A Deep Learning Models for Blind Guidance by Integrating CNN and ELM

Hsin Yi Tsai; Hanyu Zhang; Che Lun Hung; Fang Rong Hsu

doi:10.1109/HPCC/SmartCity/DSS.2018.00207

A Deep Learning Models for Blind Guidance by Integrating CNN and ELM

Hsin Yi Tsai, Hanyu Zhang, Che Lun Hung, Fang Rong Hsu

Institute of Biomedical Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Sign recognition is a challenging task but has many important applications. Blind guidance system in one of them. Besides accuracy, which is one of the main metrics as in many other applications, blind guidance system demands real-time response in addition to make the application practical in real word. In this paper, we propose to combine ELM classifier with Deep Convolutional Features, which are obtained from some popular CNNs including AlexNet, GoogLeNet and ResNet, etc., to reduce both training time and prediction time and meanwhile maintain the same level of accuracy comparing to a transfer learning scheme with a single hidden dense layer. Experiments on toilet sign images demonstrate that the proposed method may perform much faster and maintain comparable accuracy. Performance comparisons are also investigated with different CNNs and hyper-parameters.

Original language	English
Title of host publication	Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1229-1234
Number of pages	6
ISBN (Electronic)	9781538666142
DOIs	https://doi.org/10.1109/HPCC/SmartCity/DSS.2018.00207
State	Published - 22 Jan 2019
Event	20th International Conference on High Performance Computing and Communications, 16th IEEE International Conference on Smart City and 4th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018 - Exeter, United Kingdom Duration: 28 Jun 2018 → 30 Jun 2018

Publication series

Name	Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018

Conference

Conference	20th International Conference on High Performance Computing and Communications, 16th IEEE International Conference on Smart City and 4th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018
Country/Territory	United Kingdom
City	Exeter
Period	28/06/18 → 30/06/18

Keywords

Blind Guidance
CNN
Deep Learning
ELM

Access to Document

10.1109/HPCC/SmartCity/DSS.2018.00207

Cite this

Tsai, H. Y., Zhang, H., Hung, C. L., & Hsu, F. R. (2019). A Deep Learning Models for Blind Guidance by Integrating CNN and ELM. In Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018 (pp. 1229-1234). Article 8622945 (Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HPCC/SmartCity/DSS.2018.00207

Tsai, Hsin Yi ; Zhang, Hanyu ; Hung, Che Lun et al. / A Deep Learning Models for Blind Guidance by Integrating CNN and ELM. Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1229-1234 (Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018).

@inproceedings{b2a552c7be6544a1945cc5faec35e5c9,

title = "A Deep Learning Models for Blind Guidance by Integrating CNN and ELM",

abstract = "Sign recognition is a challenging task but has many important applications. Blind guidance system in one of them. Besides accuracy, which is one of the main metrics as in many other applications, blind guidance system demands real-time response in addition to make the application practical in real word. In this paper, we propose to combine ELM classifier with Deep Convolutional Features, which are obtained from some popular CNNs including AlexNet, GoogLeNet and ResNet, etc., to reduce both training time and prediction time and meanwhile maintain the same level of accuracy comparing to a transfer learning scheme with a single hidden dense layer. Experiments on toilet sign images demonstrate that the proposed method may perform much faster and maintain comparable accuracy. Performance comparisons are also investigated with different CNNs and hyper-parameters.",

keywords = "Blind Guidance, CNN, Deep Learning, ELM",

author = "Tsai, {Hsin Yi} and Hanyu Zhang and Hung, {Che Lun} and Hsu, {Fang Rong}",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 20th International Conference on High Performance Computing and Communications, 16th IEEE International Conference on Smart City and 4th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018 ; Conference date: 28-06-2018 Through 30-06-2018",

year = "2019",

month = jan,

day = "22",

doi = "10.1109/HPCC/SmartCity/DSS.2018.00207",

language = "English",

series = "Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1229--1234",

booktitle = "Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018",

address = "美國",

}

Tsai, HY, Zhang, H, Hung, CL & Hsu, FR 2019, A Deep Learning Models for Blind Guidance by Integrating CNN and ELM. in Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018., 8622945, Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1229-1234, 20th International Conference on High Performance Computing and Communications, 16th IEEE International Conference on Smart City and 4th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018, Exeter, United Kingdom, 28/06/18. https://doi.org/10.1109/HPCC/SmartCity/DSS.2018.00207

A Deep Learning Models for Blind Guidance by Integrating CNN and ELM. / Tsai, Hsin Yi; Zhang, Hanyu; Hung, Che Lun et al.
Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1229-1234 8622945 (Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Deep Learning Models for Blind Guidance by Integrating CNN and ELM

AU - Tsai, Hsin Yi

AU - Zhang, Hanyu

AU - Hung, Che Lun

AU - Hsu, Fang Rong

PY - 2019/1/22

Y1 - 2019/1/22

N2 - Sign recognition is a challenging task but has many important applications. Blind guidance system in one of them. Besides accuracy, which is one of the main metrics as in many other applications, blind guidance system demands real-time response in addition to make the application practical in real word. In this paper, we propose to combine ELM classifier with Deep Convolutional Features, which are obtained from some popular CNNs including AlexNet, GoogLeNet and ResNet, etc., to reduce both training time and prediction time and meanwhile maintain the same level of accuracy comparing to a transfer learning scheme with a single hidden dense layer. Experiments on toilet sign images demonstrate that the proposed method may perform much faster and maintain comparable accuracy. Performance comparisons are also investigated with different CNNs and hyper-parameters.

AB - Sign recognition is a challenging task but has many important applications. Blind guidance system in one of them. Besides accuracy, which is one of the main metrics as in many other applications, blind guidance system demands real-time response in addition to make the application practical in real word. In this paper, we propose to combine ELM classifier with Deep Convolutional Features, which are obtained from some popular CNNs including AlexNet, GoogLeNet and ResNet, etc., to reduce both training time and prediction time and meanwhile maintain the same level of accuracy comparing to a transfer learning scheme with a single hidden dense layer. Experiments on toilet sign images demonstrate that the proposed method may perform much faster and maintain comparable accuracy. Performance comparisons are also investigated with different CNNs and hyper-parameters.

KW - Blind Guidance

KW - CNN

KW - Deep Learning

KW - ELM

UR - http://www.scopus.com/inward/record.url?scp=85062559726&partnerID=8YFLogxK

U2 - 10.1109/HPCC/SmartCity/DSS.2018.00207

DO - 10.1109/HPCC/SmartCity/DSS.2018.00207

M3 - Conference contribution

AN - SCOPUS:85062559726

T3 - Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018

SP - 1229

EP - 1234

BT - Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 20th International Conference on High Performance Computing and Communications, 16th IEEE International Conference on Smart City and 4th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018

Y2 - 28 June 2018 through 30 June 2018

ER -

Tsai HY, Zhang H, Hung CL, Hsu FR. A Deep Learning Models for Blind Guidance by Integrating CNN and ELM. In Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1229-1234. 8622945. (Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018). doi: 10.1109/HPCC/SmartCity/DSS.2018.00207

A Deep Learning Models for Blind Guidance by Integrating CNN and ELM

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this