Ultraviolet-visible (UV-Vis) spectroscopy is a well-established technique for real-time analyzing contaminants in finished drinking water and wastewater. However, it has struggled in surface water because surface water such as river water has more complex chemical compositions than drinking water and lower concentrations of nutrient contaminants such as nitrate. Previous spectrophotometric analysis using absorbance peak at UV region to estimate nitrate in drinking water performs poorly in surface water because of interference from suspended particles and dissolved organic carbon which absorb light along similar wavelengths. To overcome these challenges, the paper develops a machine learning approach to utilize the entire spectral wavelengths for accurate estimation of low concentration of dissolved nutrients from surface water background. The spectral training data used in this research are obtained by analyzing water samples collected from the US-Canada bi-nationally regulated Detroit River during agricultural seasons using A.U.G. Signals' dual channel spectrophotometer system. Confirmatory concentrations of dissolved nitrate in these samples are validated by laboratory analysis. Several commonly used supervised learning techniques including linear regression, support vector machine (SVM), and deep learning using convolutional neural network (CNN) and long short-term memory (LSTM) network are studied and compared in this work. The results conclude that the SVM with linear kernel, CNN with linear activation function, and LSTM network are the best regression models, which are able to achieve a cross validation root-mean-squared-error (RMSE) less than 0.17 ppm. The results demonstrate effectiveness of the machine learning approach and feasibility of real-time UV-Vis spectral analysis to monitor dissolved nutrient levels in the surface watersheds.
The presented work is an extension of previous work carried out at A.U.G. Signals Ltd. The problem is approached herein for vessel identification/verification using Deep Learning Neural Networks in a persistent surveillance scenario. Using images with vessels in the scene, Deep Learning Neural Networks were set up to detect vessels from still imagery (visible wavelength). Different neural network designs were implemented for vessel detection and compared based on learning performance (speed and demanded training sets) and estimation accuracy. Unique features from these designs were taken to create an optimized solution. This paper presents a comparison of the deep learning approaches implemented and their relative capabilities in vessel verification.
The objective of this paper is to develop novel classification structures for military targets detection and recognition by
employing different fusion techniques. In real applications, the great diversity of materials in the background areas and
the similarity between the background and target signatures result in high false alarm rates and large miss classification
errors. In this paper, three new systems are proposed using different fusion techniques: pixel level fusion, decision
fusion, and classification fusion employing confidence vectors. These new developed systems are tested using an
experimental data to show its effectiveness.
The probability distribution function (pdf) used to model Synthetic Aperture Radar (SAR) clutter is an important design element in Constant False Alarm Rate (CFAR) detection; the mean of the local CFAR window is taken as the first moment of the pdf. This study presents research examining the relationship between clutter statistics and radar resolution cell size in the Convair-580 (CV-580) C-SAR and RADARSAT-2 systems. The experiment consisted of decreasing the resolution of a HV polarized, high-resolution, CV-580 sea SAR image and determining the best fit pdf for the corresponding clutter. The same methodology was used on standard- and fine-beam-mode RADARSAT-2 HV images. It was found that the GΓ pdf could be fitted very well to the experimental data for all CV-580 and RADARSAT-2 resolutions. Furthermore, the highest resolution SAR data was Weibull distributed, and decidedly non-Gaussian, in all cases. The medium resolution CV-580 image was very closely modelled by the Lognormal distribution while the Rayleigh distribution (Gaussian statistics) proved highly suitable for modelling the lowest resolution SAR data. The test results presented in this paper may be useful to SAR researchers.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.