Examinando por Autor "Angarita Zapata, Juan S."

Mostrando 1 - 3 de 3
  • Miniatura
    Ítem
    Automated machine learning to support model selection in supervised traffic forecasting
    (Universidad de Deusto, 2020-11-25) Angarita Zapata, Juan S.; Masegosa Arredondo, Antonio David; Facultad de Ingeniería
    Intelligent Transportation Systems announce the production of tons of hardly manageable traffic data that motivate the use of data-driven approaches, with a particular interest in Machine Learning (ML), to analyzing this data. ITS data can be used by different applications such as Traffic Forecasting (TF) schemes. Recently, TF is gaining relevance due to its ability to deal with traffic congestion through forecasting future states of different traffic measures (e.g. travel time). TF poses two main challenges to the ML paradigm. First, traffic data can be collected in multiple formats (e.g. traffic-counting measures, GPS tracks) and under different transportation circumstances (e.g. urban, freeway). These characteristics influence the performance of ML methods, and choosing the most competitive method from a set of candidates brings human effort and time costs. Second, raw traffic data usually needs to be preprocessed before being analyzed. Hence, deciding the most suitable combination of data preprocessing techniques and ML method is a time-consuming task that demands specialized ML knowledge to approach it. Automated Machine Learning (AutoML) arises as a promising approach that addresses the issues mentioned above in problem domains wherein expert ML knowledge is not always an available or affordable asset such as TF. AutoML methods have been broadly used in other areas; however, it has been underexplored in TF. The latter raises the question if general-purpose AutoML guarantees competitive results while reducing the human-time costs of ML in TF. However, current AutoML approaches suffer from issues that can also affect its performance in TF as well as in other ML problems. The optimization process to find competitive pipelines is complicated and computational costly because of the diversity of the search space and the high evaluation cost of the objective function. Alternative learning approaches (e.g. meta-learning) have been designed to try to overcome these issues, but they could not properly work on diverse datasets such as TF. Therefore, this thesis focuses on the development of new AutoML approaches more suited to specific problem domains that can also offer competitive results in TF. We present a new AutoML method for supervised problems, such as TF, with a search strategy based on the construction of ensembles from a portfolio of multiple classifiers. This AutoML mechanism can better adapt to specific problem domains using data preprocessing techniques, ML methods and raw data. The proposed method can lead to better or competitive results in the general-purpose field and TF with respect to the state-of-the-art. This is accomplished by taking advantage of the automated generation of ensembles from a predefined set of ML pipelines. The use of these multiple classifier systems significantly speed up the AutoML process, and it also opens the path towards AutoML frameworks based on ensemble strategies.
  • Miniatura
    Ítem
    The FOODRUS index: assessing suitability for effective food loss and waste prevention management under an integral perspective
    (Elsevier Ltd, 2024-04) Amador Cervera, Manuel; Angarita Zapata, Juan S.; Calle, Alberto de la; Alonso Vicario, Ainhoa
    The impact of food loss and waste (FLW) generation on food supply chains' (FSC) sustainability represents a challenge embodied in the Sustainable Development Goal (SDG) 12.3. This problem requires a methodology to measure such an impact in a rigorous, holistic, and standardized way that can be applied to any FSC. This paper aims to develop and validate a single index to assess the readiness of FSCs to implement FLW prevention strategies and measure their impact: the so-called FOODRUS index. The co-creation methodology followed incorporates experts and FSC stakeholders feedback. The index has been validated in 3 FSCs: The Slovak pilot scored 74.35%, the Spanish pilot reached 68.79%, and the Danish pilot was rated 61.14%. Its calculation, eased by the FOODRUS index self-assessment tool (described in the Appendix), allows quick diagnosis of the FSC capability to implement FLW prevention strategies considering both the knowledge provided by experts and the experience of the FSC stakeholders that participated in its co-creation process. In this way the FSC can assess its FLW prevention performance at a strategic and management level, with the aim of improving its sustainability impact.
  • No hay miniatura disponible
    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, Peter
    Traffic 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.