Pub Date : 2020-06-05DOI: 10.1109/TENSYMP50017.2020.9231032
Mohammad Rejwan Uddin, Khan Farhan Ibne Faruque, Palash Das, K. M. Salim
Easy bikes or electric auto-rickshaws are the foremost commonly used electric vehicle in Bangladesh. Mainly, iron core transformer-based bulky chargers with an efficiency of up to 75% are employed to charge quite 1 million easy bikes daily without any smart controls. Implementation of power electronics-based charger ready to operate in additional than 90% efficiency which might reduce the power losses from the utility grid. A high capacity synchronous buck converter based charger with automated charging current controlling topology is proposed during this paper. A high-frequency system makes the circuit compact and light-weight. After the simulation by using PROTEUS software, a light-weight prototype of a straightforward bike charger is build and its performance is evaluated. The efficiency and its maximum rated power are observed and compared with the typical charger.
{"title":"An Alternative PWM Controlled High Efficient Solution for 60V Electric Vehicle Charging System to Replace Typical Iron Core Charger: Technical Performance Assessment and Comparison of Efficiency","authors":"Mohammad Rejwan Uddin, Khan Farhan Ibne Faruque, Palash Das, K. M. Salim","doi":"10.1109/TENSYMP50017.2020.9231032","DOIUrl":"https://doi.org/10.1109/TENSYMP50017.2020.9231032","url":null,"abstract":"Easy bikes or electric auto-rickshaws are the foremost commonly used electric vehicle in Bangladesh. Mainly, iron core transformer-based bulky chargers with an efficiency of up to 75% are employed to charge quite 1 million easy bikes daily without any smart controls. Implementation of power electronics-based charger ready to operate in additional than 90% efficiency which might reduce the power losses from the utility grid. A high capacity synchronous buck converter based charger with automated charging current controlling topology is proposed during this paper. A high-frequency system makes the circuit compact and light-weight. After the simulation by using PROTEUS software, a light-weight prototype of a straightforward bike charger is build and its performance is evaluated. The efficiency and its maximum rated power are observed and compared with the typical charger.","PeriodicalId":6721,"journal":{"name":"2020 IEEE Region 10 Symposium (TENSYMP)","volume":"9 1","pages":"312-315"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89210270","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 : 2020-06-05DOI: 10.1109/TENSYMP50017.2020.9230918
Ahmed Hasin Neehal, Md. Nur E Azam, Md. Sazzadul Islam, Md. Ishrak Hossain, M. Parvez
Parkinson's disease is the second most common neurodegenerative disorder after Alzheimer's disease. Almost 10 million people are estimated to have the disorder of Parkinson's disease. However, Parkinson's symptoms appear gradually and get worse over time. Therefore, the detection of Parkinson's disease at an early stage might significantly improve lifestyle by giving proper treatment. In recent years, the use of Functional Imaging in neurodegenerative diseases has increased. As Functional Imaging seems very efficient in the case of brain disorders, we used Functional Magnetic Resonance Imaging (fMRI) data for conducting our research. Furthermore, SVM classifier was used for the classification and prediction of Parkinson's disease. Using our proposed method, we have achieved 100% sensitivity, specificity, and accuracy considering seven subjects. However, one subject was exceptional whereas we have achieved 99.76% accuracy, 100% specificity, and 99.53% sensitivity. Finally, this process is a well-structured model for predicting the early stages of PD. It may help the doctors for diagnosis of the disease at its early stages and the patients should receive better treatment.
{"title":"Prediction of Parkinson's Disease by Analyzing fMRI Data and using Supervised Learning","authors":"Ahmed Hasin Neehal, Md. Nur E Azam, Md. Sazzadul Islam, Md. Ishrak Hossain, M. Parvez","doi":"10.1109/TENSYMP50017.2020.9230918","DOIUrl":"https://doi.org/10.1109/TENSYMP50017.2020.9230918","url":null,"abstract":"Parkinson's disease is the second most common neurodegenerative disorder after Alzheimer's disease. Almost 10 million people are estimated to have the disorder of Parkinson's disease. However, Parkinson's symptoms appear gradually and get worse over time. Therefore, the detection of Parkinson's disease at an early stage might significantly improve lifestyle by giving proper treatment. In recent years, the use of Functional Imaging in neurodegenerative diseases has increased. As Functional Imaging seems very efficient in the case of brain disorders, we used Functional Magnetic Resonance Imaging (fMRI) data for conducting our research. Furthermore, SVM classifier was used for the classification and prediction of Parkinson's disease. Using our proposed method, we have achieved 100% sensitivity, specificity, and accuracy considering seven subjects. However, one subject was exceptional whereas we have achieved 99.76% accuracy, 100% specificity, and 99.53% sensitivity. Finally, this process is a well-structured model for predicting the early stages of PD. It may help the doctors for diagnosis of the disease at its early stages and the patients should receive better treatment.","PeriodicalId":6721,"journal":{"name":"2020 IEEE Region 10 Symposium (TENSYMP)","volume":"89 25","pages":"362-365"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91406978","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 : 2020-06-05DOI: 10.1109/TENSYMP50017.2020.9230984
M. T. Masud, Nazarekh Rahman, Ashraful Alam, M. Griffiths, Mohammad Alamin
The number of people suffering with mental health disorders is rapidly increasing in recent years and it is very common with individuals who like to live alone and escape social meetings. Amongst various kinds of mental health disorders, depression is very common and serious one. In this paper, we propose a method to assess the depression level of an individual using smartphone by monitoring their daily activities. Smartphone time domain acceleration and gyroscope sensor filtered data were used in LSTM-RNN model to classify four physical activities (i.e., resting, exercising, running, walking) Additionally, the geographical location data was clustered to simplify movement activities. Subsequently, from participant activities, ten features were extracted that corresponded with their weekly reported questionnaire (QIDS-16) depression score. Features were used in the regression model to estimate the participant QIDS score. Among all the features, a subset that showed promising relationship with depressive symptom severity was selected using the wrapper feature selection method. Afterwards, these selected subset features were applied in both linear regression model and quadratic discriminant analysis classifier to estimate depression score as well as depression severity level. Regression model for score estimation showed the error rate of root mean square deviation is 3.117. On the other hand, for depression level classification selected quadratic discriminant analysis classifier method had an accuracy of 92%. This identification system appears to be a cost-effective solution that can be used for long-term and can monitor depressed individuals without invading their personal space or creating any disturbance.
{"title":"Non-Pervasive Monitoring of Daily-Life Behavior to Access Depressive Symptom Severity Via Smartphone Technology","authors":"M. T. Masud, Nazarekh Rahman, Ashraful Alam, M. Griffiths, Mohammad Alamin","doi":"10.1109/TENSYMP50017.2020.9230984","DOIUrl":"https://doi.org/10.1109/TENSYMP50017.2020.9230984","url":null,"abstract":"The number of people suffering with mental health disorders is rapidly increasing in recent years and it is very common with individuals who like to live alone and escape social meetings. Amongst various kinds of mental health disorders, depression is very common and serious one. In this paper, we propose a method to assess the depression level of an individual using smartphone by monitoring their daily activities. Smartphone time domain acceleration and gyroscope sensor filtered data were used in LSTM-RNN model to classify four physical activities (i.e., resting, exercising, running, walking) Additionally, the geographical location data was clustered to simplify movement activities. Subsequently, from participant activities, ten features were extracted that corresponded with their weekly reported questionnaire (QIDS-16) depression score. Features were used in the regression model to estimate the participant QIDS score. Among all the features, a subset that showed promising relationship with depressive symptom severity was selected using the wrapper feature selection method. Afterwards, these selected subset features were applied in both linear regression model and quadratic discriminant analysis classifier to estimate depression score as well as depression severity level. Regression model for score estimation showed the error rate of root mean square deviation is 3.117. On the other hand, for depression level classification selected quadratic discriminant analysis classifier method had an accuracy of 92%. This identification system appears to be a cost-effective solution that can be used for long-term and can monitor depressed individuals without invading their personal space or creating any disturbance.","PeriodicalId":6721,"journal":{"name":"2020 IEEE Region 10 Symposium (TENSYMP)","volume":"125 1","pages":"602-607"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83721796","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 : 2020-06-05DOI: 10.1109/TENSYMP50017.2020.9230895
K. Lakshika, M. K. Perera, W. D. Prasad, K. Hemapala, V. Saravanan, M. Arumugam
This paper proposes a reconfigurable architecture for residential microgrid (MG). The distinct feature of the residential MG is the power architecture which is developed using Z-source inverter (ZSI) for solar photovoltaic (PV) system and it can be reconfigured to current controlling mode and voltage-frequency controlling mode as well as reactive power controlling mode when solar system is idle. Hence, it improves the utilization factor of solar PV system and contributes to maintain the power quality in distribution feeder, while providing an uninterrupted power supply to the customer. The proposed architecture is developed in four stages. As the first stage, current controlling mode with MPPT is developed in MATLAB/Simulink environment and results are discussed in this paper.
{"title":"Z-Source Inverter based reconfigurable architecture for solar photovoltaic microgrid","authors":"K. Lakshika, M. K. Perera, W. D. Prasad, K. Hemapala, V. Saravanan, M. Arumugam","doi":"10.1109/TENSYMP50017.2020.9230895","DOIUrl":"https://doi.org/10.1109/TENSYMP50017.2020.9230895","url":null,"abstract":"This paper proposes a reconfigurable architecture for residential microgrid (MG). The distinct feature of the residential MG is the power architecture which is developed using Z-source inverter (ZSI) for solar photovoltaic (PV) system and it can be reconfigured to current controlling mode and voltage-frequency controlling mode as well as reactive power controlling mode when solar system is idle. Hence, it improves the utilization factor of solar PV system and contributes to maintain the power quality in distribution feeder, while providing an uninterrupted power supply to the customer. The proposed architecture is developed in four stages. As the first stage, current controlling mode with MPPT is developed in MATLAB/Simulink environment and results are discussed in this paper.","PeriodicalId":6721,"journal":{"name":"2020 IEEE Region 10 Symposium (TENSYMP)","volume":"71 1","pages":"1543-1546"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83723026","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 : 2020-06-05DOI: 10.1109/TENSYMP50017.2020.9231007
S. M. Taslim Uddin Raju, Md Shamimur Rahman
Erroneous data can cause a system to be failed. Though there are several methods for detection and correction, with the increasing amount of errors, it becomes difficult, for both detection, and correction of these erroneous codes. For solving these issues, this paper represents an effective method for solving multiple errors by using Horizontal-Vertical-SuperQueen (HVSQ) parity bits in code. It works with 121 data bits and 44 parity bits. And this method has a higher correction rate with less code overhead and higher code-rate. For these 121 bits of data, we need only 44 redundant bits which, indicate 36.36% of bit overhead and can solve up to 3 bit of errors. It also shows better accuracy in the increased number of errors in data bits.
{"title":"Horizontal Vertical and SuperQueen Parity (HVSQ) Method for Soft Error Tolerance","authors":"S. M. Taslim Uddin Raju, Md Shamimur Rahman","doi":"10.1109/TENSYMP50017.2020.9231007","DOIUrl":"https://doi.org/10.1109/TENSYMP50017.2020.9231007","url":null,"abstract":"Erroneous data can cause a system to be failed. Though there are several methods for detection and correction, with the increasing amount of errors, it becomes difficult, for both detection, and correction of these erroneous codes. For solving these issues, this paper represents an effective method for solving multiple errors by using Horizontal-Vertical-SuperQueen (HVSQ) parity bits in code. It works with 121 data bits and 44 parity bits. And this method has a higher correction rate with less code overhead and higher code-rate. For these 121 bits of data, we need only 44 redundant bits which, indicate 36.36% of bit overhead and can solve up to 3 bit of errors. It also shows better accuracy in the increased number of errors in data bits.","PeriodicalId":6721,"journal":{"name":"2020 IEEE Region 10 Symposium (TENSYMP)","volume":"55 1","pages":"1734-1737"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83363076","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 : 2020-06-05DOI: 10.1109/TENSYMP50017.2020.9230711
Md. Farhamdur Reza, Md. Selim Hossain, M. Rashid
The performance of Uniform Concentric Circular Array (UCCA) by adopting robust technique is analyzed in this paper. The inter-element spacing and the interring spacing this UCCA structure is kept uniformly as half wavelength. UCCA is chosen because of its circular structure and it has the ability to scan the desired signal from 0° to 360°. If there is any mismatch between actual signal and steering directions, the performance of Minimum Variance Distortion-less Response (MVDR) will degrade will degrade. Different loading techniques can resolve the problem for mismatch and make the system robust enough to receive the anticipated signal in the presence of inequality between actual and steering direction. A New Variable Loading (NVL) based UCCA beamformer is proposed in this work and compared the performance with existing loading technique-based UCCA beamformers. It is observed that the proposed UCCA beamformer exhibits better interference attenuation capability and offers better robustness against mismatch compared to the existing beamformers. The performance of proposed NVL based beamformer is analyzed using MATLAB software.
{"title":"Performance Study of NVL Technique Based Robust Uniform Concentric Circular Array Beamformer under Mismatch Condition","authors":"Md. Farhamdur Reza, Md. Selim Hossain, M. Rashid","doi":"10.1109/TENSYMP50017.2020.9230711","DOIUrl":"https://doi.org/10.1109/TENSYMP50017.2020.9230711","url":null,"abstract":"The performance of Uniform Concentric Circular Array (UCCA) by adopting robust technique is analyzed in this paper. The inter-element spacing and the interring spacing this UCCA structure is kept uniformly as half wavelength. UCCA is chosen because of its circular structure and it has the ability to scan the desired signal from 0° to 360°. If there is any mismatch between actual signal and steering directions, the performance of Minimum Variance Distortion-less Response (MVDR) will degrade will degrade. Different loading techniques can resolve the problem for mismatch and make the system robust enough to receive the anticipated signal in the presence of inequality between actual and steering direction. A New Variable Loading (NVL) based UCCA beamformer is proposed in this work and compared the performance with existing loading technique-based UCCA beamformers. It is observed that the proposed UCCA beamformer exhibits better interference attenuation capability and offers better robustness against mismatch compared to the existing beamformers. The performance of proposed NVL based beamformer is analyzed using MATLAB software.","PeriodicalId":6721,"journal":{"name":"2020 IEEE Region 10 Symposium (TENSYMP)","volume":"10 1","pages":"953-956"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81054538","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 : 2020-06-05DOI: 10.1109/TENSYMP50017.2020.9230692
Md. Sohel Rana, Rifah Sanjida Prodhan, Md. Nayemul Hasan
With the expanding demand of energy worldwide, an extreme shortage and inflation of the non- renewable energy resources will be observed in near future. Therefore, before the crucial stage comes up, all the countries of the world are trying their level best to replace fossil fuels with renewable energy resources as the main sources of generating electricity. Solar energy is one of the most effectual resources of renewable energy, which can play a significant role to solve energy crisis. By tracking the movement of sun, photovoltaic panel can be positioned in such a way that it can collect maximum amount of solar radiation. Trackers generate more electricity than conventional static solar panels due to increased direct exposure to solar rays and can be up to 25% more efficient than their static counterparts. While tracking sun, the dual axis solar trackers provide better efficiency as they allow for two degrees of flexibility, offering a much wider range of motion. This paper presents the design and construction of a self-powered automatic dual axis solar tracking and positioning system. It can execute both front tracking and back tracking operation without any manual help and provide a high degree of accuracy without any requirement of GPS or computers. The design requires no supplemental power supply which means it will be self-powered which will reduce any extra operational costs. A small prototype is also constructed to implement the design methodology presented here.
{"title":"Self Powered Automatic Dual Axis Tracking and Positioning System Design","authors":"Md. Sohel Rana, Rifah Sanjida Prodhan, Md. Nayemul Hasan","doi":"10.1109/TENSYMP50017.2020.9230692","DOIUrl":"https://doi.org/10.1109/TENSYMP50017.2020.9230692","url":null,"abstract":"With the expanding demand of energy worldwide, an extreme shortage and inflation of the non- renewable energy resources will be observed in near future. Therefore, before the crucial stage comes up, all the countries of the world are trying their level best to replace fossil fuels with renewable energy resources as the main sources of generating electricity. Solar energy is one of the most effectual resources of renewable energy, which can play a significant role to solve energy crisis. By tracking the movement of sun, photovoltaic panel can be positioned in such a way that it can collect maximum amount of solar radiation. Trackers generate more electricity than conventional static solar panels due to increased direct exposure to solar rays and can be up to 25% more efficient than their static counterparts. While tracking sun, the dual axis solar trackers provide better efficiency as they allow for two degrees of flexibility, offering a much wider range of motion. This paper presents the design and construction of a self-powered automatic dual axis solar tracking and positioning system. It can execute both front tracking and back tracking operation without any manual help and provide a high degree of accuracy without any requirement of GPS or computers. The design requires no supplemental power supply which means it will be self-powered which will reduce any extra operational costs. A small prototype is also constructed to implement the design methodology presented here.","PeriodicalId":6721,"journal":{"name":"2020 IEEE Region 10 Symposium (TENSYMP)","volume":"69 1","pages":"166-169"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80618179","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 : 2020-06-05DOI: 10.1109/TENSYMP50017.2020.9230974
Md. Ahsan Habib Raj, Md. Al Mamun, Md. Farukuzzaman Faruk
One of the most diabetes complication is Diabetic Retinopathy (DR) that causes major loss of vision or blindness. In present day medical science, estimation of images has become key instrument for exact identification of disease. So we have designed a computational model for predicting Diabetic Retinopathy (DR) status which is based on retinal image and neural network. Our computational model has been consisting of a feature extraction phase and a classification phase. In feature extraction phase we have extracted the most appropriate features from digital fundus images by Blood Vessels and Micro aneurysms detection. For this research work we have used Diabetic Retinopathy dataset provided by Kaggle Community. Finally, we have used CNN to predict the Diabetic Retinopathy (DR). In our proposed methodology, we have achieved 95.41% accuracy.
{"title":"CNN Based Diabetic Retinopathy Status Prediction Using Fundus Images","authors":"Md. Ahsan Habib Raj, Md. Al Mamun, Md. Farukuzzaman Faruk","doi":"10.1109/TENSYMP50017.2020.9230974","DOIUrl":"https://doi.org/10.1109/TENSYMP50017.2020.9230974","url":null,"abstract":"One of the most diabetes complication is Diabetic Retinopathy (DR) that causes major loss of vision or blindness. In present day medical science, estimation of images has become key instrument for exact identification of disease. So we have designed a computational model for predicting Diabetic Retinopathy (DR) status which is based on retinal image and neural network. Our computational model has been consisting of a feature extraction phase and a classification phase. In feature extraction phase we have extracted the most appropriate features from digital fundus images by Blood Vessels and Micro aneurysms detection. For this research work we have used Diabetic Retinopathy dataset provided by Kaggle Community. Finally, we have used CNN to predict the Diabetic Retinopathy (DR). In our proposed methodology, we have achieved 95.41% accuracy.","PeriodicalId":6721,"journal":{"name":"2020 IEEE Region 10 Symposium (TENSYMP)","volume":"75 1","pages":"190-193"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90826905","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 : 2020-06-05DOI: 10.1109/TENSYMP50017.2020.9231046
M. Mishra, S. Chaudhuri, R. S. Kshetrimayum
A low mutually coupled four-port MIMO antenna design for 3.5 GHz WiMAX application is presented in this article. This array consists of four monopole antennas interconnected with a neutralization line network. Using the S-parameters and surface current plots, the working mechanism of antenna array is explained. The -10 dB impedance bandwidth ranges from 3.37 GHz to 3.61 GHz. The combination of the neutralization line network and the H-shaped periodic structures along with a grounded rectangular loop reduces the mutual coupling by 7.5 dB within the operating frequency range and is found to be ≤ -17.5 dB. Envelope correlation coefficient is noted to be less than 0.1 and gain is noted to be between 2.71 dBi and 2.83 dBi.
{"title":"Low Mutual Coupling Four-Port MIMO Antenna Array for 3.5 GHz WiMAX Application","authors":"M. Mishra, S. Chaudhuri, R. S. Kshetrimayum","doi":"10.1109/TENSYMP50017.2020.9231046","DOIUrl":"https://doi.org/10.1109/TENSYMP50017.2020.9231046","url":null,"abstract":"A low mutually coupled four-port MIMO antenna design for 3.5 GHz WiMAX application is presented in this article. This array consists of four monopole antennas interconnected with a neutralization line network. Using the S-parameters and surface current plots, the working mechanism of antenna array is explained. The -10 dB impedance bandwidth ranges from 3.37 GHz to 3.61 GHz. The combination of the neutralization line network and the H-shaped periodic structures along with a grounded rectangular loop reduces the mutual coupling by 7.5 dB within the operating frequency range and is found to be ≤ -17.5 dB. Envelope correlation coefficient is noted to be less than 0.1 and gain is noted to be between 2.71 dBi and 2.83 dBi.","PeriodicalId":6721,"journal":{"name":"2020 IEEE Region 10 Symposium (TENSYMP)","volume":"10 1","pages":"791-794"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91146638","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 : 2020-06-05DOI: 10.1109/TENSYMP50017.2020.9230817
Arifa I. Champa, Md. Atikur Rahman, S. M. Mahedy Hasan, Md. Fazle Rabbi
Researchers have found profound interest in the field ‘hyperspectral imaging’ as it has numerous applications. However, the center of motivation for this task has been the immense practice of hyperspectral imaging in ground cover classification problem. But, the high dimensionality of hyperspectral images (HSI) appears to be a menace for researchers. Unprecedented feasible solution to this crux is reduction of dimensionality. Therefore, a hybrid technique has been proposed for dimensionality reduction by combining feature extraction method with feature selection method. Here, Principal Component Analysis (PCA), a renowned technique, has been utilized for feature extraction. Thenceforth, three feature selection methods named Mutual Information (MI), normalized Mutual Information (nMI) and Quadratic Mutual Information (qMI) have been chosen for selecting features from the extracted features. Subsequently, the data have been fed to Support Vector Machine (SVM). SVM is implemented using Kernel trick which we are calling Kernel SVM.
{"title":"Hybrid Technique for Classification of Hyperspectral Image Using Quadratic Mutual Information","authors":"Arifa I. Champa, Md. Atikur Rahman, S. M. Mahedy Hasan, Md. Fazle Rabbi","doi":"10.1109/TENSYMP50017.2020.9230817","DOIUrl":"https://doi.org/10.1109/TENSYMP50017.2020.9230817","url":null,"abstract":"Researchers have found profound interest in the field ‘hyperspectral imaging’ as it has numerous applications. However, the center of motivation for this task has been the immense practice of hyperspectral imaging in ground cover classification problem. But, the high dimensionality of hyperspectral images (HSI) appears to be a menace for researchers. Unprecedented feasible solution to this crux is reduction of dimensionality. Therefore, a hybrid technique has been proposed for dimensionality reduction by combining feature extraction method with feature selection method. Here, Principal Component Analysis (PCA), a renowned technique, has been utilized for feature extraction. Thenceforth, three feature selection methods named Mutual Information (MI), normalized Mutual Information (nMI) and Quadratic Mutual Information (qMI) have been chosen for selecting features from the extracted features. Subsequently, the data have been fed to Support Vector Machine (SVM). SVM is implemented using Kernel trick which we are calling Kernel SVM.","PeriodicalId":6721,"journal":{"name":"2020 IEEE Region 10 Symposium (TENSYMP)","volume":"45 1","pages":"933-936"},"PeriodicalIF":0.0,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90401148","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：