Pub Date : 2021-11-26DOI: 10.1109/iccica52458.2021.9697290
P. Chouragade, P. Ambhore
From the last few years, database of digital images has advanced substantially along with the techniques for image processing. Today, the databases of digital image are found in an increasing number, that provide useable and effective access to image collections. Image databases are becoming larger and more prevalent as a result of the Internet’s spread and the accessibility of optical imaging technologies like digital camera systems and scanning of images, necessitating the development of image retrieval methods that are more productive and useful. The research focuses on feature’s selection for extracting them in view to enhance the result of content-based image retrieval system. Identification of image features, corelating them on the basis of their effects, and the influence of these factors on retrieval are all part of this process. Low-level visual features that address more detailed perceptual components of visual data are observed along with high-level features that underpin in image retrieval techniques. As a result, the research is attempting to review these elements for improving the efficiency of CBIR search results. Further, in order to recognize the wider conceptual features of visual data, various features can be integrated with one another.
{"title":"Enhancing Content Based Image Retrieval Technique by Observing Image Feature Extraction Methods","authors":"P. Chouragade, P. Ambhore","doi":"10.1109/iccica52458.2021.9697290","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697290","url":null,"abstract":"From the last few years, database of digital images has advanced substantially along with the techniques for image processing. Today, the databases of digital image are found in an increasing number, that provide useable and effective access to image collections. Image databases are becoming larger and more prevalent as a result of the Internet’s spread and the accessibility of optical imaging technologies like digital camera systems and scanning of images, necessitating the development of image retrieval methods that are more productive and useful. The research focuses on feature’s selection for extracting them in view to enhance the result of content-based image retrieval system. Identification of image features, corelating them on the basis of their effects, and the influence of these factors on retrieval are all part of this process. Low-level visual features that address more detailed perceptual components of visual data are observed along with high-level features that underpin in image retrieval techniques. As a result, the research is attempting to review these elements for improving the efficiency of CBIR search results. Further, in order to recognize the wider conceptual features of visual data, various features can be integrated with one another.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121406733","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 : 2021-11-26DOI: 10.1109/iccica52458.2021.9697137
V. Prashanthi, Srinivas Kanakala, V. Akila, A. Harshavardhan
Music genre prediction is a difficult job in the field in Retrieval of Musical Data. Music group categorization is essential for the music recommending systems, since genre has a high weight in such systems and their recommendations. A machine learning model is designed which automatically classifies the genre of a music clip. Here, we are going to extract acoustic music features with the help of digital signal processing and then classification of music is done with the help of machine learning methods. Librosa, is a tool we will be using for audio feature extraction, which offers a full-featured work-flow situation for low and high-level audio features. In this paper, we are going to utilize k-Nearest Neighbours method for the reason that in many research it is shown that this method gives good outcomes in such scenario. We will be using music dataset GTZAN Genre Collection (1010 clips).
{"title":"Music Genre Categorization using Machine learning Algorithms","authors":"V. Prashanthi, Srinivas Kanakala, V. Akila, A. Harshavardhan","doi":"10.1109/iccica52458.2021.9697137","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697137","url":null,"abstract":"Music genre prediction is a difficult job in the field in Retrieval of Musical Data. Music group categorization is essential for the music recommending systems, since genre has a high weight in such systems and their recommendations. A machine learning model is designed which automatically classifies the genre of a music clip. Here, we are going to extract acoustic music features with the help of digital signal processing and then classification of music is done with the help of machine learning methods. Librosa, is a tool we will be using for audio feature extraction, which offers a full-featured work-flow situation for low and high-level audio features. In this paper, we are going to utilize k-Nearest Neighbours method for the reason that in many research it is shown that this method gives good outcomes in such scenario. We will be using music dataset GTZAN Genre Collection (1010 clips).","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115213825","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 : 2021-11-26DOI: 10.1109/iccica52458.2021.9697123
Mahendra Gaikwad
Network-on-chip architecture is a new paradigm shift for designing IP core based system on chip and also referred as network based communication subsystem which is recently looked as an innovative approach to provide a highly scalable, high computational and communication performance. Energy consumption of network based communication subsystems is becoming the valuable parameter in the design of system which further needs to be optimized. In the recent development of IP core architecture, it is necessary to propose new approach for design methodologies to minimize the communication energy for network based communication subsystems. We have addressed the Rectangular Perfect Difference Network topology for network based communication subsystems for providing optimum bandwidth utilization with lesser number of routing hops and at the most two hops in the communication to achieve the best energy performance. In this paper, we propose Rectangular PDN topology for network based communication subsystems for minimization of communication energy using the mathematical representation of Perfect Difference Set (PDS). We have proposed the analytical model with lower energy consumption for chordal Ring Perfect Difference Network Topology and Rectangular Perfect Difference Network Topology. The proposed analytical model for network based communication subsystems using Perfect Difference Network topology results is simulated and validated for different Network topology having order of n=7. The link energy model and router energy model are validated against simulation results for Rectangular PDN topology of network based communication subsystems. The overall average energy consumption for transfer of data through router from one IP to another IP for Rectangular PDN Topology for network n=7 for perfect difference set of {0, 1, 3} having order δ=2; is compared with overall average energy consumption for 2X2 CLICHÉ architecture
{"title":"Energy Performance of Network on Chip Architecture for Rectangular Perfect Difference Network Topology","authors":"Mahendra Gaikwad","doi":"10.1109/iccica52458.2021.9697123","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697123","url":null,"abstract":"Network-on-chip architecture is a new paradigm shift for designing IP core based system on chip and also referred as network based communication subsystem which is recently looked as an innovative approach to provide a highly scalable, high computational and communication performance. Energy consumption of network based communication subsystems is becoming the valuable parameter in the design of system which further needs to be optimized. In the recent development of IP core architecture, it is necessary to propose new approach for design methodologies to minimize the communication energy for network based communication subsystems. We have addressed the Rectangular Perfect Difference Network topology for network based communication subsystems for providing optimum bandwidth utilization with lesser number of routing hops and at the most two hops in the communication to achieve the best energy performance. In this paper, we propose Rectangular PDN topology for network based communication subsystems for minimization of communication energy using the mathematical representation of Perfect Difference Set (PDS). We have proposed the analytical model with lower energy consumption for chordal Ring Perfect Difference Network Topology and Rectangular Perfect Difference Network Topology. The proposed analytical model for network based communication subsystems using Perfect Difference Network topology results is simulated and validated for different Network topology having order of n=7. The link energy model and router energy model are validated against simulation results for Rectangular PDN topology of network based communication subsystems. The overall average energy consumption for transfer of data through router from one IP to another IP for Rectangular PDN Topology for network n=7 for perfect difference set of {0, 1, 3} having order δ=2; is compared with overall average energy consumption for 2X2 CLICHÉ architecture","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116086645","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}
Data transfer is a way to attain the goal of data monetization. While the data is being transferred, securing the records and information of users is the prime concern which needs to be taken care of. There is a strong necessity to find out a new, safe and reliable process in which information of customers should be transferred. This research paper provides a smart and secured method to transfer data from one organization to different organizations for data monetization. It focuses on achieving efficient transfer of data with the permission of the person whose credentials are getting shared, leading to economic growth of both the dealers. It also focuses on how different organizations can use data of a single organization at same time for data monetization without actually accessing the data with the help of the proposed methodology. Proposed methodology is time saving for the different organizations as insights helps to target the relevant people from the same domain.
{"title":"Smart Data Transfer For Data Monetization","authors":"Aditi Prakash Mukte, Ritesh Pravin Jaiswal, Sanket Anil Dambhare, Urvashi Agrawal, R. Agrawal","doi":"10.1109/iccica52458.2021.9697182","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697182","url":null,"abstract":"Data transfer is a way to attain the goal of data monetization. While the data is being transferred, securing the records and information of users is the prime concern which needs to be taken care of. There is a strong necessity to find out a new, safe and reliable process in which information of customers should be transferred. This research paper provides a smart and secured method to transfer data from one organization to different organizations for data monetization. It focuses on achieving efficient transfer of data with the permission of the person whose credentials are getting shared, leading to economic growth of both the dealers. It also focuses on how different organizations can use data of a single organization at same time for data monetization without actually accessing the data with the help of the proposed methodology. Proposed methodology is time saving for the different organizations as insights helps to target the relevant people from the same domain.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125698000","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 : 2021-11-26DOI: 10.1109/iccica52458.2021.9697232
Akash Kothare, Shridhara Chaube, Yash Moharir, Gaurav Bajodia, S. Dongre
Synthetic data is superficial data generated using various machine learning techniques. The respective synthetic data generated can be used to preserve privacy, test systems, or create training data for machine learning algorithms. Synthetic data generation is critical as the need for specific data is huge in today's world, for example, synthetic data can be used to practice various data science tasks and techniques, while maintaining the anonymity of the samples generated. We used an open-source engine named Faker (v5.6.1) and Gaussian copula to create a platform that can generate datasets, based on user requirements as well as available resources. The user can also perform a variety of machine learning algorithms and differentiate their performance either over the generated dataset or a predefined dataset.
{"title":"SynGen: Synthetic Data Generation","authors":"Akash Kothare, Shridhara Chaube, Yash Moharir, Gaurav Bajodia, S. Dongre","doi":"10.1109/iccica52458.2021.9697232","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697232","url":null,"abstract":"Synthetic data is superficial data generated using various machine learning techniques. The respective synthetic data generated can be used to preserve privacy, test systems, or create training data for machine learning algorithms. Synthetic data generation is critical as the need for specific data is huge in today's world, for example, synthetic data can be used to practice various data science tasks and techniques, while maintaining the anonymity of the samples generated. We used an open-source engine named Faker (v5.6.1) and Gaussian copula to create a platform that can generate datasets, based on user requirements as well as available resources. The user can also perform a variety of machine learning algorithms and differentiate their performance either over the generated dataset or a predefined dataset.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"39 14","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133007794","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 : 2021-11-26DOI: 10.1109/iccica52458.2021.9697144
D. Singh, S. Kediya, R. Mahajan, P. Asthana
The research article aims to know the role of Management Information System in Food grains (Soyabean and Tuwar) in Eastern Maharashtra. Indian Government in its market liberalization plan emphasized on the priority to the development of a market information system (MIS) which could be utilized by traders as well as to deliver frequent information by media on current market price and availability.In collaboration with NIC, the IT project department has created several vital software programs to assist farmers. This study aims at management information systems in the context of food grains (soyabean and tuwar) in Eastern Maharashtra. To ensure that the research design aligns with the research objectives, the researcher has made sure that the instruments used in the study are objective oriented such as Measure of central tendency and Z statistic. The result of the study suggests that because of technical complexity, end-users underestimate the agricultural information system's utility. Because of lack of agricultural knowledge, assistance for people information financing as a key priority in cultivation may dwindle. Farmers should have easier access to public information by increased funding for public information. More interactive information sources might persuade traditional farmers to embrace more modern farming techniques.
{"title":"Management Information System in context of Food grains: An Empirical Study at Eastern Maharashtra","authors":"D. Singh, S. Kediya, R. Mahajan, P. Asthana","doi":"10.1109/iccica52458.2021.9697144","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697144","url":null,"abstract":"The research article aims to know the role of Management Information System in Food grains (Soyabean and Tuwar) in Eastern Maharashtra. Indian Government in its market liberalization plan emphasized on the priority to the development of a market information system (MIS) which could be utilized by traders as well as to deliver frequent information by media on current market price and availability.In collaboration with NIC, the IT project department has created several vital software programs to assist farmers. This study aims at management information systems in the context of food grains (soyabean and tuwar) in Eastern Maharashtra. To ensure that the research design aligns with the research objectives, the researcher has made sure that the instruments used in the study are objective oriented such as Measure of central tendency and Z statistic. The result of the study suggests that because of technical complexity, end-users underestimate the agricultural information system's utility. Because of lack of agricultural knowledge, assistance for people information financing as a key priority in cultivation may dwindle. Farmers should have easier access to public information by increased funding for public information. More interactive information sources might persuade traditional farmers to embrace more modern farming techniques.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130523790","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 : 2021-11-26DOI: 10.1109/iccica52458.2021.9697245
Pankaj Ramtekkar, H. Naidu, Suraj Dudhe
in this paper, we are focusing on detection of fire at a location. The fire is extinguishing by Trifluoroiodomethane CF3I to abide by the Kyoto Protocol of 1997 of United Nations Convention of climate change. The transmitter side gives signal to the hooter simultaneously with visual indication showing, which unit in the factory/shop/house has caught fire. The detection of fire is accessed in terms of temperature detected through RTD placed stationary or on a moving vehicle using PIC microcontroller to scale the voltage values. Transmitting and receiving messages through a channel using open band of RF frequency 434 MHz to make it more secure. The fire is contained and extinguished by Trifluoroiodomethane CF3I gas in a container.
{"title":"A Novel Wireless Fire Containment and Extinguishing System to Save Life and Destruction of Property","authors":"Pankaj Ramtekkar, H. Naidu, Suraj Dudhe","doi":"10.1109/iccica52458.2021.9697245","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697245","url":null,"abstract":"in this paper, we are focusing on detection of fire at a location. The fire is extinguishing by Trifluoroiodomethane CF3I to abide by the Kyoto Protocol of 1997 of United Nations Convention of climate change. The transmitter side gives signal to the hooter simultaneously with visual indication showing, which unit in the factory/shop/house has caught fire. The detection of fire is accessed in terms of temperature detected through RTD placed stationary or on a moving vehicle using PIC microcontroller to scale the voltage values. Transmitting and receiving messages through a channel using open band of RF frequency 434 MHz to make it more secure. The fire is contained and extinguished by Trifluoroiodomethane CF3I gas in a container.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123023004","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}
The use of Artificial Intelligence (AI) in solving real- time problems are increasing day by day with the increase in the availability of data and computation power. It is now substantial to use AI-based tools and techniques in space science. Asteroids, rocky objects that orbit around the sun, often produce an array of effects that cause harm to humans and biodiversity on earth. Such effects can cause wind blast, overpressure shock, thermal radiation, cratering, seismic shaking, ejecta deposition, tsunami, and many more. With the availability of data on asteroid parameters and nature, it provides an opportunity to use Machine Learning (ML) to address this problem and reduce the risk. This paper presents a thorough study on the impact of Potentially Hazardous Asteroids (PHAs) and proposes a supervised machine learning method to detect whether an asteroid with specific parameters is hazardous or not. We compare manifold classification algorithms that were implemented on the data. Random forest gave the best performance in terms of accuracy (99.99%) and average F1- score (99.22%).
{"title":"Supervised Classification for Analysis and Detection of Potentially Hazardous Asteroid","authors":"Vedant Bahel, Pratik Bhongade, Jagrity Sharma, Samiksha Shukla, Mahendra Gaikwad","doi":"10.1109/iccica52458.2021.9697222","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697222","url":null,"abstract":"The use of Artificial Intelligence (AI) in solving real- time problems are increasing day by day with the increase in the availability of data and computation power. It is now substantial to use AI-based tools and techniques in space science. Asteroids, rocky objects that orbit around the sun, often produce an array of effects that cause harm to humans and biodiversity on earth. Such effects can cause wind blast, overpressure shock, thermal radiation, cratering, seismic shaking, ejecta deposition, tsunami, and many more. With the availability of data on asteroid parameters and nature, it provides an opportunity to use Machine Learning (ML) to address this problem and reduce the risk. This paper presents a thorough study on the impact of Potentially Hazardous Asteroids (PHAs) and proposes a supervised machine learning method to detect whether an asteroid with specific parameters is hazardous or not. We compare manifold classification algorithms that were implemented on the data. Random forest gave the best performance in terms of accuracy (99.99%) and average F1- score (99.22%).","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124994043","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 : 2021-11-26DOI: 10.1109/iccica52458.2021.9697304
Ravi N. Srivastava, D. Padole
The IoT is the growing technology where the data of various devices like objects or virtual will be sent to the cloud server and we can access it online as well as can update the data. The technology utilized for IoT in the form of hardware is controllers and sensors. where the controllers get the data from the sensors and send them to the server database. Here the system proposed is the healthcare related that the pulse and oxygen level will send to the server for the monitoring of the patient. The data will be monitored per patient online by the doctors 24x7 in some medical diagnosis. Virus enters the body through the respiratory system which leads to injury to the lungs which can negatively impact the oxygen being transferred into the blood. SO to monitor the oxygen level is very important to give better treatment to the patient.
{"title":"Design of IoT based Remote Patient Health Care Monitoring System","authors":"Ravi N. Srivastava, D. Padole","doi":"10.1109/iccica52458.2021.9697304","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697304","url":null,"abstract":"The IoT is the growing technology where the data of various devices like objects or virtual will be sent to the cloud server and we can access it online as well as can update the data. The technology utilized for IoT in the form of hardware is controllers and sensors. where the controllers get the data from the sensors and send them to the server database. Here the system proposed is the healthcare related that the pulse and oxygen level will send to the server for the monitoring of the patient. The data will be monitored per patient online by the doctors 24x7 in some medical diagnosis. Virus enters the body through the respiratory system which leads to injury to the lungs which can negatively impact the oxygen being transferred into the blood. SO to monitor the oxygen level is very important to give better treatment to the patient.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":" 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120828478","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 : 2021-11-26DOI: 10.1109/iccica52458.2021.9697160
Shivanee Jaiswal, Joel Marvin Tellis, Rishi Kabra, Swati Mali
In the current COVID-19 pandemic, it has become extremely important to detect the affected patients as soon as possible and isolate them in order to break the chain of the spreading virus. Testing in large numbers at laboratories has overwhelmed their resources. Furthermore, the diagnosis report often takes more than a day to be returned. All this adds up to the incapability of our healthcare infrastructure to test all the possibly infected patients. Radiologists across the world have used chest X-rays to detect chest diseases. X-rays being readily available in far less time than RT-PCR reports make them an easy and quick alternative in comparison to current testing methods. However, examining a vast number of X-rays in an already overwhelmed healthcare facility may still lead to delays in determining the presence of the disease. In addition, it would require expertise and profound knowledge about the much recently explored COVID-19 virus in order to make an accurate assessment of the X-rays. In this study, to find solutions to these problems, we have made use of deep learning for the detection of coronavirus. The proposed system uses three different Convolutional Neural Network (CNN) models to detect COVID-19 from pre-processed chest X-ray images with reliable accuracy and hence provide an alternative for people to be aware of being infected rather than wait days for results.
{"title":"COVID-19 Detection From Chest X-Ray Using Deep Learning and Contrast Enhancement","authors":"Shivanee Jaiswal, Joel Marvin Tellis, Rishi Kabra, Swati Mali","doi":"10.1109/iccica52458.2021.9697160","DOIUrl":"https://doi.org/10.1109/iccica52458.2021.9697160","url":null,"abstract":"In the current COVID-19 pandemic, it has become extremely important to detect the affected patients as soon as possible and isolate them in order to break the chain of the spreading virus. Testing in large numbers at laboratories has overwhelmed their resources. Furthermore, the diagnosis report often takes more than a day to be returned. All this adds up to the incapability of our healthcare infrastructure to test all the possibly infected patients. Radiologists across the world have used chest X-rays to detect chest diseases. X-rays being readily available in far less time than RT-PCR reports make them an easy and quick alternative in comparison to current testing methods. However, examining a vast number of X-rays in an already overwhelmed healthcare facility may still lead to delays in determining the presence of the disease. In addition, it would require expertise and profound knowledge about the much recently explored COVID-19 virus in order to make an accurate assessment of the X-rays. In this study, to find solutions to these problems, we have made use of deep learning for the detection of coronavirus. The proposed system uses three different Convolutional Neural Network (CNN) models to detect COVID-19 from pre-processed chest X-ray images with reliable accuracy and hence provide an alternative for people to be aware of being infected rather than wait days for results.","PeriodicalId":327193,"journal":{"name":"2021 International Conference on Computational Intelligence and Computing Applications (ICCICA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121373943","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：