scholarly journals ANALYSIS OF VHR IMAGE CLASSIFICATION BY SINGLE AND ENSEMBLE OF CLASSIFIERS

2020 ◽  
Vol XLII-3/W12-2020 ◽  
pp. 37-42
Author(s):  
M. G. Lacerda ◽  
E. H. Shiguemori ◽  
A. J. Damião ◽  
C. S. Anjos ◽  
M. Habermann
Keyword(s):  
Processing Time ◽  
Computational Cost ◽  
Ensemble Classifiers ◽  
Ensemble Of Classifiers ◽  
Real Time Processing ◽  
Time Processing ◽  
Very High ◽  
Classified Image ◽  
Main Factor

Abstract. Given the wide variety of image classifiers available nowadays, some questions remain about the accuracy and processing time of Very High Resolution (VHR) images. Another question concerns the use of a Single or Ensemble Classifiers. Of course, the main factor to consider is the quality of the classified image, but computational cost is also important, especially in applications that require real-time processing. Given this scenario, this paper aims to relate the accuracy of seven single classifiers and the ensemble of the same classifiers with the processing time. In this paper the ensemble of classifiers had the best results in terms of accuracy, however, it comes to processing time, the decision tree had the best performance.

REAL-TIME PROCESSING OF OIL SPILL REMOTE SENSING DATA1

1987 ◽  
Vol 1987 (1) ◽  
pp. 71-73
Author(s):  
Yvon J. F. Le Guen ◽  
Marc Brussieux ◽  
Rolland Burkhalter
Keyword(s):  
Remote Sensing ◽  
Image Processing ◽  
Oil Spill ◽  
Infrared Emissivity ◽  
Real Time Processing ◽  
Time Processing ◽  
Oil Slick ◽  
Processing Program ◽  
Thermal Infrared Imagery

ABSTRACT The good quality of thermal infrared imagery and the relation between infrared emissivity and the thickness of an oil slick have led to the development of a visualizing rack and an image processing program. This system, tested on board a surveillance aircraft, has permitted on-site estimation within 20 seconds of the total volume of a 28 cubic meter slick with less than 15% error.

scholarly journals Near-real-time processing of a ceilometer network assisted with sun-photometer data: monitoring a dust outbreak over the Iberian Peninsula

2017 ◽  
Vol 17 (19) ◽  
pp. 11861-11876 ◽  
Author(s):  
Alberto Cazorla ◽  
Juan Andrés Casquero-Vera ◽  
Roberto Román ◽  
Juan Luis Guerrero-Rascado ◽  
Carlos Toledano ◽  
...  
Keyword(s):  
Iberian Peninsula ◽  
Signal To Noise Ratio ◽  
Backscatter Coefficient ◽  
Vast Number ◽  
Real Time Processing ◽  
Time Processing ◽  
Dense Networks ◽  
Lidar Measurements ◽  
Aerosol Characterization

Abstract. The interest in the use of ceilometers for optical aerosol characterization has increased in the last few years. They operate continuously almost unattended and are also much less expensive than lidars; hence, they can be distributed in dense networks over large areas. However, due to the low signal-to-noise ratio it is not always possible to obtain particle backscatter coefficient profiles, and the vast number of data generated require an automated and unsupervised method that ensures the quality of the profiles inversions. In this work we describe a method that uses aerosol optical depth (AOD) measurements from the AERONET network that it is applied for the calibration and automated quality assurance of inversion of ceilometer profiles. The method is compared with independent inversions obtained by co-located multiwavelength lidar measurements. A difference smaller than 15 % in backscatter is found between both instruments. This method is continuously and automatically applied to the Iberian Ceilometer Network (ICENET) and a case example during an unusually intense dust outbreak affecting the Iberian Peninsula between 20 and 24 February 2016 is shown. Results reveal that it is possible to obtain quantitative optical aerosol properties (particle backscatter coefficient) and discriminate the quality of these retrievals with ceilometers over large areas. This information has a great potential for alert systems and model assimilation and evaluation.

scholarly journals Near real time processing of ceilometer network data: characterizing an extraordinary dust outbreak over the Iberian Peninsula

2017 ◽  
Author(s):  
Alberto Cazorla ◽  
Juan Andrés Casquero-Vera ◽  
Roberto Román ◽  
Juan Luis Guerrero-Rascado ◽  
Carlos Toledano ◽  
...  
Keyword(s):  
Iberian Peninsula ◽  
Signal To Noise Ratio ◽  
Network Data ◽  
Backscatter Coefficient ◽  
Real Time Processing ◽  
Time Processing ◽  
Dense Networks ◽  
Lidar Measurements ◽  
Aerosol Characterization

Abstract. The interest on the use of ceilometers for optical aerosol characterization has increased in the last few years. They operate continuously almost unattended and are also much less expensive than lidars, hence they can be distributed in dense networks over large areas. However, due to the low signal-to-noise-ratio it is not always possible to obtain particle backscatter coefficient profiles, and the vast amount of data generated requires an automated and unsupervised method that ensures the quality of the profiles inversions. In this work a method that uses aerosol optical depth (AOD) measurements from the AERONET network is applied for the calibration and automated quality assurance of inversion of ceilometer profiles. The method is compared with independent inversions obtained by co-located multiwavelength lidar measurements and a difference up to 15 % in backscatter is found between both instruments. This method is continuously and automatically applied to the Iberian Ceilometer Network (ICENET) and a case example during an unusually intense dust outbreak that affected the Iberian Peninsula on 20 February 2016 and lasted until 24 February 2016 is shown. Results reveal that it is possible to obtain a quantitative optical aerosol characterization (particle backscatter coefficient) with ceilometers over large areas and this information has a great potential for alert systems and model assimilation and evaluation.

scholarly journals A GRAPHIC PROCESSING UNIT FRAME WORK FOR CONVOLUTIONAL NEURAL NETWORK BASED CLASSIFICATION OF REMOTELY SENSED SATELLITE IMAGES

2018 ◽  
Vol IV-5 ◽  
pp. 383-390
Author(s):  
R. A. Ansari ◽  
W. Thomas ◽  
K. M. Buddhiraju
Keyword(s):  
Real Time ◽  
Performance Improvement ◽  
Satellite Images ◽  
Processing Unit ◽  
Real Time Processing ◽  
Time Processing ◽  
Huge Data ◽  
Gpu Implementation ◽  
Sequential Implementation ◽  
Very High

<p><strong>Abstract.</strong> Near real time processing and feature extraction from high-resolution satellite images aids in various applications of remote sensing including segmentation, classification and change detection. The latest generation of satellite sensors are able to capture the data at a very high spatial, spectral and temporal resolution. The processing time required for such a huge data is also large. Disaster monitoring applications such as forest fire monitoring, earthquakes require fast/real time processing of high resolution data to enable response activities. In general, due to the large size of satellite data, the computational time of feature calculation and training neural network is found to be very high. Therefore in order to achieve the aim of near real time processing of such huge data, we developed a parallel implementation. The implementation is performed on NVIDIA’s Graphical Processing Unit. The performance improvement obtained is demonstrated by a GPU implementation on Resourcesat-1 data and compared with the traditional sequential implementation. The results show that the GPU implementation is found to achieve performance improvement in terms of execution time and speedup throughput as compared to the sequential implementation.</p>

scholarly journals The yield and the quality of crushed cereals from the polba wheat grain

2020 ◽  
pp. 79-89
Author(s):  
V. Lubich ◽  
I. Leshchenko ◽  
L. Storozhyk ◽  
V. Voitovska
Keyword(s):  
Raw Materials ◽  
Total Yield ◽  
Fine Fraction ◽  
Wheat Grain ◽  
Culinary Quality ◽  
Organoleptic Characteristics ◽  
High Level ◽  
Very High ◽  
Main Factor

The article presents the results of research on the yield of crushed cereals, its culinary quality depending on the index of grain peeling of different varieties of spelled wheat. Holikovska wheat grain and LP 1152 line were used as raw materials for cereal production. A significant (p≤0.05) effect on the total yield of crushed cereals of different grain peeling duration was established. A decrease in the total yield of cereals was accompanied by an increase in the yield of flour. The use of larger grains (line LP 1152) provides a significant increase in the total yield of crushed cereals. Peeling of grain helped to reduce the total yield of cereals and crushed cereals № 1 and № 2. At the same time, there was an increase in the yield of fine fraction of cereals № 3. The use of grain with a higher content of shells provides a higher yield of larger grains. The total yield of wheat spelled from line LP 1152 varied from 83.6 to 86.0 % depending on the grain husking index. When using grain, the yield of cereals № 1 was 9.3±0.3 %, cereals №2 – 54.5±0.6, cereals № 3 – 22.2±0.9 %. The use of husking of spelled wheat grain reduced the yield of cereals №1 to 6.0±0.3 %, cereals № 2 – to 50.4±0.4 %. The grain yield №3 increased to 27.2±0.7 % in the variant with the highest peeling index. The lowest amount of flour (9.0 %) was obtained using unhulled grain. Peeling causes an increase in yield to 11.5 % with the use of hulled grain (peeling index 11 %). No association has been established between mechanical losses, category I, II wastes, and the use of grain husking. The total yield of Holikovska spelled wheat groats varied from 77.5 to 76.0 % depending on the grain-husking index. The yield of cereals by numbers varied like a line of spelled wheat. The main importance in changing the duration of cooking, boiling ratio and organoleptic characteristics is the coefficient of grain peeling. Varietal features did not have a significant impact and had similar meanings. The reduction in cooking time was observed with an increase in the index of grain peeling, as well as with the use of cereals of a smaller fraction. The main factor that influenced the improvement of the overall culinary quality of cereals is the improvement of color and consistency during chewing because of increasing the peeling index. With a grain-peeling index of 3–6 %, the culinary quality was at a high level. Very high culinary quality of cereals is ensured by the use of grain husking for 120–160 s (peeling index 9–11 %). When producing crushed groats from spelled wheat grain, it is optimal to use LP 1152 grain with a peeling index of 3–6 %. This ensures a high total yield of cereals (85.0–84.6 %) and high culinary quality of porridge. Key words: spelled wheat, grain, peeling, crushed groats, culinary evaluation.

INFLUENCE OF FORCED CONVECTION IN LIQUID INSIDE THE TIN ON DURATION OF STERILIZATION IN THE COURSE OF FISH PROCESSING

2017 ◽  
pp. 137-144
Author(s):  
Gennadiy Valentinovich Alexeev ◽  
Elena Igorevna Verboloz
Keyword(s):  
High Temperature ◽  
Liquid Phase ◽  
Forced Convection ◽  
Thermal Process ◽  
Processing Time ◽  
Fish Processing ◽  
Study Results ◽  
Equipment Modernization ◽  
Bottom To Top

The article focuses on the process of intensive mixing of liquid phase in the tin during high-temperature sterilization, i.e. sterilization when temperature of the heat carrier reaches 150-160°C. It has been stated that for intensification of the thermal process during sterilization of tinned fish with liquid filling it is preferable to turn a tin from bottom to top. This operation helps to increase the driving power of the process and to shorten warming time. Besides, high-temperature sterilization carried out according to experimental modes, where the number of tin turnovers is calculated, greatly shortens processing time and improves quality of the product. In this case there is no superheating, all tins are evenly heated. The study results will contribute to equipment modernization and to preserving valuable food qualities.

Driving Torsion Scans with Wavefront Propagation

2020 ◽  
Author(s):  
Yudong Qiu ◽  
Daniel Smith ◽  
Chaya Stern ◽  
mudong feng ◽  
Lee-Ping Wang
Keyword(s):  
Potential Energy ◽  
Force Field ◽  
Degrees Of Freedom ◽  
Computational Cost ◽  
Initial Guess ◽  
Field Development ◽  
Force Field Development ◽  
Wavefront Propagation ◽  
Open Source Software Package

<div>The parameterization of torsional / dihedral angle potential energy terms is a crucial part of developing molecular mechanics force fields.</div><div>Quantum mechanical (QM) methods are often used to provide samples of the potential energy surface (PES) for fitting the empirical parameters in these force field terms.</div><div>To ensure that the sampled molecular configurations are thermodynamically feasible, constrained QM geometry optimizations are typically carried out, which relax the orthogonal degrees of freedom while fixing the target torsion angle(s) on a grid of values.</div><div>However, the quality of results and computational cost are affected by various factors on a non-trivial PES, such as dependence on the chosen scan direction and the lack of efficient approaches to integrate results started from multiple initial guesses.</div><div>In this paper we propose a systematic and versatile workflow called \textit{TorsionDrive} to generate energy-minimized structures on a grid of torsion constraints by means of a recursive wavefront propagation algorithm, which resolves the deficiencies of conventional scanning approaches and generates higher quality QM data for force field development.</div><div>The capabilities of our method are presented for multi-dimensional scans and multiple initial guess structures, and an integration with the MolSSI QCArchive distributed computing ecosystem is described.</div><div>The method is implemented in an open-source software package that is compatible with many QM software packages and energy minimization codes.</div>

Ground water quality of selected areas of Punjab and Sind Provinces, Pakistan: Chemical and microbiological aspects

2019 ◽  
Author(s):  
Chem Int
Keyword(s):  
Ionic Concentration ◽  
Chloride Ions ◽  
Potassium Ions ◽  
Ammonium Ions ◽  
High Concentration ◽  
Phosphate Ions ◽  
Sodium Magnesium ◽  
Very High ◽  
Microbiological Aspects

The assessment of groundwater is essential for the estimation of suitability of water for safe use. An attempt has been made to study the groundwater of selected areas of Punjab (Sheikhupura &amp; Sahiwal) and Sindh (Sindh, Jawar Dharki and Dharki), Pakistan. The results indicate that pH, color and odor were all within limits of WHO that is pH ranges 6.5–8.5, colorless and odorless, respectively. The high values of suspended solids were observed in the Sindh-1 and Dharki samples. Microbiologically only Sahiwal and Jawar Dharki were found fit for drinking purpose. Trace metals analysis of Sheikhupura-1 and Sindh-1 showed that values do not fall within limits of WHO for Iron. The ionic concentration analysis showed that high bicarbonate (HCO3-), ions are present in the samples of Sahiwal and Dharki; Sindh-1 and Jawar Dharki samples showed very high concentration for chloride ions, all samples were satisfactory level for sulphate (SO42-), sodium, magnesium and phosphate ions except samples of Sindh-1 and Jawar Dharki. High concentration of calcium and potassium ions was observed in samples of Sindh-1, while all other samples were found fit for drinking purposes in respect of nitrate, nitrite and ammonium ions. The high concentration of Fluoride was found only in Sheikhupura-2 samples.

Sign in / Sign up

Export Citation Format

Share Document