2021 |
|
Abad Real, M. P. (2021). Cómo creamos mapas inteligentes para planificar mejor los desplazamientos en la ciudad. The Conversation, .
Abstract: Cada uno de nosotros somos productores de datos. Cada vez que vamos a un lugar
que nos gusta podemos describirlo y hacer partícipes a otros de ello a través de las redes sociales, comentarios en Google, etc. La información vuela a la velocidad de la luz por estas autopistas.
La secuencia que se inicia con un clic nutre de información al mundo entero. Esto permite que otras personas puedan interesarse en la información que hemos
compartido y preguntarse: ¿dónde está ese lugar? ¿Cómo puedo llegar? ¿Qué utilidad puedo yo darle?
|
|
|
Balea-Fernandez, F. J., Martinez-Vega, B., Ortega, S., Fabelo, H., Leon, R., Callico, G. M., et al. (2021). Analysis of Risk Factors in Dementia Through Machine Learning. J Alzheimers Dis, 79(2), 845–861.
Abstract: BACKGROUND: Sociodemographic data indicate the progressive increase in life expectancy and the prevalence of Alzheimer's disease (AD). AD is raised as one of the greatest public health problems. Its etiology is twofold: on the one hand, non-modifiable factors and on the other, modifiable. OBJECTIVE: This study aims to develop a processing framework based on machine learning (ML) and optimization algorithms to study sociodemographic, clinical, and analytical variables, selecting the best combination among them for an accurate discrimination between controls and subjects with major neurocognitive disorder (MNCD). METHODS: This research is based on an observational-analytical design. Two research groups were established: MNCD group (n = 46) and control group (n = 38). ML and optimization algorithms were employed to automatically diagnose MNCD. RESULTS: Twelve out of 37 variables were identified in the validation set as the most relevant for MNCD diagnosis. Sensitivity of 100%and specificity of 71%were achieved using a Random Forest classifier. CONCLUSION: ML is a potential tool for automatic prediction of MNCD which can be applied to relatively small preclinical and clinical data sets. These results can be interpreted to support the influence of the environment on the development of AD.
|
|
|
Cabrera Peña, J. M., Quevedo, E., Fabelo, H., Ortega, S., Marrero Callicó, G., & Zapatera-Llinares, A. (2021). Influence of the change of methodology in the practical laboratories of the power electronics subject. Computer Applications in Engineering Education, .
Abstract: The use of novel didactic approaches in Science, Technology, Engineering, Arts and Mathematics (STEAM) academic programs is a relevant topic in current educational research. In this context, Project-Based learning is shown as a promising didactic tool for improving the motivation of engineering students. Objective: To propose an adapted project-based approach for lecturing on Power Electronics. The main objective of the project-based approach is to enhance the attention and motivation of the students in the practical lessons, increasing their knowledge about the subject and, hence, improving results in the theoretical part of the subject. Methods: First, we propose a project which combines all the theoretical aspects related to the subject Power Electronics, namely. “Power, Control, Monitoring and Supervision System of an Electric Motor.” Second, each subsystem of the final project is analyzed during each practical lesson, and simulation environments and real circuit manipulations are used for introducing complex Power Electronics concepts to undergraduate students. Results: This project-based methodology has been compared with the demonstration method followed in the previous course by using the validated Students' Evaluations of Educational Quality survey (SEEQ). Conclusions: The results show that the adopted methodology has clearly improved the SEEQ results with respect to the demonstration method.
|
|
|
Manni, F., Cai, C., van der Sommen, F., Zinger, S., Shan, C., Edström, E., et al. (2021). Hyperspectral imaging for tissue classification in glioblastoma tumor patients: a deep spectral-spatial approach. In SPIE Medical Imaging, 2021.
Abstract: Surgery is a crucial treatment for malignant brain tumors where gross total resection improves the prognosis. Tissue samples taken during surgery are either subject to a preliminary intraoperative histological analysis, or sent for a full pathological evaluation which can take days or weeks. Whereas a lengthy complete pathological analysis includes an array of techniques to be executed, a preliminary tissue analysis on frozen tissue is performed as quickly as possible (30-45 minutes on average) to provide fast feedback to the surgeon during the surgery. The surgeon uses the information to confirm that the resected tissue is indeed tumor and may, at least in theory, initiate repeated biopsies to help achieve gross total resection. However, due to the total turn-around time of the tissue inspection for repeated analyses, this approach may not be feasible during a single surgery. In this context, intraoperative image-guided techniques can improve the clinical workflow for tumor resection and improve outcome by aiding in the identification and removal of the malignant lesion. Hyperspectral imaging (HSI) is an optical imaging technique with the potential to extract combined spectral-spatial information. By exploiting HSI for human brain-tissue classification in 13 in-vivo hyperspectral images from 9 patients, a brain-tissue classifier is developed. The framework consists of a hybrid 3D-2D CNN-based approach and a band-selection step to enhance the capability of extracting both spectral and spatial information from the hyperspectral images. An overall accuracy of 77% was found when tumor, normal and hyper-vascularized tissue are classified, which clearly outperforms the state-of-the-art approaches (SVM, 2D-CNN). These results may open an attractive future perspective for intraoperative brain-tumor classification using HSI.
|
|
|
Santana Abril, J., Santana Sosa, G., Sosa, J., Bautista, T., & Montiel-Nelson, J. A. (2021). A Novel Charging Method for Underwater Batteryless Sensor Node Networks. In Sensors (Basel, Switzerland) (Vol. 21).
Abstract: In this paper, we present a novel charging method for underwater batteryless sensor node networks. The target application is a practical underwater sensor network for oceanic fish farms. The underwater sections of the network use a wireless power transfer system based on the ISO 11784/11785 HDX standard for supplying energy to the batteryless sensor nodes. Each sensor has an accumulator capacitor, which is charged for voltage supplying to the sensor node. A new distributed charging scheme is proposed and discussed in detail to reduce the required time to charge all sensor nodes of the underwater sections. One important key is its decentralized control of the charging process. The proposal is based on the self disconnection ability of each sensor node from the charging network. The second important key is that the hardware implementation of this new feature is quite simple and only requires to include a minimal circuitry in parallel to the current sensor node antenna while the rest of the sensor network remains unaltered. The proposed charging scheme is evaluated using real corner cases from practical oceanic fish farms sensor networks. The results from experiments demonstrate that it is possible to charge up to 10 sensor nodes which is the double charging capability than previous research presented. In the same conditions as the approach found in the literature, it represents reaching an ocean depth of 60 m. In terms of energy, in case of an underwater network with 5 sensors to reach 30 m deep, the proposed charging scheme requires only a 25% of the power required using the traditional approach.
|
|
|
Uteng, S., Quevedo, E., M Callico, G., Castano, I., Carretero, G., Almeida, P., et al. (2021). Curve-Based Classification Approach for Hyperspectral Dermatologic Data Processing. In Sensors (Basel, Switzerland) (Vol. 21).
Abstract: This paper shows new contributions in the detection of skin cancer, where we present the use of a customized hyperspectral system that captures images in the spectral range from 450 to 950 nm. By choosing a 7 x 7 sub-image of each channel in the hyperspectral image (HSI) and then taking the mean and standard deviation of these sub-images, we were able to make fits of the resulting curves. These fitted curves had certain characteristics, which then served as a basis of classification. The most distinct fit was for the melanoma pigmented skin lesions (PSLs), which is also the most aggressive malignant cancer. Furthermore, we were able to classify the other PSLs in malignant and benign classes. This gives us a rather complete classification method for PSLs with a novel perspective of the classification procedure by exploiting the variability of each channel in the HSI.
|
|
2020 |
|
Alemán Ortíz, D., Lalchand Khemchandani, S., & San Miguel Montesdeoca, M. (2020). Diseño de un desfasador programable para antenas de tipo array. Master's thesis, , .
Abstract: This paper presents the implementation of an 8 bits programmable active phase shifter for phased array antenna applications. This circuit is designed to operate in the bandwidth that goes from 27.5 GHz to 30 GHz and it has been implemented in SiGe_1K5PAx technology of Global Foundries. The phase shifter has a vector sum phase structure, generating 360° phase shifts. Also, is composed by of a quadrature generator formed by a polyphase filter. In the same way, is composed by of an amplifier based on a Gilbert cell, considering the current of the Digital/Analog Converter (DAC), that will perform as current mirror of the net mentioned.
|
|
|
Aranda, L. A., Sánchez, A., Garcia-Herrero, F., Barrios, Y., Sarmiento, R., & Maestro, J. A. (2020). Reliability Analysis of the SHyLoC CCSDS123 IP Core for Lossless Hyperspectral Image Compression Using COTS FPGAs. Electronics, 9(10), 1681.
Abstract: Hyperspectral images can comprise hundreds of spectral bands, which means that they can represent a large volume of data difficult to manage with the available on-board resources. Lossless compression solutions are interesting for reducing the amount of information stored or transmitted while preserving it at the same time. The Hyperspectral Lossless Compressor for space applications (SHyLoC), which is part of the European Space Agency (ESA) IP core’s library, has been demonstrated to meet the requirements of space missions in terms of compression efficiency, low complexity and high throughput. Currently, there is a trend to use Commercial Off-The-Shelf (COTS) on-board electronic devices on small satellites. Moreover, commercial Field-Programmable Gate Arrays (FPGAs) have been used in a number of them. Hence, a reliability analysis is required to ensure the robustness of the applications to Single Event Upsets (SEUs) in the configuration memory. In this work, we present a reliability analysis of this hyperspectral image compression module as a first step towards the development of ad-hoc fault-tolerant protection techniques for the SHyLoC IP core. The reliability analysis is performed using a fault-injection-based experimental set-up in which a hardware implementation of the Consultative Committee for Space Data Systems (CCSDS) 123.0-B-1 lossless compression standard is tested against configuration memory errors in a Xilinx Zynq XC7Z020 System-on-Chip. The results obtained for unhardened and redundancy-based protected versions of the module are put into perspective in terms of area/power consumption and availability/protection coverage gained to provide insight into the development of more efficient knowledge-based protection schemes.
|
|
|
Barrios, Y., Rodríguez, A., Sánchez, A., Pérez, A., López, S., Otero, A., et al. (2020). Lossy Hyperspectral Image Compression on a Reconfigurable and Fault-Tolerant FPGA-Based Adaptive Computing Platform. In Electronics (Vol. 9, 1576).
Abstract: This paper describes a novel hardware implementation of a lossy multispectral and hyperspectral image compressor for on-board operation in space missions. The compression algorithm is a lossy extension of the Consultative Committee for Space Data Systems (CCSDS) 123.0-B-1 lossless standard that includes a bit-rate control stage, which in turn manages the losses the compressor may introduce to achieve higher compression ratios without compromising the recovered image quality. The algorithm has been implemented using High-Level Synthesis (HLS) techniques to increase design productivity by raising the abstraction level. The proposed lossy compression solution is deployed onto ARTICo3, a dynamically reconfigurable multi-accelerator architecture, obtaining a run-time adaptive solution that enables user-selectable performance (i.e., load more hardware accelerators to transparently increase throughput), power consumption, and fault tolerance (i.e., group hardware accelerators to transparently enable hardware redundancy). The whole compression solution is tested on a Xilinx Zynq UltraScale+ Field-Programmable Gate Array (FPGA)-based MPSoC using different input images, from multispectral to ultraspectral. For images acquired by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS), the proposed implementation renders an execution time of approximately 36 s when 8 accelerators are compressing concurrently at 100 MHz, which in turn uses around 20% of the LUTs and 17% of the dedicated memory blocks available in the target device. In this scenario, a speedup of 15.6× is obtained in comparison with a pure software version of the algorithm running in an ARM Cortex-A53 processor.
|
|
|
Barrios, Y., Sanchez, A. J., Santos, L., & Sarmiento, R. (2020). SHyLoC 2.0: A Versatile Hardware Solution for On-Board Data and Hyperspectral Image Compression on Future Space Missions. IEEE Access, 8, 54269–54287.
Abstract: In this paper, we present the design, implementation and results of a set of IP cores that perform on-board hyperspectral image compression according to the CCSDS 123.0-B-1 lossless standard, specifically designed to be suited for on-board systems and for any kind of hyperspectral sensor. As entropy coder, the sample-adaptive entropy coder defined in the 123.0-B-1 standard or the low-complexity block-adaptive encoder defined by the CCSDS 121.0-B-2 lossless standard could be used. Both IPs, 123.0-B-1 and 121.0-B-2, are part of SHyLoC 2.0, and can be used together for compression of hyperspectral images, being also possible the compression of any kind of data using only the 121-IP. SHyLoC 2.0 improves and extends the capabilities of SHyLoC 1.0, currently available at the ESA IP Cores library, increasing its compression efficiency and throughput, without compromising the resources footprint. Moreover, it incorporates new features, such as the unit-delay predictor option defined by the CCSDS 121.0-B-2 standard, and burst capabilities in the external memory interface of the CCSDS 123-IP, among others. Dedicated architectures have been designed for all the possible input image sample arrangements, in order to maximise throughput and reduce the hardware resources utilization. The design is technology-agnostic, enabling the mapping of the VHDL code in different FPGAs or ASICs. Results are presented for a representative group of well-known space-qualified FPGAs, including the new NanoXplore BRAVE family. A maximum throughput of 150 MSamples/s is obtained for Xilinx Virtex XQR5VFX130 when the SHyLoC 2.0 CCSDS-123 IP is configured in Band-Interleaved by Pixel (BIP) order, using only the 4% of LUTs and less than the 1% of internal memory.
|
|