Enrique Sodupe-Ortega

Improving Hotel Room Demand Forecasting with a Hybrid GA-SVR Methodology Based on Skewed Data Transformation, Feature Selection and Parsimony Tuning

This paper presents a hybrid methodology, in which a KDD-scheme is optimized to build accurate parsimonious models. The methodology tries to find the best model by using genetic algorithms to optimize a KDD scheme formed with the following stages: feature selection, transformation of the skewed input and output data, parameter tuning, and parsimonious model selection. In this work, experiments demonstrated that optimization of these steps significantly improved the model generalization capabilities in some UCI databases. Finally, this methodology was applied to create room demand parsimonious models using booking databases from a hotel located in a region of Northern Spain. Results proved that the proposed method was useful to create models with higher generalization capacity and lower complexity to those obtained with classical KDD processes.

Evaluation of a novel GA-based methodology for model structure selection: The GA-PARSIMONY

Abstract Most proposed metaheuristics for feature selection and model parameter optimization are based on a two-termed L o s s + P e n a l t y function. Their main drawback is the need of a manual set of the parameter that balances between the loss and the penalty term. In this paper, a novel methodology referred as the GA-PARSIMONY and specifically designed to overcome this issue is evaluated in detail in thirteen public databases with five regression techniques. It is a GA-based meta-heuristic that splits the classic two-termed minimization functions by making two consecutive ranks of individuals. The first rank is based solely on the generalization error, while the second (named ReRank) is based on the complexity of the models, giving a special weight to the complexity entailed by large number of inputs. For each database, models with lowest testing RMSE and without statistical difference among them were referred as winner models. Within this group, the number of features selected was below 50%, which proves an optimal balance between error minimization and parsimony. Particularly, the most complex algorithms (MLP and SVR) were mostly selected in the group of winner models, while using around40–45% of the available attributes. The most basic IBk, ridge regression (LIN) and M5P were only classified as winner models in the simpler databases, but using less number of features in those cases (up to a 20–25% of the initial inputs).

Optimization of Solar Integration in Combined Cycle Gas Turbines (ISCC)

The estimation of the optimum number of loops to operate an integrated solar combined cycle gas turbine (ISCC) represents a complex problem and a very time demanding operation, which must be calculated in near-real time and as a result, it is hardly possible to be solved with regular ISCC production models. This problem is addressed evaluating different soft computing techniques, concluding that the BAG-REPT metamodel fits best generating MAE test of 4.19% and RMSE test of 8.75%. This model presents much lower time than regular ISCC production models and might be used as a decision tool for feasibility assessments and also in pre-design stages of new ISCC projects.

Towards Improving the Applicability of Non-parametric Multiple Comparisons to Select the Best Soft Computing Models in Rubber Extrusion Industry

In this paper we propose different strategies to apply non-parametric multiple comparisons in industrial environments. These techniques have been widely used in theoretical studies and research to evaluate the performance of models, but they are still far from being implemented in real applications. So, we develop three new automatized strategies to ease the selection of soft computing models using data from industrial processes. A rubber products manufacturer was selected as a real industry to conduct the experiments. More specifically, we focus our study on the mixing phase. The rheology curve of rubber compounds is predicted to anticipate possible failures in the vulcanization process. More accurate predictions are needed to provide set points to enhance the control the process, particularly working in this rapidly changing environment. Selecting among a wide range of models increases the probability of achieving the best predictions. The main goal of our methodology is therefore to automatize the selection process when many choices are availables. The models based on soft computing used to validate our proposal are neural networks and support vector machines and also other alternatives such as linear and rule-based models.

Accurate Calibration in Multi-Material 3D Bioprinting for Tissue Engineering

Most of the studies in three-dimensional (3D) bioprinting have been traditionally based on printing a single bioink. Addressing the complexity of organ and tissue engineering, however, will require combining multiple building and sacrificial biomaterials and several cells types in a single biofabrication session. This is a significant challenge, and, to tackle that, we must focus on the complex relationships between the printing parameters and the print resolution. In this paper, we study the influence of the main parameters driven multi-material 3D bioprinting and we present a method to calibrate these systems and control the print resolution accurately. Firstly, poloxamer hydrogels were extruded using a desktop 3D printer modified to incorporate four microextrusion-based bioprinting (MEBB) printheads. The printed hydrogels provided us the particular range of printing parameters (mainly printing pressure, deposition speed, and nozzle z-offset) to assure the correct calibration of the multi-material 3D bioprinter. Using the printheads, we demonstrated the excellent performance of the calibrated system extruding different fluorescent bioinks. Representative multi-material structures were printed in both poloxamer and cell-laden gelatin-alginate bioinks in a single session corroborating the capabilities of our system and the calibration method. Cell viability was not significantly affected by any of the changes proposed. We conclude that our proposal has enormous potential to help with advancing in the creation of complex 3D constructs and vascular networks for tissue engineering.

Makerspaces in Higher Education

According to the CDIO (Conceive-Design-Implement-Operate) Syllabus, apart from technical knowledge, labour markets are demanding engineers with personal, interpersonal and system building skills. The current educational system, however, is based on teaching theoretical concepts rather than on practical activities. Makerspaces could become a bridge between universities and industry, particularly in STEM (Science, Technology, Engineering and Math) carriers. Makerspaces, also known as hackerspaces, hack labs and fab labs, are open-access spaces where a community shares tools, machines and knowledge in order to implement an idea. This communication reviews the makerspaces at the world’s top 10 engineering universities and three of the most recognized in Spain. The qualitative data was collected through the universities’ websites. We observed that most of the reviewed universities have outstanding makerspaces for engineering students, generally open to the entire university community. In Spain, the ‘Maker UPV’ was found exceptionally successful in activities and projects performed in spite of their lack of material resources. Lastly, the authors describe their experience implementing a campus makerspace at the University of La Rioja, sharing interesting information about the organization, budget, funding and activities.

Methodology based on micro-projects in DIY desktop machines for educational purposes in engineering degrees

The 21 st century university has the big educational challenge of how to encourage “a will to learn” in students living in a world saturated with a huge amount of information and distractions. A needed step to keep students motivated is to update their learning environments. Herein we present a proposal with a methodology based on microprojects in DIY desktop machines (MicroP-DIY-DkM). The main idea is to consolidate students’ theoretical background using motivating microprojects in which foreign entities act as petitioners. The students will also receive a broad view of current state of manufacturing technologies. At the same time, English language and Information and Communication Technologies skills can be promoted by our methodology. We provide information about the implementation of several examples of these microprojects, which were applied in the technical subject ‘Manufacturing Technology’. The use of open source DIY-DkM offers students the possibility to understand essential principles of industrial technologies and processes. According to our surveys, students’ scores and success rate results, the methodology proposed demonstrated its convenience to be applied in technical subjects. Students showed greater motivation level and success rate than previous years using conventional methods. Limitation of the proposal and possible means of improvement are also included.

On-line Soft Sensor Based on Regression Models and Feature Selection Techniques for Predicting Rubber Properties in Mixture Processes

The paper deals with the complexity of rubber mixture process. The main issue is to develop well performing on-line soft sensors to monitoring rheological rubber properties. When mixing all raw materials, continual discards of defective materials with high costs associated can be caused by unexpected process variations and incorrect operating set points. Therefore, accurate on-line rubber properties predictions are crucial to obtain higher quality rubber bands. An on-line soft sensor based on a wrapper scheme is proposed to this end. The wrapper is mainly composed of a regression model and a feature selection routine. This routine is designed to find those optimal process variable subsets (input variables) that explain better the rubber properties (output variables). A backwards selection strategy is the basis of the feature selection routine. After an iterative process, the subset finally selected as inputs for the regression model was the one that predicted better the rubber properties. The proposed approach showed several advantages. First, wider and deeper knowledge of the industrial process was clearly achieved. In addition, the final on-line soft sensor was able to establish clear relations between the independent process variables and some rheological parameters of the rubber. A parsimony model was achieved thanks to a combination of a linear model and a selection feature routine that provided these good results.

An Overall Performance Comparative of GA-PARSIMONY Methodology with Regression Algorithms

This paper presents a performance comparative of GA-PAR SIMONY methodology with five well-known regression algorithms and with different genetic algorithm (GA) configurations. This approach is mainly based on combining GA and feature selection (FS) during model tuning process to achieve better overall parsimonious models that assure good generalization capacities. For this purpose, individuals, already sorted by their fitness function, are rearranged in each iteration depending on the model complexity. The main objective is to analyze the overall model performance achieve with this methodology for each regression algorithm against different real databases and varying the GA setting parameters. Our preliminary results show that two algorithms, multilayer perceptron (MLP) with the Broyden-Fletcher-Goldfarb-Shanno training method and support vector machines for regression (SVR) with radial basis function kernel, performing better with similar features reduction when database has low number of input attributes (\(\lesssim32\)) and it has been used low GA population sizes.

Soft Computing Metamodels for the Failure Prediction of T-stub Bolted Connections

In structural and mechanical fields, there is a growing trend to replace expensive numerical simulations with more cost-effective approximations. In this context, the use of metamodels represents an attractive option. Without significant loss of accuracy, metamodelling techniques can drastically reduce the computational burden required by simulations. This paper proposes a method for developing soft computing metamodels to predict the failure of steel bolted connections. The setting parameters of the metamodels are tuned by an optimisation based on genetic algorithms during the training process. The method also includes the selection of the most relevant input features to reduce the models’ complexity. In total, two well-known metamodelling techniques are evaluated to compare their performances on accuracy and parsimony. This case studies the T-stub bolted connection, which allows us to validate the proposed models. The results show soft computing’s metamodelling capacity to accurately predict the T-stub response, while reducing the number of variables and with negligible computation cost.