Sukanta Ghosh

Mr. Sukanta Ghosh


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 May 2023 in INTELIGENCIA ARTIFICIAL
Verified
Journal Article
Open access
PDF file
SGSukanta Ghosh
Sukanta Ghosh
ASAmar Singh
Amar Singh
SKShakti Kumar
Shakti Kumar
Plant identification and classification are critical to understand, protect, and conserve biodiversity. Traditional plant classification requires years of intensive training and experience, making it difficult for others to classify plants. Plant leaf classification is a challenging issue as similar features appears in different species of plant. With the development of automated image-based classification, machine learning (ML) is becoming very popular. Deep learning (DL) methods have significantly improved plant image identification and classification. In the last decade, convolutional neural networks (CNN) have entirely dominated the field of computer vision, showing outstanding feature extraction capabilities and significant identification and classification performance. The capability of CNN lies in its network. The primary strategy to continue this trend in the literature relies on further scaling networks in size. However, costs increase rapidly, while performance improvements may be marginal when the number of net-works increases. Hence, there is a need to optimize the CNN network to get the best possible result with the minimum number of networks and other parameters such as the number of epochs, number of layers, batch size and number of neurons. The paper aims to evolve the optimal architecture of CNN using PB3C algorithm for plant leaf classification. For this, we use the nature-inspired computing technique parallel big bang–big crunch to evolve a CNN's optimal architecture automatically. Current study validated the proposed approach for plant leaf classification and compared it with 11 other machine learning-based approaches. From the results obtained it was found that the proposed approach was able to outperforms all 11 existing state-of-the-art techniques.

1 May 2020 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
SGSukanta Ghosh
Sukanta Ghosh
ASAmar Singh
Amar Singh

1 September 2023 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
SGSukanta Ghosh
Sukanta Ghosh
ASAmar Singh
Amar Singh
SKShakti Kumar
Shakti Kumar
Ayurveda is one of the oldest holistic treatment systems in the world. Finding an accurate and correct plant is the key to the working of Ayurvedic treatment. Identification of medicinal plants is a tedious job due to the look-alike feature and availability issue of medicinal plants with other plants. This paper emphases on the ideal identification and classification of plants of medicinal use using deep learning approaches. Previously researchers have used traditional machine learning techniques to identify medicinal plants, which lead to mixed results. Such results are good but not enough as the identification of medicinal plants may lead to a worsening situation for patients. This research is conducted to get results closer to an ayurvedic expert. The dataset used for this research has been taken from Mendeley Data. The dataset comprises 30 different species of medicinal plants. Hybrid transfer learning has been applied to this dataset. The model has generated a test accuracy of 95.25% which is better than the other popular transfer learning techniques.

7 June 2025 in Discover Internet of Things
Verified
Journal Article
Open access
PDF file
SGSukanta Ghosh
Sukanta Ghosh
ASAmar Singh
Amar Singh
SKShakti Kumar
Shakti Kumar
This paper proposes the multiplier leadership optimization algorithm, which draws inspiration from multiplier leadership principles to search for and optimize solutions to complex problems effectively. Multiplier leaders possess the unique ability to amplify their teams’ collective intelligence and capabilities. They cultivate an environment of open discussion, creative thinking, accountability, and motivating team members to excel. The proposed algorithm is implemented in MATLAB, and its performance is evaluated on the IEEE Congress on Evolutionary Computation 2021 test bench suite, which consists of 80 benchmark functions. The performance of the proposed approach is compared with those of the other 9 other state-of-the-art optimization algorithms. The proposed algorithm successfully solved 47 out of 80 benchmark functions, demonstrating its superior performance. The computational complexity of proposed algorithm is $$O(M * N^2)$$ O ( M ∗ N 2 ) , making it efficient for large-scale problems. Furthermore, this paper proposes an MLOA-based approach to evolve the near-optimal architecture of convolution neural networks for Melanoma classification. The proposed approach is implemented in Python and tested on the PH2 and ISIC2020 datasets. The PH2 dataset consists of 200 dermoscopic images, while the ISIC2020 dataset comprises 33,126 images. The proposed approach is compared with 12 other state-of-the-art methods and achieves high classification accuracies of 98.97% on the PH2 dataset and 99.47% on the ISIC2020 dataset. Additional performance metrics include precision of 98.72%, recall of 98.85%, and F1-score of 98.78% on the PH2 dataset, while on the ISIC2020 dataset, it achieves precision of 99.32%, recall of 99.51%, and F1-score of 99.41%. The results indicate that MLOA-based CNN architecture outperforms all existing approaches for Melanoma classification, offering a promising solution for medical image analysis.

1 January 2021
Verified
Book Chapter
Closed access
SGSukanta Ghosh
Sukanta Ghosh
ASAmar Singh
Amar Singh
Facial expression recognition is an activity that is performed by every human in their day-to-day lives. Each one of us analyses the expressions of the individuals we interact with to understand how people interact and respond with us. The malicious intentions of a thief or a person to be interviewed can be recognized with the help of his facial features and gestures. Face recognition from picture or video is a well-known point in biometrics inquiry. Numerous open places, for the most part, have reconnaissance cameras, and these cameras have their noteworthy security incentives. It is generally recognized that face recognition has assumed a significant job in reconnaissance framework. The genuine favorable circumstances of face-based distinguishing proof over different biometrics are uniqueness. Since the human face is a unique item having a high level of inconstancy in its appearance, face location is a troublesome issue in computer vision. This chapter explores emotion detection using facial images.

14 June 2024
Verified
Book Chapter
Closed access
PDF file
PCPriya Chanda
Priya Chanda
PSPritpal Singh
Pritpal Singh
PCPriyanka Chhibber
Priyanka Chhibber
SGSukanta Ghosh
Sukanta Ghosh