Gaurav Dhiman
Wattana Viriyasitavat
Atulya K. Nagar- 1Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon
- 2University Centre for Research and Development, Department of Computer Science and Engineering, Chandigarh University, Mohali, India
- 3Department of Computer Science and Engineering, Graphic Era Deemed to be University, Dehradun, India
- 4Division of Research and Development, Lovely Professional University, Phagwara, India
- 5Chitkara University Institute of Engineering and Technology, Chitkara University, Chandigarh, Punjab, India
- 6Department of Computer Science, Government Bikram College of Commerce, Patiala, India
- 7Faculty of Commerce and Accountancy, Chulalongkorn University, Bangkok, Thailand
- 8Liverpool Hope University, Liverpool, United Kingdom
Editorial on the Research Topic
Machine and deep-learning for computational neuroscience
The field of computational neuroscience has rapidly evolved over the past few decades, fueled by advancements in technology and the accumulation of large-scale neural data (Shen and Saab, 2021; Shen et al., 2021; Abdellatef et al., 2022; Sayour et al., 2022). With the emergence of machine and deep-learning techniques, there has been a shift toward utilizing these methods to extract insights from complex neural data, leading to unprecedented progress in understanding the brain's inner workings (Helwan et al., 2021; Saab and Jaafar, 2021; Saab et al., 2021; Hammoud et al., 2022). Machine and deep-learning approaches (Abbas et al., 2021; Gerges et al., 2021; Tarhini et al., 2022) offer several advantages over traditional statistical techniques, including their ability to handle large and complex datasets, learn from data, and make predictions based on patterns and relationships within the data. Machine and deep-learning techniques have been applied to various areas of computational neuroscience, including brain-computer interfaces, neuroimaging, and neural decoding (Tarhini et al., 2020; Hammoud et al., 2021; Sorkhoh et al., 2021). These approaches have led to new insights into brain function and the development of novel diagnostic and therapeutic tools (Chamra and Harmanani, 2020; Fakhoury et al., 2022) for neurological disorders. For example, deep-learning models have been used to accurately predict epileptic seizures, diagnose Alzheimer's disease, and analyze neural network dynamics (Prakash and Lina, 2021; Senay et al., 2021; Tohme and Martin, 2021; Tohme et al., 2021). In this Research Topic, we accepted six papers that showcase the latest advancements in machine and deep-learning for computational neuroscience.
The first paper, “Transfer learning-based modified inception model for the diagnosis of Alzheimer's disease (Sharma et al.),” proposes a new deep-learning model that utilizes transfer learning to diagnose Alzheimer's disease with high accuracy. The model is based on a modified version of the inception model and was trained on a large dataset of brain images. The results demonstrate that the proposed model outperforms traditional machine learning methods and can be a useful tool for early diagnosis of Alzheimer's disease.
The second paper, “A multi-frame network model for predicting seizures based on sEEG and iEEG data (Lu et al.),” presents a new deep-learning model that can predict seizures with high accuracy using intracranial and scalp electroencephalogram (EEG) data. The model is based on a novel multi-frame network architecture and was trained on a large dataset of epilepsy patients. The results demonstrate that the proposed model can accurately predict seizures up to 20 seconds in advance, which could be a game-changer for epilepsy treatment.
The third paper, “Analysis of instantaneous brain interactions contribution to a motor imagery classification task (Cristancho Cuervo et al.),” investigates the contribution of instantaneous brain interactions to a motor imagery classification task. The study uses a machine learning approach to analyze the interactions between brain regions during a motor imagery task. The results demonstrate that instantaneous brain interactions play a crucial role in motor imagery classification and could be used to improve brain-computer interfaces.
The fourth paper, “Research on the network handoff strategy based on the best access point name decision (Shu et al.),” proposes a new machine learning-based network handoff strategy for wireless communication networks. The model uses a decision tree algorithm to select the best access point for a mobile device, which could improve the quality of service for wireless users.
The fifth paper, “Improved space breakdown method—A robust clustering technique for spike sorting (Ardelean et al.),” presents a new clustering technique for spike sorting. The method uses a machine learning approach to improve the accuracy of spike sorting, which is a crucial step in analyzing neural data. The results demonstrate that the proposed method outperforms traditional spike sorting methods and could be a useful tool for studying neural circuits.
The sixth and final paper, “Stability of mental motor-imagery classification in EEG depends on the choice of classifier model and experiment design, but not on signal preprocessing (Rosenfelder et al.),” investigates the stability of mental motor-imagery classification in EEG. The study compares different machine learning classifiers and experimental designs and finds that the choice of classifier and experimental design have a significant impact on the stability of the classification, while signal preprocessing does not.
In summary, the papers presented in this Research Topic demonstrate the power of machine and deep-learning for computational neuroscience. These approaches have the potential to revolutionize our understanding of brain function and improve diagnosis and treatment of neurological disorders. We hope that this Research Topic will inspire further research in this exciting and rapidly evolving field.
Author contributions
All authors have equally contributed in this Research Topic. All authors contributed to the article and approved the submitted version.
Acknowledgments
We would like to express our sincere gratitude to the Frontiers in Computational Neuroscience team for their hard work and dedication in making this Research Topic a success.
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
Abbas, N., Nasser, Y., Shehab, M., and Sharafeddine, S. (2021). “Attack-specific feature selection for anomaly detection in software-defined networks,” in 2021 3rd IEEE Middle East and North Africa COMMunications Conference (MENACOMM) (New York, NY: IEEE), 142–146.
Abdellatef, H., Khalil-Hani, M., Shaikh-Husin, N., and Ayat, S. O. (2022). Accurate and compact convolutional neural network based on stochastic computing. Neurocomputing 471, 31–47. doi: 10.1016/j.neucom.2021.10.105
Chamra, A., and Harmanani, H. (2020). “A smart green house control and management system using iot,” in 17th International Conference on Information Technology–New Generations (ITNG 2020) (Cham: Springer) 641–646.
Fakhoury, M., Michael, F., and Sama, F. S. (2022). “Behavioral paradigms for assessing cognitive functions in the chronic social defeat stress model of depression.” in Translational Research Methods for Major Depressive Disorder (New York, NY: Springer), 147–164.
Gerges, F., Shih, F., and Azar, D. (2021). “Automated diagnosis of acne and rosacea using convolution neural networks,” In 2021 4th International Conference on Artificial Intelligence and Pattern Recognition, 607–613
Hammoud, A., Otrok, H., Mourad, A., and Dziong, Z. (2021). Stable federated fog formation: an evolutionary game theoretical approach. Fut. Generat. Comput. Syst. 124, 21–32. doi: 10.1016/j.future.2021.05.021
Hammoud, A., Otrok, H., Mourad, A., and Dziong, Z. (2022). On demand fog federations for horizontal federated learning in IoV. IEEE Transact. Netw. Serv. Manage. 22, 370. doi: 10.1109/TNSM.2022.3172370
Helwan, A., Ma'aitah, M. K. S., Uzelaltinbulat, S., Altobel, M. Z., and Darwish, M. (2021). Gaze Prediction Based on Convolutional Neural Network. In International Conference on Emerging Technologies and Intelligent Systems (Cham: Springer), 215–224.
Prakash, C. D., and Lina, J. K. (2021). It GAN DO better: GAN-based detection of objects on images with varying quality. IEEE Transact. Image Process. 30, 9220–9230. doi: 10.1109/TIP.2021.3124155
Saab, S. S., and Jaafar, R. H. (2021). A proportional-derivative-double derivative controller for robot manipulators. Int. J. Control 94, 1273–1285. doi: 10.1080/00207179.2019.1642518
Saab, S. S., Shen, D., Orabi, M., Kors, D., and Jaafar, R. H. (2021). Iterative learning control: practical implementation and automation. IEEE Transact. Industr. Electron. 69, 1858–1866. doi: 10.1109/TIE.2021.3063866
Sayour, M. H., Kozhaya, S. E., and Saab, S. S. (2022). Autonomous robotic manipulation: real-time, deep-learning approach for grasping of unknown objects. J. Robot. 2022, 256. doi: 10.1155/2022/2585656
Senay, B., Toufic, C., Danilo, C., and Shraddha, M. (2021). Ultrasound-guided therapies in the Neuro ICU. Curr. Treatment Opt. Neurol. 23, 24. doi: 10.1007/s11940-021-00679-z
Shen, D., Huo, N., and Saab, S. S. (2021). A probabilistically quantized learning control framework for networked linear systems. IEEE Transact. Neural Netw. Learn. Syst. 21, 559. doi: 10.1109/TNNLS.2021.3085559
Shen, D., and Saab, S. S. (2021). Noisy output based direct learning tracking control with markov nonuniform trial lengths using adaptive gains. IEEE Transact. Automat. Control. 21, 310. doi: 10.1109/TAC.2021.3106860
Sorkhoh, I., Assi, C., Ebrahimi, D., and Sharafeddine, S. (2021). Optimizing information freshness for mec-enabled cooperative autonomous driving. IEEE Transact. Intell. Transport. Syst. 21, 1961. doi: 10.1109/TITS.2021.3119961
Tarhini, A., Danach, K., and Harfouche, A. (2020). Swarm intelligence-based hyper-heuristic for the vehicle routing problem with prioritized customers. Annal. Operat. Res. 20, 1–22. doi: 10.1007/s10479-020-03625-5
Tarhini, A., Harfouche, A., and De Marco, M. (2022). Artificial intelligence-based digital transformation for sustainable societies: The prevailing effect of COVID-19 crises. Pacific Asia J. Assoc. Informat. Syst. 14, 1.
Tohme, P., and Martin, K. (2021). Mentalizing glasses: multifocal attention in mentalization-based treatment and the role of the supervision. Front. Psychol. 12, 708393. doi: 10.3389/fpsyg.2021.708393
Keywords: machine learning, deep learning, neuroscience, classification, disease
Citation: Dhiman G, Viriyasitavat W and Nagar AK (2023) Editorial: Machine and deep-learning for computational neuroscience. Front. Comput. Neurosci. 17:1218895. doi: 10.3389/fncom.2023.1218895
Received: 08 May 2023; Accepted: 23 June 2023;
Published: 04 July 2023.
Edited and reviewed by: Si Wu, Peking University, China
Copyright © 2023 Dhiman, Viriyasitavat and Nagar. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Gaurav Dhiman, gdhiman0001@gmail.com