Research Staff, Lecturer
Call: +34 876 555 464
Email: amarco@unizar.es, amarco@geoslab.com
Address: Lab. 5.1.10, Edificio I+D+i, Campus Río Ebro, C/ Mariano Esquillor s/n 50018 (Zaragoza, Spain)
ABOUT ME
Álvaro Marco is a Researcher & Development Engineer in GeospatiumLab, a software company based in Zaragoza, Spain, and a partial-time lecturer at University of Zaragoza.
He received an M.S. degree in electrical engineering in 2000 and a Ph.D. degree in electronic engineering in 2007, both from the University of Zaragoza, Zaragoza, Spain.
Álvaro joined Howlab in 2011 when the group was established, and he has participated in more than 60 R&D projects for public administrations and private companies, holding 14 patents and having published over 60 scientific papers, including both conference and journal’s indexed papers. He has served as editorial board member on International Journal of Distributed Sensor Networks and on Wireless Computing and Mobile Communications and is also TPC member of several international conferences.
His interests include Machine Learning, IoT, sensor networks, ambient intelligence, and middleware applications.
PUBLICATIONS
2022
Gascón, Alberto; Casas, Roberto; Buldain, David; Marco, Álvaro
Providing Fault Detection from Sensor Data in Complex Machines That Build the Smart City Journal Article
In: Sensors, vol. 22, no. 2, 2022, ISSN: 1424-8220.
@article{s22020586,
title = {Providing Fault Detection from Sensor Data in Complex Machines That Build the Smart City},
author = {Alberto Gascón and Roberto Casas and David Buldain and Álvaro Marco},
url = {https://www.mdpi.com/1424-8220/22/2/586},
doi = {10.3390/s22020586},
issn = {1424-8220},
year = {2022},
date = {2022-01-01},
journal = {Sensors},
volume = {22},
number = {2},
abstract = {Household appliances, climate control machines, vehicles, elevators, cash counting machines, etc., are complex machines with key contributions to the smart city. Those devices have limited memory and processing power, but they are not just actuators; they embed tens of sensors and actuators managed by several microcontrollers and microprocessors communicated by control buses. On the other hand, predictive maintenance and the capability of identifying failures to avoid greater damage of machines is becoming a topic of great relevance in Industry 4.0, and the large amount of data to be processed is a concern. This article proposes a layered methodology to enable complex machines with automatic fault detection or predictive maintenance. It presents a layered structure to perform the collection, filtering and extraction of indicators, along with their processing. The aim is to reduce the amount of data to work with, and to optimize them by generating indicators that concentrate the information provided by data. To test its applicability, a prototype of a cash counting machine has been used. With this prototype, different failure cases have been simulated by introducing defective elements. After the extraction of the indicators, using the Kullback-Liebler divergence, it has been possible to visualize the differences between the data associated with normal and failure operation. Subsequently, using a neural network, good results have been obtained, being able to correctly classify the failure in 90% of the cases. The result of this application demonstrates the proper functioning of the proposed approach in complex machines.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Household appliances, climate control machines, vehicles, elevators, cash counting machines, etc., are complex machines with key contributions to the smart city. Those devices have limited memory and processing power, but they are not just actuators; they embed tens of sensors and actuators managed by several microcontrollers and microprocessors communicated by control buses. On the other hand, predictive maintenance and the capability of identifying failures to avoid greater damage of machines is becoming a topic of great relevance in Industry 4.0, and the large amount of data to be processed is a concern. This article proposes a layered methodology to enable complex machines with automatic fault detection or predictive maintenance. It presents a layered structure to perform the collection, filtering and extraction of indicators, along with their processing. The aim is to reduce the amount of data to work with, and to optimize them by generating indicators that concentrate the information provided by data. To test its applicability, a prototype of a cash counting machine has been used. With this prototype, different failure cases have been simulated by introducing defective elements. After the extraction of the indicators, using the Kullback-Liebler divergence, it has been possible to visualize the differences between the data associated with normal and failure operation. Subsequently, using a neural network, good results have been obtained, being able to correctly classify the failure in 90% of the cases. The result of this application demonstrates the proper functioning of the proposed approach in complex machines.
2021
Casas, Roberto; Hermosa, Arturo; Marco, Álvaro; Blanco, Teresa; Zarazaga-Soria, Francisco Javier
Real-Time Extensive Livestock Monitoring Using LPWAN Smart Wearable and Infrastructure Journal Article
In: Applied Sciences, vol. 11, no. 3, 2021, ISSN: 2076-3417.
@article{app11031240,
title = {Real-Time Extensive Livestock Monitoring Using LPWAN Smart Wearable and Infrastructure},
author = {Roberto Casas and Arturo Hermosa and Álvaro Marco and Teresa Blanco and Francisco Javier Zarazaga-Soria},
url = {https://www.mdpi.com/2076-3417/11/3/1240},
doi = {10.3390/app11031240},
issn = {2076-3417},
year = {2021},
date = {2021-01-01},
journal = {Applied Sciences},
volume = {11},
number = {3},
abstract = {Extensive unsupervised livestock farming is a habitual technique in many places around the globe. Animal release can be done for months, in large areas and with different species packing and behaving very differently. Nevertheless, the farmer’s needs are similar: where livestock is (and where has been) and how healthy they are. The geographical areas involved usually have difficult access with harsh orography and lack of communications infrastructure. This paper presents the design of a solution for extensive livestock monitoring in these areas. Our proposal is based in a wearable equipped with inertial sensors, global positioning system and wireless communications; and a Low-Power Wide Area Network infrastructure that can run with and without internet connection. Using adaptive analysis and data compression, we provide real-time monitoring and logging of cattle’s position and activities. Hardware and firmware design achieve very low energy consumption allowing months of battery life. We have thoroughly tested the devices in different laboratory setups and evaluated the system performance in real scenarios in the mountains and in the forest.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Extensive unsupervised livestock farming is a habitual technique in many places around the globe. Animal release can be done for months, in large areas and with different species packing and behaving very differently. Nevertheless, the farmer’s needs are similar: where livestock is (and where has been) and how healthy they are. The geographical areas involved usually have difficult access with harsh orography and lack of communications infrastructure. This paper presents the design of a solution for extensive livestock monitoring in these areas. Our proposal is based in a wearable equipped with inertial sensors, global positioning system and wireless communications; and a Low-Power Wide Area Network infrastructure that can run with and without internet connection. Using adaptive analysis and data compression, we provide real-time monitoring and logging of cattle’s position and activities. Hardware and firmware design achieve very low energy consumption allowing months of battery life. We have thoroughly tested the devices in different laboratory setups and evaluated the system performance in real scenarios in the mountains and in the forest.
2020
Vizárraga, Jorge; Casas, Roberto; Marco, Álvaro; Buldain, David J
Dimensionality Reduction for Smart IoT Sensors Journal Article
In: Electronics, vol. 9, no. 12, 2020, ISSN: 2079-9292.
@article{electronics9122035,
title = {Dimensionality Reduction for Smart IoT Sensors},
author = {Jorge Vizárraga and Roberto Casas and Álvaro Marco and David J Buldain},
url = {https://www.mdpi.com/2079-9292/9/12/2035},
doi = {10.3390/electronics9122035},
issn = {2079-9292},
year = {2020},
date = {2020-01-01},
journal = {Electronics},
volume = {9},
number = {12},
abstract = {Smart IoT sensors are characterized by their ability to sense and process signals, producing high-level information that is usually sent wirelessly while minimising energy consumption and maximising communication efficiency. Systems are getting smarter, meaning that they are providing ever richer information from the same raw data. This increasing intelligence can occur at various levels, including in the sensor itself, at the edge, and in the cloud. As sending one byte of data is several orders of magnitude more energy-expensive than processing it, data must be handled as near as possible to its generation. Thus, the intelligence should be located in the sensor; nevertheless, it is not always possible to do so because real data is not always available for designing the algorithms or the hardware capacity is limited. Smart devices detecting data coming from inertial sensors are a good example of this. They generate hundreds of bytes per second (100 Hz, 12-bit sampling of a triaxial accelerometer) but useful information comes out in just a few bytes per minute (number of steps, type of activity, and so forth). We propose a lossy compression method to reduce the dimensionality of raw data from accelerometers, gyroscopes, and magnetometers, while maintaining a high quality of information in the reconstructed signal coming from an embedded device. The implemented method uses an adaptive vector-quantisation algorithm that represents the input data with a limited set of codewords. The adaptive process generates a codebook that evolves to become highly specific for the input data, while providing high compression rates. The codebook’s reconstruction quality is measured with a peak signal-to-noise ratio (PSNR) above 40 dB for a 12-bit representation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Smart IoT sensors are characterized by their ability to sense and process signals, producing high-level information that is usually sent wirelessly while minimising energy consumption and maximising communication efficiency. Systems are getting smarter, meaning that they are providing ever richer information from the same raw data. This increasing intelligence can occur at various levels, including in the sensor itself, at the edge, and in the cloud. As sending one byte of data is several orders of magnitude more energy-expensive than processing it, data must be handled as near as possible to its generation. Thus, the intelligence should be located in the sensor; nevertheless, it is not always possible to do so because real data is not always available for designing the algorithms or the hardware capacity is limited. Smart devices detecting data coming from inertial sensors are a good example of this. They generate hundreds of bytes per second (100 Hz, 12-bit sampling of a triaxial accelerometer) but useful information comes out in just a few bytes per minute (number of steps, type of activity, and so forth). We propose a lossy compression method to reduce the dimensionality of raw data from accelerometers, gyroscopes, and magnetometers, while maintaining a high quality of information in the reconstructed signal coming from an embedded device. The implemented method uses an adaptive vector-quantisation algorithm that represents the input data with a limited set of codewords. The adaptive process generates a codebook that evolves to become highly specific for the input data, while providing high compression rates. The codebook’s reconstruction quality is measured with a peak signal-to-noise ratio (PSNR) above 40 dB for a 12-bit representation.
2019
Moreno, Carlos Andres Trasviña; Blasco, Ruben; Casas, Roberto; Marco, Álvaro
Evaluación de la modulación lora en la banda de 433 MHZ para monitorización en exteriores Journal Article
In: DYNA New Technologies, vol. 6, no. 1, pp. 11–p, 2019.
@article{moreno2019evaluacion,
title = {Evaluación de la modulación lora en la banda de 433 MHZ para monitorización en exteriores},
author = {Carlos Andres Trasviña Moreno and Ruben Blasco and Roberto Casas and Álvaro Marco},
year = {2019},
date = {2019-01-01},
journal = {DYNA New Technologies},
volume = {6},
number = {1},
pages = {11–p},
publisher = {Publicaciones DYNA SL},
abstract = {En los últimos años, las Redes de Sensores Inalámbricas, o WSN por sus siglas en inglés, han aumentado su relevancia para la monitorización en exteriores. La creciente necesidad de analizar en tiempo real los espacios abiertos como reservas naturales, campos agrícolas, ciudades inteligentes, etc., han impulsado el desarrollo de nuevas tecnologías de comunicación. Diversos protocolos y técnicas han sido creados para cumplir los requerimientos de distintos escenarios de WSN, sin embargo, la monitorización de exteriores presenta retos distintos y muy característicos que aún no han sido logrados, especialmente cuando se intenta cubrir áreas de gran cobertura con un consumo energético reducido. Las recientemente desarrolladas Low Power Wide Area Networks (LPWAN) buscan llenar este vacío, con la capacidad de transmitir a grandes distancias con un bajo consumo energético. Una de estas LPWAN es la modulación LoRa (Long Range), la cual opera en frecuencias sub-GHz. Para proveer un mayor entendimiento en esta técnica de comunicación inalámbrica, en este artículo se realiza una evaluación de la modulación LoRa, utilizando la banda ISM de 433 MHz. Para esto, se realiza un análisis energético, así como de capacidad y rango de transmisión. Los resultados aportan una mayor comprensión del impacto de cada uno de los parámetros de esta modulación, así como las capacidades que tiene esta tecnología para redes de monitorización para exteriores.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
En los últimos años, las Redes de Sensores Inalámbricas, o WSN por sus siglas en inglés, han aumentado su relevancia para la monitorización en exteriores. La creciente necesidad de analizar en tiempo real los espacios abiertos como reservas naturales, campos agrícolas, ciudades inteligentes, etc., han impulsado el desarrollo de nuevas tecnologías de comunicación. Diversos protocolos y técnicas han sido creados para cumplir los requerimientos de distintos escenarios de WSN, sin embargo, la monitorización de exteriores presenta retos distintos y muy característicos que aún no han sido logrados, especialmente cuando se intenta cubrir áreas de gran cobertura con un consumo energético reducido. Las recientemente desarrolladas Low Power Wide Area Networks (LPWAN) buscan llenar este vacío, con la capacidad de transmitir a grandes distancias con un bajo consumo energético. Una de estas LPWAN es la modulación LoRa (Long Range), la cual opera en frecuencias sub-GHz. Para proveer un mayor entendimiento en esta técnica de comunicación inalámbrica, en este artículo se realiza una evaluación de la modulación LoRa, utilizando la banda ISM de 433 MHz. Para esto, se realiza un análisis energético, así como de capacidad y rango de transmisión. Los resultados aportan una mayor comprensión del impacto de cada uno de los parámetros de esta modulación, así como las capacidades que tiene esta tecnología para redes de monitorización para exteriores.
Blanco, Teresa; Casas, Roberto; Marco, Álvaro; Martínez, Ignacio
Micro ad-hoc Health Social Networks (uHSN). Design and evaluation of a social-based solution for patient support Journal Article
In: Journal of Biomedical Informatics, vol. 89, pp. 68-80, 2019, ISSN: 1532-0464.
@article{BLANCO201968,
title = {Micro ad-hoc Health Social Networks (uHSN). Design and evaluation of a social-based solution for patient support},
author = {Teresa Blanco and Roberto Casas and Álvaro Marco and Ignacio Martínez},
url = {https://www.sciencedirect.com/science/article/pii/S1532046418302181},
doi = {https://doi.org/10.1016/j.jbi.2018.11.009},
issn = {1532-0464},
year = {2019},
date = {2019-01-01},
journal = {Journal of Biomedical Informatics},
volume = {89},
pages = {68-80},
abstract = {Objective
To contribute the design, development, and assessment of a new concept: Micro ad hoc Health Social Networks (uHSN), to create a social-based solution for supporting patients with chronic disease.
Design
After in-depth fieldwork and intensive co-design over a 4-year project following Community-Based Participatory Research (CBPR), this paper contributes a new paradigm of uHSN, defining two interaction areas (the “backstage”, the sphere invisible to the final user, where processes that build services take place; and the “onstage”, the visible part that includes the patients and relatives), and describes a new transversal concept, i.e., “network spaces segments,” to provide timely interaction among all involved profiles and guaranteeing qualitative relationships. This proposal is applicable to any service design project and to all types of work areas; in the present work, it served as a social-based solution for supporting patients with chronic disease in two real-life health scenarios: a Parkinson disease patient association and a Stroke rehabilitation service in a hospital. These two scenarios included the following main features: thematic (related to the specific disease), private, and secure (only for the patient, relatives, healthcare professional, therapist, carer), with defined specific objectives (around patient support), small size (from tens to hundreds of users), ability to integrate innovative services (e.g., connection to hospital information service or to health sensors), supported by local therapeutic associations, and clustered with preconfigured relationships among users based in network groups.
Measurements
Using a mixed qualitative and quantitative approach for 6 months, the performance of the uHSN was assessed in the two environments: a hospital rehabilitation unit working with Stroke patients, and a Parkinson disease association providing physiotherapy, occupational therapy, psychological support, speech therapy, and social services. We describe the proposed methods for evaluating the uHSN quantitatively and qualitatively, and how the scientific community can replicate and/or integrate this contribution in its research.
Results
The uHSN overcomes the main limitations of traditional HSNs in the main areas recommended in the literature: privacy, security, transparency, system ecology, Quality of Service (QoS), and technology enhancement. The qualitative and quantitative research demonstrated its viability and replicability in four key points: user acceptance, productivity improvement, QoS enhancement, and fostering of social relations. It also meets the expectation of connecting health and social worlds, supporting distance rehabilitation, improving professionals’ efficiency, expanding users’ social capital, improving information quality and immediacy, and enhancing perceived peer/social/emotional support. The scientific contributions of the present paper are the first step not only in customizing health solutions that empower patients, their families, and healthcare professionals, but also in transferring this new paradigm to other scientific, professional, and social environments to create new opportunities.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Objective
To contribute the design, development, and assessment of a new concept: Micro ad hoc Health Social Networks (uHSN), to create a social-based solution for supporting patients with chronic disease.
Design
After in-depth fieldwork and intensive co-design over a 4-year project following Community-Based Participatory Research (CBPR), this paper contributes a new paradigm of uHSN, defining two interaction areas (the “backstage”, the sphere invisible to the final user, where processes that build services take place; and the “onstage”, the visible part that includes the patients and relatives), and describes a new transversal concept, i.e., “network spaces segments,” to provide timely interaction among all involved profiles and guaranteeing qualitative relationships. This proposal is applicable to any service design project and to all types of work areas; in the present work, it served as a social-based solution for supporting patients with chronic disease in two real-life health scenarios: a Parkinson disease patient association and a Stroke rehabilitation service in a hospital. These two scenarios included the following main features: thematic (related to the specific disease), private, and secure (only for the patient, relatives, healthcare professional, therapist, carer), with defined specific objectives (around patient support), small size (from tens to hundreds of users), ability to integrate innovative services (e.g., connection to hospital information service or to health sensors), supported by local therapeutic associations, and clustered with preconfigured relationships among users based in network groups.
Measurements
Using a mixed qualitative and quantitative approach for 6 months, the performance of the uHSN was assessed in the two environments: a hospital rehabilitation unit working with Stroke patients, and a Parkinson disease association providing physiotherapy, occupational therapy, psychological support, speech therapy, and social services. We describe the proposed methods for evaluating the uHSN quantitatively and qualitatively, and how the scientific community can replicate and/or integrate this contribution in its research.
Results
The uHSN overcomes the main limitations of traditional HSNs in the main areas recommended in the literature: privacy, security, transparency, system ecology, Quality of Service (QoS), and technology enhancement. The qualitative and quantitative research demonstrated its viability and replicability in four key points: user acceptance, productivity improvement, QoS enhancement, and fostering of social relations. It also meets the expectation of connecting health and social worlds, supporting distance rehabilitation, improving professionals’ efficiency, expanding users’ social capital, improving information quality and immediacy, and enhancing perceived peer/social/emotional support. The scientific contributions of the present paper are the first step not only in customizing health solutions that empower patients, their families, and healthcare professionals, but also in transferring this new paradigm to other scientific, professional, and social environments to create new opportunities.
To contribute the design, development, and assessment of a new concept: Micro ad hoc Health Social Networks (uHSN), to create a social-based solution for supporting patients with chronic disease.
Design
After in-depth fieldwork and intensive co-design over a 4-year project following Community-Based Participatory Research (CBPR), this paper contributes a new paradigm of uHSN, defining two interaction areas (the “backstage”, the sphere invisible to the final user, where processes that build services take place; and the “onstage”, the visible part that includes the patients and relatives), and describes a new transversal concept, i.e., “network spaces segments,” to provide timely interaction among all involved profiles and guaranteeing qualitative relationships. This proposal is applicable to any service design project and to all types of work areas; in the present work, it served as a social-based solution for supporting patients with chronic disease in two real-life health scenarios: a Parkinson disease patient association and a Stroke rehabilitation service in a hospital. These two scenarios included the following main features: thematic (related to the specific disease), private, and secure (only for the patient, relatives, healthcare professional, therapist, carer), with defined specific objectives (around patient support), small size (from tens to hundreds of users), ability to integrate innovative services (e.g., connection to hospital information service or to health sensors), supported by local therapeutic associations, and clustered with preconfigured relationships among users based in network groups.
Measurements
Using a mixed qualitative and quantitative approach for 6 months, the performance of the uHSN was assessed in the two environments: a hospital rehabilitation unit working with Stroke patients, and a Parkinson disease association providing physiotherapy, occupational therapy, psychological support, speech therapy, and social services. We describe the proposed methods for evaluating the uHSN quantitatively and qualitatively, and how the scientific community can replicate and/or integrate this contribution in its research.
Results
The uHSN overcomes the main limitations of traditional HSNs in the main areas recommended in the literature: privacy, security, transparency, system ecology, Quality of Service (QoS), and technology enhancement. The qualitative and quantitative research demonstrated its viability and replicability in four key points: user acceptance, productivity improvement, QoS enhancement, and fostering of social relations. It also meets the expectation of connecting health and social worlds, supporting distance rehabilitation, improving professionals’ efficiency, expanding users’ social capital, improving information quality and immediacy, and enhancing perceived peer/social/emotional support. The scientific contributions of the present paper are the first step not only in customizing health solutions that empower patients, their families, and healthcare professionals, but also in transferring this new paradigm to other scientific, professional, and social environments to create new opportunities.