リケラボ論文検索は、全国の大学リポジトリにある学位論文・教授論文を一括検索できる論文検索サービスです。

リケラボ 全国の大学リポジトリにある学位論文・教授論文を一括検索するならリケラボ論文検索大学・研究所にある論文を検索できる

リケラボ 全国の大学リポジトリにある学位論文・教授論文を一括検索するならリケラボ論文検索大学・研究所にある論文を検索できる

大学・研究所にある論文を検索できる 「Efficient Convolutional Neural Networks for Brain Machine Interface Systems : A transfer learning approach」の論文概要。リケラボ論文検索は、全国の大学リポジトリにある学位論文・教授論文を一括検索できる論文検索サービスです。
リケラボ

コピーが完了しました

URLをコピーしました

論文の公開元へ論文の公開元へ
書き出し

Efficient Convolutional Neural Networks for Brain Machine Interface Systems : A transfer learning approach

PETOKU Eneo 法政大学 DOI:info:doi/10.15002/00025869

2022.12.12

概要

The goal of Brain Machine Interface (BMI) systems is to enable humans to interact with computers or machines by using their brain activity. BMI systems capture the user’s brain activity and translate it to a message or a command for certain interactive applications. Systems that make use of BMIs paradigms permit the disabled and elderly people to control wheelchairs, home appliances and robots. Another application is to write sentences and move the cursor on the screen by using brain signals, playing video games, creating arts, etc. Brain Computer Interface (BCI) systems are also investigated on stroke rehabilitation and real time health monitoring.

Motor imagery and motor execution are two of the methods that are used to map the EEG signals into external robotic or computer applications. Motor imagery is a dynamic state during which the subjects imagine the performing of an action. In motor execution applications, the subject performs actual movements (for example, moving arms and legs), or other daily life activities. The motor cortex is the part of the brain where the brain signals for limb motions originates. Several studies have compared motor imagery with motor execution. In both paradigms, the brain signals have patterns which can be used for classification.

In the recent years, the research literature on BMI systems shifted to implementing Deep Learning (DL) models to map the brain signals into the desired command. In addition, DL has shown good performance in robotics applications. Eliminating one or more of intermediate processing steps, such as preprocessing, feature extraction and classification is one of the advantages of applying DL in BMI/BCI systems. There are two ways to implement CNNs on BMI/BCI systems. In the first method, the raw EEG (electroencephalography) data are directly fed into the CNN. The second implementation is to use the CNN only as a classifier, and employ other algorithms for the feature extraction, such as Short-time Fourier Transform (STFT), or Common Spatial Patterns (CSP) and more advanced versions of it, like Filter Bank Common Spatial Pattern (FBCSP).

The deep neural network can do these two functions simultaneously: 1) feature extraction and 2) classification. However, transfer learning has not been yet fully utilized to improve the performance of the deep learning architectures for the BMI systems. Therefore, in this thesis the main motivation is to improve the performance of CNNs by transfer learning. Especially, the impact of transfer learning according to window size and hop size is deeply investigated. Window size is the number of data points taken from the brain signal for classification, while the hop size is the number of data points this window jumps each time. The reason why these parameters are so important is because window size is strongly related to the time it takes to map the user’s brain signals to the robot motion. Therefore, the window size impacts the latency between the command and the robot response. Hop size also impacts the latency due to classification time correlation with the number of augmented samples.

We implemented the proposed algorithm in motor and imaginary task using the brain signals. In addition to implementing transfer learning for similar tasks using the same subject, we implemented transfer learning among different subjects. The experimental results show that transfer learning can successfully be utilized to increase the performance of deep learning architectures for brain signal classification applications. A larger window size corresponds to a larger accuracy, but a shorter window size can be utilized by increasing its accuracy through transfer learning. Accuracy can also be increased through a small hop size.

The trained CNNs using transfer learning are also implemented to map in real time the brain signals to the robot motion. In the first implementation, the humanoid robot with 18 degrees of freedom developed in our laboratory is controlled using brain signals. We also implemented the imaginary motor task to control the robot action. As stated above there is a tradeoff between window size and robot command accuracy. A small window size leads to faster response of the robotic arm, but the accuracy is not optimal. As the window size gets bigger, the robotic arm responses with higher accuracy, but the motion takes longer to start.

This thesis shows that transfer learning can successfully utilized to increase the performance of deep learning architectures on brain signal classification. The results show a satisfying improvement in the CNNs performance.

論文の公開元へ

この論文で使われている画像

関連論文

関連論文をもっと見る

参考文献

[1] Wolpaw JR, Birbaumer N, McFarland DJ, Pfurtscheller G, Vaughan TM (2002) Brain– computer interfaces for communication and control. Clin Neurophysiol 113(6):767–791

[2] Nicolas-Alonso, Luis Fernando; Gomez-Gil, Jaime. 2012. "Brain Computer Interfaces, a Review." Sensors 12, no. 2: 1211-1279 doi: 10.3390/s120201211

[3] Chang S. Nam, Anthon Nijholt, Fabien Lotte, Brain–Computer Interfaces Handbook: Technological and Theoretical Advances, CRC Press, 2018

[4] Guger, Christoph & Tangermann, Michael & Allison, Brendan. (2021). Brain-Computer Interface Research: A State-of-the-Art Summary 9. 10.1007/978-3-030-60460-8_1.

[5] Berger, H. 1929. Über das Elektrenkephalogramm des Menschen. Archiv für Psychiatrie und Nervenkrankheiten 87 (1): 527–570.

[6] Estrin, T. 1965. On-line electroencephalosraphic digital computing system. Electroencephalography and Clinical Neurophysiology 19 (5): 524–526.

[7] Vidal, J.J. 1973. Toward direct brain-computer communication. Annual Review of Biophysics and Bioengineering 2: 157–180.

[8] Wolpaw, J.R. Brain–computer interfaces as new brain output pathways. J. Physiol. 2007, 579, 613–619.

[9] M.A. Hofman, D. Falk, Evolution of the Primate Brain: From Neuron to Behavior, Elsevier Science, 2012.

[10] G. Buzsaki, Rhythms of the Brain, Oxford University Press, 2006.

[11] R. Melillo, G. Leisman, Neurobehavioral Disorders of Childhood: An Evolutionary Perspective, Springer, 2004.

[12] J. Illes, B.J. Sahakian, The Oxford Handbook of Neuroethics, Oxford Univ Pr, 2011.

[13] T. Felzer, On the possibility of developing a brain-computer interface (BCI), technical  University of Darmstadt, Darmstadt, Germany, Tech. Rep. (2001).

[14] E. Niedermeyer, F.H.L. Da Silva, Electroencephalography: Basic Principles, Clinical Applications, and Related Fields, Lippincott Williams & Wilkins, 2004.

[15] B. He, XVI, 488 p.203 Illus. with CD-ROM. 0306486091 in: B. He (Ed.), Neural Engineering, Neural Engineering, Springer, Berlin, 2005.

[16] K. Blinowska, P. Durka, Electroencephalography (EEG), Wiley Encycl. Biomed. Eng. (2006).

[17] Li, L., Wang, J., Xu, G., Li, M., and Xie, J. (2015). The study of objectoriented motor imagery based on EEG suppression. PLoS ONE 10:e0144256. doi: 10.1371/journal.pone.0144256

[18] M. Alimardani, Sh. Nishio and H. Ishiguro, “Brain-Computer Interface and Motor Imagery Training: The Role of Visual Feedback and Embodiment”, Evolving BCI Therapy-Engaging Brain State. Dynamics 2, 64 (2018) ,doi: 10.5772/intechopen.78695

[19] G. Pfurtscheller and C. Neuper, "Motor imagery and direct brain- computer communication," in Proceedings of the IEEE, vol. 89, no. 7, pp. 1123-1134, July 2001, doi: 10.1109/5.939829.

[20] F. Nijboer, A. Furdea, I. Gunst, J. Mellinger, D. J. McFarland, N. Birbaumer, A. Kübler, An auditory brain–computer interface (BCI), Journal of Neuroscience Methods, Volume 167, Issue 1, 2008, Pages 43-50, ISSN 0165-0270, doi.org/10.1016/j.jneumeth.2007.02.009.

[21] B. Blankertz, G. Dornhege, M. Krauledat, K. R.Müller, G. Curio, The non-invasive Berlin Brain–Computer Interface: Fast acquisition of effective performance in untrained subjects, NeuroImage, Volume 37, Issue 2, 2007, Pages 539-550, ISSN 1053-8119, doi.org/10.1016/j.neuroimage.2007.01.051.

[22] Alimardani M, Nishio S, Ishiguro H (2016) The Importance of Visual Feedback Design in BCIs; from Embodiment to Motor Imagery Learning.PLOS ONE 11(9): e0161945. doi.org/10.1371/journal.pone.0161945

[23] M. Alimardani, Sh. Nishio and H. Ishiguro, “Brain-Computer Interface and Motor  Imagery Training: The Role of Visual Feedback and Embodiment”, Evolving BCI Therapy-Engaging Brain State. Dynamics 2, 64 (2018) ,doi: 10.5772/intechopen.78695

[24] Neuper C, Scherer R, Reiner M, Pfurtscheller G. Imagery of motor actions: differential effects of kinesthetic and visual-motor mode of imagery in single-trial EEG. Brain Res Cogn Brain Res. 2005 Dec;25(3):668-77. doi: 10.1016/j.cogbrainres.2005.08.014. Epub 2005 Oct 19. PMID: 16236487.

[25] Sale P, Franceschini M. Action observation and mirror neuron network: a tool for motor stroke rehabilitation. Eur J Phys Rehabil Med. 2012 Jun;48(2):313-8. Epub 2012 Apr 20. PMID: 22522432.

[26] Ono T, Kimura A, Ushiba J. Daily training with realistic visual feedback improves reproducibility of event-related desynchronisation following hand motor imagery. Clin Neurophysiol. 2013 Sep;124(9):1779-86. doi: 10.1016/j.clinph.2013.03.006. Epub 2013 May 3. PMID: 23643578.

[27] Batula, Alyssa & Mark, Jesse & Kim, Youngmoo & Ayaz, Hasan. (2017). Comparison of Brain Activation during Motor Imagery and Motor Movement Using fNIRS. Computational Intelligence and Neuroscience. 2017. 1-12. 10.1155/2017/5491296.

[28] Kim, Do-Hyung & Yeom, Hong Gi & Kim, Minjung & Kim, Seung & Yang, Tae-Won & Kwon, Oh-Young & Kim, Young-Soo. (2021). Introduction of brain computer interface to neurologists. Annals of Clinical Neurophysiology. 23. 92-98. 10.14253/acn.2021.23.2.92.

[29] Barrett, G., Shibasaki, H., and Neshige, R. (1986). Cortical potentials preceding voluntary movement: evidence for three periods of preparation in man. Electroencephalogr. Clin. Neurophysiol. 63, 327–339. doi: 10.1016/0013- 4694(86)90017-9

[30] Georgopoulos AP, Kettner RE, Schwartz AB. Primate motor cortex and free arm movements to visual targets in three-dimensional space. II. Coding of the direction of movement by a neuronal population. J Neurosci 1988;8:2928-2937.

[31] Hochberg LR, Bacher D, Jarosiewicz B, Masse NY, Simeral JD, Vogel J, et al. Reach  and grasp by people with tetraplegia using a neurally controlled robotic arm. Nature 2012;485:372-375. crossref pmid pmc

[32] Collinger JL, Wodlinger B, Downey JE, Wang W, Tyler-Kabara EC, Weber DJ, et al. High-performance neuro-prosthetic control by an individual with tetraplegia. Lancet 2013;381:557-564.

[33] Catrambone V, Averta G, Bianchi M, et al. Toward brain-heartcomputer interfaces: a study on the classifcation of upper limb movements using multisystem directional estimates. J. Neural Eng 2021,doi:10.1088/1741-2552/abe7b9

[34] Bartolo A et al 2008 Cognitive approach to the assessment of limb apraxia Clin. Neuropsychol. 22 27–45

[35] Petreska B et al 2007 Apraxia: a review Prog. Brain Res. 164 61–83

[36] Canzano L et al 2016 The representation of objects in apraxia: From action execution to error awareness Front. Hum. Neurosci. 10 39

[37] S. Lim, D. P. Jang and H. Choi, "Deep learning classification features visualization for arm movement brain-computer inter-face," 2020 8th International Winter Conference on Brain-Computer Interface (BCI), 2020, pp. 1-3, doi: 10.1109/BCI48061.2020.9061651.

[38] Quiles, Eduardo et al. “Low-Cost Robotic Guide Based on a Motor Imagery BrainComputer Interface for Arm Assisted Re-habilitation.” International journal of environmental research and public health vol. 17,3 699. 21 Jan. 2020, doi:10.3390/ijerph17030699

[39] Bandara, Sanjaya & Arata, Jumpei & Kiguchi, Kazuo. (2018). A Non-Invasive BCI Approach for Predicting Motion Inten-tion of ADL Tasks for an Upper-Limb Wearable Robot. International Journal of Advanced Robotic Systems. 10.1177/1729881418767310.

[40] Korik A, Sosnik R, Siddique N, Coyle D. Decoding Imagined 3D Hand Movement Trajectories From EEG: Evidence to Support the Use of Mu, Beta, and Low Gamma Oscillations. Front Neurosci. 2018 Mar 20;12:130. doi: 10.3389/fnins.2018.00130.  PMID: 29615848; PMCID: PMC5869206.

[41] P. Johan, J.R. del Milla´n, V. Gerolf, L. Eileen, G. Ferran, F. Pierre, et al., Adaptive shared control of a brain actuated simulated wheelchair, Proc. 2007 IEEE 10th Int. Conf. Rehabil. Rob. (2007) 408-414.

[42] B. Obermaier, G. Muller, G. Pfurtscheller, Virtual keyboard controlled by spontaneous EEG activity, IEEE Trans. Neural Syst. Rehabil. Eng. 11 (2003) 422-426.

[43] B. Blankertz, G. Dornhege, M. Krauledat, K.R. Mu¨ ller, V. Kunzmann, F. Losch, et al., The Berlin Brain-Computer Interface: EEG-based communication without subject training, Hand 3 (2006) C4.

[44] B. Rebsamen, E. Burdet, C. Guan, C.L. Teo, Q. Zeng, M. Ang, et al., Controlling a wheelchair using a BCI with low information transfer rate, 10th IEEE Int. Conf. Rehabil. Rob. (2007) 1003-1008.

[45] R. Brice, C.L. Teo, Z. Qiang, A. Marcelo, B. Etienne, G. Cuntai, et al., Controlling a wheelchair in a building using thought, IEEE Intell. Syst. (2007) 1-8.

[46] F. Galan, M. Nuttin, E. Lew, P.W. Ferrez, G. Vanacker, J. Philips, et al., A brainactuated wheelchair: asynchronous and non-invasive brain-computer interfaces for continuous control of robots, Clin. Neurophysiol. 119 (2008) 2159-2169.

[47] T. Geng, J.Q. Gan, Motor prediction in brain-computer interfaces for controlling mobile robots, 30th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (2008) 634-637.

[48] P. Shenoy, M. Krauledat, B. Blankertz, R.P. Rao, K.R. Muller, Towards adaptive classification for BCI, J. Neural. Eng. 3 (2006) R13-23.

[49] A. Nijholt, D. Tan, Brain-computer interfacing for intelligent systems, IEEE Intell.Syst. 23 (2008) 72-79.

[50] B. Rebsamen, C.L. Teo, Q. Zeng, M.H. Ang Jr, E. Burdet, C. Guan, et al., Controlling a wheelchair indoors using thought, IEEE Intell. Syst. 22 (2007) 18-24.

[51] N. Birbaumer, N. Ghanayim, T. Hinterberger, I. Iversen, B. Kotchoubey, A. Kuebler, et al., A spelling device for the paralysed, Nature 398 (1999) 297-298.

[52] J.R. Wolpaw, D.J. McFarland, G.W. Neat, C.A. Forneris, An EEG-based braincomputer interface for cursor control, Electroencephalogr. Clin. Neurophysiol. 78 (1991) 252-259.

[53] Fleiss J L, Cohen J. The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability [J]. Educational and psychological measurement, 1973, 33(3): 613-619

[54] X. Zhao, H. Zhang, G. Zhu, F. You, S. Kuang and L. Sun, "A Multi-Branch 3D Convolutional Neural Network for EEG-Based Motor Imagery Classification," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 27, no. 10, pp. 2164-2177, Oct. 2019, doi: 10.1109/TNSRE.2019.2938295.

[55] McHugh, Mary L. “Interrater reliability: the kappa statistic.” Biochemia medica vol. 22,3 (2012): 276-82.

[56] P. Meinicke, M. Kaper, F. Hoppe, M. Heumann, H. Ritter, Improving transfer rates in brain computer interfacing: a case study, Adv. Neural Inf. Process. Syst. (2003) 1131- 1138.

[57] Hossain, Delowar & Capi, Genci. (2017). Genetic Algorithm Based Deep Learning Parameters Tuning for Robot Object Recognition and Grasping. International Journal of Mechanical, Aerospace, Industrial, Mechatronic and Manufacturing Engineering. 11. 591-595.

[58] Hossain, Delowar & Capi, Genci. (2017). Multiobjective evolution for deep learning and its robotic applications. 1-6. 10.1109/IISA.2017.8316404.

[59] S. Nilwong, D. Hossain, S. I. Kaneko, G. Capi, “Deep Learning-Based Landmark Detection for Mobile Robot Outdoor Localization,” Machines, vol. 7, issue 2, 2019, pp. 1-14.

[60] Schirrmeister, Robin Tibor, et al. "Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG." arXiv preprint arXiv:1703.05051 (2017).

[61] Liu Jingwei, Cheng Yin, Zhang Weidong. “deep learning EEG response representation  for brain computer interface.” Proceedings of the 34th Chinese Control Conference, 2015.

[62] Tang, Xianlun, Na Zhang, Jialin Zhou, and Qing Liu. "Hiddenlayer visible deep stacking network optimized by PSO for motor imagery EEG recognition." Neurocomputing 234 (2017): 1-10.

[63] J. Zhang, C. Yan and X. Gong, "Deep convolutional neural network for decoding motor imagery based brain computer interface," 2017 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Xia-men, 2017, pp. 1- 5, doi: 10.1109/ICSPCC.2017.8242581.

[64] T. Uktveris and V. Jusas, “Application of convolutional neural networks to four-class motor imagery classification problem,” Inf. Technol. Control, vol. 46, no. 2, pp. 260– 273, 2017.

[65] Tabar, Yousef Rezaei, and Ugur Halici. "A novel deep learning approach for classification of EEG motor imagery sig-nals." Journal of neural engineering 14, no. 1 (2016): 016003.

[66] S. Kumar, A. Sharma, K. Mamun and T. Tsunoda, "A Deep Learning Approach for Motor Imagery EEG Signal Classifica-tion," 2016 3rd Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE), Nadi, 2016, pp. 34-39, doi: 10.1109/APWC-on-CSE.2016.017.

[67] Yang H, Sakhavi S, Ang KK, Guan C. On the use of convolutional neural networks and augmented CSP features for multi-class motor imagery of EEG signals classification. Conf Proc IEEE Eng Med Biol Soc. 2015; 2015: 2620-2623. doi:10.1109/EMBC.2015. 7318929

[68] Kai Keng Ang, Zheng Yang Chin, Haihong Zhang and Cuntai Guan, "Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface," 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computa-tional Intelligence), 2008, pp. 2390-2397, doi: 10.1109/IJCNN.2008.4634130.

[69] S. Chua, Y. Tao and R. Q. So, "Improved Decoding of EEG-Based Motor Imagery  Using Convolutional Neural Network and Data Space Adaptation," 2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Chicago, IL, USA, 2019, pp. 1-4, doi: 10.1109/BHI.2019.8834564.

[70] L. Mousapour, F. Agah, S. Salari and M. Zare, "A Novel Approach to Classify MotorImagery EEG with Convolutional Neural Network Using Network Measures," 2018 4th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS), Tehran, Iran, 2018, pp. 43-47, doi: 10.1109/ICSPIS.2018.8700560.

[71] M. Dai, D. Zheng, S. Liu, and P. Zhang, “Transfer kernel common spatial patterns for motor imagery brain-computer interface classifi cation,” Computational and Mathematical Methods in Medicine, vol. 2018, 2018.

[72] V. Jayaram, M. Alamgir, Y. Altun, B. Scholkopf, and M. Grosse Wentrup, “Transfer learning in brain-computer interfaces,” IEEE Com putational Intelligence Magazine, vol. 11, no. 1, pp. 20–31, 2016.

[73] A. M. Azab, L. Mihaylova, K. K. Ang, and M. Arvaneh, “Weighted transfer learning for improving motor imagery-based brain–computer interface,” IEEE Trans. on Neural Systems and Rehabilitation Engi neering, vol. 27, no. 7, pp. 1352–1359, 2019.

[74] I. Hossain, A. Khosravi, I. Hettiarachchi, and S. Nahavandi, “Multiclass informative instance transfer learning framework for motor imagery based brain-computer interface,” Computational Intelligence and Neu roscience, vol. 2018, 2018.

[75] P. Zanini, M. Congedo, C. Jutten, S. Said, and Y. Berthoumieu, “Trans fer learning: a Riemannian geometry framework with applications to brain-computer interfaces,” IEEE Trans. on Biomedical Engineering, vol. 65, no. 5, pp. 1107–1116, 2018.

[76] M. Parvan, A. R. Ghiasi, T. Y. Rezaii and A. Farzamnia, "Transfer Learning based Motor Imagery Classification using Convolutional Neural Networks," 2019 27th Iranian Conference on Electrical Engineering (ICEE), 2019, pp. 1825-1828, doi: 10.1109/IranianCEE.2019.8786636.

[77] O. Akinari. Convolutional Neural Network Transfer Learning Applied to the Affective Auditory P300-Based BCI Journal of Robotics and Mechatronics; Tokyo 巻 32, 号 4,  (Aug 2020): 731-737. DOI:10.20965/jrm.2020.p0731

[78] Roy S, Chowdhury A, McCreadie K, Prasad G (2020) Deep learning based intersubject continuous decoding of motor imagery for practical brain-computer interfaces. Front Neurosci https://doi.org/10.3389/fnins.2020.00918

[79] Deng, L. (2014). A tutorial survey of architectures, algorithms, and applications for deep learning, APSIPA Transactions on Signal and Information Processing 3.

[80] https://www.braininstitute.com.au/equipment

[81] Jason P. Gallivan, D. Adam McLean, J. Randall Flanagan, Jody C. Culham, Where One Hand Meets the Other: Limb-Specific and Action-Dependent Movement Plans Decoded from Preparatory Signals in Single Human Frontoparietal Brain Areas, Journal of Neuroscience 30 January 2013, 33 (5) 1991-2008; DOI: 10.1523/JNEUROSCI.0541- 12.2013

[82] Kleih SC, Riccio A, Mattia D, Kaiser V, Friedrich EVC, Scherer R, Kübler A. et al. Motivation influences performance in SMR-BCI. na. In: Proceeding of the 5th International Brain-Computer Interface Conference. 2011:108-111 doi:10.3217/978-3- 85125-260-6-81

[83] R. Leeb, F. Lee, C. Keinrath, R. Scherer, H. Bischof and G. Pfurtscheller, "Brain– Computer Communication: Motivation, Aim, and Impact of Exploring a Virtual Apartment," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 15, no. 4, pp. 473-482, Dec. 2007, doi: 10.1109/TNSRE.2007.906956.

[84] E. P toku and G. Capi, "Object Movement Motor Imagery for EEG based BCI System using Convolutional Neural Networks," 2021 9th International Winter Conference on Brain Computer Interface (BCI), 2 021, pp. 1 5, doi: 10.1109/BCI51272.2021. 9385319.

[85] S. Sugiyama, E Petoku, R Takahashi G Capi Optimizing Convolutional Neural Networks to Controlthe Robotic Hand using Brain Signals ””, International Conference on Micromechatronics forInformation and Precision Equipment (MIPE2022), Organized Session on Machine Learning and Intelligent Mechanical Systems, Submitted.

[86] E. Petoku, R. Takahashi, G . Capi Improving the convolutional neural network performance through transfer learning for brain machine interface systems” Accepted

[87] R. Takahashi, S. Sugiyama, E. Petoku, A. Shirai G. Capi Impro vi ng the performance of CNNs through transfer learning: A BMI application ””, The Society of Instrument and Control E ngineers

参考文献をもっと見る

全国の大学の
卒論・修論・学位論文
を
一発検索！

この論文の関連論文を見る