Institut für Informatik und Computational Science
Refine
Year of publication
Document Type
- Article (682) (remove)
Keywords
- Didaktik (13)
- Ausbildung (12)
- Hochschuldidaktik (12)
- Informatik (12)
- Answer set programming (10)
- answer set programming (8)
- Answer Set Programming (6)
- Computer Science Education (4)
- E-Learning (4)
- Competence Measurement (3)
Institute
- Institut für Informatik und Computational Science (682)
- Institut für Physik und Astronomie (2)
- eLiS - E-Learning in Studienbereichen (2)
- Department Erziehungswissenschaft (1)
- Department Linguistik (1)
- Extern (1)
- Fachgruppe Betriebswirtschaftslehre (1)
- Historisches Institut (1)
- Universitätsbibliothek (1)
- Zentrum für Qualitätsentwicklung in Lehre und Studium (ZfQ) (1)
Deep metric learning employs deep neural networks to embed instances into a metric space such that distances between instances of the same class are small and distances between instances from different classes are large. In most existing deep metric learning techniques, the embedding of an instance is given by a feature vector produced by a deep neural network and Euclidean distance or cosine similarity defines distances between these vectors. This paper studies deep distributional embeddings of sequences, where the embedding of a sequence is given by the distribution of learned deep features across the sequence. The motivation for this is to better capture statistical information about the distribution of patterns within the sequence in the embedding. When embeddings are distributions rather than vectors, measuring distances between embeddings involves comparing their respective distributions. The paper therefore proposes a distance metric based on Wasserstein distances between the distributions and a corresponding loss function for metric learning, which leads to a novel end-to-end trainable embedding model. We empirically observe that distributional embeddings outperform standard vector embeddings and that training with the proposed Wasserstein metric outperforms training with other distance functions.
Objectives To compare image quality of deep learning reconstruction (AiCE) for radiomics feature extraction with filtered back projection (FBP), hybrid iterative reconstruction (AIDR 3D), and model-based iterative reconstruction (FIRST). Methods Effects of image reconstruction on radiomics features were investigated using a phantom that realistically mimicked a 65-year-old patient's abdomen with hepatic metastases. The phantom was scanned at 18 doses from 0.2 to 4 mGy, with 20 repeated scans per dose. Images were reconstructed with FBP, AIDR 3D, FIRST, and AiCE. Ninety-three radiomics features were extracted from 24 regions of interest, which were evenly distributed across three tissue classes: normal liver, metastatic core, and metastatic rim. Features were analyzed in terms of their consistent characterization of tissues within the same image (intraclass correlation coefficient >= 0.75), discriminative power (Kruskal-Wallis test p value < 0.05), and repeatability (overall concordance correlation coefficient >= 0.75). Results The median fraction of consistent features across all doses was 6%, 8%, 6%, and 22% with FBP, AIDR 3D, FIRST, and AiCE, respectively. Adequate discriminative power was achieved by 48%, 82%, 84%, and 92% of features, and 52%, 20%, 17%, and 39% of features were repeatable, respectively. Only 5% of features combined consistency, discriminative power, and repeatability with FBP, AIDR 3D, and FIRST versus 13% with AiCE at doses above 1 mGy and 17% at doses >= 3 mGy. AiCE was the only reconstruction technique that enabled extraction of higher-order features. Conclusions AiCE more than doubled the yield of radiomics features at doses typically used clinically. Inconsistent tissue characterization within CT images contributes significantly to the poor stability of radiomics features.
Programs are often subjected to significant optimizing and parallelizing transformations based on extensive dependence analysis. Formal validation of such transformations needs modelling paradigms which can capture both control and data dependences in the program vividly. Being value-based with an inherent scope of capturing parallelism, the untimed coloured Petri net (CPN) models, reported in the literature, fit the bill well; accordingly, they are likely to be more convenient as the intermediate representations (IRs) of both the source and the transformed codes for translation validation than strictly sequential variable-based IRs like sequential control flow graphs (CFGs). In this work, an efficient path-based equivalence checking method for CPN models of programs on integers is presented. Extensive experimentation has been carried out on several sequential and parallel examples. Complexity and correctness issues have been treated rigorously for the method.
The intensity of cosmic radiation may differ over five orders of magnitude within a few hours or days during the Solar Particle Events (SPEs), thus increasing for several orders of magnitude the probability of Single Event Upsets (SEUs) in space-borne electronic systems. Therefore, it is vital to enable the early detection of the SEU rate changes in order to ensure timely activation of dynamic radiation hardening measures. In this paper, an embedded approach for the prediction of SPEs and SRAM SEU rate is presented. The proposed solution combines the real-time SRAM-based SEU monitor, the offline-trained machine learning model and online learning algorithm for the prediction. With respect to the state-of-the-art, our solution brings the following benefits: (1) Use of existing on-chip data storage SRAM as a particle detector, thus minimizing the hardware and power overhead, (2) Prediction of SRAM SEU rate one hour in advance, with the fine-grained hourly tracking of SEU variations during SPEs as well as under normal conditions, (3) Online optimization of the prediction model for enhancing the prediction accuracy during run-time, (4) Negligible cost of hardware accelerator design for the implementation of selected machine learning model and online learning algorithm. The proposed design is intended for a highly dependable and self-adaptive multiprocessing system employed in space applications, allowing to trigger the radiation mitigation mechanisms before the onset of high radiation levels.
We present a method employing Answer Set Programming in combination with Approximate Model Counting for fast and accurate calculation of error propagation probabilities in digital circuits. By an efficient problem encoding, we achieve an input data format similar to a Verilog netlist so that extensive preprocessing is avoided. By a tight interconnection of our application with the underlying solver, we avoid iterating over fault sites and reduce calls to the solver. Several circuits were analyzed with varying numbers of considered cycles and different degrees of approximation. Our experiments show, that the runtime can be reduced by approximation by a factor of 91, whereas the error compared to the exact result is below 1%.
Instruments for measuring the absorbed dose and dose rate under radiation exposure, known as radiation dosimeters, are indispensable in space missions. They are composed of radiation sensors that generate current or voltage response when exposed to ionizing radiation, and processing electronics for computing the absorbed dose and dose rate. Among a wide range of existing radiation sensors, the Radiation Sensitive Field Effect Transistors (RADFETs) have unique advantages for absorbed dose measurement, and a proven record of successful exploitation in space missions. It has been shown that the RADFETs may be also used for the dose rate monitoring. In that regard, we propose a unique design concept that supports the simultaneous operation of a single RADFET as absorbed dose and dose rate monitor. This enables to reduce the cost of implementation, since the need for other types of radiation sensors can be minimized or eliminated. For processing the RADFET's response we propose a readout system composed of analog signal conditioner (ASC) and a self-adaptive multiprocessing system-on-chip (MPSoC). The soft error rate of MPSoC is monitored in real time with embedded sensors, allowing the autonomous switching between three operating modes (high-performance, de-stress and fault-tolerant), according to the application requirements and radiation conditions.
The radiation-sensitive field-effect transistors (RADFETs) with an oxide thickness of 400 nm are irradiated with gate voltages of 2, 4 and 6 V, and without gate voltage.
A detailed analysis of the mechanisms responsible for the creation of traps during irradiation is performed.
The creation of the traps in the oxide, near and at the silicon/silicon-dioxide (Si/SiO2) interface during irradiation is modelled very well. This modelling can also be used for other MOS transistors containing SiO2.
The behaviour of radiation traps during postirradiation annealing is analysed, and the corresponding functions for their modelling are obtained. The switching traps (STs) do not have significant influence on threshold voltage shift, and two radiation-induced trap types fit the fixed traps (FTs) very well. The fading does not depend on the positive gate voltage applied during irradiation, but it is twice lower in case there is no gate voltage.
A new dosimetric parameter, called the Golden Ratio (GR), is proposed, which represents the ratio between the threshold voltage shift after irradiation and fading after spontaneous annealing. This parameter can be useful for comparing MOS dosimeters.
Answer set planning
(2022)
Answer Set Planning refers to the use of Answer Set Programming (ASP) to compute plans, that is, solutions to planning problems, that transform a given state of the world to another state. The development of efficient and scalable answer set solvers has provided a significant boost to the development of ASP-based planning systems. This paper surveys the progress made during the last two and a half decades in the area of answer set planning, from its foundations to its use in challenging planning domains. The survey explores the advantages and disadvantages of answer set planning. It also discusses typical applications of answer set planning and presents a set of challenges for future research.
The bulk built-in current sensor (BBICS) is a cost-effective solution for detection of energetic particle strikes in integrated circuits.
With an appropriate number of BBICSs distributed across the chip, the soft error locations can be identified, and the dynamic fault-tolerant mechanisms can be activated locally to correct the soft errors in the affected logic.
In this work, we introduce a pulse stretching BBICS (PS-BBICS) constructed by connecting a standard BBICS and a custom-designed pulse stretching cell.
The aim of PS-BBICS is to enable the on-chip measurement of the single event transient (SET) pulse width, allowing to detect the linear energy transfer (LET) of incident particles, and thus assess more accurately the radiation conditions.
Based on Spectre simula-tions, we have shown that for the LET from 1 to 100 MeV cm2 mg -1, the SET pulse width detected by PS-BBICS varies by 620-800 ps. The threshold LET of PS-BBICS increases linearly with the number of monitored inverters, and it is around 1.7 MeV cm2 mg- 1 for ten monitored inverters.
On the other hand, the SET pulse width is in-dependent of the number of monitored inverters for LET > 4 MeV cm2 mg -1. It was shown that supply voltage, temperature and process variations have strong impact on the response of PS-BBICS.
We present SURFER, a novel reduced model for estimating the impact of CO2 emissions and solar radiation modification options on sea level rise and ocean acidification over timescales of several thousands of years.
SURFER has been designed for the analysis of CO2 emission and solar radiation modification policies, for supporting the computation of optimal (CO2 emission and solar radiation modification) policies and for the study of commitment and responsibility under uncertainty.
The model is based on a combination of conservation laws for the masses of atmospheric and oceanic carbon and for the oceanic temperature anomalies, and of adhoc parameterisations for the different sea level rise contributors: ice sheets, glaciers and ocean thermal expansion. It consists of 9 loosely coupled ordinary differential equations, is understandable, fast and easy to modify and calibrate.
It reproduces the results of more sophisticated, high-dimensional earth system models on timescales up to millennia.
We study the concept of reversibility in connection with parallel communicating systems of finite automata (PCFA in short). We define the notion of reversibility in the case of PCFA (also covering the non-deterministic case) and discuss the relationship of the reversibility of the systems and the reversibility of its components. We show that a system can be reversible with non-reversible components, and the other way around, the reversibility of the components does not necessarily imply the reversibility of the system as a whole. We also investigate the computational power of deterministic centralized reversible PCFA. We show that these very simple types of PCFA (returning or non-returning) can recognize regular languages which cannot be accepted by reversible (deterministic) finite automata, and that they can even accept languages that are not context-free. We also separate the deterministic and non-deterministic variants in the case of systems with non-returning communication. We show that there are languages accepted by non-deterministic centralized PCFA, which cannot be recognized by any deterministic variant of the same type.
We introduce a new measure of descriptional complexity on finite automata, called the number of active states. Roughly speaking, the number of active states of an automaton A on input w counts the number of different states visited during the most economic computation of the automaton A for the word w. This concept generalizes to finite automata and regular languages in a straightforward way. We show that the number of active states of both finite automata and regular languages is computable, even with respect to nondeterministic finite automata. We further compare the number of active states to related measures for regular languages. In particular, we show incomparability to the radius of regular languages and that the difference between the number of active states and the total number of states needed in finite automata for a regular language can be of exponential order.
Image feature detection is a key task in computer vision. Scale Invariant Feature Transform (SIFT) is a prevalent and well known algorithm for robust feature detection. However, it is computationally demanding and software implementations are not applicable for real-time performance. In this paper, a versatile and pipelined hardware implementation is proposed, that is capable of computing keypoints and rotation invariant descriptors on-chip. All computations are performed in single precision floating-point format which makes it possible to implement the original algorithm with little alteration. Various rotation resolutions and filter kernel sizes are supported for images of any resolution up to ultra-high definition. For full high definition images, 84 fps can be processed. Ultra high definition images can be processed at 21 fps.
Large-scale literature mining to assess the relation between anti-cancer drugs and cancer types
(2021)
Background:
There is a huge body of scientific literature describing the relation between tumor types and anti-cancer drugs. The vast amount of scientific literature makes it impossible for researchers and physicians to extract all relevant information manually.
Methods:
In order to cope with the large amount of literature we applied an automated text mining approach to assess the relations between 30 most frequent cancer types and 270 anti-cancer drugs. We applied two different approaches, a classical text mining based on named entity recognition and an AI-based approach employing word embeddings. The consistency of literature mining results was validated with 3 independent methods: first, using data from FDA approvals, second, using experimentally measured IC-50 cell line data and third, using clinical patient survival data.
Results:
We demonstrated that the automated text mining was able to successfully assess the relation between cancer types and anti-cancer drugs. All validation methods showed a good correspondence between the results from literature mining and independent confirmatory approaches. The relation between most frequent cancer types and drugs employed for their treatment were visualized in a large heatmap. All results are accessible in an interactive web-based knowledge base using the following link: .
Conclusions:
Our approach is able to assess the relations between compounds and cancer types in an automated manner. Both, cancer types and compounds could be grouped into different clusters. Researchers can use the interactive knowledge base to inspect the presented results and follow their own research questions, for example the identification of novel indication areas for known drugs.
Student teachers often struggle to keep track of everything that is happening in the classroom, and particularly to notice and respond when students cause disruptions. The complexity of the classroom environment is a potential contributing factor that has not been empirically tested. In this experimental study, we utilized a virtual reality (VR) classroom to examine whether classroom complexity affects the likelihood of student teachers noticing disruptions and how they react after noticing. Classroom complexity was operationalized as the number of disruptions and the existence of overlapping disruptions (multidimensionality) as well as the existence of parallel teaching tasks (simultaneity). Results showed that student teachers (n = 50) were less likely to notice the scripted disruptions, and also less likely to respond to the disruptions in a comprehensive and effortful manner when facing greater complexity. These results may have implications for both teacher training and the design of VR for training or research purpose. This study contributes to the field from two aspects: 1) it revealed how features of the classroom environment can affect student teachers' noticing of and reaction to disruptions; and 2) it extends the functionality of the VR environment-from a teacher training tool to a testbed of fundamental classroom processes that are difficult to manipulate in real-life.
Background:
Pruritus often accompanies chronic skin diseases, exerting considerable burden on many areas of patient functioning; this burden and the features of pruritus remain insufficiently characterized.
Objective:
To investigate characteristics, including localization patterns, and burden of pruritus in patients with chronic dermatoses.
Methods:
We recruited 800 patients with active chronic skin diseases. We assessed pruritus intensity, localization, and further characteristics. We used validated questionnaires to assess quality of life, work productivity and activity impairment, anxiety, depression, and sleep quality.
Results:
Nine out of every 10 patients had experienced pruritus throughout their disease and 73% in the last 7 days. Pruritus often affected the entire body and was not restricted to skin lesions. Patients with moderate to severe pruritus reported significantly more impairment to their sleep quality and work productivity, and they were more depressed and anxious than control individuals and patients with mild or no pruritus. Suicidal ideations were highly prevalent in patients with chronic pruritus (18.5%) and atopic dermatitis (11.8%).
Conclusions:
Pruritus prevalence and intensity are very high across all dermatoses studied; intensity is linked to impairment in many areas of daily functioning. Effective treatment strategies are urgently required to treat pruritus and the underlying skin disease. ( J Am Acad Dermatol 2021;84:691-700.)
Tropical cyclones range among the costliest disasters on Earth. Their economic repercussions along the supply and trade network also affect remote economies that are not directly affected. We here simulate possible global repercussions on consumption for the example case of Hurricane Sandy in the US (2012) using the shock-propagation model Acclimate. The modeled shock yields a global three-phase ripple: an initial production demand reduction and associated consumption price decrease, followed by a supply shortage with increasing prices, and finally a recovery phase. Regions with strong trade relations to the US experience strong magnitudes of the ripple. A dominating demand reduction or supply shortage leads to overall consumption gains or losses of a region, respectively. While finding these repercussions in historic data is challenging due to strong volatility of economic interactions, numerical models like ours can help to identify them by approaching the problem from an exploratory angle, isolating the effect of interest. For this, our model simulates the economic interactions of over 7000 regional economic sectors, interlinked through about 1.8 million trade relations. Under global warming, the wave-like structures of the economic response to major hurricanes like the one simulated here are likely to intensify and potentially overlap with other weather extremes.
Due to climate change the frequency and character of precipitation are changing as the hydrological cycle intensifies. With regards to snowfall, global warming has two opposing influences; increasing humidity enables intense snowfall, whereas higher temperatures decrease the likelihood of snowfall. Here we show an intensification of extreme snowfall across large areas of the Northern Hemisphere under future warming. This is robust across an ensemble of global climate models when they are bias-corrected with observational data. While mean daily snowfall decreases, both the 99th and the 99.9th percentiles of daily snowfall increase in many regions in the next decades, especially for Northern America and Asia. Additionally, the average intensity of snowfall events exceeding these percentiles as experienced historically increases in many regions. This is likely to pose a challenge to municipalities in mid to high latitudes. Overall, extreme snowfall events are likely to become an increasingly important impact of climate change in the next decades, even if they will become rarer, but not necessarily less intense, in the second half of the century.
Stripe rust (Pst) is a major disease of wheat crops leading untreated to severe yield losses. The use of fungicides is often essential to control Pst when sudden outbreaks are imminent. Sensors capable of detecting Pst in wheat crops could optimize the use of fungicides and improve disease monitoring in high-throughput field phenotyping. Now, deep learning provides new tools for image recognition and may pave the way for new camera based sensors that can identify symptoms in early stages of a disease outbreak within the field. The aim of this study was to teach an image classifier to detect Pst symptoms in winter wheat canopies based on a deep residual neural network (ResNet). For this purpose, a large annotation database was created from images taken by a standard RGB camera that was mounted on a platform at a height of 2 m. Images were acquired while the platform was moved over a randomized field experiment with Pst-inoculated and Pst-free plots of winter wheat. The image classifier was trained with 224 x 224 px patches tiled from the original, unprocessed camera images. The image classifier was tested on different stages of the disease outbreak. At patch level the image classifier reached a total accuracy of 90%. To test the image classifier on image level, the image classifier was evaluated with a sliding window using a large striding length of 224 px allowing for fast test performance. At image level, the image classifier reached a total accuracy of 77%. Even in a stage with very low disease spreading (0.5%) at the very beginning of the Pst outbreak, a detection accuracy of 57% was obtained. Still in the initial phase of the Pst outbreak with 2 to 4% of Pst disease spreading, detection accuracy with 76% could be attained. With further optimizations, the image classifier could be implemented in embedded systems and deployed on drones, vehicles or scanning systems for fast mapping of Pst outbreaks.
Machine learning for improvement of thermal conditions inside a hybrid ventilated animal building
(2021)
In buildings with hybrid ventilation, natural ventilation opening positions (windows), mechanical ventilation rates, heating, and cooling are manipulated to maintain desired thermal conditions. The indoor temperature is regulated solely by ventilation (natural and mechanical) when the external conditions are favorable to save external heating and cooling energy. The ventilation parameters are determined by a rule-based control scheme, which is not optimal. This study proposes a methodology to enable real-time optimum control of ventilation parameters. We developed offline prediction models to estimate future thermal conditions from the data collected from building in operation. The developed offline model is then used to find the optimal controllable ventilation parameters in real-time to minimize the setpoint deviation in the building. With the proposed methodology, the experimental building's setpoint deviation improved for 87% of time, on average, by 0.53 degrees C compared to the current deviations.