A5101565230- Remote-Sensing Image Classification
- Power Transformer Diagnostics and Insulation
- High voltage insulation and dielectric phenomena
- Advanced Image Fusion Techniques
- Reservoir Engineering and Simulation Methods
- Water Quality Monitoring Technologies
- Power Quality and Harmonics
- Image Enhancement Techniques
- Remote Sensing and Land Use
- Remote Sensing in Agriculture
- Identification and Quantification in Food
- Hydraulic Fracturing and Reservoir Analysis
- Advanced MEMS and NEMS Technologies
- Electrohydrodynamics and Fluid Dynamics
- Traffic control and management
- Coral and Marine Ecosystems Studies
- Drilling and Well Engineering
- Building Energy and Comfort Optimization
- Ichthyology and Marine Biology
- Remote Sensing and LiDAR Applications
- Image and Signal Denoising Methods
- Mechanical and Optical Resonators
- Photonic and Optical Devices
- Traffic Prediction and Management Techniques
- Advanced Measurement and Metrology Techniques
Universidad de León
2022
Old Dominion University
2017-2021
Universidad Carlos III de Madrid
2018-2020
Dominion (United States)
2019
Children's National
2019
Schlumberger (British Virgin Islands)
2005-2010
University of California, San Francisco
2009
Land cover classification with the focus on chlorophyll-rich vegetation detection plays an important role in urban growth monitoring and planning, autonomous navigation, drone mapping, biodiversity conservation, etc. Conventional approaches usually apply normalized difference index (NDVI) for detection. In this paper, we investigate performance of deep learning conventional methods Two methods, DeepLabV3+ our customized convolutional neural network (CNN) were evaluated respect to their when...
There is an emerging interest in using hyperspectral data for land cover classification. The motivation behind the notion that increasing number of narrowband spectral channels would provide richer information and thus help improve classification performance. Although with hundreds detailed signatures, curse dimensionality might lead to degradation Moreover, some practical applications, may not be available due cost, storage, or bandwidth issues, RGB near infrared (NIR) could only image...
Effector functions and proliferation of T helper (Th) cells are influenced by cytokines in the environment.Th1 respond to a synergistic effect interleukin-12 (IL-12) interleukin-18 (IL-18) secrete interferon-gamma (IFN-γ).In contrast, Th2 interleukin-4 (IL-4) IL-4, interleukin-13 (IL-13), interleukin-5 (IL-5), interleukin-10 (IL-10).The authors were interested identifying nonpeptide inhibitors Th1 response selective for IL-12/IL-18-mediated secretion IFN-γ while leaving IL-4-mediated...
Recent evidence suggests the Akt-mTOR pathway may play a role in development of low-grade gliomas (LGG). We sought to evaluate whether activation this correlates with survival LGG by examining expression patterns proteins within pathway. Forty-five tumor specimens from newly diagnosed patients were analyzed for methylation putative 5′-promoter region PTEN using methylation-specific PCR as well phosphorylation S6 and PRAS40 protein immunohistochemistry. Relationships between molecular markers...
Although Worldview-2 (WV) images (non-pansharpened) have 2-m resolution, the re-visit times for same areas may be seven days or more. In contrast, Planet are collected using small satellites that can cover whole Earth almost daily. However, resolution of is 3.125 m. It would ideal to fuse these two generate high spatial (2 m) and temporal (1 2 days) applications such as damage assessment, border monitoring, etc. require quick decisions. this paper, we evaluate three approaches fusing...
This paper presents a new deep learning based approach for soil detection using high resolution multispectral satellite images with of 0.31 m. In particular, convolutional neural network (CNN) is proposed to identify potential tunnel digging activities. Spatial and spectral information in the image cube has been incorporated into CNN. We also propose novel method handle imbalance context CNN model training. Experimental results on Worldview-2 (WV-2) captured at border between USA Mexico...
Remote sensing images play a critical role in natural disaster prevention and damage estimation. With the fast advances hyperspectral sensors, imaging also known as spectrometry is becoming relatively recent trend. Hyperspectral are expected to be more effective object detection, environmental monitoring, urban growth assessment. In this paper, we present 4 layers deep convolutional neural network (CNN) model for soil detection by using combination of 80 synthetic bands its original 8...
Coastal ecosystems are critically affected by seagrass, both economically and ecologically. However, reliable seagrass distribution information is lacking in nearly all parts of the world because excessive costs associated with its assessment. In this paper, we develop two deep learning models for automatic quantification based on 8-band satellite imagery. Specifically, implemented a capsule network (DCN) convolutional neural (CNN) to assess through regression. The DCN model first determines...
The connectivity advances in industrial control systems have also increased the possibility of cyberattacks industry. Thus, security becomes crucial critical infrastructures, whose services are considered essential fields such as manufacturing, energy or public health. Although theoretical and formal approaches often proposed to advance field cybersecurity, more experimental efforts realistic scenarios needed understand impact incidents, assess technologies provide training. In this paper,...
This paper presents a novel approach to detect changes in satellite images taken from the same location at different timestamps. Different change detection methods are applied multispectral with Worldview-2 (WV-2) satellite, as well several of their feature indices such normalized difference vegetation index (NDVI), soil (NDSI), non-homogeneous (NHFD) and red-blue ratio (R/B). Besides, an additional image is used remove temporary like vehicles, persons etc. The combination computed set...
Human voice could be significantly affected by neoplasm, vocal palsy, and phono-trauma diseases. Computer aided diagnosis analyzing human can a remote cost-effective tool for patients around the world. In this paper, we propose deep transfer learning approach to differentiate pathological samples from normal ones. We utilize recorded 200 at Far Eastern Memorial Hospital (FEMH) develop model. extract prosodic, tract excitation features as new representations diagnosis. To address small data...
The interest in developing new nanodielectric fluids suitable for electrotechnical applications has increased significantly the last decade. Several authors have reported experiences on manufactured using different base and nanoparticles. Most of these studies are focused comparison thermal dielectric properties nanofluids liquids most found that addition nanoparticles to insulating can lead an improvement their properties. This two-part paper analyzes enhancement AC breakdown voltage...
This paper evaluates the stability of three industrial cesium clocks located in different sites, comparing them via common-view technique and using three-cornered hat (TCH) method. Validation implementation is obtained by results with Coordinated Universal Time (UTC) Rapid UTC values reported for involved. An enhanced TCH method presented implemented, yielding corrections up to 30% Allan deviation estimates. The main feature developed possibility computing absolute remote at averaging times...
This paper presents some preliminary results using Landsat and Worldview images for change detection. The studied area had significant changes such as construction of buildings between May 2014 October 2015. We investigated several simple, practical, effective approaches to For images, we first performed pansharpening enhance the resolution 15 meters. then a chronochrome covariance equalization two images. residual equalized was analyzed simple algorithms direct subtraction global...
Pansharpened Landsat images have 15 m spatial resolution with 16-day revisit periods. On the other hand, Worldview 0.5 after pansharpening but times are uncertain. We present some preliminary results for a challenging image fusion problem that fuses and (WV) to yield high temporal sequence at same of WV images. Since between is 30 1, our mixed in objective performance metrics such as peak signal-to-noise ratio (PSNR), correlation coefficient (CC), etc. sometimes showed good performance, poor...
Full comprehension of microscopic traffic simulation (MTS) models has necessitated the development proper visualizations. Existing MTS only provide limited capability two- and/or three-dimensional displays that often restrict users’ viewpoint to a flat screen. Their downscaled scenes neither realistic representation environment nor allow different users simultaneously experience model from perspectives. This largely prevents analysts effectively demonstrating and disseminating their results...
Several authors have suggested that one of the main differences between conventional insulating liquids and nanodielectric fluids is behavior water in fluid. It has been reported impact on dielectric strength reduced when nanoparticles are dispersed fluid, present higher breakdown voltage values than base under similar moisture content. The second part this two-part paper analyzes effect presence AC several prepared from mineral oil Fe <sub xmlns:mml="http://www.w3.org/1998/Math/MathML"...
The interest in the development of new nanodielectric fluids suitable for electrotechnical applications has increased significantly last decade. Several authors have reported experiences on manufactured using different base and nanoparticles. Most these studies are focused comparison thermal dielectric properties nanofluids liquids most found that addition nanoparticles can lead to an improvement insulating liquids. main objective this paper is study enhancement AC Breakdown Voltage (AC BV)...