Pub Date : 2021-09-02DOI: 10.1109/ACCESS51619.2021.9563306
Dhiya Maria, Ebey Sibi, Sharon Jerome, Yadukrishna N Kumar, Saju Nampoothiri, R. Anurag, C. K. Jayadas, P. S. Nijesh
Autonomous Mobile Robots (AMR) are gaining traction owing to their ability to perform complicated tasks that require navigation in complex and dynamic indoor environments, thus, leading to the replacement of manual workforce with an efficient and affordable robotic system with greater precision, accuracy and minimal error. This paper focuses on developing a system which is based on the two important aspects that determine the performance of an indoor AMR i.e. environment model generation and localisation of an indoor AMR. The perception system is based on the representation and processing of the data obtained from proprioceptive sensors. So far, the Bayesian Occupancy Grid (OG) mapping is the best approach for environment model generation in mobile robotics. The grid mapping approach is used owing to its higher efficiency, better accuracy, faster implementation and probabilistic framework. Localisation is complicated in indoor environments such as warehouses as GPS is not reliable. This is achieved using Hector Simultaneous Localisation And Mapping (SLAM) and Adaptive Monte Carlo Localisation (AMCL) techniques using data received from a 2D-Light Detection And Ranging (LiDAR). Robot Operating System (ROS) is used as the core to design the mobile robot system with high performance and scalability. The simulation environment and robot are created in Gazebo, and visualised using Rviz. The generated OG and localisation results are compared with the ground truth, and its performance analysis is done.
{"title":"Environment Model Generation And Localisation Of Mobile Indoor Autonomous Robots","authors":"Dhiya Maria, Ebey Sibi, Sharon Jerome, Yadukrishna N Kumar, Saju Nampoothiri, R. Anurag, C. K. Jayadas, P. S. Nijesh","doi":"10.1109/ACCESS51619.2021.9563306","DOIUrl":"https://doi.org/10.1109/ACCESS51619.2021.9563306","url":null,"abstract":"Autonomous Mobile Robots (AMR) are gaining traction owing to their ability to perform complicated tasks that require navigation in complex and dynamic indoor environments, thus, leading to the replacement of manual workforce with an efficient and affordable robotic system with greater precision, accuracy and minimal error. This paper focuses on developing a system which is based on the two important aspects that determine the performance of an indoor AMR i.e. environment model generation and localisation of an indoor AMR. The perception system is based on the representation and processing of the data obtained from proprioceptive sensors. So far, the Bayesian Occupancy Grid (OG) mapping is the best approach for environment model generation in mobile robotics. The grid mapping approach is used owing to its higher efficiency, better accuracy, faster implementation and probabilistic framework. Localisation is complicated in indoor environments such as warehouses as GPS is not reliable. This is achieved using Hector Simultaneous Localisation And Mapping (SLAM) and Adaptive Monte Carlo Localisation (AMCL) techniques using data received from a 2D-Light Detection And Ranging (LiDAR). Robot Operating System (ROS) is used as the core to design the mobile robot system with high performance and scalability. The simulation environment and robot are created in Gazebo, and visualised using Rviz. The generated OG and localisation results are compared with the ground truth, and its performance analysis is done.","PeriodicalId":409648,"journal":{"name":"2021 2nd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130811352","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 : 2021-09-02DOI: 10.1109/ACCESS51619.2021.9563324
V. Gopakumar, K. Neetha, Prasanth P Menon, Remya Ramesh
The current technologically vibrant world is demanding more data transfer, data communications and optical computing. Main focus areas are high-definition internet video streaming, image processing, sensing applications, distance learning and in cloud computing. Since last decade we use optical communication technologies for above mentioned bandwidth hungry applications. The biggest advantage of processing the information in the all-optical domain is the availability of huge bandwidth and of course it's ultrahigh processing speeds even for future technologies including 5G. Fiber Bragg grating is widely used for filtering and sensing applications. In order to meet with the high bandwidth requirements for the applications mentioned above, the fiber Bragg gratings are replaced with ultra-narrowband filters like Fabry-Perot filters using fiber Bragg gratings. This article reports a Fabry-Perot narrow band filter using fiber Bragg grating (FP-FBGs) can be designed for all optical memory unit and for detecting the phase keys encrypted in the optical intensity waveforms. All optical integrators are used for both these applications. We also report here the phase key decryption by inputting Double Gaussian to an optical integrating circuit. The optical encryption methods are getting very much attraction in the present days. In order to overcome the fabrication difficulty for optical data encoding in both amplitude and phase regimes, here we propose the decrypting phase keys method where the data is entirely in phase only domain.
{"title":"Proposal for all Optical Memory Unit and Phase Key Recovery using Fabry-Perot Narrowband Filters","authors":"V. Gopakumar, K. Neetha, Prasanth P Menon, Remya Ramesh","doi":"10.1109/ACCESS51619.2021.9563324","DOIUrl":"https://doi.org/10.1109/ACCESS51619.2021.9563324","url":null,"abstract":"The current technologically vibrant world is demanding more data transfer, data communications and optical computing. Main focus areas are high-definition internet video streaming, image processing, sensing applications, distance learning and in cloud computing. Since last decade we use optical communication technologies for above mentioned bandwidth hungry applications. The biggest advantage of processing the information in the all-optical domain is the availability of huge bandwidth and of course it's ultrahigh processing speeds even for future technologies including 5G. Fiber Bragg grating is widely used for filtering and sensing applications. In order to meet with the high bandwidth requirements for the applications mentioned above, the fiber Bragg gratings are replaced with ultra-narrowband filters like Fabry-Perot filters using fiber Bragg gratings. This article reports a Fabry-Perot narrow band filter using fiber Bragg grating (FP-FBGs) can be designed for all optical memory unit and for detecting the phase keys encrypted in the optical intensity waveforms. All optical integrators are used for both these applications. We also report here the phase key decryption by inputting Double Gaussian to an optical integrating circuit. The optical encryption methods are getting very much attraction in the present days. In order to overcome the fabrication difficulty for optical data encoding in both amplitude and phase regimes, here we propose the decrypting phase keys method where the data is entirely in phase only domain.","PeriodicalId":409648,"journal":{"name":"2021 2nd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134490257","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 : 2021-09-02DOI: 10.1109/ACCESS51619.2021.9563329
A. Naghiyeva, K. Akbarzadeh, S. Verdiyev
Data hiding is the science of concealing a secret information in a digital image called a cover image or other multimedia files. This allows the transmit of secret data undetected through open communication channels. Target this article is the development of a new reversible method of data hiding with the priority of preserving the visual quality of the stego image at sufficient hiding capacity. The problem is solved in two stages. In the first step the input image is divided into blocks 2×2, within which the smallest pixel is chosen. The difference between the remaining three pixels and the smallest pixel is then calculated. The decimal values of the resulting difference are converted into binaries. The second stage involves the concealing of bits of secret information into calculated binary pixels using the LSB to increase the payload capacity. The results of the experiment confirmed the effectiveness of the proposed method, which consists of an acceptable value of data hiding capacity value and in the best visual quality of the stego image.
{"title":"New Steganography Method of Reversible Data Hiding With Priority to Visual Quality of Image","authors":"A. Naghiyeva, K. Akbarzadeh, S. Verdiyev","doi":"10.1109/ACCESS51619.2021.9563329","DOIUrl":"https://doi.org/10.1109/ACCESS51619.2021.9563329","url":null,"abstract":"Data hiding is the science of concealing a secret information in a digital image called a cover image or other multimedia files. This allows the transmit of secret data undetected through open communication channels. Target this article is the development of a new reversible method of data hiding with the priority of preserving the visual quality of the stego image at sufficient hiding capacity. The problem is solved in two stages. In the first step the input image is divided into blocks 2×2, within which the smallest pixel is chosen. The difference between the remaining three pixels and the smallest pixel is then calculated. The decimal values of the resulting difference are converted into binaries. The second stage involves the concealing of bits of secret information into calculated binary pixels using the LSB to increase the payload capacity. The results of the experiment confirmed the effectiveness of the proposed method, which consists of an acceptable value of data hiding capacity value and in the best visual quality of the stego image.","PeriodicalId":409648,"journal":{"name":"2021 2nd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131252244","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 : 2021-09-02DOI: 10.1109/ACCESS51619.2021.9563301
K. Pranav, R. Ananthakrishna, N. Jithin, Nikhil George, Anju George
severe acute respiratory syndrome coronavirus 2 (SARS-CoV2) provisionally named COVID-19 is a significant public health and wellness issue. It is rapidly dispersed around the world, leading to a colossal mortality rate. Pneumonia or lung infection is the most usual complication of COVID-19. The best and critical advance in battling COVID-19 is the capacity to recognize the tainted patients quickly and put them under seclusion. As a typical symptomatic apparatus, an X-Ray is fast and simple to secure absent a lot of costs. Developing a touchy analytic apparatus utilizing X-Ray pictures can accelerate the symptomatic cycle and is supplementing and steady to RT-PCR just as the Antigen-based tests. By benefiting the solid component learning capacity, profound learning techniques can mine highlights that are consequently relied upon to have quick and vigorous outcomes that are identified with clinical results from Chest X-Ray pictures. Subsequently, the point is to foster a profound learning framework to effectively recognize, characterize and distinguish amid COVID-19, viral Pneumonia and Tuberculosis from a bunch of chest X-Ray pictures utilizing profound learning techniques which could help exceptionally obliged clinical experts, professionals and analysts in deciding the route of medicine.
{"title":"Predicting COVID-19 and other Lung Related Diseases like Pneumonia and Tuberculosis using Deep Learning","authors":"K. Pranav, R. Ananthakrishna, N. Jithin, Nikhil George, Anju George","doi":"10.1109/ACCESS51619.2021.9563301","DOIUrl":"https://doi.org/10.1109/ACCESS51619.2021.9563301","url":null,"abstract":"severe acute respiratory syndrome coronavirus 2 (SARS-CoV2) provisionally named COVID-19 is a significant public health and wellness issue. It is rapidly dispersed around the world, leading to a colossal mortality rate. Pneumonia or lung infection is the most usual complication of COVID-19. The best and critical advance in battling COVID-19 is the capacity to recognize the tainted patients quickly and put them under seclusion. As a typical symptomatic apparatus, an X-Ray is fast and simple to secure absent a lot of costs. Developing a touchy analytic apparatus utilizing X-Ray pictures can accelerate the symptomatic cycle and is supplementing and steady to RT-PCR just as the Antigen-based tests. By benefiting the solid component learning capacity, profound learning techniques can mine highlights that are consequently relied upon to have quick and vigorous outcomes that are identified with clinical results from Chest X-Ray pictures. Subsequently, the point is to foster a profound learning framework to effectively recognize, characterize and distinguish amid COVID-19, viral Pneumonia and Tuberculosis from a bunch of chest X-Ray pictures utilizing profound learning techniques which could help exceptionally obliged clinical experts, professionals and analysts in deciding the route of medicine.","PeriodicalId":409648,"journal":{"name":"2021 2nd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"431 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123864329","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 : 2021-09-02DOI: 10.1109/ACCESS51619.2021.9563283
Marie Philip, Merin Anna Kurian, Reenu Joseph, R. Sruthi, Sania Thomas
According to the World Health Organization, each year about 1.35 million people are involved in road accidents. These mishaps bring great economic losses to victims, their families, and nations. A system for guiding the drivers is one among the foremost important aspects of recent vehicles; to ensure the security of the driver and to scale back the danger of auto accidents on the road. The proposed system helps the driver to spot the lane through which he or she is meant to drive, and if the vehicle deviates from the right lane, then an alert is shown on the screen. The screen also displays the radius of curvature at each point consistent with the road, along with the position of the vehicle depending on the middle of the lane. The proposed system uses a camera attached to the dashboard of the vehicle which makes it easy for the camera to record the video of the road ahead. This system isn't only helpful for the drivers to avoid accidents but can also be employed by the automated vehicles for following certain lanes. The multiple advantages of this technique emphasize the very fact that this is often a promising system. The expenses for this technique are very low considering the fact that the majority of the vehicles now accompany a camera mounted on its front. This system considers two algorithms; the first one makes use of Canny edge detection along with Hough transform, and the next one is based on Sobel operator along with perspective transform. The latter came out to be more accurate and precise in detecting the lanes along with the detection of curves in these lanes. Hence, for developing the final system the Sobel operator and the perspective transform were used.
{"title":"A Computer Vision Approach for Lane Detection and Tracking","authors":"Marie Philip, Merin Anna Kurian, Reenu Joseph, R. Sruthi, Sania Thomas","doi":"10.1109/ACCESS51619.2021.9563283","DOIUrl":"https://doi.org/10.1109/ACCESS51619.2021.9563283","url":null,"abstract":"According to the World Health Organization, each year about 1.35 million people are involved in road accidents. These mishaps bring great economic losses to victims, their families, and nations. A system for guiding the drivers is one among the foremost important aspects of recent vehicles; to ensure the security of the driver and to scale back the danger of auto accidents on the road. The proposed system helps the driver to spot the lane through which he or she is meant to drive, and if the vehicle deviates from the right lane, then an alert is shown on the screen. The screen also displays the radius of curvature at each point consistent with the road, along with the position of the vehicle depending on the middle of the lane. The proposed system uses a camera attached to the dashboard of the vehicle which makes it easy for the camera to record the video of the road ahead. This system isn't only helpful for the drivers to avoid accidents but can also be employed by the automated vehicles for following certain lanes. The multiple advantages of this technique emphasize the very fact that this is often a promising system. The expenses for this technique are very low considering the fact that the majority of the vehicles now accompany a camera mounted on its front. This system considers two algorithms; the first one makes use of Canny edge detection along with Hough transform, and the next one is based on Sobel operator along with perspective transform. The latter came out to be more accurate and precise in detecting the lanes along with the detection of curves in these lanes. Hence, for developing the final system the Sobel operator and the perspective transform were used.","PeriodicalId":409648,"journal":{"name":"2021 2nd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124195741","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 : 2021-09-02DOI: 10.1109/ACCESS51619.2021.9563290
Labdhi Jain, K. Gala, Dhruv Doshi
With each new wave of COVID-19, the number of patients requiring hospital beds increases, and as we have observed from our previous experiences, a lot of people have lost lives because of the unavailability of hospital beds at the right time. Hence this paper aims to resolve such a situation by the prioritization of patients using machine learning algorithms. Prioritization of patients at a hospital is the process of ordering or ranking patients based on various factors, to make a fair decision about which patient is in utmost need of care. This paper studies the different algorithms like Decision Tree Classifier, Naive Bayes and KNeighbors Classifier with which such a system could be made to predict the severity of patients and finally proposes a fair and efficient system to rank COVID-19 patients based on their severity.
随着新一波COVID-19的爆发，需要医院床位的患者数量增加，正如我们从以前的经验中观察到的那样，许多人因为在正确的时间无法获得医院床位而失去生命。因此，本文旨在通过使用机器学习算法对患者进行优先排序来解决这种情况。医院对患者进行优先排序是根据各种因素对患者进行排序或排名的过程，以公平地决定哪些患者最需要护理。本文研究了决策树分类器(Decision Tree Classifier)、朴素贝叶斯(Naive Bayes)和KNeighbors分类器(KNeighbors Classifier)等不同的算法对患者的严重程度进行预测，最终提出了一个公平高效的基于严重程度对COVID-19患者进行排名的系统。
{"title":"Hospitalization Priority of COVID-19 Patients using Machine Learning","authors":"Labdhi Jain, K. Gala, Dhruv Doshi","doi":"10.1109/ACCESS51619.2021.9563290","DOIUrl":"https://doi.org/10.1109/ACCESS51619.2021.9563290","url":null,"abstract":"With each new wave of COVID-19, the number of patients requiring hospital beds increases, and as we have observed from our previous experiences, a lot of people have lost lives because of the unavailability of hospital beds at the right time. Hence this paper aims to resolve such a situation by the prioritization of patients using machine learning algorithms. Prioritization of patients at a hospital is the process of ordering or ranking patients based on various factors, to make a fair decision about which patient is in utmost need of care. This paper studies the different algorithms like Decision Tree Classifier, Naive Bayes and KNeighbors Classifier with which such a system could be made to predict the severity of patients and finally proposes a fair and efficient system to rank COVID-19 patients based on their severity.","PeriodicalId":409648,"journal":{"name":"2021 2nd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131876424","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 : 2021-09-02DOI: 10.1109/ACCESS51619.2021.9563281
Kashish Wattal, S. Singh
The rising air pollution levels in a country are a matter of grave concern. For the development of measures to tackle air pollution, the forecasting of air pollutant levels becomes extremely important. Easier implementation of deep learning techniques in recent years has made the development of accurate forecasting techniques straightforward. In this paper, a multivariate forecasting framework is proposed to accurately predict various air pollutant levels in Indonesia. The pollutants include Particulate Matter 10 (PM 10), Carbon Monoxide (CO), Ground level Ozone (O3) and Nitric Dioxide (NO2). For each pollutant, a number of deep learning models have been separately trained and tested. The deep learning models include Multi Layer Perceptron (MLP), Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTM) networks. The model with the lowest errors on test data can be concluded as the most accurate on that pollutant and hence can be used for reliable future prediction.
{"title":"Multivariate Air Pollution Levels Forecasting","authors":"Kashish Wattal, S. Singh","doi":"10.1109/ACCESS51619.2021.9563281","DOIUrl":"https://doi.org/10.1109/ACCESS51619.2021.9563281","url":null,"abstract":"The rising air pollution levels in a country are a matter of grave concern. For the development of measures to tackle air pollution, the forecasting of air pollutant levels becomes extremely important. Easier implementation of deep learning techniques in recent years has made the development of accurate forecasting techniques straightforward. In this paper, a multivariate forecasting framework is proposed to accurately predict various air pollutant levels in Indonesia. The pollutants include Particulate Matter 10 (PM 10), Carbon Monoxide (CO), Ground level Ozone (O3) and Nitric Dioxide (NO2). For each pollutant, a number of deep learning models have been separately trained and tested. The deep learning models include Multi Layer Perceptron (MLP), Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTM) networks. The model with the lowest errors on test data can be concluded as the most accurate on that pollutant and hence can be used for reliable future prediction.","PeriodicalId":409648,"journal":{"name":"2021 2nd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115312822","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：