Automatic understanding of domain specific texts in order to extract useful relationships for later use is a non-trivial task. One such relationship would be between railroad accidents' causes and their correspondent descriptions in reports. From 2001 to 2016 rail accidents in the U.S. cost more than $4.6B. Railroads involved in accidents are required to submit an accident report to the Federal Railroad Administration (FRA). These reports contain a variety of fixed field entries including primary cause of the accidents (a coded variable with 389 values) as well as a narrative field which is a short text description of the accident. Although these narratives provide more information than a fixed field entry, the terminologies used in these reports are not easy to understand by a non-expert reader. Therefore, providing an assisting method to fill in the primary cause from such domain specific texts(narratives) would help to label the accidents with more accuracy. Another important question for transportation safety is whether the reported accident cause is consistent with narrative description. To address these questions, we applied deep learning methods together with powerful word embeddings such as Word2Vec and GloVe to classify accident cause values for the primary cause field using the text in the narratives. The results show that such approaches can both accurately classify accident causes based on report narratives and find important inconsistencies in accident reporting.

The complete part of the earthquake frequency-magnitude distribution (FMD), above completeness magnitude mc, is well described by the Gutenberg-Richter law. The parameter mc however varies in space due to the seismic network configuration, yielding a convoluted FMD shape below max(mc). This paper investigates the shape of the generalized FMD (GFMD), which may be described as a mixture of elemental FMDs (eFMDs) defined as asymmetric Laplace distributions of mode mc [Mignan, 2012, https://doi.org/10.1029/2012JB009347]. An asymmetric Laplace mixture model (GFMD- ALMM) is thus proposed with its parameters (detection parameter kappa, Gutenberg-Richter beta-value, mc distribution, as well as number K and weight w of eFMD components) estimated using a semi-supervised hard expectation maximization approach including BIC penalties for model complexity. The performance of the proposed method is analysed, with encouraging results obtained: kappa, beta, and the mc distribution range are retrieved for different GFMD shapes in simulations, as well as in regional catalogues (southern and northern California, Nevada, Taiwan, France), in a global catalogue, and in an aftershock sequence (Christchurch, New Zealand). We find max(mc) to be conservative compared to other methods, kappa = k/log(10) = 3 in most catalogues (compared to beta = b/log(10) = 1), but also that biases in kappa and beta may occur when rounding errors are present below completeness. The GFMD-ALMM, by modelling different FMD shapes in an autonomous manner, opens the door to new statistical analyses in the realm of incomplete seismicity data, which could in theory improve earthquake forecasting by considering c. ten times more events.

One of the most brilliant minds to have graced the planet, Stephen Hawking, throughout his life, was curiously sceptical of artificial intelligence (AI), the flavour of the moment in technology. Stephen Hawking never doubted AI's prowess; in fact, to the contrary, he believed it would surpass human intelligence and, thus, machines could one day seize control from humans. In his last book, Brief Answers to Big Questions, the scientist predicts that machine-learning will lead to a super-intelligent AI and "a super-intelligent AI will be extremely good at accomplishing its goals, and if those goals aren't aligned with ours we're in trouble". Comparing the human race to an anthill in a region that will soon get flooded, the late physicist also predicted that the Earth will be destroyed, either due to the proliferation of nuclear weapons and the ensuing warfare or a human-made environmental disaster. However, there will be certain humans who will manage to evade these catastrophes.

This technology could be put in smartphones that understand and predict our behaviour, potentially offering personalised support. They could also be used by robot companions for older people, or in self-driving cars and interactive video games.

The increasing popularity of cell phones has made them the most personal and ubiquitous communication devices nowadays. Typically, the ringing notifications of mobile phones are used to inform the users about the incoming calls. However, the notifications of inappropriate incoming calls sometimes cause interruptions not only for the users but also the surrounding people. In this paper, we present a data-driven approach to infer the opportune moments for such phone call interruptions based on user's unavailability, i.e., when a user is unable to answer the incoming phone calls, by analyzing individual's past phone log data, and to discover the corresponding phone silent mode configuring rules for the purpose of minimizing call interruptions in an automated intelligent system. Experiments on the real mobile phone datasets show that our approach is able to identify the opportune moments for call interruptions and generates corresponding silent mode configuring rules by capturing the dominant behavior of individual users' at various times-of-the-day and days-of-theweek. Received on XXXX; accepted on XXXX; published on XXXX Keywords: Mobile phones, phone log data, temporal context, user modeling, phone ringer mode, interruptions, unavailability, personalization, intelligent systems.

SYDNEY (BLOOMBERG) Does the idea to use artificial intelligence (AI), drones and electric force fields to prevent sharks from eating human bathers have teeth? Several tech start-ups in Australia say yes. Officials in the United States are watching the advancements keenly, aware that climate change is altering migration patterns and threatening to push great whites ever closer to American shores. This summer, sharks have attacked teenagers on beaches from California to New York. Sharks typically frequent lower latitudes, but warming oceans are pushing their prey north, said Florida Atlantic University Professor Stephen Kajiura.

Understanding dynamic fracture propagation is essential to predicting how brittle materials fail. Various mathematical models and computational applications have been developed to predict fracture evolution and coalescence, including finite-discrete element methods such as the Hybrid Optimization Software Suite (HOSS). While such methods achieve high fidelity results, they can be computationally prohibitive: a single simulation takes hours to run, and thousands of simulations are required for a statistically meaningful ensemble. We propose a machine learning approach that, once trained on data from HOSS simulations, can predict fracture growth statistics within seconds. Our method uses deep learning, exploiting the capabilities of a graph convolutional network to recognize features of the fracturing material, along with a recurrent neural network to model the evolution of these features. In this way, we simultaneously generate predictions for qualitatively distinct material properties. Our prediction for total damage in a coalesced fracture, at the final simulation time step, is within 3% of its actual value, and our prediction for total length of a coalesced fracture is within 2%. We also develop a novel form of data augmentation that compensates for the modest size of our training data, and an ensemble learning approach that enables us to predict when the material fails, with a mean absolute error of approximately 15%.

But unsure where to focus his research, he had a conversation with a professor the same day the professor's mother had been diagnosed with breast cancer and it took his interest down an unexpected path. "Most of the AI back when I started was based around mobile robots and making vehicles move around autonomously in factories. That frankly wasn't very interesting to me," he told news.com.au. As part of his PhD he began to pioneer a way to use computer software to detect and measure breast density in screening images. At the time, breast cancer screening was far from perfect and he thought artificial intelligence could revolutionise it.

Use of artificial intelligence (AI) in digital commerce is generally considered a success, according to a survey by Gartner, Inc. About 70 percent of digital commerce organizations surveyed report that their AI projects are very or extremely successful. Gartner conducted a survey* of 307 digital commerce organizations that are currently using or piloting AI to understand the adoption, value, success and challenges of AI in digital commerce. Respondents included organizations in the U.S., Canada, Brazil, France, Germany, the U.K., Australia, New Zealand, India and China. Three-quarters of respondents said they are seeing double-digit improvements in the outcomes they measure.

Accurately estimating the remaining useful life (RUL) of industrial machinery is beneficial in many real-world applications. Estimation techniques have mainly utilized linear models or neural network based approaches with a focus on short term time dependencies. This paper introduces a system model that incorporates temporal convolutions with both long term and short term time dependencies. The proposed network learns salient features and complex temporal variations in sensor values, and predicts the RUL. A data augmentation method is used for increased accuracy. The proposed method is compared with several state-of-the-art algorithms on publicly available datasets. It demonstrates promising results, with superior results for datasets obtained from complex environments.