Browsing by Author "Vani, M."

Now showing 1 - 12 of 12

A Paradigm Shift in Brain Tumor Classification: Harnessing the Potential of Capsule Networks
(Institute of Electrical and Electronics Engineers Inc., 2023) Raythatha, Y.; Vani, M.
Accurate and timely classification of brain tumors is critical for developing effective treatment plans and predicting treatment outcomes. However, CNN-based models commonly used for this task have limitations, such as their reliance on large amounts of training data and difficulties with input orientation and transformations. To address these limitations, we propose a CapsNet-based model for brain tumor classification designed to effectively handle limited datasets, class imbalance, and input transformations. CapsNet relies on 'capsules,' groups of neurons that work together to represent specific input image features and are resistant to input orientation and transformations. Our study compares the performance of the proposed CapsNet-based model with state-of-The-Art CNN models, and our results demonstrate that the CapsNet-based model outperforms CNN models in terms of accuracy and robustness to input orientation and transformations. These findings suggest that CapsNet has the potential to be a promising alternative to CNNs for accurate and efficient brain tumor classification. Â© 2023 IEEE.
ARBAC: Attribute-enabled role based access control model
(2019) Singh, M.P.; Sudharsan, S.; Vani, M.
Role Based Access Control (RBAC) is well-known for ease of policy administration, whereas Attribute Based Access Control (ABAC) is renowned for flexible policy specification and dynamic decision making capability. However, they both have some well-known limitations. In this paper, we present an approach that uniquely combines the benefits of RBAC and ABAC. Specifically, our approach associates attribute based rules with roles and permissions that enables the specification of multi-dimensional fine-grained attribute enabled role-based policies. These policies along with rules are also stored as in-memory data, which helps in minimizing the execution time of access requests. Experiments on a wide range of policy data sets demonstrate feasibility and scalability of the proposed approach. � Springer Nature Singapore Pte Ltd. 2019.
ARBAC: Attribute-enabled role based access control model
(Springer Verlag service@springer.de, 2019) Singh, M.P.; Sudharsan, S.; Vani, M.
Role Based Access Control (RBAC) is well-known for ease of policy administration, whereas Attribute Based Access Control (ABAC) is renowned for flexible policy specification and dynamic decision making capability. However, they both have some well-known limitations. In this paper, we present an approach that uniquely combines the benefits of RBAC and ABAC. Specifically, our approach associates attribute based rules with roles and permissions that enables the specification of multi-dimensional fine-grained attribute enabled role-based policies. These policies along with rules are also stored as in-memory data, which helps in minimizing the execution time of access requests. Experiments on a wide range of policy data sets demonstrate feasibility and scalability of the proposed approach. Â© Springer Nature Singapore Pte Ltd. 2019.
Automated Diagnosis of Lung and Colorectal Pathologies Using a Shallow Capsule Network Model
(Institute of Electrical and Electronics Engineers Inc., 2023) Vishwakarma, H.; Vani, M.
One of the most hazardous diseases is cancer caused by many biochemical abnormalities. Among all the cancers, lung and colon cancer are the most common and tragic diseases. Effective detection of thoracic and colorectal pathology is vital for timely diagnosis and treatment. In this study, we propose a shallow capsule network model for detecting malignancies in lung and colorectal imaging. Our proposed model is trained and tested on three different datasets: LC25000, IQ-OTHNCCD Lung Cancer Dataset and Chest CT-Scan Dataset with varying train and test data ratios. Despite its shallow architecture, the proposed model achieves high accuracy, with test accuracy metrics of 99.32%, 89.05%, and 99.09% on the respective datasets. We have also shown that the proposed capsule network outperforms traditional deep learning models using less training data. Our findings show that the suggested shallow capsule network model is effective in identifying lung and colorectal disease. Â© 2023 IEEE.
Image Based Tomato Leaf Disease Detection
(2019) Kumar, A.; Vani, M.
Leaf diseases are the major problem in agricultural sector, which affects crop production as well as economic profit. Early detection of diseases using deep learning could avoid such a disaster. Currently, Convolutional Neural Network (CNN) is a class of deep learning which is widely used for the image classification task. We have performed experiments with the CNN architecture for detecting disease in tomato leaves. We trained a deep convolutional neural network using PlantVillage dataset of 14,903 images of diseased and healthy plant leaves, to identify the type of leaves. The trained model achieves test accuracy of 99.25%. � 2019 IEEE.
Image Based Tomato Leaf Disease Detection
(Institute of Electrical and Electronics Engineers Inc., 2019) Kumar, A.; Vani, M.
Leaf diseases are the major problem in agricultural sector, which affects crop production as well as economic profit. Early detection of diseases using deep learning could avoid such a disaster. Currently, Convolutional Neural Network (CNN) is a class of deep learning which is widely used for the image classification task. We have performed experiments with the CNN architecture for detecting disease in tomato leaves. We trained a deep convolutional neural network using PlantVillage dataset of 14,903 images of diseased and healthy plant leaves, to identify the type of leaves. The trained model achieves test accuracy of 99.25%. Â© 2019 IEEE.
Search improvement in unstructured P2P network considering type of content
(2008) Totekar, C.R.; Vani, M.; Palavalli, S.R.
One of the key challenging aspects of peer-to-peer systems has been efficient search for objects. To achieve this, we need to minimize the number of nodes that have to be searched, thereby use minimum number of messages during the search process. This can be done by selectively sending requests to nodes having higher probability of a hit for the queried object. In this paper we present an algorithm CBWS, for searching in unstructured peer-to-peer network, which is based on the fact that most users in peer-to-peer network share various types of data(e.g. audio, video, text, archive) in different proportions. The information about the number of objects of each file-type shared by nodes, is used to selectively forward the query to a node having higher hit-ratio for the data objects of requested type, based on the history of recently succeeded queries. Simulation results prove that our searching algorithm performs better than the selective walk searching algorithm.
Search improvement in unstructured P2P network considering type of content
(2008) Totekar, C.R.; Vani, M.; Palavalli, S.R.
One of the key challenging aspects of peer-to-peer systems has been efficient search for objects. To achieve this, we need to minimize the number of nodes that have to be searched, thereby use minimum number of messages during the search process. This can be done by selectively sending requests to nodes having higher probability of a hit for the queried object. In this paper we present an algorithm CBWS, for searching in unstructured peer-to-peer network, which is based on the fact that most users in peer-to-peer network share various types of data(e.g. audio, video, text, archive) in different proportions. The information about the number of objects of each file-type shared by nodes, is used to selectively forward the query to a node having higher hit-ratio for the data objects of requested type, based on the history of recently succeeded queries. Simulation results prove that our searching algorithm performs better than the selective walk searching algorithm.
Stress Detection with Machine Learning and Deep Learning using Multimodal Physiological Data
(Institute of Electrical and Electronics Engineers Inc., 2020) Bobade, P.; Vani, M.
Stress is a common part of everyday life that most people have to deal with on various occasions. However, having long-term stress, or a high degree of stress, will hinder our safety and disrupt our normal lives. Detecting mental stress earlier can prevent many health problems associated with stress. When a person gets stressed, there are notable shifts in various bio-signals like thermal, electrical, impedance, acoustic, optical, etc., by using such bio-signals stress levels can be identified. This paper proposes different machine learning and deep learning techniques for stress detection on individuals using multimodal dataset recorded from wearable physiological and motion sensors, which can prevent a person from various stress-related health problems. Data of sensor modalities like three-axis acceleration (ACC), electrocardiogram (ECG), blood volume pulse (BVP), body temperature (TEMP), respiration (RESP), electromyogram (EMG) and electrodermal activity (EDA) are for three physiological conditions - amusement, neutral and stress states, are taken from WESAD dataset. The accuracies for three-class (amusement vs. baseline vs. stress) and binary (stress vs. non-stress) classifications were evaluated and compared by using machine learning techniques like K-Nearest Neighbour, Linear Discriminant Analysis, Random Forest, Decision Tree, AdaBoost and Kernel Support Vector Machine. Besides, simple feed forward deep learning artificial neural network is introduced for these three-class and binary classifications. During the study, by using machine learning techniques, accuracies of up to 81.65% and 93.20% are achieved for three-class and binary classification problems respectively, and by using deep learning, the achieved accuracy is up to 84.32% and 95.21% respectively. Â© 2020 IEEE.
What makes a video memorable?
(2017) Kar, A.; Mavin, P.; Ghaturle, Y.; Vani, M.
Humans are exposed to many pictures and videos on a daily basis, but they have this exceptional ability to remember the details, even though many of them look very similar. This Video Memorability (VM) is mainly due to distinguishable and a fine representation of the frames in human mind that people tend to remember. Videos have an abundance data contained in the frames which can be used for feature extraction purposes. Each feature from each frame has to be carefully considered to determine the intrinsic property of the video i.e. memorability. Using Convolutional Neural Network (CNN), we propose a solution to the problem of predicting VM, by estimating its memorability. A model has been developed to predict VM using algorithmically extracted features. Two types of features (i) semantic features (ii) visual features have been considered. The effectiveness of the model has been tested using publicly available image and video data. The results confirm that the CNN model can predict memorability with a acceptable performance. � 2017 IEEE.
What makes a video memorable?
(Institute of Electrical and Electronics Engineers Inc., 2017) Kar, A.; Prashasthi, P.; Ghaturle, Y.; Vani, M.
Humans are exposed to many pictures and videos on a daily basis, but they have this exceptional ability to remember the details, even though many of them look very similar. This Video Memorability (VM) is mainly due to distinguishable and a fine representation of the frames in human mind that people tend to remember. Videos have an abundance data contained in the frames which can be used for feature extraction purposes. Each feature from each frame has to be carefully considered to determine the intrinsic property of the video i.e. memorability. Using Convolutional Neural Network (CNN), we propose a solution to the problem of predicting VM, by estimating its memorability. A model has been developed to predict VM using algorithmically extracted features. Two types of features (i) semantic features (ii) visual features have been considered. The effectiveness of the model has been tested using publicly available image and video data. The results confirm that the CNN model can predict memorability with a acceptable performance. Â© 2017 IEEE.
WideCaps: a wide attention-based capsule network for image classification
(Springer Science and Business Media Deutschland GmbH, 2023) Pawan, S.J.; Sharma, R.; Reddy, H.; Vani, M.; Rajan, J.
The capsule network is a distinct and promising segment of the neural network family that has drawn attention due to its unique ability to maintain equivariance by preserving spatial relationships among the features. The capsule network has attained unprecedented success in image classification with datasets such as MNIST and affNIST by encoding the characteristic features into capsules and building a parse-tree structure. However, on datasets involving complex foreground and background regions, such as CIFAR-10 and CIFAR-100, the performance of the capsule network is suboptimal due to its naive data routing policy and incompetence in extracting complex features. This paper proposes a new design strategy for capsule network architectures for efficiently dealing with complex images. The proposed method incorporates the optimal placement of the novel wide bottleneck residual block and squeeze and excitation Attention Blocks into the capsule network upheld by the modified factorized machines routing algorithm to address the defined problem. This setup allows channel interdependencies at almost no computational cost, thereby enhancing the representation ability of capsules on complex images. We extensively evaluate the performance of the proposed model on the five publicly available datasets, namely the CIFAR-10, Fashion MNIST, Brain Tumor, SVHN, and the CIFAR-100 datasets. The proposed method outperformed the top-5 capsule network-based methods on Fashion MNIST, CIFAR-10, SVHN, Brain Tumor, and gave a highly competitive performance on the CIFAR-100 datasets. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.