2016 9th International Conference on Electrical and Computer Engineering (ICECE)最新文献_第8页

Towards optimal shallow ANN for recognizing isolated handwritten Bengali numerals 面向识别孤立手写孟加拉数字的最佳浅层人工神经网络

2016 9th International Conference on Electrical and Computer Engineering (ICECE) Pub Date : 2016-12-01 DOI: 10.1109/ICECE.2016.7853889

A. Chowdhury, M. S. Rahman

{"title":"Towards optimal shallow ANN for recognizing isolated handwritten Bengali numerals","authors":"A. Chowdhury, M. S. Rahman","doi":"10.1109/ICECE.2016.7853889","DOIUrl":"https://doi.org/10.1109/ICECE.2016.7853889","url":null,"abstract":"This work attempts to find the most optimal setting for shallow artificial neural network (ANN) for Bengali digit dataset. Recognition of handwritten Bengali numerals has recently gained much interest among researchers due to significant performance gain found in the recognition of English numerals using artificial neural network. In this work, a new dataset of 70,000 samples were created first by taking handwriting of 1750 persons where 982 persons were male and the rests were female. These individual image samples are then converted to grayscale, normalized, inverted and pickled to complete the data preprocessing step. Later this dataset was recognized using several artificial neural network settings where the most optimal setting being found to be one hidden layer with rectified linear unit activation and one output layer with softmax activation. In this study, we have given enough evidence to support our choice of these activations. We proposed the optimal number of neurons that can be used in the hidden layer is 700; also the optimal batch size is 200. The maximum accuracy on the test set has been found to be 96.05% which is a good result due to the complexity of the recognition task.","PeriodicalId":122930,"journal":{"name":"2016 9th International Conference on Electrical and Computer Engineering (ICECE)","volume":"252 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115596085","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

Reduction of detection volume in total internal reflection fluorescence microscopy using graphene 利用石墨烯减少全内反射荧光显微镜的检测体积

2016 9th International Conference on Electrical and Computer Engineering (ICECE) Pub Date : 2016-12-01 DOI: 10.1109/ICECE.2016.7853876

Shiekh Zia Uddin, M. A. Talukder

引用次数: 1

FLC based optimization of AGC controller parameters for an interconnected power system 基于FLC的互联电力系统AGC控制器参数优化

2016 9th International Conference on Electrical and Computer Engineering (ICECE) Pub Date : 2016-12-01 DOI: 10.1109/ICECE.2016.7853946

A. Ferdoush, M. G. Rabbani

引用次数: 0

Porous core Photonic Crystal Fiber based chemical sensor 基于多孔芯光子晶体光纤的化学传感器

2016 9th International Conference on Electrical and Computer Engineering (ICECE) Pub Date : 2016-12-01 DOI: 10.1109/ICECE.2016.7853903

B. K. Paul, Md. Shadidul Islam, Sawrab Chowdhury, S. Asaduzzaman, K. Ahmed

引用次数: 3

Ultra-high nonlinear photonic crystal fiber with GeO2 doped core 掺GeO2芯的超高非线性光子晶体光纤

2016 9th International Conference on Electrical and Computer Engineering (ICECE) Pub Date : 2016-12-01 DOI: 10.1109/ICECE.2016.7853963

Shekh Farhad Uddin Ahmed, SK Nayemuzzaman, M. Faisal

引用次数: 1

A novel low buffered optimized Solid State Drive controller 一种新型的低缓冲优化固态驱动器控制器

2016 9th International Conference on Electrical and Computer Engineering (ICECE) Pub Date : 2016-12-01 DOI: 10.1109/ICECE.2016.7853899

R. Das, B. Biswas, A. Rashid, M. Abedin

引用次数: 0

Solid State Transformer based on cascade multilevel converter for distribution network 基于级联多电平变换器的配电网固态变压器

2016 9th International Conference on Electrical and Computer Engineering (ICECE) Pub Date : 2016-12-01 DOI: 10.1109/ICECE.2016.7853973

Muhammad Masud Rana, Rafiur Rahman, Md Monibor Rahman

引用次数: 5

FCSEA: A Floodless Carrier-grade Scalable Ethernet Architecture FCSEA:无流量的电信级可扩展以太网架构

2016 9th International Conference on Electrical and Computer Engineering (ICECE) Pub Date : 2016-12-01 DOI: 10.1109/ICECE.2016.7853948

A. S. M. Asadujjaman, Shafika Showkat Moni, M. S. Alam

引用次数: 2

High efficient and stable ultra-thin CdTe solar cell with a potential Copper Telluride BSF 具有潜在碲化铜BSF的高效稳定超薄碲化镉太阳能电池

2016 9th International Conference on Electrical and Computer Engineering (ICECE) Pub Date : 2016-12-01 DOI: 10.1109/ICECE.2016.7853989

Mrinmoy Dey, Maitry Dey, M. Matin, N. Amin

引用次数: 10

Analysis of ECG signal and classification of heart abnormalities using Artificial Neural Network 心电信号分析及人工神经网络对心脏异常的分类

2016 9th International Conference on Electrical and Computer Engineering (ICECE) Pub Date : 2016-12-01 DOI: 10.1109/ICECE.2016.7853929

Tanoy Debnath, M. Hasan, Tanwi Biswas

{"title":"Analysis of ECG signal and classification of heart abnormalities using Artificial Neural Network","authors":"Tanoy Debnath, M. Hasan, Tanwi Biswas","doi":"10.1109/ICECE.2016.7853929","DOIUrl":"https://doi.org/10.1109/ICECE.2016.7853929","url":null,"abstract":"Cardiac arrhythmia indicates abnormal electrical activity of heart that can be a great threat to human. So it needs to be identified for clinical diagnosis and treatment. Analysis of ECG signal plays an important role in diagnosing cardiac diseases. An efficient method of analysing ECG signal and predicting heart abnormalities have been proposed in this paper. In the proposed scheme, at first the QRS components have been extracted from the noisy ECG signal by rejecting the background noise. This is done by using the Pan Tompkins algorithm. The second task involves calculation of heart rate and detection of tachycardia, bradycardia, asystole and second degree AV block from detected QRS peaks using MATLAB. The results show that from detected QRS peaks, arrhythmias which are based on increase or decrease in the number of QRS peak, absence of QRS peak can be diagnosed. The final task is to classify the heart abnormalities according to previous extracted features. The back propagation (BP) trained feed-forward neural network has been selected for this research. Here, data used for the analysis of ECG signal are from MIT database","PeriodicalId":122930,"journal":{"name":"2016 9th International Conference on Electrical and Computer Engineering (ICECE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123673485","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: 23