Copyright © 2025 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{167147,
        author = {Dr. Manukonda Divya and Bussa Uday Kiran},
        title = {PREDICTIVE MODEL-BASED SELECTION OF DEEP NEURAL NETWORKS FOR EMBEDDED IMAGE CLASSIFICATION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {3},
        pages = {400-406},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=167147},
        abstract = {Efficient and accurate picture categorization in the realm of embedded systems is being pursued via the investigation of deep neural networks (DNNs) due to high demand. Nevertheless, the task of choosing the most suitable DNN structure for certain embedded applications continues to be difficult because of limitations on processing resources, power use, and memory.This research introduces an adaptive algorithm to ascertain the appropriate Deep Neural Network (DNN) model for a given input, taking into account the desired level of accuracy and inference time. Our methodology employs machine learning to create a prediction model that efficiently chooses a pre-trained deep neural network (DNN) based on a given input and optimisation constraint. We implement our methodology to the job of image classification and assess its performance on a Jetson TX2 embedded deep learning platform, using the ImageNet ILSVRC 2012 validation dataset for evaluation. We evaluate a variety of prominent deep neural network (DNN) models.

},
        keywords = {Deep learning, Embedded, Predictive model, Inference, Accuracy },
        month = {August},
        }