Sofie Van Hoecke

The pragmatic proof: Hypermedia API composition and execution

Machine clients are increasingly making use of the Web to perform tasks. While Web services traditionally mimic remote procedure calling interfaces, a new generation of so-called hypermedia APIs works through hyperlinks and forms, in a way similar to how people browse the Web. This means that existing composition techniques, which determine a procedural plan upfront, are not sufficient to consume hypermedia APIs, which need to be navigated at runtime. Clients instead need a more dynamic plan that allows them to follow hyperlinks and use forms with a preset goal. Therefore, in this article, we show how compositions of hypermedia APIs can be created by generic Semantic Web reasoners. This is achieved through the generation of a proof based on semantic descriptions of the APIs functionality. To pragmatically verify the applicability of compositions, we introduce the notion of pre-execution and post-execution proofs. The runtime interaction between a client and a server is guided by proofs but driven by hypermedia, allowing the client to react to the applications actual state indicated by the servers response. We describe how to generate compositions from descriptions, discuss a computer-assisted process to generate descriptions, and verify reasoner performance on various composition tasks using a benchmark suite. The experimental results lead to the conclusion that proof-based consumption of hypermedia APIs is a feasible strategy at Web scale.

Deep learning for infrared thermal image based machine health monitoring

The condition of a machine can automatically be identified by creating and classifying features that summarize characteristics of measured signals. Currently, experts, in their respective fields, devise these features based on their knowledge. Hence, the performance and usefulness depends on the experts knowledge of the underlying physics or statistics. Furthermore, if new and additional conditions should be detectable, experts have to implement new feature extraction methods. To mitigate the drawbacks of feature engineering, a method from the subfield of feature learning, i.e., deep learning (DL), more specifically convolutional neural networks (NNs), is researched in this paper. The objective of this paper is to investigate if and how DL can be applied to infrared thermal (IRT) video to automatically determine the condition of the machine. By applying this method on IRT data in two use cases, i.e.,xa0machine-fault detection and oil-level prediction, we show that the proposed system is able to detect many conditions in rotating machinery very accurately (i.e.,xa095 and 91.67% accuracy for the respective use cases), without requiring any detailed knowledge about the underlying physics, and thus having the potential to significantly simplify condition monitoring using complex sensor data. Furthermore, we show that by using the trained NNs, important regions in the IRT images can be identified related to specific conditions, which can potentially lead to new physical insights.

Extended FTLD pedigree segregating a Belgian GRN-null mutation : neuropathological heterogeneity in one family

BackgroundIn this paper, we describe the clinical and neuropathological findings of nine members of the Belgian progranulin gene (GRN) founder family. In this family, the loss-of-function mutation IVS1u2009+u20095Gu2009>u2009C was identified in 2006. In 2007, a clinical description of the mutation carriers was published that revealed the clinical heterogeneity among IVS1u2009+u20095Gu2009>u2009C carriers. We report our comparison of our data with the published clinical and neuropathological characteristics of other GRN mutations as well as other frontotemporal lobar degeneration (FTLD) syndromes, and we present a review of the literature.MethodsFor each case, standardized sampling and staining were performed to identify proteinopathies, cerebrovascular disease, and hippocampal sclerosis.ResultsThe neuropathological substrate in the studied family was compatible in all cases with transactive response DNA-binding protein (TDP) proteinopathy type A, as expected. Additionally, most of the cases presented also with primary age-related tauopathy (PART) or mild Alzheimer’s disease (AD) neuropathological changes, and one case had extensive Lewy body pathology. An additional finding was the presence of cerebral small vessel changes in every patient in this family.ConclusionsOur data show not only that the IVS1u2009+u20095Gu2009>u2009C mutation has an exclusive association with FTLD-TDP type A proteinopathy but also that other proteinopathies can occur and should be looked for. Because the penetrance rate of the clinical phenotype of carriers of GRN mutations is age-dependent, further research is required to investigate the role of co-occurring age-related pathologies such as AD, PART, and cerebral small vessel disease.

A genetic algorithm for interpretable model extraction from decision tree ensembles

Models obtained by decision tree induction techniques excel in being interpretable. However, they can be prone to overfitting, which results in a low predictive performance. Ensemble techniques provide a solution to this problem, and are hence able to achieve higher accuracies. However, this comes at a cost of losing the excellent interpretability of the resulting model, making ensemble techniques impractical in applications where decision support, instead of decision making, is crucial.

Extensible multi-domain generation of Virtual Worlds using blackboards

Procedural generation of large virtual worlds remains a challenge, because current procedural methods mainly focus on generating assets for a single content domain, such as height maps, trees or buildings. Furthermore current approaches for multi-domain content generation, i.e. generating complete virtual environments, are often too ad-hoc to allow for varying design constraints from creatives industries such as the development of video games. In this paper, we propose a multi-domain procedural generation method that uses modularized, single-domain generation methods that interact on the data level while operating independently. Our method uses a blackboard architecture specialized to fit the needs of procedural content generation. We show that our approach is extensible to a wide range of use cases of virtual world generation and that manual or procedural editing of the generated content of one generator is automatically communicated to the other generators, which ensures a consistent and coherent virtual world. Furthermore, the blackboard approach automatically reasons about the generation process which allows 52% to 98% of the activations, i.e. executions of the single-domain content generators, to be discarded without compromising the generated content, resulting in better performing large world generation.