Search

Your search keyword '"Surendiran, J."' showing total 4 results
Start Over Author "Surendiran, J." Language english
4 results on '"Surendiran, J."'

1. M2F-Net: A Deep Learning-Based Multimodal Classification with High-Throughput Phenotyping for Identification of Overabundance of Fertilizers

Author

Surendiran, J. Dhakshayani

Subjects
phenotyping, fusion strategies, synthetic fertilizer overuse, MLP, DenseNet, environmental deterioration
Abstract

Amaranth, a pseudocereal crop which is rich in nutrients and climate resistant, can provide an opportunity to increase food security and nutritional content for the growing population. Farmers rely mainly on synthetic fertilizers to improve the quality and yield of the crop; however, this overuse harms the ecosystem. Understanding the mechanism causing this environmental deterioration is crucial for crop production and ecological sustainability. In recent years, high-throughput phenotyping using Artificial Intelligence (AI) has been thriving and can provide an effective solution for the identification of fertilizer overuse. Influenced by the strength of deep learning paradigms and IoT sensors, a novel multimodal fusion network (M2F-Net) is proposed for high-throughput phenotyping to diagnose overabundance of fertilizers. In this paper, we developed and analyzed three strategies that fuse agrometeorological and image data by assessing fusion at various stages. Initially two unimodal baseline networks were trained: Multi-Layer Perceptron (MLP) on agrometeorological data and a pre-trained Convolutional Neural Network (CNN) model DenseNet-121 on image data. With these baselines, the multimodal fusion network is developed, capable of adeptly learning from image and non-image data and the model’s performance is evaluated in terms of accuracy and Area Under Curve (AUC). Moreover, the fusion approaches that are considered outperformed the unimodal networks remarkably with 91% accuracy. From the experimental result, it is proven that incorporating agrometeorological information and images can substantially boost the classification performance for the overabundance of fertilizer.

Published
2023
Full Text
View/download PDF

2. Security for health information by elliptical curve Diffie-Hellman and improve energy efficiency in WBAN.

Author

Azath, H., Gokulraj, J., Surendiran, J., Geetha, D., and Babu, T. R. Ganesh

Subjects
ENERGY consumption, BODY area networks, INFORMATION technology security, WIRELESS sensor network security, TRUST, PUBLIC key cryptography
Abstract

Wireless body area networks (WBAN) necessitate long-life connections and energy-efficient systems. Moreover, the rising commercialization, health observing applications calls for raising the routing efficiency. The concern of the trustworthy and energy-efficient link is vital to support the enhancement of the WBAN function. In addition, in each sensor node activity, dissolute energy has a heating result that may reason poor operation of the many physical condition risks to observed individuals. Therefore, the concern of a sensor node energy is a significant parameter. Furthermore, several existing lightweight authentication approaches have various security exposures, particularly the need for forwarding secrecy. Security for Health Information by Elliptical Curve Diffie-Hellman and improved energy efficiency (EIEE) in WBAN are proposed to solve these issues. This approach's main goal is to distinguish the unreliable sensor and improve energy efficiency in the WBAN. Here, the untrustworthy node is recognized through the ECDH technique. This approach updates the secret key to notice the inconsistent sensor node and segregate from routing, raising the network function. Here, we simulate the IEEE approach utilizing the network simulator. The simulation outcomes demonstrate that EIEE declares you minimize the delay and enhance the throughput and remaining energy in the WBAN. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

3. Data mining based chronic kidney disease (CKID) prediction.

Author

Sathiya, T., Geetha, D., Surendiran, J., Azath, H., and Babu, T. R. Ganesh

Subjects
CHRONIC kidney failure, DATA mining, RECURRENT neural networks, CHRONIC diseases
Abstract

Nowadays, chronic kidney illness (CKD) is one of the significant reasons for mortality, and it has a drawn-out handicap. The inclining factors for CKD incorporate hypertension, cardiovascular sicknesses, diabetes mellitus, and innate kidney issues. Renal substitution treatment is the treatment of decision for CKD. Information mining is an exact strategy that assists with anticipating the illness utilizing different techniques incorporate calculated relapse, Naive Bayes order, k-closest neighbours, and backing vector machine. Aside from these past procedures, it was essential to use an arrangement strategy for information division as indicated by their determination and relapse technique for discovering hazard factors.The results of the study reveal that the RNN computations show "91.75%" accuracy, and that IPM offers "96.75%" accuracy. This connection has the benefit that the interplay between expectations is less powerful. It will help experts to initiate treatments for persistent patients on time and will help to detect more individuals within a shorter period of time. In this current review, information is ordered utilizing proposed Identification of Pattern Mining, Recurrent Neural Network strategies, and Regression procedures to help diagnose a patient with CKD. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

4. Segmentation of Optic Disc and Cup Using Modified Recurrent Neural Network.

Author

Surendiran, J., Theetchenya, S., Benson Mansingh, P. M., Sekar, G., Dhipa, M., Yuvaraj, N., Arulkarthick, V. J., Suresh, C., Sriram, Arram, Srihari, K., and Alene, Assefa

Subjects
*GLAUCOMA diagnosis, *ARTIFICIAL neural networks, *EYE examination, *ALGORITHMS
Abstract

Glaucoma is one of the leading factors of vision loss, where the people tends to lose their vision quickly. The examination of cup-to-disc ratio is considered essential in diagnosing glaucoma. It is hence regarded that the segmentation of optic disc and cup is useful in finding the ratio. In this paper, we develop an extraction and segmentation of optic disc and cup from an input eye image using modified recurrent neural networks (mRNN). The mRNN use the combination of recurrent neural network (RNN) with fully convolutional network (FCN) that exploits the intra- and interslice contexts. The FCN extracts the contents from an input image by constructing a feature map for the intra- and interslice contexts. This is carried out to extract the relevant information, where RNN concentrates more on interslice context. The simulation is conducted to test the efficacy of the model that integrates the contextual information for optimal segmentation of optical cup and disc. The results of simulation show that the proposed method mRNN is efficient in improving the rate of segmentation than the other deep learning models like Drive, STARE, MESSIDOR, ORIGA, and DIARETDB. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results