Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Indonesian Journal of Electrical Engineering and Computer Science
Singh, Seema
Unknown Affiliation
Computer Science & IT Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Hybrid adaptive neural network for remote sensing image classification Sathyanarayana, Natya; Singh, Seema
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 2: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i2.pp2291-2300

Abstract

The proposed study employed a method for identifying the main contents (category/class) that a remote sensing image (RSI) belongs to, as well as the percentage contribution if the image comprises a significant number of different content types. Histogram based approach has been used to extract the pixel density distribution (PDD) and its normalized form helps to make solution independent from image physical characteristics. A multilayer feedforward artificial neural network (ANN) design has been used to address the classification problem. The architecture included an adaptive form of transfer function, whose slope characteristics changes along with weights as learning progresses. The approach of solution design is computation efficient because it doesn’t apply extensive pre-processing.
Mysore sentinel-2: deep learning for image classification with optimizer exploration Sathyanarayana, Natya; Singh, Seema

Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v34.i1.pp647-657

Abstract

The classification of Sentinel-2 image is presented in this work using a tile based methodology. The Mysore district of India's Karnataka state serves as the subject region of this research. By tiling Sentinel-2 images, we were able to construct a distinct dataset and get approximately 3,000 training samples for the five classes. These images are manually labelled and geo-referenced. Three different optimizers were employed in a thorough analysis with deep learning models such as ResNet50, MobileNetV2, ShuffleNet, and VGG16 to achieve better performance metrics. With a classification accuracy of 98.1% on RESNet50 using ADAM surpassed the others. This facilitates investigating various geographical data analytics applications of the study region.
Characterization of binarized neural networks for efficient deployment on resource-limited edge devices Narayana, Ramya Banavara; Singh, Seema
Indonesian Journal of Electrical Engineering and Computer Science Vol 39, No 3: September 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v39.i3.pp1815-1825

Abstract

This paper delves into binarized neural networks (BNNs) tailored for resource-constrained edge devices. BNNs harness binary weights and activations to amplify efficiency while upholding accuracy. Across diverse network configurations, BNNs consistently outshine traditional neural networks (NNs). A pioneering BNN architecture is developed in LARQ, achieving an impressive. 61% accuracy on the MNIST dataset through binary quantization, weight clipping, and pointwise convolutions. Implementation on the Xilinx PYNQZ2 FPGA board shows far quicker classification rates, with a maximum inference time of 0.00841 milliseconds per image, approximately 10,000 images being classified in this length of time. The time taken per image represents approximately 0.01% of the total inference time. This underscores BNNs' potential to redefine real-time edge computing applications. The paper makes significant strides by elucidating BNNs' performance superiority, proposing an innovative architecture, and validating its prowess through real-world deployment. These findings underscore BNNs as agile, high-performance models primed for edge computing, fostering a new era of real-time processing innovations.
Co-Authors Narayana, Ramya Banavara Sathyanarayana, Natya