Applying a Method for Augmenting Data Mixed from Two Different Sources Using Deep Generative Neural Networks to Management Science
Although a multimodal data analysis, comprising physiological and questionnaire survey data, provides better insights into addressing management science concerns, such as challenging the predictions of consumer choice behavior, studies in this field are scarce because of two obstacles: limited sampl...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/1/378 |
| _version_ | 1797359082817978368 |
|---|---|
| author | Shinya Watanuki Yumiko Nomura Yuki Kiyota Minami Kubo Kenji Fujimoto Junko Okada Katsue Edo |
| author_facet | Shinya Watanuki Yumiko Nomura Yuki Kiyota Minami Kubo Kenji Fujimoto Junko Okada Katsue Edo |
| author_sort | Shinya Watanuki |
| collection | DOAJ |
| description | Although a multimodal data analysis, comprising physiological and questionnaire survey data, provides better insights into addressing management science concerns, such as challenging the predictions of consumer choice behavior, studies in this field are scarce because of two obstacles: limited sample size and information privacy. This study addresses these challenges by synthesizing multimodal data using deep generative models. We obtained multimodal data by conducting an electroencephalography (EEG) experiment and a questionnaire survey on the prediction of skilled nurses. Subsequently, we validated the effectiveness of the synthesized data compared with real data regarding the similarities between these data and the predictive performance. We confirmed that the synthesized big data were almost equal to the real data using the trained models through sufficient epochs. Conclusively, we demonstrated that synthesizing data using deep generative models might overcome two significant concerns regarding multimodal data utilization, including physiological data. Our approach can contribute to the prevailing combined big data from different modalities, such as physiological and questionnaire survey data, when solving management issues. |
| first_indexed | 2024-03-08T15:11:10Z |
| format | Article |
| id | doaj.art-884e3635f5ed44859c64b446296359f8 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T15:11:10Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-884e3635f5ed44859c64b446296359f82024-01-10T14:51:56ZengMDPI AGApplied Sciences2076-34172023-12-0114137810.3390/app14010378Applying a Method for Augmenting Data Mixed from Two Different Sources Using Deep Generative Neural Networks to Management ScienceShinya Watanuki0Yumiko Nomura1Yuki Kiyota2Minami Kubo3Kenji Fujimoto4Junko Okada5Katsue Edo6Department of Marketing, Faculty of Commerce, University of Marketing and Distribution Sciences, 3-1 Gakuen-Nishimachi, Nishi-ku, Kobe 651-2188, Hyogo, JapanDepartment of Nursing, Japanese Red Cross Hiroshima College of Nursing, 1-2 Ajinadai-Higashi, Hatsukaichi 738-0052, Hiroshima, JapanGraduate School of Comprehensive Scientific Research Program in Health and Welfare, Prefectural University of Hiroshima, 1-1 Gakuencho, Mihara 723-0053, Hiroshima, JapanHiroshima Red Cross Hospital Atomic-Bomb Survivors Hospital, 1-9-6 Sendamachi, Naka-ku, Hiroshima 730-8619, Hiroshima, JapanHiroshima Office, Survey Research Center Co., Ltd., 2-29 Tatemachi, Naka-ku, Hiroshima 730-0032, Hiroshima, JapanFaculty of Health and Welfare, Prefectural University of Hiroshima, 1-1 Gakuencho, Mihara 723-0053, Hiroshima, JapanHiroshima Business and Management School, Prefectural University of Hiroshima, 1-1-71 Ujina-Higashi, Minami-ku, Hiroshima 734-8558, Hiroshima, JapanAlthough a multimodal data analysis, comprising physiological and questionnaire survey data, provides better insights into addressing management science concerns, such as challenging the predictions of consumer choice behavior, studies in this field are scarce because of two obstacles: limited sample size and information privacy. This study addresses these challenges by synthesizing multimodal data using deep generative models. We obtained multimodal data by conducting an electroencephalography (EEG) experiment and a questionnaire survey on the prediction of skilled nurses. Subsequently, we validated the effectiveness of the synthesized data compared with real data regarding the similarities between these data and the predictive performance. We confirmed that the synthesized big data were almost equal to the real data using the trained models through sufficient epochs. Conclusively, we demonstrated that synthesizing data using deep generative models might overcome two significant concerns regarding multimodal data utilization, including physiological data. Our approach can contribute to the prevailing combined big data from different modalities, such as physiological and questionnaire survey data, when solving management issues.https://www.mdpi.com/2076-3417/14/1/378questionnaire surveymarketing researchEEGdeep learninggenerative adversarial networks (GANs) |
| spellingShingle | Shinya Watanuki Yumiko Nomura Yuki Kiyota Minami Kubo Kenji Fujimoto Junko Okada Katsue Edo Applying a Method for Augmenting Data Mixed from Two Different Sources Using Deep Generative Neural Networks to Management Science Applied Sciences questionnaire survey marketing research EEG deep learning generative adversarial networks (GANs) |
| title | Applying a Method for Augmenting Data Mixed from Two Different Sources Using Deep Generative Neural Networks to Management Science |
| title_full | Applying a Method for Augmenting Data Mixed from Two Different Sources Using Deep Generative Neural Networks to Management Science |
| title_fullStr | Applying a Method for Augmenting Data Mixed from Two Different Sources Using Deep Generative Neural Networks to Management Science |
| title_full_unstemmed | Applying a Method for Augmenting Data Mixed from Two Different Sources Using Deep Generative Neural Networks to Management Science |
| title_short | Applying a Method for Augmenting Data Mixed from Two Different Sources Using Deep Generative Neural Networks to Management Science |
| title_sort | applying a method for augmenting data mixed from two different sources using deep generative neural networks to management science |
| topic | questionnaire survey marketing research EEG deep learning generative adversarial networks (GANs) |
| url | https://www.mdpi.com/2076-3417/14/1/378 |
| work_keys_str_mv | AT shinyawatanuki applyingamethodforaugmentingdatamixedfromtwodifferentsourcesusingdeepgenerativeneuralnetworkstomanagementscience AT yumikonomura applyingamethodforaugmentingdatamixedfromtwodifferentsourcesusingdeepgenerativeneuralnetworkstomanagementscience AT yukikiyota applyingamethodforaugmentingdatamixedfromtwodifferentsourcesusingdeepgenerativeneuralnetworkstomanagementscience AT minamikubo applyingamethodforaugmentingdatamixedfromtwodifferentsourcesusingdeepgenerativeneuralnetworkstomanagementscience AT kenjifujimoto applyingamethodforaugmentingdatamixedfromtwodifferentsourcesusingdeepgenerativeneuralnetworkstomanagementscience AT junkookada applyingamethodforaugmentingdatamixedfromtwodifferentsourcesusingdeepgenerativeneuralnetworkstomanagementscience AT katsueedo applyingamethodforaugmentingdatamixedfromtwodifferentsourcesusingdeepgenerativeneuralnetworkstomanagementscience |