Shailendra Aswale | Goa University (original) (raw)
Papers by Shailendra Aswale
International journal of engineering research and technology, May 24, 2021
3D Reconstruction has been a field of interest for multiple disciplines, and in the past decade, ... more 3D Reconstruction has been a field of interest for multiple disciplines, and in the past decade, many researchers have devoted their studies to improve on state-of-art automated methods used for 3D Reconstruction. 3D models have their application in solving numerous visualization problems and a large number of undertakings beyond visualization. In this paper, we conduct a short survey of research in 3D Reconstruction of Satellite data, and finally, we propose a workflow that will provide a direction for future researchers in generation 3D models of Satellite Data using Deep learning techniques. The workflow includes the use of CNN for object segmentation and use of GAN for DSM or height map construction and 3D model generation
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM)
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM)
2021 International Conference on Technological Advancements and Innovations (ICTAI)
When it comes to determining whether or not to buy a product, reviews are very crucial. These rev... more When it comes to determining whether or not to buy a product, reviews are very crucial. These review sites are continually bombarded with inaccurate information, which may be perpetrated by individuals or groups who fabricate fake reviews in order to promote or demonize specific goods. This research work concentrates on the identification of fake reviews or feedbacks using sentiment analysis and natural language processing. To transform the data into a format appropriate for analysis and detection, a pre-processing technique is used. The proposed method involves analyzing review feedbacks with deep learning neural networks like the Gated Recurrent Unit (GRU), Bidirectional LSTM (Bi-LSTM) & Long Short Term Memory (LSTM), and evaluating the results using activation functions like ReLu, TanH, and Sigmoid.
2021 International Conference on Technological Advancements and Innovations (ICTAI)
Web browsing has become the integral part of our daily activities. Users come across various adve... more Web browsing has become the integral part of our daily activities. Users come across various advertisement while accessing these web pages. Various companies advertise their products on web pages to increase their sales. The companies hire other Advertisement Agencies for the task of publishing the advertisement. The Advertisement Agency charges the company for clicks made on the Advertisement links using pay-per-click model. Few Advertisements Agency indulge in malpractices to increase their profit by manipulating the number of clicks, this leads to financial loss to the company advertising their products. Click fraud detection helps in identifying the genuine clicks made by the user and the counterfeit clicks made using click bots or other software. In this paper, a comparison is conducted between different machine learning algorithms- Logistic Regression, RNN and various Boosting Algorithm on the basis of accuracy, precision, recall rate, f1-score, subsample, n_estimator, max depth and Learning Rate. The system was experimented on TalkingData AdTracking Fraud Detection Dataset from Kaggle. After experimental analysis it is observed that Logistic Regression shows superiority over the models in comparison.
Microscopy Research and Technique, 2018
Complicated stages of diabetes are the major cause of Diabetic Retinopathy (DR) and no symptoms a... more Complicated stages of diabetes are the major cause of Diabetic Retinopathy (DR) and no symptoms appear at the initial stage of DR. At the early stage diagnosis of DR, screening and treatment may reduce vision harm. In this work, an automated technique is applied for detection and classification of DR. A local contrast enhancement method is used on grayscale images to enhance the region of interest. An adaptive threshold method with mathematical morphology is used for the accurate lesions region segmentation. After that, the geometrical and statistical features are fused for better classification. The proposed method is validated on DIARETDB1, E-ophtha, Messidor, and local data sets with different metrics such as area under the curve (AUC) and accuracy (ACC).
2021 International Conference on Technological Advancements and Innovations (ICTAI), 2021
X-ray imaging are frequently utilized to study inside objects of the human body. X-ray images hav... more X-ray imaging are frequently utilized to study inside objects of the human body. X-ray images have less contrast, noise, and brightness than normal images. As a result, improvement is required. Histogram Equalization, Contrast Enhancement, Edge Detection, Denoising, Deblurring, and other enhancement methods are among them. A new image enhancement technique for X-ray pictures is proposed here, which employs various image processing techniques. Contrast-stretching transformation, Gaussian filter, Logarithmic image processing, standard logic, Edge detection method, and other techniques are used in this method. The proposed technology detects edges and produces higher-quality images, allowing doctors, physicians, and patients to appropriately diagnose illnesses. Images with better brightness and contrast, for example, are produced using the proposed method. In addition, our proposed solution takes less time to compute.
2021 International Conference on Technological Advancements and Innovations (ICTAI), 2021
2021 International Conference on Technological Advancements and Innovations (ICTAI), 2021
2021 International Conference on Technological Advancements and Innovations (ICTAI), 2021
2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), 2020
Pneumonia is among the most prevalent diseases, and due to lack of experts it is difficult to det... more Pneumonia is among the most prevalent diseases, and due to lack of experts it is difficult to detect. This paper focuses on surveying and comparing the detection of lung disease using different computer-aided techniques and suggests a revised model for detecting pneumonia, which will then be implemented as part of our future research. In this survey, we also tried to familiarize ourselves with the different image pre-processing techniques used to convert raw X-ray images into standard formats for analysis and detection, machine learning techniques such as CNN, RESNET, CheXNet, DENSENET, ANN and KNN, which is an important phase in accurate pneumonia detection.
International Journal of Recent Technology and Engineering, 2019
Affording in the direction of Breast Cancer Organization, Breast Cancer is solitary and one and o... more Affording in the direction of Breast Cancer Organization, Breast Cancer is solitary and one and only of the most perilous sorts of viruses that is located operative for females in the biosphere. By way of experimental professional distinguishing this cancer in her initial phase aids in abiding breathes. Based on cancer.net proposal individualized funnels for additional 120 kinds of cancer and correlated to genetic diseases. Aimed At discovering breast cancer fundamentally AI rehearses are utilized. We have foreseen adaptive ensemble voting scheme for broke down breast cancer with WBC (Wisconsin Breast Cancer) record. Intention of our effort is to associate & describe in what way CNN and logistic algorithm afford used for detecting breast cancer yet the variables are condensed. Here remain 2 categories of tumours be situated. Benign tumour and malignant tumours, where benign tumour is non-cancer and malignant is cancer tumour
Journal of Computer Networks and Communications, 2015
The emergence of Wireless Multimedia Sensor Networks (WMSNs) has stimulated the refocusing of res... more The emergence of Wireless Multimedia Sensor Networks (WMSNs) has stimulated the refocusing of research from conventional scalar Wireless Sensor Networks (WSNs) to WMSNs. Currently, because of their prevalence WMSNs are used in different applications. Due to the unique features of WMSNs, fulfilling Quality of Service (QoS) requirements for a variety of applications is the challenge. QoS routing is a backbone of WMSNs and plays a vital role in satisfying QoS requirements. The performance of QoS routing depends upon the selection of an optimal path or paths. Path selection is based on evaluation of a cost function using various routing metrics. A careful blend of such metrics in a routing cost function guarantees a committed level of QoS. This survey uses number of routing metrics as criteria for categorizing state-of-the-art QoS WMSNs routing techniques. In addition, open issues and future research directions to further develop efficient routing protocols to guarantee QoS are discussed.
International Journal of Computer Applications, 2021
2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), 2020
Machine Translation is a popular field in computer science. It’s also a key part in the field of ... more Machine Translation is a popular field in computer science. It’s also a key part in the field of Natural Language Processing. Since India is a country where multiple languages are spoken there is a need for Language Translation. In this paper, we present a survey of several research works and the machine translation approaches mentioned in them. We begin with some well-established methodologies and further delve into more recent and hybrid techniques which are still in the state of improvement. We also compare these papers using several parameters such as the tools & technologies, datasets, advantages, disadvantages, and accuracy. We propose a machine translation model based on Statistical Machine Translation that will help us to translate from the Indian regional language Konkani to English and vice versa.
Diabetes is a very common disease among people who suffer from glucose abnormalities. Diabetic Re... more Diabetes is a very common disease among people who suffer from glucose abnormalities. Diabetic Retinopathy (DR) is a severe microvascular complication that is found only in diabetic patients that affects the retina of the patient and causes permanent partial or complete blindness to the affected person if not detected and cured at an early stage. However, many diabetic patients fail to detect this disease & lead themselves to visual impairments and this happens due to delay in detection as the patient needs to approach the ophthalmologist who screens the retina of the patient. This manual screening & traditional approach is time-consuming and delays the DR detection process which causes the disease to advance to further stages in the time window and also this manual processing isn’t always accurate. This article surveys & reviews the latest research as well as survey papers discussing about the accurate diagnosis as well as Classification of DR into different categories from mild to...
2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE)
Conversation agents or chatbots are software’s which can have conversations with human beings as ... more Conversation agents or chatbots are software’s which can have conversations with human beings as if the conversation is between two humans. Such bots use artificial intelligence to understand the input given by human and accordingly respond back. In today’s world, a lot of people use the smartphones most of the time. They may use chatbots for their personal assistance and to extract information from the internet. Medical/Health, Agriculture and educational domains are important domains to pay attention to. Today, Chatbots can perform tasks such as Minimized Agent Transfers, Quicker Issue Resolution, improved Self-Service, etc. with no waiting time and cost optimization. Other chatbots perform prediction tasks (especially in the medical domain) which is possible today with advancements in AI and Data Mining Techniques.The goal of this paper is to conduct a survey to compare already existing chatbots with respect to platforms used, algorithms applied, tools and software used etc.
2019 International Conference on Vision Towards Emerging Trends in Communication and Networking (ViTECoN), 2019
Finding criminals or hunting for people, in a CCTV video footage, after a crime scene or major at... more Finding criminals or hunting for people, in a CCTV video footage, after a crime scene or major attack takes place, is a time consuming task. As informed to us by cyber cell members of Goa branch, they make multiple members of the department sit with laptops and computers literally to search through the CCTV footage to find and trace the guilty, as they don’t have the automated system for doing this task with them. This process is both time and labor intensive.In this research paper we have tried to survey the existing technologies as well as we propose a new system for criminal Detection & Recognition using Cloud Computing and Machine Learning, which if used by our Crime Agencies would definitely help them to find criminals from CCTV footage. The proposed system can not only help find criminals but if used properly on different sites such as railway stations etc, can also help find missing children and people from the CCTV footage available from the respective site.Existing solution...
Chatbots, or conversational interfaces as they are also known, present a new way for individuals ... more Chatbots, or conversational interfaces as they are also known, present a new way for individuals to interact with computer systems. A chatbot allows a user to simply ask questions in the same manner that they would address a human. However, chatbots are currently being adopted at a high rate on computer chat platforms. Such bots use artificial intelligence to understand the input given by humans and accordingly respond. Medical/ Health, Agriculture and educational domains are important domains to pay attention to. Nowadays, chatbots can be used anywhere a human can interact with a system anytime. Customer Service, Sales/Marketing/Branding, Human Resources, These are the areas where the fastest adoption is occurring. Other chatbots perform prediction tasks (especially in the medical domain) which is possible today with advancements in AI and Data Mining Techniques. As in today’s world, the number of patients daily is increasing rapidly with the change in lifestyle. The queues in hosp...
2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), 2020
Low light imaging is one of the vital and modernistic research areas in digital image processing.... more Low light imaging is one of the vital and modernistic research areas in digital image processing. Low light imaging is a complex task due to low SNR and photon count. This happens when the image signal is simply too weak to pay for the noise. There are many unfold algorithms and every approach has its assumptions, blessings, and limitations. The range of techniques such as de-mosaicking, de-noising, image enhancement, amplification for low light images has been introduced. This paper provides a review of some imperative and significant work that has been carried out in the field of low light imaging. After providing a short introduction, an outline of various algorithms and analysis, some vital approaches have been classified into different respective groups. The main intention of the technique used in this paper is to process the image so that the outcome is more compatible than the original one i.e. altering and analyzing pictorial information of images. Finally, it discusses the ...
International journal of engineering research and technology, May 24, 2021
3D Reconstruction has been a field of interest for multiple disciplines, and in the past decade, ... more 3D Reconstruction has been a field of interest for multiple disciplines, and in the past decade, many researchers have devoted their studies to improve on state-of-art automated methods used for 3D Reconstruction. 3D models have their application in solving numerous visualization problems and a large number of undertakings beyond visualization. In this paper, we conduct a short survey of research in 3D Reconstruction of Satellite data, and finally, we propose a workflow that will provide a direction for future researchers in generation 3D models of Satellite Data using Deep learning techniques. The workflow includes the use of CNN for object segmentation and use of GAN for DSM or height map construction and 3D model generation
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM)
2022 3rd International Conference on Intelligent Engineering and Management (ICIEM)
2021 International Conference on Technological Advancements and Innovations (ICTAI)
When it comes to determining whether or not to buy a product, reviews are very crucial. These rev... more When it comes to determining whether or not to buy a product, reviews are very crucial. These review sites are continually bombarded with inaccurate information, which may be perpetrated by individuals or groups who fabricate fake reviews in order to promote or demonize specific goods. This research work concentrates on the identification of fake reviews or feedbacks using sentiment analysis and natural language processing. To transform the data into a format appropriate for analysis and detection, a pre-processing technique is used. The proposed method involves analyzing review feedbacks with deep learning neural networks like the Gated Recurrent Unit (GRU), Bidirectional LSTM (Bi-LSTM) & Long Short Term Memory (LSTM), and evaluating the results using activation functions like ReLu, TanH, and Sigmoid.
2021 International Conference on Technological Advancements and Innovations (ICTAI)
Web browsing has become the integral part of our daily activities. Users come across various adve... more Web browsing has become the integral part of our daily activities. Users come across various advertisement while accessing these web pages. Various companies advertise their products on web pages to increase their sales. The companies hire other Advertisement Agencies for the task of publishing the advertisement. The Advertisement Agency charges the company for clicks made on the Advertisement links using pay-per-click model. Few Advertisements Agency indulge in malpractices to increase their profit by manipulating the number of clicks, this leads to financial loss to the company advertising their products. Click fraud detection helps in identifying the genuine clicks made by the user and the counterfeit clicks made using click bots or other software. In this paper, a comparison is conducted between different machine learning algorithms- Logistic Regression, RNN and various Boosting Algorithm on the basis of accuracy, precision, recall rate, f1-score, subsample, n_estimator, max depth and Learning Rate. The system was experimented on TalkingData AdTracking Fraud Detection Dataset from Kaggle. After experimental analysis it is observed that Logistic Regression shows superiority over the models in comparison.
Microscopy Research and Technique, 2018
Complicated stages of diabetes are the major cause of Diabetic Retinopathy (DR) and no symptoms a... more Complicated stages of diabetes are the major cause of Diabetic Retinopathy (DR) and no symptoms appear at the initial stage of DR. At the early stage diagnosis of DR, screening and treatment may reduce vision harm. In this work, an automated technique is applied for detection and classification of DR. A local contrast enhancement method is used on grayscale images to enhance the region of interest. An adaptive threshold method with mathematical morphology is used for the accurate lesions region segmentation. After that, the geometrical and statistical features are fused for better classification. The proposed method is validated on DIARETDB1, E-ophtha, Messidor, and local data sets with different metrics such as area under the curve (AUC) and accuracy (ACC).
2021 International Conference on Technological Advancements and Innovations (ICTAI), 2021
X-ray imaging are frequently utilized to study inside objects of the human body. X-ray images hav... more X-ray imaging are frequently utilized to study inside objects of the human body. X-ray images have less contrast, noise, and brightness than normal images. As a result, improvement is required. Histogram Equalization, Contrast Enhancement, Edge Detection, Denoising, Deblurring, and other enhancement methods are among them. A new image enhancement technique for X-ray pictures is proposed here, which employs various image processing techniques. Contrast-stretching transformation, Gaussian filter, Logarithmic image processing, standard logic, Edge detection method, and other techniques are used in this method. The proposed technology detects edges and produces higher-quality images, allowing doctors, physicians, and patients to appropriately diagnose illnesses. Images with better brightness and contrast, for example, are produced using the proposed method. In addition, our proposed solution takes less time to compute.
2021 International Conference on Technological Advancements and Innovations (ICTAI), 2021
2021 International Conference on Technological Advancements and Innovations (ICTAI), 2021
2021 International Conference on Technological Advancements and Innovations (ICTAI), 2021
2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), 2020
Pneumonia is among the most prevalent diseases, and due to lack of experts it is difficult to det... more Pneumonia is among the most prevalent diseases, and due to lack of experts it is difficult to detect. This paper focuses on surveying and comparing the detection of lung disease using different computer-aided techniques and suggests a revised model for detecting pneumonia, which will then be implemented as part of our future research. In this survey, we also tried to familiarize ourselves with the different image pre-processing techniques used to convert raw X-ray images into standard formats for analysis and detection, machine learning techniques such as CNN, RESNET, CheXNet, DENSENET, ANN and KNN, which is an important phase in accurate pneumonia detection.
International Journal of Recent Technology and Engineering, 2019
Affording in the direction of Breast Cancer Organization, Breast Cancer is solitary and one and o... more Affording in the direction of Breast Cancer Organization, Breast Cancer is solitary and one and only of the most perilous sorts of viruses that is located operative for females in the biosphere. By way of experimental professional distinguishing this cancer in her initial phase aids in abiding breathes. Based on cancer.net proposal individualized funnels for additional 120 kinds of cancer and correlated to genetic diseases. Aimed At discovering breast cancer fundamentally AI rehearses are utilized. We have foreseen adaptive ensemble voting scheme for broke down breast cancer with WBC (Wisconsin Breast Cancer) record. Intention of our effort is to associate & describe in what way CNN and logistic algorithm afford used for detecting breast cancer yet the variables are condensed. Here remain 2 categories of tumours be situated. Benign tumour and malignant tumours, where benign tumour is non-cancer and malignant is cancer tumour
Journal of Computer Networks and Communications, 2015
The emergence of Wireless Multimedia Sensor Networks (WMSNs) has stimulated the refocusing of res... more The emergence of Wireless Multimedia Sensor Networks (WMSNs) has stimulated the refocusing of research from conventional scalar Wireless Sensor Networks (WSNs) to WMSNs. Currently, because of their prevalence WMSNs are used in different applications. Due to the unique features of WMSNs, fulfilling Quality of Service (QoS) requirements for a variety of applications is the challenge. QoS routing is a backbone of WMSNs and plays a vital role in satisfying QoS requirements. The performance of QoS routing depends upon the selection of an optimal path or paths. Path selection is based on evaluation of a cost function using various routing metrics. A careful blend of such metrics in a routing cost function guarantees a committed level of QoS. This survey uses number of routing metrics as criteria for categorizing state-of-the-art QoS WMSNs routing techniques. In addition, open issues and future research directions to further develop efficient routing protocols to guarantee QoS are discussed.
International Journal of Computer Applications, 2021
2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), 2020
Machine Translation is a popular field in computer science. It’s also a key part in the field of ... more Machine Translation is a popular field in computer science. It’s also a key part in the field of Natural Language Processing. Since India is a country where multiple languages are spoken there is a need for Language Translation. In this paper, we present a survey of several research works and the machine translation approaches mentioned in them. We begin with some well-established methodologies and further delve into more recent and hybrid techniques which are still in the state of improvement. We also compare these papers using several parameters such as the tools & technologies, datasets, advantages, disadvantages, and accuracy. We propose a machine translation model based on Statistical Machine Translation that will help us to translate from the Indian regional language Konkani to English and vice versa.
Diabetes is a very common disease among people who suffer from glucose abnormalities. Diabetic Re... more Diabetes is a very common disease among people who suffer from glucose abnormalities. Diabetic Retinopathy (DR) is a severe microvascular complication that is found only in diabetic patients that affects the retina of the patient and causes permanent partial or complete blindness to the affected person if not detected and cured at an early stage. However, many diabetic patients fail to detect this disease & lead themselves to visual impairments and this happens due to delay in detection as the patient needs to approach the ophthalmologist who screens the retina of the patient. This manual screening & traditional approach is time-consuming and delays the DR detection process which causes the disease to advance to further stages in the time window and also this manual processing isn’t always accurate. This article surveys & reviews the latest research as well as survey papers discussing about the accurate diagnosis as well as Classification of DR into different categories from mild to...
2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE)
Conversation agents or chatbots are software’s which can have conversations with human beings as ... more Conversation agents or chatbots are software’s which can have conversations with human beings as if the conversation is between two humans. Such bots use artificial intelligence to understand the input given by human and accordingly respond back. In today’s world, a lot of people use the smartphones most of the time. They may use chatbots for their personal assistance and to extract information from the internet. Medical/Health, Agriculture and educational domains are important domains to pay attention to. Today, Chatbots can perform tasks such as Minimized Agent Transfers, Quicker Issue Resolution, improved Self-Service, etc. with no waiting time and cost optimization. Other chatbots perform prediction tasks (especially in the medical domain) which is possible today with advancements in AI and Data Mining Techniques.The goal of this paper is to conduct a survey to compare already existing chatbots with respect to platforms used, algorithms applied, tools and software used etc.
2019 International Conference on Vision Towards Emerging Trends in Communication and Networking (ViTECoN), 2019
Finding criminals or hunting for people, in a CCTV video footage, after a crime scene or major at... more Finding criminals or hunting for people, in a CCTV video footage, after a crime scene or major attack takes place, is a time consuming task. As informed to us by cyber cell members of Goa branch, they make multiple members of the department sit with laptops and computers literally to search through the CCTV footage to find and trace the guilty, as they don’t have the automated system for doing this task with them. This process is both time and labor intensive.In this research paper we have tried to survey the existing technologies as well as we propose a new system for criminal Detection & Recognition using Cloud Computing and Machine Learning, which if used by our Crime Agencies would definitely help them to find criminals from CCTV footage. The proposed system can not only help find criminals but if used properly on different sites such as railway stations etc, can also help find missing children and people from the CCTV footage available from the respective site.Existing solution...
Chatbots, or conversational interfaces as they are also known, present a new way for individuals ... more Chatbots, or conversational interfaces as they are also known, present a new way for individuals to interact with computer systems. A chatbot allows a user to simply ask questions in the same manner that they would address a human. However, chatbots are currently being adopted at a high rate on computer chat platforms. Such bots use artificial intelligence to understand the input given by humans and accordingly respond. Medical/ Health, Agriculture and educational domains are important domains to pay attention to. Nowadays, chatbots can be used anywhere a human can interact with a system anytime. Customer Service, Sales/Marketing/Branding, Human Resources, These are the areas where the fastest adoption is occurring. Other chatbots perform prediction tasks (especially in the medical domain) which is possible today with advancements in AI and Data Mining Techniques. As in today’s world, the number of patients daily is increasing rapidly with the change in lifestyle. The queues in hosp...
2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), 2020
Low light imaging is one of the vital and modernistic research areas in digital image processing.... more Low light imaging is one of the vital and modernistic research areas in digital image processing. Low light imaging is a complex task due to low SNR and photon count. This happens when the image signal is simply too weak to pay for the noise. There are many unfold algorithms and every approach has its assumptions, blessings, and limitations. The range of techniques such as de-mosaicking, de-noising, image enhancement, amplification for low light images has been introduced. This paper provides a review of some imperative and significant work that has been carried out in the field of low light imaging. After providing a short introduction, an outline of various algorithms and analysis, some vital approaches have been classified into different respective groups. The main intention of the technique used in this paper is to process the image so that the outcome is more compatible than the original one i.e. altering and analyzing pictorial information of images. Finally, it discusses the ...