Examinando por Autor "Onieva Caracuel, Enrique"
Mostrando 1 - 10 de 10
Resultados por página
Opciones de ordenación
Ítem An analysis of heuristic metrics for classifier ensemble pruning based on ordered aggregation(Elsevier Ltd, 2022-04) Elsayed, Amgad Monir Mohamed ; Onieva Caracuel, Enrique; Woźniak, Michał; Martínez Muñoz, GonzaloClassifier ensemble pruning is a strategy through which a subensemble can be identified via optimizing a predefined performance criterion. Choosing the optimum or suboptimum subensemble decreases the initial ensemble size and increases its predictive performance. In this article, a set of heuristic metrics will be analyzed to guide the pruning process. The analyzed metrics are based on modifying the order of the classifiers in the bagging algorithm, with selecting the first set in the queue. Some of these criteria include general accuracy, the complementarity of decisions, ensemble diversity, the margin of samples, minimum redundancy, discriminant classifiers, and margin hybrid diversity. The efficacy of those metrics is affected by the original ensemble size, the required subensemble size, the kind of individual classifiers, and the number of classes. While the efficiency is measured in terms of the computational cost and the memory space requirements. The performance of those metrics is assessed over fifteen binary and fifteen multiclass benchmark classification tasks, respectively. In addition, the behavior of those metrics against randomness is measured in terms of the distribution of their accuracy around the median. Results show that ordered aggregation is an efficient strategy to generate subensembles that improve both predictive performance as well as computational and memory complexities of the whole bagging ensemble.Ítem Genetic optimised serial hierarchical fuzzy classifier for breast cancer diagnosis(Inderscience Publishers, 2020) Zhang, Xiao; Onieva Caracuel, Enrique; Perallos Ruiz, Asier; Osaba, EnekoAccurate early-stage medical diagnosis of breast cancer can improve the survival rates and fuzzy rule-base system (FRBS) has been a promising classification system to detect breast cancer. However, the existing classification systems involves large number of input variables for training and produces a large number of fuzzy rules, which lead to high complexity and barely acceptable accuracy. In this paper, we present a genetic optimised serial hierarchical FRBS, which incorporates lateral tuning of membership functions and optimisation of the rule base. The serial hierarchical structure of FRBS allows selecting and ranking the input variables, which reduces the system complexity and distinguish the importance of attributes in datasets. We conduct an experimental study on Original Wisconsin Breast Cancer Database and Wisconsin Breast Cancer Diagnostic Database from UCI Machine Learning Repository, and show that the proposed system can classify breast cancer accurately and efficiently.Ítem A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data(Elsevier Ltd, 2020-03) Bogaerts, Toon; Masegosa Arredondo, Antonio David; Angarita Zapata, Juan S.; Onieva Caracuel, Enrique; Hellinckx, PeterTraffic forecasting is an important research area in Intelligent Transportation Systems that is focused on anticipating traffic in order to mitigate congestion. In this work we propose a deep neural network that simultaneously extracts the spatial features of traffic, using graph convolution, and its temporal features by means of Long Short Term Memory (LSTM) cells to make both short-term and long-term predictions. The model is trained and tested using sparse trajectory (GPS) data coming from the ride-hailing service of DiDi in the cities of Xi'an and Chengdu in China. Besides, presenting the deep neural network, we also propose a data-reduction technique based on temporal correlation to select the most relevant road links to be used as input. Combining the suggested approaches, our model obtains better results compared to high-performance algorithms for traffic forecasting, such as LSTM or the algorithms presented in the TRANSFOR19 forecasting competition. The model is capable of maintaining its performance over different time-horizons from 5 min to up to 4 h with multi-step predictions.Ítem Multi-head CNN–RNN for multi-time series anomaly detection: an industrial case study(Elsevier B.V., 2019-10-21) Canizo, Mikel; Triguero, Isaac; Conde, Ángel; Onieva Caracuel, EnriqueDetecting anomalies in time series data is becoming mainstream in a wide variety of industrial applications in which sensors monitor expensive machinery. The complexity of this task increases when multiple heterogeneous sensors provide information of different nature, scales and frequencies from the same machine. Traditionally, machine learning techniques require a separate data pre-processing before training, which tends to be very time-consuming and often requires domain knowledge. Recent deep learning approaches have shown to perform well on raw time series data, eliminating the need for pre-processing. In this work, we propose a deep learning based approach for supervised multi-time series anomaly detection that combines a Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN) in different ways. Unlike other approaches, we use independent CNNs, so-called convolutional heads, to deal with anomaly detection in multi-sensor systems. We address each sensor individually avoiding the need for data pre-processing and allowing for a more tailored architecture for each type of sensor. We refer to this architecture as Multi-head CNN–RNN. The proposed architecture is assessed against a real industrial case study, provided by an industrial partner, where a service elevator is monitored. Within this case study, three type of anomalies are considered: point, context-specific, and collective.The experimental results show that the proposed architecture is suitable for multi-time series anomaly detection as it obtained promising results on the real industrial scenario.Ítem A new Hyper-heuristic based on Adaptive Simulated Annealing and Reinforcement Learning for the Capacitated Electric Vehicle Routing Problem(Elsevier Ltd, 2024-10-15) Rodríguez Esparza, Erick; Masegosa Arredondo, Antonio David; Oliva, Diego; Onieva Caracuel, EnriqueElectric vehicles (EVs) have been adopted in urban areas to reduce environmental pollution and global warming due to the increasing number of freight vehicles. However, there are still deficiencies in routing the trajectories of last-mile logistics that continue to impact social and economic sustainability. For that reason, in this paper, a hyper-heuristic (HH) approach called Hyper-heuristic Adaptive Simulated Annealing with Reinforcement Learning (HHASARL) is proposed. It is composed of a multi-armed bandit method and the self-adaptive Simulated Annealing (SA) metaheuristic algorithm for solving the problem called Capacitated Electric Vehicle Routing Problem (CEVRP). Due to the limited number of charging stations and the travel range of EVs, the EVs must require battery recharging moments in advance and reduce travel times and costs. The implementation of the HH improves multiple minimum best-known solutions and obtains the best mean values for some high-dimensional instances for the proposed benchmark for the IEEE WCCI2020 competition.Ítem Optimizing road traffic surveillance: a robust hyper-heuristic approach for vehicle segmentation(Institute of Electrical and Electronics Engineers Inc., 2024) Rodríguez Esparza, Erick; Ramos Soto, Oscar; Masegosa Arredondo, Antonio David; Onieva Caracuel, Enrique; Oliva, Diego; Arriandiaga Laresgoiti, Ander; Ghosh, ArkaDue to rising consumer demand and traffic congestion, last-mile logistics is becoming more challenging. To optimize urban distribution networks, digital image processing plays a key role in addressing these challenges through efficient traffic monitoring systems, an essential component of intelligent transportation systems. This paper introduces the Hyper-heuristic Genetic Algorithm based on Thompson Sampling with Diversity (HHGATSD), a novel approach to efficiently solving complex optimization and versatility problems in image segmentation. We evaluate its efficiency and robustness using the IEEE CEC2017 benchmark function set in general optimization problems with 30 and 50 dimensions. HHGATSD's applicability extends beyond optimization to computer vision in traffic management. First, the multilevel thresholding segmentation is performed on images extracted from the Berkeley Segmentation Dataset with minimum cross-entropy as the objective function, and its performance is compared using PSNR, SSIM, and FSIM metrics. Following that, the proposed methodology addresses the task of vehicle segmentation in traffic camera videos, reaffirming HHGATSD's effectiveness, adaptability, and consistency by consistently outperforming alternative segmentation methods found in the state-of-the-art. The results of comprehensive experiments, validated by statistical and non-parametric analyses, show that the proposed hyper-heuristic and methodology produce accurate and consistent segmentations for road traffic surveillance compared to the other methods in the literatureÍtem Portfolio construction using explainable reinforcement learning(John Wiley and Sons Inc, 2024-11) Cortés González, Daniel; Onieva Caracuel, Enrique; Pastor López, Iker; Trinchera, Laura; Wu, JianWhile machine learning's role in financial trading has advanced considerably, algorithmic transparency and explainability challenges still exist. This research enriches prior studies focused on high-frequency financial data prediction by introducing an explainable reinforcement learning model for portfolio management. This model transcends basic asset prediction, formulating concrete, actionable trading strategies. The methodology is applied in a custom trading environment mimicking the CAC-40 index's financial conditions, allowing the model to adapt dynamically to market changes based on iterative learning from historical data. Empirical findings reveal that the model outperforms an equally weighted portfolio in out-of-sample tests. The study offers a dual contribution: it elevates algorithmic planning while significantly boosting transparency and interpretability in financial machine learning. This approach tackles the enduring ‘black-box’ issue and provides a holistic, transparent framework for managing investment portfolios.Ítem Selective ensemble of classifiers trained on selective samples(Elsevier B.V., 2022-04-14) Elsayed, Amgad Monir Mohamed ; Onieva Caracuel, Enrique; Woźniak, MichałClassifier ensembles are characterized by the high quality of classification, thanks to their generalizing ability. Most existing ensemble algorithms use all learning samples to learn the base classifiers that may negatively impact the ensemble's diversity. Also, the existing ensemble pruning algorithms often return suboptimal solutions that are biased by the selection criteria. In this work, we present a proposal to alleviate these drawbacks. We employ an instance selection method to query a reduced training set that reduces both the space complexity of the formed ensemble members and the time complexity to classify an instance. Additionally, we propose a guided search-based pruning schema that perfectly explores large-size ensembles and brings on a near-optimal subensemble with less computational requirements in reduced memory space and improved prediction time. We show experimentally how the proposed method could be an alternative to large-size ensembles. We demonstrate how to form less-complex, small-size, and high-accurate ensembles through our proposal. Experiments on 25 datasets show that the proposed method can produce effective ensembles better than Random Forest and baseline classifier pruning methods. Moreover, our proposition is comparable with the Extreme Gradient Boosting Algorithm in terms of accuracy.Ítem Training set selection and swarm intelligence for enhanced integration in multiple classifier systems(Elsevier Ltd, 2020-10) Elsayed, Amgad Monir Mohamed ; Onieva Caracuel, Enrique; Woźniak, MichałMultiple classifier systems (MCSs) constitute one of the most competitive paradigms for obtaining more accurate predictions in the field of machine learning. Systems of this type should be designed efficiently in all of their stages, from data preprocessing to multioutput decision fusion. In this article, we present a framework for utilizing the power of instance selection methods and the search capabilities of swarm intelligence to train learning models and to aggregate their decisions. The process consists of three steps: First, the essence of the complete training data set is captured in a reduced set via the application of intelligent data sampling. Second, the reduced set is used to train a group of heterogeneous classifiers using bagging and distance-based feature sampling. Finally, swarm intelligence techniques are applied to identify a pattern among multiple decisions to enhance the fusion process by assigning class-specific weights for each classifier. The proposed methodology yielded competitive results in experiments that were conducted on 25 benchmark datasets. The Matthews correlation coefficient (MCC) is regarded as the objective to be maximized by various nature-inspired metaheuristics, which include the moth-flame optimization algorithm (MFO), the grey wolf optimizer (GWO) and the whale optimization algorithm (WOA).Ítem A variable neighbourhood search for minimization of operation times through warehouse layout optimization(Oxford University Press, 2024-08) Díaz, Jon; Rodriguez, Haizea; Fajardo Calderín, Jenny; Angulo Martínez, Ignacio; Onieva Caracuel, EnriqueFor companies involved in the supply chain, proper warehousing management is crucial. Warehouse layout arrangement and operation play a critical role in a company’s ability to maintain and improve its competitiveness. Reducing costs and increasing efficiency are two of the most crucial warehousing goals. Deciding on the best warehouse layout is a remarkable optimization problem. This paper uses an optimization method to set bin allocations within an automated warehouse with particular characteristics. The warehouse’s initial layout and the automated platforms limit the search and define the time required to move goods within the warehouse. With the help of historical data and the definition of the time needed to move goods, a mathematical model of warehouse operation was created. An optimization procedure based on the well-known Variable Neighbourhood Search algorithm is defined and applied to the problem. Experimental results demonstrate increments in the efficiency of warehousing operations.