Abstract

Abstract
Falls are very rare and extremely difficult to acquire in free living conditions. Due to this, most of prior work on fall detection has focused on simulated datasets acquired in scenarios that mimic the real-world context, however, the validation of systems trained with simulated falls remains unclear. This work presents a transfer learning approach for combining a dataset of simulated falls and non-falls, obtained from young volunteers, with the real-world FARSEEING dataset, in order to train a set of supervised classifiers for discriminating between falls and non-falls events. The objective is to analyze if a combination of simulated and real falls could enrich the model. In the real-world, falls are a sporadic event, which results in imbalanced datasets. In this work, several methods for imbalance learning were employed: SMOTE, Balance Cascade and Ranking models. The Balance Cascade obtained less misclassifications in the validation set.There was an improvement when mixing the real falls and simulated non-falls compared to the case when only simulated falls were used for training. When testing with a mixed set with real falls and simulated non-falls, it is even more important to train with a mixed set. Moreover, it was possible to onclude that a model trained with simulated falls generalize better when tested with real falls, than the opposite. The overall accuracy obtained for the combination of different datasets were above 95 %. © 2018 IEEE.

Abstract
The economic impact of fraud is wide and fraud can be a critical problem when the prevention procedures are not robust. In this paper we create a model to detect fraudulent transactions, and then use a classification algorithm to assess if the agent is fraud prone or not. The model (BOND) is based on the analytics of an economic network of agents of three types: individuals, businesses and financial intermediaries. From the dataset of transactions, a sliding window of rows previously aggregated per agent has been used and machine learning (classification) algorithms have been applied. Results show that it is possible to predict the behavior of agents, based on previous transactions. © 2018, Springer International Publishing AG, part of Springer Nature.

Abstract
Demand response (DR) is one of the most cost-effective elements of residential and small industrial building for the purpose of reducing the cost of energy. Today with broadening of the smart grid, electricity market and especially smart home, using DR can reduce cost and even make profits for consumers. On the other hand, utilizing centralized controls and have bidirectional communications Bi-directional communication between DR aggregators and consumers make many problems such as scalability and privacy violation. In this chapter, we propose a multi-agent method based on a Q-learning algorithm Q-learning algorithm for decentralized control of DR. Q-learning is a model-free reinforcement learning Reinforcement learning technique and a simple way for agents to learn how to act optimally in controlled Markovian domains. With this method, each consumer adapts its bidding and buying strategy over time according to the market outcomes. We consider energy supply for consumers such as small-scale renewable energy generators. We compare the result of the proposed method with a centralized aggregator-based approach that shows the effectiveness of the proposed decentralized DR market Decentralized DR market. © Springer International Publishing AG, part of Springer Nature 2018.

Abstract
Ordinal arrangement of objects is a common property in biomedical images. Traditional methods to deal with semantic image segmentation in this setting are ad-hoc and application specific. In this paper, we propose ordinal-aware deep learning architectures for image segmentation that enforce pixelwise consistency by construction. We validated the proposed architectures on several real-life biomedical datasets and achieved competitive results in all cases. © 2018 IEEE.

Abstract
Service applications are increasingly being deployed in virtualized environments, such as virtual machines (VMs) as a means to provide elasticity and to allow fast recovery from failures. The recent trend is now to deploy applications in containers (e.g., Docker or RKT containers), which allow, among many other benefits, to further reduce recovery time, since containers are much more lightweight than VMs. Although several performance benchmarks exist for web services (e.g., TPC-App and SPEC SPECjEnterprise2010) or even virtualized environments (e.g., SPEC Cloud IaaS 2016, TPCx-V), understanding the behavior of containerized services in the presence of faults has been generally disregarded. This paper proposes an experimental approach for evaluating the performance of containerized services in presence of operator faults. The approach is based on the injection of a simple set of operator faults targeting the containers and middleware. Results show noticeable differences regarding the impact of operator faults in Docker and RKT, with the latter one allowing for faster recovery, despite showing the lowest throughput.