Explore the vast range of titles available.

We investigate the capabilities of transfer learning in the area of structural health monitoring. In particular, we are interested in damage detection for concrete structures. Typical image datasets for such problems are relatively small, calling for the transfer of learned representation from a related large-scale dataset. Past efforts of damage detection using images have mainly considered cross-domain transfer learning approaches using pre-trained ImageNet models that are subsequently fine-tuned for the target task. However, there are rising concerns about the generalizability of ImageNet representations for specific target domains, such as for visual inspection and medical imaging. We, therefore, evaluate a combination of in-domain and cross-domain transfer learning strategies for damage detection in bridges. We perform comprehensive comparisons to study the impact of cross-domain and in-domain transfer, with various initialization strategies, using six publicly available visual inspection datasets. The pre-trained models are also evaluated for their ability to cope with the extremely low-data regime. We show that the combination of cross-domain and in-domain transfer persistently shows superior performance specially with tiny datasets. Likewise, we also provide visual explanations of predictive models to enable algorithmic transparency and provide insights to experts about the intrinsic decision logic of typically black-box deep models.

Background CHANTER (Cerebellar Hippocampal and Basal Nuclei Transient Edema with Restricted diffusion) is a recently described syndrome occurring in the context of drug abuse. While clinical findings are rather unspecific (disorientation, unresponsiveness), MR imaging (MRI) discloses a characteristic pattern (restricted diffusion in the basal ganglia and hippocampi, cerebellar oedema and haemorrhage), allowing for timely diagnosis before complications such as cerebellar swelling and herniation do occur. Here we report a case of CHANTER primarily based on imaging findings, as there was no evidence of drug abuse on admission. Case presentation A 62-year-old Patient was admitted to our hospital after being unresponsive at home. Prehospital intubation was performed, which limited neurological assessment. Under these circumstances no obvious symptoms could be determined, i.e. pupils were isocoric and responsive, and there were no signs of seizures. While the initial CT scan was unremarkable, the subsequent MRI scan showed a distinct imaging pattern: moderately enhancing areas in the basal ganglia and hippocampi with diffusion restriction, accompanied by cerebellar haemorrhage and oedema (Figs. 1 and 2). A comprehensive clinical and laboratory work-up was performed, including drug screening, spinal tap, Holter ECG, echocardiography and EEG. The only conspicuous anamnestic finding was a chronic pain syndrome whose medication had been supplemented with opioids two months previously. The opioid medication was discontinued, which led to a rapid improvement in the patient’s clinical condition without any further measures. The patient was able to leave the intensive care unit and was discharged 10 days after admission without persistent neurological deficits. Conclusion Familiarity with typical MRI patterns of toxic encephalopathy in patients from high-risk groups, such as drug abusers, is crucial in emergency neuroradiology. In the presence of typical MRI findings, CHANTER syndrome should be included in the differential diagnosis, even if there is no history of drug abuse, to avoid delay in diagnosis and treatment.

The full potential of predictive maintenance has not yet been utilised. Current solutions focus on individual steps of the predictive maintenance cycle and only work for very specific settings. The overarching challenge of predictive maintenance is to leverage these individual building blocks to obtain a framework that supports optimal maintenance and asset management. The PrimaVera project has identified four obstacles to tackle in order to utilise predictive maintenance at its full potential: lack of orchestration and automation of the predictive maintenance workflow, inaccurate or incomplete data and the role of human and organisational factors in data-driven decision support tools. Furthermore, an intuitive generic applicable predictive maintenance process model is presented in this paper to provide a structured way of deploying predictive maintenance solutions.

Partially observable Markov decision processes (POMDPs) are models for sequential decision-making under uncertainty and incomplete information. Machine learning methods typically train recurrent neural networks (RNN) as effective representations of POMDP policies that can efficiently process sequential data. However, it is hard to verify whether the POMDP driven by such RNN-based policies satisfies safety constraints, for instance, given by temporal logic specifications. We propose a novel method that combines techniques from machine learning with the field of formal methods: training an RNN-based policy and then automatically extracting a so-called finite-state controller (FSC) from the RNN. Such FSCs offer a convenient way to verify temporal logic constraints. Implemented on a POMDP, they induce a Markov chain, and probabilistic verification methods can efficiently check whether this induced Markov chain satisfies a temporal logic specification. Using such methods, if the Markov chain does not satisfy the specification, a byproduct of verification is diagnostic information about the states in the POMDP that are critical for the specification. The method exploits this diagnostic information to either adjust the complexity of the extracted FSC or improve the policy by performing focused retraining of the RNN. The method synthesizes policies that satisfy temporal logic specifications for POMDPs with up to millions of states, which are three orders of magnitude larger than comparable approaches.

Microbial studies of the Mediterranean sponge Tethya aurantium led to the isolation of the fungus Bartalinia robillardoides strain LF550. The strain produced a number of secondary metabolites belonging to the chloroazaphilones. This is the first report on the isolation of chloroazaphilones of a fungal strain belonging to the genus Bartalinia. Besides some known compounds (helicusin A (1) and deacetylsclerotiorin (2)), three new chloroazaphilones (helicusin E (3); isochromophilone X (4) and isochromophilone XI (5)) and one new pentaketide (bartanolide (6)) were isolated. The structure elucidations were based on spectroscopic analyses. All isolated compounds revealed different biological activity spectra against a test panel of four bacteria: three fungi; two tumor cell lines and two enzymes.

We report the rare occurrence of a temporal glioblastoma multiforme (GBM) showing transdural tumor extension into adjacent mastoid cells. As the dura mater provides a barrier to intraaxial tumors, GBM seldom penetrates into the skull base, even though it is a high-grade astrocytoma with a tendency to spread. Yet, some mechanisms of GBM-induced skull invasion have been identified, making this entity a very rare but nonetheless relevant differential diagnosis in otherwise ambiguous cases of an intracerebral tumor extending into the skull base. In addition, imaging markers that may assist in distinguishing extra- from intraaxial tumor infiltration of the temporal bone are described.

Controllers for dynamical systems that operate in safety-critical settings must account for stochastic disturbances. Such disturbances are often modeled as process noise in a dynamical system, and common assumptions are that the underlying distributions are known and/or Gaussian. In practice, however, these assumptions may be unrealistic and can lead to poor approximations of the true noise distribution. We present a novel controller synthesis method that does not rely on any explicit representation of the noise distributions. In particular, we address the problem of computing a controller that provides probabilistic guarantees on safely reaching a target, while also avoiding unsafe regions of the state space. First, we abstract the continuous control system into a finite-state model that captures noise by probabilistic transitions between discrete states. As a key contribution, we adapt tools from the scenario approach to compute probably approximately correct (PAC) bounds on these transition probabilities, based on a finite number of samples of the noise. We capture these bounds in the transition probability intervals of a so-called interval Markov decision process (iMDP). This iMDP is, with a user-specified confidence probability, robust against uncertainty in the transition probabilities, and the tightness of the probability intervals can be controlled through the number of samples. We use state-of-the-art verification techniques to provide guarantees on the iMDP and compute a controller for which these guarantees carry over to the original control system. In addition, we develop a tailored computational scheme that reduces the complexity of the synthesis of these guarantees on the iMDP. Benchmarks on realistic control systems show the practical applicability of our method, even when the iMDP has hundreds of millions of transitions.

In February 2008, an Interim Outline Edition of the Draft Common Frame of Reference (DCFR) for European private law was published, and in February 2009 the definitive Outline Edition.1 By the end of 2009, the full work (i.e. model rules, comments and comparative notes) was available in print, consisting of six volumes comprising about 6,100 pages. The DCFR project was launched and sponsored by the Commission of the European Union. Ever since the enigmatic term \"Common Frame of Reference\" (CFR) was coined in a Communication from 2003, commentators have been trying to figure out what it might be intended to mean. The Commission itself has repeatedly stated that the CFR is supposed to be a \"tool box\" for future legislation in the field of contract law. But the CFR might also conceivably serve as an \"optional instrument\", i.e. a set of rules which parties to a transnational contract can agree upon to govern their transaction. Yet, the main part of the DCFR constitutes a fully-fledged draft code of 'patrimonial' law at large. For its scope reaches far beyond (general) 'contract law'. It has a book with rules on obligations in general, and it comprises specific types of contract (including mandate and donation), noncontractual obligations (including \"benevolent intervention in another's affairs\", i.e. 'negotiorum gestio'), a property law regime concerning movables as well as a book with no less than 116 articles on trust law.

In this paper, we present the envisioned style and scope of the new topic “Explanation Paradigms Leveraging Analytic Intuition” (ExPLAIn) with the International Journal on Software Tools for Technology Transfer (STTT). Intention behind this new topic is to (1) explicitly address all aspects and issues that arise when trying to, if possible, reveal and then confirm hidden properties of black-box systems, or (2) to enforce vital properties by embedding them into appropriate system contexts. Machine-learned systems, such as Deep Neural Networks, are particularly challenging black-box systems, and there is a wealth of formal methods for analysis and verification waiting to be adapted and applied. The selection of papers of this first Special Section of ExPLAIn, most of which were co-authored by editorial board members, is an illustrative example of the style and scope envisioned: In addition to methodological papers on verification, explanation, and their scalability, case studies, tool papers, literature reviews, and position papers are also welcome.

This position paper reflects on the state-of-the-art in decision-making under uncertainty. A classical assumption is that probabilities can sufficiently capture all uncertainty in a system. In this paper, the focus is on the uncertainty that goes beyond this classical interpretation, particularly by employing a clear distinction between aleatoric and epistemic uncertainty. The paper features an overview of Markov decision processes (MDPs) and extensions to account for partial observability and adversarial behavior. These models sufficiently capture aleatoric uncertainty, but fail to account for epistemic uncertainty robustly. Consequently, we present a thorough overview of so-called uncertainty models that exhibit uncertainty in a more robust interpretation. We show several solution techniques for both discrete and continuous models, ranging from formal verification, over control-based abstractions, to reinforcement learning. As an integral part of this paper, we list and discuss several key challenges that arise when dealing with rich types of uncertainty in a model-based fashion.