Intelligent vehicles technologies require a good understanding of human driver behaviors to guarantee safe, adjust to drivers’ needs and meet their preferences. This research line try to answer these questions monitoring driving behaviors by using the emerging deep learning approach, based on big data, which is revolutionizing the classical machine learning techniques, getting a breakthrough in the performance of complex classification and decision-making problems. Our proposal is to monitor driver behavior in real-time and to carry out decision making tasks, by using deep learning techniques, in order to implement a safe switching system between manual and automatic mode in the future V2U (Vehicle to User) interfaces for autonomous vehicles.
Improving Energy Performance Contracting (EPC) adoption by using smart contracts and Blockchain technologies
EPC is one of the most relevant tool for implementing energy efficiency measures in buildings. The research activity will be focused on the development of novel EPC model, considering smart contracts based on blockchain technology. The EPC definition will also consider associated business models and related side disciplines (i.e. social science and humanities).
Global control of smart grids through integration of Automatic Metering Infrastructure in Advanced Distribution Management Systems
Power network analysis have been mostly based on HV and MV signals, while today availability of smart meters data in (near) real-time is disclosing new possibilities for optimal control. Moreover, the increasing number of dispersed generators is focusing the objective on low voltage grid monitoring and control.
This research activity will be focused on integrate the smart metering signals and data from different utility metering infrastructures, into a unified platform able to ingest data with different models and protocols (DLMS/COSEM, PLC Prime, M-Bus, etc.). The expected result is the capacity to acquire and expose data from different utilities (i.e. energy carriers) into a unique centralized solution.
A bi-lateral optimization through novel Artificial Intelligence applications, based on High Energy Performance approach in buildings
This research activity will be focused on the creation of novel tools and services through a High Energy Performance approach. The main goal is to develop an AI service for optimal control of energy considering behind the meter resources (management of energy sources at user level), with local (building or district) overall efficiency.
One significant line of research of the group focuses on micro-grid (MG) design and optimization problems in smart grids using meta-heuristics and Machine Learning approaches. We are also interested in the application of novel soft computing techniques to smart grids challenges.
NILM and smart meters imply a new approach to monitor elderlies by using one single sensor, enabling scalability and non-intrusiveness. The energy disaggregation and appliance identification are actually the foundations, where a deep learning approach can propose novel methods to identity, determine and analyse behaviours, patterns and routines in the daily activities of people living in the households under analysis. These methods can provide relatives and carers with a powerful tool to evaluate and/or infer a person’s situation with a null intrusiveness over time, not only in the short but also in the long term.
Energy efficiency in transportation systems is a widely studied field due to its big economic and environmental impact. One of the most important problems that the research community has focused on during the last decades is the reduction of the consumed energy in all aspects of our daily life. One of the most important factors of energy consumption is transportation. To this end, a great amount of work in the field of intelligent transportation systems focuses on improving energy efficiency. Our main line of research is the study of energy efficiency in road transportation, taking into account both driver’s behavior and truck’s characteristics by using big data analysis techniques. To achieve this, models are inferred from machine learning algorithms, which are designed and implemented inside a research scope. Afterwards these models are validated with real data provided by a logistics operator specialized in dangerous goods, mainly hydrocarbon materials (in liquid state), which has a high incidence in the Spanish economy, and at the same time, has high levels of security and regulation.
Driver Assistance Systems (ADAS) have spread within the automotive industry, supporting the driver e.g. for braking, steering or automated systems like adaptive cruise control, automatic emergency braking or lane keeping assist. However, for automation level 3, these sub-functions require further developments concerning user acceptance to facilitate their adoption. The main goal of EPIC proposal is to contribute to the adoption of automated vehicles by considering the needs and requirements of all the road users (drivers and VRUs), assuring safe and acceptable integration of key
The mechanical engineering area from UAH is actively researching on new smart transport system based on railways. Freight and passenger transport on railways system can be improved and time optimized by creating new vehicles systems and by applying new smart algorithms to traffic and network control systems. The project CAPSULE deals with a new transport system for underground mobility, reducing drastically the travel time for passengers. This multidisciplinary project involves mechanical and electrical engineers as well as computer engineers and mathematicians