Searcharxiv⌕ Search

arXiv subjects

Ralf Mikut

Publications and source records attributed to Ralf Mikut.

68 records · Page 4Linked to original sources
arXiv2019

Towards DeepSpray: Using Convolutional Neural Network to post-process Shadowgraphy Images of Liquid Atomization

This technical report investigates the potential of Convolutional Neural Networks to post-process images from primary atomization. Three tasks are investigated. First, the detection and segmentation of liquid droplets in degraded optical conditions. Second, the detection of overlapping ellipses and the prediction of their geometrical characteristics. This task corresponds to extrapolate the hidden contour of an ellipse with reduced visual information. Third, several features of the liquid surface during primary breakup (ligaments, bags, rims) are manually annotated on 15 experimental images. The detector is trained on this minimal database using simple data augmentation and then applied to other images from numerical simulation and from other experiment. In these three tasks, models from the literature based on Convolutional Neural Networks showed very promising results, thus demonstrating the high potential of Deep Learning to post-process liquid atomization. The next step is to embed these models into a unified framework DeepSpray.

cs.CV↗
arXiv2019

Probabilistic Energy Forecasting using Quantile Regressions based on a new Nearest Neighbors Quantile Filter

Parametric quantile regressions are a useful tool for creating probabilistic energy forecasts. Nonetheless, since classical quantile regressions are trained using a non-differentiable cost function, their creation using complex data mining techniques (e.g., artificial neural networks) may be complicated. This article presents a method that uses a new nearest neighbors quantile filter to obtain quantile regressions independently of the utilized data mining technique and without the non-differentiable cost function. Thereafter, a validation of the presented method using the dataset of the Global Energy Forecasting Competition of 2014 is undertaken. The results show that the presented method is able to solve the competition's task with a similar accuracy and in a similar time as the competition's winner, but requiring a much less powerful computer. This property may be relevant in an online forecasting service for which the fast computation of probabilistic forecasts using not so powerful machines is required.

cs.LG↗
arXiv2018

Transfer Learning with Human Corneal Tissues: An Analysis of Optimal Cut-Off Layer

Transfer learning is a powerful tool to adapt trained neural networks to new tasks. Depending on the similarity of the original task to the new task, the selection of the cut-off layer is critical. For medical applications like tissue classification, the last layers of an object classification network might not be optimal. We found that on real data of human corneal tissues the best feature representation can be found in the middle layers of the Inception-v3 and in the rear layers of the VGG-19 architecture.

cs.NE↗
arXiv2018

Digital Transformation in Airport Ground Operations

How has digital transformation changed airport ground operations? Although the relevant peer-reviewed literature emphasizes the role of cost savings as a key driver behind digitalization of airport ground operations, the focus is on data-driven, customer-centric innovations. This paper argues that ground handling agents are deploying new technologies mainly to boost process efficiency and to cut costs. Our research shows that ground handling agents are embracing current trends to craft new business models and develop new revenue streams. In this paper, we examine the ground handling agent's value chain and identify areas that are strongly affected by digital transformation and those that are not. We discuss different business scenarios for digital technology and link them with relevant research, such as automated service data capturing, new digital services for passengers, big data, indoor navigation, and wearables in airport ground operations. We assess the maturity level of discussed technologies using NASA technology readiness levels.

cs.CY↗
arXiv2017

Cell Segmentation in 3D Confocal Images using Supervoxel Merge-Forests with CNN-based Hypothesis Selection

Automated segmentation approaches are crucial to quantitatively analyze large-scale 3D microscopy images. Particularly in deep tissue regions, automatic methods still fail to provide error-free segmentations. To improve the segmentation quality throughout imaged samples, we present a new supervoxel-based 3D segmentation approach that outperforms current methods and reduces the manual correction effort. The algorithm consists of gentle preprocessing and a conservative super-voxel generation method followed by supervoxel agglomeration based on local signal properties and a postprocessing step to fix under-segmentation errors using a Convolutional Neural Network. We validate the functionality of the algorithm on manually labeled 3D confocal images of the plant Arabidopis thaliana and compare the results to a state-of-the-art meristem segmentation algorithm.

cs.CV↗
arXiv2017

The MATLAB Toolbox SciXMiner: User's Manual and Programmer's Guide

The Matlab toolbox SciXMiner is designed for the visualization and analysis of time series and features with a special focus to classification problems. It was developed at the Institute of Applied Computer Science of the Karlsruhe Institute of Technology (KIT), a member of the Helmholtz Association of German Research Centres in Germany. The aim was to provide an open platform for the development and improvement of data mining methods and its applications to various medical and technical problems. SciXMiner bases on Matlab (tested for the version 2017a). Many functions do not require additional standard toolboxes but some parts of Signal, Statistics and Wavelet toolboxes are used for special cases. The decision to a Matlab-based solution was made to use the wide mathematical functionality of this package provided by The Mathworks Inc. SciXMiner is controlled by a graphical user interface (GUI) with menu items and control elements like popup lists, checkboxes and edit elements. This makes it easier to work with SciXMiner for inexperienced users. Furthermore, an automatization and batch standardization of analyzes is possible using macros. The standard Matlab style using the command line is also available. SciXMiner is an open source software. The download page is http://sourceforge.net/projects/SciXMiner. It is licensed under the conditions of the GNU General Public License (GNU-GPL) of The Free Software Foundation.

cs.LG↗
arXiv2017

3D Cell Nuclei Segmentation with Balanced Graph Partitioning

Cell nuclei segmentation is one of the most important tasks in the analysis of biomedical images. With ever-growing sizes and amounts of three-dimensional images to be processed, there is a need for better and faster segmentation methods. Graph-based image segmentation has seen a rise in popularity in recent years, but is seen as very costly with regard to computational demand. We propose a new segmentation algorithm which overcomes these limitations. Our method uses recursive balanced graph partitioning to segment foreground components of a fast and efficient binarization. We construct a model for the cell nuclei to guide the partitioning process. Our algorithm is compared to other state-of-the-art segmentation algorithms in an experimental evaluation on two sets of realistically simulated inputs. Our method is faster, has similar or better quality and an acceptable memory overhead.

cs.CV↗
arXiv2017

Nearest-Neighbor Based Non-Parametric Probabilistic Forecasting with Applications in Photovoltaic Systems

The present contribution offers a simple methodology for the obtainment of data-driven interval forecasting models by combining pairs of quantile regressions. Those regressions are created without the usage of the non-differentiable pinball-loss function, but through a k-nearest-neighbors based training set transformation and traditional regression approaches. By leaving the underlying training algorithms of the data mining techniques unchanged, the presented approach simplifies the creation of quantile regressions with more complex techniques (e.g. artificial neural networks). The quality of the presented methodology is tested on the usecase of photovoltaic power forecasting, for which quantile regressions using polynomial models as well as artificial neural networks and support vector regressions are created. From the resulting evaluation values it can be concluded that acceptable interval forecasting models are created.

eess.SY↗
arXiv2017

Datenqualität in Regressionsproblemen

Regression models are increasingly built using datasets which do not follow a design of experiment. Instead, the data is e.g. gathered by an automated monitoring of a technical system. As a consequence, already the input data represents phenomena of the system and violates statistical assumptions of distributions. The input data can show correlations, clusters or other patterns. Further, the distribution of input data influences the reliability of regression models. We propose criteria to quantify typical phenomena of input data for regression and show their suitability with simulated benchmark datasets. ----- Regressionen werden zunehmend auf Datensätzen angewendet, deren Eingangsvektoren nicht durch eine statistische Versuchsplanung festgelegt wurden. Stattdessen werden die Daten beispielsweise durch die passive Beobachtung technischer Systeme gesammelt. Damit bilden bereits die Eingangsdaten Phänomene des Systems ab und widersprechen statistischen Verteilungsannahmen. Die Verteilung der Eingangsdaten hat Einfluss auf die Zuverlässigkeit eines Regressionsmodells. Wir stellen deshalb Bewertungskriterien für einige typische Phänomene in Eingangsdaten von Regressionen vor und zeigen ihre Funktionalität anhand simulierter Benchmarkdatensätze.

stat.ML↗
arXiv2016

Fuzzy-based Propagation of Prior Knowledge to Improve Large-Scale Image Analysis Pipelines

Many automatically analyzable scientific questions are well-posed and offer a variety of information about the expected outcome a priori. Although often being neglected, this prior knowledge can be systematically exploited to make automated analysis operations sensitive to a desired phenomenon or to evaluate extracted content with respect to this prior knowledge. For instance, the performance of processing operators can be greatly enhanced by a more focused detection strategy and the direct information about the ambiguity inherent in the extracted data. We present a new concept for the estimation and propagation of uncertainty involved in image analysis operators. This allows using simple processing operators that are suitable for analyzing large-scale 3D+t microscopy images without compromising the result quality. On the foundation of fuzzy set theory, we transform available prior knowledge into a mathematical representation and extensively use it enhance the result quality of various processing operators. All presented concepts are illustrated on a typical bioimage analysis pipeline comprised of seed point detection, segmentation, multiview fusion and tracking. Furthermore, the functionality of the proposed approach is validated on a comprehensive simulated 3D+t benchmark data set that mimics embryonic development and on large-scale light-sheet microscopy data of a zebrafish embryo. The general concept introduced in this contribution represents a new approach to efficiently exploit prior knowledge to improve the result quality of image analysis pipelines. Especially, the automated analysis of terabyte-scale microscopy data will benefit from sophisticated and efficient algorithms that enable a quantitative and fast readout. The generality of the concept, however, makes it also applicable to practically any other field with processing strategies that are arranged as linear pipelines.

cs.CV↗
arXiv2016

Generating Semi-Synthetic Validation Benchmarks for Embryomics

Systematic validation is an essential part of algorithm development. The enormous dataset sizes and the complexity observed in many recent time-resolved 3D fluorescence microscopy imaging experiments, however, prohibit a comprehensive manual ground truth generation. Moreover, existing simulated benchmarks in this field are often too simple or too specialized to sufficiently validate the observed image analysis problems. We present a new semi-synthetic approach to generate realistic 3D+t benchmarks that combines challenging cellular movement dynamics of real embryos with simulated fluorescent nuclei and artificial image distortions including various parametrizable options like cell numbers, acquisition deficiencies or multiview simulations. We successfully applied the approach to simulate the development of a zebrafish embryo with thousands of cells over 14 hours of its early existence.

cs.CV↗
arXiv2016

Robust Individual Circadian Parameter Estimation for Biosignal-based Personalisation of Cancer Chronotherapy

In cancer treatment, chemotherapy is administered according a constant schedule. The chronotherapy approach, considering chronobiological drug delivery, adapts the chemotherapy profile to the circadian rhythms of the human organism. This reduces toxicity effects and at the same time enhances efficiency of chemotherapy. To personalize cancer treatment, chemotherapy profiles have to be further adapted to individual patients. Therefore, we present a new model to represent cycle phenomena in circadian rhythms. The model enables a more precise modelling of the underlying circadian rhythms. In comparison with the standard model, our model delivers better results in all defined quality indices. The new model can be used to adapt the chemotherapy profile efficiently to individual patients. The adaption to individual patients contributes to the aim of personalizing cancer therapy.

q-bio.QM↗
arXiv2016

Challenges of Integrating A Priori Information Efficiently in the Discovery of Spatio-Temporal Objects in Large Databases

Using the knowledge discovery framework, it is possible to explore object databases and extract groups of objects with highly heterogeneous movement behavior by efficiently integrating a priori knowledge through interacting with the framework. The whole process is modular expandable and is therefore adaptive to any problem formulation. Further, the flexible use of different information allocation processes reveal a great potential to efficiently incorporate the a priori knowledge of different users in different ways. Therefore, the stepwise knowledge discovery process embedded in the knowledge discovery framework is described in detail to point out the flexibility of such a system incorporating object databases from different applications. The described framework can be used to gain knowledge out of object databases in many different fields. This knowledge can be used to gain further insights and improve the understanding of underlying phenomena. The functionality of the proposed framework is exemplarily demonstrated using a benchmark database based on real biological object data.

cs.CV↗