Showing papers by "Daniel Rodriguez published in 2016"

Evaluation of estimation models using the Minimum Interval of Equivalence

Abstract: Graphical abstractDisplay Omitted HighlightsDefinition of a new measure for evaluating estimation models.The measure is based on the concept of Equivalence Hypothesis Testing.Application of the measure to estimations by different soft computing methods.Construction of probability intervals for each estimation method.Genetic programming and linear regression provide the best intervals. This article proposes a new measure to compare soft computing methods for software estimation. This new measure is based on the concepts of Equivalence Hypothesis Testing (EHT). Using the ideas of EHT, a dimensionless measure is defined using the Minimum Interval of Equivalence and a random estimation. The dimensionless nature of the metric allows us to compare methods independently of the data samples used.The motivation of the current proposal comes from the biases that other criteria show when applied to the comparison of software estimation methods. In this work, the level of error for comparing the equivalence of methods is set using EHT. Several soft computing methods are compared, including genetic programming, neural networks, regression and model trees, linear regression (ordinary and least mean squares) and instance-based methods. The experimental work has been performed on several publicly available datasets.Given a dataset and an estimation method we compute the upper point of Minimum Interval of Equivalence, MIEu, on the confidence intervals of the errors. Afterwards, the new measure, MIEratio, is calculated as the relative distance of the MIEu to the random estimation.Finally, the data distributions of the MIEratios are analysed by means of probability intervals, showing the viability of this approach. In this experimental work, it can be observed that there is an advantage for the genetic programming and linear regression methods by comparing the values of the intervals.

Integrated Toolset for WSN Application Planning, Development, Commissioning and Maintenance: The WSN-DPCM ARTEMIS-JU Project

Abstract: In this article we present the main results obtained in the ARTEMIS-JU WSN-DPCM project between October 2011 and September 2015. The first objective of the project was the development of an integrated toolset for Wireless sensor networks (WSN) application planning, development, commissioning and maintenance, which aims to support application domain experts, with limited WSN expertise, to efficiently develop WSN applications from planning to lifetime maintenance. The toolset is made of three main tools: one for planning, one for application development and simulation (which can include hardware nodes), and one for network commissioning and lifetime maintenance. The tools are integrated in a single platform which promotes software reuse by automatically selecting suitable library components for application synthesis and the abstraction of the underlying architecture through the use of a middleware layer. The second objective of the project was to test the effectiveness of the toolset for the development of two case studies in different domains, one for detecting the occupancy state of parking lots and one for monitoring air concentration of harmful gasses near an industrial site.

Triaxial Accelerometer Located on the Wrist for Elderly People’s Fall Detection

Abstract: The loss of motor function in the elderly makes this population group prone to accidental falls. Actually, falls are one of the most notable concerns in elder care. Not surprisingly, there are several technical solutions to detect falls, however, none of them has achieved great acceptance. The popularization of smartwatches provides a promising tool to address this problem. In this work, we present a solution that applies machine learning techniques to process the output of a smartwatch accelerometer, being able to detect a fall event with high accuracy. To this end, we simulated the two most common types of falls in elders, gathering acceleration data from the wrist, then applied that data to train two classifiers. The results show high accuracy and robust classifiers able to detect falls.

Designing an ontology-based Zika virus news authoring environment for the semantic web

Abstract: This paper describes the experience of researching and teaching the conceptual and practical basis for the specification, modelling and design of an ontology-based news authoring environment for the Semantic Web, that takes into account the construction and use of an ontology of the Zika disease. Some CMSs are being adapted in order to receive semantic features, such as automatic generations of keywords, semantic annotation and tagging, content reviewing etc. We present here the infrastructure designed to foster research on semantic CMSs as well as semantic web technologies that can be integrated into an ontology-based news authoring environment.

A Low-Volume Weight Training Protocol Reduces Abdominal Fat and Increases Muscle Strength in 12 Weeks

Abstract: Martins AP, Ceschini FL, Battazza R, Rodriguez D, João GA, Bocalini DS, Charro MA, Figueira Junior A. A Low-Volume Weight Training Protocol Reduces Abdominal Fat and Increases Muscle Strength in 12 Weeks. JEPonline 2016;19(1):96-106. This study evaluated the effect of a 12-wk low-volume weight training (WT) program on body composition and neuromotor fitness of WT practitioners. Fifteen men and women (28.2 ± 4.9 yrs old; body weight: 69.2 ± 13.4 kg; height: 170 ± 10 cm; BMI: 23.7 ± 2.7 kg·m-2; with at least 1 yr of WT experience) were evaluated in a WT protocol (3 times·wk-1 for 12 wks). Training sessions included 9 exercises (45o leg press, bench press, trunk curl, stiff-leg deadlift, front pull-downs, adduction machine, lateral raises, triceps extensions, and bicep curls) of 3 sets of 8 reps at 85% (1RM) with 40-sec rest between sets and exercises. Body composition and maximum strength were analyzed with a one-way analysis ANOVA and Scheffe post hoc test (P<0.05). The 12-wk WT protocol slightly decreased body mass (−1.3%) and waist circumference (−2.4%) as skinfolds sum (5.6 cm = Δ% −19.40%) and abdominal fat (−10.31). Increases in lean body mass (3.4%) and lower limbs strength (63.4%) suggest that 12 wks of low-volume WT reduced abdominal fat and increased muscle strength.

Actas de la XVII Conferencia de la Asociación Española para la Inteligencia Artificial

Abstract: The reduction of energy consumption in buildings is one of the goals to improve energy efficiency. One way to achieve energy savings in buildings is to develop intelligent control strategies for heating systems that are able to reduce power consumption without affecting the thermal comfort. An intelligent control system must be able to predict the temperature of the building in order to manage the heating system. In this paper, we present a rule-based model that is able to predict the indoor temperature for different values of k (hours ahead in time). The model has been learned with FRULER, a genetic fuzzy system that generates accurate and simple knowledge bases. Our approach has been validated with real data from a residential college.