Pub Date : 2022-02-12DOI: 10.1109/AISP53593.2022.9760517
Kiran Chand Ravi, V. Slyusar, J. Kumar
5G communication systems ensure high data rate, low latency, network reliability, and energy efficiency and high throughput that require new and very efficient antenna designs. In this paper, we proposed a simple and very effective antenna with centre frequency 28GHz designed on an RF4 substrate of 1. 6mm thickness. The performance characteristics of the antenna-like reflection coefficient (Sll), voltage standing wave ratio (VSWR), radiation pattern and impedance have been investigated using HFSS. optimization techniques are applied to achieve significant results. A defective ground structure was chosen for obtaining proper impedance matching. The simulated results are satisfactory and the proposed antenna is a good candidate to operate in the millimetre wave frequency band that is 28GHz range for 5G application.
{"title":"SRR Loaded Wideband Antenna 5G Application","authors":"Kiran Chand Ravi, V. Slyusar, J. Kumar","doi":"10.1109/AISP53593.2022.9760517","DOIUrl":"https://doi.org/10.1109/AISP53593.2022.9760517","url":null,"abstract":"5G communication systems ensure high data rate, low latency, network reliability, and energy efficiency and high throughput that require new and very efficient antenna designs. In this paper, we proposed a simple and very effective antenna with centre frequency 28GHz designed on an RF4 substrate of 1. 6mm thickness. The performance characteristics of the antenna-like reflection coefficient (Sll), voltage standing wave ratio (VSWR), radiation pattern and impedance have been investigated using HFSS. optimization techniques are applied to achieve significant results. A defective ground structure was chosen for obtaining proper impedance matching. The simulated results are satisfactory and the proposed antenna is a good candidate to operate in the millimetre wave frequency band that is 28GHz range for 5G application.","PeriodicalId":6793,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","volume":"49 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86012811","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 : 2022-02-12DOI: 10.1109/AISP53593.2022.9760674
V. Cp, S. Kalaivanan, R. Karthik, A. Sanjana
Due to the quick increase of IoT devices, they lack the authentication standards and administration needed to keep user data secure. Hackers could cause significant infrastructure harm by infiltrating a wide spectrum of IoT devices. Blockchain use in IoT technology guarantees trust and authentication across all IoT elements, resulting in IoT security. Blockchain is a decentralized, distributed, and shared database that enables the creation of decentralized apps. Traceability, openness, immutability, and fault tolerance are some of the qualities of this technology that help maintain data privacy in IoT scenarios and thus create a safe environment. We look at a potential strategy for securely controlling IoT devices,i.e., devices connected to the internet using smart contracts on the blockchain in this study. This paper demonstrates how the proposed system comprising of a blockchain and smart contracts work efficiently in concurrence to avoid tampering by unauthorized parties. We have employed web3 library to control the linked devices by implementing Ethereum nodes (second most popular blockchain) on Raspberry Pi simulations and node.js.
{"title":"Blockchain-based IoT Device Security","authors":"V. Cp, S. Kalaivanan, R. Karthik, A. Sanjana","doi":"10.1109/AISP53593.2022.9760674","DOIUrl":"https://doi.org/10.1109/AISP53593.2022.9760674","url":null,"abstract":"Due to the quick increase of IoT devices, they lack the authentication standards and administration needed to keep user data secure. Hackers could cause significant infrastructure harm by infiltrating a wide spectrum of IoT devices. Blockchain use in IoT technology guarantees trust and authentication across all IoT elements, resulting in IoT security. Blockchain is a decentralized, distributed, and shared database that enables the creation of decentralized apps. Traceability, openness, immutability, and fault tolerance are some of the qualities of this technology that help maintain data privacy in IoT scenarios and thus create a safe environment. We look at a potential strategy for securely controlling IoT devices,i.e., devices connected to the internet using smart contracts on the blockchain in this study. This paper demonstrates how the proposed system comprising of a blockchain and smart contracts work efficiently in concurrence to avoid tampering by unauthorized parties. We have employed web3 library to control the linked devices by implementing Ethereum nodes (second most popular blockchain) on Raspberry Pi simulations and node.js.","PeriodicalId":6793,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","volume":"37 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73187454","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 : 2022-02-12DOI: 10.1109/AISP53593.2022.9760652
N. Kumar, Nidhi Gupta
Emotion recognition is the process to study about the emotions in a human being. This is a research field where one can understand and recognize the feelings of human and ability of expression which varies from each other at great extent. Several methods have been developed to study emotions such as facial expression, speech method, textual method and EEG signal. In this study work, we have reviewed several methods to find an efficiency of emotions up to accurate observations. Several papers on emotion recognition from the year 2007 to 2021 are been explored in this paper to observe the accuracy 95.20% using electroencephalogram (EEG) signal and 95% using EEG signals with statistical features and neural network. The average accuracy ranges in between 63% to 73% using EEG signal and facial expressions, both.
{"title":"A Comprehensive Study on Machine Learning Approaches for Emotion Recognition","authors":"N. Kumar, Nidhi Gupta","doi":"10.1109/AISP53593.2022.9760652","DOIUrl":"https://doi.org/10.1109/AISP53593.2022.9760652","url":null,"abstract":"Emotion recognition is the process to study about the emotions in a human being. This is a research field where one can understand and recognize the feelings of human and ability of expression which varies from each other at great extent. Several methods have been developed to study emotions such as facial expression, speech method, textual method and EEG signal. In this study work, we have reviewed several methods to find an efficiency of emotions up to accurate observations. Several papers on emotion recognition from the year 2007 to 2021 are been explored in this paper to observe the accuracy 95.20% using electroencephalogram (EEG) signal and 95% using EEG signals with statistical features and neural network. The average accuracy ranges in between 63% to 73% using EEG signal and facial expressions, both.","PeriodicalId":6793,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","volume":"33 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77238237","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 : 2022-02-12DOI: 10.1109/AISP53593.2022.9760559
Kaustubha H. Shedbalkar, D. More
The solar power forecasting is important factor that provides support to planning terms of power distribution organizations. The time based forecasting is feasible due to dependable outcome of solar power generation on weather status. The weather status itself is prediction method involving approach which is becoming considerably accurate these days. The power generation outcome is the multiple parameter regression model. This paper shows the experimental outcome of solar power generation forecasting with linear, ridge and Bayesian regression models. The best performing Bayesian model is compared with other existing methods in which Bayesian model outperforms in terms of mean square error for 15 minutes time interval data in batch processing approach.
{"title":"Bayesian Regression for Solar Power Forecasting","authors":"Kaustubha H. Shedbalkar, D. More","doi":"10.1109/AISP53593.2022.9760559","DOIUrl":"https://doi.org/10.1109/AISP53593.2022.9760559","url":null,"abstract":"The solar power forecasting is important factor that provides support to planning terms of power distribution organizations. The time based forecasting is feasible due to dependable outcome of solar power generation on weather status. The weather status itself is prediction method involving approach which is becoming considerably accurate these days. The power generation outcome is the multiple parameter regression model. This paper shows the experimental outcome of solar power generation forecasting with linear, ridge and Bayesian regression models. The best performing Bayesian model is compared with other existing methods in which Bayesian model outperforms in terms of mean square error for 15 minutes time interval data in batch processing approach.","PeriodicalId":6793,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","volume":"122 4 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75176514","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 : 2022-02-12DOI: 10.1109/AISP53593.2022.9760667
Ch Madhurya, Ajith Jubilson E, Goutham N
In last quarter of 2019, Corona Virus Disease (COVID-19), has flared up globally due to which many organizations and institutions are suffering and practically they are going to be closed if the current scenario does not change. COVID-19 is an transmissible disease causes due to Serious Acute Respiratory Syndrome Corona Virus-2 (SARS-CoV-2), which spreads from small liquid particles released from mouth or nose of an infected person. With this virus, anyone can get sick and become seriously ill or even die at any age. The best way to protect our self and others is by wearing a properly fitted facemask, washing hands regularly or frequently rubbing your hands by using an alcohol-based sanitizer and the way is to get vaccinated when ones turn comes. The proposed study uses Convolutional Neural Networks (CNNs) which is a technique of deep learning is used for classification by processing images. This study uses deep learning techniques for identifying if the person is with proper facemask or with no facemask from live video streams. For training the model the dataset is collected kaggle repository which contains 2000 images and attained an accuracy of 98.2% while training the model. The created system is put into action with the help of openCV, python and mobileV2 architecture v2 for recognizing the persons who are wearing and not wearing the facemasks.
{"title":"Facemask Detection using Convolutional Neural Networks (CNN)","authors":"Ch Madhurya, Ajith Jubilson E, Goutham N","doi":"10.1109/AISP53593.2022.9760667","DOIUrl":"https://doi.org/10.1109/AISP53593.2022.9760667","url":null,"abstract":"In last quarter of 2019, Corona Virus Disease (COVID-19), has flared up globally due to which many organizations and institutions are suffering and practically they are going to be closed if the current scenario does not change. COVID-19 is an transmissible disease causes due to Serious Acute Respiratory Syndrome Corona Virus-2 (SARS-CoV-2), which spreads from small liquid particles released from mouth or nose of an infected person. With this virus, anyone can get sick and become seriously ill or even die at any age. The best way to protect our self and others is by wearing a properly fitted facemask, washing hands regularly or frequently rubbing your hands by using an alcohol-based sanitizer and the way is to get vaccinated when ones turn comes. The proposed study uses Convolutional Neural Networks (CNNs) which is a technique of deep learning is used for classification by processing images. This study uses deep learning techniques for identifying if the person is with proper facemask or with no facemask from live video streams. For training the model the dataset is collected kaggle repository which contains 2000 images and attained an accuracy of 98.2% while training the model. The created system is put into action with the help of openCV, python and mobileV2 architecture v2 for recognizing the persons who are wearing and not wearing the facemasks.","PeriodicalId":6793,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","volume":"31 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80504470","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 : 2022-02-12DOI: 10.1109/AISP53593.2022.9760527
S. Sriraman, R. Manjunathan, Nethraa Sivakumar, S. Pooja, Nikhil Viswanath
In this paper, we analyze the performance of graph convolutional networks (GCNs) in predicting COVID-19 incidence in states and union territories (UTs) in India as a semisupervised learning task. By training the model with data from a small number of states whose incidence is known, we analyze the accuracy in predicting incidence levels in the remaining states and UTs in India. We explore the effect of pre-existing factors such as foreign visitor count, senior citizen population and population density of states in predicting spread. To show the robustness of this model, we introduce a novel method to choose states for training that reduces bias through random sampling in five regions that cover India’s geography. We show that GCNs, on average, produce a 9% improvement in accuracy over the best performing non-graph-based model and discuss if the results are feasible for use in a real-world scenario.
{"title":"Graph Convolutional Networks for Predicting State-wise Pandemic Incidence in India","authors":"S. Sriraman, R. Manjunathan, Nethraa Sivakumar, S. Pooja, Nikhil Viswanath","doi":"10.1109/AISP53593.2022.9760527","DOIUrl":"https://doi.org/10.1109/AISP53593.2022.9760527","url":null,"abstract":"In this paper, we analyze the performance of graph convolutional networks (GCNs) in predicting COVID-19 incidence in states and union territories (UTs) in India as a semisupervised learning task. By training the model with data from a small number of states whose incidence is known, we analyze the accuracy in predicting incidence levels in the remaining states and UTs in India. We explore the effect of pre-existing factors such as foreign visitor count, senior citizen population and population density of states in predicting spread. To show the robustness of this model, we introduce a novel method to choose states for training that reduces bias through random sampling in five regions that cover India’s geography. We show that GCNs, on average, produce a 9% improvement in accuracy over the best performing non-graph-based model and discuss if the results are feasible for use in a real-world scenario.","PeriodicalId":6793,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","volume":"44 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82881861","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 : 2022-02-12DOI: 10.1109/AISP53593.2022.9760640
P. Vaidya, S. Chauhan, V. Jaiswal
The drug-like molecule which could treat multiple diseases is commercially more viable and can act on multiple biological pathways. Such drug candidates can also be more important in the treatment of complex diseases like cancer. Traditional methods are not focused on the development of such drugs, but computational method can be developed to predict multiple disease potential of drug-like molecules. Computational methods have been extremely successful in drug discovery through prediction of drug potential of the drug-like molecules such as toxicity, physiological effects, binding energy and binding pose with the receptor. Computational methods to predict multiple disease potential of the drug-like molecules are not worked out so far in spite of the high importance of such drugs and it can also expedite the drug repurposing. Hence, information of approved drugs used for the treatment of single and multiple diseases was included to develop the machine learning-based model for the prediction of multiple disease potential of the drug-like molecules. Molecular descriptors were used as the features and optimally selected for support vector machine-based prediction models. The fairly high accuracy of developed method justifies the importance of selected method and approach. The developed method is expected to expedite the drug discovery process through the prediction of multi-drug potential of drug-like molecules.
{"title":"Prediction of Multi Class Drugs: A Perspective for Designing Drug with Many Uses","authors":"P. Vaidya, S. Chauhan, V. Jaiswal","doi":"10.1109/AISP53593.2022.9760640","DOIUrl":"https://doi.org/10.1109/AISP53593.2022.9760640","url":null,"abstract":"The drug-like molecule which could treat multiple diseases is commercially more viable and can act on multiple biological pathways. Such drug candidates can also be more important in the treatment of complex diseases like cancer. Traditional methods are not focused on the development of such drugs, but computational method can be developed to predict multiple disease potential of drug-like molecules. Computational methods have been extremely successful in drug discovery through prediction of drug potential of the drug-like molecules such as toxicity, physiological effects, binding energy and binding pose with the receptor. Computational methods to predict multiple disease potential of the drug-like molecules are not worked out so far in spite of the high importance of such drugs and it can also expedite the drug repurposing. Hence, information of approved drugs used for the treatment of single and multiple diseases was included to develop the machine learning-based model for the prediction of multiple disease potential of the drug-like molecules. Molecular descriptors were used as the features and optimally selected for support vector machine-based prediction models. The fairly high accuracy of developed method justifies the importance of selected method and approach. The developed method is expected to expedite the drug discovery process through the prediction of multi-drug potential of drug-like molecules.","PeriodicalId":6793,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","volume":"85 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82356600","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 : 2022-02-12DOI: 10.1109/AISP53593.2022.9760529
Naga Chandrika Gandikota, Gurumurthy Komanapalli
In this paper, a second order sinusoidal oscillator (SO) has been presented using Current Feedback Operational Amplifiers (CFOA) as active element. It uses five resistors and two capacitors. It exhibits complete independent tuning between frequency of oscillation and condition of oscillation through resistors. The sensitivity analysis has been carried out and it is observed that it exhibits low FO sensitivity to various circuit parameters. PSPICE simulations are used to check the efficacy of the proposed circuit and the simulation results are in close proximity with theoretical calculations. The observed total harmonic distortion (THD) is lower than 2.5%.
{"title":"CFOA Based Second Order Low Frequency Sensitive Sinusoidal Oscillator","authors":"Naga Chandrika Gandikota, Gurumurthy Komanapalli","doi":"10.1109/AISP53593.2022.9760529","DOIUrl":"https://doi.org/10.1109/AISP53593.2022.9760529","url":null,"abstract":"In this paper, a second order sinusoidal oscillator (SO) has been presented using Current Feedback Operational Amplifiers (CFOA) as active element. It uses five resistors and two capacitors. It exhibits complete independent tuning between frequency of oscillation and condition of oscillation through resistors. The sensitivity analysis has been carried out and it is observed that it exhibits low FO sensitivity to various circuit parameters. PSPICE simulations are used to check the efficacy of the proposed circuit and the simulation results are in close proximity with theoretical calculations. The observed total harmonic distortion (THD) is lower than 2.5%.","PeriodicalId":6793,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","volume":"16 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87867518","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}
This paper proposes a speech enhancement method for non-stationary Gaussian noise based on regularized non-negative matrix factorization (NMF). The magnitudes of speech and noise are implemented by a model based in iterative posterior NMF which are applied using prior distributions in transform domain. This is used since the sample distributions of the above are well suited to Weibull and Rayleigh densities well. For the accomplishment in time-varying noise environments, both the speech and noise bases of NMF are adapted simultaneously. With the usage of estimated speech presence probability, this paper proposes to adaptively estimate the statistics of these distributions. The method in this paper gives the best results for perceptual evaluation of speech quality (PESQ) and the signal-to-distortion ratio (SDR).
{"title":"Weibull Prior based Single Channel Speech Enhancement using Iterative Posterior NMF","authors":"S. Vanambathina, Vaishnavi Anumola, Ponnapalli Tejasree, Nandeesh Kumar, Rama Prakash Reddy Ch","doi":"10.1109/AISP53593.2022.9760648","DOIUrl":"https://doi.org/10.1109/AISP53593.2022.9760648","url":null,"abstract":"This paper proposes a speech enhancement method for non-stationary Gaussian noise based on regularized non-negative matrix factorization (NMF). The magnitudes of speech and noise are implemented by a model based in iterative posterior NMF which are applied using prior distributions in transform domain. This is used since the sample distributions of the above are well suited to Weibull and Rayleigh densities well. For the accomplishment in time-varying noise environments, both the speech and noise bases of NMF are adapted simultaneously. With the usage of estimated speech presence probability, this paper proposes to adaptively estimate the statistics of these distributions. The method in this paper gives the best results for perceptual evaluation of speech quality (PESQ) and the signal-to-distortion ratio (SDR).","PeriodicalId":6793,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","volume":"17 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86892737","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 : 2022-02-12DOI: 10.1109/AISP53593.2022.9760604
Samarpita Hatua, D. Ray, Sahadeb Shit, D. Das, Sayanti Hazra
Industry 4.0 offers a radical transformation to increase cost-effective, flexible, and efficient production of higher-quality fully automated systems by collecting and analyzing data across machines. From the last few decades, power industry has started to focus on real-time systems instead of using static methodology in periodical boiler inspection. The power plant undergoes sudden break down due to cracks and foreign bodies causing huge economic loss to the plant as well as the country. To avoid such unforeseen breakdown, most of the power plants has adopted inspection and monitoring system as a regular solution. Visual inspection is one of the most popular techniques for such inspections using a tiny camera with high-power LEDs (Known as Borescope). But it has several limitations for circumferential (360°) and longitudinal (2000mm) coverage and also equidistance inspection from the center of the header is not possible using a conventional Borescope. A specific Digital Video Recorder (DVR) used for the inspection and monitoring is not sufficient to resolve multipurpose requirements such as position of the foreign body and crack, feature of magnification, and more important is data log including plant information and crack details with images. A real-time inspection module has been developed integrated with robotic (AI) based on computer vision to make the inspection dynamic and fully automated.
{"title":"Development of an Inspection Software towards Detection and Location of Cracks and Foreign Objects in Boiler header or Pipes","authors":"Samarpita Hatua, D. Ray, Sahadeb Shit, D. Das, Sayanti Hazra","doi":"10.1109/AISP53593.2022.9760604","DOIUrl":"https://doi.org/10.1109/AISP53593.2022.9760604","url":null,"abstract":"Industry 4.0 offers a radical transformation to increase cost-effective, flexible, and efficient production of higher-quality fully automated systems by collecting and analyzing data across machines. From the last few decades, power industry has started to focus on real-time systems instead of using static methodology in periodical boiler inspection. The power plant undergoes sudden break down due to cracks and foreign bodies causing huge economic loss to the plant as well as the country. To avoid such unforeseen breakdown, most of the power plants has adopted inspection and monitoring system as a regular solution. Visual inspection is one of the most popular techniques for such inspections using a tiny camera with high-power LEDs (Known as Borescope). But it has several limitations for circumferential (360°) and longitudinal (2000mm) coverage and also equidistance inspection from the center of the header is not possible using a conventional Borescope. A specific Digital Video Recorder (DVR) used for the inspection and monitoring is not sufficient to resolve multipurpose requirements such as position of the foreign body and crack, feature of magnification, and more important is data log including plant information and crack details with images. A real-time inspection module has been developed integrated with robotic (AI) based on computer vision to make the inspection dynamic and fully automated.","PeriodicalId":6793,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence and Signal Processing (AISP)","volume":"33 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79444570","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：