Pub Date : 2021-11-10DOI: 10.1109/ICTAI53825.2021.9673289
Aditi Chandra, A. Chauhan, N. Bansal, A. Rajpoot
Immediate and precise clinical conclusion is fundamental for viable treatment of sicknesses. It utilizes AI calculations and dependent on the consequences of research centre blood tests, we have constructed two models anticipating hematologic sickness. One prescient model uses all accessible boundaries for blood tests and another utilized just a diminished set that is typically estimated in understanding confirmation. The two sorts yield positive results, securing 0.88 and 0.86 judicious data from an overview of five no doubt infections and 0.59 and 0.57 while pondering only the most likely disease. Models it was not altogether extraordinary, showing that the diminished arrangement of boundaries can address the relating “Fingerprints” of the infection. This data upgrades the utilization of the model to be used by broad experts and it shows that the consequences of a blood test contain more data than specialists normally do. A clinical preliminary has shown, the precision of our theoretical models was reliable with hematology treatment specialists. Our examination rushes to show that the learning model is a blood-based judicious model tests alone can be used satisfactorily to expect Hematological sicknesses. This impact can likewise be opened exceptional freedoms for clinical analysis.
{"title":"Application of Machine Learning In Hematological Diagnosis","authors":"Aditi Chandra, A. Chauhan, N. Bansal, A. Rajpoot","doi":"10.1109/ICTAI53825.2021.9673289","DOIUrl":"https://doi.org/10.1109/ICTAI53825.2021.9673289","url":null,"abstract":"Immediate and precise clinical conclusion is fundamental for viable treatment of sicknesses. It utilizes AI calculations and dependent on the consequences of research centre blood tests, we have constructed two models anticipating hematologic sickness. One prescient model uses all accessible boundaries for blood tests and another utilized just a diminished set that is typically estimated in understanding confirmation. The two sorts yield positive results, securing 0.88 and 0.86 judicious data from an overview of five no doubt infections and 0.59 and 0.57 while pondering only the most likely disease. Models it was not altogether extraordinary, showing that the diminished arrangement of boundaries can address the relating “Fingerprints” of the infection. This data upgrades the utilization of the model to be used by broad experts and it shows that the consequences of a blood test contain more data than specialists normally do. A clinical preliminary has shown, the precision of our theoretical models was reliable with hematology treatment specialists. Our examination rushes to show that the learning model is a blood-based judicious model tests alone can be used satisfactorily to expect Hematological sicknesses. This impact can likewise be opened exceptional freedoms for clinical analysis.","PeriodicalId":278263,"journal":{"name":"2021 International Conference on Technological Advancements and Innovations (ICTAI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133993758","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 Mobile Devices (Smart Mobile Phones, Tablets PCS) are becoming a computing and service access devices at anytime and anywhere. These devices are constrained by the CPU workload, memory capacity and battery life. MCC is the technology which enhances the power and capabilities of mobile devices by extending the services and resources of computational clouds to smart mobile devices on demand bases. The offloading mechanism gives the provision to enrich the mobile devices with sufficient resources. This paper explains the offloading mechanism in MCC domain. The objective of this paper is to investigate the issues and challenges for the partitioning of the application. Further it highlights few research questions on how offloading can be done efficiently so that performance improvement as well as energy saving can be achieved.
{"title":"Study and Analysis of Offloading in Mobile Cloud Computing","authors":"Puneet Singh, PankajPratap Singh, Subhadra Rajpoot, Devang Pratap Singh","doi":"10.1109/ICTAI53825.2021.9673481","DOIUrl":"https://doi.org/10.1109/ICTAI53825.2021.9673481","url":null,"abstract":"The Mobile Devices (Smart Mobile Phones, Tablets PCS) are becoming a computing and service access devices at anytime and anywhere. These devices are constrained by the CPU workload, memory capacity and battery life. MCC is the technology which enhances the power and capabilities of mobile devices by extending the services and resources of computational clouds to smart mobile devices on demand bases. The offloading mechanism gives the provision to enrich the mobile devices with sufficient resources. This paper explains the offloading mechanism in MCC domain. The objective of this paper is to investigate the issues and challenges for the partitioning of the application. Further it highlights few research questions on how offloading can be done efficiently so that performance improvement as well as energy saving can be achieved.","PeriodicalId":278263,"journal":{"name":"2021 International Conference on Technological Advancements and Innovations (ICTAI)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127615491","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 : 2021-11-10DOI: 10.1109/ICTAI53825.2021.9673193
H. Agrawal, Aditya Gupta, Aryan Sharma, P. Singh
Roads play an important role in developing the infrastructure of a city and they also play an important role in our day-to-day life, as more people travel from one place to another by road. Road surface quality needs to be monitored properly, as bad roads with a lot of potholes and cracks in it lead to some fatal accidents. Due to the advancement in technology, compact smart devices (smartphones, tablets) with high computation power and having the ability to sense their environment with the help of different sensors have provided the ideas to solve some real-life problems effectively. We propose a method for detecting the potholes on the road surface by using the smartphone sensors. A flutter based android application is developed to collect the accelerometer and gyroscope readings from smartphone sensors. By analyzing and detecting patterns from the accelerometer and gyroscope readings from the smartphone sensors we find the exact location of the potholes on the road surface and store that data in database. Later that can be provided to relevant authorities for maintenance of roads.
{"title":"Road Pothole Detection Mechanism using Mobile Sensors","authors":"H. Agrawal, Aditya Gupta, Aryan Sharma, P. Singh","doi":"10.1109/ICTAI53825.2021.9673193","DOIUrl":"https://doi.org/10.1109/ICTAI53825.2021.9673193","url":null,"abstract":"Roads play an important role in developing the infrastructure of a city and they also play an important role in our day-to-day life, as more people travel from one place to another by road. Road surface quality needs to be monitored properly, as bad roads with a lot of potholes and cracks in it lead to some fatal accidents. Due to the advancement in technology, compact smart devices (smartphones, tablets) with high computation power and having the ability to sense their environment with the help of different sensors have provided the ideas to solve some real-life problems effectively. We propose a method for detecting the potholes on the road surface by using the smartphone sensors. A flutter based android application is developed to collect the accelerometer and gyroscope readings from smartphone sensors. By analyzing and detecting patterns from the accelerometer and gyroscope readings from the smartphone sensors we find the exact location of the potholes on the road surface and store that data in database. Later that can be provided to relevant authorities for maintenance of roads.","PeriodicalId":278263,"journal":{"name":"2021 International Conference on Technological Advancements and Innovations (ICTAI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115990878","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 : 2021-11-10DOI: 10.1109/ICTAI53825.2021.9673303
Aravind Nalamothu, J. Vijaya
Palmprints have fascinated academics attributable to their steady and exclusive residences as biometric technology grows to be extra popular. Over fingerprints and facial biometrics, palmprints offer extra targeted characteristic statistics for reputation systems. This study paper ambition to offer a complete overview of numerous palmprint popularity methods, together with ROI extraction mechanism, characteristic extraction strategy, and matching systems, in addition to a top-level view of to be had palmprint datasets, for you to apprehend the cutting-edge developments and studies dynamics with inside the palmprint popularity area.
{"title":"A review on Palmprint Recognition system using Machine learning and Deep learning methods","authors":"Aravind Nalamothu, J. Vijaya","doi":"10.1109/ICTAI53825.2021.9673303","DOIUrl":"https://doi.org/10.1109/ICTAI53825.2021.9673303","url":null,"abstract":"Palmprints have fascinated academics attributable to their steady and exclusive residences as biometric technology grows to be extra popular. Over fingerprints and facial biometrics, palmprints offer extra targeted characteristic statistics for reputation systems. This study paper ambition to offer a complete overview of numerous palmprint popularity methods, together with ROI extraction mechanism, characteristic extraction strategy, and matching systems, in addition to a top-level view of to be had palmprint datasets, for you to apprehend the cutting-edge developments and studies dynamics with inside the palmprint popularity area.","PeriodicalId":278263,"journal":{"name":"2021 International Conference on Technological Advancements and Innovations (ICTAI)","volume":"455 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124488942","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 : 2021-11-10DOI: 10.1109/ICTAI53825.2021.9673394
Rajat Tiwari, Bhawna Goyal, Ayush Dogra
Haze reduces an image's quality, reducing its aesthetic appeal and visibility in outdoor locations. This is because of the presence of smog, fog, haze etc. Therefore, image de hazing is one of the important considerations. Dehazing mechanisms are widely used in military and civil regions, such as, monitoring of traffic, remote sensing, identification of targets etc. This study examines the key de haze approaches that have been developed over the last decade. This paper conducts a thorough examination of dehazing techniques in order to demonstrate that they may be used effectively in real-world situations. In this paper, image dehazing is classified into two sections, first section is on image enhancement and second is explained on restoration model. According to principles and characteristics, all approaches are analyzed and corresponding sub-categories are presented. Following that, many quality assessment methodologies are explained, sorted, and examined in depth. The aim of the paper is to analysis recent advances in image de hazing in a short manner, as well as to give one concise knowledge of image de hazing methodologies.
{"title":"Haze removal in Remote sensing 2-D information: Methods and Analysis","authors":"Rajat Tiwari, Bhawna Goyal, Ayush Dogra","doi":"10.1109/ICTAI53825.2021.9673394","DOIUrl":"https://doi.org/10.1109/ICTAI53825.2021.9673394","url":null,"abstract":"Haze reduces an image's quality, reducing its aesthetic appeal and visibility in outdoor locations. This is because of the presence of smog, fog, haze etc. Therefore, image de hazing is one of the important considerations. Dehazing mechanisms are widely used in military and civil regions, such as, monitoring of traffic, remote sensing, identification of targets etc. This study examines the key de haze approaches that have been developed over the last decade. This paper conducts a thorough examination of dehazing techniques in order to demonstrate that they may be used effectively in real-world situations. In this paper, image dehazing is classified into two sections, first section is on image enhancement and second is explained on restoration model. According to principles and characteristics, all approaches are analyzed and corresponding sub-categories are presented. Following that, many quality assessment methodologies are explained, sorted, and examined in depth. The aim of the paper is to analysis recent advances in image de hazing in a short manner, as well as to give one concise knowledge of image de hazing methodologies.","PeriodicalId":278263,"journal":{"name":"2021 International Conference on Technological Advancements and Innovations (ICTAI)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124649349","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 : 2021-11-10DOI: 10.1109/ICTAI53825.2021.9673172
P. Singh, Y. P. Singh, Sparshi Kapil, Shristi Srivastava, Vishwas Vishwakarma
Mining of opinions are very crucial in all fields from e commerce websites to social media platforms. The products on any e commerce websites have thousands of reviews which helps customers to make a decision a product. Social media websites also have people with large number of opinions on a particular subject. Mining of opinions can be extensively used in the fields where opinions play a major role. This project caters to this need and classifies the opinions of people as positive and negative. This can further be used by movie recommendation systems and e commerce websites for evaluation of their product. It involved in the classification the opinions as positive opinions and negative opinions with the help of deep learning algorithms by achieving high accuracy. The procedures involved in this project will be of dataset selection, data preprocessing, data tokenization, and data cleansing and building a neural network. We have taken the dataset of reviews for this purpose. Data preprocessing and data cleansing is done so that deep learning algorithms can be easily applied on the data. Deep learning algorithms learn on their own and do not require guidance. The main objective of using deep learning model is for increasing efficiency, performance and accuracy. Here, we have applied three different neural network models to our dataset and compare the performances according to the testing and training accuracy obtained. Analysis of the three models concludes that Recurrent Neural Model (RNN) has least over fitting with considerable testing and training accuracy. Hence, it best suits the problem statement.
{"title":"An Improved Model for Opinion Mining of Public Reviews using Recurrent Neural Network","authors":"P. Singh, Y. P. Singh, Sparshi Kapil, Shristi Srivastava, Vishwas Vishwakarma","doi":"10.1109/ICTAI53825.2021.9673172","DOIUrl":"https://doi.org/10.1109/ICTAI53825.2021.9673172","url":null,"abstract":"Mining of opinions are very crucial in all fields from e commerce websites to social media platforms. The products on any e commerce websites have thousands of reviews which helps customers to make a decision a product. Social media websites also have people with large number of opinions on a particular subject. Mining of opinions can be extensively used in the fields where opinions play a major role. This project caters to this need and classifies the opinions of people as positive and negative. This can further be used by movie recommendation systems and e commerce websites for evaluation of their product. It involved in the classification the opinions as positive opinions and negative opinions with the help of deep learning algorithms by achieving high accuracy. The procedures involved in this project will be of dataset selection, data preprocessing, data tokenization, and data cleansing and building a neural network. We have taken the dataset of reviews for this purpose. Data preprocessing and data cleansing is done so that deep learning algorithms can be easily applied on the data. Deep learning algorithms learn on their own and do not require guidance. The main objective of using deep learning model is for increasing efficiency, performance and accuracy. Here, we have applied three different neural network models to our dataset and compare the performances according to the testing and training accuracy obtained. Analysis of the three models concludes that Recurrent Neural Model (RNN) has least over fitting with considerable testing and training accuracy. Hence, it best suits the problem statement.","PeriodicalId":278263,"journal":{"name":"2021 International Conference on Technological Advancements and Innovations (ICTAI)","volume":"168 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124680613","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 : 2021-11-10DOI: 10.1109/ICTAI53825.2021.9673233
Jyoti Dargan, N. Gupta, Latika Singh
There is tremendous growth in the renewable energy generation due to international awareness and treaty compulsions like Paris Agreement, 2016 etc. for renewable and climate friendly energy generation and distribution. Present power distribution system is centralized in nature and do not have much scope for the distributed energy generation and distribution. Therefore, there is an urgent need to change the present centralized power distribution system with a new decentralized power distribution system integrating both traditional and sustainable energy sources in efficient energy management system. The devolved nature of the smart grids has demanded integration of novel technology like Blockchain to create a secure, immutable and trustless power distribution system for peer-to-peer energy transmission. This paper proposes a model for blockchain based energy management system which integrates all energy sources, identifies the stakeholders as per their roles, generates certificates /token, does energy transactions, and incentivize the use of sustainable or green energy.
{"title":"Blockchain Based Energy Management System: A Proposed Model","authors":"Jyoti Dargan, N. Gupta, Latika Singh","doi":"10.1109/ICTAI53825.2021.9673233","DOIUrl":"https://doi.org/10.1109/ICTAI53825.2021.9673233","url":null,"abstract":"There is tremendous growth in the renewable energy generation due to international awareness and treaty compulsions like Paris Agreement, 2016 etc. for renewable and climate friendly energy generation and distribution. Present power distribution system is centralized in nature and do not have much scope for the distributed energy generation and distribution. Therefore, there is an urgent need to change the present centralized power distribution system with a new decentralized power distribution system integrating both traditional and sustainable energy sources in efficient energy management system. The devolved nature of the smart grids has demanded integration of novel technology like Blockchain to create a secure, immutable and trustless power distribution system for peer-to-peer energy transmission. This paper proposes a model for blockchain based energy management system which integrates all energy sources, identifies the stakeholders as per their roles, generates certificates /token, does energy transactions, and incentivize the use of sustainable or green energy.","PeriodicalId":278263,"journal":{"name":"2021 International Conference on Technological Advancements and Innovations (ICTAI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127063365","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 : 2021-11-10DOI: 10.1109/ICTAI53825.2021.9673174
Surbhi Gupta, Anish Gupta, Yogesh Kumar
Cancer is a leading cause of mortality and morbidity on a global scale. Cancer research has gradually improved in the past three decades with the advent of automated learning techniques. Artificial Intelligence (AI) practices have emerged as valuable tools in predictive modeling. AI-based prediction models can serve as clinical decision support systems and aid in improving cancer mortality rates. Prominent research works have been conducted to predict cancer at an early stage. AI practices extending from machine learning to deep learning architectures have been employed in cancer prediction. Although the validation of AI prediction models in clinical settings is missing, many studies have still achieved better prediction outcomes than physicians, which advocate integrating AI in real-world settings. The review paper aims to highlight the potential of AI in cancer detection. This study also provides an outline of the automated prediction framework used for the diagnosis of cancer.
{"title":"Artificial intelligence techniques in Cancer research: Opportunities and challenges","authors":"Surbhi Gupta, Anish Gupta, Yogesh Kumar","doi":"10.1109/ICTAI53825.2021.9673174","DOIUrl":"https://doi.org/10.1109/ICTAI53825.2021.9673174","url":null,"abstract":"Cancer is a leading cause of mortality and morbidity on a global scale. Cancer research has gradually improved in the past three decades with the advent of automated learning techniques. Artificial Intelligence (AI) practices have emerged as valuable tools in predictive modeling. AI-based prediction models can serve as clinical decision support systems and aid in improving cancer mortality rates. Prominent research works have been conducted to predict cancer at an early stage. AI practices extending from machine learning to deep learning architectures have been employed in cancer prediction. Although the validation of AI prediction models in clinical settings is missing, many studies have still achieved better prediction outcomes than physicians, which advocate integrating AI in real-world settings. The review paper aims to highlight the potential of AI in cancer detection. This study also provides an outline of the automated prediction framework used for the diagnosis of cancer.","PeriodicalId":278263,"journal":{"name":"2021 International Conference on Technological Advancements and Innovations (ICTAI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129029132","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 : 2021-11-10DOI: 10.1109/ICTAI53825.2021.9673479
Ashok Kumar, K. Bhatia
Signature verification is a difficult research area since two people’s signatures may be similar, but an individual’s signature might vary depending on the situation. The accuracy of the signature verification framework is largely determined by the classifier and feature extraction scheme employed in the classification process. With this in mind, the current study looks into the effectiveness of the k-Nearest Neighbors classifier in conjunction with the Local Binary Pattern feature set for the development of a writer-independent offline signature verification system. To evaluate the system’s performance, two signature databases of 100 and 260 writers are used. Genuine signatures, as well as random forgery, unskilled forgery, and simulated forgery signatures, are considered for the development of the desired system, while genuine signatures, as well as random forgery, unskilled forgery, and simulated forgery signatures, are used to test the performance of the developed system. In simulation study false acceptance rate of 2.00%, 11.00% and 12.00% for random, unskilled, and simulated forgery signatures, respectively is obtained whereas the false rejection rate of 0.00% is achieved using Local Binary Pattern feature set.
{"title":"k-NN based Writer Independent Offline Signature Verification System","authors":"Ashok Kumar, K. Bhatia","doi":"10.1109/ICTAI53825.2021.9673479","DOIUrl":"https://doi.org/10.1109/ICTAI53825.2021.9673479","url":null,"abstract":"Signature verification is a difficult research area since two people’s signatures may be similar, but an individual’s signature might vary depending on the situation. The accuracy of the signature verification framework is largely determined by the classifier and feature extraction scheme employed in the classification process. With this in mind, the current study looks into the effectiveness of the k-Nearest Neighbors classifier in conjunction with the Local Binary Pattern feature set for the development of a writer-independent offline signature verification system. To evaluate the system’s performance, two signature databases of 100 and 260 writers are used. Genuine signatures, as well as random forgery, unskilled forgery, and simulated forgery signatures, are considered for the development of the desired system, while genuine signatures, as well as random forgery, unskilled forgery, and simulated forgery signatures, are used to test the performance of the developed system. In simulation study false acceptance rate of 2.00%, 11.00% and 12.00% for random, unskilled, and simulated forgery signatures, respectively is obtained whereas the false rejection rate of 0.00% is achieved using Local Binary Pattern feature set.","PeriodicalId":278263,"journal":{"name":"2021 International Conference on Technological Advancements and Innovations (ICTAI)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121088641","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 : 2021-11-10DOI: 10.1109/ICTAI53825.2021.9673218
Neeboy Nogueira, Shawnon Guedes, Vaishnavi Mardolker, Amar Parab, S. Aswale, Pratiksha R. Shetgaonkar
Advancements in deep learning techniques have paved a way for efficient up scaling of images and videos. Similar to up scaling an image, we can reach upto a higher resolution by the process of video super resolution. Various existing methods and technologies for achieving a higher resolution are briefly surveyed in this paper and compared to analyze the downfall of the existing approach and proposing a solution. It was ascertained that deep learning approach of Convolutional Neural Network (CNN) is favorable solution to carry out video super resolution. It was also noted that most of the existing techniques focused on either of accuracy or on decreasing complexity, wherein the question of audio was also neglected. Considering the audio factor a innovative video embellished technique is recommended to overcome the balance needed in precision and complexity.
{"title":"Expeditious Video Super Resolution Using Convolutional Neural Network","authors":"Neeboy Nogueira, Shawnon Guedes, Vaishnavi Mardolker, Amar Parab, S. Aswale, Pratiksha R. Shetgaonkar","doi":"10.1109/ICTAI53825.2021.9673218","DOIUrl":"https://doi.org/10.1109/ICTAI53825.2021.9673218","url":null,"abstract":"Advancements in deep learning techniques have paved a way for efficient up scaling of images and videos. Similar to up scaling an image, we can reach upto a higher resolution by the process of video super resolution. Various existing methods and technologies for achieving a higher resolution are briefly surveyed in this paper and compared to analyze the downfall of the existing approach and proposing a solution. It was ascertained that deep learning approach of Convolutional Neural Network (CNN) is favorable solution to carry out video super resolution. It was also noted that most of the existing techniques focused on either of accuracy or on decreasing complexity, wherein the question of audio was also neglected. Considering the audio factor a innovative video embellished technique is recommended to overcome the balance needed in precision and complexity.","PeriodicalId":278263,"journal":{"name":"2021 International Conference on Technological Advancements and Innovations (ICTAI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122869909","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：