Pub Date : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718944
P. Biswas, K. K. Halder
The primary concept of this paper is a fuzzy membership function-based filter with the expertise to reduce speckle noise that is often utilized in clinical diagnosis such as ultrasonography. In medical science, image sharpening is a highly effective approach for recognizing human inner organs and body tissues. Speckle noise is multiplicative in nature and it highly affects the image and reduces some useful information. The target of image noise reduction is to extract the genuine image from a noisy speckled image. In this paper, a Gaussian fuzzy-based system has been developed that is fast and provides good accuracy depending upon the membership function. Also, experimental results demonstrate that the proposed algorithm ensures better filtering quality and image restoration ability in comparison with others.
{"title":"Speckle Noise Reduction from Medical Images Using Gaussian Fuzzy Membership Function","authors":"P. Biswas, K. K. Halder","doi":"10.1109/ICEEE54059.2021.9718944","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718944","url":null,"abstract":"The primary concept of this paper is a fuzzy membership function-based filter with the expertise to reduce speckle noise that is often utilized in clinical diagnosis such as ultrasonography. In medical science, image sharpening is a highly effective approach for recognizing human inner organs and body tissues. Speckle noise is multiplicative in nature and it highly affects the image and reduces some useful information. The target of image noise reduction is to extract the genuine image from a noisy speckled image. In this paper, a Gaussian fuzzy-based system has been developed that is fast and provides good accuracy depending upon the membership function. Also, experimental results demonstrate that the proposed algorithm ensures better filtering quality and image restoration ability in comparison with others.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128197081","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718802
Tasnim Irtifa Chowdhury, M. Mowla
Recently, fifth generation (5G) wireless standard is entering into the implementation stage with some of the initial design concepts and ideas. The 5G standard triangle is designed for supporting enhanced mobile broadband, massive machine type communication, and ultra reliable communication for the users. One of the major inclusions of this design targets is to provide internet to the huge small devices with low power, Internet of Things (IoT). In this direction, 5G technology has started to ensure IoT connectivity for the next generation users. The single clustering approach does not ensure the high throughput with low block error rate. In this paper, we have used the facilities of 5G to design a novel multi-clustered 5G network for IoT applications. A systematic analysis of the network is performed using well-suited UMa (urban-macro), and UMa3D (urban-macro-3-dimensional) path-loss models, for femto cell (FC) and pico cell (PC) configurations. Our investigation shows the superior performances of signal-to-interference-noise ratio (SINR), and throughput for UMa3D and pico cell configuration than their counterpart. We also find stable throughput over a wide range of users for the same configuration through maintaining insignificant block error rate (BLER) difference. Therefore, the proposed network seems very promising for practical implementation.
{"title":"Design of a novel multi-clustered 5G network for IoT applications","authors":"Tasnim Irtifa Chowdhury, M. Mowla","doi":"10.1109/ICEEE54059.2021.9718802","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718802","url":null,"abstract":"Recently, fifth generation (5G) wireless standard is entering into the implementation stage with some of the initial design concepts and ideas. The 5G standard triangle is designed for supporting enhanced mobile broadband, massive machine type communication, and ultra reliable communication for the users. One of the major inclusions of this design targets is to provide internet to the huge small devices with low power, Internet of Things (IoT). In this direction, 5G technology has started to ensure IoT connectivity for the next generation users. The single clustering approach does not ensure the high throughput with low block error rate. In this paper, we have used the facilities of 5G to design a novel multi-clustered 5G network for IoT applications. A systematic analysis of the network is performed using well-suited UMa (urban-macro), and UMa3D (urban-macro-3-dimensional) path-loss models, for femto cell (FC) and pico cell (PC) configurations. Our investigation shows the superior performances of signal-to-interference-noise ratio (SINR), and throughput for UMa3D and pico cell configuration than their counterpart. We also find stable throughput over a wide range of users for the same configuration through maintaining insignificant block error rate (BLER) difference. Therefore, the proposed network seems very promising for practical implementation.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126561493","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718797
Shehan Irteza Pranto, Rahad Arman Nabid, Ahnaf Mozib Samin, Nabeel Mohammed, F. Sarker, M. N. Huda, K. Mamun
The research study presents an architecture of HumanRobot Interaction (HRI) based Artificial Conversational Entity integrated with speaker recognition ability to avail modern healthcare services. Due to the Covid-19 pandemic, the situation has become troublesome for health workers and patients to visit hospitals because of the high risk of virus dissemination. To minimize the mass congestion, our developed architecture would be an appropriate, cost-effective solution that automates the reception system by enabling AI-based HRI and providing fast and advanced healthcare services in the context of Bangladesh. The architecture consists of two significant subsections: Speaker Recognition and Artificial Conversational Entities having Automatic Speech Recognition in Bengali, Interactive Agent, and Text-to-Speech-synthesis. We used MFCC features as the linguistic parameters and the GMM statistical model to adapt each speaker’s voice and estimation and maximization algorithm to identify the speaker’s identity. The developed speaker recognition module performed significantly with 94.38% average accuracy in noisy environments and 96.27% average accuracy in studio quality environments and achieved a word error rate (WER) of 42.15% from RNN based Deep Speech 2 model for Bangla Automatic Speech Recognition (ASR). Besides, Artificial Conversational Entity performs with an average accuracy of 98.58% in a small-scale real-time environment.
{"title":"Human-Robot Interaction in Bengali language for Healthcare Automation integrated with Speaker Recognition and Artificial Conversational Entity","authors":"Shehan Irteza Pranto, Rahad Arman Nabid, Ahnaf Mozib Samin, Nabeel Mohammed, F. Sarker, M. N. Huda, K. Mamun","doi":"10.1109/ICEEE54059.2021.9718797","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718797","url":null,"abstract":"The research study presents an architecture of HumanRobot Interaction (HRI) based Artificial Conversational Entity integrated with speaker recognition ability to avail modern healthcare services. Due to the Covid-19 pandemic, the situation has become troublesome for health workers and patients to visit hospitals because of the high risk of virus dissemination. To minimize the mass congestion, our developed architecture would be an appropriate, cost-effective solution that automates the reception system by enabling AI-based HRI and providing fast and advanced healthcare services in the context of Bangladesh. The architecture consists of two significant subsections: Speaker Recognition and Artificial Conversational Entities having Automatic Speech Recognition in Bengali, Interactive Agent, and Text-to-Speech-synthesis. We used MFCC features as the linguistic parameters and the GMM statistical model to adapt each speaker’s voice and estimation and maximization algorithm to identify the speaker’s identity. The developed speaker recognition module performed significantly with 94.38% average accuracy in noisy environments and 96.27% average accuracy in studio quality environments and achieved a word error rate (WER) of 42.15% from RNN based Deep Speech 2 model for Bangla Automatic Speech Recognition (ASR). Besides, Artificial Conversational Entity performs with an average accuracy of 98.58% in a small-scale real-time environment.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126436271","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718780
M. M. R. Biswas, Md. Faruk Hossain, H. Okada
In this research work, the performance of the fabricated Quantum-dot Light-Emitting Diode was measured, where the sputtered oxide layer (ZnO) was used as the carrier transport layer, and the thickness of the films were varied to check the current and power efficiency of the devices. The ZnO film was deposited using RF (radio frequency) sputtering process with mixed working gas and substrate temperature of 150°C. The structure of the film was characterized using FE-SEM and a semiconductor parameter analyzer. Moreover, the current efficiency (CE) of 6.55 cd/A was obtained for the ZnCuInS/ZnS-based QLEDs with yellow emission at 580 nm.
{"title":"Investigation of the ZnCuInS/ZnS based Quantum-dot Light-Emitting Diodes with different ZnO Film Thickness Prepared by RF Sputtering","authors":"M. M. R. Biswas, Md. Faruk Hossain, H. Okada","doi":"10.1109/ICEEE54059.2021.9718780","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718780","url":null,"abstract":"In this research work, the performance of the fabricated Quantum-dot Light-Emitting Diode was measured, where the sputtered oxide layer (ZnO) was used as the carrier transport layer, and the thickness of the films were varied to check the current and power efficiency of the devices. The ZnO film was deposited using RF (radio frequency) sputtering process with mixed working gas and substrate temperature of 150°C. The structure of the film was characterized using FE-SEM and a semiconductor parameter analyzer. Moreover, the current efficiency (CE) of 6.55 cd/A was obtained for the ZnCuInS/ZnS-based QLEDs with yellow emission at 580 nm.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132210658","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718863
Md. Harun-Ur-Roshid, M. Rahman, Md. Tariqul Islam, M. H. Maruf, Sourav Barua, H. H. Fayek
Multilevel Inverter has become trending topology due to the involvement of renewable sources in the grid operation. Therefore, researchers have worked on the controlling methodology so that its efficiency will be almost 100%. In this regard, several multicarrier arrangements have been proposed for the reduction of THDs and switching losses, where the triangular wave is used as a carrier signal. In this paper, for increasing the performance of grid-connected eleven-level inverter, trapezoidal triangular carrier-based several multicarrier arrangements like phase disposition (PD), phase opposition disposition (POD), alternate phase opposition disposition (APOD) have been introduced and the performances of these arrangements were evaluated in MATLAB Simulink environment. From the simulation results, it is seen that the PD arrangement curtails 18.05% and 12.19 % of total harmonic distortions than POD and APOD arrangements gradually. Besides that, the lower order harmonic of the multilevel inverter is significantly lower in PD arrangement than other topologies and these characteristics will make the PD topology an optimal multicarrier arrangement in the future.
{"title":"Performance Analysis of Trapezoidal Triangular Carrier Based Modulation Techniques in Multilevel Inverter for Grid Integrated Solar Photovoltaic System","authors":"Md. Harun-Ur-Roshid, M. Rahman, Md. Tariqul Islam, M. H. Maruf, Sourav Barua, H. H. Fayek","doi":"10.1109/ICEEE54059.2021.9718863","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718863","url":null,"abstract":"Multilevel Inverter has become trending topology due to the involvement of renewable sources in the grid operation. Therefore, researchers have worked on the controlling methodology so that its efficiency will be almost 100%. In this regard, several multicarrier arrangements have been proposed for the reduction of THDs and switching losses, where the triangular wave is used as a carrier signal. In this paper, for increasing the performance of grid-connected eleven-level inverter, trapezoidal triangular carrier-based several multicarrier arrangements like phase disposition (PD), phase opposition disposition (POD), alternate phase opposition disposition (APOD) have been introduced and the performances of these arrangements were evaluated in MATLAB Simulink environment. From the simulation results, it is seen that the PD arrangement curtails 18.05% and 12.19 % of total harmonic distortions than POD and APOD arrangements gradually. Besides that, the lower order harmonic of the multilevel inverter is significantly lower in PD arrangement than other topologies and these characteristics will make the PD topology an optimal multicarrier arrangement in the future.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134443129","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718781
Md. Alimul Islam Salim, Md. Selim Hossain, Md. Alawal Kabir
If Tariff which typically demonstrate the per unit cost of electricity fluctuates day along directly with the daily demand curve as the theory of economy suggests the demand is directly proportional to the price, the demand of electricity will also fluctuate in direct manner. The increased cost of the electricity at peaking hours will inspire the consumers to implement volunteer load shed by shifting their usage of non-critical loads at off peaking hours. Thus the shortage of low cost electricity at the time of maximum demand peak would be subsidized to some extent as some uses of the non-critical loads are voluntarily shifted to the off peaking hours.
{"title":"Implementation of Volunteer Load Shedding By Variable Tariff Mode Energy Meter","authors":"Md. Alimul Islam Salim, Md. Selim Hossain, Md. Alawal Kabir","doi":"10.1109/ICEEE54059.2021.9718781","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718781","url":null,"abstract":"If Tariff which typically demonstrate the per unit cost of electricity fluctuates day along directly with the daily demand curve as the theory of economy suggests the demand is directly proportional to the price, the demand of electricity will also fluctuate in direct manner. The increased cost of the electricity at peaking hours will inspire the consumers to implement volunteer load shed by shifting their usage of non-critical loads at off peaking hours. Thus the shortage of low cost electricity at the time of maximum demand peak would be subsidized to some extent as some uses of the non-critical loads are voluntarily shifted to the off peaking hours.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130045403","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 : 2021-12-22DOI: 10.1109/ICEEE54059.2021.9718791
Rehnuma Hasnat, Abdullah Al Mamun, Ahmmad Musha, Tonmoy Ghosh
One of the most common gastrointestinal (GI) diseases is polyps. It is capable of causing the most lethal colon and rectal cancers. As a result, it must be removed during the primitive stage. In this paper, we investigated seven different classifiers with seven distinct features and proposed a simple polyp removal detection approach. It has also compared the performance of all classifiers for the features. The researchers noted that the Support Vector Machine (SVM) classifier provided the highest result for all features except Auto Color Correlogram. Besides, Bag of Features has achieved the highest result accuracy of 70.35%, the precision of 69.93%, F1-score 70.66%, and recall 71.40% for SVM classifier among all the features. It is optimistic that the research will open a path for future research in Polyp removal classification.
息肉是最常见的胃肠道疾病之一。它能引起最致命的结肠癌和直肠癌。因此，它必须在原始阶段被移除。在本文中，我们研究了7种具有7个不同特征的分类器，并提出了一种简单的息肉去除检测方法。它还比较了所有分类器对特征的性能。研究人员指出，支持向量机(SVM)分类器提供了除自动颜色相关图之外的所有特征的最高结果。其中，Bag of Features的结果准确率为70.35%，精密度为69.93%，f1得分为70.66%，召回率为71.40%。本研究将为今后息肉去除分类的研究开辟一条新的道路。
{"title":"Computer-Aided Polyp Removal Detection in Endoscopic Images","authors":"Rehnuma Hasnat, Abdullah Al Mamun, Ahmmad Musha, Tonmoy Ghosh","doi":"10.1109/ICEEE54059.2021.9718791","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718791","url":null,"abstract":"One of the most common gastrointestinal (GI) diseases is polyps. It is capable of causing the most lethal colon and rectal cancers. As a result, it must be removed during the primitive stage. In this paper, we investigated seven different classifiers with seven distinct features and proposed a simple polyp removal detection approach. It has also compared the performance of all classifiers for the features. The researchers noted that the Support Vector Machine (SVM) classifier provided the highest result for all features except Auto Color Correlogram. Besides, Bag of Features has achieved the highest result accuracy of 70.35%, the precision of 69.93%, F1-score 70.66%, and recall 71.40% for SVM classifier among all the features. It is optimistic that the research will open a path for future research in Polyp removal classification.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114327805","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：