Reachability problems on reliable and lossy queue automata. - In: Theory of computing systems, ISSN 1433-0490, Bd. 65 (2021), 8, S. 1211-1242
We study the reachability problem for queue automata and lossy queue automata. Concretely, we consider the set of queue contents which are forwards resp. backwards reachable from a given set of queue contents. Here, we prove the preservation of regularity if the queue automaton loops through some special sets of transformation sequences. This is a generalization of the results by Boigelot et al. and Abdulla et al. regarding queue automata looping through a single sequence of transformations. We also prove that our construction is possible in polynomial time.
https://doi.org/10.1007/s00224-021-10031-2
Defocus particle tracking : a comparison of methods based on model functions, cross-correlation, and neural networks. - In: Measurement science and technology, ISSN 1361-6501, Bd. 32 (2021), 9, 094011, insges. 14 S.
Defocus particle tracking (DPT) has gained increasing importance for its use to determine particle trajectories in all three dimensions with a single-camera system, as typical for a standard microscope, the workhorse of todays ongoing biomedical revolution. DPT methods derive the depth coordinates of particle images from the different defocusing patterns that they show when observed in a volume much larger than the respective depth of field. Therefore it has become common for state-of-the-art methods to apply image recognition techniques. Two of the most commonly and widely used DPT approaches are the application of (astigmatism) particle image model functions (MF methods) and the normalized cross-correlations between measured particle images and reference templates (CC methods). Though still young in the field, the use of neural networks (NN methods) is expected to play a significant role in future and more complex defocus tracking applications. To assess the different strengths of such defocus tracking approaches, we present in this work a general and objective assessment of their performances when applied to synthetic and experimental images of different degrees of astigmatism, noise levels, and particle image overlapping. We show that MF methods work very well in low-concentration cases, while CC methods are more robust and provide better performance in cases of larger particle concentration and thus stronger particle image overlap. The tested NN methods generally showed the lowest performance, however, in comparison to the MF and CC methods, they are yet in an early stage and have still great potential to develop within the field of DPT.
https://doi.org/10.1088/1361-6501/abfef6
Von Daten zu Künstlicher Intelligenz - Datenmanagement als Basis für erfolgreiche KI-Anwendungen. - In: Digitale Welt, ISSN 2569-1996, Bd. 5 (2021), 3, S. 75-79
https://doi.org/10.1007/s42354-021-0383-z
SynDistNet: self-supervised monocular fisheye camera distance estimation synergized with semantic segmentation for autonomous driving. - In: 2021 IEEE Winter Conference on Applications of Computer Vision, (2021), S. 61-71
State-of-the-art self-supervised learning approaches for monocular depth estimation usually suffer from scale ambiguity. They do not generalize well when applied on distance estimation for complex projection models such as in fisheye and omnidirectional cameras. This paper introduces a novel multi-task learning strategy to improve self-supervised monocular distance estimation on fisheye and pinhole camera images. Our contribution to this work is threefold: Firstly, we introduce a novel distance estimation network architecture using a self-attention based encoder coupled with robust semantic feature guidance to the decoder that can be trained in a one-stage fashion. Secondly, we integrate a generalized robust loss function, which improves performance significantly while removing the need for hyperparameter tuning with the reprojection loss. Finally, we reduce the artifacts caused by dynamic objects violating static world assumptions using a semantic masking strategy. We significantly improve upon the RMSE of previous work on fisheye by 25% reduction in RMSE. As there is little work on fisheye cameras, we evaluated the proposed method on KITTI using a pinhole model. We achieved state-of-the-art performance among self-supervised methods without requiring an external scale estimation.
https://doi.org/10.1109/WACV48630.2021.00011
Virtual environments for Smart House system studying. - In: Educating engineers for future industrial revolutions, (2021), S. 569-576
Today, virtual worlds are used not only in the gaming industry. Virtual, augmented and cross-reality also allow to organize effectively 3D environments that provide the effect of immersion and user interaction with objects and processes of the learning environment. The combination of physical objects and virtual models is a modern trend in the online lab development. Based on this approach, online experiment becomes more visual and interesting for students. In addition, it reduces queues for experiments on the real equipment. The paper presents the results of the development of an interactive web-oriented virtual model that expands the Smart House & IoT remote laboratory functionality as well as 3D virtual environment of Smart House for the virtual reality helmet. The proposed solutions will motivate students to study home automation technologies and the features of Smart Home systems realization.
Modern mobile interface for remote laboratory control. - In: Educating engineers for future industrial revolutions, (2021), S. 584-592
The implementation of modern mobile interfaces for online laboratories is an urgent task because it allows increasing students' interest in such educational resources usage, especially in non-standard situations (for example, during self-isolation period). The results of Telegram messenger's chatbot development for interaction with remote laboratory Smart House & IoT are presented in this paper. It gives comfortable and effective tools and possibilities for the popularization of remote laboratory application for home automation technologies studying.
Explaining clinical decision support systems in medical imaging using cycle-consistent activation maximization. - In: Neurocomputing, ISSN 1872-8286, Bd. 458 (2021), S. 141-156
Clinical decision support using deep neural networks has become a topic of steadily growing interest. While recent work has repeatedly demonstrated that deep learning offers major advantages for medical image classification over traditional methods, clinicians are often hesitant to adopt the technology because its underlying decision-making process is considered to be intransparent and difficult to comprehend. In recent years, this has been addressed by a variety of approaches that have successfully contributed to providing deeper insight. Most notably, additive feature attribution methods are able to propagate decisions back into the input space by creating a saliency map which allows the practitioner to "see what the network sees." However, the quality of the generated maps can become poor and the images noisy if only limited data is available - a typical scenario in clinical contexts. We propose a novel decision explanation scheme based on CycleGAN activation maximization which generates high-quality visualizations of classifier decisions even in smaller data sets. We conducted a user study in which we evaluated our method on the LIDC dataset for lung lesion malignancy classification, the BreastMNIST dataset for ultrasound image breast cancer detection, as well as two subsets of the CIFAR-10 dataset for RBG image object recognition. Within this user study, our method clearly outperformed existing approaches on the medical imaging datasets and ranked second in the natural image setting. With our approach we make a significant contribution towards a better understanding of clinical decision support systems based on deep neural networks and thus aim to foster overall clinical acceptance.
https://doi.org/10.1016/j.neucom.2021.05.081
A generative approach for creating Eclipse Sirius editors for generic systems. - In: SYSCON 2021, (2021), insges. 8 S.
Model-Driven Engineering (MDE) is getting more and more important for modeling, analyzing, and simulating complicated systems. It can also be used for both documenting and generating source code, which is less error-prone than a manually written one. For defining a model, it is common to have a graphical representation that can be edited through an editor. Creating such an editor for a given domain may be a difficult task for first-time users and a tedious, repetitive, and error-prone task for experienced ones. This paper introduces a new automated flow to ease the creation of ready-to-use Sirius editors based on a model, graphically defined by the domain experts, which describe their domains structure. We provide different model transformations to generate the required artifacts to obtain a fully-fledged Sirius editor based on a generated domain metamodel. The generated editor can then be distributed as an Eclipse application or as a collaborative web application. Thanks to this generative approach, it is possible to reduce the cost of refactoring the domains model in successive iterations, as only the final models need to be updated to conform to the latest format. At the same time, the editor gets generated and hence updated automatically at practically no cost.
https://doi.org/10.1109/SysCon48628.2021.9447062
Surface-modified magnetite nanoparticles affect lysozyme amyloid fibrillization. - In: Biochimica et biophysica acta, ISSN 1872-8006, Bd. 1865 (2021), 9, 129941, insges. 9 S.
Background - The surface of nanoparticles (NPs) is an important factor affecting the process of poly/peptides' amyloid aggregation. We have investigated the in vitro effect of trisodium citrate (TC), gum arabic (GA) and citric acid (CA) surface-modified magnetite nanoparticles (COAT-MNPs) on hen egg-white lysozyme (HEWL) amyloid fibrillization and mature HEWL fibrils. - Methods - Dynamic light scattering (DLS) was used to characterize the physico-chemical properties of studied COAT-MNPs and determine the adsorption potential of their surface towards HEWL. The anti-amyloid properties were studied using thioflavin T (ThT) and tryptophan (Trp) intrinsic fluorescence assays, and atomic force microscopy (AFM). The morphology of amyloid aggregates was analyzed using Gwyddion software. The cytotoxicity of COAT-MNPs was determined utilizing Trypan blue (TB) assay. - Results - Agents used for surface modification affect the COAT-MNPs physico-chemical properties and modulate their anti-amyloid potential. The results from ThT and intrinsic fluorescence showed that the inhibitory activities result from the more favorable interactions of COAT-MNPs with early pre-amyloid species, presumably reducing nuclei and oligomers formation necessary for amyloid fibrillization. COAT-MNPs also possess destroying potential, which is presumably caused by the interaction with hydrophobic residues of the fibrils, resulting in the interruption of an interface between [beta]-sheets stabilizing the amyloid fibrils. - Conclusion - COAT-MNPs were able to inhibit HEWL fibrillization and destroy mature fibrils with different efficacy depending on their properties, TC-MNPs being the most potent nanoparticles. - General significance - The study reports findings regarding the general impact of nanoparticles' surface modifications on the amyloid aggregation of proteins.
https://doi.org/10.1016/j.bbagen.2021.129941
Sparse modeling and monitoring for industrial processes using sparse, distributed principal component analysis. - In: Journal of the Taiwan Institute of Chemical Engineers, ISSN 1876-1089, Bd. 122 (2021), S. 14-22
Driven by the strong demand for sparsity in dimensional reduction techniques, a sparse modeling and monitoring approach based on sparse, distributed principal component analysis (SDPCA) is proposed to achieve sparsity. To this end, the data set is first divided into highly correlated blocks (HCBs) and one remainder block (RB) on the basis of the mutual-information-based correlation matrix. From this, the sparse loading vectors for the HCBs are obtained using the PCA models, while for the RB, it is obtained using the sparse PCA model. It is worth noting that the sparsity in SDPCA enables the sparse loading vectors to produce interpretable principal components, which keeps the correlations between the highly correlated variables and achieves the sparsity for the weakly correlated ones. Moreover, to fully appreciate the interpretation of the sparse principal components, a fault diagnosis strategy named blockwise contribution plots is proposed by first determining the faulty block, and then, identifying the faulty variables. Compared with PCA and SPCA, the proposed SDPCA detects more faulty samples and gives more accurate diagnosis results.
https://doi.org/10.1016/j.jtice.2021.04.029