Abstract
In different areas of knowledge, phenomena are represented by directional-angular or periodic-data; from wind direction and geographical coordinates to time references like days of the week or months of the calendar. These values are usually represented in a linear scale, and restricted to a given range (e.g. [0,2 pi)), hiding the real nature of this information. Therefore, dealing with directional data requires special methods. So far, the design of classifiers for periodic variables adopts a generative approach based on the usage of the von Mises distribution or variants. Since for non-periodic variables state of the art approaches are based on non-generative methods, it is pertinent to investigate the suitability of other approaches for periodic variables. We propose a discriminative Directional Logistic Regression model able to deal with angular data, which does not make any assumption on the data distribution. Also, we study the expressiveness of this model for any number of features. Finally, we validate our model against the previously proposed directional naive Bayes approach and against a Support Vector Machine with a directional Radial Basis Function kernel with synthetic and real data obtaining competitive results.

Abstract
This paper presents the development framework for an energy management platform that is being developed within the AnyPLACE project. In order to ensure that end-users become active participants in services like demand response, a combined approach is necessary in terms of monitoring, automation, and user interfacing. The success in engaging the end-user, as the centerpiece of the energy management challenge, is vital in taking advantage of a more efficient use of energy, as it is shown in this paper. The proposed framework can be run in a single board computer.

Abstract
It is known that code readability has an impact on software quality. This paper introduces a preliminary list of 33 good practices for code readability that could be taught in object oriented programming courses of informatics programs. In this set are included practices with both positive and negative impact, the latter mainly from bad smells. A survey was made with OOP teachers in order to assess the significance of teaching a set of good practices. The results showed that teachers consider it important to teach the defined set. Such result was statistically significant. Still, the same level of significance was not awarded to all practices. Some additional results are presented.

Abstract
Intraoperative evaluation of the efficacy of Deep Brain Stimulation includes evaluation of the effect on rigidity. A subjective semi-quantitative scale is used, dependent on the examiner perception and experience. A system was proposed previously, aiming to tackle this subjectivity, using quantitative data and providing real-time feedback of the computed rigidity reduction, hence supporting the physician decision. This system comprised of a gyroscope-based motion sensor in a textile band, placed in the patients hand, which communicated its measurements to a laptop. The latter computed a signal descriptor from the angular velocity of the hand during wrist flexion in DBS surgery. The first approach relied on using a general rigidity reduction model, regardless of the initial severity of the symptom. Thus, to enhance the performance of the previously presented system, we aimed to develop models for high and low baseline rigidity, according to the examiner assessment before any stimulation. This would allow a more patient-oriented approach. Additionally, usability was improved by having in situ processing in a smartphone, instead of a computer. Such system has shown to be reliable, presenting an accuracy of 82.0% and a mean error of 3.4%. Relatively to previous results, the performance was similar, further supporting the importance of considering the cogwheel rigidity to better infer about the reduction in rigidity. Overall, we present a simple, wearable, mobile system, suitable for intra-operatory conditions during DBS, supporting a physician in decision-making when setting stimulation parameters.

Abstract
Cloud computing is the latest trend in business for providing software, platforms and services over the Internet. However, a widespread adoption of this paradigm has been hampered by the lack of security mechanisms. In view of this, the aim of this work is to propose a new approach for detecting anomalies in cloud network traffic. The anomaly detection mechanism works on the basis of a Support Vector Machine (SVM). The key requirement for improving the accuracy of the SVM model, in the context of cloud, is to reduce the total amount of data. In light of this, we put forward the Poisson Moving Average predictor which is the core of the feature extraction approach and is able to handle the vast amount of information generated over time. In addition, two case studies are employed to validate the effectiveness of the mechanism on the basis of real datasets. Compared with other approaches, our solution exhibits the best performance in terms of detection and false alarm rates.

Abstract
Nowadays, many companies have migrated their applications and data to the cloud. Among other benefits of this technology, the ability to answer quickly business requirements has been one of the main motivations. Thereby, in cloud environments, resources should be acquired and released automatically and quickly at runtime. This way, to ensure QoS, the major cloud providers emphasize ensuring of availability, CPU instance and cost measure in their SLAs (Service Level Agreements). However, the QoS performance are not completely handled or inappropriately treated in SLAs. Although from the user's point of view, it is considered one of the main QoS parameters. Therefore, the aim of this work consists in development of a solution to efficient query processing on large databases available in the cloud environments. It integrates adaptive re-optimization at query runtime and their costs are based on the SRT (Service Response Time) QoS performance parameter of SLA. Finally, the solution was evaluated in Amazon EC2 cloud infrastructure and the TPC-DS like benchmark was used for generating a database.