Application of CNN deep learning in product design evaluation

Baorui Li; Yi Wang; Kesheng Wang; Jinghui Yang

doi:10.1007/978-981-13-2375-1_65

Application of CNN deep learning in product design evaluation

Baorui Li
, Yi Wang
, Kesheng Wang
, Jinghui Yang

Shanghai University
University of Plymouth
Norwegian University of Science and Technology
Shanghai Second Polytechnic University

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

4 Citations (Scopus)

Abstract

Convolutional Neural Network (CNN) is an excellent deep learning algorithm. It can not only extract image features accurately, but also can reduce the complexity of the model. This paper combines the advanced technology of cognitive neurology, where we uses EEG equipment to read the real brain activity data when people make evaluation and at the same time we uses the eye-tracking equipment to collect the subject’s gaze point and gaze path, and then generates gaze hotspot map with gaze time. The CNN model is trained by the samples obtained by expert system scoring. Thanks to the advantages of CNN in image processing. AlexNet model with 8-layer network structure is used to extract the features of Brain Electrical Activity Mapping (BEAM) and gaze hot spot image, and then the Support Vector Machine (SVM) is used to classify and predict different degrees. Ultimately the product design features evaluation is achieved.

Original language	English
Title of host publication	Advanced Manufacturing and Automation VIII (IWAMA 2018)
Publisher	Springer
Pages	517-526
ISBN (Electronic)	9789811323751
ISBN (Print)	9789811323744
DOIs	https://doi.org/10.1007/978-981-13-2375-1_65
Publication status	Published - 15 Dec 2018

Publication series

Name	Advanced Manufacturing and Automation VIII
Volume	484
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Access to Document

10.1007/978-981-13-2375-1_65

http://link.springer.com/10.1007/978-981-13-2375-1_65

Handle.net

Persistent link

Cite this

@inproceedings{1e187c5c1f34455da8f573a69b56c618,

title = "Application of CNN deep learning in product design evaluation",

abstract = "Convolutional Neural Network (CNN) is an excellent deep learning algorithm. It can not only extract image features accurately, but also can reduce the complexity of the model. This paper combines the advanced technology of cognitive neurology, where we uses EEG equipment to read the real brain activity data when people make evaluation and at the same time we uses the eye-tracking equipment to collect the subject{\textquoteright}s gaze point and gaze path, and then generates gaze hotspot map with gaze time. The CNN model is trained by the samples obtained by expert system scoring. Thanks to the advantages of CNN in image processing. AlexNet model with 8-layer network structure is used to extract the features of Brain Electrical Activity Mapping (BEAM) and gaze hot spot image, and then the Support Vector Machine (SVM) is used to classify and predict different degrees. Ultimately the product design features evaluation is achieved. ",

author = "Baorui Li and Yi Wang and Kesheng Wang and Jinghui Yang",

year = "2018",

month = dec,

day = "15",

doi = "10.1007/978-981-13-2375-1\_65",

language = "English",

isbn = "9789811323744",

series = "Advanced Manufacturing and Automation VIII",

publisher = "Springer",

pages = "517--526",

booktitle = "Advanced Manufacturing and Automation VIII (IWAMA 2018)",

address = "Germany",

}

TY - GEN

T1 - Application of CNN deep learning in product design evaluation

AU - Li, Baorui

AU - Wang, Yi

AU - Wang, Kesheng

AU - Yang, Jinghui

PY - 2018/12/15

Y1 - 2018/12/15

N2 - Convolutional Neural Network (CNN) is an excellent deep learning algorithm. It can not only extract image features accurately, but also can reduce the complexity of the model. This paper combines the advanced technology of cognitive neurology, where we uses EEG equipment to read the real brain activity data when people make evaluation and at the same time we uses the eye-tracking equipment to collect the subject’s gaze point and gaze path, and then generates gaze hotspot map with gaze time. The CNN model is trained by the samples obtained by expert system scoring. Thanks to the advantages of CNN in image processing. AlexNet model with 8-layer network structure is used to extract the features of Brain Electrical Activity Mapping (BEAM) and gaze hot spot image, and then the Support Vector Machine (SVM) is used to classify and predict different degrees. Ultimately the product design features evaluation is achieved.

AB - Convolutional Neural Network (CNN) is an excellent deep learning algorithm. It can not only extract image features accurately, but also can reduce the complexity of the model. This paper combines the advanced technology of cognitive neurology, where we uses EEG equipment to read the real brain activity data when people make evaluation and at the same time we uses the eye-tracking equipment to collect the subject’s gaze point and gaze path, and then generates gaze hotspot map with gaze time. The CNN model is trained by the samples obtained by expert system scoring. Thanks to the advantages of CNN in image processing. AlexNet model with 8-layer network structure is used to extract the features of Brain Electrical Activity Mapping (BEAM) and gaze hot spot image, and then the Support Vector Machine (SVM) is used to classify and predict different degrees. Ultimately the product design features evaluation is achieved.

U2 - 10.1007/978-981-13-2375-1_65

DO - 10.1007/978-981-13-2375-1_65

M3 - Conference contribution

SN - 9789811323744

T3 - Advanced Manufacturing and Automation VIII

SP - 517

EP - 526

BT - Advanced Manufacturing and Automation VIII (IWAMA 2018)

PB - Springer

ER -

Application of CNN deep learning in product design evaluation

Abstract

Publication series

Access to Document

Handle.net

Fingerprint

Cite this