2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)最新文献

Design and Implementation of Bandwidth Based Time Varying Online Exam 基于带宽的时变在线考试的设计与实现

2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE) Pub Date : 2021-12-22 DOI: 10.1109/ICEEE54059.2021.9718990

Md. Nazmul Islam, Abdullah Mohammad Tanvirul Hoque, Md. Ahasan Habib

引用次数: 0

Offline Bangla Handwritten Text Recognition: A Comprehensive Study of Various Deep Learning Approaches 离线孟加拉语手写文本识别:各种深度学习方法的综合研究

2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE) Pub Date : 2021-12-22 DOI: 10.1109/ICEEE54059.2021.9718890

Farhan Sadaf, S. M. Taslim Uddin Raju, Abdul Muntakim

{"title":"Offline Bangla Handwritten Text Recognition: A Comprehensive Study of Various Deep Learning Approaches","authors":"Farhan Sadaf, S. M. Taslim Uddin Raju, Abdul Muntakim","doi":"10.1109/ICEEE54059.2021.9718890","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718890","url":null,"abstract":"Offline Handwritten Text Recognition (HTR) is a technique for translating handwritten images into digitally editable text format. Due to the presence of cursive letters, punctuation marks, and compound characters, it is more complex to recognize Bangla handwritten text. Over the years, several approaches to the optical model of the HTR system have been developed, including Hidden Markov Model (HMM) or deep learning techniques such as Convolutional Recurrent Neural Networks (CRNN), and current state-of-the-art Gated-CNN based architectures. Despite this, there are relatively limited works available for Bangla word recognition. In this paper, we introduce an end-to-end system for Bangla word recognition. We used a variety of popular pre-trained CNN architectures, including Xception, MobileNet, and DenseNet, followed by recurrent units such as LSTM or GRU. Furthermore, we experimented with Puigcerver’s CRNN based and Flor’s Gated-CNN based optical model architectulimited works available in Bangla.res. Flor architecture provided the highest recognition rate in our experiment, with a CER of 12.83% and a WER of 36.01%.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"77 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":"120947270","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}

引用次数: 3

Double Plasmonic Layered Electro-Absorption Modulator on Silicon Waveguide 硅波导双等离子体层状电吸收调制器

2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE) Pub Date : 2021-12-22 DOI: 10.1109/ICEEE54059.2021.9718801

Riziya Akter Keya, Abdul Khaleque, K. Shaha, Sumaya Akter, Md. Sarwar Hosen

引用次数: 0

FPGA based Histogram Equalization for Image Processing 基于FPGA的直方图均衡化图像处理

2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE) Pub Date : 2021-12-22 DOI: 10.1109/ICEEE54059.2021.9718837

Nahin Ul Sadad, Afsana Afrin, Md. Nazrul Islam Mondal

引用次数: 3

A Backstepping Sliding Mode Controller Design for Synchronous Machine Excitation Systems for Enhancing the Transient Stability 提高同步电机励磁系统暂态稳定性的反步滑模控制器设计

2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE) Pub Date : 2021-12-22 DOI: 10.1109/ICEEE54059.2021.9718838

T. S. Joyeeta, T. K. Roy, M. Sheikh

引用次数: 0

Deep Transfer Learning Based Multi-Class Brain Tumors Classification Using MRI Images 基于深度迁移学习的MRI多类脑肿瘤分类

2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE) Pub Date : 2021-12-22 DOI: 10.1109/ICEEE54059.2021.9719003

Mrinmoy Mondal, Md. Farukuzzaman Faruk, Nasif Raihan, Protiva Ahammed

{"title":"Deep Transfer Learning Based Multi-Class Brain Tumors Classification Using MRI Images","authors":"Mrinmoy Mondal, Md. Farukuzzaman Faruk, Nasif Raihan, Protiva Ahammed","doi":"10.1109/ICEEE54059.2021.9719003","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9719003","url":null,"abstract":"A brain tumor is a severe disease that can be fatal and significantly impacts one’s quality of life. The traditional method of identifying tumors relies on physicians, which is time-consuming and prone to errors, putting the patient’s life in jeopardy. Identifying the classes of brain tumors is difficult due to the high anatomical and spatial diversity of the brain tumor’s surrounding region. An automated and precise diagnosis approach is required to treat this severe disease effectively. Deep learning technology, such as CNN, can be used to diagnose various tumor types in the early stages of their development using brain MRI. In this study, a deep transfer learning framework based on VGG-19 is introduced to accurately detect three common kinds of tumors from brain MRI. There are primarily two phases to the suggested framework. The VGG-19 frozen part is the first phase, while the modified neural style classification part is the second phase. With certain modified techniques, the class imbalance impact within the MRI dataset and the generalization error issue during the training process were also resolved. The proposed model has a 94% classification accuracy and a 94% F1-score.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"19 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":"124806513","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}

引用次数: 5

Performance Analysis of Textile Antennas for Body Worn Application 用于人体磨损的纺织天线性能分析

2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE) Pub Date : 2021-12-22 DOI: 10.1109/ICEEE54059.2021.9718796

Sadia Enam, M. Rana

{"title":"Performance Analysis of Textile Antennas for Body Worn Application","authors":"Sadia Enam, M. Rana","doi":"10.1109/ICEEE54059.2021.9718796","DOIUrl":"https://doi.org/10.1109/ICEEE54059.2021.9718796","url":null,"abstract":"This paper presents conventional shaped (rectangular elliptical, and circular) textile antennas performance and SAR analysis with and without human body tissue model (HBTM) at 2.45 GHz. The antenna design involved a coaxial probe feeding technique and fabric substrates (wash cotton, curtain cotton, and polycot) of 3 mm thickness. At 2.45 GHz WLAN band, both for OFF body and ON body, circular antenna with curtain cotton presents an overall superior performance in terms of return loss (−60.9995 dB and −52.423 dB), VSWR (1.0018 and 1.0048), peak directivity (8.969 dBi and 8.825 dBi), gain (7.391 dBi and 7.109 dBi), and radiation efficiency (69.81% and 68.07%) maintaining a bandwidth (BW) of 108.2 MHz and 107.4 MHz at −10dB. The antennas are also analyzed in close proximity (2 mm away) to a three-layered (skin, fat, and muscle) flat body phantom to determine the Specific Absorption Rate (SAR). The SAR recorded for circular MPA (curtain cotton) is 0.0293 W/kg< 2 W/kg averaged over 10g tissue. The overall simulation is done using CST Microwave Studio software. The proposed antenna is considered to be an effective antenna for on body wireless communication.","PeriodicalId":188366,"journal":{"name":"2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE)","volume":"22 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":"122812220","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}

引用次数: 0

Optimization-based Energy Management System to Minimize Electricity Bill for Residential Customer 基于优化的能源管理系统，实现住宅用户电费最小化

2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE) Pub Date : 2021-12-22 DOI: 10.1109/ICEEE54059.2021.9718575

Sancoy Barua, N. Mohammad

引用次数: 6

Predicting Autism Spectrum Disorder Based On Gender Using Machine Learning Techniques 使用机器学习技术基于性别预测自闭症谱系障碍

2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE) Pub Date : 2021-12-22 DOI: 10.1109/ICEEE54059.2021.9718798

Tania Akter, M. Ali

引用次数: 0

Unreal Engine Blueprint: Developing Hack and Slash Using Spawn Projectile Method 虚幻引擎蓝图:开发Hack和Slash使用刷出射弹方法

2021 3rd International Conference on Electrical & Electronic Engineering (ICEEE) Pub Date : 2021-12-22 DOI: 10.1109/ICEEE54059.2021.9718774

Shadib Mahmud, S. S. Ghosh

引用次数: 0