Pub Date : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514202
Ashhadul Islam, S. Belhaouari
In this work, a modified operation of Auto Encoder has been proposed to generate better features from the input data. General autoencoders work unsupervised and learn features using the input data as a reference for output. In our method of training autoencoders, we include the class labels into the reference data so as to gear the learning of the autoencoder towards the reference data as well as the specific class it belongs to. This ensures that the features learned are representations of individual data points as well as the corresponding class. The efficacy of our method is measured by comparing the accuracy of classifiers trained on features extracted by our models from the MNIST dataset, the CIFAR-10 dataset, and the UTKFace dataset. Features extracted by our brand of autoencoders enable classifiers to obtain higher accuracy in comparison to the same classifiers trained on features extracted by traditional autoen-coders.
{"title":"Class Aware Auto Encoders for Better Feature Extraction","authors":"Ashhadul Islam, S. Belhaouari","doi":"10.1109/ICECCE52056.2021.9514202","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514202","url":null,"abstract":"In this work, a modified operation of Auto Encoder has been proposed to generate better features from the input data. General autoencoders work unsupervised and learn features using the input data as a reference for output. In our method of training autoencoders, we include the class labels into the reference data so as to gear the learning of the autoencoder towards the reference data as well as the specific class it belongs to. This ensures that the features learned are representations of individual data points as well as the corresponding class. The efficacy of our method is measured by comparing the accuracy of classifiers trained on features extracted by our models from the MNIST dataset, the CIFAR-10 dataset, and the UTKFace dataset. Features extracted by our brand of autoencoders enable classifiers to obtain higher accuracy in comparison to the same classifiers trained on features extracted by traditional autoen-coders.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131973440","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514212
Aisha Zahid Junejo, Manzoor Ahmed Hashmani, Abdullah Abdulrehman Alabdulatif
The increasing awareness of the Blockchain technology has gained interest of researchers and industrialists in recent years, hence several business enterprises are keen on using blockchain technology for their day-to-day transactions and record keeping. However, due to public availability of data on the blockchain, it is not advisable for organizations dealing with sensitive and confidential data to risk their data privacy by using blockchain networks. In this study we talk about privacy vulnerabilities and challenges in blockchain based applications. We verify the extent of the problem by both, literary findings, and empirical analyses. Next, we propose a conceptual framework to strengthen privacy preservation of the blockchain networks. The proposed framework is based on the idea of limiting the number of nodes that a transaction is broadcast to, for verification. The selected nodes will differ for each transaction, decreasing the possibilities of network listening and deanonymization of users. Moreover, limiting the number of verifying nodes will result in drastic reduction of computation overhead of the network, along with improved scalability. The proposed framework is analyzed based on various privacy features and risks. The evaluation results show that the model has a privacy rank of 0.76.
{"title":"Blockchain Privacy Preservation by Limiting Verifying Nodes' During Transaction Broadcasting","authors":"Aisha Zahid Junejo, Manzoor Ahmed Hashmani, Abdullah Abdulrehman Alabdulatif","doi":"10.1109/ICECCE52056.2021.9514212","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514212","url":null,"abstract":"The increasing awareness of the Blockchain technology has gained interest of researchers and industrialists in recent years, hence several business enterprises are keen on using blockchain technology for their day-to-day transactions and record keeping. However, due to public availability of data on the blockchain, it is not advisable for organizations dealing with sensitive and confidential data to risk their data privacy by using blockchain networks. In this study we talk about privacy vulnerabilities and challenges in blockchain based applications. We verify the extent of the problem by both, literary findings, and empirical analyses. Next, we propose a conceptual framework to strengthen privacy preservation of the blockchain networks. The proposed framework is based on the idea of limiting the number of nodes that a transaction is broadcast to, for verification. The selected nodes will differ for each transaction, decreasing the possibilities of network listening and deanonymization of users. Moreover, limiting the number of verifying nodes will result in drastic reduction of computation overhead of the network, along with improved scalability. The proposed framework is analyzed based on various privacy features and risks. The evaluation results show that the model has a privacy rank of 0.76.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132302847","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514264
Nor'asnilawati Salleh, Nurulhuda Firdaus Mohd Azmi, S. Yuhaniz
The orbit propagation model is used to predict the position and velocity of the satellites. It is crucial to obtain accurate predictions to ensure that satellite operation planning is in place and detects any possible disasters. However, the model's accuracy decreases as the propagation span increases if the input data are not updated. Therefore, to minimize these errors while still maintaining the model accuracy, a study is conducted. The Simplified General Perturbations-4 (SGP4) model and two-line elements (TLE) data are selected to perform this study. The problem is analyzed, and the deep learning technique is the proposed method to solve the issue. Next, the enhanced model is validated. The study aims to produce a reliable orbit propagation model and assist the satellite's operational planning. Also, the improved model can provide vital information for space-based organizations and anyone who may be affected.
{"title":"An Adaptation of Deep Learning Technique In Orbit Propagation Model Using Long Short-Term Memory","authors":"Nor'asnilawati Salleh, Nurulhuda Firdaus Mohd Azmi, S. Yuhaniz","doi":"10.1109/ICECCE52056.2021.9514264","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514264","url":null,"abstract":"The orbit propagation model is used to predict the position and velocity of the satellites. It is crucial to obtain accurate predictions to ensure that satellite operation planning is in place and detects any possible disasters. However, the model's accuracy decreases as the propagation span increases if the input data are not updated. Therefore, to minimize these errors while still maintaining the model accuracy, a study is conducted. The Simplified General Perturbations-4 (SGP4) model and two-line elements (TLE) data are selected to perform this study. The problem is analyzed, and the deep learning technique is the proposed method to solve the issue. Next, the enhanced model is validated. The study aims to produce a reliable orbit propagation model and assist the satellite's operational planning. Also, the improved model can provide vital information for space-based organizations and anyone who may be affected.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"507 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134422106","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514114
G. Bonifazi, G. Capobianco, R. Gasbarrone, S. Serranti
Pasta is widely used in many cuisines all around the world for its important nutritional properties. The quality assurance and the maintenance of the cold chain of pre-cooked pasta products have a significant impact in economic terms on the manufacturing companies. For this reason, a fast, reliable, not-destructive and non-invasive method is needed to fulfill the above-mentioned goals. Visible and Near InfraRed spectroscopy, coupled with chemometric analysis, are powerful tools that can make the production and supply of pre-cooked pasta more transparent, also reducing food waste. In this study, a spectrophotoradiometer operating in the Visible - Short Wave InfraRed (Vis-SWIR) range (350-2500 nm) was used to acquire reflectance spectra on pre-cooked pasta samples, with two levels of saltiness, produced in Italy and intended for the US market. Partial Least Squares - Discriminant Analysis (PLS-DA) classification models were calibrated and validated to recognize the samples according to their salting and physical conditions (i.e. frozen/thawed), starting from their spectral signatures. Classification performances showed promising ability in characterizing samples according to the previously mentioned attributes.
{"title":"Cold Chain Maintenance Evaluation of Pre-Cooked Pasta by Visible and Short Wave InfraRed Spectroscopy","authors":"G. Bonifazi, G. Capobianco, R. Gasbarrone, S. Serranti","doi":"10.1109/ICECCE52056.2021.9514114","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514114","url":null,"abstract":"Pasta is widely used in many cuisines all around the world for its important nutritional properties. The quality assurance and the maintenance of the cold chain of pre-cooked pasta products have a significant impact in economic terms on the manufacturing companies. For this reason, a fast, reliable, not-destructive and non-invasive method is needed to fulfill the above-mentioned goals. Visible and Near InfraRed spectroscopy, coupled with chemometric analysis, are powerful tools that can make the production and supply of pre-cooked pasta more transparent, also reducing food waste. In this study, a spectrophotoradiometer operating in the Visible - Short Wave InfraRed (Vis-SWIR) range (350-2500 nm) was used to acquire reflectance spectra on pre-cooked pasta samples, with two levels of saltiness, produced in Italy and intended for the US market. Partial Least Squares - Discriminant Analysis (PLS-DA) classification models were calibrated and validated to recognize the samples according to their salting and physical conditions (i.e. frozen/thawed), starting from their spectral signatures. Classification performances showed promising ability in characterizing samples according to the previously mentioned attributes.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133754839","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514195
Ida, Hamdan Gani, Muhammad Faisal, Rosnani
Corruption is a primary development challenge in Indonesia's economic and social field. In order to overcome these threats, Indonesia's government has been established the Corruption Eradication Commission (Komisi Pemberantasan Korupsi, abbreviated KPK). KPK's goal is to free Indonesia from corruption by investigating corruption cases and monitoring the governance process. KPK uses one effective method called “hand arrest operation”, abbreviated OTT, to handle corruption cases. However, the existing hand arrest operation that KPK used today is not always effective because, in real action, the KPK's official always overdue to find actual evidence of the communication between the suspect. Thus, there is a need for a rapid method to record the suspicious conversation or transaction voice between the suspect as actual evidence for a corruption case. Thus, this paper aims to propose a supporting tool for real-time hand arrest operations to support KPK officials in OTT action. The experimental results show that the proposed method can effectively record all the suspicious communication or transaction voices between the suspect in a scenario room. Finally, this study concluded that the proposed method is a promising way to help the work of KPK in OTT.
{"title":"Optimal Auto Calling Algorithm For Real-Time Condition Reporting By Corruption Handling Officer","authors":"Ida, Hamdan Gani, Muhammad Faisal, Rosnani","doi":"10.1109/ICECCE52056.2021.9514195","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514195","url":null,"abstract":"Corruption is a primary development challenge in Indonesia's economic and social field. In order to overcome these threats, Indonesia's government has been established the Corruption Eradication Commission (Komisi Pemberantasan Korupsi, abbreviated KPK). KPK's goal is to free Indonesia from corruption by investigating corruption cases and monitoring the governance process. KPK uses one effective method called “hand arrest operation”, abbreviated OTT, to handle corruption cases. However, the existing hand arrest operation that KPK used today is not always effective because, in real action, the KPK's official always overdue to find actual evidence of the communication between the suspect. Thus, there is a need for a rapid method to record the suspicious conversation or transaction voice between the suspect as actual evidence for a corruption case. Thus, this paper aims to propose a supporting tool for real-time hand arrest operations to support KPK officials in OTT action. The experimental results show that the proposed method can effectively record all the suspicious communication or transaction voices between the suspect in a scenario room. Finally, this study concluded that the proposed method is a promising way to help the work of KPK in OTT.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134520178","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514138
A. Demidovskij
The task of building hybrid decision support systems that combine symbolic and connectionist approaches is actual and challenging. In particular, decision support systems operate with symbolic structures that describe the problem situation, stakeholders, assessment criteria, etc. Integrating connectionist approaches into certain parts of the decision-making process bring robustness, fixed response speed and ability to generalize. This paper examines Neural Turing Machines - a special case of Memory-Augmented Neural Networks - and demonstrates that such an architecture can be integrated into the Decision Support Systems. It was also shown that Neural Turing Machine can solve arithmetic sum task for numbers represented as binary vectors of length 10.
{"title":"Exploring Neural Turing Machines Applicability in Neural-Symbolic Decision Support Systems","authors":"A. Demidovskij","doi":"10.1109/ICECCE52056.2021.9514138","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514138","url":null,"abstract":"The task of building hybrid decision support systems that combine symbolic and connectionist approaches is actual and challenging. In particular, decision support systems operate with symbolic structures that describe the problem situation, stakeholders, assessment criteria, etc. Integrating connectionist approaches into certain parts of the decision-making process bring robustness, fixed response speed and ability to generalize. This paper examines Neural Turing Machines - a special case of Memory-Augmented Neural Networks - and demonstrates that such an architecture can be integrated into the Decision Support Systems. It was also shown that Neural Turing Machine can solve arithmetic sum task for numbers represented as binary vectors of length 10.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133125178","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514225
Saman Saadizadeh
In recent years it has been noticed that early breast cancer detection can decrease death rates considerably and to pursue early detection, there is a need for advanced screening tool along with experts, among screening tools infrared camera in thermography is low cost, contactless and does not include vulnerable rays, so it can be a good alternative to the most common screening tool techniques like mammography which entails all of the mentioned limitations. This paper aims to introduce an architecture by which the computer automatically classifies the cases into the malignant, benign and normal using labeled Thermal breast images. To obtain our goal, Gray Level Run Length Matrix (GLRLM) algorithm for feature selection and Long Short-Term Memory (LSTM) as a classifier are utilized. We achieved near 100% accuracy result for the training process, and for testing, we are selecting eight trained images of a single patient and we get quite accurate outcome. This proposed method using thermal images is a completely non-invasive method for cancerous patients in comparison to other methods.
{"title":"Breast Cancer Detection in Thermal Images Using GLRLM Algorithm","authors":"Saman Saadizadeh","doi":"10.1109/ICECCE52056.2021.9514225","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514225","url":null,"abstract":"In recent years it has been noticed that early breast cancer detection can decrease death rates considerably and to pursue early detection, there is a need for advanced screening tool along with experts, among screening tools infrared camera in thermography is low cost, contactless and does not include vulnerable rays, so it can be a good alternative to the most common screening tool techniques like mammography which entails all of the mentioned limitations. This paper aims to introduce an architecture by which the computer automatically classifies the cases into the malignant, benign and normal using labeled Thermal breast images. To obtain our goal, Gray Level Run Length Matrix (GLRLM) algorithm for feature selection and Long Short-Term Memory (LSTM) as a classifier are utilized. We achieved near 100% accuracy result for the training process, and for testing, we are selecting eight trained images of a single patient and we get quite accurate outcome. This proposed method using thermal images is a completely non-invasive method for cancerous patients in comparison to other methods.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126962423","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514137
I. Ostheimer, M. Hercog, Bojan Bijelić, D. Vranješ
This paper introductory presents a multi agent system model that uses blockchain as the basic technology for successful integration of advanced management solutions into a smart grid environment, realized through the SEGIP project. The paper explains the need for innovative management solutions and provides an overview of energy exchange based on peer-to-peer trading. Additionally, the paper covers the role of a multi-agent system in effective integration and outlines the structure of the proposed project solution. The functioning of such a smart grid is explained through a description of the roles and interactions of different actors, and a smart contract proposal is described through an example of a transaction between different types of network nodes. The conclusion completes everything presented in the paper and confirms the validity of the presented approach.
{"title":"Efficient Integration Model of MAS and Blockchain for emergence of Self-Organized Smart Grids","authors":"I. Ostheimer, M. Hercog, Bojan Bijelić, D. Vranješ","doi":"10.1109/ICECCE52056.2021.9514137","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514137","url":null,"abstract":"This paper introductory presents a multi agent system model that uses blockchain as the basic technology for successful integration of advanced management solutions into a smart grid environment, realized through the SEGIP project. The paper explains the need for innovative management solutions and provides an overview of energy exchange based on peer-to-peer trading. Additionally, the paper covers the role of a multi-agent system in effective integration and outlines the structure of the proposed project solution. The functioning of such a smart grid is explained through a description of the roles and interactions of different actors, and a smart contract proposal is described through an example of a transaction between different types of network nodes. The conclusion completes everything presented in the paper and confirms the validity of the presented approach.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116395969","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514208
Habib Conrad Sotiman Yotto, P. Chetangny, S. Houndedako, J. Aredjodoun, D. Chamagne, G. Barbier, A. Vianou
In order to help governments in energy development programming and also public service operators and network managers to have better planning for managing electricity demand and design better operational planning on production units and distribution networks, it is necessary to make the long-term, prediction, estimation and evaluation of the electrical load. The aim of this work is to propose the econometric model to estimate and forecast the electricity load in Benin for a long term, until 2030. It is important to notice that due to the complexity and multiple parameters considered for the forecasting, the use of single model will lack of accuracy and the results will not be conform to the reality. In this paper we propose an hybrid model ARIMA/GARCH, a non-linear model that combines a linear model of autoregressive integrated moving average (ARIMA) and a non-linear model, generalized autoregressive conditional heteroscedasticity (GARCH). This model is applied to obtain a non-linear relationship between load variation and determinants such as demographic change, gross domestic product GDP and weather parameters for an accurate demand forecasting.
{"title":"Estimation and Forecasting Electricity Load in Benin: Using Econometric Model ARIMA/GARCH","authors":"Habib Conrad Sotiman Yotto, P. Chetangny, S. Houndedako, J. Aredjodoun, D. Chamagne, G. Barbier, A. Vianou","doi":"10.1109/ICECCE52056.2021.9514208","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514208","url":null,"abstract":"In order to help governments in energy development programming and also public service operators and network managers to have better planning for managing electricity demand and design better operational planning on production units and distribution networks, it is necessary to make the long-term, prediction, estimation and evaluation of the electrical load. The aim of this work is to propose the econometric model to estimate and forecast the electricity load in Benin for a long term, until 2030. It is important to notice that due to the complexity and multiple parameters considered for the forecasting, the use of single model will lack of accuracy and the results will not be conform to the reality. In this paper we propose an hybrid model ARIMA/GARCH, a non-linear model that combines a linear model of autoregressive integrated moving average (ARIMA) and a non-linear model, generalized autoregressive conditional heteroscedasticity (GARCH). This model is applied to obtain a non-linear relationship between load variation and determinants such as demographic change, gross domestic product GDP and weather parameters for an accurate demand forecasting.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125545657","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 : 2021-06-12DOI: 10.1109/ICECCE52056.2021.9514254
Maria Murad, A. Jalil, Muhammad Bilal, Shahid Ikram, Ahmad Ali, Khizer Mehmeed, Baber Khan
Magnetic Resonance Imaging (MRI) is used to produce detailed images of body tissues and organs using strong magnets and radio waves, but with a very slow acquisition process. Compressed Sensing (CS) has efficiently accelerated the MRI acquisition process by employing different reconstruction strategies using a fraction of the Nyquist samples. This scan time can be further reduced using a new technique called interpolated compressed sensing (iCS) by exploiting the inter-slice correlation of multi-slice MRI. In this paper, a modified fast interpolated compressed sensing (Mod-FiCS) technique is proposed using the Gaussian-Radial under-sampling scheme. The Gaussian-Radial under-sampling approach adopted by Mod-FiCS has an edge that it neither shows any streaking artifacts like Radial nor blurred edges like Gaussian. The new interpolation approach used in Mod-FiCS technique uses three consecutive slices to estimate the missing samples. Six evaluation metrics are used to analyze the performance of the proposed technique such as structural similarity index measurement (SSIM), feature similarity index measurement (FSIM), mean square error (MSE), peak signal to noise ratio (PSNR), correlation (CORR), and sharpness index (SI), and compared with recent sampling and interpolation techniques. The simulation result shows that the proposed technique has improvement both quantitatively and qualitatively.
{"title":"Gaussian-Radial Under-Sampling Based CSMRI Reconstruction using a Modified Interpolation Approach","authors":"Maria Murad, A. Jalil, Muhammad Bilal, Shahid Ikram, Ahmad Ali, Khizer Mehmeed, Baber Khan","doi":"10.1109/ICECCE52056.2021.9514254","DOIUrl":"https://doi.org/10.1109/ICECCE52056.2021.9514254","url":null,"abstract":"Magnetic Resonance Imaging (MRI) is used to produce detailed images of body tissues and organs using strong magnets and radio waves, but with a very slow acquisition process. Compressed Sensing (CS) has efficiently accelerated the MRI acquisition process by employing different reconstruction strategies using a fraction of the Nyquist samples. This scan time can be further reduced using a new technique called interpolated compressed sensing (iCS) by exploiting the inter-slice correlation of multi-slice MRI. In this paper, a modified fast interpolated compressed sensing (Mod-FiCS) technique is proposed using the Gaussian-Radial under-sampling scheme. The Gaussian-Radial under-sampling approach adopted by Mod-FiCS has an edge that it neither shows any streaking artifacts like Radial nor blurred edges like Gaussian. The new interpolation approach used in Mod-FiCS technique uses three consecutive slices to estimate the missing samples. Six evaluation metrics are used to analyze the performance of the proposed technique such as structural similarity index measurement (SSIM), feature similarity index measurement (FSIM), mean square error (MSE), peak signal to noise ratio (PSNR), correlation (CORR), and sharpness index (SI), and compared with recent sampling and interpolation techniques. The simulation result shows that the proposed technique has improvement both quantitatively and qualitatively.","PeriodicalId":302947,"journal":{"name":"2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130169639","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：