Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206812,
        author = {Akshata U. Bhomkar and Prof. Deeksha and Nisarga S. Bhat and Pooja M. Waingankar and Sudha V. Gatteppanavar},
        title = {Implementation of Leaky Integrate-and-Fire Neuron Model for Handwritten Character Recognition with a Deployment Demonstration on Jetson Nano},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {547-550},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206812},
        abstract = {In this paper, the design, simulation, and implementation of the LIF model are performed for recognizing handwritten characters. At first, the spike response of the neuron to different amounts of input currents was analyzed in MATLAB. Then, the accuracy of the results was verified in order to confirm the correct behavior of the neuron under different circumstances. In the next step, the same model was implemented using Python code to perform classification based on EMNIST data set, converting the pixel values to spikes in a period of time. Next, the model was run on the NVIDIA Jetson Nano Developer Kit, resulting in a working system with acceptable performance in an actual environment. As a result, it could be understood that inference is possible even in real-time mode without a significant amount of energy consumption.},
        keywords = {Edge AI, EMNIST dataset, Jetson Nano, Leaky Integrate-and-Fire neuron, neuromorphic computing, spiking neural networks, temporal coding.},
        month = {July},
        }