Pub Date : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297427
Neetu Agrawal, Manish Gupta, Sanjay Chouhan
This article presents a lightweight rectangular microstrip antenna which is developed for 5G communication systems. The resonance frequency is selected as 28 GHz for 5G use. FR4 epoxy material with a permittivity of 4.4 is selected as substrate material which has low cost and substrate size is $5.5times 4.5$ mm2. The shape of the radiating patch is rectangular and using the microstrip feeding technique. HFSS software is used for the simulation. Different parameters are observed, such as return loss, Gain, and radiation pattern. The antenna has a gain of over 2.9 dB which is very useful for 5G communications.
{"title":"Miniaturized Micro-strip Antenna for 5th Generation Applications","authors":"Neetu Agrawal, Manish Gupta, Sanjay Chouhan","doi":"10.1109/ICECA49313.2020.9297427","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297427","url":null,"abstract":"This article presents a lightweight rectangular microstrip antenna which is developed for 5G communication systems. The resonance frequency is selected as 28 GHz for 5G use. FR4 epoxy material with a permittivity of 4.4 is selected as substrate material which has low cost and substrate size is $5.5times 4.5$ mm2. The shape of the radiating patch is rectangular and using the microstrip feeding technique. HFSS software is used for the simulation. Different parameters are observed, such as return loss, Gain, and radiation pattern. The antenna has a gain of over 2.9 dB which is very useful for 5G communications.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"752 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117003320","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297565
Amruta Madhukar Dabhade, P. Kanjalkar
In this paper, the system identification and noise cancellation has been done and further the adaptive control algorithms like LMS(Least mean square),NLMS(normalized least mean square),NLMF(normalized least mean forth) and RLS(recursive least square) filters are compared. System identification identifies an unknown system given an input and output. It is used in active vibration and noise control applications. The LMS algorithm has lowest computations involved than all other ones. RLS is a computationally complex filter algorithm but it works more efficiently. In all of these filter algorithms, the weight coefficient is continuously updated until the convergence is reached. These algorithms are implemented and are compared by using parameters such as MSE (mean square error), PSNR (peak signal to noise ratio), convergence, complexity and accuracy.
{"title":"Comparative Study of Different Adaptive Control Strategies in Noise Cancellation Applications","authors":"Amruta Madhukar Dabhade, P. Kanjalkar","doi":"10.1109/ICECA49313.2020.9297565","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297565","url":null,"abstract":"In this paper, the system identification and noise cancellation has been done and further the adaptive control algorithms like LMS(Least mean square),NLMS(normalized least mean square),NLMF(normalized least mean forth) and RLS(recursive least square) filters are compared. System identification identifies an unknown system given an input and output. It is used in active vibration and noise control applications. The LMS algorithm has lowest computations involved than all other ones. RLS is a computationally complex filter algorithm but it works more efficiently. In all of these filter algorithms, the weight coefficient is continuously updated until the convergence is reached. These algorithms are implemented and are compared by using parameters such as MSE (mean square error), PSNR (peak signal to noise ratio), convergence, complexity and accuracy.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"209 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115388860","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297633
Arti Badhoutiya, S. Chandra, S. Goyal
In order to obtain a sustainable alternative for the power generation in developing countries, grid coupled PV panels are the best solution which is widely preferred in developed countries. A PV module with a grid coupled inverter is embodied in an AC module. Transformer less single stage arrangements are highly efficient and preferred over different arrangements of an AC module. ZS I being one of such arrangements have seen a fast evolution since its first release in 2003, in which its different arrangements along with its control and modulation schemes are included. This paper work emphasizes on the performance of ZS I under three modulation techniques provided with constant input voltage and modulation index, and finally conclude with a suitable scheme to obtain high output voltage.
{"title":"dentification of Suitable Modulation Scheme for Boosted output in ZSI","authors":"Arti Badhoutiya, S. Chandra, S. Goyal","doi":"10.1109/ICECA49313.2020.9297633","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297633","url":null,"abstract":"In order to obtain a sustainable alternative for the power generation in developing countries, grid coupled PV panels are the best solution which is widely preferred in developed countries. A PV module with a grid coupled inverter is embodied in an AC module. Transformer less single stage arrangements are highly efficient and preferred over different arrangements of an AC module. ZS I being one of such arrangements have seen a fast evolution since its first release in 2003, in which its different arrangements along with its control and modulation schemes are included. This paper work emphasizes on the performance of ZS I under three modulation techniques provided with constant input voltage and modulation index, and finally conclude with a suitable scheme to obtain high output voltage.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115583310","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297639
P. Shivani, S. Harshit, Ch.Vamsi Varma, R. Mahalakshmi
Transmission lines act as a medium to transmit power between the generating station and distribution station. The overhead transmission lines are placed at a height from the ground for safety purposes. When the transmission line is exposed to the environment for the long term, they are subjected to vibration due to wind, icing of conductors, etc., Hence there are chances of damages like partial breaks and fractures on the surfaces of the line. This leads to a reduction in load-bearing capacity. To overcome these issues, there is a necessity for continuous observation of the transmission lines. This paper targets the detection of fault due to broken strands in a transmission line using image processing. It is done using grayscale variance normalization along with the average intensity method in OpenCV, Python. The statistics about the transmission lines will be sent to the monitoring station for implementing precautionary measures.
{"title":"Detection of Broken Strands on Transmission Lines through Image Processing","authors":"P. Shivani, S. Harshit, Ch.Vamsi Varma, R. Mahalakshmi","doi":"10.1109/ICECA49313.2020.9297639","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297639","url":null,"abstract":"Transmission lines act as a medium to transmit power between the generating station and distribution station. The overhead transmission lines are placed at a height from the ground for safety purposes. When the transmission line is exposed to the environment for the long term, they are subjected to vibration due to wind, icing of conductors, etc., Hence there are chances of damages like partial breaks and fractures on the surfaces of the line. This leads to a reduction in load-bearing capacity. To overcome these issues, there is a necessity for continuous observation of the transmission lines. This paper targets the detection of fault due to broken strands in a transmission line using image processing. It is done using grayscale variance normalization along with the average intensity method in OpenCV, Python. The statistics about the transmission lines will be sent to the monitoring station for implementing precautionary measures.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114476289","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297440
U. Harita, V. U. Kumar, Dorababu Sudarsa, G. R. Krishna, C. Z. Basha, B. S. S. P. Kumar
Suicides in India have been registering at an alarming rate. The rainfall rate in India is unpredictable due to changes in environment. Farmers faces huge losses due to this unpredictable rains. This leads into loss of lives and results the farmers into suicide state. Relative analysis of rainfall and suicide rate will support farmers to avoid losses due to rainfall and further suicides can be avoided. Prediction of rainfall and suicide rate is achieved in India using machine learning algorithms such as Linear regression, Logistic regression, Support Vector Machine and Random Forest. Relative analysis provides better prediction results which greatly supports the farmers and avoid losses.
{"title":"A Fundamental Study on Suicides and Rainfall Datasets Using basic Machine Learning Algorithms","authors":"U. Harita, V. U. Kumar, Dorababu Sudarsa, G. R. Krishna, C. Z. Basha, B. S. S. P. Kumar","doi":"10.1109/ICECA49313.2020.9297440","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297440","url":null,"abstract":"Suicides in India have been registering at an alarming rate. The rainfall rate in India is unpredictable due to changes in environment. Farmers faces huge losses due to this unpredictable rains. This leads into loss of lives and results the farmers into suicide state. Relative analysis of rainfall and suicide rate will support farmers to avoid losses due to rainfall and further suicides can be avoided. Prediction of rainfall and suicide rate is achieved in India using machine learning algorithms such as Linear regression, Logistic regression, Support Vector Machine and Random Forest. Relative analysis provides better prediction results which greatly supports the farmers and avoid losses.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116222007","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297536
R. Sangeetha, A. Mohanarathinam, G. Aravindh, S. Jayachitra, M. Bhuvaneswari
Brain tumor is the result of an abnormal growth of cells, which reproduce themselves in an uncontrolled manner. This type of tumour is diagnosed through Magnetic Resonance Imaging (MRI), which plays a significant role in segmenting the tumor region into different ways for performing surgical and medical planning assessment but the manual detection may lead to errors and it is a time consuming process. To overcome the problem, experts use various algorithms for automatic detection of the tumor region, which are based on deep learning algorithms. They are designed to train and tune millions of images within a short period of time. Further, this paper proposes different types of classification methods with a number of iterations are based on CNN architectures such as VggNet, GoogleNet and ResNet 50. For 60 iterations VggNet reports 89.33% accuracy, GoogleNet 93.45% and ResNet 50 96.50%. Finally, it is proved that ResNet 50 achieves better results than VggNet and GoogleNet with comparatively less time and better accuracy.
{"title":"Automatic Detection of Brain Tumor Using Deep Learning Algorithms","authors":"R. Sangeetha, A. Mohanarathinam, G. Aravindh, S. Jayachitra, M. Bhuvaneswari","doi":"10.1109/ICECA49313.2020.9297536","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297536","url":null,"abstract":"Brain tumor is the result of an abnormal growth of cells, which reproduce themselves in an uncontrolled manner. This type of tumour is diagnosed through Magnetic Resonance Imaging (MRI), which plays a significant role in segmenting the tumor region into different ways for performing surgical and medical planning assessment but the manual detection may lead to errors and it is a time consuming process. To overcome the problem, experts use various algorithms for automatic detection of the tumor region, which are based on deep learning algorithms. They are designed to train and tune millions of images within a short period of time. Further, this paper proposes different types of classification methods with a number of iterations are based on CNN architectures such as VggNet, GoogleNet and ResNet 50. For 60 iterations VggNet reports 89.33% accuracy, GoogleNet 93.45% and ResNet 50 96.50%. Finally, it is proved that ResNet 50 achieves better results than VggNet and GoogleNet with comparatively less time and better accuracy.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126619207","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297508
Parneet Kaur Chowdhary, Mohan P. Thakre
Owing to the growing demand for pollution free energy in metropolitan transport, HEV’s (Hybrid electric vehicles) and EVs (Electric Vehicle) are gaining ample consideration due to their fuel efficient performance and no ecological damage due to the absence of harmful emissions. Thus countries all over the world are now paying increasing attention on the development of FV and HEV technology. HEVs (Hybrid Electric Vehicles) driven by SRM (switched reluctance motor) is supported by MMC (modular multilevel converter) has been proved to be a capable system by considering a hybrid vehicle system with decentralized battery energy storage system (BES S). In this drive, a SM (sub-module) is comprised of cell of battery and half-bridge converter and numerous such Sub-modules together form MMC. Adjustable discharging and charging functionality for every sub-module are acquired by scheming SMs switches. This topology is unmatched to the conventional SRM drives and is also very beneficial by offering several advantages. The functioning of the drive is effectively simulated in MATLAB and the performance is evaluated in the Generator Control Unit (GCU) with only driving case and GCU-Battery hybrid case. The battery cells are also investigated for analyzing fault tolerant ability in battery driving mode and GCU-battery hybrid mode.
{"title":"MMC based SRM Drives for Hybrid EV with Decentralized BESS","authors":"Parneet Kaur Chowdhary, Mohan P. Thakre","doi":"10.1109/ICECA49313.2020.9297508","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297508","url":null,"abstract":"Owing to the growing demand for pollution free energy in metropolitan transport, HEV’s (Hybrid electric vehicles) and EVs (Electric Vehicle) are gaining ample consideration due to their fuel efficient performance and no ecological damage due to the absence of harmful emissions. Thus countries all over the world are now paying increasing attention on the development of FV and HEV technology. HEVs (Hybrid Electric Vehicles) driven by SRM (switched reluctance motor) is supported by MMC (modular multilevel converter) has been proved to be a capable system by considering a hybrid vehicle system with decentralized battery energy storage system (BES S). In this drive, a SM (sub-module) is comprised of cell of battery and half-bridge converter and numerous such Sub-modules together form MMC. Adjustable discharging and charging functionality for every sub-module are acquired by scheming SMs switches. This topology is unmatched to the conventional SRM drives and is also very beneficial by offering several advantages. The functioning of the drive is effectively simulated in MATLAB and the performance is evaluated in the Generator Control Unit (GCU) with only driving case and GCU-Battery hybrid case. The battery cells are also investigated for analyzing fault tolerant ability in battery driving mode and GCU-battery hybrid mode.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127044732","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297542
Sovan Roy, Shah Md. Tanvir Siddiquee, Md. Khalidur Rahman, A. Marouf
Data hacking has become one of the anxiety issue in this modern era. Therefore, we have to prevent this illegal data hacking, theft at any cost. For ensuring data integrity, there are many methods including backups, encryption, access control, etc. We have presented an encryption methodology without merging the existing methods. By using the number conversion system and a defined mathematical calculation equation is the key to encrypt the password of the users. The password and date of birth are inputted by the users during the signup process. The encryption of the passwords has been stored into the database and manual calculation for the same cardinalities provides the same result. We have achieved an accuracy of 96% which is good as well as promising. Encryption is using in every sector to protect data and it has a wide range of future to work with it.
{"title":"A Novel Authentication Method for Password Encryption","authors":"Sovan Roy, Shah Md. Tanvir Siddiquee, Md. Khalidur Rahman, A. Marouf","doi":"10.1109/ICECA49313.2020.9297542","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297542","url":null,"abstract":"Data hacking has become one of the anxiety issue in this modern era. Therefore, we have to prevent this illegal data hacking, theft at any cost. For ensuring data integrity, there are many methods including backups, encryption, access control, etc. We have presented an encryption methodology without merging the existing methods. By using the number conversion system and a defined mathematical calculation equation is the key to encrypt the password of the users. The password and date of birth are inputted by the users during the signup process. The encryption of the passwords has been stored into the database and manual calculation for the same cardinalities provides the same result. We have achieved an accuracy of 96% which is good as well as promising. Encryption is using in every sector to protect data and it has a wide range of future to work with it.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125949786","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297395
A. Pooja, M. Sridhar
Phishing is a critical internet hazard and phishing losses progressively and it is caused by electronic means to deprive the users of sensitive information. Feature engineering is remaining essential for website-detection phishing solutions, although the quality of detection depends ultimately on previous knowledge of its features. Moreover, while the functionalities derived from different measurements are more precise, these characteristics take a lot of time to remove. This suggest a multidimensional approach to the detection of phishings focused on a quick detection mechanism through deep learning to overcome these limitations. The first step is to extract and use the character sequence features of the given URL for rapid classification through in-depth learning; this step does not include support from third parties or previous experience in phishing. It combine statistical URLs, web page code functions, website text features and easily categorise Profound learning in the second level on multidimensional functions. By the approach, the detection time of the threshold is shortened. The experimental results show that a rational adjustment of the threshold allows for the efficiency of the detection.
{"title":"Analysis of Phishing Website Detection Using CNN and Bidirectional LSTM","authors":"A. Pooja, M. Sridhar","doi":"10.1109/ICECA49313.2020.9297395","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297395","url":null,"abstract":"Phishing is a critical internet hazard and phishing losses progressively and it is caused by electronic means to deprive the users of sensitive information. Feature engineering is remaining essential for website-detection phishing solutions, although the quality of detection depends ultimately on previous knowledge of its features. Moreover, while the functionalities derived from different measurements are more precise, these characteristics take a lot of time to remove. This suggest a multidimensional approach to the detection of phishings focused on a quick detection mechanism through deep learning to overcome these limitations. The first step is to extract and use the character sequence features of the given URL for rapid classification through in-depth learning; this step does not include support from third parties or previous experience in phishing. It combine statistical URLs, web page code functions, website text features and easily categorise Profound learning in the second level on multidimensional functions. By the approach, the detection time of the threshold is shortened. The experimental results show that a rational adjustment of the threshold allows for the efficiency of the detection.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"36 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125725828","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 : 2020-11-05DOI: 10.1109/ICECA49313.2020.9297545
Nagaraj N. Bhat, K. V. Archana Hebbar, Sachin S. Bhat, Jayalakshmi, Pooja, D. Harshitha
This exhibits multilabel classification and segmentation of remote sensing satellite images through the deep learning framework. Here, the proposed methodology uses multi labelled Land-Mercede dataset and satellite images to perform the classification. The images obtained through satellite are first preprocessed by perfroming the operations like resizing and spatial blurring. In the next step, it performs the classification to classify each object based on the classes trained and finally segmentation is carried out to detect the changes at a particular place in a different time period. This method has achieved an overall classification accuracy of about 98.58% on a test set and least validation loss of 0.0001468 was also achieved by using a proposed model. The result of this approach can be used for more practical applications like urban planning and also to identify illegal activities that take place in restricted areas, forest, etc.. One of the main applications considered here will help to detect changes that happen in land change over time.
{"title":"Multilabel Spatial Image Recognition using Deep Convolutional Neural Network","authors":"Nagaraj N. Bhat, K. V. Archana Hebbar, Sachin S. Bhat, Jayalakshmi, Pooja, D. Harshitha","doi":"10.1109/ICECA49313.2020.9297545","DOIUrl":"https://doi.org/10.1109/ICECA49313.2020.9297545","url":null,"abstract":"This exhibits multilabel classification and segmentation of remote sensing satellite images through the deep learning framework. Here, the proposed methodology uses multi labelled Land-Mercede dataset and satellite images to perform the classification. The images obtained through satellite are first preprocessed by perfroming the operations like resizing and spatial blurring. In the next step, it performs the classification to classify each object based on the classes trained and finally segmentation is carried out to detect the changes at a particular place in a different time period. This method has achieved an overall classification accuracy of about 98.58% on a test set and least validation loss of 0.0001468 was also achieved by using a proposed model. The result of this approach can be used for more practical applications like urban planning and also to identify illegal activities that take place in restricted areas, forest, etc.. One of the main applications considered here will help to detect changes that happen in land change over time.","PeriodicalId":297285,"journal":{"name":"2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125809288","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：