Maiboli is a proposed programming language solution based on Marathi Devanagari script. It aims to bring the knowledge of programming to common individuals who find language as a barrier while learning programming. Here, the proposed system will be based on Python programming language and it will cover up basic libraries required for one to learn programming as a concept. This research paper serves insights of how Maiboli as a programming method, will serve for the well being of common individuals residing in areas where Marathi Language is dominant.
{"title":"Maiboli - A programming language solution based on Marathi Devanagari Script","authors":"Chaudhari Nimish Dadabhau, Shaikh Bushra, Karan Bansal, Bhanushali Mitesh","doi":"10.1109/IBSSC47189.2019.8973043","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973043","url":null,"abstract":"Maiboli is a proposed programming language solution based on Marathi Devanagari script. It aims to bring the knowledge of programming to common individuals who find language as a barrier while learning programming. Here, the proposed system will be based on Python programming language and it will cover up basic libraries required for one to learn programming as a concept. This research paper serves insights of how Maiboli as a programming method, will serve for the well being of common individuals residing in areas where Marathi Language is dominant.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131037658","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973020
Vijayasri Iyer, A. M. Hima Vyshnavi, Sriram Iyer, P. K. Namboori
In the pharmacogenomic and theranostic approach of treating melanoma, a continuous monitoring of the disease and the mutations associated with the disease is essential. Such a monitoring system has been designed and developed based upon the concept ‘One-shot learning’, a machine learning technique adapted to work with a relatively small number of training images. The samples have been exhaustively studied through genomics, epigenomics, metagenomics and environmental genomics, finding the genetic signature behind proneness of these attributes. The mutations CDK4, CDKN2A, BRAF and KIT have been included in the analysis. The prediction accuracy of the machine is found to substantially high suggesting the device for the theranostic and pharmacogenomic strategies of controlling melanoma. A Distributed Ledger Technology (DLT) based system has been proposed for real time data sharing, training and analysis enabling hospitals and research labs to communicate with each other and conduct a cost-effective diagnostic workflow.
{"title":"An AI driven Genomic Profiling System and Secure Data Sharing using DLT for cancer patients","authors":"Vijayasri Iyer, A. M. Hima Vyshnavi, Sriram Iyer, P. K. Namboori","doi":"10.1109/IBSSC47189.2019.8973020","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973020","url":null,"abstract":"In the pharmacogenomic and theranostic approach of treating melanoma, a continuous monitoring of the disease and the mutations associated with the disease is essential. Such a monitoring system has been designed and developed based upon the concept ‘One-shot learning’, a machine learning technique adapted to work with a relatively small number of training images. The samples have been exhaustively studied through genomics, epigenomics, metagenomics and environmental genomics, finding the genetic signature behind proneness of these attributes. The mutations CDK4, CDKN2A, BRAF and KIT have been included in the analysis. The prediction accuracy of the machine is found to substantially high suggesting the device for the theranostic and pharmacogenomic strategies of controlling melanoma. A Distributed Ledger Technology (DLT) based system has been proposed for real time data sharing, training and analysis enabling hospitals and research labs to communicate with each other and conduct a cost-effective diagnostic workflow.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116924543","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973062
Shravya Bhat, Shilpa Nair, Shravya Kadur, S. R
The Adaptive Learning Application (ALA) is an intelligent tutoring system that identifies the manner in which a student assimilates information, and accordingly evolves itself to generate personalised lesson plans that optimise learning. The ALA is built using a combination of a Weighted Support Vector Machine, a custom-built algorithm amalgamating versions of the FP-Growth and Genetic algorithms, and Natural Language Processing techniques. Thus, it uses both supervised and unsupervised learning to learn two things in parallel – how to quantifiably identify the types of topics a student finds difficult, and the best way in which to teach a topic of a particular difficulty level. Natural Language Processing techniques including but not limited to POS-tagging and TF-IDF scores are used to evaluate how much the student has learnt. The results are propagated back into a feedback loop to facilitate learning.
自适应学习应用程序(ALA)是一种智能辅导系统，可以识别学生吸收信息的方式，并相应地发展自己以生成个性化的课程计划，从而优化学习。ALA是使用加权支持向量机(Weighted Support Vector Machine)、一种融合FP-Growth和遗传算法的定制算法以及自然语言处理技术的组合来构建的。因此，它同时使用监督学习和无监督学习来学习两件事——如何量化地识别学生觉得困难的主题类型，以及教授特定难度级别主题的最佳方式。自然语言处理技术包括但不限于pos标记和TF-IDF分数用于评估学生的学习程度。结果被传播回一个反馈循环，以促进学习。
{"title":"A Personalised Approach to Adaptive Tutoring using Machine Learning and Natural Language Processing","authors":"Shravya Bhat, Shilpa Nair, Shravya Kadur, S. R","doi":"10.1109/IBSSC47189.2019.8973062","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973062","url":null,"abstract":"The Adaptive Learning Application (ALA) is an intelligent tutoring system that identifies the manner in which a student assimilates information, and accordingly evolves itself to generate personalised lesson plans that optimise learning. The ALA is built using a combination of a Weighted Support Vector Machine, a custom-built algorithm amalgamating versions of the FP-Growth and Genetic algorithms, and Natural Language Processing techniques. Thus, it uses both supervised and unsupervised learning to learn two things in parallel – how to quantifiably identify the types of topics a student finds difficult, and the best way in which to teach a topic of a particular difficulty level. Natural Language Processing techniques including but not limited to POS-tagging and TF-IDF scores are used to evaluate how much the student has learnt. The results are propagated back into a feedback loop to facilitate learning.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117011530","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973024
S. C. Hiremath, J. Mallapur
The modern India is proposing and developing smart cities, so that Indian standard of living to grow and reach on par with other countries. The smart cities should be embedded with all new technologies such as sensors, environmental, cloud access, IoT interface, data acquisition, etc. In our proposed work, we are planning to interface cloud with a smart city traffic management. In metro cities people go to cluster area such as Temples, Shopping malls, Cine theatres, etc and waste time in searching parking lots and withdrawing themselves with no solutions. We have come up with the concept that uses smart dynamic parking provision mechanism that can be accessed before the hand at target place or nearby sub parking possibilities. This solution reduces traffic turbulence and pleasure of utilizing possible parking lots as alternate solution rather than withdrawal.
{"title":"Optimization of Parking Dynamics in Smart City using Cloud Networks","authors":"S. C. Hiremath, J. Mallapur","doi":"10.1109/IBSSC47189.2019.8973024","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973024","url":null,"abstract":"The modern India is proposing and developing smart cities, so that Indian standard of living to grow and reach on par with other countries. The smart cities should be embedded with all new technologies such as sensors, environmental, cloud access, IoT interface, data acquisition, etc. In our proposed work, we are planning to interface cloud with a smart city traffic management. In metro cities people go to cluster area such as Temples, Shopping malls, Cine theatres, etc and waste time in searching parking lots and withdrawing themselves with no solutions. We have come up with the concept that uses smart dynamic parking provision mechanism that can be accessed before the hand at target place or nearby sub parking possibilities. This solution reduces traffic turbulence and pleasure of utilizing possible parking lots as alternate solution rather than withdrawal.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124900035","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973057
Shachi Sharma, I. Bassi
Categorical data clustering is an important area of research today as databases usually contain categorical data [1]. The current work proposes that the behavior of attributes in categorical dataset is important in selecting the clustering algorithm. A Tsallis entropy based categorical data clustering (TEC) algorithm is also presented. It is shown that when the attributes depict power law behavior, the proposed TEC algorithm outperforms existing Shannon entropy based clustering algorithms. Experimental results on UCI and WEB KB datasets validates the efficacy of TEC algorithm.
{"title":"Efficacy of Tsallis Entropy in Clustering Categorical Data","authors":"Shachi Sharma, I. Bassi","doi":"10.1109/IBSSC47189.2019.8973057","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973057","url":null,"abstract":"Categorical data clustering is an important area of research today as databases usually contain categorical data [1]. The current work proposes that the behavior of attributes in categorical dataset is important in selecting the clustering algorithm. A Tsallis entropy based categorical data clustering (TEC) algorithm is also presented. It is shown that when the attributes depict power law behavior, the proposed TEC algorithm outperforms existing Shannon entropy based clustering algorithms. Experimental results on UCI and WEB KB datasets validates the efficacy of TEC algorithm.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125038589","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8972989
Jaideepsinh K. Raulji, Jatinderkumar R. Saini
Looking at vastness, depth and precise nature of Sanskrit grammar and geographically wide proliferation of Gujarati language and its native speaker, it becomes necessary to spotlight on constituency characteristics and features of Sanskrit and Gujarati. Both the languages fall under Indo-Iranian language sub-tree, but there are grammatical divergences which are discussed here so as to reflect in implementation of Machine Translation System (MTS). The content revolves around divergence pattern for a rule base MT system, due to scarce or unavailability of parallel aligned corpora to incorporate statistical or Example based methodology. The Sanskrit grammatical constituents like indeclinables, pronouns, verbs and nouns are analyzed. The Sanskrit inflectional affixes are mapped to its Gujarati inflectional affixes for each equivalent grammar constituent.
{"title":"Sanskrit-Gujarati Constituency Mapper for Machine Translation System","authors":"Jaideepsinh K. Raulji, Jatinderkumar R. Saini","doi":"10.1109/IBSSC47189.2019.8972989","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8972989","url":null,"abstract":"Looking at vastness, depth and precise nature of Sanskrit grammar and geographically wide proliferation of Gujarati language and its native speaker, it becomes necessary to spotlight on constituency characteristics and features of Sanskrit and Gujarati. Both the languages fall under Indo-Iranian language sub-tree, but there are grammatical divergences which are discussed here so as to reflect in implementation of Machine Translation System (MTS). The content revolves around divergence pattern for a rule base MT system, due to scarce or unavailability of parallel aligned corpora to incorporate statistical or Example based methodology. The Sanskrit grammatical constituents like indeclinables, pronouns, verbs and nouns are analyzed. The Sanskrit inflectional affixes are mapped to its Gujarati inflectional affixes for each equivalent grammar constituent.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129208333","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973018
Sushama Telrandhe, P. Daigavane
Fetus facial expression analysis is a recent and upcoming field of study in the area of biomedical image processing. Fetus images are obtained using 3D ultra-sounds, and thus there is minimum clarity in terms of the fetus face alignment, the fetus face posture and the fetus face size. All these issues make it a challenging task to identify the location of fetus face, and thus the fetal expression or mood analysis becomes a complicated task. In this paper, a saliency map based method is proposed to segment out the fetus face with good level of accuracy, and then identify the fetus mood using a recurrent neural network based classifier. Our work shows more than 80% accuracy across various fetus aging images, and has moderate delay of classification. We also proposed techniques for improving the accuracy further and also improving the precision and recall rates for the classification process.
{"title":"Automatic Fetal Facial Expression Recognition by Hybridizing Saliency Maps with Recurrent Neural Network","authors":"Sushama Telrandhe, P. Daigavane","doi":"10.1109/IBSSC47189.2019.8973018","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973018","url":null,"abstract":"Fetus facial expression analysis is a recent and upcoming field of study in the area of biomedical image processing. Fetus images are obtained using 3D ultra-sounds, and thus there is minimum clarity in terms of the fetus face alignment, the fetus face posture and the fetus face size. All these issues make it a challenging task to identify the location of fetus face, and thus the fetal expression or mood analysis becomes a complicated task. In this paper, a saliency map based method is proposed to segment out the fetus face with good level of accuracy, and then identify the fetus mood using a recurrent neural network based classifier. Our work shows more than 80% accuracy across various fetus aging images, and has moderate delay of classification. We also proposed techniques for improving the accuracy further and also improving the precision and recall rates for the classification process.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121374304","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}
Nowadays the Internet and Social Media are flooded with fake accounts, fake posts and misleading news articles. The intention of these are often to mislead the common people and/or manipulate them into believing something that is not real. Misinformation or fake news can leave negative impact on a person or society as a whole that can last forever even if they get corrected afterwards. This work proposed here is to tackle this issue and it aims to identify a news articles whether it is real or misleading. This is achieved using an ensemble technique of state of the art recurrent neural networks (LSTM and GRU). An android application has also been developed for determining the sanctity of a news article. The proposed model is tested on a large dataset which is prepared in this work by collecting news from various fake and real news sources. It has also been tested using different standard datasets available in the literature and it is found that the proposed model performs better.
{"title":"F-NAD: An Application for Fake News Article Detection using Machine Learning Techniques","authors":"Ranojoy Barua, Rajdeep Maity, Dipankar Minj, Tarang Barua, Ashish Kumar Layek","doi":"10.1109/IBSSC47189.2019.8973059","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973059","url":null,"abstract":"Nowadays the Internet and Social Media are flooded with fake accounts, fake posts and misleading news articles. The intention of these are often to mislead the common people and/or manipulate them into believing something that is not real. Misinformation or fake news can leave negative impact on a person or society as a whole that can last forever even if they get corrected afterwards. This work proposed here is to tackle this issue and it aims to identify a news articles whether it is real or misleading. This is achieved using an ensemble technique of state of the art recurrent neural networks (LSTM and GRU). An android application has also been developed for determining the sanctity of a news article. The proposed model is tested on a large dataset which is prepared in this work by collecting news from various fake and real news sources. It has also been tested using different standard datasets available in the literature and it is found that the proposed model performs better.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121705977","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973046
Nikhil B. Gaikwad, A. Keskar, V. Tiwari, N. Shivaprakash
The wearable technology carries sufficient potential to incorporate smartness into working of the military workforces like the Military Control Unit, Medical Responders, Backup Unit and War Strategist. The proposed work focuses on real-time soldier activity detection, which is essential for the operation of the smart military suit. The customized Artificial Neural Network (ANN) IP core is developed for the soldier activity classification, which is an integral component of suit gateway design. The multilayer perceptron (7-5-4) classification algorithm is implemented on the low-cost (99$) FPGA evaluation platform by using Xilinx vivado and system generator development tools. The training (70%) and testing (30%) of this ANN design is performed on the UCI human activity dataset. The LabVIEW GUI and IP test design completed the hardware testing of this IP. The presented ANN IP is able to achieve 98.5% classification accuracy by utilizing minimal FPGA (Artix-7 xc7a35t) resources. The implemented ANN design requires only 285 nanoseconds for a classification and consumes 103 milliwatts of dynamic power. The system’s accuracy at different development levels is also studied in this work.
{"title":"FPGA Implementation of Real-Time Soldier Activity Detection based on Neural Network Classifier in Smart Military Suit","authors":"Nikhil B. Gaikwad, A. Keskar, V. Tiwari, N. Shivaprakash","doi":"10.1109/IBSSC47189.2019.8973046","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973046","url":null,"abstract":"The wearable technology carries sufficient potential to incorporate smartness into working of the military workforces like the Military Control Unit, Medical Responders, Backup Unit and War Strategist. The proposed work focuses on real-time soldier activity detection, which is essential for the operation of the smart military suit. The customized Artificial Neural Network (ANN) IP core is developed for the soldier activity classification, which is an integral component of suit gateway design. The multilayer perceptron (7-5-4) classification algorithm is implemented on the low-cost (99$) FPGA evaluation platform by using Xilinx vivado and system generator development tools. The training (70%) and testing (30%) of this ANN design is performed on the UCI human activity dataset. The LabVIEW GUI and IP test design completed the hardware testing of this IP. The presented ANN IP is able to achieve 98.5% classification accuracy by utilizing minimal FPGA (Artix-7 xc7a35t) resources. The implemented ANN design requires only 285 nanoseconds for a classification and consumes 103 milliwatts of dynamic power. The system’s accuracy at different development levels is also studied in this work.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"184 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121711298","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 : 2019-07-01DOI: 10.1109/IBSSC47189.2019.8973105
G. Rohith, L. S. Kumar
Super-resolution has gained significant importance recently owing to its finer sampling image details. Deep learning algorithms have remarked as an entity for developing single image high-quality reconstruction. Super-resolution with Deep Learning algorithms has demonstrated state of the art approaches for reconstructing sharper and more accurate images. Satellite images are highly prone to lose minute details of the image when subjected to algorithmic modeling. Thus, it is necessary to preserve the details of image. In this paper, an attempt is made to incorporate the state of the art approaches for reconstructing the satellite images. This requires careful conditioning of validating parameters like bias value, weights, appropriate usage of filters and scaling factors. The existing super-resolution algorithms such as Bicubic interpolation, Super resolution convolutional neural network (SRCNN), fast Super resolution convolutional neural network (FSRCNN) and Deep Laplacian Pyramid (LapSRN) are simulated to reconstruct the satellite images obtained from benchmark data sets of Indian and International satellite sensors. An extensive quantitative and qualitative evaluation of the super-resolution algorithms shows that the Deep Laplacian Pyramid networks perform favorably against the other state-of-the-art methods exclusively for satellite images.
{"title":"Performance analysis of Satellite Image Super Resolution using Deep Learning Techniques","authors":"G. Rohith, L. S. Kumar","doi":"10.1109/IBSSC47189.2019.8973105","DOIUrl":"https://doi.org/10.1109/IBSSC47189.2019.8973105","url":null,"abstract":"Super-resolution has gained significant importance recently owing to its finer sampling image details. Deep learning algorithms have remarked as an entity for developing single image high-quality reconstruction. Super-resolution with Deep Learning algorithms has demonstrated state of the art approaches for reconstructing sharper and more accurate images. Satellite images are highly prone to lose minute details of the image when subjected to algorithmic modeling. Thus, it is necessary to preserve the details of image. In this paper, an attempt is made to incorporate the state of the art approaches for reconstructing the satellite images. This requires careful conditioning of validating parameters like bias value, weights, appropriate usage of filters and scaling factors. The existing super-resolution algorithms such as Bicubic interpolation, Super resolution convolutional neural network (SRCNN), fast Super resolution convolutional neural network (FSRCNN) and Deep Laplacian Pyramid (LapSRN) are simulated to reconstruct the satellite images obtained from benchmark data sets of Indian and International satellite sensors. An extensive quantitative and qualitative evaluation of the super-resolution algorithms shows that the Deep Laplacian Pyramid networks perform favorably against the other state-of-the-art methods exclusively for satellite images.","PeriodicalId":148941,"journal":{"name":"2019 IEEE Bombay Section Signature Conference (IBSSC)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128374552","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：