{"title":"DenseNet Based Speech Imagery EEG Signal Classification using Gramian Angular Field","authors":"M. Islam, Md. Maruf Hossain Shuvo","doi":"10.1109/ICAEE48663.2019.8975572","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975572","url":null,"abstract":"One of the most challenging tasks in the Brain-Computer Interface (BCI) system is to classify the speech imagery electroencephalography (EEG) signals. In this work, we addressed the existing low classification accuracy problem with deep learning and improved beta band selection method. When the subject imagines, uttering a word rather saying it directly, there are changes in electrical stimulation in the brain. These electrical stimulations of the brain are recorded using EEG signal recording device. The recorded EEG data is then processed using the Dual-Tree Complex Wavelet Transform (DTCWT) for beta band selection which is responsible for activity related to imagery. To take advantage of Deep Convolutional Neural Networks (DCNN), we converted the time series EEG data into images. We generated images using two versions of Gramian Angular Field (GAF): Gramian Summation Angular Filed (GASF) and Gramian Difference Angular Field (GADF). Then these images were fed to DenseNet for image classification. DenseNet is an improved version of DCNN that minimizes the vanishing gradient problem. Between two different image generation techniques, GADF has the best average classification accuracy rate of 90.68 %. The dataset used in this study named ‘The KARA ONE Database’ is collected from Computational Linguistics Lab, University of Toronto, Canada.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"21 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":"132709649","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. Raseduzzaman Ruman, Joybrota Kumar Badhon, Saikat Saha
{"title":"Safety Assistant And Harassment Prevention For Women","authors":"Md. Raseduzzaman Ruman, Joybrota Kumar Badhon, Saikat Saha","doi":"10.1109/icaee48663.2019.8975648","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975648","url":null,"abstract":"Nowadays we have seen many women, young girls and mothers disappearing and facing physical and sexual harassment from public places, streets and public transport. Many cases are being filed on a regular basis on issues such as kidnapping, harassments or assaults and these crimes are increasing day by day. In order to stop these crimes, we designed an embedded system for women safety based on Arduino and GSM module with GPS to send an emergency message with location and generate an alarm. This system sends a message to the police control room, family and friends. It’s also track the location to ensure safety for women. This also comes with an additional feature consisting of a shock generator for self-defense of women in an intense situation. When the victim will be in danger, it also generate an emergency call which will be activated by the victim. This wireless device is convenient and can be activated by the victim on being harassed just by the click of a push button. The performance of this device showed an overall accuracy of 92.6%. The main purpose is to ensure public safety in the emergency situation.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"22 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133003491","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":"A Unified Analysis of Proposed Wavelet Transform Domain LMS-algorithm for ARMA Process","authors":"Suryaia Rahman, M. Rashid, M. Z. Alam","doi":"10.1109/ICAEE48663.2019.8975625","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975625","url":null,"abstract":"A unified analysis of Wavelet Transform (WT) domain Least Mean Square (LMS) adaptive filter is presented in this work for highly correlated Autoregressive-Moving-Average (ARMA) input process. It is well known that the Unitary transform (UT) domain LMS (UT-LMS) adaptive filter for Autoregressive (AR) process with power normalization improves the filter performance, where DCT provides best performance among them. In this work, we apply the UT-LMS algorithm for time-varying ARMA process, and the analytical result shows that the lower decorrelation property of UT degrades the LMS performance. As a result, Unitary transform is not applicable for LMS as a transform algorithm for ARMA process, and this outcome has not been explored in early published work. In this paper, we propose Discrete Wavelet domain LMS (DWT-LMS) for ARMA process to enhance the basic performances of LMS such as misadjustment, convergence, and tracking properties, and the theoretical and simulation result of this work show that DWT-LMS provides better performance than that of DCT-LMS for 1st and $2^{mathrm{n}mathrm{d}}$ order AR, Moving-average (MA), and ARMA process. This paper concludes with the MATLAB simulation for the proposed method with various inputs for demonstrating the validity of the derived mathematical algorithm.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"5 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":"122211155","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":"A Location Aware Communication Mode Selection Mechanism for M2M Communications over Cellular Networks","authors":"Sree Krishna Das, Md. Farhad Hossain","doi":"10.1109/ICAEE48663.2019.8975497","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975497","url":null,"abstract":"Machine-to-machine (M2M) communication is viewed as a promising technology for reducing traffic burden on the cellular base stations (BSs), enhancing the spectrum utilization and improving energy efficiency. To achieve this benefits, communication mode selection mechanism is crucial. This paper proposes a location-aware communication mode selection mechanism and resource blocks (RBs) allocation strategy for M2M communications over cellular networks. The mode selection mechanism depends on the threshold distance and threshold signal-to-interference-plus-noise-ratio (SINR). As a result, user equipment (UE) automatically selects the appropriate communication mode. On the other hand, the proposed mechanism allocates RBs based on the selected mode. It is inferred that the proposed mode selection scheme before data transfer can improve the system performance. Simulation results show that the proposed scheme can substantially improve the system performance in terms of per-user throughput and reduced traffic burden on the BSs.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"10 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":"115675687","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}
Swarup Chakraborty, Muhammad Asad Rahman, M. Hossain, A. Mobashsher, E. Nishiyama, I. Toyoda
{"title":"Design and Performance Studies of a MIMO Antenna With Circular Polarization Diversity for 5G Applications","authors":"Swarup Chakraborty, Muhammad Asad Rahman, M. Hossain, A. Mobashsher, E. Nishiyama, I. Toyoda","doi":"10.1109/icaee48663.2019.8975509","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975509","url":null,"abstract":"An innovative 2-element multiple input multiple output (MIMO) antenna with the circular polarization (CP) diversity is proposed in this paper with an intention to use in the sub−6 GHz spectrum (3.6–3.8 GHz) for 5G wireless applications. A microstrip line fed slot antenna is working as a single element for the MIMO arrangement. An elliptical shaped slot and the unequal feed lines mechanism are used to sense CP for every element. For CP diversity, mirror operation between the antenna elements is performed. A rectangular slot line in the ground plane is inserted to realize better isolation between the antenna elements. The MIMO antenna provides good isolation < -25 dB between the antenna elements in 5G operating frequency band of 3.6-3.8 GHz. Considering 5 dBic gain as well as axial ratio (AR) less than 0.5 dB, this antenna shows promising CP radiation pattern. Moreover, result of envelope correlation coefficient (ECC) (< 0.002) and channel capacity loss (CCL) less than 0.3 b/sec/Hz make it suitable for fifth generation wireless applications.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"41 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":"124002294","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":"Weight-based Bandwidth Allocation Algorithm for Improving the QoSs of Multi-OLT PON in Downstream Direction","authors":"Md. Saklain Mustak, M. Hossen, Shuvashis Saha","doi":"10.1109/icaee48663.2019.8975683","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975683","url":null,"abstract":"In this era of optical communication, the passive optical network (PON) having multiple optical line terminals (multi-OLT) will play a vital role for both the data and voice communications of multiple service providers. For downstream data transmission of multi-OLT PON, the existing algorithms are not effective to allocate bandwidth among different service providers. Because, the existing scheme does not provide fairness in sharing of downstream bandwidth. This paper proposes a new downstream bandwidth allocation scheme for multi-OLT PON system called fair and weight-based bandwidth allocation (FWBA) algorithm. In the proposed scheme, we have considered a multi-OLT PON system for convergence of cable television, fiber-to-the-home, wireless sensor, and femto networks. The performances of the FWBA scheme have been analyzed on the basis of transmission delay, idle-time as well as traffic handling capacity. The comparative analysis of simulation results show that the FWBA scheme performs better than non-weight-based DBA (NWBA) scheme.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"181 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":"116117064","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":"A New 36-Pulse Star Rectifier for Power Quality Improvement","authors":"Md. Abdul Malek, Muhammad Abdul Goffar Khan","doi":"10.1109/ICAEE48663.2019.8975670","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975670","url":null,"abstract":"In this paper, current injection technique based 36-pulse uncontrolled star rectifier is proposed for large current rating application. The proposed rectifier consists of a new delta/fork conFigure transformer, 18-pulse star rectifier with passive injection circuit at dc link and specially tapped inter phase transformer (STIT). Delta/fork transformer creates two 9-phase supplies for 18-pulse star rectifier. STIT and single phase full-wave rectifier (SPFWR) constitutes the passive injection circuit and conduction loss of proposed passive injection circuit is much smaller than the conventional ripple re-injection circuit. SPFWR extract harmonics current from STIT which feed back to the load and this harmonic current modify the output voltage wave shape of 18-pulse star rectifier. Proposed rectifier operate as 36-pulse star rectifier when turns ratio of STIT is designed optimally and under this condition total harmonic (THD) of the input line current is about 4.68%. Proposed rectifier is analyzed, designed and simulated in MATLAB software environment and simulation results confirm the IEEE -519 standard requirement.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"15 6 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":"116137636","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":"Behavior of the Proton Exchange Membrane Fuel Cell Around Critical Fuel and Air Supply Pressure","authors":"K. Ahmed, Md. Rawshan Habib, Shuva Dasgupta Avi, Md. Hasanuzzaman Sagor, Omar Farrok","doi":"10.1109/ICAEE48663.2019.8975597","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975597","url":null,"abstract":"The performance of a fuel cell depends on fuel and air supply within a range of atmospheric pressure. This paper presents the mathematical model and performance of the proton exchange membrane (PEM) fuel cell under the condition of critical fuel supply and air pressure. At first, air supply pressure is changed under the condition of constant fuel supply. Secondly, the pressure of fuel supply is changed under the condition of constant air pressure. The effect on air consumption, fuel supply, and overall efficiency of the fuel cell are observed under these conditions. Simulations are carried out for a specific model of PEM fuel cell named Nedstack PS6 which is rated at 6 kW. The results show that, variation of both air pressure and fuel pressure have a noticeable effect on the system.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"1 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":"116612542","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":"Forecasting-Aided State Estimation for Power Distribution System Application: Case Study","authors":"Shahid Jaman, Md. Rezwanur Rashid Mazumder, Md. Istiak Ahmed, A. Rahman","doi":"10.1109/ICAEE48663.2019.8975430","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975430","url":null,"abstract":"State Estimation (SE) is a vital component of the Supervisory Control and Data Acquisition (SCADA) system used today in power networks. In traditional SE methods, such as Weighted Least Squares (WLS), the state variables of the grid (voltage magnitudes and phase angles) are estimated from a snapshot of the meters embedded in the network (i.e. the last measurements available). The problem in traditional WLS process is it gives wrong estimation when the Remote Terminal Unit (RTU) is not work or technical fault for a short time. New approaches to the SE technique, known as Forecasting-Aided State Estimation (FASE), take advantage of past states in order to improve the estimation and endow the system with forecasting capabilities. The application of FASE to the low voltage grid in the context of the distribution system paradigm is an alluring area of research. In this work, a FASE algorithm using Kalman Filters is developed and applied to a distribution network. The algorithm is implemented in Matlab and is assessed in the context of test feeders using quasi-static time series data. The performance of the new algorithm is compared with a traditional WLS implementation.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"601 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":"123193117","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":"Analysis of Different Interpolation Methods in Watermarking Scheme Based on Prediction Error Expansion, Interpolation and Segmentation","authors":"Majeza Begum Shama, Tasnim Azad Abir","doi":"10.1109/icaee48663.2019.8975611","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975611","url":null,"abstract":"Watermarking is a way to keep secret information hidden in the cover media that is indistinguishable to the human eye but easily noticeable to the decoder. In this paper, a watermarking scheme is analyzed based on prediction error expansion using interpolation and segmentation in order to find an optimal watermarking technique. In this method, watermark is embedded into a cover image using additive prediction error expansion method by interpolating and segmenting the cover image. Interpolation reduces artifacts and segmentation distinguishes sharp areas and smooth areas. Here, interpolation is used instead of other prediction method in order to reduce the computation time and complexity of the method. Segmentation is used so that higher embedding capacity can be used for sharp segments and lower embedding capacity for smooth regions using additive PEE. The interpolation method will be varied to determine the most efficient interpolation method for this scheme. Different noise attacks will be applied to find the robustness of the method. The idea of applying different bits in different segments will be applied. For this purpose, the segments are classified into different classes according to their average slopes. The segments that have higher slopes will get more bits embedded into them. Finally, different performance parameters like PSNR, NCC, MSE & embedding capacity will be calculated for evaluating the proposed scheme.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"68 3 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":"124788070","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}