Pub Date : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663614
Ashwini Dasare, Harsha S
Covid-19 has opened up a plethora of worries to the world since the past 2 years. The infection rate and death rate are increasing rapidly. It has worsened by the number of genetic mutations this virus has undergone. Timely detection of the disease is the only way out to handle this health emergency. Severity of this disease is when the virus attacks the major volume of the lung and results in pneumonia. To diagnose the pneumonia the first preferred modality is chest X-ray. There are two solid reasons why the Computer Aided Diagnosis (CAD) system is the need of the hour. First, the volume of X-rays generated for a huge number of infected patients to be assessed and second being the requirement of accuracy in diagnosis. Radiologists find it difficult to assess the severity through bare eyes and most of the time end up making a wrong conclusion which is chaotic decision. With the advent of technology, deep learning algorithms are proving to be most appropriate because of its ability to deliver expected accuracy and capacity to handle huge volume of data. This paper proposed a Deep Learning based Computer Aided Diagnosis System that accepts Chest X-ray image of a patient as input and classifies them as pneumonia or non-pneumonia. The Deep learning model is built and is trained with over 5000 chest X-ray images. Thus, trained model is then tested and validated and an accuracy of 96.66% is achieved. However, since the data is not real time, this work does not claim medical accuracy. The validation plots of the training loss and accuracy and validation loss and accuracy have been validated through regression.
{"title":"Covid19 Infection Detection and Classification Using CNN On Chest X-ray Images","authors":"Ashwini Dasare, Harsha S","doi":"10.1109/DISCOVER52564.2021.9663614","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663614","url":null,"abstract":"Covid-19 has opened up a plethora of worries to the world since the past 2 years. The infection rate and death rate are increasing rapidly. It has worsened by the number of genetic mutations this virus has undergone. Timely detection of the disease is the only way out to handle this health emergency. Severity of this disease is when the virus attacks the major volume of the lung and results in pneumonia. To diagnose the pneumonia the first preferred modality is chest X-ray. There are two solid reasons why the Computer Aided Diagnosis (CAD) system is the need of the hour. First, the volume of X-rays generated for a huge number of infected patients to be assessed and second being the requirement of accuracy in diagnosis. Radiologists find it difficult to assess the severity through bare eyes and most of the time end up making a wrong conclusion which is chaotic decision. With the advent of technology, deep learning algorithms are proving to be most appropriate because of its ability to deliver expected accuracy and capacity to handle huge volume of data. This paper proposed a Deep Learning based Computer Aided Diagnosis System that accepts Chest X-ray image of a patient as input and classifies them as pneumonia or non-pneumonia. The Deep learning model is built and is trained with over 5000 chest X-ray images. Thus, trained model is then tested and validated and an accuracy of 96.66% is achieved. However, since the data is not real time, this work does not claim medical accuracy. The validation plots of the training loss and accuracy and validation loss and accuracy have been validated through regression.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123495280","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663728
A. Shetty, Navya Thirumaleshwar Hegde, A. Vaz
Disparity maps generated through stereo matching algorithms possess the capacity to provide depth information, when at least two or more images of a scene taken from different viewpoints, are presented. This is a computationally complex task and the presence of radiometric differences, such as exposure variations, in the images only further complicates the stereo matching problem. The authors attempt to overcome this problem and try to extract dense disparity maps from a pair of stereo images using a combination of different data cost metrics followed by a fuzzy disparity selector. The images are preprocessed into small patches of pixels, such that pixels in each patch have similar intensities, before being subjected to the stereo matching algorithm. The effect of the number of segments and the tuning parameter ‘α’, on the various exposure conditions is studied and the performance is compared with other methods that try to tackle the problem of stereo matching under similar conditions.
{"title":"Fuzzy Logic Based Stereo Matching Method for Images with Variation in Exposure Conditions","authors":"A. Shetty, Navya Thirumaleshwar Hegde, A. Vaz","doi":"10.1109/DISCOVER52564.2021.9663728","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663728","url":null,"abstract":"Disparity maps generated through stereo matching algorithms possess the capacity to provide depth information, when at least two or more images of a scene taken from different viewpoints, are presented. This is a computationally complex task and the presence of radiometric differences, such as exposure variations, in the images only further complicates the stereo matching problem. The authors attempt to overcome this problem and try to extract dense disparity maps from a pair of stereo images using a combination of different data cost metrics followed by a fuzzy disparity selector. The images are preprocessed into small patches of pixels, such that pixels in each patch have similar intensities, before being subjected to the stereo matching algorithm. The effect of the number of segments and the tuning parameter ‘α’, on the various exposure conditions is studied and the performance is compared with other methods that try to tackle the problem of stereo matching under similar conditions.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131584894","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663646
K. Nandini, G. Seshikala
Embedded computing systems are an amalgamation of various electronic devices, sensors, and processor that is designed to perform specific tasks. In the biomedical field, embedded computing systems are typically used to process data and storage purposes. In recent years, there has been a surge in interest in embedded computing systems for biomedical applications because of their high level of dependability and ability to provide effective healthcare solutions and services. These systems play an important in various applications such as electronic devices, specialized health care systems, reliable wearable electronic gadgets, electrocardiograms, and others. With tremendous technological innovations, such as the assimilation of computing systems with the IoT (Internet of Things) and AI (artificial intelligence) ML (Machine Learning) are the driving factors which has led to gain tremendous usage in the present scenario, and it will continue to grow exponentially in future with global advancements. This technological transformation could certainly create a revolution in embedded computing systems having the global market estimated to be USD 86.5 billion in 2020 and projected to reach USD 116.2 billion by 2025; at a CAGR of 6.1% from 2020 to 2025. This paper attempts to brief the role, opportunities, and challenges of embedded computing devices in the biomedical field particularly to health care applications.
{"title":"Role of Embedded Computing Systems in Biomedical Applications–Opportunities and Challenges","authors":"K. Nandini, G. Seshikala","doi":"10.1109/DISCOVER52564.2021.9663646","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663646","url":null,"abstract":"Embedded computing systems are an amalgamation of various electronic devices, sensors, and processor that is designed to perform specific tasks. In the biomedical field, embedded computing systems are typically used to process data and storage purposes. In recent years, there has been a surge in interest in embedded computing systems for biomedical applications because of their high level of dependability and ability to provide effective healthcare solutions and services. These systems play an important in various applications such as electronic devices, specialized health care systems, reliable wearable electronic gadgets, electrocardiograms, and others. With tremendous technological innovations, such as the assimilation of computing systems with the IoT (Internet of Things) and AI (artificial intelligence) ML (Machine Learning) are the driving factors which has led to gain tremendous usage in the present scenario, and it will continue to grow exponentially in future with global advancements. This technological transformation could certainly create a revolution in embedded computing systems having the global market estimated to be USD 86.5 billion in 2020 and projected to reach USD 116.2 billion by 2025; at a CAGR of 6.1% from 2020 to 2025. This paper attempts to brief the role, opportunities, and challenges of embedded computing devices in the biomedical field particularly to health care applications.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"14 9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132454570","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663580
Calvin Marian Netto, Cifha Crecil Saldanha, Davin Dsouza
The light intensity controller automatically varies the brightness of an LED light depending on the natural light available in the room. In addition to this is room temperature and humidity monitoring. This system uses an Arduino and PWM technology for controlling the intensity of the LED. LDR is used as the LUX meter. The power losses incurred in PWM switching devices is extremely low. A PWM voltage regulator is built using a LM2596 buck converter which is driven by the PWM signal from the Arduino. By mapping the LDR output values to the PWM signal duty cycle the LED light intensity is varied. In addition to the light intensity controller is a temperature monitoring system, using a DHT11 sensor to measure temperature and humidity. This system is more functional than analog dimmers and timer based light controllers. Through the intended system we aim to reduce power consumption of lights through light dimming using PWM technology. It uses the available resources and is suitable for other light dimming applications as well.
{"title":"Room Light Intensity Control with Temperature Monitoring System Using Arduino","authors":"Calvin Marian Netto, Cifha Crecil Saldanha, Davin Dsouza","doi":"10.1109/DISCOVER52564.2021.9663580","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663580","url":null,"abstract":"The light intensity controller automatically varies the brightness of an LED light depending on the natural light available in the room. In addition to this is room temperature and humidity monitoring. This system uses an Arduino and PWM technology for controlling the intensity of the LED. LDR is used as the LUX meter. The power losses incurred in PWM switching devices is extremely low. A PWM voltage regulator is built using a LM2596 buck converter which is driven by the PWM signal from the Arduino. By mapping the LDR output values to the PWM signal duty cycle the LED light intensity is varied. In addition to the light intensity controller is a temperature monitoring system, using a DHT11 sensor to measure temperature and humidity. This system is more functional than analog dimmers and timer based light controllers. Through the intended system we aim to reduce power consumption of lights through light dimming using PWM technology. It uses the available resources and is suitable for other light dimming applications as well.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130842876","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663695
G.B Rakshith, K. Narendra, Sanjeev Gurugopinath
In this paper, we demonstrate the viability of multitaper (MT) features for classification of s peech and music with pretrained audio neural networks (PANN). Among several well-known features for audio tagging, log-mel is widely-used. Therefore, log-mel has been used to train and establish a near-perfect accurate PANN for audio tagging. For the classification problem at hand, we study the performance of MT numerator group delay (MT-NGD) and MT magnitude (MT-Mag) spectral features and compare it with the log-mel feature. Our experimental results on the MARSYAS speech and music database shows that the accuracy of the PANN converges faster as opposed to other features, when trained with MT-NGD spectrogram. Further, the multitaper representations are observed to be robust to the presence of noise in both speech and music.
{"title":"Multitaper Spectrogram for Classification of Speech and Music With Pretrained Audio Neural Networks","authors":"G.B Rakshith, K. Narendra, Sanjeev Gurugopinath","doi":"10.1109/DISCOVER52564.2021.9663695","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663695","url":null,"abstract":"In this paper, we demonstrate the viability of multitaper (MT) features for classification of s peech and music with pretrained audio neural networks (PANN). Among several well-known features for audio tagging, log-mel is widely-used. Therefore, log-mel has been used to train and establish a near-perfect accurate PANN for audio tagging. For the classification problem at hand, we study the performance of MT numerator group delay (MT-NGD) and MT magnitude (MT-Mag) spectral features and compare it with the log-mel feature. Our experimental results on the MARSYAS speech and music database shows that the accuracy of the PANN converges faster as opposed to other features, when trained with MT-NGD spectrogram. Further, the multitaper representations are observed to be robust to the presence of noise in both speech and music.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123655700","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663658
Isha Bhandary, K. Atul, A. Athani, Somashekar Patil, D. Narayan
Cloud data centers consume a huge amount of energy in the form of electrical energy for their operation. They also emit carbon dioxide and impact the balance of nature. This management of exponentially increasing load and the minimization of energy use along with the impact on the environment is the biggest challenge a cloud service provider (CSP) faces. CSPs establish and maintain data center farms, which enable the delivery of cloud services to millions of clients. The reduction in energy usage by data centers while also minimizing the number of service level agreement (SLA) violations is a major challenge. In this work, we have proposed a reinforcement learning (RL)-based dynamic virtual machine (VM) consolidation mechanism wherein the host load is predicted by considering previous and current host utilization. The learning agent chooses a suitable-power mode for the hosts. Load balancing is done for the over-utilized hosts and dynamic VM consolidation is performed for the under-utilized hosts. The VM scheduling is performed using an energy-aware best fit method. Ourproposed model shows a significant drop in the number of SLA violations and energy consumption when compared to the ARIMA model.
{"title":"Energy-Efficient VM Scheduling in the Cloud Environment using Reinforcement Learning","authors":"Isha Bhandary, K. Atul, A. Athani, Somashekar Patil, D. Narayan","doi":"10.1109/DISCOVER52564.2021.9663658","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663658","url":null,"abstract":"Cloud data centers consume a huge amount of energy in the form of electrical energy for their operation. They also emit carbon dioxide and impact the balance of nature. This management of exponentially increasing load and the minimization of energy use along with the impact on the environment is the biggest challenge a cloud service provider (CSP) faces. CSPs establish and maintain data center farms, which enable the delivery of cloud services to millions of clients. The reduction in energy usage by data centers while also minimizing the number of service level agreement (SLA) violations is a major challenge. In this work, we have proposed a reinforcement learning (RL)-based dynamic virtual machine (VM) consolidation mechanism wherein the host load is predicted by considering previous and current host utilization. The learning agent chooses a suitable-power mode for the hosts. Load balancing is done for the over-utilized hosts and dynamic VM consolidation is performed for the under-utilized hosts. The VM scheduling is performed using an energy-aware best fit method. Ourproposed model shows a significant drop in the number of SLA violations and energy consumption when compared to the ARIMA model.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"422 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126713811","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：