Shital Bhatt - Academia.edu (original) (raw)

Papers by Shital Bhatt

Research paper thumbnail of Automated System for Lung Nodule Classification Based on ResNet50 and SVM

2022 3rd International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT)

Research paper thumbnail of Compensator Design for Magnetic Levitation System

2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)

Research paper thumbnail of Corrigendum to: Improving Classification Accuracy of Pulmonary Nodules using Simplified Deep Neural Network

The Open Biomedical Engineering Journal

Research paper thumbnail of Diagnosis of Pulmonary Nodules on CT Images Using YOLOv4

International Journal of Online and Biomedical Engineering (iJOE)

In this paper, the Scale-Invariant Feature Transform (SIFT) and Fast Library for Approximate Near... more In this paper, the Scale-Invariant Feature Transform (SIFT) and Fast Library for Approximate Nearest Neighbors (FLANN) based algorithm is used to detect the abnormalities in the National Lung Screening Trial (NLST) CT scans as the exact clinical nodule locations are not provided in the dataset. These identified nodules on NLST CT Scans are then annotated using LabelImg tool. This process consumes time and so furthermore, the automatic nodule detection, You Only Look Once version 4 (YOLOv4) object detection model is implemented. The YOLOv4 object detection model is provided with total of 4187 labelled images in form of training (70%), validation (20%), and test (10%) datasets. Our YOLOv4 model achieves precision of 95%, sensitivity of 81% and mean Average Precision (mAP) of 89.1%.

Research paper thumbnail of Improving Classification Accuracy of Pulmonary Nodules using Simplified Deep Neural Network

The Open Biomedical Engineering Journal

Background: Lung cancer is among the major causes of death in the world. Early detection of lung ... more Background: Lung cancer is among the major causes of death in the world. Early detection of lung cancer is a major challenge. These encouraged the development of Computer-Aided Detection (CAD) system. Objectives: We designed a CAD system for performance improvement in detecting and classifying pulmonary nodules. Though the system will not replace radiologists, it will be helpful to them in order to accurately diagnose lung cancer. Methods: The architecture comprises of two steps, among which in the first step CT scans are pre-processed and the candidates are extracted using the positive and negative annotations provided along with the LUNA16 dataset, and the second step consists of three different neural networks for classifying the pulmonary nodules obtained from the first step. The models in the second step consist of 2D-Convolutional Neural Network (2D-CNN), Visual Geometry Group-16 (VGG-16) and simplified VGG-16, which independently classify pulmonary nodules. Results: The class...

Research paper thumbnail of Advances In Em (Expectation - Maximization) Algorithm for Image Classification As Per Cost and Accuracy

Image classification is the process of grouping image pixels into categories or classes to produc... more Image classification is the process of grouping image pixels into categories or classes to produce a Thematic representation.. Image classification used in many areas such as medical imaging, object identification in satellite images, traffic control systems, brake light detection, machine vision, face recognition, fingerprint recognition, etc. The performance of classification algorithms can be expressed in terms of their accuracy and time requires classifying image. Classification divides into two categories, supervised and unsupervised. This paper describe variations in unsupervised EM algorithm by using wavelet transform and Ycbcr colour model which gives comparison between accuracy and elapsed time

Research paper thumbnail of Image Retrieval using Bag-of-Features for Lung Cancer Classification

2021 6th International Conference on Inventive Computation Technologies (ICICT), 2021

In this paper, Content Based Image Retrieval (CBIR) technique is used to retrieve the images from... more In this paper, Content Based Image Retrieval (CBIR) technique is used to retrieve the images from a large database that are identical to the image provided as a query. The CBIR based Bag-of-Features (BOF) technique is used for extracting features and their classification on the dataset of LIDC/IDRI. Therefore, a lung image retrieval using grid-based feature extraction method and Speeded-Up Robust Features (SURF) algorithm are implemented in this paper. K-Means clustering algorithm is extended to the features extracted by SURF algorithm. MATLAB simulation is performed on selective database, which provides 99% and 98.56% of training and testing accuracy respectively.

Research paper thumbnail of Effect of Contrast Enhancement in Retinal Blood Vessel Image Segmentation

The retina has two sources of oxygen and nutrients: the retinal blood vessels and the choroid, wh... more The retina has two sources of oxygen and nutrients: the retinal blood vessels and the choroid, which lies under the retinal pigment epithelium. The blood vessels within the retina itself that carry oxygen and nutrients are called arteries. Blood vessel is also very useful in tracking of disease progression. Assessment of blood vessels network plays an important role in a variety of medical disorders. Detection and quantitative measurement of variations in the retinal blood vessels can help diagnose several diseases including diabetic retinopathy. Morphological operation to smoothen the background, Disc structuring elements were used in this work. The proposed algorithm has employed modules such as gray scale conversation, contrast enhancement, morphological operation .The techniques describe in the paper is based on morphological operation and apply on the publicly available DRIVE and STARE datasets. An average accuracy of 0.96 has been respectively achieved on the DRIVE and STARE d...

Research paper thumbnail of Dual Band Microstrip Patch Antenna Deisgn for Wireless Communication Application

International Journal of Advance Engineering and Research Development, Jan 31, 2016

The desired dual-band operation was obtained by proper loading for a rectangular patch antenna .T... more The desired dual-band operation was obtained by proper loading for a rectangular patch antenna .The parametric study of the considered design shows that the radiation pattern, return loss, voltage standing wave ratio (VSWR),impedance matching ,bandwidth and gain are optimized within the band of operation. The results obtained with CST simulations. The results obtained from our simulated antenna of 2.45 GHz (2.4000 to 2.4835GHz) for GPS band and 3.81 GHz (3.4 GHz-5.255) for WIMAX.

Research paper thumbnail of Training Based MIMO Channel Estimation

International Journal of Modern Trends in Engineering and Research, 2015

Research paper thumbnail of Automated System for Lung Nodule Classification Based on ResNet50 and SVM

2022 3rd International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT)

Research paper thumbnail of Compensator Design for Magnetic Levitation System

2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)

Research paper thumbnail of Corrigendum to: Improving Classification Accuracy of Pulmonary Nodules using Simplified Deep Neural Network

The Open Biomedical Engineering Journal

Research paper thumbnail of Diagnosis of Pulmonary Nodules on CT Images Using YOLOv4

International Journal of Online and Biomedical Engineering (iJOE)

In this paper, the Scale-Invariant Feature Transform (SIFT) and Fast Library for Approximate Near... more In this paper, the Scale-Invariant Feature Transform (SIFT) and Fast Library for Approximate Nearest Neighbors (FLANN) based algorithm is used to detect the abnormalities in the National Lung Screening Trial (NLST) CT scans as the exact clinical nodule locations are not provided in the dataset. These identified nodules on NLST CT Scans are then annotated using LabelImg tool. This process consumes time and so furthermore, the automatic nodule detection, You Only Look Once version 4 (YOLOv4) object detection model is implemented. The YOLOv4 object detection model is provided with total of 4187 labelled images in form of training (70%), validation (20%), and test (10%) datasets. Our YOLOv4 model achieves precision of 95%, sensitivity of 81% and mean Average Precision (mAP) of 89.1%.

Research paper thumbnail of Improving Classification Accuracy of Pulmonary Nodules using Simplified Deep Neural Network

The Open Biomedical Engineering Journal

Background: Lung cancer is among the major causes of death in the world. Early detection of lung ... more Background: Lung cancer is among the major causes of death in the world. Early detection of lung cancer is a major challenge. These encouraged the development of Computer-Aided Detection (CAD) system. Objectives: We designed a CAD system for performance improvement in detecting and classifying pulmonary nodules. Though the system will not replace radiologists, it will be helpful to them in order to accurately diagnose lung cancer. Methods: The architecture comprises of two steps, among which in the first step CT scans are pre-processed and the candidates are extracted using the positive and negative annotations provided along with the LUNA16 dataset, and the second step consists of three different neural networks for classifying the pulmonary nodules obtained from the first step. The models in the second step consist of 2D-Convolutional Neural Network (2D-CNN), Visual Geometry Group-16 (VGG-16) and simplified VGG-16, which independently classify pulmonary nodules. Results: The class...

Research paper thumbnail of Advances In Em (Expectation - Maximization) Algorithm for Image Classification As Per Cost and Accuracy

Image classification is the process of grouping image pixels into categories or classes to produc... more Image classification is the process of grouping image pixels into categories or classes to produce a Thematic representation.. Image classification used in many areas such as medical imaging, object identification in satellite images, traffic control systems, brake light detection, machine vision, face recognition, fingerprint recognition, etc. The performance of classification algorithms can be expressed in terms of their accuracy and time requires classifying image. Classification divides into two categories, supervised and unsupervised. This paper describe variations in unsupervised EM algorithm by using wavelet transform and Ycbcr colour model which gives comparison between accuracy and elapsed time

Research paper thumbnail of Image Retrieval using Bag-of-Features for Lung Cancer Classification

2021 6th International Conference on Inventive Computation Technologies (ICICT), 2021

In this paper, Content Based Image Retrieval (CBIR) technique is used to retrieve the images from... more In this paper, Content Based Image Retrieval (CBIR) technique is used to retrieve the images from a large database that are identical to the image provided as a query. The CBIR based Bag-of-Features (BOF) technique is used for extracting features and their classification on the dataset of LIDC/IDRI. Therefore, a lung image retrieval using grid-based feature extraction method and Speeded-Up Robust Features (SURF) algorithm are implemented in this paper. K-Means clustering algorithm is extended to the features extracted by SURF algorithm. MATLAB simulation is performed on selective database, which provides 99% and 98.56% of training and testing accuracy respectively.

Research paper thumbnail of Effect of Contrast Enhancement in Retinal Blood Vessel Image Segmentation

The retina has two sources of oxygen and nutrients: the retinal blood vessels and the choroid, wh... more The retina has two sources of oxygen and nutrients: the retinal blood vessels and the choroid, which lies under the retinal pigment epithelium. The blood vessels within the retina itself that carry oxygen and nutrients are called arteries. Blood vessel is also very useful in tracking of disease progression. Assessment of blood vessels network plays an important role in a variety of medical disorders. Detection and quantitative measurement of variations in the retinal blood vessels can help diagnose several diseases including diabetic retinopathy. Morphological operation to smoothen the background, Disc structuring elements were used in this work. The proposed algorithm has employed modules such as gray scale conversation, contrast enhancement, morphological operation .The techniques describe in the paper is based on morphological operation and apply on the publicly available DRIVE and STARE datasets. An average accuracy of 0.96 has been respectively achieved on the DRIVE and STARE d...

Research paper thumbnail of Dual Band Microstrip Patch Antenna Deisgn for Wireless Communication Application

International Journal of Advance Engineering and Research Development, Jan 31, 2016

The desired dual-band operation was obtained by proper loading for a rectangular patch antenna .T... more The desired dual-band operation was obtained by proper loading for a rectangular patch antenna .The parametric study of the considered design shows that the radiation pattern, return loss, voltage standing wave ratio (VSWR),impedance matching ,bandwidth and gain are optimized within the band of operation. The results obtained with CST simulations. The results obtained from our simulated antenna of 2.45 GHz (2.4000 to 2.4835GHz) for GPS band and 3.81 GHz (3.4 GHz-5.255) for WIMAX.

Research paper thumbnail of Training Based MIMO Channel Estimation

International Journal of Modern Trends in Engineering and Research, 2015