{"title":"Recognition of Handwritten Digit using Convolutional Neural Network in Python with Tensorflow and Comparison of Performance for Various Hidden Layers","authors":"Fathma Siddique, S. Sakib, M. Siddique","doi":"10.1109/ICAEE48663.2019.8975496","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975496","url":null,"abstract":"In recent times, with the increase of Artificial Neural Network (ANN), deep learning has brought a dramatic twist in the field of machine learning by making it more artificially intelligent. Deep learning is remarkably used in vast ranges of fields because of its diverse range of applications such as surveillance, health, medicine, sports, robotics, drones, etc. In deep learning, Convolutional Neural Network (CNN) is at the center of spectacular advances that mixes Artificial Neural Network (ANN) and up to date deep learning strategies. It has been used broadly in pattern recognition, sentence classification, speech recognition, face recognition, text categorization, document analysis, scene, and handwritten digit recognition. The goal of this paper is to observe the variation of accuracies of CNN to classify handwritten digits using various numbers of hidden layers and epochs and to make the comparison between the accuracies. For this performance evaluation of CNN, we performed our experiment using Modified National Institute of Standards and Technology (MNIST) dataset. Further, the network is trained using stochastic gradient descent and the back-propagation algorithm.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126543725","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}
M. A. Mahfuz, Md. Nazmus Sakib, M. Hasib, H. Banna, Muzahidul Islam, M. Uddin
{"title":"Design and Performance Analysis of a Silver-Coated Microstructure Optical Fiber Plasmonic Sensor","authors":"M. A. Mahfuz, Md. Nazmus Sakib, M. Hasib, H. Banna, Muzahidul Islam, M. Uddin","doi":"10.1109/ICAEE48663.2019.8975424","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975424","url":null,"abstract":"In this manuscript, a highly amplitude sensitive surface plasmon resonance (SPR) based microstructure optical fiber (MOF) or photonic crystal fiber (PCF) based plasmonic biosensor is proposed and numerically analyzed. To make a simple and straightforward design, the proposed structure is demonstrated consisting of all circular air holes with an external coating of metal and sensing layer, unlike the coating of inner air-hole (s). Sensing characteristics are investigated with the modal analysis based finite element method (FEM). The numerical performance shows that the maximum amplitude and wavelength sensitivity of 3731 RIU-1 and 9000 nm/RIU with the analyte detection range from 1.36-1.40. Because of the high sensitivity, simple structure, and excellent polynomial characteristics, the proposed sensor can be a promising candidate for the detection of various biochemical and biological samples (DNA, mRNA, proteins, sugar) detection.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121584963","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}
{"title":"Near-Optimal Hybrid Precoding Analysis in 5G mmWave massive MIMO Systems with Large Antenna Arrays","authors":"Sawkat Osman, M. Mowla","doi":"10.1109/ICAEE48663.2019.8975555","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975555","url":null,"abstract":"Millimeter-wave (mmWave) communication is most likely to appear as a aspiring technology in the upcoming generation of cellular communication (5G). To confront several challenges (e.g., system complexity, energy consumption etc.), hybrid precoding is largely investigated in mmWave massive MIMO systems due to its low energy consuming nature and reduced system complexity. Most prior works have focused on two types of hybrid precoding structures: (i) fully-connected structure which requiring a massive amount of phase-shifters (PS), (ii) sub-connected structure where comparatively less number of PS is needed; both structures considering only mmWave channel. In this paper, the downlink communication of a mmWave massive MIMO system in considered and the achievable sum-rate of a hybrid precoding (sub-connected) based on successive interference cancellation (SIC) is analyzed in both mmWave channel as well as in different wireless channels. Results demonstrate that the SIC-based scheme achieves nearoptimum sum-rate in different wireless channels and mmWave channel as well regardless of the fact that it utilizes a small number of phase-shifters compared to other architectures and performs even better in the conventional wireless channels than in mmWave channel. Results also indicate that the sum-rate is even more near to optimal when the user antennas and RF chains are sufficiently increased.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115082140","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}
Mehadi Hasan Khan, Mohammad Rejwan Uddin, Zaima Tasneem, K. M. Salim
{"title":"Power Factor Analysis of an Energy Efficient Single Phase VFD for Industrial Sewing Machines","authors":"Mehadi Hasan Khan, Mohammad Rejwan Uddin, Zaima Tasneem, K. M. Salim","doi":"10.1109/icaee48663.2019.8975645","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975645","url":null,"abstract":"The Ready-Made Garments (RMG) sector plays a huge role in the Bangladesh economy in terms of employment, foreign exchange earnings and its contribution to GDP. Mainly clutch motors are used in this industry which has no speed control, low starting torque, energy loss through heat and motor burn problems, etc. A VFD based inverter can protect the motors from these problems. Moreover, a stand by position for controlling the speed by VFD during no-load time can make the system more energy efficient. But, an inversion process can affect the line power factor though it increases the system efficiency. In this paper, the field implemented data of a 1kW capacity VFD for clutch motors is shown. Efficiency improvement and distortion in PF is analyzed by field implementation and lab experiment. In addition, in this paper, a boost converter integrated VFD inverter is also analyzed for the specific capacity to get an ideal power factor with improved efficiency.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129942078","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}
{"title":"Speaker Identification System Under Noisy Conditions","authors":"Md. Shariful Alam, M. S. Zilany","doi":"10.1109/icaee48663.2019.8975420","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975420","url":null,"abstract":"Speaker identification (SID) systems need to be robust to extrinsic variations in the speech signal, such as background noise, to be applicable in many real-life scenarios. Mel-frequency cepstral coefficient (MFCC)-based i-vector systems have been defined as the state-of-the-art technique for speaker identification, but it is well-known that the performance of traditional methods, in which features are mostly extracted from the properties of the acoustic signal, degrades substantially under noisy conditions. This study proposes a robust SID system using the neural responses of a physiologically-based computational model of the auditory periphery. The 2-D neurograms were constructed from the simulated responses of the auditory-nerve fibers to speech signals from the TIMIT database. The neurogram coefficients were trained using the i-vector based systems to generate an identity model for each speaker, and performances were evaluated and compared in quiet and under noisy conditions with the results from existing methods such as the MFCC, frequency-domain linear prediction (FDLP) and Gammatone frequency cepstral coefficient (GFCC). Results showed that the proposed system outperformed all existing acoustic-signal-based methods for both in quiet and under noisy conditions.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127094612","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}
{"title":"Robust Control of Hand Prostheses from Surface EMG Signal for Transradial Amputees","authors":"Anika Nastarin, Ashrina Akter, M. Awal","doi":"10.1109/ICAEE48663.2019.8975630","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975630","url":null,"abstract":"This paper investigates the difficulty in gaining robust control of hand prostheses by the Surface Electromyogram (sEMG) of transradial amputees under dynamic force levels because these changes can create a significant effect on robust controlling of the prostheses. A set of attributes has also been proposed to lessen the effect of force level changes on the prosthetic hand users which is controlled by amputees. To accomplish this task, at first the signal is pre-processed to abolish noise and artefacts from the raw-sEMG signals and then extracts features. Features are extracted from three specific domains: time, spectral and wavelet domain. For farther analysis, wavelet packet and entropy-based features have also been extracted. Finally, for classification purpose state-of-the-art classifiers such as Support Vector Machine (SVM), Decision Tree (DT), Linear Discriminant Analysis (LDA) and Quadratic Linear Discriminant Analysis (QLDA) have been used and compared. To optimize the hyper-parameters of classifiers, Bayesian optimization algorithm has been used. Our recommended system is verified through openly accessible EMG database and results relate with the proposed system. Classification was done under four well known classifier which are DT, LDA, QLDA and SVM respectively and their accuracy is calculated for both feature and signal level.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132849553","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}
A. Saha, F. Sultana, Md. Asrarul Haque, Shams S. M. Nasif
{"title":"Design of MPPT mounted Solar Based Double Coil DC Electric Cooker with Smart Temperature Control Device","authors":"A. Saha, F. Sultana, Md. Asrarul Haque, Shams S. M. Nasif","doi":"10.1109/icaee48663.2019.8975451","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975451","url":null,"abstract":"This paper presents a cooking technology consisting of a Maximum Power Point Tracking (MPPT) based Electric Cooker with a feature of temperature control which can be operated by both solar panel or battery. Perturb & Observe method has been used as the algorithm of the MPPT which ensures battery charging by drawing Maximum Power from the PV Panel. Temperature control has been performed by using K-type thermocouple using relay. The hardware study has been done by using Photovoltaic (PV) Panel, MPPT, Temperature control circuit and battery. Time for cooking different food items has been observed and other necessary data have been analyzed to evaluate the performance of the electric cooker.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133089918","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}
Abu Shufian, Md. Mominur Rahman, Riadul Islam, Shimul Kumar Dey
{"title":"Smart Irrigation System with Solar Power and GSM Technology","authors":"Abu Shufian, Md. Mominur Rahman, Riadul Islam, Shimul Kumar Dey","doi":"10.1109/icaee48663.2019.8975634","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975634","url":null,"abstract":"In recent days everything depends on smart technology. Irrigation system is also becoming smart by using modern technologies, which is more advantageous rather than the traditional methods. In this paper, a smart irrigation system is developed that automates the irrigation process with the help of solar power. This proposed system can optimize the use of water based on different data, such as soil moisture, weather prediction, etc. It will also notify its owner about the current condition of the soil and motor through GSM technology. This proposed model can automatically turn ON and OFF the motor pump by sensing the moisture content of the soil depending on the demand of water in the field. A moisture sensor is used to collect data (soil moister level) of a particular area. The motor will automatically turn OFF after fulfilling the demand of water and get turns ON again when the field becomes dry. GSM technology is used to send the update (ON/OFF) of a motor to the farmers. The whole proposed system is controlled by an Arduino. Here, DC power is generated from the solar panel. All these features will make irrigation system much smarter and economical.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133327524","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}
{"title":"Design of an Automatic High Precision Solar Tracking System with an Integrated Solar Sensor","authors":"Taslim Ahmed, I. Chowdhury","doi":"10.1109/icaee48663.2019.8975475","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975475","url":null,"abstract":"A sustainable powered standalone automatic Solar Tracking System is designed and successfully simulated to provide the best alignment of solar panel with position of the sun automatically, to extract an increased efficiency by 40 percent. A very low cost (approx. 5 USD), high precision Solar Tacking Sensor has been designed to rotate the solar panel coupled to the stepper motor rotates 25.70 degree at single step and to tracks the whole 180-degree trace in 8 (eight) steps per day with greater accuracy. Microcontroller (ATmega16) is used as main control unit where its ADC ports are used to interface the Sensor unit and ULN2000A motor driver is used to interface the stepper motor to rotate the solar panel at maximum solar energy angle. The results found from the simulation and analysis shows that, the system required 12.04 mA and 37.163 mA current, and 144.48 mW and 445.956 mW power, during standby and panel rotating mode respectively. The maximum current drawn by the Solar Tracking Sensor is less than 0.5 mA. ‘Proteus ISIS 7.7 professional’ is used for design and simulation, and ‘Code Vision AVR v2.5’ is used to write the program code and burning into the ATmega16 for simulation and analysis.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133374206","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}
Md. Sarwar Uddin Chowdhury, Muhammad Asad Rahman, M. Hossain, A. Mobashsher
{"title":"Design of an ITO Based CNT Coated Transparent Nano Patch Antenna Assisted by Characteristic Mode Analysis","authors":"Md. Sarwar Uddin Chowdhury, Muhammad Asad Rahman, M. Hossain, A. Mobashsher","doi":"10.1109/icaee48663.2019.8975428","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975428","url":null,"abstract":"An Indium-doped Tin Oxide (ITO) based optically transparent nano-antenna is presented in this paper. E-shaped patch is used to resonate at 0.76 THz. Despite of high fractional bandwidth, the radiation efficiency as well as gain of the ITO based antennas are low due to high resistivity and low conductivity of ITO thin films. To overcome this limitation, carbon nano tube (CNT) is used as cover over radiating patch of the proposed antenna. As a result, due to high conductivity of CNT, along with gain and efficiency, the fractional bandwidth of the proposed antenna is also increased. Characteristic mode analysis (CMA) is carried out to provide more insightful physical characteristics of the proposed antenna. It helps to understand the structural optimization and to determine the operating frequency. Moreover, a copper based non-transparent E-shaped patch antenna, resonated at 0.76 THz is also designed to compare with the proposed antenna. The proposed antenna has fractional bandwidth of 21% which is much better than conventional patch antenna and some previous transparent antennas. A peak gain of 4.9 dBi is obtained at 0.76 THz with good radiation performance. The designed antenna is suitable for satellite communication because of its broad bandwidth, reasonable radiation efficiency, sufficient gain, light weight and compactness.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"89 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132302661","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}