Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Bulletin of Electrical Engineering and Informatics
Nilesh N. Thorat
MIT Art, Design and Technology University
Electrical & Electronics Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Transfer learning-based texture-enhanced convolutional neural networks over plant disease identification Nilesh N. Thorat; Mangesh D. Salunke; Aarti P. Pimpalkar; Mayuresh B. Gulame; Babeetta Bbhagat; Sumit Hirve; Saleha Saudagar; Madhura Eknath Sanap
Bulletin of Electrical Engineering and Informatics Vol 15, No 2: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i2.10510

Abstract

The global agricultural productivity and food security take serious threats due to the presence of plant diseases; thus, early and accurate diagnosis becomes the key to successful management of the disease. The traditional diagnosis techniques that rely on visual observation are time-based, subjective, and cannot be implemented on a large scale. Recent development in machine learning and computer vision provides possible solutions to automated plant disease detection. This paper suggests a plant disease identification with transfer learning (PDD-TL) model with the preprocessing, segmentation, feature extraction, and disease prediction phases. In the initial stages, median filtering is used to simplify the image quality, after which cells affected by the disease are segmented with the help of the integration of adaptive pixels in joint segmentation (IAPJS) algorithm. Multi-texton and pyramid histogram of oriented gradients (PHOG) are the discriminative features extracted. The classification of the disease is done with a new triple convolutional activation CNN with transfer learning (CNN-TCA-TL). In contrast to the current methods that use either a pure deep learning method or handcrafted features, the framework proposed explicitly employs both the use of texture descriptors and transferable deep representations, which retain fine-grained structural details. The experimental findings prove that CNN-TCA-TL has an accuracy of 0.92 which will prove that it is effective.
Improved feature-based hybrid deep learning for multiclassification of ultrasound thyroid nodules Mayuresh Gulame; Deepthi D. Kulkarni; Priya Khune; Nilesh N. Thorat; Ashwini G. Shahapurkar; Vijaya S. Patil; Sumit Arun Hirve; Aarti Pimpalkar
Bulletin of Electrical Engineering and Informatics Vol 15, No 1: February 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i1.10447

Abstract

Ultrasonography is frequently used to identify thyroid nodules. Because of their internal features, variable appearances, and ill-defined borders, it might be difficult for a hospitalist to distinguish amongst benign and malignant forms of the nodule based solely on visual inspection. Although deep learning, a subset of artificial intelligence, has significantly advanced medical image recognition, challenges remain in achieving accurate and efficient diagnosis of thyroid nodules. To identify and classify thyroid nodules, this study uses an innovative hybrid DL-assisted multi-classification technique. A median blur eliminates salt-and-pepper noise, and this is followed by segmentation using a method based on enhanced pooling integrated U-Net (EPIU-Net). To produce a single histogram series, features are recovered from the segmented image, including multi-texton, and local ternary pattern (LTP) based patterns. Following feature extraction, the data is expanded and input into a fusion classification model utilizing Deep Maxout and convolutional neural network (CNN) to categorize nodules. This work uses 2 types of datasets and for both datasets, we achieved great results with our hybrid technique across all performance criteria. 0.976, 0.008, 0.992, and 0.017 are the corresponding values for accuracy, false discovery rate (FDR), sensitivity, false negative rate (FNR). Moreover proposed work is verified by k-fold method.
Co-Authors Aarti P. Pimpalkar Aarti Pimpalkar Ashwini G. Shahapurkar Babeetta Bbhagat Deepthi D. Kulkarni Madhura Eknath Sanap Mangesh D. Salunke Mayuresh B. Gulame Mayuresh Gulame Priya Khune Saleha Saudagar Sumit Arun Hirve Sumit Hirve Vijaya S. Patil