performing the command. This way, we yield a description of the semantics of the action and, hence, a definition.
The task of this thesis is to develop an OGC-compliant Sensor Observation Service (SOS) { a component of the SWE { for GPS related sensor data in this context. It should, in contrast to existing implementations, support full mobility of the sensors and be con gurable with respect to adding di erent kinds of sensors. In particular, mobile phones should be considered as sensors, which transmit their data to the SOS server through the transactional SOS interface.