Zamora Izquierdo, Miguel Ángel

Person:
Zamora Izquierdo, Miguel Ángel

Name

Zamora Izquierdo, Miguel Ángel

publication.page.department

Universidad de Murcia. Departamento de Ingeniería de la Informacióny las Comunicaciones

Full item page

Search Results

Now showing 1 - 5 of 5

Open Access
Feature selection for blood glucose level prediction in type 1 Diabetes Mellitus by using the Sequential Input Selection Algorithm (SISAL)
(MDPI, 2019-09-14) Rodríguez Rodríguez, Ignacio ; Rodríguez, José Víctor; González Vidal, Aurora; Zamora Izquierdo, Miguel Ángel; Ingeniería de la Información y las Comunicaciones; Facultades de la UMU::Facultad de Informática
Feature selection is a primary exercise to tackle any forecasting task. Machine learning algorithms used to predict any variable can improve their performance by lessening their computational effort with a proper dataset. Anticipating future glycemia in type 1 diabetes mellitus (DM1) patients provides a baseline in its management, and in this task, we need to carefully select data, especially now, when novel wearable devices offer more and more information. In this paper, a complete characterization of 25 diabetic people has been carried out, registering innovative variables like sleep, schedule, or heart rate in addition to other well-known ones like insulin, meal, and exercise. With this ground-breaking data compilation, we present a study of these features using the Sequential Input Selection Algorithm (SISAL), which is specially prepared for time series data. The results rank features according to their importance, regarding their relevance in blood glucose level prediction as well as indicating the most influential past values to be taken into account and distinguishing features with person-dependent behavior from others with a common performance in any patient. These ideas can be used as strategies to select data for predicting glycemia depending on the availability of computational power, required speed, or required accuracy. In conclusion, this paper tries to analyze if there exists symmetry among the different features that can affect blood glucose levels, that is, if their behavior is symmetric in terms of influence in glycemia.
Open Access
Transfer and deep learning models for daily reference evapotranspiration estimation and forecasting in Spain from local to national scale
(Elsevier, 2025-03-12) Ye, Yu; Zamora Izquierdo, Miguel Ángel; Skarmeta Gómez, Antonio; González Vidal, Aurora; Ingeniería de la Información y las Comunicaciones; Facultades de la UMU::Facultad de Informática
Accurate estimation and forecasting of Reference Evapotranspiration () is critical for almost all agricultural activities and water resource management. However, the most commonly used Penman-Monteith model (FAO56-PM) requires a large amount of input data and it is difficult to compute for general users. Machine Learning (ML) techniques can be used to address this shortcoming. Nevertheless, most studies are site-specific and lack generalizability. This study compares standard ML and Deep Learning (DL) algorithms for estimating and forecasting daily at different spatial scales in Spain. While Transfer Learning (TL) is a well-established ML technique, its application in computation remains largely unexplored. We applied TL in a novel approach to retrain DL models, enabling adaptation to diverse local climatic conditions, which is particularly important in this domain. All possible combinations of FAO56-PM inputs were evaluated. The results showed that with three or more climatic variables, the TL process can consistently reduce errors by using an appropriate amount of new data to retrain the models. In estimation, with 20% (120 days) of new data, TL models can provide the same performance as if they were trained with local data, both regionally and nationally (improvement of MAE from 26.4% to 99.5%). During forecasting, we used predicted weather data as input, and despite inherent biases in some variables, the TL models successfully adapted using 9-36 days of new data, significantly improving predictive performance (reducing MAE from -1.1% to 134.3%). Thus, the TL process is highly recommended as a promising methodology for increasing the generalization capability of DL models in both daily estimation and forecasting under diverse climatic conditions with limited local data.
Open Access
Nomograms for de-complexing the dimensioning of off-grid PV systems
(Elsevier Ltd., 2020-07-28) Ramallo González, Alfonso Pablo; Loonen, Roel; Tomat, Valentina; Zamora Izquierdo, Miguel Ángel; Surugin, Dmitry; Hensen, Jan; Ingeniería de la Información y las Comunicaciones; Facultad de Informática
There is a need to move the building stock towards a more energy self-sustained and self-reliant one. In most countries, photovoltaic installations have great potential to make dwellings energy-autonomous. To do so, the PV installation has to be coupled with a battery system capable of providing energy for periods no solar resource. Considering how many systems will need to be dimensioned and installed to achieve the objectives of reducing the carbon footprint of the built environment, sizing tools will have to be used by installers and other blue-collar specialists. This paper shows a methodology that uses modelling and simulation for the creation of dimensioning charts (nomograms), that could be used for sizing PVsystems. The method has been tested in two locations and it seems to be accurate and robust, despite uncertainty in demand profiles. Furthermore, a survey was conducted to evaluate users’ response to the method. The results show that, although the tool may not be appealing to certain users, it achieves its goal fully: all participants managed to size the installation correctly in all cases, regardless of their level of training or expertise.
Open Access
Commissioning of the Controlled and Automatized Testing Facility for Human Behavior and Control (CASITA)
(MDPI, 2018-08-27) Rodríguez Rodríguez, Ignacio; González Vidal, Aurora; Ramallo González, Alfonso Pablo; Zamora Izquierdo, Miguel Ángel; Ingeniería de la Información y las Comunicaciones; Facultades de la UMU::Facultad de Informática
Human behavior is one of the most challenging aspects in the understanding of building physics. The need to evaluate it requires controlled environments and facilities in which researchers can test their methods. In this paper, we present the commissioning of the Controlled and Automatized Testing Facility for Human Behavior (CASITA). This is a controlled space emulation of an office or flat, with more than 20 environmental sensors, 5 electrical meters, and 10 actuators. Our contribution shown in this paper is the development of an infrastructure-Artificial Intelligence (AI) model pair that is perfectly integrated for the study of a variety of human energy use aspects. This facility will help to perform studies about human behavior in a controlled space. To verify this, we have tested this emulation for 60 days, in which equipment was turned on and off, the settings of the conditioning system were modified remotely, and lighting operation was similar to that in real behaviors. This period of commissioning generated 74.4 GB of raw data including high-frequency measurements. This work has shown that CASITA performs beyond expectations and that sensors and actuators could enable research on a variety of disciplines related to building physics and human behavior. Also, we have tested the PROPHET software, which was previously used in other disciplines and found that it could be an excellent complement to CASITA for experiments that require the prediction of several pertinent variables in a given study. Our contribution has also been to proof that this package is an ideal “soft” addition to the infrastructure. A case study forecasting energy consumption has been performed, concluding that the facility and the software PROPHET have a great potential for research and an outstanding accuracy.
Open Access
Applicability of Big Data Techniques to Smart Cities Deployments
(2001-09-16) M. Victoria Moreno; Fernando Terroso-Sáenz; González Vidal, Aurora; Valdés Vela, Mercedes; Skarmeta Gómez, Antonio; Zamora Izquierdo, Miguel Ángel; Victor Chang; Ingeniería de la Información y las Comunicaciones; Facultades de la UMU::Facultad de Informática
This paper presents the main foundations of big data applied to smart cities. A general Internet of Things based architecture is proposed to be applied to different smart cities applications. We describe two scenarios of big data analysis. One of them illustrates some services implemented in the smart campus of the University of Murcia. The second one is focused on a tram service scenario, where thousands of transit-card transactions should be processed. Results obtained from both scenarios show the potential of the applicability of this kind of techniques to provide profitable services of smart cities, such as the management of the energy consumption and comfort in smart buildings, and the detection of travel profiles in smart transport.