Search

Your search keyword '"V, Pandiyaraju"' showing total 15 results
Start Over Author "V, Pandiyaraju"
15 results on '"V, Pandiyaraju"'

1. An Integrated Deep Learning Framework for Effective Brain Tumor Localization, Segmentation, and Classification from Magnetic Resonance Images

Author

V, Pandiyaraju, Venkatraman, Shravan, A, Abeshek, A, Aravintakshan S, S, Pavan Kumar, and S, Madhan

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, I.4.6
Abstract

Tumors in the brain result from abnormal cell growth within the brain tissue, arising from various types of brain cells. When left undiagnosed, they lead to severe neurological deficits such as cognitive impairment, motor dysfunction, and sensory loss. As the tumor grows, it causes an increase in intracranial pressure, potentially leading to life-threatening complications such as brain herniation. Therefore, early detection and treatment are necessary to manage the complications caused by such tumors to slow down their growth. Numerous works involving deep learning (DL) and artificial intelligence (AI) are being carried out to assist physicians in early diagnosis by utilizing the scans obtained through Magnetic Resonance Imaging (MRI). Our research proposes DL frameworks for localizing, segmenting, and classifying the grade of these gliomas from MRI images to solve this critical issue. In our localization framework, we enhance the LinkNet framework with a VGG19- inspired encoder architecture for improved multimodal tumor feature extraction, along with spatial and graph attention mechanisms to refine feature focus and inter-feature relationships. Following this, we integrated the SeResNet101 CNN model as the encoder backbone into the LinkNet framework for tumor segmentation, which achieved an IoU Score of 96%. To classify the segmented tumors, we combined the SeResNet152 feature extractor with an Adaptive Boosting classifier, which yielded an accuracy of 98.53%. Our proposed models demonstrated promising results, with the potential to advance medical AI by enabling early diagnosis and providing more accurate treatment options for patients., Comment: 36 pages, 27 figures, 5 tables

Published
2024

2. Leveraging SeNet and ResNet Synergy within an Encoder-Decoder Architecture for Glioma Detection

Author

V, Pandiyaraju, Venkatraman, Shravan, A, Abeshek, S, Pavan Kumar, and A, Aravintakshan S

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, I.4.6
Abstract

Brain tumors are abnormalities that can severely impact a patient's health, leading to life-threatening conditions such as cancer. These can result in various debilitating effects, including neurological issues, cognitive impairment, motor and sensory deficits, as well as emotional and behavioral changes. These symptoms significantly affect a patient's quality of life, making early diagnosis and timely treatment essential to prevent further deterioration. However, accurately segmenting the tumor region from medical images, particularly MRI scans, is a challenging and time-consuming task that requires the expertise of radiologists. Manual segmentation can also be prone to human errors. To address these challenges, this research leverages the synergy of SeNet and ResNet architectures within an encoder-decoder framework, designed specifically for glioma detection and segmentation. The proposed model incorporates the power of SeResNet-152 as the backbone, integrated into a robust encoder-decoder structure to enhance feature extraction and improve segmentation accuracy. This novel approach significantly reduces the dependency on manual tasks and improves the precision of tumor identification. Evaluation of the model demonstrates strong performance, achieving 87% in Dice Coefficient, 89.12% in accuracy, 88% in IoU score, and 82% in mean IoU score, showcasing its effectiveness in tackling the complex problem of brain tumor segmentation., Comment: 9 pages, 6 figures, 1 table

Published
2024

3. A Channel Attention-Driven Hybrid CNN Framework for Paddy Leaf Disease Detection

Author

V, Pandiyaraju, Venkatraman, Shravan, A, Abeshek, S, Pavan Kumar, A, Aravintakshan S, M, Senthil Kumar A, and A, Kannan

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, F.2.2, I.2.7
Abstract

Farmers face various challenges when it comes to identifying diseases in rice leaves during their early stages of growth, which is a major reason for poor produce. Therefore, early and accurate disease identification is important in agriculture to avoid crop loss and improve cultivation. In this research, we propose a novel hybrid deep learning (DL) classifier designed by extending the Squeeze-and-Excitation network architecture with a channel attention mechanism and the Swish ReLU activation function. The channel attention mechanism in our proposed model identifies the most important feature channels required for classification during feature extraction and selection. The dying ReLU problem is mitigated by utilizing the Swish ReLU activation function, and the Squeeze-andExcitation blocks improve information propagation and cross-channel interaction. Upon evaluation, our model achieved a high F1-score of 99.76% and an accuracy of 99.74%, surpassing the performance of existing models. These outcomes demonstrate the potential of state-of-the-art DL techniques in agriculture, contributing to the advancement of more efficient and reliable disease detection systems., Comment: 17 pages, 4 tables, 10 figures

Published
2024

4. Leveraging Bi-Focal Perspectives and Granular Feature Integration for Accurate Reliable Early Alzheimer's Detection

Author

V, Pandiyaraju, Venkatraman, Shravan, A, Abeshek, A, Aravintakshan S, S, Pavan Kumar, and A, Kannan

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, I.4.8, I.2.10, I.4.6
Abstract

Alzheimer's disease (AD) is the most common form of neurodegeneration, which impacts millions of people each year. Diagnosing and classifying AD accurately with neuroimaging data is an ongoing challenge in the field of medicine. Traditional Convolutional Neural Networks (CNNs) are good at capturing low-level information from images, but their capability to extract high-level minuscule particles is suboptimal, which is a significant challenge in detecting AD from MRI scans. To overcome this, we propose a novel Granular Feature Integration method to combine information extraction at different scales combined with an efficient information flow. We also propose a Bi-Focal Perspective mechanism to highlight focus on subtle neurofibrillary tangles and amyloid plaques in MRI scans. Our model yielded an F1-Score of 99.31%, a precision of 99.24%, and a recall of 99.51%, which shows a major improvement in comparison to existing state-of-the-art (SOTA) CNNs., Comment: 17 pages, 10 figures, 6 tables

Published
2024

5. Multi-Attention Integrated Deep Learning Frameworks for Enhanced Breast Cancer Segmentation and Identification

Author

V, Pandiyaraju, Venkatraman, Shravan, S, Pavan Kumar, Malarvannan, Santhosh, and A, Kannan

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, F.2.2, I.2.7
Abstract

Breast cancer poses a profound threat to lives globally, claiming numerous lives each year. Therefore, timely detection is crucial for early intervention and improved chances of survival. Accurately diagnosing and classifying breast tumors using ultrasound images is a persistent challenge in medicine, demanding cutting-edge solutions for improved treatment strategies. This research introduces multiattention-enhanced deep learning (DL) frameworks designed for the classification and segmentation of breast cancer tumors from ultrasound images. A spatial channel attention mechanism is proposed for segmenting tumors from ultrasound images, utilizing a novel LinkNet DL framework with an InceptionResNet backbone. Following this, the paper proposes a deep convolutional neural network with an integrated multi-attention framework (DCNNIMAF) to classify the segmented tumor as benign, malignant, or normal. From experimental results, it is observed that the segmentation model has recorded an accuracy of 98.1%, with a minimal loss of 0.6%. It has also achieved high Intersection over Union (IoU) and Dice Coefficient scores of 96.9% and 97.2%, respectively. Similarly, the classification model has attained an accuracy of 99.2%, with a low loss of 0.31%. Furthermore, the classification framework has achieved outstanding F1-Score, precision, and recall values of 99.1%, 99.3%, and 99.1%, respectively. By offering a robust framework for early detection and accurate classification of breast cancer, this proposed work significantly advances the field of medical image analysis, potentially improving diagnostic precision and patient outcomes., Comment: 29 pages, 15 figures, 6 tables

Published
2024

6. An optimal energy utilization model for precision agriculture in WSNs using multi-objective clustering and deep learning

Author

V. Pandiyaraju, Sannasi Ganapathy, N. Mohith, and A. Kannan

Subjects
Precision Agriculture, Wireless Sensor Networks, Clustering, Aquila optimization, Classification, Cluster Head, Electronic computers. Computer science, QA75.5-76.95
Abstract

Wireless Sensor Networks (WSNs) play a crucial role in Precision Agriculture by providing real-time data on various environmental parameters like temperature, humidity, soil moisture, etc. However, the efficient utilization of energy in the sensor nodes of WSNs is a major challenge that needs to be addressed. To address this issue, a new multi-objective clustering approach is introduced in this work for grouping the sensor nodes of WSNs. Moreover, a multi-objective hybrid optimisation technique called Election based Aquila Optimizer (EAO) which is the combination of Aquila Optimizer (AO) and the Election-Based Optimisation Algorithm (EBOA) is proposed in this work to make sure that the Cluster Head (CH) selection process in WSNs to identify the best CH. In addition, the proposed method incorporates the newly developed optimization technique with convolutional neural network (CNN) as an Optimized CNN (O-CNN) to improve the clustering algorithm's precision and also enhance the training accuracy and testing accuracy. The proposed approach is evaluated through experiments and proved as better than other approaches by obtaining 99.23% as classification accuracy, 76.92% as throughput, 99% as packet delivery ratio, 98.24% as network lifetime and 50% as maximum energy consumption and it resolves a significant difficulty in precision agriculture.

Published
2023
Full Text
View/download PDF

8. Improved tomato leaf disease classification through adaptive ensemble models with exponential moving average fusion and enhanced weighted gradient optimization.

Author

V., Pandiyaraju, Kumar, A. M. Senthil, Praveen, Joe I. R., Venkatraman, Shravan, Kumar, S. Pavan, Aravintakshan, S. A., Abeshek, A., and Kannan, A.

Subjects
TOMATOES, NOSOLOGY, MOVING average process, SWARM intelligence, RECEIVER operating characteristic curves, FOOD crops, TOMATO diseases & pests, TOMATO farming
Abstract

Tomato is one of the most popular and most important food crops consumed globally. The quality and quantity of yield by tomato plants are affected by the impact made by various kinds of diseases. Therefore, it is essential to identify these diseases early so that it is possible to reduce the occurrences and effect of the diseases on tomato plants to improve the overall crop yield and to support the farmers. In the past, many research works have been carried out by applying the machine learning techniques to segment and classify the tomato leaf images. However, the existing machine learning-based classifiers are not able to detect the new types of diseases more accurately. On the other hand, deep learning-based classifierswith the support of swarm intelligence-based optimization techniques are able to enhance the classification accuracy, leading to the more effective and accurate detection of leaf diseases. This research paper proposes a new method for the accurate classification of tomato leaf diseases by harnessing the power of an ensemble model in a sample dataset of tomato plants, containing images pertaining to nine different types of leaf diseases. This research introduces an ensemble model with an exponential moving average function with temporal constraints and an enhanced weighted gradient optimizer that is integrated into fine-tuned Visual Geometry Group-16 (VGG-16) and Neural Architecture Search Network (NASNet) mobile training methods for providing improved learning and classification accuracy. The dataset used for the research consists of 10,000 tomato leaf images categorized into nine classes for training and validating the model and an additional 1,000 images reserved for testing the model. The results have been analyzed thoroughly and benchmarked with existing performance metrics, thus proving that the proposed approach gives better performance in terms of accuracy, loss, precision, recall, receiver operating characteristic curve, and F1-score with values of 98.7%, 4%, 97.9%, 98.6%, 99.97%, and 98.7%, respectively. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

9. Wireless Sensor Network Assisted Intelligent Drip Irrigation System for Water Conservation in Agriculture

Author

V PANDIYARAJU, P SHUNMUGA PERUMAL, V EZHIL ARASI, and ARPUTHARAJ KANNAN

Abstract

Agriculture is the backbone for most of the countries in the globe including our India. Crop Yield influences a country's economy and common public. Water is the most important factor in agriculture, water requirements for different crops. Now availability of water is a big challenge everywhere because of the climate change, No proper rain fall. Now a day’s our country faces severe drought. In agriculture, Conventional Solutions to Fight the Drought: (1).Storing water in dams, lakes and ponds, (2.)Restoration of the dams, lakes and ponds, (3).Drip irrigation system. Moreover, the Conventional Solutions are (1).Highly influenced by rain fall.(2).A long time & continuous process.(3).The method of irrigating crops by saving water by allowing water to drip slowly to the roots of plants either onto the soil surface or directly onto the root zone. Existing drip irrigation systems are not completely automated - Need more involvement of farmers. Farmer’s history of knowledge is used to take decisions about “duration of irrigation” and “quantity of irrigation”. These may not be accurate always which leads to underwater or over water irrigations - Nowadays farmers purchase water for irrigation. There is a huge gap between activities of agriculture laboratories and actual field conditions. High-technologies and intelligent systems are not integrated in full-fledge to agriculture in the perspective of drip irrigation. In this paper, we propose an Intelligent Drip Irrigation System (IDIS) for water conservation. The proposed system consists of two important components namely an Intelligent Soil Moisture Sensor Unit (ISMSU) and an Agriculture Control Station (ACS). The ISMSU is used to measure the soil moisture value accurately indifferent root length of the crop dynamically using a newly proposed multi-depth soil moisture measurement algorithm. These soil moisture values help the farmers to conserve water, electricity and to avoid both excess and shortage of water supply in irrigation. Moreover, a new protocol called ISMSU communication protocol also proposed in this paper to collect the soil moisture data from the network of ISMSUs with less battery power consumption. This power conservation in ISMSUs is useful to prolong the lifetime of the sensors present in the network of ISMSUs. The ACS is responsible for collecting the data from sensor nodes and to process them accurately by using the data collection module for effective data collection. This data is useful for agriculture scientists to guide the farmers through the farmer web portal, Short Message Service (SMS) and also to find the rules which are used for performing drip irrigation.

Published
2022

10. An Energy Efficient Routing Algorithm for WSNs Using Intelligent Fuzzy Rules in Precision Agriculture

Author

Arputharaj Kannan, Sannasi Ganapathy, V. Pandiyaraju, and R. Logambigai

Subjects
Routing protocol, Computer science, ComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKS, 020206 networking & telecommunications, 02 engineering and technology, Fuzzy logic, Computer Science Applications, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Precision agriculture, Electrical and Electronic Engineering, Routing (electronic design automation), Algorithm, Protocol (object-oriented programming), Wireless sensor network, Energy (signal processing), Efficient energy use
Abstract

Many agricultural activities can be highly enhanced by using sensor networks and data mining techniques. One of these activities is the regulation of the quantity of water in cultivated fields. Moreover, wireless sensor network have become a more emerging technology in precision agriculture during the recent years. The important issue in the design of wireless sensor networks is the utilization of energy and to enhance the lifetime of the sensor nodes. In this paper, a new intelligent routing protocol has been proposed to improve the network lifetime and to provide energy efficiency in the routing process which is used to provide data to the irrigation system. This novel intelligent energy efficient routing protocol uses fuzzy rules and the protocol is called as Terrain based Routing using Fuzzy rules for precision agriculture. The fuzzy inference system developed in this work has been used to take decisions for routing. The system has been implemented and compared with two routing algorithms called Region Based Routing and Equalized Cluster Head Election Routing Protocol. The experimental results show that the proposed algorithm performs better than the other existing algorithms.

Published
2020

11. SMART TERRACE GARDENING WITH INTELLIGENT ROOF CONTROL ALGORITHM FOR WATER CONSERVATION

Author

P. S. Perumal, V. Pandiyaraju, Arputharaj Kannan, and L. S. Ramesh

Subjects
geography, Irrigation, geography.geographical_feature_category, Crop yield, Soil Science, Humidity, Plant Science, Agricultural engineering, Fuzzy logic, Water conservation, Terrace (geology), Soil water, Environmental science, Agronomy and Crop Science, Roof, Food Science
Published
2017

12. Prediction of User Interests for Providing Relevant Information Using Relevance Feedback and Re-ranking

Author

V. Pandiyaraju, Sannasi Ganapathy, R. Bhuvaneshwari, K. Kulothungan, L. Sai Ramesh, and Arputharaj Kannan

Subjects
Information retrieval, Computer science, business.industry, Inference, Relevance feedback, Personalization, Personalized search, Search engine, User experience design, Decision Sciences (miscellaneous), The Internet, business, Cluster analysis, Information Systems
Abstract

Predicting user interest based on their browsing pattern is useful in relevant information retrieval. In such a scenario, queries must be unambiguous and precise. For a broad-topic and ambiguous query, different users may with different interests may search for information from the internet. The inference and analysis of user search goals using rules will be helpful to enhance the relevancy and user experience. A major deficiency of generic search system is that they have static model which is to be applied for all the users and hence are not adaptable to individual users. User interest is important when performing clustering so that it is possible to enhance the personalization. In this paper, a new approach is proposed to infer user interests based on their queries and fast profile logs and to provide relevant information to users based on personalization. For this purpose, a framework is designed to analyze different user profiles and interests while query processing including relevance analysis. Implicit Feedback sessions are also constructed from user profiles based on mouse and button clicks made in their current and past queries. In addition, browsing behaviors of users are analyzed using rules and also using the feedback sessions. Temporary documents are generated in this work for representing the feedback sessions effectively. Finally, personalization is made based on browsing behavior and relevant information is provided to the users. From the experiments conducted in this work, it is observed that the proposed model provide most accurate and relevant contents to the users when compared with other related work.

Published
2015

13. Non-Naive Bayesian classifier for Farmer Advisory System

Author

D. Santhosh, V. Pandiyaraju, and Arputharaj Kannan

Subjects
business.industry, Naive bayesian classifier, Computer science, Confusion matrix, Pattern recognition, Machine learning, computer.software_genre, Kernel (linear algebra), Naive Bayes classifier, ComputingMethodologies_PATTERNRECOGNITION, Advisory system, Bayesian programming, Artificial intelligence, business, Classifier (UML), computer
Abstract

Agri-mining is a recent trend that helps the farmer through an Information Technology domain that is needed to improve the crop yield system. In this paper, create an effective classifier. For that purpose, Soybean dataset is used for analysis and is pre-processed for improving the accuracy of the classifier. Then the pre-processed input is given to the Non-Naive classifier which performs classification by using the Error Distribution method in the Kernel space. A new Non-Naive Bayesian algorithm is proposed in this project work which improves the performance of the Naive Bayesian algorithm by using Error Distribution functions. The result is compared with Naive Bayesian algorithm using the performance measures such that the ROC and Confusion Matrix. Then the performance of the proposed model is proved to be better than the Naive Bayesian algorithm.

Published
2014

14. CBIR: Retrieval of similar images using median vector algorithm

Author

V. Pandiyaraju, P. Elumalaivasan, S. Ravikumar, S. Suthir, and T. Munirathinam

Subjects
Color histogram, Computer science, Color image, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, Content-based image retrieval, Color quantization, Image texture, Computer Science::Computer Vision and Pattern Recognition, Computer vision, Visual Word, Artificial intelligence, business, Image retrieval, Algorithm, Feature detection (computer vision)
Abstract

In content based image retrieval (CBIR) system, target images are sorted by feature similarities in terms of related query. Image classification is the important field in applications like security, biometrics, and in medical applications. An efficient image retrieval system is Hue, Saturation and Value (HSV) color space. This Classify the image into n number of areas based on different selected ranges of hue and value, then each area is partitioned into m number of segments based on the number of pixels it contains, the area which has more pixels will be partitioned into more segments and which has less pixels will be partitioned into less number of segments. This is used as a feature vector. Here color feature is one of the important features for image retrieval and content based image retrieval of clustering is the best method to sort the similar images. The proposed algorithms, inverse, inverse of engrave, double emboss, 3D shape detection, edge detection, gray scale, gray scale extended, color reduction and high color mode are used in the image enhancement process and color median vector algorithm is used to retrieve the similar images.

Published
2013

15. Dynamic Waypoint Navigation Assisted Agricultural Flying Vehicle for Field Data Collection

Author

Sannasi Ganapathy, V. Pandiyaraju, P. Shunmuga Perumal, L. Sai Ramesh, and Arunachala Mada Kannan

Subjects
Irrigation, Engineering, geography, geography.geographical_feature_category, Fire detection, business.industry, General Medicine, Agricultural engineering, Unit (housing), Residential area, ComputingMilieux_GENERAL, Waypoint, Home automation, Agriculture, business, Wireless sensor network, Simulation
Abstract

Wireless Sensor Networks (WSNs) are widely used in agriculture applications, industrial automations, smart home applications, battlefield surveillances, landslides detection, forest fire detection systems, etc. Agriculture is the backbone for any country as its stability and economy are totally depend on agriculture. Most of the cultivation lands in our world are located in remote places, which are far away from the residential area, where frequent land observation is not possible. In conventional agriculture, farmers should physically visit their sites to observe the soil moisture, humidity, fertilizer contents to ensure the proper irrigation and crop management. This requires lot of human resources, time and money. In this paper, a novel Field Sensor Unit (FSU) and a Flying Agriculture Vehicle (FAV) are proposed to collect the agricultural field data like soil moisture, temperature, fertilizer contents from the field without manual intervention. The proposed FAV system significantly reduces the manual intervention, cost and field observation time.

Published
2016

Catalog

Books, media, physical & digital resources
See catalog results