swapnil shinde - Academia.edu (original) (raw)
Papers by swapnil shinde
ITM Web of Conferences
In Today’s date plagiarism is a very important aspect because content originality is the client&#... more In Today’s date plagiarism is a very important aspect because content originality is the client's prior requirement. Many people on the internet use others' images and get publicity while the owner of the image or data won′t get anything out of it. Many users copy the data or image features from the other users and modify it a little bit or create an artificial replica of it. With sufficient computational power and volume of data, the GAN models are capable enough to produce fake images that look very much similar to the real images. These kinds of images are generally not detected by modern plagiarism systems. GAN stands for generative adversarial network. It has two neural networks working inside. The first one is the generator which generates a random image and the second one is the discriminator which identifies whether the image being generated is a real or a fake image. In this paper, we have proposed a system that has been trained on both fake images (GAN Generated im...
2019 International Conference on Communication and Electronics Systems (ICCES)
In this paper, the cameras capture lot of information that can be highly used in detecting and tr... more In this paper, the cameras capture lot of information that can be highly used in detecting and tracking objects in motion. Though it is challenging, object detection is used to detect object either in each frame or when it first comes in the video. Various methods like frame difference, background subtraction, optical flow can be used for detection. The highest objective of this is to contribute the human operators which help in detecting and tracking doubtful or uncommon actions in the video sequence. The visual observation system needs fast and strong approaches of detecting and tracking the moving objects. Moving objects were detected using canny edge method positively. Moments of different order were extracted using Zernike moments techniques. Analysis was done on all the Zernike moments from z00 to z88. The results show that the number of unique motion in the video and number of unique motion detected by the system is equal with accuracy of 100%.
2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
Modern audience measurement requires combining observations from disparate panel datasets. Connec... more Modern audience measurement requires combining observations from disparate panel datasets. Connecting and relating such panel datasets is a process termed panel fusion. This paper formalizes the panel fusion problem and presents a novel approach to solve it. We cast the panel fusion as a network flow problem, allowing the application of a rich body of research. In the context of digital audience measurement, where panel sizes can grow into the tens of millions, we propose an efficient algorithm to partition the network into sub-problems. While the algorithm solves a relaxed version of the original problem, we provide conditions under which it guarantees optimality. We demonstrate our approach by fusing two real-world panel datasets in a distributed computing environment.
ArXiv, 2019
Modern audience measurement requires combining observations from disparate panel datasets. Connec... more Modern audience measurement requires combining observations from disparate panel datasets. Connecting and relating such panel datasets is a process termed panel fusion. This paper formalizes the panel fusion problem and presents a novel approach to solve it. We cast the panel fusion as a network flow problem, allowing the application of a rich body of research. In the context of digital audience measurement, where panel sizes can grow into the tens of millions, we propose an efficient algorithm to partition the network into sub-problems. While the algorithm solves a relaxed version of the original problem, we provide conditions under which it guarantees optimality. We demonstrate our approach by fusing two real-world panel datasets in a distributed computing environment.
In last few decades large technology development raised new needs. Financial sector has no except... more In last few decades large technology development raised new needs. Financial sector has no exception. People are approaching all over the world to fulfill their dreams. Any sector needs to understand changing need of customer. Recently, with the awareness of businessmen and consumers and the development of mobile technologies, the potential use of mobile devices in financial applications such as banking and stock trading has seen a rapid increase. However, the security challenges being faced are diverse and increasing in number because of huge amount of money flowing across the mobiles. The aim of this work is to provide a secure environment in terms of security for transaction by various ways. But due to many security flaws these schemes are not feasible for real-life implementation. In this project we focus on mobile banking and explore different ways to make authentications more secure as means to improve the security of communication in various channels for any intrusion by the hackers.
Indian Journal of Dentistry, 2015
Lipoma is the most common tumor of the human body, but their presences in the oral cavity are ver... more Lipoma is the most common tumor of the human body, but their presences in the oral cavity are very rare. Reported cases of lipoma of tongue in English literature are very few. Here, we report a case of lipoma of tongue in 63-year-old male patient, with its clinical presentation, the histological picture, classification, and brief review of the literature.
Contemporary Clinical Dentistry, 2014
Salivary gland tumors comprise of less than 3% of all tumors of the head and neck region. Pleomor... more Salivary gland tumors comprise of less than 3% of all tumors of the head and neck region. Pleomorphic adenoma represents 45 to 74% of all these salivary gland tumors and 65% of them occur in the parotid gland. Owing to the close proximity of this tumor to the facial nerve, there have been various techniques for surgical management of this tumor in the literature. Extracapsular dissection of pleomorphic adenoma is a conservative treatment modality which spares the handling of facial nerve. We are reporting a case of extracapsular dissection of pleomorphic adenoma in the lower pole of the superfi cial lobe of the parotid gland in a 22 year-old Indian male with a 1-year follow-up.
Cancer Research, 2012
PTEN is a well-defined tumor suppressor gene that antagonizes the PI3K/Akt pathway to regulate a ... more PTEN is a well-defined tumor suppressor gene that antagonizes the PI3K/Akt pathway to regulate a multitude of cellular processes, such as survival, growth, motility, invasiveness, and angiogenesis. While the functions of PTEN have been studied extensively, the regulation of its activity during normal and disease conditions still remains incompletely understood. In this study, we identified the protein phosphatase-1 nuclear targeting subunit PNUTS (PPP1R10) as a PTEN-associated protein. PNUTS directly interacted with the lipid-binding domain (C2 domain) of PTEN and sequestered it in the nucleus. Depletion of PNUTS leads to increased apoptosis and reduced cellular proliferation in a PTEN-dependent manner. PNUTS expression was elevated in certain cancers compared with matched normal tissues. Collectively, our studies reveal PNUTS as a novel PTEN regulator and a likely oncogene. Cancer Res; 73(1); 205–14. ©2012 AACR.
2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), 2021
Diabetic Retinopathy has been one of the common reason why diabetic patients lose sight. It is ca... more Diabetic Retinopathy has been one of the common reason why diabetic patients lose sight. It is caused by the damaging of the blood vessel of the light sensitive tissue at the back of the eye or the retina. The traditional methods for the detection of the disease requires lots of time and efforts hence the proposed system aims to detect diabetic retinopathy using Image Processing and Machine Learning. The input provided to the proposed system are the retinal images from the standard databases DIARETDB0 and DIARETDB1. The system aims to automate the process of detection using a combination of basic image processing steps with more focus on pre-processing to obtain clear image for feature extraction, further Machine Learning algorithms are applied for classification. The statistical features such as area and perimeter are obtained from blood vessels and exudates after pre-processing stage, different pre-processing techniques such as grayscale conversion, binarization, canny edge detection and some morphological operations including image dilation and erosion are applied to obtain clear image. The Machine Learning algorithms that are used for result analysis are Weighted KNN, Cubic SVM and Simple Tree which provides an accuracy of 85.8%, 87.2% and 88.6% respectively. The sensitivity and specificity parameters are also obtained, Simple tree yields better results for all the three result parameters.
ITM Web of Conferences
In Today’s date plagiarism is a very important aspect because content originality is the client&#... more In Today’s date plagiarism is a very important aspect because content originality is the client's prior requirement. Many people on the internet use others' images and get publicity while the owner of the image or data won′t get anything out of it. Many users copy the data or image features from the other users and modify it a little bit or create an artificial replica of it. With sufficient computational power and volume of data, the GAN models are capable enough to produce fake images that look very much similar to the real images. These kinds of images are generally not detected by modern plagiarism systems. GAN stands for generative adversarial network. It has two neural networks working inside. The first one is the generator which generates a random image and the second one is the discriminator which identifies whether the image being generated is a real or a fake image. In this paper, we have proposed a system that has been trained on both fake images (GAN Generated im...
2019 International Conference on Communication and Electronics Systems (ICCES)
In this paper, the cameras capture lot of information that can be highly used in detecting and tr... more In this paper, the cameras capture lot of information that can be highly used in detecting and tracking objects in motion. Though it is challenging, object detection is used to detect object either in each frame or when it first comes in the video. Various methods like frame difference, background subtraction, optical flow can be used for detection. The highest objective of this is to contribute the human operators which help in detecting and tracking doubtful or uncommon actions in the video sequence. The visual observation system needs fast and strong approaches of detecting and tracking the moving objects. Moving objects were detected using canny edge method positively. Moments of different order were extracted using Zernike moments techniques. Analysis was done on all the Zernike moments from z00 to z88. The results show that the number of unique motion in the video and number of unique motion detected by the system is equal with accuracy of 100%.
2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
Modern audience measurement requires combining observations from disparate panel datasets. Connec... more Modern audience measurement requires combining observations from disparate panel datasets. Connecting and relating such panel datasets is a process termed panel fusion. This paper formalizes the panel fusion problem and presents a novel approach to solve it. We cast the panel fusion as a network flow problem, allowing the application of a rich body of research. In the context of digital audience measurement, where panel sizes can grow into the tens of millions, we propose an efficient algorithm to partition the network into sub-problems. While the algorithm solves a relaxed version of the original problem, we provide conditions under which it guarantees optimality. We demonstrate our approach by fusing two real-world panel datasets in a distributed computing environment.
ArXiv, 2019
Modern audience measurement requires combining observations from disparate panel datasets. Connec... more Modern audience measurement requires combining observations from disparate panel datasets. Connecting and relating such panel datasets is a process termed panel fusion. This paper formalizes the panel fusion problem and presents a novel approach to solve it. We cast the panel fusion as a network flow problem, allowing the application of a rich body of research. In the context of digital audience measurement, where panel sizes can grow into the tens of millions, we propose an efficient algorithm to partition the network into sub-problems. While the algorithm solves a relaxed version of the original problem, we provide conditions under which it guarantees optimality. We demonstrate our approach by fusing two real-world panel datasets in a distributed computing environment.
In last few decades large technology development raised new needs. Financial sector has no except... more In last few decades large technology development raised new needs. Financial sector has no exception. People are approaching all over the world to fulfill their dreams. Any sector needs to understand changing need of customer. Recently, with the awareness of businessmen and consumers and the development of mobile technologies, the potential use of mobile devices in financial applications such as banking and stock trading has seen a rapid increase. However, the security challenges being faced are diverse and increasing in number because of huge amount of money flowing across the mobiles. The aim of this work is to provide a secure environment in terms of security for transaction by various ways. But due to many security flaws these schemes are not feasible for real-life implementation. In this project we focus on mobile banking and explore different ways to make authentications more secure as means to improve the security of communication in various channels for any intrusion by the hackers.
Indian Journal of Dentistry, 2015
Lipoma is the most common tumor of the human body, but their presences in the oral cavity are ver... more Lipoma is the most common tumor of the human body, but their presences in the oral cavity are very rare. Reported cases of lipoma of tongue in English literature are very few. Here, we report a case of lipoma of tongue in 63-year-old male patient, with its clinical presentation, the histological picture, classification, and brief review of the literature.
Contemporary Clinical Dentistry, 2014
Salivary gland tumors comprise of less than 3% of all tumors of the head and neck region. Pleomor... more Salivary gland tumors comprise of less than 3% of all tumors of the head and neck region. Pleomorphic adenoma represents 45 to 74% of all these salivary gland tumors and 65% of them occur in the parotid gland. Owing to the close proximity of this tumor to the facial nerve, there have been various techniques for surgical management of this tumor in the literature. Extracapsular dissection of pleomorphic adenoma is a conservative treatment modality which spares the handling of facial nerve. We are reporting a case of extracapsular dissection of pleomorphic adenoma in the lower pole of the superfi cial lobe of the parotid gland in a 22 year-old Indian male with a 1-year follow-up.
Cancer Research, 2012
PTEN is a well-defined tumor suppressor gene that antagonizes the PI3K/Akt pathway to regulate a ... more PTEN is a well-defined tumor suppressor gene that antagonizes the PI3K/Akt pathway to regulate a multitude of cellular processes, such as survival, growth, motility, invasiveness, and angiogenesis. While the functions of PTEN have been studied extensively, the regulation of its activity during normal and disease conditions still remains incompletely understood. In this study, we identified the protein phosphatase-1 nuclear targeting subunit PNUTS (PPP1R10) as a PTEN-associated protein. PNUTS directly interacted with the lipid-binding domain (C2 domain) of PTEN and sequestered it in the nucleus. Depletion of PNUTS leads to increased apoptosis and reduced cellular proliferation in a PTEN-dependent manner. PNUTS expression was elevated in certain cancers compared with matched normal tissues. Collectively, our studies reveal PNUTS as a novel PTEN regulator and a likely oncogene. Cancer Res; 73(1); 205–14. ©2012 AACR.
2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), 2021
Diabetic Retinopathy has been one of the common reason why diabetic patients lose sight. It is ca... more Diabetic Retinopathy has been one of the common reason why diabetic patients lose sight. It is caused by the damaging of the blood vessel of the light sensitive tissue at the back of the eye or the retina. The traditional methods for the detection of the disease requires lots of time and efforts hence the proposed system aims to detect diabetic retinopathy using Image Processing and Machine Learning. The input provided to the proposed system are the retinal images from the standard databases DIARETDB0 and DIARETDB1. The system aims to automate the process of detection using a combination of basic image processing steps with more focus on pre-processing to obtain clear image for feature extraction, further Machine Learning algorithms are applied for classification. The statistical features such as area and perimeter are obtained from blood vessels and exudates after pre-processing stage, different pre-processing techniques such as grayscale conversion, binarization, canny edge detection and some morphological operations including image dilation and erosion are applied to obtain clear image. The Machine Learning algorithms that are used for result analysis are Weighted KNN, Cubic SVM and Simple Tree which provides an accuracy of 85.8%, 87.2% and 88.6% respectively. The sensitivity and specificity parameters are also obtained, Simple tree yields better results for all the three result parameters.