Predicting the completion time of business process instances would be a very helpful aid when managing processes under service level agreement constraints. The ability to know in advance the trend of running process instances would allow business managers to react in time, in order to prevent delays or undesirable situations. However, making such accurate forecasts is not easy: many factors may influence the required time to complete a process instance. In this paper, we propose an approach based on deep Recurrent Neural Networks (specifically LSTMs) that is able to exploit arbitrary information associated to single events, in order to produce an as-accurate-as-possible prediction of the completion time of running instances. Experiments on real-world datasets confirm the quality of our proposal.

Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets. It opens the door to large-scale statistical models. Finding a unified perspective for all available data calls for scalable and automated solutions to an old challenge: how to aggregate heterogeneous information on brain function into a universal cognitive system that relates mental operations/cognitive processes/psychological tasks to brain networks? We cast this challenge in a machine-learning approach to predict conditions from statistical brain maps across different studies. For this, we leverage multi-task learning and multi-scale dimension reduction to learn low-dimensional representations of brain images that carry cognitive information and can be robustly associated with psychological stimuli. Our multi-dataset classification model achieves the best prediction performance on several large reference datasets, compared to models without cognitive-aware low-dimension representations, it brings a substantial performance boost to the analysis of small datasets, and can be introspected to identify universal template cognitive concepts.

In this work we propose a new method for the rhythm classification of short single-lead ECG records, using a set of high-level and clinically meaningful features provided by the abductive interpretation of the records. These features include morphological and rhythm-related features that are used to build two classifiers: one that evaluates the record globally, using aggregated values for each feature; and another one that evaluates the record as a sequence, using a Recurrent Neural Network fed with the individual features for each detected heartbeat. The two classifiers are finally combined using the stacking technique, providing an answer by means of four target classes: Normal sinus rhythm (N), Atrial fibrillation (A), Other anomaly (O) and Noisy (). The approach has been validated against the 2017 Physionet/CinC Challenge dataset, obtaining a final score of 0.83 and ranking first in the competition.

We analyze the data complexity of ontology-mediated querying where the ontologies are formulated in a description logic (DL) of the ALC family and queries are conjunctive queries, positive existential queries, or acyclic conjunctive queries. Our approach is non-uniform in the sense that we aim to understand the complexity of each single ontology instead of for all ontologies formulated in a certain language. While doing so, we quantify over the queries and are interested, for example, in the question whether all queries can be evaluated in polynomial time w.r.t. a given ontology. Our results include a PTime/coNP-dichotomy for ontologies of depth one in the description logic ALCFI, the same dichotomy for ALC- and ALCI-ontologies of unrestricted depth, and the non-existence of such a dichotomy for ALCF-ontologies. For the latter DL, we additionally show that it is undecidable whether a given ontology admits PTime query evaluation. We also consider the connection between PTime query evaluation and rewritability into (monadic) Datalog.

There are many different types of sites that provide a wealth of free, freemium and paid data that can help audience developers and journalists with their reporting and storytelling efforts, The team at State of Digital Publishing would like to acknowledge these, as derived from manual searches and recognition from our existing audience. Kaggle's a site that allows users to discover machine learning while writing and sharing cloud-based code. Relying primarily on the enthusiasm of its sizable community, the site hosts dataset competitions for cash prizes and as a result it has massive amounts of data compiled into it. Whether you're looking for historical data from the New York Stock Exchange, an overview of candy production trends in the US, or cutting edge code, this site is chockful of information. It's impossible to be on the Internet for long without running into a Wikipedia article.

Space is a cold and barren place. Nothing can exist there, nothing!" Ludwig Von Drake, an obscure uncle of Donald Duck and a professor of astronomy, is sitting on a high stool in his observatory. When he sees that he is being filmed, he falls off and lands on the floor with a loud thump. "Now I can see stars I've never seen before!" he groans. He walks over to a table with a large pile of books on it. The thickest of them all is a guide to space travel that he wrote himself. In a 45 -minute- long monologue, he tells us in a thick German accent how mankind discovered the planets in our solar system and has fantasized about everything that might be crawling around on them. Every now and then, he picks up a book from the large pile and reads from it, and then throws it nonchalantly into a corner of the room. He tells us about Copernicus and Galileo, and about Kepler's dreams about Martians, Fontenelle's speculations about life on other planets, and even John Herschel's Great Moon Hoax. Science fiction comes to life in the colorful cartoon: Hairy space beings and flying saucers shoot across the screen. At the end, the professor has the last word. He finds all these fantasies poppycock; nothing can live in that empty, barren space! But, as he is speaking, Von Drake is kidnapped by a black Martian robot from one of his stories. The cartoon, Inside Outer Space, is part of Walt Disney's Wonderful World of Color, a television series from the 1960s. The absent minded duck professor hosts a number of episodes, each with their own topic: the history of flight, the color spectrum, space--all exciting stuff for American kids in the Space Age. Lou Allamandola spent his teenage years in the science- crazy 1960s. He grew up in a Catholic family in the state of New Jersey. His grandparents were immigrants from Italy, and he didn't learn to speak English until he went to school. He still clearly remembers the Disney cartoons with Ludwig Von Drake, which were broadcast on Saturday evenings. "Von Drake called the interstellar medium--the empty space between the stars and the planets--a barren place where nothing could exist," he tells me. "That was all we knew in the '60s.

Originally published in France in 2016, Living with Robots combines the authors' expertise in philosophy--in particular, Paul Du mouchel's scholarship on the role of emo tion in shaping social life and Luisa Damiano's work on human and artificial cognition--to offer insight into problems raised by advances in robotics and artificial intelli gence that will be faced by future societies. Throughout the book, the authors provide a conceptual framework for thinking about possible scenarios of human-robot interac tions, most extensively with regard to our relationships with social robots.

An affordable and effective device for detecting skin cancer has picked up an award of £30,000 ($40,000) from Britain's best-known inventor. This year's James Dyson prize for engineering was given to a group of four Canadian graduates, for their sKan system. The gadget picks up on subtle changes in the skin's ability to retain heat, which can indicate the presences of cancerous tissue. The device costs £760 ($1,000), compared with the £20,000 ($26,000) for high-resolution thermal imaging cameras. An affordable and effective device for detecting skin cancer has picked up an award of £30,000 ($40,000) from Britain's best-known inventor.

Stressful situations really do make it harder to remember things, new research has found. Challenging situations make it harder to understand where you are and what's happening around you, the study showed. The research could help us understand why people who have been through extremely stressful events, such as war veterans or victims of crime, struggle to remember them. Stressful situations really do make it harder to remember things, new research has found. Challenging situations make it harder to understand where you are and what's happening around you (stock image) The research shows that difficult situations - whether positive or negative - cause the brain to drop nuanced, context-based thought in flavor of reflexive action.

The BNAIC2018 and BENELEARN2018 will be co-located and organized by the Jheronimus Academy of Data Science (JADS) in's-Hertogenbosch. For more information see https://bnaic2018.nl