scholarly journals Improvement of Algorithm in the Particle Tracking Velocimetry Using Self-Organizing Maps

1970 ◽  
Vol 7 (1) ◽  
pp. 6-23 ◽  
Author(s):  
Shashidhar Ram Joshi
Keyword(s):  
Particle Tracking ◽  
Particle Tracking Velocimetry ◽  
A Priori ◽  
Maximum Flow ◽  
Tracking Algorithm ◽  
Self Organizing Map ◽  
Self Organizing Maps ◽  
Particle Tracking Algorithm ◽  
Modified Algorithm ◽  
Self Organizing

The neural network techniques are becoming a useful tool for the particle tracking algorithm of the PIV system software and among others, the self-organizing maps (SOM) model seems to have turned out particularly effective for this purpose. This is mainly because of the performance of the particle tracking itself, capacity of dealing with unpaired particles between two frames and no necessity for a priori knowledge on the flow field (e.g. maximum flow rate) to be measured. Initially, concept of SOM was applied to PIV by Labonte. It was modified by Ohmi and further modified algorithm is developed using the concept of Delta-Bar-Delta rule. It is a heuristic algorithm for modifying the learning rate as training progresses. Earlier, the treatment of unpaired particles, a specific problem to any type of PIV, is not fully considered and thereby, the tracking goes unsuccessfully for some particles. The present research is to bring about further improvement and practicability in this promising particle tracking algorithm. The computational complexity can be reduced employing modified algorithm compared to other algorithms. The modified algorithm is tested in the light of the synthetic PIV standard image as well as in particle images obtained from visualization experiments.Key words: Delta-Bar Delta, Dynamic Threshold Binarization, HVD Algorithm, Labonte's SOM, Modified Algorithm, Ohmi's SOM, Particle Image Velocimetry(PIV), Particle Tracking Velocimetry(PTV), Self-Organizing Map(SOM), Single Threshold Binarization.Journal of the Institute of Engineering, Vol. 7, No. 1,  2009, July, pp. 6-23doi: 10.3126/jie.v7i1.2057

Improvement of the Delaunay-Tessellation Particle Tracking Algorithm in the Flow Visualization Research

2013 ◽  
Vol 411-414 ◽  
pp. 2134-2137
Author(s):  
Yang Zhang ◽  
Yuan Wang ◽  
Bin Yang
Keyword(s):  
Flow Visualization ◽  
Particle Tracking ◽  
Particle Tracking Velocimetry ◽  
Simple Structure ◽  
High Accuracy ◽  
Tracking Algorithm ◽  
Delaunay Tessellation ◽  
Complex Flows ◽  
Particle Tracking Algorithm ◽  
Novel Concept

The particle tracking velocimetry (PTV) algorithm is one of the most important branches in the flow visualization research. An efficient two-frame PTV based on Delaunay tessellation was updated by a novel concept called Dual Computation. The updated algorithm was tested using CFD flows with changeable parameters and random erasing of particles as perturbation. In addition to the simple structure and the minimal dependence on algorithmic assumptions, the advantages of this updated algorithm also include the high accuracy in addressing complex flows with noticeable ratio of particles having no match.

scholarly journals Segmentation of color images by chromaticity features using self-organizing maps

2016 ◽  
Vol 36 (2) ◽  
pp. 78 ◽  
Author(s):  
Farid García-Lamont ◽  
Alma Delia Cuevas Rasgado ◽  
Yedid Erandini Niño Membrillo
Keyword(s):  
Image Segmentation ◽  
A Priori ◽  
Human Perception ◽  
Color Images ◽  
Experimental Results ◽  
A Priori Knowledge ◽  
Self Organizing Map ◽  
Uniform Illumination ◽  
Self Organizing Maps ◽  
Self Organizing

Usually, the segmentation of color images is performed using cluster-based methods and the RGB space to represent the colors. The drawback with these methods is the a priori knowledge of the number of groups, or colors, in the image; besides, the RGB space issensitive to the intensity of the colors. Humans can identify different sections within a scene by the chromaticity of its colors of, as this is the feature humans employ to tell them apart. In this paper, we propose to emulate the human perception of color by training a self-organizing map (SOM) with samples of chromaticity of different colors. The image to process is mapped to the HSV space because in this space the chromaticity is decoupled from the intensity, while in the RGB space this is not possible. Our proposal does not require knowing a priori the number of colors within a scene, and non-uniform illumination does not significantly affect the image segmentation. We present experimental results using some images from the Berkeley segmentation database by employing SOMs with different sizes, which are segmented successfully using only chromaticity features.

scholarly journals Visualization of submerged turbulent jets using particle tracking velocimetry

2021 ◽  
Author(s):  
Franklin Shaffer ◽  
Eric Ibarra ◽  
Ömer Savaş
Keyword(s):  
Particle Tracking ◽  
Particle Tracking Velocimetry ◽  
Turbulent Jets ◽  
Reynolds Numbers ◽  
Tracking Algorithm ◽  
Small Scale ◽  
High Particle ◽  
Tracer Particles ◽  
Abrupt Changes ◽  
Particle Tracking Algorithm

Abstract Over the past few decades, advances have been made in using particle image velocimetry (PIV) and particle tracking velocimetry (PTV) for mapping of Lagrangian velocity and acceleration flow fields. With PIV, Lagrangian trajectories are not measured directly; rather, hypothetical trajectories must be constructed from sequences of Eulerian velocity snapshots. Because PTV directly measures actual trajectories, it provides distinct advantages over PIV, especially for trajectories with abrupt changes in direction. In this work, a novel particle tracking algorithm is described, then applied to track trajectories of tracer particles in submerged turbulent jets. The Reynolds numbers ranged from 1000 to 25,000, thereby covering laminar, transitioning-to-turbulence, and fully turbulent flow regimes. The novel particle tracking algorithm is designed to handle flows with very high particle concentrations, thereby resolving small-scale flow structures. Trajectories are tracked with high velocity gradients, sharp curvatures, cycloids, abrupt changes in direction, and strong recirculation—all of which are inaccessible via construction from PIV sequences. Most trajectories measured in this work are at least 500 camera frames (time steps) long, with many being more than 3000 frames long. Graphic abstract

scholarly journals Adaptive settings for the nearest-neighbor particle tracking algorithm

2014 ◽  
Vol 31 (8) ◽  
pp. 1279-1285 ◽  
Author(s):  
Javier Mazzaferri ◽  
Joannie Roy ◽  
Stephane Lefrancois ◽  
Santiago Costantino
Keyword(s):  
Particle Tracking ◽  
Nearest Neighbor ◽  
Tracking Algorithm ◽  
Neighbor Particle ◽  
Particle Tracking Algorithm

scholarly journals The Spread of the COVID-19 Outbreak in Brazil: An Overview by Kohonen Self-Organizing Map Networks

Medicina ◽  
2021 ◽  
Vol 57 (3) ◽  
pp. 235
Author(s):  
Diego Galvan ◽  
Luciane Effting ◽  
Hágata Cremasco ◽  
Carlos Adam Conte-Junior
Keyword(s):  
The Self ◽  
Self Organizing Map ◽  
Virus Spread ◽  
Self Organizing Maps ◽  
The North ◽  
Som Clustering ◽  
Unsupervised Neural Networks ◽  
Mining Tools ◽  
Temporal Spread ◽  
Self Organizing

Background and objective: In the current pandemic scenario, data mining tools are fundamental to evaluate the measures adopted to contain the spread of COVID-19. In this study, unsupervised neural networks of the Self-Organizing Maps (SOM) type were used to assess the spatial and temporal spread of COVID-19 in Brazil, according to the number of cases and deaths in regions, states, and cities. Materials and methods: The SOM applied in this context does not evaluate which measures applied have helped contain the spread of the disease, but these datasets represent the repercussions of the country’s measures, which were implemented to contain the virus’ spread. Results: This approach demonstrated that the spread of the disease in Brazil does not have a standard behavior, changing according to the region, state, or city. The analyses showed that cities and states in the north and northeast regions of the country were the most affected by the disease, with the highest number of cases and deaths registered per 100,000 inhabitants. Conclusions: The SOM clustering was able to spatially group cities, states, and regions according to their coronavirus cases, with similar behavior. Thus, it is possible to benefit from the use of similar strategies to deal with the virus’ spread in these cities, states, and regions.

scholarly journals Geospatial Analysis of Extreme Weather Events in Nigeria (1985–2015) Using Self-Organizing Maps

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Adeoluwa Akande ◽  
Ana Cristina Costa ◽  
Jorge Mateu ◽  
Roberto Henriques
Keyword(s):  
Extreme Precipitation ◽  
Large Scale ◽  
Northern Region ◽  
Extreme Weather Events ◽  
Self Organizing Map ◽  
Spatial And Temporal Patterns ◽  
Self Organizing Maps ◽  
The North ◽  
Precipitation Regimes ◽  
Self Organizing

The explosion of data in the information age has provided an opportunity to explore the possibility of characterizing the climate patterns using data mining techniques. Nigeria has a unique tropical climate with two precipitation regimes: low precipitation in the north leading to aridity and desertification and high precipitation in parts of the southwest and southeast leading to large scale flooding. In this research, four indices have been used to characterize the intensity, frequency, and amount of rainfall over Nigeria. A type of Artificial Neural Network called the self-organizing map has been used to reduce the multiplicity of dimensions and produce four unique zones characterizing extreme precipitation conditions in Nigeria. This approach allowed for the assessment of spatial and temporal patterns in extreme precipitation in the last three decades. Precipitation properties in each cluster are discussed. The cluster closest to the Atlantic has high values of precipitation intensity, frequency, and duration, whereas the cluster closest to the Sahara Desert has low values. A significant increasing trend has been observed in the frequency of rainy days at the center of the northern region of Nigeria.

scholarly journals Dynamic Gesture Recognition System with Gesture Spotting Based on Self-Organizing Maps

2021 ◽  
Vol 11 (4) ◽  
pp. 1933
Author(s):  
Hiroomi Hikawa ◽  
Yuta Ichikawa ◽  
Hidetaka Ito ◽  
Yutaka Maeda
Keyword(s):  
Real Time ◽  
Gesture Recognition ◽  
Weight Vector ◽  
Recognition System ◽  
Self Organizing Map ◽  
Self Organizing Maps ◽  
Time Dynamic ◽  
System Input ◽  
Self Organizing ◽  
Gesture Spotting

In this paper, a real-time dynamic hand gesture recognition system with gesture spotting function is proposed. In the proposed system, input video frames are converted to feature vectors, and they are used to form a posture sequence vector that represents the input gesture. Then, gesture identification and gesture spotting are carried out in the self-organizing map (SOM)-Hebb classifier. The gesture spotting function detects the end of the gesture by using the vector distance between the posture sequence vector and the winner neuron’s weight vector. The proposed gesture recognition method was tested by simulation and real-time gesture recognition experiment. Results revealed that the system could recognize nine types of gesture with an accuracy of 96.6%, and it successfully outputted the recognition result at the end of gesture using the spotting result.

A New Method for Emulating Self-Organizing Maps for Visualization of Datasets

2018 ◽  
Vol 17 (03) ◽  
pp. 1850014 ◽  
Author(s):  
Macario O. Cordel ◽  
Arnulfo P. Azcarraga
Keyword(s):  
Disaster Response ◽  
Dimensional Space ◽  
Main Idea ◽  
Cost Effective ◽  
Fine Tuning ◽  
Visualization Tool ◽  
Self Organizing Map ◽  
Text Complexity ◽  
Self Organizing Maps ◽  
Self Organizing

Several time-critical problems relying on large amount of data, e.g., business trends, disaster response and disease outbreak, require cost-effective, timely and accurate data summary and visualization, in order to come up with an efficient and effective decision. Self-organizing map (SOM) is a very effective data clustering and visualization tool as it provides intuitive display of data in lower-dimensional space. However, with [Formula: see text] complexity, SOM becomes inappropriate for large datasets. In this paper, we propose a force-directed visualization method that emulates SOMs capability to display the data clusters with [Formula: see text] complexity. The main idea is to perform a force-directed fine-tuning of the 2D representation of data. To demonstrate the efficiency and the vast potential of the proposed method as a fast visualization tool, the methodology is used to do a 2D-projection of the MNIST handwritten digits dataset.

Sign in / Sign up

Export Citation Format

Share Document