The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dalam kertas kerja ini, kami menggunakan dua kaedah dalam pembelajaran mesin, pembelajaran tercicir dan separa diselia, kepada kaedah yang dicadangkan baru-baru ini dipanggil CSQ-SDL yang menggunakan rangkaian saraf dalam untuk menilai kualiti anjakan daripada data pengukuran siri masa. Apabila membangunkan Transmisi Automatik (AT) baharu, penentukuran berlaku di mana banyak parameter AT dilaraskan untuk merealisasikan pengalaman pemanduan yang menyenangkan dalam semua situasi yang berlaku di semua jalan di seluruh dunia. Penentukuran memerlukan pakar untuk menilai secara visual kualiti anjakan daripada data pengukuran siri masa bagi eksperimen setiap kali parameter ditukar, yang berulang dan memakan masa. CSQ-SDL telah dibangunkan untuk memendekkan masa yang digunakan oleh penilaian visual, dan keberkesanannya bergantung pada memperoleh bilangan titik data yang mencukupi. Walau bagaimanapun, dalam amalan, jumlah data selalunya tidak mencukupi. Kaedah yang dicadangkan di sini boleh mengendalikan kes sedemikian. Untuk kes di mana hanya sebilangan kecil titik data berlabel tersedia, kami mencadangkan kaedah yang menggunakan keciciran. Bagi kes di mana bilangan titik data berlabel adalah kecil tetapi bilangan data tidak berlabel adalah mencukupi, kami mencadangkan kaedah yang menggunakan pembelajaran separa penyeliaan. Eksperimen menunjukkan bahawa walaupun yang pertama memberikan peningkatan sederhana, yang terakhir menawarkan peningkatan prestasi yang ketara.
Takefumi KAWAKAMI
AISIN CORPORATION
Takanori IDE
AISIN CORPORATION
Kunihito HOKI
The University of Electro-Communications
Masakazu MURAMATSU
The University of Electro-Communications
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Takefumi KAWAKAMI, Takanori IDE, Kunihito HOKI, Masakazu MURAMATSU, "Shift Quality Classifier Using Deep Neural Networks on Small Data with Dropout and Semi-Supervised Learning" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 12, pp. 2078-2084, December 2023, doi: 10.1587/transinf.2023EDP7033.
Abstract: In this paper, we apply two methods in machine learning, dropout and semi-supervised learning, to a recently proposed method called CSQ-SDL which uses deep neural networks for evaluating shift quality from time-series measurement data. When developing a new Automatic Transmission (AT), calibration takes place where many parameters of the AT are adjusted to realize pleasant driving experience in all situations that occur on all roads around the world. Calibration requires an expert to visually assess the shift quality from the time-series measurement data of the experiments each time the parameters are changed, which is iterative and time-consuming. The CSQ-SDL was developed to shorten time consumed by the visual assessment, and its effectiveness depends on acquiring a sufficient number of data points. In practice, however, data amounts are often insufficient. The methods proposed here can handle such cases. For the cases wherein only a small number of labeled data points is available, we propose a method that uses dropout. For those cases wherein the number of labeled data points is small but the number of unlabeled data is sufficient, we propose a method that uses semi-supervised learning. Experiments show that while the former gives moderate improvement, the latter offers a significant performance improvement.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023EDP7033/_p
Salinan
@ARTICLE{e106-d_12_2078,
author={Takefumi KAWAKAMI, Takanori IDE, Kunihito HOKI, Masakazu MURAMATSU, },
journal={IEICE TRANSACTIONS on Information},
title={Shift Quality Classifier Using Deep Neural Networks on Small Data with Dropout and Semi-Supervised Learning},
year={2023},
volume={E106-D},
number={12},
pages={2078-2084},
abstract={In this paper, we apply two methods in machine learning, dropout and semi-supervised learning, to a recently proposed method called CSQ-SDL which uses deep neural networks for evaluating shift quality from time-series measurement data. When developing a new Automatic Transmission (AT), calibration takes place where many parameters of the AT are adjusted to realize pleasant driving experience in all situations that occur on all roads around the world. Calibration requires an expert to visually assess the shift quality from the time-series measurement data of the experiments each time the parameters are changed, which is iterative and time-consuming. The CSQ-SDL was developed to shorten time consumed by the visual assessment, and its effectiveness depends on acquiring a sufficient number of data points. In practice, however, data amounts are often insufficient. The methods proposed here can handle such cases. For the cases wherein only a small number of labeled data points is available, we propose a method that uses dropout. For those cases wherein the number of labeled data points is small but the number of unlabeled data is sufficient, we propose a method that uses semi-supervised learning. Experiments show that while the former gives moderate improvement, the latter offers a significant performance improvement.},
keywords={},
doi={10.1587/transinf.2023EDP7033},
ISSN={1745-1361},
month={December},}
Salinan
TY - JOUR
TI - Shift Quality Classifier Using Deep Neural Networks on Small Data with Dropout and Semi-Supervised Learning
T2 - IEICE TRANSACTIONS on Information
SP - 2078
EP - 2084
AU - Takefumi KAWAKAMI
AU - Takanori IDE
AU - Kunihito HOKI
AU - Masakazu MURAMATSU
PY - 2023
DO - 10.1587/transinf.2023EDP7033
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2023
AB - In this paper, we apply two methods in machine learning, dropout and semi-supervised learning, to a recently proposed method called CSQ-SDL which uses deep neural networks for evaluating shift quality from time-series measurement data. When developing a new Automatic Transmission (AT), calibration takes place where many parameters of the AT are adjusted to realize pleasant driving experience in all situations that occur on all roads around the world. Calibration requires an expert to visually assess the shift quality from the time-series measurement data of the experiments each time the parameters are changed, which is iterative and time-consuming. The CSQ-SDL was developed to shorten time consumed by the visual assessment, and its effectiveness depends on acquiring a sufficient number of data points. In practice, however, data amounts are often insufficient. The methods proposed here can handle such cases. For the cases wherein only a small number of labeled data points is available, we propose a method that uses dropout. For those cases wherein the number of labeled data points is small but the number of unlabeled data is sufficient, we propose a method that uses semi-supervised learning. Experiments show that while the former gives moderate improvement, the latter offers a significant performance improvement.
ER -