A Spiking Neural Network Approach for Autonomous Underwater Object Classification Through Bio-Inspired Deep Learning and Edge Computing
Keywords:
Underwater Object Classification (UOC), Autonomous Underwater Vehicles (AUVs), Constrained Application Protocol (CoAP), Deep Q-Networks (DQN), Field-Programmable Gate Arrays (FPGAs).Abstract
Underwater Object Classification (UOC) is a critical task for Autonomous Underwater Vehicles (AUVs) engaged in underwater exploration and environmental monitoring. This paper explores the integration of bio-inspired deep learning techniques, particularly Spiking Neural Networks (SNN), with edge computing paradigms utilizing Field-Programmable Gate Arrays (FPGAs) and Graphics Processing Units (GPUs), coupled with the Constrained Application Protocol (CoAP) communication protocol. The application of Deep Q-Networks (DQN) for reinforcement learning-based object classification is investigated. The proposed framework aims to enhance the autonomy, efficiency, and adaptability of AUVs in discerning and classifying underwater objects in real-time scenarios. By leveraging the inherent parallelism and energy efficiency of SNNs, along with the computational capabilities of FPGAs and GPUs for accelerated inference, AUVs can perform object classification tasks onboard with reduced latency and energy consumption. Moreover, the integration of CoAP facilitates seamless communication between AUVs and remote servers for data exchange and collaborative decision-making. The utilization of DQN enables AUVs to learn and adapt their classification strategies based on feedback from the environment, thereby improving their performance over time. The proposed approach demonstrates promising results in underwater object classification through experimental validation and simulation studies, paving the way for advanced applications in underwater robotics and exploration. Through experimental validation, the system achieves a remarkable increase in classification accuracy by 15%, as evidenced by adaptability scores ranging from 7.5 to 8.9. These results signify a significant advancement in underwater robotics, paving the way for more efficient and precise exploration and monitoring of underwater environments.Top of Form
Downloads
References
Wynn, R. B., Huvenne, V. A., Le Bas, T. P., Murton, B. J., Connelly, D. P., Bett, B. J., ... & Hunt, J. E. (2014). Autonomous Underwater Vehicles (AUVs): Their past, present, and future contributions to the advancement of marine geoscience. Marine geology, 352, 451-468.
González-García, J., Gómez-Espinosa, A., Cuan-Urquizo, E., García-Valdovinos, L. G., Salgado-Jiménez, T., & Escobedo Cabello, J. A. (2020). Autonomous underwater vehicles: Localization, navigation, and communication for collaborative missions. Applied sciences, 10(4), 1256.
Joshi, P., Kalita, A., & Gurusamy, M. (2023). Reliable and Efficient Data Collection in UAV-based IoT Networks. arXiv preprint arXiv:2311.05303.
Fotouhi, A., Qiang, H., Ding, M., Hassan, M., Giordano, L. G., Garcia-Rodriguez, A., & Yuan, J. (2019). Survey on UAV cellular communications: Practical aspects, standardization advancements, regulation, and security challenges. IEEE Communications surveys & tutorials, 21(4), 3417-3442.
Huy, D. Q., Sadjoli, N., Azam, A. B., Elhadidi, B., Cai, Y., & Seet, G. (2023). Object perception in underwater environments: a survey on sensors and sensing methodologies. Ocean Engineering, 267, 113202.
Mehonic, A., Sebastian, A., Rajendran, B., Simeone, O., Vasilaki, E., & Kenyon, A. J. (2020). Memristors—From in‐memory computing, deep learning acceleration, and spiking neural networks to the future of neuromorphic and bio‐inspired computing. Advanced Intelligent Systems, 2(11), 2000085.
Ganeshkumar, S., Maniraj, J., Gokul, S., & Ramaswamy, K. (2023). Biologically Inspired SNN for Robot Control. In Neuromorphic Computing Systems for Industry 4.0 (pp. 289-318). IGI Global.
Fraga-Lamas, P., Ramos, L., Mondéjar-Guerra, V., & Fernández-Caramés, T. M. (2019). A review on IoT deep learning UAV systems for autonomous obstacle detection and collision avoidance. Remote Sensing, 11(18), 2144.
Atyabi, A., MahmoudZadeh, S., & Nefti-Meziani, S. (2018). Current advancements on autonomous mission planning and management systems: An AUV and UAV perspective. Annual Reviews in Control, 46, 196-215.
Sola, Y. (2021). Contributions to the development of deep reinforcement learning-based controllers for AUV (Doctoral dissertation, ENSTA Bretagne-École nationale supérieure de techniques avancées Bretagne).
Nicholson, J. W., & Healey, A. J. (2008). The present state of autonomous underwater vehicle (AUV) applications and technologies. Marine Technology Society Journal, 42(1), 44-51.
Cui, X., Sun, B., Zhu, Y., Yang, N., Zhang, H., Cui, W., ... & Wang, J. (2024). Enhancing efficiency and propulsion in bio-mimetic robotic fish through end-to-end deep reinforcement learning. Physics of Fluids, 36(3).
Jakšić, Z., Devi, S., Jakšić, O., & Guha, K. (2023). A comprehensive review of bio-inspired optimization algorithms, including applications in microelectronics and nanophotonics. Biomimetics, 8(3), 278.
Saleh, A., Sheaves, M., & Rahimi Azghadi, M. (2022). Computer vision and deep learning for fish classification in underwater habitats: A survey. Fish and Fisheries, 23(4), 977-999.
Garg, S., Singh, A., Batra, S., Kumar, N., & Yang, L. T. (2018). UAV-empowered edge computing environment for cyber-threat detection in smart vehicles. IEEE Network, 32(3), 42-51.
Paull, L., Saeedi, S., Seto, M., & Li, H. (2013). AUV navigation and localization: A review. IEEE Journal of Oceanic Engineering, 39(1), 131-149.
Khetavath, S., Sendhilkumar, N.C., Mukunthan, P., Jana, S., Gopalakrishnan, S., Malliga, L., Chand, S.R. and Farhaoui, Y., 2023. An intelligent heuristic manta-ray foraging optimization and adaptive extreme learning machine for hand gesture image recognition. Big Data Mining and Analytics, 6(3), pp.321-335.
Al-Fatlawy, M.H., Sheela, M.S., Yadav, S.K., Srinivasan, V., Gopalakrishnan, S. and Reddy, N.U., 2023, August. Research on Graphic Design Image Processing Technology Based on Newton's method in Photoshop. In 2023 Second International Conference On Smart Technologies For Smart Nation (SmartTechCon) (pp. 710-715). IEEE.
Slavko Prytula, (2020) Underwater Object Detection Dataset, Kaggle.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 S. Jayanthi, S. Vishnupriya, P. Yashaswinii, G. Karthikeyan, N. Ashokkumar, K. A. Karthigeyan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
