Refine
Departments, institutes and facilities
- Fachbereich Informatik (62)
- Fachbereich Angewandte Naturwissenschaften (53)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (47)
- Fachbereich Wirtschaftswissenschaften (43)
- Fachbereich Ingenieurwissenschaften und Kommunikation (33)
- Internationales Zentrum für Nachhaltige Entwicklung (IZNE) (21)
- Institut für funktionale Gen-Analytik (IFGA) (15)
- Institut für Verbraucherinformatik (IVI) (14)
- Institute of Visual Computing (IVC) (13)
- Institut für Cyber Security & Privacy (ICSP) (10)
Document Type
- Article (110)
- Conference Object (53)
- Part of a Book (16)
- Preprint (12)
- Research Data (6)
- Doctoral Thesis (5)
- Master's Thesis (5)
- Report (4)
- Book (monograph, edited volume) (2)
- Conference Proceedings (2)
Year of publication
- 2022 (219) (remove)
Language
- English (219) (remove)
Keywords
- Machine Learning (5)
- virtual reality (4)
- Cathepsin K (3)
- GDPR (3)
- Knowledge Graphs (3)
- Lignin (3)
- usable privacy (3)
- 3D user interface (2)
- Bioinformatics (2)
- Chemometrics (2)
Self-supervised learning has proved to be a powerful approach to learn image representations without the need of large labeled datasets. For underwater robotics, it is of great interest to design computer vision algorithms to improve perception capabilities such as sonar image classification. Due to the confidential nature of sonar imaging and the difficulty to interpret sonar images, it is challenging to create public large labeled sonar datasets to train supervised learning algorithms. In this work, we investigate the potential of three self-supervised learning methods (RotNet, Denoising Autoencoders, and Jigsaw) to learn high-quality sonar image representation without the need of human labels. We present pre-training and transfer learning results on real-life sonar image datasets. Our results indicate that self-supervised pre-training yields classification performance comparable to supervised pre-training in a few-shot transfer learning setup across all three methods. Code and self-supervised pre-trained models are be available at https://github.com/agrija9/ssl-sonar-images
We introduce canonical weight normalization for convolutional neural networks. Inspired by the canonical tensor decomposition, we express the weight tensors in so-called canonical networks as scaled sums of outer vector products. In particular, we train network weights in the decomposed form, where scale weights are optimized separately for each mode. Additionally, similarly to weight normalization, we include a global scaling parameter. We study the initialization of the canonical form by running the power method and by drawing randomly from Gaussian or uniform distributions. Our results indicate that we can replace the power method with cheaper initializations drawn from standard distributions. The canonical re-parametrization leads to competitive normalization performance on the MNIST, CIFAR10, and SVHN data sets. Moreover, the formulation simplifies network compression. Once training has converged, the canonical form allows convenient model-compression by truncating the parameter sums.
Comparative study of 3D object detection frameworks based on LiDAR data and sensor fusion techniques
(2022)
Estimating and understanding the surroundings of the vehicle precisely forms the basic and crucial step for the autonomous vehicle. The perception system plays a significant role in providing an accurate interpretation of a vehicle's environment in real-time. Generally, the perception system involves various subsystems such as localization, obstacle (static and dynamic) detection, and avoidance, mapping systems, and others. For perceiving the environment, these vehicles will be equipped with various exteroceptive (both passive and active) sensors in particular cameras, Radars, LiDARs, and others. These systems are equipped with deep learning techniques that transform the huge amount of data from the sensors into semantic information on which the object detection and localization tasks are performed. For numerous driving tasks, to provide accurate results, the location and depth information of a particular object is necessary. 3D object detection methods, by utilizing the additional pose data from the sensors such as LiDARs, stereo cameras, provides information on the size and location of the object. Based on recent research, 3D object detection frameworks performing object detection and localization on LiDAR data and sensor fusion techniques show significant improvement in their performance. In this work, a comparative study of the effect of using LiDAR data for object detection frameworks and the performance improvement seen by using sensor fusion techniques are performed. Along with discussing various state-of-the-art methods in both the cases, performing experimental analysis, and providing future research directions.
Vietnam requires a sustainable urbanization, for which city sensing is used in planning and de-cision-making. Large cities need portable, scalable, and inexpensive digital technology for this purpose. End-to-end air quality monitoring companies such as AirVisual and Plume Air have shown their reliability with portable devices outfitted with superior air sensors. They are pricey, yet homeowners use them to get local air data without evaluating the causal effect. Our air quality inspection system is scalable, reasonably priced, and flexible. Minicomputer of the sys-tem remotely monitors PMS7003 and BME280 sensor data through a microcontroller processor. The 5-megapixel camera module enables researchers to infer the causal relationship between traffic intensity and dust concentration. The design enables inexpensive, commercial-grade hardware, with Azure Blob storing air pollution data and surrounding-area imagery and pre-venting the system from physically expanding. In addition, by including an air channel that re-plenishes and distributes temperature, the design improves ventilation and safeguards electrical components. The gadget allows for the analysis of the correlation between traffic and air quali-ty data, which might aid in the establishment of sustainable urban development plans and poli-cies.
Comparative study of 3D object detection frameworks based on LiDAR data and sensor fusion techniques
(2022)
Estimating and understanding the surroundings of the vehicle precisely forms the basic and crucial step for the autonomous vehicle. The perception system plays a significant role in providing an accurate interpretation of a vehicle's environment in real-time. Generally, the perception system involves various subsystems such as localization, obstacle (static and dynamic) detection, and avoidance, mapping systems, and others. For perceiving the environment, these vehicles will be equipped with various exteroceptive (both passive and active) sensors in particular cameras, Radars, LiDARs, and others. These systems are equipped with deep learning techniques that transform the huge amount of data from the sensors into semantic information on which the object detection and localization tasks are performed. For numerous driving tasks, to provide accurate results, the location and depth information of a particular object is necessary. 3D object detection methods, by utilizing the additional pose data from the sensors such as LiDARs, stereo cameras, provides information on the size and location of the object. Based on recent research, 3D object detection frameworks performing object detection and localization on LiDAR data and sensor fusion techniques show significant improvement in their performance. In this work, a comparative study of the effect of using LiDAR data for object detection frameworks and the performance improvement seen by using sensor fusion techniques are performed. Along with discussing various state-of-the-art methods in both the cases, performing experimental analysis, and providing future research directions.
Recent advances in Natural Language Processing have substantially improved contextualized representations of language. However, the inclusion of factual knowledge, particularly in the biomedical domain, remains challenging. Hence, many Language Models (LMs) are extended by Knowledge Graphs (KGs), but most approaches require entity linking (i.e., explicit alignment between text and KG entities). Inspired by single-stream multimodal Transformers operating on text, image and video data, this thesis proposes the Sophisticated Transformer trained on biomedical text and Knowledge Graphs (STonKGs). STonKGs incorporates a novel multimodal architecture based on a cross encoder that uses the attention mechanism on a concatenation of input sequences derived from text and KG triples, respectively. Over 13 million so-called text-triple pairs, coming from PubMed and assembled using the Integrated Network and Dynamical Reasoning Assembler (INDRA), were used in an unsupervised pre-training procedure to learn representations of biomedical knowledge in STonKGs. By comparing STonKGs to an NLP- and a KG-baseline (operating on either text or KG data) on a benchmark consisting of eight fine-tuning tasks, the proposed knowledge integration method applied in STonKGs was empirically validated. Specifically, on tasks with a comparatively small dataset size and a larger number of classes, STonKGs resulted in considerable performance gains, beating the F1-score of the best baseline by up to 0.083. Both the source code as well as the code used to implement STonKGs are made publicly available so that the proposed method of this thesis can be extended to many other biomedical applications.
Contextual information is widely considered for NLP and knowledge discovery in life sciences since it highly influences the exact meaning of natural language. The scientific challenge is not only to extract such context data, but also to store this data for further query and discovery approaches. Classical approaches use RDF triple stores, which have serious limitations. Here, we propose a multiple step knowledge graph approach using labeled property graphs based on polyglot persistence systems to utilize context data for context mining, graph queries, knowledge discovery and extraction. We introduce the graph-theoretic foundation for a general context concept within semantic networks and show a proof of concept based on biomedical literature and text mining. Our test system contains a knowledge graph derived from the entirety of PubMed and SCAIView data and is enriched with text mining data and domain-specific language data using Biological Expression Language. Here, context is a more general concept than annotations. This dense graph has more than 71M nodes and 850M relationships. We discuss the impact of this novel approach with 27 real-world use cases represented by graph queries. Storing and querying a giant knowledge graph as a labeled property graph is still a technological challenge. Here, we demonstrate how our data model is able to support the understanding and interpretation of biomedical data. We present several real-world use cases that utilize our massive, generated knowledge graph derived from PubMed data and enriched with additional contextual data. Finally, we show a working example in context of biologically relevant information using SCAIView.
For research in audiovisual interview archives often it is not only of interest what is said but also how. Sentiment analysis and emotion recognition can help capture, categorize and make these different facets searchable. In particular, for oral history archives, such indexing technologies can be of great interest. These technologies can help understand the role of emotions in historical remembering. However, humans often perceive sentiments and emotions ambiguously and subjectively. Moreover, oral history interviews have multi-layered levels of complex, sometimes contradictory, sometimes very subtle facets of emotions. Therefore, the question arises of the chance machines and humans have capturing and assigning these into predefined categories. This paper investigates the ambiguity in human perception of emotions and sentiment in German oral history interviews and the impact on machine learning systems. Our experiments reveal substantial differences in human perception for different emotions. Furthermore, we report from ongoing machine learning experiments with different modalities. We show that the human perceptual ambiguity and other challenges, such as class imbalance and lack of training data, currently limit the opportunities of these technologies for oral history archives. Nonetheless, our work uncovers promising observations and possibilities for further research.
State-of-the-art object detectors are treated as black boxes due to their highly non-linear internal computations. Even with unprecedented advancements in detector performance, the inability to explain how their outputs are generated limits their use in safety-critical applications. Previous work fails to produce explanations for both bounding box and classification decisions, and generally make individual explanations for various detectors. In this paper, we propose an open-source Detector Explanation Toolkit (DExT) which implements the proposed approach to generate a holistic explanation for all detector decisions using certain gradient-based explanation methods. We suggests various multi-object visualization methods to merge the explanations of multiple objects detected in an image as well as the corresponding detections in a single image. The quantitative evaluation show that the Single Shot MultiBox Detector (SSD) is more faithfully explained compared to other detectors regardless of the explanation methods. Both quantitative and human-centric evaluations identify that SmoothGrad with Guided Backpropagation (GBP) provides more trustworthy explanations among selected methods across all detectors. We expect that DExT will motivate practitioners to evaluate object detectors from the interpretability perspective by explaining both bounding box and classification decisions.
21 pages, with supplementary
ProtSTonKGs: A Sophisticated Transformer Trained on Protein Sequences, Text, and Knowledge Graphs
(2022)
While most approaches individually exploit unstructured data from the biomedical literature or structured data from biomedical knowledge graphs, their union can better exploit the advantages of such approaches, ultimately improving representations of biology. Using multimodal transformers for such purposes can improve performance on context dependent classication tasks, as demonstrated by our previous model, the Sophisticated Transformer Trained on Biomedical Text and Knowledge Graphs (STonKGs). In this work, we introduce ProtSTonKGs, a transformer aimed at learning all-encompassing representations of protein-protein interactions. ProtSTonKGs presents an extension to our previous work by adding textual protein descriptions and amino acid sequences (i.e., structural information) to the text- and knowledge graph-based input sequence used in STonKGs. We benchmark ProtSTonKGs against STonKGs, resulting in improved F1 scores by up to 0.066 (i.e., from 0.204 to 0.270) in several tasks such as predicting protein interactions in several contexts. Our work demonstrates how multimodal transformers can be used to integrate heterogeneous sources of information, paving the foundation for future approaches that use multiple modalities for biomedical applications.
Differential-Algebraic Equations and Beyond: From Smooth to Nonsmooth Constrained Dynamical Systems
(2022)
Effective Neighborhood Feature Exploitation in Graph CNNs for Point Cloud Object-Part Segmentation
(2022)
Part segmentation is the task of semantic segmentation applied on objects and carries a wide range of applications from robotic manipulation to medical imaging. This work deals with the problem of part segmentation on raw, unordered point clouds of 3D objects. While pioneering works on deep learning for point clouds typically ignore taking advantage of local geometric structure around individual points, the subsequent methods proposed to extract features by exploiting local geometry have not yielded significant improvements either. In order to investigate further, a graph convolutional network (GCN) is used in this work in an attempt to increase the effectiveness of such neighborhood feature exploitation approaches. Most of the previous works also focus only on segmenting complete point cloud data. Considering the impracticality of such approaches, taking into consideration the real world scenarios where complete point clouds are scarcely available, this work proposes approaches to deal with partial point cloud segmentation.
In the attempt to better capture neighborhood features, this work proposes a novel method to learn regional part descriptors which guide and refine the segmentation predictions. The proposed approach helps the network achieve state-of-the-art performance of 86.4% mIoU on the ShapeNetPart dataset for methods which do not use any preprocessing techniques or voting strategies. In order to better deal with partial point clouds, this work also proposes new strategies to train and test on partial data. While achieving significant improvements compared to the baseline performance, the problem of partial point cloud segmentation is also viewed through an alternate lens of semantic shape completion.
Semantic shape completion networks not only help deal with partial point cloud segmentation but also enrich the information captured by the system by predicting complete point clouds with corresponding semantic labels for each point. To this end, a new network architecture for semantic shape completion is also proposed based on point completion network (PCN) which takes advantage of a graph convolution based hierarchical decoder for completion as well as segmentation. In addition to predicting complete point clouds, results indicate that the network is capable of reaching within a margin of 5% to the mIoU performance of dedicated segmentation networks for partial point cloud segmentation.
As cameras are ubiquitous in autonomous systems, object detection is a crucial task. Object detectors are widely used in applications such as autonomous driving, healthcare, and robotics. Given an image, an object detector outputs both the bounding box coordinates as well as classification probabilities for each object detected. The state-of-the-art detectors are treated as black boxes due to their highly non-linear internal computations. Even with unprecedented advancements in detector performance, the inability to explain how their outputs are generated limits their use in safety-critical applications in particular. It is therefore crucial to explain the reason behind each detector decision in order to gain user trust, enhance detector performance, and analyze their failure.
Previous work fails to explain as well as evaluate both bounding box and classification decisions individually for various detectors. Moreover, no tools explain each detector decision, evaluate the explanations, and also identify the reasons for detector failures. This restricts the flexibility to analyze detectors. The main contribution presented here is an open-source Detector Explanation Toolkit (DExT). It is used to explain the detector decisions, evaluate the explanations, and analyze detector errors. The detector decisions are explained visually by highlighting the image pixels that most influence a particular decision. The toolkit implements the proposed approach to generate a holistic explanation for all detector decisions using certain gradient-based explanation methods. To the author’s knowledge, this is the first work to conduct extensive qualitative and novel quantitative evaluations of different explanation methods across various detectors. The qualitative evaluation incorporates a visual analysis of the explanations carried out by the author as well as a human-centric evaluation. The human-centric evaluation includes a user study to understand user trust in the explanations generated across various explanation methods for different detectors. Four multi-object visualization methods are provided to merge the explanations of multiple objects detected in an image as well as the corresponding detector outputs in a single image. Finally, DExT implements the procedure to analyze detector failures using the formulated approach.
The visual analysis illustrates that the ability to explain a model is more dependent on the model itself than the actual ability of the explanation method. In addition, the explanations are affected by the object explained, the decision explained, detector architecture, training data labels, and model parameters. The results of the quantitative evaluation show that the Single Shot MultiBox Detector (SSD) is more faithfully explained compared to other detectors regardless of the explanation methods. In addition, a single explanation method cannot generate more faithful explanations than other methods for both the bounding box and the classification decision across different detectors. Both the quantitative and human-centric evaluations identify that SmoothGrad with Guided Backpropagation (GBP) provides more trustworthy explanations among selected methods across all detectors. Finally, a convex polygon-based multi-object visualization method provides more human-understandable visualization than other methods.
The author expects that DExT will motivate practitioners to evaluate object detectors from the interpretability perspective by explaining both bounding box and classification decisions.
We describe a systematic approach for rendering time-varying simulation data produced by exa-scale simulations, using GPU workstations. The data sets we focus on use adaptive mesh refinement (AMR) to overcome memory bandwidth limitations by representing interesting regions in space with high detail. Particularly, our focus is on data sets where the AMR hierarchy is fixed and does not change over time. Our study is motivated by the NASA Exajet, a large computational fluid dynamics simulation of a civilian cargo aircraft that consists of 423 simulation time steps, each storing 2.5 GB of data per scalar field, amounting to a total of 4 TB. We present strategies for rendering this time series data set with smooth animation and at interactive rates using current generation GPUs. We start with an unoptimized baseline and step by step extend that to support fast streaming updates. Our approach demonstrates how to push current visualization workstations and modern visualization APIs to their limits to achieve interactive visualization of exa-scale time series data sets.
Trojanized software packages used in software supply chain attacks constitute an emerging threat. Unfortunately, there is still a lack of scalable approaches that allow automated and timely detection of malicious software packages and thus most detections are based on manual labor and expertise. However, it has been observed that most attack campaigns comprise multiple packages that share the same or similar malicious code. We leverage that fact to automatically reproduce manually identified clusters of known malicious packages that have been used in real world attacks, thus, reducing the need for expert knowledge and manual inspection. Our approach, AST Clustering using MCL to mimic Expertise (ACME), yields promising results with a 𝐹1 score of 0.99. Signatures are automatically generated based on characteristic code fragments from clusters and are subsequently used to scan the whole npm registry for unreported malicious packages. We are able to identify and report six malicious packages that have been removed from npm consequentially. Therefore, our approach can support the detection by reducing manual labor and hence may be employed by maintainers of package repositories to detect possible software supply chain attacks through trojanized software packages.
Hydrogen is a versatile energy carrier. When produced with renewable energy by water splitting, it is a carbon neutral alternative to fossil fuels. The industrialization process of this technology is currently dominated by electrolyzers powered by solar or wind energy. For small scale applications, however, more integrated device designs for water splitting using solar energy might optimize hydrogen production due to lower balance of system costs and a smarter thermal management. Such devices offer the opportunity to thermally couple the solar cell and the electrochemical compartment. In this way, heat losses in the absorber can be turned into an efficiency boost for the device via simultaneously enhancing the catalytic performance of the water splitting reactions, cooling the absorber, and decreasing the ohmic losses.[1,2] However,integrated devices (sometimes also referred to as “artificial leaves”), currently suffer from a lower technology readiness level (TRL) than the completely decoupled approach.
Integrated solar water splitting devices that produce hydrogen without the use of power inverters operate outdoors and are hence exposed to varying weather conditions. As a result, they might sometimes work at non-optimal operation points below or above the maximum power point of the photovoltaic component, which would directly translate into efficiency losses. Up until now, however, no common parameter describing and quantifying this and other real-life operating related losses (e.g. spectral mismatch) exists in the community. Therefore, the annual-hydrogen-yield-climatic-response (AHYCR) ratio is introduced as a figure of merit to evaluate the outdoor performance of integrated solar water splitting devices. This value is defined as the ratio between the real annual hydrogen yield and the theoretical yield assuming the solar-to-hydrogen device efficiency at standard conditions. This parameter is derived for an exemplary system based on state-of-the-art AlGaAs//Si dual-junction solar cells and an anion exchange membrane electrolyzer using hourly resolved climate data from a location in southern California and from reanalysis data of Antarctica. This work will help to evaluate, compare and optimize the climatic response of solar water splitting devices in different climate zones.
Research-Practice-Collaborations Addressing One Health and Urban Transformation. A Case Study
(2022)
One Health is an integrative approach at the interface of humans, animals and the environment, which can be implemented as Research-Practice-Collaboration (RPC) for its interdisciplinarity and intersectoral focus on the co-production of knowledge. To exemplify this, the present commentary shows the example of the Forschungskolleg “One Health and Urban Transformation” funded by the Ministry of Culture and Science of the State Government of Nord Rhine Westphalia in Germany. After analysis, the factors identified for a better implementation of RPC for One Health were the ones that allowed for constant communication and the reduction of power asymmetries between practitioners and academics in the co-production of knowledge. In this light, the training of a new generation of scientists at the boundaries of different disciplines that have mediation skills between academia and practice is an important contribution with great implications for societal change that can aid the further development of RPC.
Silicon carbide and graphene possess extraordinary chemical and physical properties. Here, these different systems are linked and the changes in structural and dynamic properties are investigated. For the simulations performed a classical molecular dynamic (MD) approach was used. In this approach, a graphene layer (N = 240 atoms) was grafted at different distances on top of a 6H-SiC structure (N = 2400 atoms) and onto a 3C-SiC structure (N = 1728 atoms). The distances between the graphene and the 6H are 1.0, 1.3 and 1.5 Å and the distances between the graphene layer and the 3C-SiC are 2.0, 2.3, and 2.5 Å. Each system has been equilibrated at room temperature until no further relaxation was observed. The 6H-SiC structure in combination with graphene proves to be more stable compared to the combination with 3C-SiC. This can be seen well in the determined energies. Pair distribution functions were influenced slightly by the graphene layer due to steric and energetic changes. This becomes clear from the small shifts of the C-C distances. Interactions as well as bonds between graphene and SiC lead to the fact that small shoulders of the high-frequency SiC-peaks are visible in the spectra and at the same time the high-frequency peaks of graphene are completely absent.
Graph databases employ graph structures such as nodes, attributes and edges to model and store relationships among data. To access this data, graph query languages (GQL) such as Cypher are typically used, which might be difficult to master for end-users. In the context of relational databases, sequence to SQL models, which translate natural language questions to SQL queries, have been proposed. While these Neural Machine Translation (NMT) models increase the accessibility of relational databases, NMT models for graph databases are not yet available mainly due to the lack of suitable parallel training data. In this short paper we sketch an architecture which enables the generation of synthetic training data for the graph query language Cypher.
MOTIVATION
The majority of biomedical knowledge is stored in structured databases or as unstructured text in scientific publications. This vast amount of information has led to numerous machine learning-based biological applications using either text through natural language processing (NLP) or structured data through knowledge graph embedding models (KGEMs). However, representations based on a single modality are inherently limited.
RESULTS
To generate better representations of biological knowledge, we propose STonKGs, a Sophisticated Transformer trained on biomedical text and Knowledge Graphs (KGs). This multimodal Transformer uses combined input sequences of structured information from KGs and unstructured text data from biomedical literature to learn joint representations in a shared embedding space. First, we pre-trained STonKGs on a knowledge base assembled by the Integrated Network and Dynamical Reasoning Assembler (INDRA) consisting of millions of text-triple pairs extracted from biomedical literature by multiple NLP systems. Then, we benchmarked STonKGs against three baseline models trained on either one of the modalities (i.e., text or KG) across eight different classification tasks, each corresponding to a different biological application. Our results demonstrate that STonKGs outperforms both baselines, especially on the more challenging tasks with respect to the number of classes, improving upon the F1-score of the best baseline by up to 0.084 (i.e., from 0.881 to 0.965). Finally, our pre-trained model as well as the model architecture can be adapted to various other transfer learning applications.
AVAILABILITY
We make the source code and the Python package of STonKGs available at GitHub (https://github.com/stonkgs/stonkgs) and PyPI (https://pypi.org/project/stonkgs/). The pre-trained STonKGs models and the task-specific classification models are respectively available at https://huggingface.co/stonkgs/stonkgs-150k and https://zenodo.org/communities/stonkgs.
SUPPLEMENTARY INFORMATION
Supplementary data are available at Bioinformatics online.
In recent years, the ability of intelligent systems to be understood by developers and users has received growing attention. This holds in particular for social robots, which are supposed to act autonomously in the vicinity of human users and are known to raise peculiar, often unrealistic attributions and expectations. However, explainable models that, on the one hand, allow a robot to generate lively and autonomous behavior and, on the other, enable it to provide human-compatible explanations for this behavior are missing. In order to develop such a self-explaining autonomous social robot, we have equipped a robot with own needs that autonomously trigger intentions and proactive behavior, and form the basis for understandable self-explanations. Previous research has shown that undesirable robot behavior is rated more positively after receiving an explanation. We thus aim to equip a social robot with the capability to automatically generate verbal explanations of its own behavior, by tracing its internal decision-making routes. The goal is to generate social robot behavior in a way that is generally interpretable, and therefore explainable on a socio-behavioral level increasing users' understanding of the robot's behavior. In this article, we present a social robot interaction architecture, designed to autonomously generate social behavior and self-explanations. We set out requirements for explainable behavior generation architectures and propose a socio-interactive framework for behavior explanations in social human-robot interactions that enables explaining and elaborating according to users' needs for explanation that emerge within an interaction. Consequently, we introduce an interactive explanation dialog flow concept that incorporates empirically validated explanation types. These concepts are realized within the interaction architecture of a social robot, and integrated with its dialog processing modules. We present the components of this interaction architecture and explain their integration to autonomously generate social behaviors as well as verbal self-explanations. Lastly, we report results from a qualitative evaluation of a working prototype in a laboratory setting, showing that (1) the robot is able to autonomously generate naturalistic social behavior, and (2) the robot is able to verbally self-explain its behavior to the user in line with users' requests.
Introduction. The experience of pain is regularly accompanied by facial expressions. The gold standard for analyzing these facial expressions is the Facial Action Coding System (FACS), which provides so-called action units (AUs) as parametrical indicators of facial muscular activity. Particular combinations of AUs have appeared to be pain-indicative. The manual coding of AUs is, however, too time- and labor-intensive in clinical practice. New developments in automatic facial expression analysis have promised to enable automatic detection of AUs, which might be used for pain detection. Objective. Our aim is to compare manual with automatic AU coding of facial expressions of pain. Methods. FaceReader7 was used for automatic AU detection. We compared the performance of FaceReader7 using videos of 40 participants (20 younger with a mean age of 25.7 years and 20 older with a mean age of 52.1 years) undergoing experimentally induced heat pain to manually coded AUs as gold standard labeling. Percentages of correctly and falsely classified AUs were calculated, and we computed as indicators of congruency, "sensitivity/recall," "precision," and "overall agreement (F1)." Results. The automatic coding of AUs only showed poor to moderate outcomes regarding sensitivity/recall, precision, and F1. The congruency was better for younger compared to older faces and was better for pain-indicative AUs compared to other AUs. Conclusion. At the moment, automatic analyses of genuine facial expressions of pain may qualify at best as semiautomatic systems, which require further validation by human observers before they can be used to validly assess facial expressions of pain.
Current research in augmented, virtual, and mixed reality (XR) reveals a lack of tool support for designing and, in particular, prototyping XR applications. While recent tools research is often motivated by studying the requirements of non-technical designers and end-user developers, the perspective of industry practitioners is less well understood. In an interview study with 17 practitioners from different industry sectors working on professional XR projects, we establish the design practices in industry, from early project stages to the final product. To better understand XR design challenges, we characterize the different methods and tools used for prototyping and describe the role and use of key prototypes in the different projects. We extract common elements of XR prototyping, elaborating on the tools and materials used for prototyping and establishing different views on the notion of fidelity. Finally, we highlight key issues for future XR tools research.
Modern GPUs come with dedicated hardware to perform ray/triangle intersections and bounding volume hierarchy (BVH) traversal. While the primary use case for this hardware is photorealistic 3D computer graphics, with careful algorithm design scientists can also use this special-purpose hardware to accelerate general-purpose computations such as point containment queries. This article explains the principles behind these techniques and their application to vector field visualization of large simulation data using particle tracing.
BACKGROUND: Humans demonstrate many physiological changes in microgravity for which long-duration head down bed rest (HDBR) is a reliable analog. However, information on how HDBR affects sensory processing is lacking.
OBJECTIVE: We previously showed [25] that microgravity alters the weighting applied to visual cues in determining the perceptual upright (PU), an effect that lasts long after return. Does long-duration HDBR have comparable effects?
METHODS: We assessed static spatial orientation using the luminous line test (subjective visual vertical, SVV) and the oriented character recognition test (PU) before, during and after 21 days of 6° HDBR in 10 participants. Methods were essentially identical as previously used in orbit [25].
RESULTS: Overall, HDBR had no effect on the reliance on visual relative to body cues in determining the PU. However, when considering the three critical time points (pre-bed rest, end of bed rest, and 14 days post-bed rest) there was a significant decrease in reliance on visual relative to body cues, as found in microgravity. The ratio had an average time constant of 7.28 days and returned to pre-bed-rest levels within 14 days. The SVV was unaffected.
CONCLUSIONS: We conclude that bed rest can be a useful analog for the study of the perception of static self-orientation during long-term exposure to microgravity. More detailed work on the precise time course of our effects is needed in both bed rest and microgravity conditions.
The latest trends in inverse rendering techniques for reconstruction use neural networks to learn 3D representations as neural fields. NeRF-based techniques fit multi-layer perceptrons (MLPs) to a set of training images to estimate a radiance field which can then be rendered from any virtual camera by means of volume rendering algorithms. Major drawbacks of these representations are the lack of well-defined surfaces and non-interactive rendering times, as wide and deep MLPs must be queried millions of times per single frame. These limitations have recently been singularly overcome, but managing to accomplish this simultaneously opens up new use cases. We present KiloNeuS, a new neural object representation that can be rendered in path-traced scenes at interactive frame rates. KiloNeuS enables the simulation of realistic light interactions between neural and classic primitives in shared scenes, and it demonstrably performs in real-time with plenty of room for future optimizations and extensions.
This project focuses on object detection in dense volume data. There are several types of dense volume data, namely Computed Tomography (CT) scan, Positron Emission Tomography (PET), Magnetic Resonance Imaging (MRI). This work focuses on CT scans. CT scans are not limited to the medical domain; they are also used in industries. CT scans are used in airport baggage screening, assembly lines, and the object detection systems in these places should be able to detect objects fast. One of the ways to address the issue of computational complexity and make the object detection systems fast is to use low-resolution images. Low-resolution CT scanning is fast. The entire process of scanning and detection can be made faster by using low-resolution images. Even in the medical domain, to reduce the rad iation dose, the exposure time of the patient should be reduced. The exposure time of patients could be reduced by allowing low-resolution CT scans. Hence it is essential to find out which object detection model has better accuracy as well as speed at low-resolution CT scans. However, the existing approaches did not provide details about how the model would perform when the resolution of CT scans is varied. Hence in this project, the goal is to analyze the impact of varying resolution of CT scans on both the speed and accuracy of the model. Three object detection models, namely RetinaNet, YOLOv3, and YOLOv5, were trained at various resolutions. Among the three models, it was found that YOLOv5 has the best mAP and f1 score at multiple resolutions on the DeepLesion dataset. RetinaNet model h as the least inference time on the DeepLesion dataset. From the experiments, it could be asserted that sacrificing mean average precision (mAP) to improve inference time by reducing resolution is feasible.
In (dynamic) adaptive mesh refinement (AMR) an input mesh is refined or coarsened to the need of the numerical application. This refinement happens with no respect to the originally meshed domain and is therefore limited to the geometrical accuracy of the original input mesh. We presented a novel approach to equip this input mesh with additional geometry information, to allow refinement and high-order cells based on the geometry of the original domain. We already showed a limited implementation of this algorithm. Now we evaluate this prototype with a numerical application and we prove its influence on the accuracy of certain numerical results. To be as practical as possible, we implement the ability to import meshes generated by Gmsh and equip them with the needed geometry information. Furthermore, we improve the mapping algorithm, which maps the geometry information of the boundary of a cell into the cell's volume. With these preliminary steps done, we use out new approach in a simulation of the advection of a concentration along the boundary of a sphere shell and past the boundary of a rotating cylinder. We evaluate the accuracy of our approach in comparison to the conventional refinement of cells to answer our research question: How does the performance and accuracy of the hexahedral curved domain AMR algorithm compare to linear AMR when solving the advection equation with the linear finite volume method? To answer this question, we show the influence of curved AMR on our simulation results and see, that it is even able to outperform far finer linear meshes in terms of accuracy. We also see that the current implementation of this approach is too slow for practical usage. We can therefore prove the benefits of curved AMR in certain, geometry-related application scenarios and show possible improvements to make it more feasible and practical in the future.
In the field of autonomous robotics, sensors have played a major role in defining the scope of technology and to a great extent, limitations of it as well. This cycle of constant updates and hence technological advancement has made given birth to some serious industries which were once inconceivable. Industries like autonomous driving which has a serious impact on safety and security of people, also has an equally harsh implication on the dynamics and economics of the market. With sensors like LiDAR and RADAR delivering 3D measurements as point clouds, there is a necessity to process the raw measurements directly and many research groups are working on the same. A sizable research has gone in solving the task of object detection on 2D images. In this thesis we aim to develop a LiDAR based 3D object detection scheme. We combine the ideas of PointPillars and feature pyramid networks from 2D vision to propose Pillar-FPN. The proposed method directly takes 3D point clouds as input and outputs a 3D bounding box. Our pipeline consists of multiple variations of proposed Pillar-FPN at the feature fusion level that are described in the results section. We have trained our model on the KITTI train dataset and evaluated it on KITTI validation dataset.
Modeling of Creep Behavior of Particulate Composites with Focus on Interfacial Adhesion Effect
(2022)
Evaluation of creep compliance of particulate composites using empirical models always provides parameters depending on initial stress and material composition. The effort spent to connect model parameters with physical properties has not resulted in success yet. Further, during the creep, delamination between matrix and filler may occur depending on time and initial stress, reducing an interface adhesion and load transfer to filler particles. In this paper, the creep compliance curves of glass beads reinforced poly(butylene terephthalate) composites were fitted with Burgers and Findley models providing different sets of time-dependent model parameters for each initial stress. Despite the finding that the Findley model performs well in a primary creep, the Burgers model is more suitable if secondary creep comes into play; they allow only for a qualitative prediction of creep behavior because the interface adhesion and its time dependency is an implicit, hidden parameter. As Young’s modulus is a parameter of these models (and the majority of other creep models), it was selected to be introduced as a filler content-dependent parameter with the help of the cube in cube elementary volume approach of Paul. The analysis led to the time-dependent creep compliance that depends only on the time-dependent creep of the matrix and the normalized particle distance (or the filler volume content), and it allowed accounting for the adhesion effect. Comparison with the experimental data confirmed that the elementary volume-based creep compliance function can be used to predict the realistic creep behavior of particulate composites.
Technological objects present themselves as necessary, only to become obsolete faster than ever before. This phenomenon has led to a population that experiences a plethora of technological objects and interfaces as they age, which become associated with certain stages of life and disappear thereafter. Noting the expanding body of literature within HCI about appropriation, our work pinpoints an area that needs more attention, “outdated technologies.” In other words, we assert that design practices can profit as much from imaginaries of the future as they can from reassessing artefacts from the past in a critical way. In a two-week fieldwork with 37 HCI students, we gathered an international collection of nostalgic devices from 14 different countries to investigate what memories people still have of older technologies and the ways in which these memories reveal normative and accidental use of technological objects. We found that participants primarily remembered older technologies with positive connotations and shared memories of how they had adapted and appropriated these technologies, rather than normative uses. We refer to this phenomenon as nostalgic reminiscence. In the future, we would like to develop this concept further by discussing how nostalgic reminiscence can be operationalized to stimulate speculative design in the present.
This edited volume on “Recent Advances in Renewable Energy” presents a selection of refereed papers presented at the 1st International Conference on Electrical Systems and Automation. The book provides rigorous discussions, the state of the art, and recent developments in the field of renewable energy sources supported by examples and case studies, making it an educational tool for relevant undergraduate and graduate courses. The book will be a valuable reference for beginners, researchers, and professionals interested in renewable energy.