Enrique A. de la Cal

A soft computing method for detecting lifetime building thermal insulation failures

The detection of thermal insulation failures in buildings in operation responds to the challenge of improving building energy efficiency. This multidisciplinary study presents a novel four-step soft computing knowledge identification model called IKBIS to perform thermal insulation failure detection. It proposes the use of Exploratory Projection Pursuit methods to study the relation between input and output variables and data dimensionality reduction. It also applies system identification theory and neural networks for modeling the thermal dynamics of the building. Finally, the novel model is used to predict dynamic thermal biases, and two real cases of study as part of its empirical validation.

A fuzzy logic based efficient energy saving approach for domestic heating systems

This paper focuses on the designing of an energy saving method for a domestic heating system based on electrical heaters. A multi-agent system architecture with two fuzzy rule based systems has been used: a fuzzy model, to estimate the energy requirements and a fuzzy controller, to distribute the energy to all of the installed heaters. The aim is to reduce the energy spent for heating the house while maintaining the predefined comfort level. The proposal has proved valid in realistic simulations, although some revisions must be be carried out prior to integrating it into a microcontroller hardware. The real prototype must also be validated in real situations. This system is to be included in the local companys product catalogue.

Generalized Models for the Classification of Abnormal Movements in Daily Life and its Applicability to Epilepsy Convulsion Recognition

The identification and the modeling of epilepsy convulsions during everyday life using wearable devices would enhance patient anamnesis and monitoring. The psychology of the epilepsy patient penalizes the use of user-driven modeling, which means that the probability of identifying convulsions is driven through generalized models. Focusing on clonic convulsions, this pre-clinical study proposes a method for generating a type of model that can evaluate the generalization capabilities. A realistic experimentation with healthy participants is performed, each with a single 3D accelerometer placed on the most affected wrist. Unlike similar studies reported in the literature, this proposal makes use of [Formula: see text] cross-validation scheme, in order to evaluate the generalization capabilities of the models. Event-based error measurements are proposed instead of classification-error measurements, to evaluate the generalization capabilities of the model, and Fuzzy Systems are proposed as the generalization modeling technique. Using this method, the experimentation compares the most common solutions in the literature, such as Support Vector Machines, [Formula: see text]-Nearest Neighbors, Decision Trees and Fuzzy Systems. The event-based error measurement system records the results, penalizing those models that raise false alarms. The results showed the good generalization capabilities of Fuzzy Systems.

Minimizing Energy Consumption in Heating Systems under Uncertainty

Energy saving systems are needed to reduce the energy taxes, so the electric energy remains balanced. In Spain, a local company that produces electric heaters needs an energy saving device to be integrated with the heaters. The building regulations in Spain introduce five different climate zones, so such device must meet all of them. In previous works the uncertainty in the process was shown, and the different configurations that must be included to accomplish the Spanish regulations were established. It was proven that a hybrid artificial intelligent systems (HAIS) could afford the energy saving reasonably, even though some improvements must be introduced. This work proposes a modified solution to relax the hardware restrictions and to solve the lack of distribution observed. The modified energy saving HAIS is detailed and compared with that obtained in previous works.

Self-Organizing Symbolic Learned Rules

In this paper we present a self-organizing process for rules obtained from a machine learning system. The resulting map can be interpreted back into the symbolic field in an attempt to make the logical representation of the original rules reflect the relationships codified by map distances. Thus, we improve the quality of the starting set of rules both in classification accuracy and in conceptual clarity.

Improving energy efficiency in buildings using machine intelligence

Improving the detection of thermal insulation in buildings -which includes the development of models for heating and ventilation processes and fabric gain - could significantly increase building energy efficiency and substantially contribute to reductions in energy consumption and in the carbon footprints of domestic heating systems. Thermal insulation standards are now contractual obligations in new buildings, although poor energy efficiency is often a defining characteristic of buildings built before the introduction of those standards. Lighting, occupancy, set point temperature profiles, air conditioning and ventilation services all increase the complexity of measuring insulation efficiency. The identification of thermal insulation failure can help to reduce energy consumption in heating systems. Conventional methods can be greatly improved through the application of hybridized machine learning techniques to detect thermal insulation failures when a building is in operation. A three-step procedure is proposed in this paper that begins by considering the local building and heating system regulations as well as the specific features of the climate zone. Firstly, the dynamic thermal performance of different variables is specifically modelled, for each building type and climate zone. Secondly, Cooperative Maximum-Likelihood Hebbian Learning is used to extract the relevant features. Finally, neural projections and identification techniques are applied, in order to detect fluctuations in room temperatures and, in consequence, thermal insulation failures. The reliability of the proposed method is validated in three winter zone C cities in Spain. Although a great deal of further research remains to be done in this field, the proposed system is expected to outperform conventional methods described in Spanish building codes that are used to calculate energetic profiles in domestic and residential buildings.

Analyzing Accelerometer Data for Epilepsy Episode Recognition

Epilepsy is one of the main neurological disorders with high impact in the patient’s everyday life. An incorrect treatment or a lack in monitoring might produce cognitive damage and depression. Therefore, developing a wearable device for epilepsy monitoring would eventually complete the anamnesis, enhancing the medical staff diagnosing and treatment setting. This study shows the preliminary results in epilepsy onset recognition based on wearable tri-axial accelerometers and simple fuzzy set learnt using genetic algorithms. A complete experimentation for learning the fuzzy set is detailed. According to the obtained results, some generalized feasible solutions are discussed. Results show a very interesting researching area that might be easily transferred to embedded devices and online health care systems.

Optimising operational costs using Soft Computing techniques

A Manufacturing Execution System MES consists of high-cost, large-scale, multi-task software systems. Companies and factories apply these complex applications for the purposes of production management to monitor and track all aspects of factory-based manufacturing processes. Nevertheless, companies seek to control the production process with even greater rigour. Improvements associated with an MES involve the identification of new knowledge within the data set and its integration in the system, which implies a step forward to Business Process Management BPM systems, from which the users of an MES may gain relevant information, not only on execution procedures but to decide on the best scheduled arrangement. This work studies the data gathered from a real MES that is used in a plastic products factory. Several Artificial Intelligence and Soft Computing modelling methods based on fuzzy rules assist in the calculation of manufacturing costs and decisions over shift work rotas: two decisions that are of relevance for the improvement of the execution system. The results of the study, which identify the most suitable models to facilitate execution-related decision-making, are presented and discussed.

Machine Learning Usefulness Relies on Accuracy and Self-Maintenance

A new machine learning system, INNER, is presented in this paper. The system starts out from a collection of training examples; some of them are inflated generalizing their description so as to obtain a first draft of classification rules. An optimization stage, borrowed from our previous system, Fan, is then applied to return the final set of rules. The main goal of Inner, besides its high level of accuracy, is its ability for self-maintenance. To close the paper, we present a number of different experiments carried` out with INNER to illustrate how good the performance and stability of the system is.

Analysing the low quality of the data in lighting control systems

Energy efficiency represents one of the main challenges in the engineering field, i.e., by means of decreasing the energy consumption due to a better design minimising the energy losses This is particularly true in real world processes in the industry or in business, where the elements involved generate data full of noise and biases In other fields as lighting control systems, the emergence of new technologies, as the Ambient Intelligence can be, degrades the quality data introducing linguistic values The presence of low quality data in Lighting Control Systems is introduced through an experimentation step, in order to realise the improvement in energy efficiency that its of managing could afford In this contribution we propose, as a future work, the use of the novel genetic fuzzy system approach to obtain classifiers and models able to deal with the above mentioned problems.