Visual Analytics Tools Tools for the Study of Complex Problems in Engineering and Biomedicine

Presentation of the AVIB Project and Midterm Advances

Project data

Call

National R+D Program for Knowledge Generation
(Proyectos I+D Generación de Conocimiento)

Reference

PID2020-115401GB-I00

Title

Visual Analytics Tools Tools for the Study of Complex Problems in Engineering and Biomedicine (AVIB)

Duration

1/9/2021 - 31/08/2024 (extended to 31/08/2025)

Project abstract

Nowadays many important problems for society in the fields of engineering (energy efficiency, process monitoring) and biomedicine (epidemiological studies, clinical studies, genomic analysis) involve a high volume of data, a large number of variables and a high complexity, with many factors involved in their behavior and in which elements from various domains (technological, socioeconomic, biomedical) often interact in a strongly coupled manner. In this type of problems, often the approach itself, the initial data and the questions to be solved are not clear. Machine learning algorithms, despite achieving unprecedented accuracies in recent years, require a defined approach, are prone to failure when faced with changes in context, and are often "black box" models. Humans, on the other hand, although less precise, can work with poorly defined problems, adapt to changing contexts, find connections and improve knowledge through an iterative and exploratory process. None of these approaches alone can properly address these problems. This project proposes to investigate an approach based on the interaction between humans and machine learning algorithms, which allows to combine the advantages of both for the study of complex problems. For this purpose we will develop techniques and tools for visual analysis that integrate mechanisms of fluid interaction, data visualization and machine learning algorithms. The potential synergies between these three elements will be the central object of research in the project, seeking to achieve an exploratory and iterative analysis process led by the user, allowing him to couple it with his domain knowledge and internalize the conclusions and results. Finally, research will be conducted on the adequacy of tools for the study of real problems, through their application and evaluation in engineering and biomedical problems in which the proponent group has previous experience.

📄 Publications

📄 Journals (JCR)

  • García, Diego; Pérez, Daniel, Papapetrou, Panagiotis, Díaz, Ignacio, Cuadrado, Abel A., Enguita, Josém., and Domínguez, Manuel, "Conditioned fully convolutional denoising autoencoder for multi-target NILM". Neural Computing and Applications, 2024. DOI: https://doi.org/10.1007/s00521-024-10552-0
  • García Peña, Daniel, Diego García Pérez, Ignacio Díaz Blanco, and Jorge Marina Juárez. "Exploring deep fully convolutional neural networks for surface defect detection in complex geometries." The International Journal of Advanced Manufacturing Technology (2024): 1-15. DOI: https://doi.org/10.1007/s00170-024-14069-7
  • Garcia-Perez, Diego, Saeed, Mariam, Diaz, Ignacio, Enguita, Jose M., Guerrero, Juan Manuel, and Briz, Fernando, "Machine Learning for Inverter-Fed Motors Monitoring and Fault Detection: An Overview". IEEE Access. 12: 27167-27179, 2024. DOI: https://doi.org/10.1109/ACCESS.2024.3366810
  • Enguita, Jose María, Díaz, Ignacio, García, Diego, Cubiella, Tamara, Chiara, María-Dolores, and Valdés, Nuria, "Visual analytics identifies key miRNAs for differentiating peripancreatic paraganglioma and pancreatic neuroendocrine tumors". Frontiers in Endocrinology. 14, 2023. DOI: https://doi.org/10.3389/FENDO.2023.1162725
  • Díaz, I., Enguita, J. M., Cuadrado, A. A., García, D., González, A., Valdés, N., & Chiara, M. D. (2023). "Exploratory Analysis of the Gene Expression Matrix Based on Dual Conditional Dimensionality Reduction". IEEE Journal of Biomedical and Health Informatics. DOI: 10.1109/JBHI.2023.3264029
  • Celada, Lucía, Tamara Cubiella, Jaime San-Juan-Guardado, Andrés San José Martínez, Nuria Valdés, Paula Jiménez-Fonseca, Ignacio Díaz, et al. 2022. “Differential HIF2α Protein Expression in Human Carotid Body and Adrenal Medulla under Physiologic and Tumorigenic Conditions.” Cancers14 (12): 2986. https://doi.org/10.3390/cancers14122986.
  • González-Muñiz, Ana, Ignacio Díaz, Abel A. Cuadrado, and Diego García-Pérez. 2022. “Health Indicator for Machine Condition Monitoring Built in the Latent Space of a Deep Autoencoder.” Reliability Engineering & System Safety224 (August): 108482. https://doi.org/10.1016/j.ress.2022.108482.
  • González-Muñiz, Ana, Ignacio Díaz, Abel A. Cuadrado, Diego García-Pérez, and Daniel Pérez. 2022. “Two-Step Residual-Error Based Approach for Anomaly Detection in Engineering Systems Using Variational Autoencoders.” Computers and Electrical Engineering 101 (July): 108065. https://doi.org/10.1016/j.compeleceng.2022.108065.

📢 Conferences

  • Enguita-Gonzalez, Jose M.; Garcia-Perez, Diego; Cuadrado-Vega, Abel Alberto; García-Peña, Daniel; Rodríguez-Ossorio, José Ramón; Diaz-Blanco, Ignacio "Trustworthiness Score for Echo State Networks by Analysis of the Reservoir Dynamics". In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2024. pp. 455-460, 2024. DOI: https://doi.org/10.14428/ESANN/2024.ES2024-38, (github), (poster)
  • Garcia-Perez, Diego; Diaz-Blanco, Ignacio; Enguita-Gonzalez, Jose M.; Menéndez, Jorge; Cuadrado-Vega, Abel A. "Interactive Machine Learning-Powered Dashboard for Energy Analytics in Residential Buildings". In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2024. pp. 339-344, 2024. DOI: https://doi.org/10.14428/ESANN/2024.ES2024-130, (poster), (github), (demo app)
  • Diaz-Blanco, Ignacio; Enguita-Gonzalez, Jose M.; Garcia-Perez, Diego; Cuadrado-Vega, Abel A.; Valdes-Gallego, Nuria; Chiara-Romero, Maria Dolores "Analysis of DNA methylation patterns in cancer samples using SOM". In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2024. pp. 715-720, 2024. DOI: https://doi.org/10.14428/ESANN/2024.ES2024-42, (github), (poster)
  • García, Diego, Pérez, Daniel, Papapetrou, Panagiotis, Díaz, Ignacio, Cuadrado, Abel A., Enguita, José Maria, González, Ana, and Domínguez, Manuel "Conditioned Fully Convolutional Denoising Autoencoder for Energy Disaggregation". In IFIP Advances in Information and Communication Technology. pp. 421-433, 2023. DOI: https://doi.org/10.1007/978-3-031-34171-7_34
  • Enguita, José María, Díaz, Ignacio, García, Diego, Cuadrado, Abel Alberto, and Rodríguez, José Ramón "Principal Component Modes of Reservoir Dynamics in Reservoir Computing". In IFIP Advances in Information and Communication Technology. pp. 434-445, 2023. DOI: https://doi.org/10.1007/978-3-031-34171-7_35
  • Díaz, Ignacio, Enguita, José M., Cuadrado, Abel A., García, Diego, and González, Ana "Visual Analytics Tools for the Study of Complex Problems in Engineering and Biomedicine". In IFIP Advances in Information and Communication Technology. pp. 446-457, 2023. DOI: https://doi.org/10.1007/978-3-031-34171-7_36
  • González, Ana, Enguita, José María, Díaz, Ignacio, García, Diego, Cuadrado, Abel Alberto, Valdés, Nuria, and Chiara, María D. "Visualizing Cell Motility Patterns from Time Lapse Videos with Interactive 2D Maps Generated with Deep Autoencoders". In IFIP Advances in Information and Communication Technology. pp. 458-468, 2023. DOI: https://doi.org/10.1007/978-3-031-34171-7_37
  • Díaz Blanco, Ignacio, Enguita, José María, García, Diego, Cuadrado, Abel A., González, Ana, & Domínguez, Manuel. (2022, June 27). Modelado de series temporales mediante echo state networks para aplicaciones de analítica visual. XVII Simposio CEA de Control Inteligente: Reunión anual del grupo de Control Inteligente del comité español de automática (CEA). Libro de Actas, León, 27-29 de junio de 2022.
  • Diaz-Blanco, Ignacio, Jose M. Enguita-Gonzalez, Diego Garcia-Perez, Ana Gonzalez-Muñiz, Abel A. Cuadrado-Vega, Maria Dolores Chiara-Romero, and Nuria Valdes-Gallego. 2022. “Interactive Dual Projections for Gene Expression Analysis.” In ESANN 2022 Proceedings , 439–44. Bruges (Belgium) and online event: Ciaco - i6doc.com. https://doi.org/10.14428/esann/2022.ES2022-22.
  • Enguita-Gonzalez, Jose M., Diego Garcia-Perez, Maria Dolores Chiara-Romero, Nuria Valdes-Gallego, Ana Gonzalez-Muñiz, Abel A. Cuadrado-Vega, and Ignacio Diaz-Blanco. 2022. “Interactive Visual Analytics for Medical Data: Application to COVID-19 Clinical Information during the First Wave.” In ESANN 2022 Proceedings , 451–56. Bruges (Belgium) and online event: Ciaco - i6doc.com. https://doi.org/10.14428/esann/2022.ES2022-31

Demo apps

We list here demo apps developed within the PID2020-115401GB-I00 project to demonstrate some of the developed ideas, along with their related material (papers, videos and source code). All them are "playable" by clicking the [app] link. You can find more apps developed by out group in the gallery page

  • Morphing projections (MP). Small demo application of the morphing projections technique to visualize cancer genomics data. Demo version of the paper published in Bioinformatics at 2021. [paper] [code] [video] [app]
  • GEM-i. Interactive visualization of the Gene Expression Matrix (GEM). The user can browse the GEM and reconfigurate its rows and columns by similarities in their expression levels. Also, 2D sample map and gene map show the projections of the samples (rows) and genes (columns) according to the gene expressions on selected subsets of interest. Demo app presented for paper of IEEE Journal of Biomedical and Health Informatics, 2023 [paper] [code] [video] [app]
  • dual iDR for cancer genomics. Dual interactive dimensionality reduction of samples and genes. DR projections of samples and genes based on their expression levels co-evolve for changes in user-selected subsets of genes and samples. Demo app of paper presented at ESANN 2022. [paper] [video] [app]
  • MP + aggregation. Morphing projections demo app featuring interactive aggregation functionality for energy analytics in residential Buildings. [paper] [code] [app]

Dissemination and outreach activities

📹 Videos

Talk about Morphing Projections

Video of the talk of the Morphing Projections technique for visual analytics of genomic data in neuroendocrine oncology

Dual Visualization of Gene Expression Data

Cellular movement (1): visualization of velocity fields

Cellular movement (2): patterns of movement

Cellular movement (3): interactive visualization

Morphing Projections for cancer genomics (Díaz et al., 2021)

Interactive dual projections for gene expression analysis (Díaz et al., 2022)

Morphing Projections for COVID data (Enguita et al., 2022)

Interactive visualization of electric power demand