Abstract
This paper introduces the Large Events Model (LEM) for soccer, a novel deep learning framework for generating and analyzing soccer matches. The framework can simulate games from a given game state, with its primary output being the ensuing probabilities and events from multiple simulations. These can provide insights into match dynamics and underlying mechanisms. We discuss the framework's design, features, and methodologies, including model optimization, data processing, and evaluation techniques. The models within this framework are developed to predict specific aspects of soccer events, such as event type, success likelihood, and further details. In an applied context, we showcase the estimation of xP+, a metric estimating a player's contribution to the team's points earned. This work ultimately enhances the field of sports event prediction and practical applications and emphasizes the potential for this kind of method.

Abstract
The recognition of human activities through sensors embedded in smart-phone devices, such as iPhone, is attracting researchers due to its relevance. The advances of this kind of technology are making possible the widespread and pervasiveness of sensing technology to take advantage of multiple sources of sensing to enrich users experience or to achieve proactive, context-aware applications and services. Human activity recognition and monitoring involves a continuing analysis of large amounts of data so, any increase or decrease in accuracy results in a wide variation in the number of activities correctly classied and incorrectly classied, so it is very important to increase the rate of correct classication. We have researched on a vector with 159 different features and on the vector subsets in order to improve the human activities recognition. We extracted features from the Magnitude of the Signal, the raw signal data, the vertical acceleration, the Horizontal acceleration, and the ltered Raw data. In the evaluation process we used the classiers: Naive Bayes, K-Nearest Neighbor and Random Forest. The features were extracted using the java programming language and the evaluation was done with WEKA. The maximum accuracy was obtained, as expected, with Random Forest using all the 159 features. The best subset found has twelve features: the Pearson correlation between vertical acceleration and horizontal acceleration, the Pearson correlation between x and y, the Pearson correlation between x and z, the STD of acceleration z, the STD of digital compass y, the STD of digital compass z, the STD of digital compass x, the mean between axis, the energy of digital compass x, the mean of acceleration x, the mean of acceleration z, the median of acceleration z.

Abstract
Nowadays, transportation vehicles are equipped with intelligent sensors. Together, they form collaborative networks that broadcast real-time data about mobility patterns in urban areas. Online intelligent transportation systems for taxi dispatching, time-saving route finding or automatic vehicle location are already exploring such information in the taxi/buses transport industries. In this PhD spotlight paper, the authors present two ML applications focused on improving the operation of Public Transportation (PT) systems: 1) Bus Bunching (BB) Online Detection and 2) Taxi-Passenger Demand Prediction. By doing so, we intend to give a brief overview of the type of approaches applicable to these type of problems. Our frameworks are straightforward. By employing online learning frameworks we are able to use both historical and real-time data to update the inference models. The results are promising.

Abstract
Built-in sensors in most modern smartphones open multipleopportunities for novel context-aware applications. Although the HumanActivity Recognition field seized such opportunity, many challengesare yet to be addressed, such as the differences in movement by peopledoing the same activities. This paper exposes empirical research onOnline Semi-supervised Learning (OSSL), an under-explored incrementalapproach capable of adapting the classification model to the userby continuously updating it as data from the users own input signalsarrives. Ultimately, we achieved an average accuracy increase of 0.18percentage points (PP) resulting in a 82.76% accuracy model with NaiveBayes, 0.14 PP accuracy increase resulting in a 83.03% accuracy modelwith a Democratic Ensemble, and 0.08 PP accuracy increase resultingin a 84.63% accuracy model with a Confidence Ensemble. These modelscould detect 3 stationary activities, 3 active activities, and all transitionsbetween the stationary activities, totaling 12 distinct activities