In this paper we introduce Bardo, a real-time intelligent system to automatically select the background music for tabletop role-playing games. Bardo uses an off-the-shelf speech recognition system to transform into text what the players say during a game session, and a supervised learning algorithm to classify the text into an emotion. Bardo then selects and plays as background music a song representing the classified emotion. We evaluate Bardo with a Dungeons and Dragons (D&D) campaign available on YouTube. Accuracy experiments show that a simple Naive Bayes classifier is able to obtain good prediction accuracy in our classification task. A user study in which people evaluated edited versions of the D&D videos suggests that Bardo's selections can be better than those used in the original videos of the campaign.

The ability to automatically recognize a person's behavioral context can contribute to health monitoring, aging care and many other domains. Validating context recognition in-the-wild is crucial to promote practical applications that work in real-life settings. We collected over 300k minutes of sensor data with context labels from 60 subjects. Unlike previous studies, our subjects used their own personal phone, in any way that was convenient to them, and engaged in their routine in their natural environments. Unscripted behavior and unconstrained phone usage resulted in situations that are harder to recognize. We demonstrate how fusion of multi-modal sensors is important for resolving such cases. We present a baseline system, and encourage researchers to use our public dataset to compare methods and improve context recognition in-the-wild.

Maybe a cautious approach to a bigger version of the Monolith (2km long) in a POD that is only 2m in diameter is advisable. What do we know about how Monoliths react to stimuli?

To avoid epidemics such as the 2014 Ebola outbreak, early detection and diagnosing of diseases is critical. Even in the more isolated cases, such as the development of cancer, early diagnosis can save lives. Big data can be used as a versatile tool to assist in the detection, monitoring, and diagnosis of bacterial diseases and cancer. Past efforts to combat outbreaks of disease typically focused on the collection of physical information from laboratory test results and public health records, to create predictive models of how the disease might spread. However, the big data model uses medical information, internet resources, social media, and other sources to enable real time tracking of disease outbreaks.

High throughput screening of compounds (chemicals) is an essential part of drug discovery [7], involving thousands to millions of compounds, with the purpose of identifying candidate hits. Most statistical tools, including the industry standard B-score method, work on individual compound plates and do not exploit cross-plate correlation or statistical strength among plates. We present a new statistical framework for high throughput screening of compounds based on Bayesian nonparametric modeling. The proposed approach is able to identify candidate hits from multiple plates simultaneously, sharing statistical strength among plates and providing more robust estimates of compound activity. It can flexibly accommodate arbitrary distributions of compound activities and is applicable to any plate geometry. The algorithm provides a principled statistical approach for hit identification and false discovery rate control. Experiments demonstrate significant improvements in hit identification sensitivity and specificity over the B-score method, which is highly sensitive to threshold choice. The framework is implemented as an efficient R extension package BHTSpack and is suitable for large scale data sets.

It turns out that Floyd Mayweather and Conor McGregor didn't have the biggest fight of all time after all. Their boxing match on Aug. 26 reportedly generated 4.4 million pay-per-view buys, falling just shy of the record-setting 4.6 PPVs sold by Mayweather and Manny Pacquiao on May 2, 2015. During the two-month build towards the fight, which included a four-city press tour in the middle of July, there was talk that the undefeated boxer and the UFC star might set a new mark and possibly approach five million buys. Mayweather and McGregor will have to settle for second-best, according to BoxingScene, and an official announcement could come later this week. Finishing at No.2 is an achievement, nonetheless, as the bout sits comfortably ahead of the third-best selling fight in history.

Layers are Python functions that take Tensors and configuration options as input and produce other tensors as output. Once the necessary Tensors have been composed, the user can convert the result into an Estimator via a model function. A scalar used to train a model via gradient descent.

People should stop using patterns to unlock their devices, researchers have warned. A new study has found that it's a lot easier for people who might be looking over your shoulder as you unlock your phone to memorise a pattern than a passcode. So-called "shoulder surfing attacks" can be easy for a criminal to plan and execute, but you can protect yourself by switching to a PIN code and increasing its length from four digits to six, the researchers say. They got over 1,000 volunteers to act as attackers, challenging them to memorise a range of unlocking authentications – four- and six-digit PINs, and four- and six-length pa tterns with and without tracing lines – by watching a victim over their shoulder from a variety of angles. The 5-inch Nexus 5 and 6-inch OnePlus One were the two handsets used in the study, as the researchers say they "are similar to a wide variety of displays and form factors available on the market today, for both Android and iPhone".

The availability of massive data about sports activities offers nowadays the opportunity to quantify the relation between performance and success. In this study, we analyze more than 6,000 games and 10 million events in six European leagues and investigate this relation in soccer competitions. We discover that a team's position in a competition's final ranking is significantly related to its typical performance, as described by a set of technical features extracted from the soccer data. Moreover we find that, while victory and defeats can be explained by the team's performance during a game, it is difficult to detect draws by using a machine learning approach. We then simulate the outcomes of an entire season of each league only relying on technical data, i.e. excluding the goals scored, exploiting a machine learning model trained on data from past seasons. The simulation produces a team ranking (the PC ranking) which is close to the actual ranking, suggesting that a complex systems' view on soccer has the potential of revealing hidden patterns regarding the relation between performance and success.

Elections unleash strong political views on Twitter, but what do people really think about politics? Opinion and trend mining on micro blogs dealing with politics has recently attracted researchers in several fields including Information Retrieval and Machine Learning (ML). Since the performance of ML and Natural Language Processing (NLP) approaches are limited by the amount and quality of data available, one promising alternative for some tasks is the automatic propagation of expert annotations. This paper intends to develop a so-called active learning process for automatically annotating French language tweets that deal with the image (i.e., representation, web reputation) of politicians. Our main focus is on the methodology followed to build an original annotated dataset expressing opinion from two French politicians over time. We therefore review state of the art NLP-based ML algorithms to automatically annotate tweets using a manual initiation step as bootstrap. This paper focuses on key issues about active learning while building a large annotated data set from noise. This will be introduced by human annotators, abundance of data and the label distribution across data and entities. In turn, we show that Twitter characteristics such as the author's name or hashtags can be considered as the bearing point to not only improve automatic systems for Opinion Mining (OM) and Topic Classification but also to reduce noise in human annotations. However, a later thorough analysis shows that reducing noise might induce the loss of crucial information.