Improving sustainability is a key concern for industrial development. Industry has recently been benefiting from the rise of IoT technologies, leading to improvements in the monitoring and breakdown prevention of industrial equipment. In order to properly achieve this monitoring and prevention, visualization techniques are of paramount importance. However, the visualization of real-time IoT sensor data has always been challenging, especially when such data are originated by sensors of different natures. In order to tackle this issue, we propose a methodology that aims to help users to visually locate and understand the failures that could arise in a production process.This methodology collects, in a guided manner, user goals and the requirements of the production process, analyzes the incoming data from IoT sensors and automatically derives the most suitable visualization type for each context. This approach will help users to identify if the production process is running as well as expected+ADs thus, it will enable them to make the most sustainable decision in each situation. Finally, in order to assess the suitability of our proposal, a case study based on gas turbines for electricity generation is presented.
Autores: Ana Lavalle / Miguel A. Teruel / Alejandro Maté / Juan Trujillo /
Palabras Clave: Artificial Intelligence - Big Data analytics - data visualization - gas turbines - Internet of Things - sustainable production
Fostering sustainability is paramount for Smart Cities development. Lately, Smart Cities are benefiting from the rising of Big Data coming from IoT devices, leading to improvements on monitoring and prevention. However, monitoring and prevention processes require visualization techniques as a key component. Indeed, in order to prevent possible hazards (such as fires, leaks, etc.) and optimize their resources, Smart Cities require adequate visualizations that provide insights to decision makers. Nevertheless, visualization of Big Data has always been a challenging issue, especially when such data are originated in real-time. This problem becomes even bigger in Smart City environments since we have to deal with many different groups of users and multiple heterogeneous data sources. Without a proper visualization methodology, complex dashboards including data from different nature are difficult to understand. In order to tackle this issue, we propose a methodology based on visualization techniques for Big Data, aimed at improving the evidence-gathering process by assisting users in the decision making in the context of Smart Cities. Moreover, in order to assess the impact of our proposal, a case study based on service calls for a fire department is presented. In this sense, our findings will be applied to data coming from citizen calls. Thus, the results of this work will contribute to the optimization of resources, namely fire extinguishing battalions, helping to improve their effectiveness and, as a result, the sustainability of a Smart City, operating better with less resources. Finally, in order to evaluate the impact of our proposal, we have performed an experiment, with non-expert users in data visualization.
Autores: Ana Lavalle / Miguel A. Teruel / Alejandro Maté / Juan Trujillo /
Palabras Clave: Artificial Intelligence - Big Data analytics - dashboards - data visualization - Internet of Things - methodology - Smart city
Context: Information visualization is paramount for the analysis of Big Data. The volume of data requiring interpretation is continuously growing. However, users are usually not experts in information visualization. Thus, defining the visualization that best suits a determined context is a very challenging task for them. Moreover, it is often the case that users do not have a clear idea of what objectives they are building the visualizations for. Consequently, it is possible that graphics are misinterpreted, making wrong decisions that lead to missed opportunities. One of the underlying problems in this process is the lack of methodologies and tools that non-expert users in visualizations can use to define their objectives and visualizations.Objective: The main objectives of this paper are to (i) enable non-expert users in data visualization to communicate their analytical needs with little effort, (ii) generate the visualizations that best fit their requirements, and (iii) evaluate the impact of our proposal with reference to a case study, describing an experiment with 97 non-expert users in data visualization.Methods: We propose a methodology that collects user requirements and semi-automatically creates suitable visualizations. Our proposal covers the whole process, from the definition of requirements to the implementation of visualizations. The methodology has been tested with several groups to measure its effectiveness and perceived usefulness.Results: The experiments increase our confidence about the utility of our methodology. It significantly improves over the case when users face the same problem manually. Specifically: (i) users are allowed to cover more analytical questions, (ii) the visualizations produced are more effective, and (iii) the overall satisfaction of the users is larger.Conclusion: By following our proposal, non-expert users will be able to more effectively express their analytical needs and obtain the set of visualizations that best suits their goals.
Autores: Ana Lavalle / Alejandro Maté / Juan Trujillo / Miguel A. Teruel / Stefano Rizzi /
Palabras Clave: Big Data analytics - data visualization - Experimental validation - Model-Driven Development - requirements engineering
Cada vez son más las cantidades de datos que necesitan ser analizadas e interpretadas y la visualización de la información juega un papel clave para ello. Definir una visualización correcta y sin errores es crucial para comprender e interpretar los patrones y resultados obtenidos por los algoritmos de análisis, ya que una incorrecta interpretación o resultados incorrectos podría suponer pérdidas significativas a la empresa. Sin embargo, la definición de visualizaciones es una tarea difícil para los usuarios de negocio, ya que en la mayoría de ocasiones no son expertos en la visualización de información y no conocen exactamente las herramientas o tipos de visualización mas adecuados para medir sus objetivos. El principal problema que se encuentra es la falta de herramientas y metodologías que ayuden a usuarios no expertos a definir sus objetivos de visualización y análisis de datos en términos de negocio. Es por ello, que para afrontar este problema, presentamos un modelo basado en el lenguaje i* para la especificación de visualización de datos. Nuestra propuesta permite seleccionar de forma objetiva las técnicas de visualización más adecuadas, con la gran ventaja de proporcionar a los usuarios no expertos, las visualizaciones más adecuadas según sus necesidades y sus datos con poco esfuerzo y sin requerir experiencia en la visualización de información.
Autores: Ana Lavalle / Alejandro Maté / Juan Trujillo /
Palabras Clave: Analíticas de datos - Modelo basado en Objetivos - Requisitos de usuario - Visualización de Datos
