Abstract
For many reasons, including sports being one of the main forms of entertainment in the world, online gambling is growing. And in growing markets, opportunities to explore it arise. In this paper, neural network ensemble approaches, such as bagging, random subspace sampling, negative correlation learning and the simple averaging of predictions, are compared. For each one of these methods, several combinations of input parameters are evaluated. We used only the expected goals metric as predictors since it is able to have good predictive power while keeping the computational demands low. These models are compared in the soccer (also known as association football) betting context where we have access to metrics, such as rentability, to analyze the results in multiple perspectives. The results show that the optimal solution is goal-dependent, with the ensemble methods being able to increase the accuracy up to +3 % over the best single model. The biggest improvement over the single model was obtained by averaging dropout networks. © 2020, Springer Nature Switzerland AG.

Abstract
The kNN machine learning method is widely used as a classifier in Human Activity Recognition (HAR) systems. Although the kNN algorithm works similarly both online and in offline mode, the use of all training instances is much more critical online than offline due to time and memory restrictions in the online mode. Some methods propose decreasing the high computational costs of kNN by focusing, e.g., on approximate kNN solutions such as the ones relying on Locality-Sensitive Hashing (LSH). However, embedded kNN implementations also need to address the target device’s memory constraints, especially as the use of online classification needs to cope with those constraints to be practical. This paper discusses online approaches to reduce the number of training instances stored in the kNN search space. To address practical implementations of HAR systems using kNN, this paper presents simple, energy/computationally efficient, and real-time feasible schemes to maintain at runtime a maximum number of training instances stored by kNN. The proposed schemes include policies for substituting the training instances, maintaining the search space to a maximum size. Experiments in the context of HAR datasets show the efficiency of our best schemes. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.

Abstract
Location tracking is an essential problem for mobility-based applications that facilitate the daily life of Smartphone users. Existing applications often use energy-hungry sensors like GPS or gyroscope to detect significant journeys. Recent research has often focused on optimizing energy consumption. As a result, approaches were proposed using sensors fusions, hybrid or eventual sensors selection. However, such research largely neglects the performance in underground tracking of automotive mobility. Possible solutions, such as those involving barometers, have well-known issues regarding performance. Oppositely, although energy-friendly, accelerometers are often overlooked based on the assumption that pattern extraction is hard due to over-noisy characteristics of the signal. In this paper, we propose a ready-to-use Framework for underground train tracking. This Framework uses an adaptive Singular Spectrum Analysis (SSA) to process the Accelerometer data. We run an empirical study using data collected from Smartphone embedded accelerometers, to track departings and arrivals of the trains in four large European cities. Results show that: 1) the Framework is able to accurately locate the trains; 2) SSA adds improvements compared to Butterworth filters and complementary filter with sensors fusion.

Abstract
Artificial Intelligence (AI) is continuously improving several aspects of our daily lives. There has been a great use of gadgets & monitoring devices for health and physical activity monitoring. Thus, by analyzing large amounts of data and applying Machine Learning (ML) techniques, we have been able to infer fruitful conclusions in various contexts. Activity Recognition is one of them, in which it is possible to recognize and monitor our daily actions. The main focus of the traditional systems is only to detect pre-established activities according to the previously configured parameters, and not to detect novel ones. However, when applying activity recognizers in real-world applications, it is necessary to detect new activities that were not considered during the training of the model. We propose a method for Novelty Detection in the context of physical activity. Our solution is based on the establishment of a threshold confidence value, which determines whether an activity is novel or not. We built and train our models by experimenting with three different algorithms and four threshold values. The best results were obtained by using the Random Forest algorithm with a threshold value of 0.8, resulting in 90.9% of accuracy and 85.1% for precision.

Abstract
Human Activity Recognition is focused on the use of sensing technology to classify human activities and to infer human behavior. While traditional machine learning approaches use hand-crafted features to train their models, recent advancements in neural networks allow for automatic feature extraction. Auto-encoders are a type of neural network that can learn complex representations of the data and are commonly used for anomaly detection. In this work we propose a novel multi-class algorithm which consists of an ensemble of auto-encoders where each auto-encoder is associated with a unique class. We compared the proposed approach with other state-of-the-art approaches in the context of human activity recognition. Experimental results show that ensembles of auto-encoders can be efficient, robust and competitive. Moreover, this modular classifier structure allows for more flexible models. For example, the extension of the number of classes, by the inclusion of new auto-encoders, without the necessity to retrain the whole model. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http:// creativecommons.org/licenses/by/4.0/).

Abstract
Forecasts of the effort or delivery date can play an important role in managing software projects, but the estimates provided by development teams are often inaccurate and time-consuming to produce. This is not surprising given the uncertainty that underlies this activity. This work studies the use of Monte Carlo simulations for generating forecasts based on project historical data. We have designed and run experiments comparing these forecasts against what happened in practice and to estimates provided by developers, when available. Comparisons were made based on the mean magnitude of relative error (MMRE). We did also analyze how the forecasting accuracy varies with the amount of work to be forecasted and the amount of historical data used. To minimize the requirements on input data, delivery date forecasts for a set of user stories were computed based on takt time of past stories (time elapsed between the completion of consecutive stories); effort forecasts were computed based on full-time equivalent (FTE) hours allocated to the implementation of past stories. The MMRE of delivery date forecasting was 32% in a set of 10 runs (for different projects) of Monte Carlo simulation based on takt time. The MMRE of effort forecasting was 20% in a set of 5 runs of Monte Carlo simulation based on FTE allocation, much smaller than the MMRE of 134% of developers' estimates. A better forecasting accuracy was obtained when the number of historical data points was 20 or higher. These results suggest that Monte Carlo simulations may be used in practice for delivery date and effort forecasting in agile projects, after a few initial sprints. © 2021 ACM.