Pub Date : 2020-06-01DOI: 10.1109/incet49848.2020.9154032
Pratik D. Shah, R. Bichkar
Steganography is used to perform covert communication. The advantage of steganography over other secret communication techniques is its ability to conceal the presence of covert communication. In image steganography, the secret information is concealed in the cover image, in such a way that it produces very negligible change in the cover image. A vast amount of research is performed in image steganography but very limited studies have explored the possibility of choosing a cover image for steganography which provides better compatibility with the secret data. In this paper, we propose a genetic algorithm based technique for selecting a cover image from a database of images. The selected cover image is most compatible with the given secret data. We further explore the possibility of rearranging the secret data to increase the imperceptibility of the stego image.
{"title":"Genetic Algorithm based Approach to Select Suitable Cover Image for Image Steganography","authors":"Pratik D. Shah, R. Bichkar","doi":"10.1109/incet49848.2020.9154032","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154032","url":null,"abstract":"Steganography is used to perform covert communication. The advantage of steganography over other secret communication techniques is its ability to conceal the presence of covert communication. In image steganography, the secret information is concealed in the cover image, in such a way that it produces very negligible change in the cover image. A vast amount of research is performed in image steganography but very limited studies have explored the possibility of choosing a cover image for steganography which provides better compatibility with the secret data. In this paper, we propose a genetic algorithm based technique for selecting a cover image from a database of images. The selected cover image is most compatible with the given secret data. We further explore the possibility of rearranging the secret data to increase the imperceptibility of the stego image.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117108611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/incet49848.2020.9154067
B. Sravani, M. M. Bala
This paper is about how the application of machine Learning have huge impact in teaching and learning for further improvement in learning environment in higher education. Due to the interest of students in online and digital courses increased rapidly websites such as Course Era, Udemy etc became very influential. We implement the new applications of machine learning in teaching and learning considering the students background, students past academic score and considering other attributes. As the sizes of classes are large, it would be difficult to assist each individual student in each open learning course, this can increase the bar of the dropout rate at the end of the course. In this paper we are implementing linear regression which is a machine learning algorithm to predict the student’s performance in academics
{"title":"Prediction of Student Performance Using Linear Regression","authors":"B. Sravani, M. M. Bala","doi":"10.1109/incet49848.2020.9154067","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154067","url":null,"abstract":"This paper is about how the application of machine Learning have huge impact in teaching and learning for further improvement in learning environment in higher education. Due to the interest of students in online and digital courses increased rapidly websites such as Course Era, Udemy etc became very influential. We implement the new applications of machine learning in teaching and learning considering the students background, students past academic score and considering other attributes. As the sizes of classes are large, it would be difficult to assist each individual student in each open learning course, this can increase the bar of the dropout rate at the end of the course. In this paper we are implementing linear regression which is a machine learning algorithm to predict the student’s performance in academics","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116234570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/incet49848.2020.9154075
Meghal Darji, Jaivik Dave, Nadim Asif, Chirag Godawat, Vishal M. Chudasama, Kishor P. Upla
Motorcycle accidents have been rapidly increasing in many countries. The helmet is the main safety equipment of motorcyclists, but many drivers do not use it. Helmets are essential for the safety of a motorcycle rider. Hence, detecting and extracting licence plate of the motorcycle in which riders have not wear helmet becomes a crucial task. Many methods have been proposed to detect and extract the licence plate; however, due to poor video quality and non-uniform illumination, licence plate detection becomes a difficult task. Recently, due to the advancement in graphical processing units (GPUs) and larger datasets, deep learning based models have obtained remarkable performance in the object detection task. One such model is single shot detection (SSD) which classify and detect real-time objects precisely. In this paper, we propose an end-to-end approach for detecting and extracting a licence plate of the motorcycle. Here, we use a MobileNet based SSD model to detect License plates as MobileNet i.e., a light-weight CNN model which is more suitable for mobile and embedded vision applications to obtain fast operation. We also prepare a dataset of Indian motorcycle licence plates which consists of 1524 images to train and validate the SSD model. From experiments, we found that the detection module detects the Indian motorcycle licence plate accurately. Once the License plates are detected, the detected licence plate is extracted and the characters of the extracted licence plate are recognized through optical character recognition (OCR) module.
{"title":"Licence Plate Identification and Recognition for Non-Helmeted Motorcyclists using Light-weight Convolution Neural Network","authors":"Meghal Darji, Jaivik Dave, Nadim Asif, Chirag Godawat, Vishal M. Chudasama, Kishor P. Upla","doi":"10.1109/incet49848.2020.9154075","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154075","url":null,"abstract":"Motorcycle accidents have been rapidly increasing in many countries. The helmet is the main safety equipment of motorcyclists, but many drivers do not use it. Helmets are essential for the safety of a motorcycle rider. Hence, detecting and extracting licence plate of the motorcycle in which riders have not wear helmet becomes a crucial task. Many methods have been proposed to detect and extract the licence plate; however, due to poor video quality and non-uniform illumination, licence plate detection becomes a difficult task. Recently, due to the advancement in graphical processing units (GPUs) and larger datasets, deep learning based models have obtained remarkable performance in the object detection task. One such model is single shot detection (SSD) which classify and detect real-time objects precisely. In this paper, we propose an end-to-end approach for detecting and extracting a licence plate of the motorcycle. Here, we use a MobileNet based SSD model to detect License plates as MobileNet i.e., a light-weight CNN model which is more suitable for mobile and embedded vision applications to obtain fast operation. We also prepare a dataset of Indian motorcycle licence plates which consists of 1524 images to train and validate the SSD model. From experiments, we found that the detection module detects the Indian motorcycle licence plate accurately. Once the License plates are detected, the detected licence plate is extracted and the characters of the extracted licence plate are recognized through optical character recognition (OCR) module.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121272147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/INCET49848.2020.9154176
Geetanjali Rohilla, Dinesh Mathur, U. Ghanekar
Peripheral Component Interconnect (PCI) Express is a modern, high performance, point to point, general purpose input output interconnect communication protocol. PCI Express supersedes other legacy buses and provides higher bandwidth which makes it ideal choice for many applications. It provides layered architecture which contains three separate layers. Information flows among these layers in terms of packets. PCI Express Gen5.0 is a latest protocol which provides data rate of 32GT/s per lane and backward compatible with previous releases of PCI Express specifications Gen4.0(16GT/s), Gen3.0(8GT/s), Gen2.0 (5GT/s) and Gen1.1 (2.5GT/s). This presented paper performs the verification of the PCI Express Gen5.0 transactions between MAC (Media Access Layer) and PHY (Combination of SerDes & Physical Sub-block (Physical Media Attachment Layer)) layers of PCIe Gen5.0 physical layer. The RTL of PCI Express Gen5.0 is designed in SystemVerilog language and for the verification purpose, the methodology used is Universal Verification Methodology. Simulation results show the efficacy of the proposed procedure which are shown in Synopsys Discovery Visual Environment tool successfully.
{"title":"Functional Verification of MAC-PHY Layer of PCI Express Gen5.0 with PIPE Interface using UVM","authors":"Geetanjali Rohilla, Dinesh Mathur, U. Ghanekar","doi":"10.1109/INCET49848.2020.9154176","DOIUrl":"https://doi.org/10.1109/INCET49848.2020.9154176","url":null,"abstract":"Peripheral Component Interconnect (PCI) Express is a modern, high performance, point to point, general purpose input output interconnect communication protocol. PCI Express supersedes other legacy buses and provides higher bandwidth which makes it ideal choice for many applications. It provides layered architecture which contains three separate layers. Information flows among these layers in terms of packets. PCI Express Gen5.0 is a latest protocol which provides data rate of 32GT/s per lane and backward compatible with previous releases of PCI Express specifications Gen4.0(16GT/s), Gen3.0(8GT/s), Gen2.0 (5GT/s) and Gen1.1 (2.5GT/s). This presented paper performs the verification of the PCI Express Gen5.0 transactions between MAC (Media Access Layer) and PHY (Combination of SerDes & Physical Sub-block (Physical Media Attachment Layer)) layers of PCIe Gen5.0 physical layer. The RTL of PCI Express Gen5.0 is designed in SystemVerilog language and for the verification purpose, the methodology used is Universal Verification Methodology. Simulation results show the efficacy of the proposed procedure which are shown in Synopsys Discovery Visual Environment tool successfully.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125478086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/incet49848.2020.9154097
Ankit Mishra, V. Dehalwar, Jalpa H. Jobanputra, Mohan Lal Kolhe
The growth of wireless data is the major driving force for an exponential increase in wireless communication. Cognitive Radio is one of the emerging wireless technologies that can be used for smart utility networks. Optimum utilization of the wireless spectrum is the objective of Cognitive Radio. Finding a spectrum hole through intelligent means is essential for the success of Cognitive Radio. Dynamic spectrum allocation is also an efficient technique for spectrum allocation. It will lead to a better spectrum utilization. In this paper, some of the machine learning techniques are used to find a frequency range for dynamic spectrum allocation. Different machine learning techniques such as Logistic Regression, Support Vector Machine, Adaboost Classifier, and Random Forests were used to find spectrum holes in skewed data. Random Forest outperforms all the other models with an accuracy of 91% for determining the spectrum bandwidth (i.e. hole) for Cognitive Radio applications.
{"title":"Spectrum Hole Detection for Cognitive Radio through Energy Detection using Random Forest","authors":"Ankit Mishra, V. Dehalwar, Jalpa H. Jobanputra, Mohan Lal Kolhe","doi":"10.1109/incet49848.2020.9154097","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154097","url":null,"abstract":"The growth of wireless data is the major driving force for an exponential increase in wireless communication. Cognitive Radio is one of the emerging wireless technologies that can be used for smart utility networks. Optimum utilization of the wireless spectrum is the objective of Cognitive Radio. Finding a spectrum hole through intelligent means is essential for the success of Cognitive Radio. Dynamic spectrum allocation is also an efficient technique for spectrum allocation. It will lead to a better spectrum utilization. In this paper, some of the machine learning techniques are used to find a frequency range for dynamic spectrum allocation. Different machine learning techniques such as Logistic Regression, Support Vector Machine, Adaboost Classifier, and Random Forests were used to find spectrum holes in skewed data. Random Forest outperforms all the other models with an accuracy of 91% for determining the spectrum bandwidth (i.e. hole) for Cognitive Radio applications.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124553277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/incet49848.2020.9154178
Sayed Azain Jaffer, Siddharth Pandey, R. Mehta, P. Bhavathankar
Delivery of subsidies to deserving beneficiaries forms an essential part of government expenditure. In 2018-19 alone, the Government of India spent $60 Bn on welfare subsidies, majorly through the Public Distribution System(PDS). Of this amount, it is estimated that 40% was lost in the form of misuse, corruption and related inefficiencies in the system. Recognising this problem, the government began Direct Benefit Transfers in 2013 for a select few schemes, for instance, LPG subsidy. Using Aadhaar and biometric tokens for validation, the beneficiaries would receive the subsidy as direct cash transfers to their bank accounts. However, in reality, the DBT program has had the same efficiency as the PDS. According to the analysis of the DBT policy, the key drawbacks of this system are lack of auditability, inability to control the use of funds for intended purposes, and over-reliance on the banking infrastructure, which is underdeveloped in the rural areas. In order to plug loopholes in the DBT system, we propose a blockchain-based system. Blockchain consists of cryptographic hash secured distributed ledgers which maintain an immutable log of transactions between all participants of a blockchain network. They have the ability to execute Smart Contracts, which allow for automation of execution of real-world contracts given that certain specified conditions are met. Appropriating the Governments Aadhaar UID, we aim to develop a smart blockchain which automates the disbursement of subsidy which bypasses the need for banks in rural nodes while creating an auditable and transparent ecosystem to curb corruption and financial mismanagement.
{"title":"Blockchain Based Direct Benefit Transfer System For Subsidy Delivery","authors":"Sayed Azain Jaffer, Siddharth Pandey, R. Mehta, P. Bhavathankar","doi":"10.1109/incet49848.2020.9154178","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154178","url":null,"abstract":"Delivery of subsidies to deserving beneficiaries forms an essential part of government expenditure. In 2018-19 alone, the Government of India spent $60 Bn on welfare subsidies, majorly through the Public Distribution System(PDS). Of this amount, it is estimated that 40% was lost in the form of misuse, corruption and related inefficiencies in the system. Recognising this problem, the government began Direct Benefit Transfers in 2013 for a select few schemes, for instance, LPG subsidy. Using Aadhaar and biometric tokens for validation, the beneficiaries would receive the subsidy as direct cash transfers to their bank accounts. However, in reality, the DBT program has had the same efficiency as the PDS. According to the analysis of the DBT policy, the key drawbacks of this system are lack of auditability, inability to control the use of funds for intended purposes, and over-reliance on the banking infrastructure, which is underdeveloped in the rural areas. In order to plug loopholes in the DBT system, we propose a blockchain-based system. Blockchain consists of cryptographic hash secured distributed ledgers which maintain an immutable log of transactions between all participants of a blockchain network. They have the ability to execute Smart Contracts, which allow for automation of execution of real-world contracts given that certain specified conditions are met. Appropriating the Governments Aadhaar UID, we aim to develop a smart blockchain which automates the disbursement of subsidy which bypasses the need for banks in rural nodes while creating an auditable and transparent ecosystem to curb corruption and financial mismanagement.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123848328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/incet49848.2020.9154186
C. Z. Basha, B. Lakshmi Pravallika, D. Vineela, S. Prathyusha
Lung cancer, a massively aggressive, quickly metastasizing and widespread disease, is the primary killer among both men and women worldwide. Regrettably, while the incidence of lung cancer decreased steadily in men over the past several years, it has increased alarmingly in women. In Computed Tomography (CT) lung cancer shows up as an isolated nodule. An Automatic Lung Cancer Detection System using improved Haar Wavelet Transform, Scale-Invariant Feature Transform (SIFT), Back Propagation Neural Network (BPNN), and Watershed Segmentation was proposed in this paper. Further, this work involves the usage of Bag of Visual Words (BOVW) based on K means Clustering to the extracted features from SIFT in the previous step. Later, classification is performed using BPNN which is a supervised learning algorithm from the field of Artificial Neural Networks (ANN). Finally, we detect the nodule in the cancerous lung image using watershed segmentation technique. The validation results have been proposed to be 91% accurate when compared to applying different algorithms.
{"title":"An Effective and Robust Cancer Detection in the Lungs with BPNN and Watershed Segmentation","authors":"C. Z. Basha, B. Lakshmi Pravallika, D. Vineela, S. Prathyusha","doi":"10.1109/incet49848.2020.9154186","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154186","url":null,"abstract":"Lung cancer, a massively aggressive, quickly metastasizing and widespread disease, is the primary killer among both men and women worldwide. Regrettably, while the incidence of lung cancer decreased steadily in men over the past several years, it has increased alarmingly in women. In Computed Tomography (CT) lung cancer shows up as an isolated nodule. An Automatic Lung Cancer Detection System using improved Haar Wavelet Transform, Scale-Invariant Feature Transform (SIFT), Back Propagation Neural Network (BPNN), and Watershed Segmentation was proposed in this paper. Further, this work involves the usage of Bag of Visual Words (BOVW) based on K means Clustering to the extracted features from SIFT in the previous step. Later, classification is performed using BPNN which is a supervised learning algorithm from the field of Artificial Neural Networks (ANN). Finally, we detect the nodule in the cancerous lung image using watershed segmentation technique. The validation results have been proposed to be 91% accurate when compared to applying different algorithms.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128097023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/incet49848.2020.9153986
Achyut Morbekar, Ashi Parihar, R. Jadhav
Agriculture is the cumulative activity for millions of farmers in India. Planters have a wide range of diversity for selecting suitable crops. But due to scarcity of knowledge, farmers are in a daze about kinds of diseases that affect the farm. Many farmers struggle and waste much of their time in reaping diseased crops. The timely assessment of the problem is necessary to avert major damage and enhance production. The proposed system makes use of a novel approach of the object detection technique to detect plant disease, YOLO(You Only Look Once). YOLO processes leaf images at 45 frames per second in real-time, which is faster than other object detection techniques. It divides the image into several grid cells before processing the image. The bounding boxes and class probabilities are predicted by a single neural network in just one evaluation. This effectively boosts the speed and accuracy of disease detection on the leaf.
农业是印度数百万农民的累积活动。种植者在选择合适的作物方面有广泛的多样性。但是由于知识的缺乏，农民对影响农场的各种疾病都很茫然。许多农民在收割有病的作物上挣扎并浪费了大量时间。及时评估问题对于避免重大损失和提高生产是必要的。该系统利用一种新的目标检测技术YOLO(You Only Look Once)来检测植物病害。YOLO实时处理叶子图像的速度为45帧/秒，比其他目标检测技术要快。在对图像进行处理之前，将图像划分为若干网格单元。边界框和类别概率由单个神经网络在一次评估中预测。这有效地提高了叶片疾病检测的速度和准确性。
{"title":"Crop Disease Detection Using YOLO","authors":"Achyut Morbekar, Ashi Parihar, R. Jadhav","doi":"10.1109/incet49848.2020.9153986","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9153986","url":null,"abstract":"Agriculture is the cumulative activity for millions of farmers in India. Planters have a wide range of diversity for selecting suitable crops. But due to scarcity of knowledge, farmers are in a daze about kinds of diseases that affect the farm. Many farmers struggle and waste much of their time in reaping diseased crops. The timely assessment of the problem is necessary to avert major damage and enhance production. The proposed system makes use of a novel approach of the object detection technique to detect plant disease, YOLO(You Only Look Once). YOLO processes leaf images at 45 frames per second in real-time, which is faster than other object detection techniques. It divides the image into several grid cells before processing the image. The bounding boxes and class probabilities are predicted by a single neural network in just one evaluation. This effectively boosts the speed and accuracy of disease detection on the leaf.","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128366664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/incet49848.2020.9154139
K. R, N. N, Komal Babasab Karangale, M. H, S. Sheela
Blood is an important biological fluid that carries vital nutrients, vitamins, minerals and oxygen to various parts of the body. It helps in actual functioning of the body organs. Blood flow is the amount of blood flowing through arteries or veins of the circulatory system. Impairment in the blood flow is an indicator of various diseases. Hence a simple, fast, accurate and non-invasive blood flow measurement technique is required for early detection of the diseases. This paper proposes a simple, accurate, non-invasive method to measure the blood flow related parameters using Photoplethysmography (PPG). The blood volume through the veins is measured by acquiring the PPG signal from the body and further analysing the signal to measure different parameters like heart rate, oxygen saturation level (SpO2) and the PPG values are further used for building a cuffless blood pressure measuring system using an Artificial Neural Networks (ANN) with the dataset obtained from Medical Information Mart for Intensive Care III (MIMIC III).
{"title":"Photoplethysmography — a Modern Approach and Applications","authors":"K. R, N. N, Komal Babasab Karangale, M. H, S. Sheela","doi":"10.1109/incet49848.2020.9154139","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154139","url":null,"abstract":"Blood is an important biological fluid that carries vital nutrients, vitamins, minerals and oxygen to various parts of the body. It helps in actual functioning of the body organs. Blood flow is the amount of blood flowing through arteries or veins of the circulatory system. Impairment in the blood flow is an indicator of various diseases. Hence a simple, fast, accurate and non-invasive blood flow measurement technique is required for early detection of the diseases. This paper proposes a simple, accurate, non-invasive method to measure the blood flow related parameters using Photoplethysmography (PPG). The blood volume through the veins is measured by acquiring the PPG signal from the body and further analysing the signal to measure different parameters like heart rate, oxygen saturation level (SpO2) and the PPG values are further used for building a cuffless blood pressure measuring system using an Artificial Neural Networks (ANN) with the dataset obtained from Medical Information Mart for Intensive Care III (MIMIC III).","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129243551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/incet49848.2020.9154071
Ayush Jain, A. Bansal, Yogesh Kakde
Generative Adversarial Network is a novel concept for a general purpose solution to Deep Fake Image generation. These networks learn mapping from input image to output image and also assign value in loss function for the same mapping. We demonstrate that this approach is effective to synthesize images from labelled images, and colorizing images, and other tasks. We have investigate performance of three different types of model i.e. simple GAN, DC-GAN, BIG-GAN, which have provided different results with generation of different loss function on the same dataset i.e. Stanford Dogs Dataset. In this paper, we have investigated the performance of models by using inception score and also track the loss function at different stages (epochs).
{"title":"Performance Analysis of Various Generative Adversarial Network using Dog image Dataset","authors":"Ayush Jain, A. Bansal, Yogesh Kakde","doi":"10.1109/incet49848.2020.9154071","DOIUrl":"https://doi.org/10.1109/incet49848.2020.9154071","url":null,"abstract":"Generative Adversarial Network is a novel concept for a general purpose solution to Deep Fake Image generation. These networks learn mapping from input image to output image and also assign value in loss function for the same mapping. We demonstrate that this approach is effective to synthesize images from labelled images, and colorizing images, and other tasks. We have investigate performance of three different types of model i.e. simple GAN, DC-GAN, BIG-GAN, which have provided different results with generation of different loss function on the same dataset i.e. Stanford Dogs Dataset. In this paper, we have investigated the performance of models by using inception score and also track the loss function at different stages (epochs).","PeriodicalId":174411,"journal":{"name":"2020 International Conference for Emerging Technology (INCET)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129582878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：