Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification

Samira Pouyanfar, Yudong Tao, Anup Mohan, Haiman Tian, Ahmed S. Kaseb, Kent Gauen, Ryan Dailey, Sarah Aghajanzadeh, Yung Hsiang Lu, Shu Ching Chen, Mei-Ling Shyu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Many multimedia systems stream real-time visual data continuously for a wide variety of applications. These systems can produce vast amounts of data, but few studies take advantage of the versatile and real-time data. This paper presents a novel model based on the Convolutional Neural Networks (CNNs) to handle such imbalanced and heterogeneous data and successfully identifies the semantic concepts in these multimedia systems. The proposed model can discover the semantic concepts from the data with a skewed distribution using a dynamic sampling technique. The paper also presents a system that can retrieve real-time visual data from heterogeneous cameras, and the run-time environment allows the analysis programs to process the data from thousands of cameras simultaneously. The evaluation results in comparison with several state-of-the-art methods demonstrate the ability and effectiveness of the proposed model on visual data captured by public network cameras.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE 1st Conference on Multimedia Information Processing and Retrieval, MIPR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages112-117
Number of pages6
ISBN (Electronic)9781538618578
DOIs
StatePublished - Jun 26 2018
Event1st IEEE Conference on Multimedia Information Processing and Retrieval, MIPR 2018 - Miami, United States
Duration: Apr 10 2018Apr 12 2018

Other

Other1st IEEE Conference on Multimedia Information Processing and Retrieval, MIPR 2018
CountryUnited States
CityMiami
Period4/10/184/12/18

Fingerprint

Multimedia systems
Cameras
Sampling
Neural networks
Semantics

Keywords

  • Convolutional Neural Networks
  • Deep Learning
  • Dynamic Sampling
  • Imbalanced Data
  • Network Cameras

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Media Technology

Cite this

Pouyanfar, S., Tao, Y., Mohan, A., Tian, H., Kaseb, A. S., Gauen, K., ... Shyu, M-L. (2018). Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification. In Proceedings - IEEE 1st Conference on Multimedia Information Processing and Retrieval, MIPR 2018 (pp. 112-117). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MIPR.2018.00027

Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification. / Pouyanfar, Samira; Tao, Yudong; Mohan, Anup; Tian, Haiman; Kaseb, Ahmed S.; Gauen, Kent; Dailey, Ryan; Aghajanzadeh, Sarah; Lu, Yung Hsiang; Chen, Shu Ching; Shyu, Mei-Ling.

Proceedings - IEEE 1st Conference on Multimedia Information Processing and Retrieval, MIPR 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 112-117.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pouyanfar, S, Tao, Y, Mohan, A, Tian, H, Kaseb, AS, Gauen, K, Dailey, R, Aghajanzadeh, S, Lu, YH, Chen, SC & Shyu, M-L 2018, Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification. in Proceedings - IEEE 1st Conference on Multimedia Information Processing and Retrieval, MIPR 2018. Institute of Electrical and Electronics Engineers Inc., pp. 112-117, 1st IEEE Conference on Multimedia Information Processing and Retrieval, MIPR 2018, Miami, United States, 4/10/18. https://doi.org/10.1109/MIPR.2018.00027
Pouyanfar S, Tao Y, Mohan A, Tian H, Kaseb AS, Gauen K et al. Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification. In Proceedings - IEEE 1st Conference on Multimedia Information Processing and Retrieval, MIPR 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 112-117 https://doi.org/10.1109/MIPR.2018.00027
Pouyanfar, Samira ; Tao, Yudong ; Mohan, Anup ; Tian, Haiman ; Kaseb, Ahmed S. ; Gauen, Kent ; Dailey, Ryan ; Aghajanzadeh, Sarah ; Lu, Yung Hsiang ; Chen, Shu Ching ; Shyu, Mei-Ling. / Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification. Proceedings - IEEE 1st Conference on Multimedia Information Processing and Retrieval, MIPR 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 112-117
@inproceedings{1e4a94b8e753437d85145c0cb372ef86,
title = "Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification",
abstract = "Many multimedia systems stream real-time visual data continuously for a wide variety of applications. These systems can produce vast amounts of data, but few studies take advantage of the versatile and real-time data. This paper presents a novel model based on the Convolutional Neural Networks (CNNs) to handle such imbalanced and heterogeneous data and successfully identifies the semantic concepts in these multimedia systems. The proposed model can discover the semantic concepts from the data with a skewed distribution using a dynamic sampling technique. The paper also presents a system that can retrieve real-time visual data from heterogeneous cameras, and the run-time environment allows the analysis programs to process the data from thousands of cameras simultaneously. The evaluation results in comparison with several state-of-the-art methods demonstrate the ability and effectiveness of the proposed model on visual data captured by public network cameras.",
keywords = "Convolutional Neural Networks, Deep Learning, Dynamic Sampling, Imbalanced Data, Network Cameras",
author = "Samira Pouyanfar and Yudong Tao and Anup Mohan and Haiman Tian and Kaseb, {Ahmed S.} and Kent Gauen and Ryan Dailey and Sarah Aghajanzadeh and Lu, {Yung Hsiang} and Chen, {Shu Ching} and Mei-Ling Shyu",
year = "2018",
month = "6",
day = "26",
doi = "10.1109/MIPR.2018.00027",
language = "English (US)",
pages = "112--117",
booktitle = "Proceedings - IEEE 1st Conference on Multimedia Information Processing and Retrieval, MIPR 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification

AU - Pouyanfar, Samira

AU - Tao, Yudong

AU - Mohan, Anup

AU - Tian, Haiman

AU - Kaseb, Ahmed S.

AU - Gauen, Kent

AU - Dailey, Ryan

AU - Aghajanzadeh, Sarah

AU - Lu, Yung Hsiang

AU - Chen, Shu Ching

AU - Shyu, Mei-Ling

PY - 2018/6/26

Y1 - 2018/6/26

N2 - Many multimedia systems stream real-time visual data continuously for a wide variety of applications. These systems can produce vast amounts of data, but few studies take advantage of the versatile and real-time data. This paper presents a novel model based on the Convolutional Neural Networks (CNNs) to handle such imbalanced and heterogeneous data and successfully identifies the semantic concepts in these multimedia systems. The proposed model can discover the semantic concepts from the data with a skewed distribution using a dynamic sampling technique. The paper also presents a system that can retrieve real-time visual data from heterogeneous cameras, and the run-time environment allows the analysis programs to process the data from thousands of cameras simultaneously. The evaluation results in comparison with several state-of-the-art methods demonstrate the ability and effectiveness of the proposed model on visual data captured by public network cameras.

AB - Many multimedia systems stream real-time visual data continuously for a wide variety of applications. These systems can produce vast amounts of data, but few studies take advantage of the versatile and real-time data. This paper presents a novel model based on the Convolutional Neural Networks (CNNs) to handle such imbalanced and heterogeneous data and successfully identifies the semantic concepts in these multimedia systems. The proposed model can discover the semantic concepts from the data with a skewed distribution using a dynamic sampling technique. The paper also presents a system that can retrieve real-time visual data from heterogeneous cameras, and the run-time environment allows the analysis programs to process the data from thousands of cameras simultaneously. The evaluation results in comparison with several state-of-the-art methods demonstrate the ability and effectiveness of the proposed model on visual data captured by public network cameras.

KW - Convolutional Neural Networks

KW - Deep Learning

KW - Dynamic Sampling

KW - Imbalanced Data

KW - Network Cameras

UR - http://www.scopus.com/inward/record.url?scp=85050162026&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050162026&partnerID=8YFLogxK

U2 - 10.1109/MIPR.2018.00027

DO - 10.1109/MIPR.2018.00027

M3 - Conference contribution

SP - 112

EP - 117

BT - Proceedings - IEEE 1st Conference on Multimedia Information Processing and Retrieval, MIPR 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -