Sorry, you need to enable JavaScript to visit this website.

Other applications of machine learning (MLR-APPL)

MODELLING LARGE SCALE DATASETS USING PARTITIONING-BASED PCA


In this study, we propose an efficient approach for modelling and compressing large-scale datasets. The main idea is to subdivide each sample into smaller partitions where each partition constitutes a particular subset of attributes and then apply PCA to each partition separately. This simple approach enjoys several key advantages over the traditional holistic scheme in terms of reduced computational cost and enhanced reconstruction quality.

Paper Details

Authors:
Salaheddin Alakkari, John Dingliana
Submitted On:
20 September 2019 - 12:08am
Short Link:
Type:
Event:
Paper Code:
Document Year:
Cite

Document Files

ICIP-poster_v3.pdf

(0)

Keywords

Additional Categories

Subscribe

[1] Salaheddin Alakkari, John Dingliana, "MODELLING LARGE SCALE DATASETS USING PARTITIONING-BASED PCA", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4758. Accessed: Sep. 20, 2019.
@article{4758-19,
url = {http://sigport.org/4758},
author = {Salaheddin Alakkari; John Dingliana },
publisher = {IEEE SigPort},
title = {MODELLING LARGE SCALE DATASETS USING PARTITIONING-BASED PCA},
year = {2019} }
TY - EJOUR
T1 - MODELLING LARGE SCALE DATASETS USING PARTITIONING-BASED PCA
AU - Salaheddin Alakkari; John Dingliana
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4758
ER -
Salaheddin Alakkari, John Dingliana. (2019). MODELLING LARGE SCALE DATASETS USING PARTITIONING-BASED PCA. IEEE SigPort. http://sigport.org/4758
Salaheddin Alakkari, John Dingliana, 2019. MODELLING LARGE SCALE DATASETS USING PARTITIONING-BASED PCA. Available at: http://sigport.org/4758.
Salaheddin Alakkari, John Dingliana. (2019). "MODELLING LARGE SCALE DATASETS USING PARTITIONING-BASED PCA." Web.
1. Salaheddin Alakkari, John Dingliana. MODELLING LARGE SCALE DATASETS USING PARTITIONING-BASED PCA [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4758

High-Accuracy Automatic Person Segmentation with Novel Spatial Saliency Map


In this work, we propose a person segmentation system that achieves high segmentation accuracy with a much smaller CNN network. In this approach, key-point detection annotation is incorporated for the first time and a novel spatial saliency map, in which the intensity of each pixel indicates the likelihood of forming a part of the human and reflects the distance from the body, is generated to provide more spatial information.

Paper Details

Authors:
Weijuan Xi, Jianhang Chen, Qian Lin and Jan P. Allebach
Submitted On:
19 September 2019 - 4:32pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icip_poster.pdf

(147)

Subscribe

[1] Weijuan Xi, Jianhang Chen, Qian Lin and Jan P. Allebach, "High-Accuracy Automatic Person Segmentation with Novel Spatial Saliency Map", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4749. Accessed: Sep. 20, 2019.
@article{4749-19,
url = {http://sigport.org/4749},
author = {Weijuan Xi; Jianhang Chen; Qian Lin and Jan P. Allebach },
publisher = {IEEE SigPort},
title = {High-Accuracy Automatic Person Segmentation with Novel Spatial Saliency Map},
year = {2019} }
TY - EJOUR
T1 - High-Accuracy Automatic Person Segmentation with Novel Spatial Saliency Map
AU - Weijuan Xi; Jianhang Chen; Qian Lin and Jan P. Allebach
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4749
ER -
Weijuan Xi, Jianhang Chen, Qian Lin and Jan P. Allebach. (2019). High-Accuracy Automatic Person Segmentation with Novel Spatial Saliency Map. IEEE SigPort. http://sigport.org/4749
Weijuan Xi, Jianhang Chen, Qian Lin and Jan P. Allebach, 2019. High-Accuracy Automatic Person Segmentation with Novel Spatial Saliency Map. Available at: http://sigport.org/4749.
Weijuan Xi, Jianhang Chen, Qian Lin and Jan P. Allebach. (2019). "High-Accuracy Automatic Person Segmentation with Novel Spatial Saliency Map." Web.
1. Weijuan Xi, Jianhang Chen, Qian Lin and Jan P. Allebach. High-Accuracy Automatic Person Segmentation with Novel Spatial Saliency Map [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4749

BODYFITR: Robust automatic 3D human body fitting


This paper proposes BODYFITR, a fully automatic method to fit a human body model to static 3D scans with complex poses. Automatic and reliable 3D human body fitting is necessary for many applications related to healthcare, digital ergonomics, avatar creation and security, especially in industrial contexts for large-scale product design. Existing works either make prior assumptions on the pose, require manual annotation of the data or have difficulty handling complex poses.

Paper Details

Authors:
Submitted On:
19 September 2019 - 12:58pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

bodyfitr poster

(6)

Subscribe

[1] , "BODYFITR: Robust automatic 3D human body fitting", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4744. Accessed: Sep. 20, 2019.
@article{4744-19,
url = {http://sigport.org/4744},
author = { },
publisher = {IEEE SigPort},
title = {BODYFITR: Robust automatic 3D human body fitting},
year = {2019} }
TY - EJOUR
T1 - BODYFITR: Robust automatic 3D human body fitting
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4744
ER -
. (2019). BODYFITR: Robust automatic 3D human body fitting. IEEE SigPort. http://sigport.org/4744
, 2019. BODYFITR: Robust automatic 3D human body fitting. Available at: http://sigport.org/4744.
. (2019). "BODYFITR: Robust automatic 3D human body fitting." Web.
1. . BODYFITR: Robust automatic 3D human body fitting [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4744

MULTIPLE INSTANCE DENSE CONNECTED CONVOLUTION NEURAL NETWORK FOR AERIAL IMAGE SCENE CLASSIFICATION


With the development of deep learning, many state-of-the-art natural image scene classification methods have demonstrated impressive performance. While the current convolution neural network tends to extract global features and global semantic information in a scene, the geo-spatial objects can be located at anywhere in an aerial image scene and their spatial arrangement tends to be more complicated. One possible solution is to preserve more local semantic information and enhance feature propagation.

Paper Details

Authors:
Qi Bi, Kun Qin, Zhili Li, Han Zhang, Kai Xu
Submitted On:
19 September 2019 - 1:10am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP1792_Poster.pdf

(0)

Subscribe

[1] Qi Bi, Kun Qin, Zhili Li, Han Zhang, Kai Xu, "MULTIPLE INSTANCE DENSE CONNECTED CONVOLUTION NEURAL NETWORK FOR AERIAL IMAGE SCENE CLASSIFICATION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4707. Accessed: Sep. 20, 2019.
@article{4707-19,
url = {http://sigport.org/4707},
author = {Qi Bi; Kun Qin; Zhili Li; Han Zhang; Kai Xu },
publisher = {IEEE SigPort},
title = {MULTIPLE INSTANCE DENSE CONNECTED CONVOLUTION NEURAL NETWORK FOR AERIAL IMAGE SCENE CLASSIFICATION},
year = {2019} }
TY - EJOUR
T1 - MULTIPLE INSTANCE DENSE CONNECTED CONVOLUTION NEURAL NETWORK FOR AERIAL IMAGE SCENE CLASSIFICATION
AU - Qi Bi; Kun Qin; Zhili Li; Han Zhang; Kai Xu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4707
ER -
Qi Bi, Kun Qin, Zhili Li, Han Zhang, Kai Xu. (2019). MULTIPLE INSTANCE DENSE CONNECTED CONVOLUTION NEURAL NETWORK FOR AERIAL IMAGE SCENE CLASSIFICATION. IEEE SigPort. http://sigport.org/4707
Qi Bi, Kun Qin, Zhili Li, Han Zhang, Kai Xu, 2019. MULTIPLE INSTANCE DENSE CONNECTED CONVOLUTION NEURAL NETWORK FOR AERIAL IMAGE SCENE CLASSIFICATION. Available at: http://sigport.org/4707.
Qi Bi, Kun Qin, Zhili Li, Han Zhang, Kai Xu. (2019). "MULTIPLE INSTANCE DENSE CONNECTED CONVOLUTION NEURAL NETWORK FOR AERIAL IMAGE SCENE CLASSIFICATION." Web.
1. Qi Bi, Kun Qin, Zhili Li, Han Zhang, Kai Xu. MULTIPLE INSTANCE DENSE CONNECTED CONVOLUTION NEURAL NETWORK FOR AERIAL IMAGE SCENE CLASSIFICATION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4707

Multi-Label Zero-Shot Learning With Transfer-Aware Label Embedding Projection


Zero-Shot learning (ZSL) recently has drawn a lot of attention due to its ability to transfer knowledge from seen classes to novel unseen classes, which greatly reduces human labor of labelling data for building new classifiers. Much effort on ZSL however has focused on the standard multi-class setting, the more challenging multi-label zero-shot problem has received limited attention. In this paper, we propose a transfer-aware embedding projection approach to tackle multi-label zero-shot learning.

Paper Details

Authors:
Meng Ye, Yuhong Guo
Submitted On:
18 September 2019 - 4:02pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICIP2019_Meng.pdf

(6)

Subscribe

[1] Meng Ye, Yuhong Guo, "Multi-Label Zero-Shot Learning With Transfer-Aware Label Embedding Projection", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4695. Accessed: Sep. 20, 2019.
@article{4695-19,
url = {http://sigport.org/4695},
author = {Meng Ye; Yuhong Guo },
publisher = {IEEE SigPort},
title = {Multi-Label Zero-Shot Learning With Transfer-Aware Label Embedding Projection},
year = {2019} }
TY - EJOUR
T1 - Multi-Label Zero-Shot Learning With Transfer-Aware Label Embedding Projection
AU - Meng Ye; Yuhong Guo
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4695
ER -
Meng Ye, Yuhong Guo. (2019). Multi-Label Zero-Shot Learning With Transfer-Aware Label Embedding Projection. IEEE SigPort. http://sigport.org/4695
Meng Ye, Yuhong Guo, 2019. Multi-Label Zero-Shot Learning With Transfer-Aware Label Embedding Projection. Available at: http://sigport.org/4695.
Meng Ye, Yuhong Guo. (2019). "Multi-Label Zero-Shot Learning With Transfer-Aware Label Embedding Projection." Web.
1. Meng Ye, Yuhong Guo. Multi-Label Zero-Shot Learning With Transfer-Aware Label Embedding Projection [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4695

Graph Signal Sampling via Reinforcement Learning


We model the sampling and recovery of clustered graph signals as a reinforcement learning (RL) problem. The signal sampling is carried out by an agent which crawls over the graph and selects the most relevant graph nodes to sample. The goal of the agent is to select signal samples which allow for the most accurate recovery. The sample selection is formulated as a multi-armed bandit (MAB) problem, which lends naturally to learning efficient sampling strategies using the well-known gradient MAB algorithm.

Paper Details

Authors:
Oleksii Abramenko, Alexander Jung
Submitted On:
30 May 2019 - 10:50am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster_Abramenko_Jung.pdf

(55)

Keywords

Additional Categories

Subscribe

[1] Oleksii Abramenko, Alexander Jung, "Graph Signal Sampling via Reinforcement Learning", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4562. Accessed: Sep. 20, 2019.
@article{4562-19,
url = {http://sigport.org/4562},
author = {Oleksii Abramenko; Alexander Jung },
publisher = {IEEE SigPort},
title = {Graph Signal Sampling via Reinforcement Learning},
year = {2019} }
TY - EJOUR
T1 - Graph Signal Sampling via Reinforcement Learning
AU - Oleksii Abramenko; Alexander Jung
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4562
ER -
Oleksii Abramenko, Alexander Jung. (2019). Graph Signal Sampling via Reinforcement Learning. IEEE SigPort. http://sigport.org/4562
Oleksii Abramenko, Alexander Jung, 2019. Graph Signal Sampling via Reinforcement Learning. Available at: http://sigport.org/4562.
Oleksii Abramenko, Alexander Jung. (2019). "Graph Signal Sampling via Reinforcement Learning." Web.
1. Oleksii Abramenko, Alexander Jung. Graph Signal Sampling via Reinforcement Learning [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4562

FAST COMPRESSIVE SENSING RECOVERY USING GENERATIVE MODELS WITH STRUCTURED LATENT VARIABLES


Deep learning models have significantly improved the visual quality and accuracy on compressive sensing recovery. In this paper, we propose an algorithm for signal reconstruction from compressed measurements with image priors captured by a generative model. We search and constrain on latent variable space to make the method stable when the number of compressed measurements is extremely limited. We show that, by exploiting certain structures of the latent variables, the proposed method produces improved reconstruction accuracy and preserves realistic and non-smooth features in the image.

Paper Details

Authors:
Submitted On:
12 May 2019 - 12:59pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Xu, Shaojie ICCASP 2019 Presentation Slides.pdf

(33)

Subscribe

[1] , "FAST COMPRESSIVE SENSING RECOVERY USING GENERATIVE MODELS WITH STRUCTURED LATENT VARIABLES", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4467. Accessed: Sep. 20, 2019.
@article{4467-19,
url = {http://sigport.org/4467},
author = { },
publisher = {IEEE SigPort},
title = {FAST COMPRESSIVE SENSING RECOVERY USING GENERATIVE MODELS WITH STRUCTURED LATENT VARIABLES},
year = {2019} }
TY - EJOUR
T1 - FAST COMPRESSIVE SENSING RECOVERY USING GENERATIVE MODELS WITH STRUCTURED LATENT VARIABLES
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4467
ER -
. (2019). FAST COMPRESSIVE SENSING RECOVERY USING GENERATIVE MODELS WITH STRUCTURED LATENT VARIABLES. IEEE SigPort. http://sigport.org/4467
, 2019. FAST COMPRESSIVE SENSING RECOVERY USING GENERATIVE MODELS WITH STRUCTURED LATENT VARIABLES. Available at: http://sigport.org/4467.
. (2019). "FAST COMPRESSIVE SENSING RECOVERY USING GENERATIVE MODELS WITH STRUCTURED LATENT VARIABLES." Web.
1. . FAST COMPRESSIVE SENSING RECOVERY USING GENERATIVE MODELS WITH STRUCTURED LATENT VARIABLES [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4467

Multiple-Graph Recurrent Graph Convolutional Neural Network architectures for predicting disease outcomes


Improving disease outcome prediction can greatly aid in the strategic deployment of secondary prevention approaches. We develop a method to predict the evolution of diseases by taking into account personal attributes of the subjects and their relationships with medical examination results. Our approach builds upon a recent formulation of this problem as a graph-based geometric matrix completion task. The primary innovation is the introduction of multiple graphs, each relying on a different combination of subject attributes.

Paper Details

Authors:
Juliette Valenchon, Mark Coates
Submitted On:
11 May 2019 - 1:04pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Poster ICASSP 2019

(20)

Subscribe

[1] Juliette Valenchon, Mark Coates, "Multiple-Graph Recurrent Graph Convolutional Neural Network architectures for predicting disease outcomes", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4449. Accessed: Sep. 20, 2019.
@article{4449-19,
url = {http://sigport.org/4449},
author = {Juliette Valenchon; Mark Coates },
publisher = {IEEE SigPort},
title = {Multiple-Graph Recurrent Graph Convolutional Neural Network architectures for predicting disease outcomes},
year = {2019} }
TY - EJOUR
T1 - Multiple-Graph Recurrent Graph Convolutional Neural Network architectures for predicting disease outcomes
AU - Juliette Valenchon; Mark Coates
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4449
ER -
Juliette Valenchon, Mark Coates. (2019). Multiple-Graph Recurrent Graph Convolutional Neural Network architectures for predicting disease outcomes. IEEE SigPort. http://sigport.org/4449
Juliette Valenchon, Mark Coates, 2019. Multiple-Graph Recurrent Graph Convolutional Neural Network architectures for predicting disease outcomes. Available at: http://sigport.org/4449.
Juliette Valenchon, Mark Coates. (2019). "Multiple-Graph Recurrent Graph Convolutional Neural Network architectures for predicting disease outcomes." Web.
1. Juliette Valenchon, Mark Coates. Multiple-Graph Recurrent Graph Convolutional Neural Network architectures for predicting disease outcomes [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4449

MATRIX COMPLETION WITH VARIATIONAL GRAPH AUTOENCODERS: APPLICATION IN HYPERLOCAL AIR QUALITY INFERENCE


Inferring air quality from a limited number of observations is an essential task for monitoring and controlling air pollution. Existing inference methods typically use low spatial resolution data collected by fixed monitoring stations and infer the concentration of air pollutants using additional types of data, e.g., meteorological and traffic information. In this work, we focus on street-level air quality inference by utilizing data collected by mobile stations.

Paper Details

Authors:
Evaggelia Tsiligianni, Angel Lopez Aguirre, Valerio Panzica La Manna, Frank Pasveer, Wilfried Philips, Nikos Deligiannis
Submitted On:
11 May 2019 - 1:38am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

icassp19_poster.pdf

(30)

Subscribe

[1] Evaggelia Tsiligianni, Angel Lopez Aguirre, Valerio Panzica La Manna, Frank Pasveer, Wilfried Philips, Nikos Deligiannis, "MATRIX COMPLETION WITH VARIATIONAL GRAPH AUTOENCODERS: APPLICATION IN HYPERLOCAL AIR QUALITY INFERENCE", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4435. Accessed: Sep. 20, 2019.
@article{4435-19,
url = {http://sigport.org/4435},
author = {Evaggelia Tsiligianni; Angel Lopez Aguirre; Valerio Panzica La Manna; Frank Pasveer; Wilfried Philips; Nikos Deligiannis },
publisher = {IEEE SigPort},
title = {MATRIX COMPLETION WITH VARIATIONAL GRAPH AUTOENCODERS: APPLICATION IN HYPERLOCAL AIR QUALITY INFERENCE},
year = {2019} }
TY - EJOUR
T1 - MATRIX COMPLETION WITH VARIATIONAL GRAPH AUTOENCODERS: APPLICATION IN HYPERLOCAL AIR QUALITY INFERENCE
AU - Evaggelia Tsiligianni; Angel Lopez Aguirre; Valerio Panzica La Manna; Frank Pasveer; Wilfried Philips; Nikos Deligiannis
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4435
ER -
Evaggelia Tsiligianni, Angel Lopez Aguirre, Valerio Panzica La Manna, Frank Pasveer, Wilfried Philips, Nikos Deligiannis. (2019). MATRIX COMPLETION WITH VARIATIONAL GRAPH AUTOENCODERS: APPLICATION IN HYPERLOCAL AIR QUALITY INFERENCE. IEEE SigPort. http://sigport.org/4435
Evaggelia Tsiligianni, Angel Lopez Aguirre, Valerio Panzica La Manna, Frank Pasveer, Wilfried Philips, Nikos Deligiannis, 2019. MATRIX COMPLETION WITH VARIATIONAL GRAPH AUTOENCODERS: APPLICATION IN HYPERLOCAL AIR QUALITY INFERENCE. Available at: http://sigport.org/4435.
Evaggelia Tsiligianni, Angel Lopez Aguirre, Valerio Panzica La Manna, Frank Pasveer, Wilfried Philips, Nikos Deligiannis. (2019). "MATRIX COMPLETION WITH VARIATIONAL GRAPH AUTOENCODERS: APPLICATION IN HYPERLOCAL AIR QUALITY INFERENCE." Web.
1. Evaggelia Tsiligianni, Angel Lopez Aguirre, Valerio Panzica La Manna, Frank Pasveer, Wilfried Philips, Nikos Deligiannis. MATRIX COMPLETION WITH VARIATIONAL GRAPH AUTOENCODERS: APPLICATION IN HYPERLOCAL AIR QUALITY INFERENCE [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4435

[Slides] Accelerating Iterative Hard Thresholding for Low-rank Matrix Completion via Adaptive Restart


This paper introduces the use of adaptive restart to accelerate iterative hard thresholding (IHT) for low-rank matrix completion. First, we analyze the local convergence of accelerated IHT in the non-convex setting of matrix completion problem (MCP). We prove the linear convergence rate of the accelerated algorithm inside the region near the solution. Our analysis poses a major challenge to parameter selection for accelerated IHT when no prior knowledge of the "local Hessian condition number" is given.

Paper Details

Authors:
Trung Vu, Raviv Raich
Submitted On:
10 May 2019 - 4:04pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP_2019_slide.pdf

(23)

Keywords

Additional Categories

Subscribe

[1] Trung Vu, Raviv Raich, "[Slides] Accelerating Iterative Hard Thresholding for Low-rank Matrix Completion via Adaptive Restart", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4400. Accessed: Sep. 20, 2019.
@article{4400-19,
url = {http://sigport.org/4400},
author = {Trung Vu; Raviv Raich },
publisher = {IEEE SigPort},
title = {[Slides] Accelerating Iterative Hard Thresholding for Low-rank Matrix Completion via Adaptive Restart},
year = {2019} }
TY - EJOUR
T1 - [Slides] Accelerating Iterative Hard Thresholding for Low-rank Matrix Completion via Adaptive Restart
AU - Trung Vu; Raviv Raich
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4400
ER -
Trung Vu, Raviv Raich. (2019). [Slides] Accelerating Iterative Hard Thresholding for Low-rank Matrix Completion via Adaptive Restart. IEEE SigPort. http://sigport.org/4400
Trung Vu, Raviv Raich, 2019. [Slides] Accelerating Iterative Hard Thresholding for Low-rank Matrix Completion via Adaptive Restart. Available at: http://sigport.org/4400.
Trung Vu, Raviv Raich. (2019). "[Slides] Accelerating Iterative Hard Thresholding for Low-rank Matrix Completion via Adaptive Restart." Web.
1. Trung Vu, Raviv Raich. [Slides] Accelerating Iterative Hard Thresholding for Low-rank Matrix Completion via Adaptive Restart [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4400

Pages