Pub Date : 2022-05-06DOI: 10.1109/PCEMS55161.2022.9808014
Khurshed Fitter, S. Sinha
Photoacoustic imaging has proved itself as a swiftly emerging hybrid imaging technique that can be employed for studying soft tissues. A major challenge in the field of photoacoustic imaging is to reduce the time and computational complexity, associated with image reconstruction while maintaining the quality of the reconstructed PA images. Traditionally, reconstruction has been tackled using several backpropagation approaches. However, these approaches are limited by factors like computational and memory overheads. Further, they often require a large number of PA acquisitions for achieving acceptable accuracy. Acoustic lens-based Photoacoustic imaging system attempts to mitigate these issues by developing a lens-based reconstruction strategy that creates a high-quality image of the Photoacoustic source on the sensor. This strategy eradicates the need for computationally exhaustive post-processing steps and hence can be deployed in real-time environments. Although researchers primarily focused their attention on developing and studying mathematical models for point source systems in photoacoustic lensing, complex source geometries are usually encountered in actual real-life Photoacoustic imaging. Thin cylindrical geometries are an important aspect of employing photoacoustic imaging to study blood vessels. We present an analytical framework for the impulse response of a photoacoustic lensing system and extend the same towards incorporating infinitesimally thick cylindrical sources or extended line sources. We verify our analytical solutions numerically.
{"title":"Development of analytical solution for Photoacoustic Imaging of an Extended line source with acoustic lens based reconstruction strategy","authors":"Khurshed Fitter, S. Sinha","doi":"10.1109/PCEMS55161.2022.9808014","DOIUrl":"https://doi.org/10.1109/PCEMS55161.2022.9808014","url":null,"abstract":"Photoacoustic imaging has proved itself as a swiftly emerging hybrid imaging technique that can be employed for studying soft tissues. A major challenge in the field of photoacoustic imaging is to reduce the time and computational complexity, associated with image reconstruction while maintaining the quality of the reconstructed PA images. Traditionally, reconstruction has been tackled using several backpropagation approaches. However, these approaches are limited by factors like computational and memory overheads. Further, they often require a large number of PA acquisitions for achieving acceptable accuracy. Acoustic lens-based Photoacoustic imaging system attempts to mitigate these issues by developing a lens-based reconstruction strategy that creates a high-quality image of the Photoacoustic source on the sensor. This strategy eradicates the need for computationally exhaustive post-processing steps and hence can be deployed in real-time environments. Although researchers primarily focused their attention on developing and studying mathematical models for point source systems in photoacoustic lensing, complex source geometries are usually encountered in actual real-life Photoacoustic imaging. Thin cylindrical geometries are an important aspect of employing photoacoustic imaging to study blood vessels. We present an analytical framework for the impulse response of a photoacoustic lensing system and extend the same towards incorporating infinitesimally thick cylindrical sources or extended line sources. We verify our analytical solutions numerically.","PeriodicalId":248874,"journal":{"name":"2022 1st International Conference on the Paradigm Shifts in Communication, Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129685028","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 : 2022-05-06DOI: 10.1109/PCEMS55161.2022.9807932
Aditya Roy, S. Mukhopadhyay, Sahadev Roy
As the technologies in different fields are developing rapidly to improve society for the betterment of human life, more and more environmental problems are arising. Water is one of the most crucial elements for human life to sustain on this planet. So to monitor the coantinuous supply of filtered and purified water is becoming more important nowadays. Now, most of the monitoring systems that are present today are not automated and also equipped with the same repeated process and also very time-consuming. In this proposed work we present a water quality monitoring system that will be consists of various spring water quality measuring sensors, microcontroller for processing gathered data and various communication systems for node communication with the cloud server. To access the gathered data from remote places various monitoring system and the Internet of Things (IoT) is implicated in the system. And to display spring water quality data in an interactive form on the user side, a separate cloud server can be used and a unique IP address can be provided so a user can access the collected data. Also, the gathered values will be compared with standard values and if the values are above the set-threshold value, an automated warning SMS alert will be sent to the user. The uniqueness of the proposed system is modularity, low power consumption, and low propagation delay.
{"title":"IoT Based Real-Time Spring Water Quality Monitoring System","authors":"Aditya Roy, S. Mukhopadhyay, Sahadev Roy","doi":"10.1109/PCEMS55161.2022.9807932","DOIUrl":"https://doi.org/10.1109/PCEMS55161.2022.9807932","url":null,"abstract":"As the technologies in different fields are developing rapidly to improve society for the betterment of human life, more and more environmental problems are arising. Water is one of the most crucial elements for human life to sustain on this planet. So to monitor the coantinuous supply of filtered and purified water is becoming more important nowadays. Now, most of the monitoring systems that are present today are not automated and also equipped with the same repeated process and also very time-consuming. In this proposed work we present a water quality monitoring system that will be consists of various spring water quality measuring sensors, microcontroller for processing gathered data and various communication systems for node communication with the cloud server. To access the gathered data from remote places various monitoring system and the Internet of Things (IoT) is implicated in the system. And to display spring water quality data in an interactive form on the user side, a separate cloud server can be used and a unique IP address can be provided so a user can access the collected data. Also, the gathered values will be compared with standard values and if the values are above the set-threshold value, an automated warning SMS alert will be sent to the user. The uniqueness of the proposed system is modularity, low power consumption, and low propagation delay.","PeriodicalId":248874,"journal":{"name":"2022 1st International Conference on the Paradigm Shifts in Communication, Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126060644","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 : 2022-05-06DOI: 10.1109/PCEMS55161.2022.9808085
S. Dhonde, Jayesh Mirani, Sunit Patwardhan, K. Bhurchandi
With the swift expansion of the global economy, cities in various nations may face day to day problems like road congestion, frequent accidents, deterioration of the traffic conditions, or other urban traffic concerns. Vehicle detection technology based on video can collect a wealth of information from video frame sequences, such as vehicle speed, vehicle type, and vehicle number plate, at a cheap cost and with great efficiency. These electronic technologies are not only useful in people’s daily lives, but they also provide management with safe and efficient services. If we solely rely on human resources, such as law enforcement officers, we may face numerous issues, including high costs and low efficiency. We have built an integrated system for speed and license plate detection of vehicles. In the method presented here, the vehicle is first segmented and extracted from a video feed, using YOLOv5 algorithm. Next, the speed of the car is calculated using a simple algorithm and then the license plate snapshots are detected. Finally, optical character recognition is applied on the license plate image. This paper presents a thorough analysis of the cutting-edge approaches for detecting and recognising vehicles, their speeds and number plates.
{"title":"Over-Speed and License Plate Detection of Vehicles","authors":"S. Dhonde, Jayesh Mirani, Sunit Patwardhan, K. Bhurchandi","doi":"10.1109/PCEMS55161.2022.9808085","DOIUrl":"https://doi.org/10.1109/PCEMS55161.2022.9808085","url":null,"abstract":"With the swift expansion of the global economy, cities in various nations may face day to day problems like road congestion, frequent accidents, deterioration of the traffic conditions, or other urban traffic concerns. Vehicle detection technology based on video can collect a wealth of information from video frame sequences, such as vehicle speed, vehicle type, and vehicle number plate, at a cheap cost and with great efficiency. These electronic technologies are not only useful in people’s daily lives, but they also provide management with safe and efficient services. If we solely rely on human resources, such as law enforcement officers, we may face numerous issues, including high costs and low efficiency. We have built an integrated system for speed and license plate detection of vehicles. In the method presented here, the vehicle is first segmented and extracted from a video feed, using YOLOv5 algorithm. Next, the speed of the car is calculated using a simple algorithm and then the license plate snapshots are detected. Finally, optical character recognition is applied on the license plate image. This paper presents a thorough analysis of the cutting-edge approaches for detecting and recognising vehicles, their speeds and number plates.","PeriodicalId":248874,"journal":{"name":"2022 1st International Conference on the Paradigm Shifts in Communication, Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127517306","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 : 2022-05-06DOI: 10.1109/PCEMS55161.2022.9807915
Nilakshi Rekhawar, Yogesh Govindani, Neeraj Rao
Mobile robots can move around in the surrounding. They are used in military, industrial applications, for surveillance tasks, etc. These tasks involve multi-floor navigation through the staircase. For efficient and safe stair climbing, it is necessary for the robot to align itself with the staircase. This paper presents a deep learning based approach for staircase detection, semantic segmentation of stair edges and vision based techniques with statistical operations for pose estimation of the staircase. The objective is to solve the problem of staircase traversing for mobile robots without any prior knowledge of the stair geometry and location by iteratively calculating the pose of the staircase from the robot’s point of view till it gets aligned with the staircase. The experimental results of staircase detection, semantic segmentation and pose estimation algorithms are presented further in the paper.
{"title":"Deep Learning based Detection, Segmentation and Vision based Pose Estimation of Staircase","authors":"Nilakshi Rekhawar, Yogesh Govindani, Neeraj Rao","doi":"10.1109/PCEMS55161.2022.9807915","DOIUrl":"https://doi.org/10.1109/PCEMS55161.2022.9807915","url":null,"abstract":"Mobile robots can move around in the surrounding. They are used in military, industrial applications, for surveillance tasks, etc. These tasks involve multi-floor navigation through the staircase. For efficient and safe stair climbing, it is necessary for the robot to align itself with the staircase. This paper presents a deep learning based approach for staircase detection, semantic segmentation of stair edges and vision based techniques with statistical operations for pose estimation of the staircase. The objective is to solve the problem of staircase traversing for mobile robots without any prior knowledge of the stair geometry and location by iteratively calculating the pose of the staircase from the robot’s point of view till it gets aligned with the staircase. The experimental results of staircase detection, semantic segmentation and pose estimation algorithms are presented further in the paper.","PeriodicalId":248874,"journal":{"name":"2022 1st International Conference on the Paradigm Shifts in Communication, Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128846751","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 : 2022-05-06DOI: 10.1109/PCEMS55161.2022.9807927
Mandeep Malik, Ashwin Kothari, R. Pandhare
5G communication networks are under promulgation globally and in India the same will be deployed by second quarter of 2022. 5G networks provide much needed flexibility non monolithic architecture for implementation of various services through core network. 5G follows independent and autonomous architecture in core network and thus provide means for creation of multiple logical networks on the same physical infrastructure called as Network Slicing. Multiple slices of the same network are available by means of virtualization and network orchestration by means of network slicing which segments the traffic flow as per user customization. This can also be used for creation of private exclusive network with customized services and features. Militaries across the globe have been using their self-deployed hardware and software which are exclusive and isolated from public networks for deployment of isolated military networks akin to commercial telecommunication networks. Though military networks emerge out of technologies used in public switched networks but since they require secrecy and isolation thus remain aloof from public networks and over a period also get outdated, since a large infrastructure has to be created for deployment of networks which also requires huge capital thus these networks are not upgraded periodically as in case of civil networks. Network slicing function of 5G provides means of using the public telecom networks with exclusivity and secrecy without deployment of infrastructure and still maintain the required isolation. An exclusive military network slice on telecommunication service providers (TSPs) infrastructure will enable economy of use, low cost of ownership and customized services with increased network security or propriety security algorithms as per requirement of Army.
{"title":"Network Slicing In 5g: Possible Military Exclusive Slice","authors":"Mandeep Malik, Ashwin Kothari, R. Pandhare","doi":"10.1109/PCEMS55161.2022.9807927","DOIUrl":"https://doi.org/10.1109/PCEMS55161.2022.9807927","url":null,"abstract":"5G communication networks are under promulgation globally and in India the same will be deployed by second quarter of 2022. 5G networks provide much needed flexibility non monolithic architecture for implementation of various services through core network. 5G follows independent and autonomous architecture in core network and thus provide means for creation of multiple logical networks on the same physical infrastructure called as Network Slicing. Multiple slices of the same network are available by means of virtualization and network orchestration by means of network slicing which segments the traffic flow as per user customization. This can also be used for creation of private exclusive network with customized services and features. Militaries across the globe have been using their self-deployed hardware and software which are exclusive and isolated from public networks for deployment of isolated military networks akin to commercial telecommunication networks. Though military networks emerge out of technologies used in public switched networks but since they require secrecy and isolation thus remain aloof from public networks and over a period also get outdated, since a large infrastructure has to be created for deployment of networks which also requires huge capital thus these networks are not upgraded periodically as in case of civil networks. Network slicing function of 5G provides means of using the public telecom networks with exclusivity and secrecy without deployment of infrastructure and still maintain the required isolation. An exclusive military network slice on telecommunication service providers (TSPs) infrastructure will enable economy of use, low cost of ownership and customized services with increased network security or propriety security algorithms as per requirement of Army.","PeriodicalId":248874,"journal":{"name":"2022 1st International Conference on the Paradigm Shifts in Communication, Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124953795","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 : 2022-05-06DOI: 10.1109/PCEMS55161.2022.9808049
Nikhil B. Gaikwad, S. K. Khare, Nitin Satpute, A. Keskar
Fog computing is a key solution for internet of things (IoT) applications, which demands operational security, real-time and power efficient intelligent responses, and low bandwidth usage. This paper introduces a novel idea related to an hardware implementation of High-performance classifiers for real-time and low power sensor data analytic on the intelligent edge gateway running on smart automobile. The high-performance classifiers uses an artificial neural network (ANN) to extract conclusive inferences from the raw automotive sensors information. The multiple classifiers are embedded into a re-configurable ANN hardware deign i.e. intellectual property core (IP core) which implemented and tested using field-programmable gate array fabric. In addition, this work studies the effect of the IP cores on the performance of the edge gateway. The implementation of fog/edge computing enables throughput reduction of 96.78% to 98.75% compared with the traditional gateway. The hardware design of the high-performance classifiers IP core requires only 31μ s and power consumption of 124mW for classification. The concept of re-configurable ANN model reduce about 41% to 93% of hardware resources requirement that contributing to reduced system power and cost.
{"title":"Hardware Implementation of High-performance Classifiers for Edge Gateway of Smart Automobile","authors":"Nikhil B. Gaikwad, S. K. Khare, Nitin Satpute, A. Keskar","doi":"10.1109/PCEMS55161.2022.9808049","DOIUrl":"https://doi.org/10.1109/PCEMS55161.2022.9808049","url":null,"abstract":"Fog computing is a key solution for internet of things (IoT) applications, which demands operational security, real-time and power efficient intelligent responses, and low bandwidth usage. This paper introduces a novel idea related to an hardware implementation of High-performance classifiers for real-time and low power sensor data analytic on the intelligent edge gateway running on smart automobile. The high-performance classifiers uses an artificial neural network (ANN) to extract conclusive inferences from the raw automotive sensors information. The multiple classifiers are embedded into a re-configurable ANN hardware deign i.e. intellectual property core (IP core) which implemented and tested using field-programmable gate array fabric. In addition, this work studies the effect of the IP cores on the performance of the edge gateway. The implementation of fog/edge computing enables throughput reduction of 96.78% to 98.75% compared with the traditional gateway. The hardware design of the high-performance classifiers IP core requires only 31μ s and power consumption of 124mW for classification. The concept of re-configurable ANN model reduce about 41% to 93% of hardware resources requirement that contributing to reduced system power and cost.","PeriodicalId":248874,"journal":{"name":"2022 1st International Conference on the Paradigm Shifts in Communication, Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125350234","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：