Md. Abdur Rahman, S. M. Shoaib, Md. Al Amin, Rafia Nishat Toma, M. Moni, M. Awal
{"title":"A Bayesian Optimization Framework for the Prediction of Diabetes Mellitus","authors":"Md. Abdur Rahman, S. M. Shoaib, Md. Al Amin, Rafia Nishat Toma, M. Moni, M. Awal","doi":"10.1109/ICAEE48663.2019.8975480","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975480","url":null,"abstract":"The advances of bioinformatics and medical sciences have generated an enormous amount of data which can be used by machine learning (ML) and data mining (DT) methods to transform the data into valuable knowledge and can improve diagnosis, prediction, and management of most chronic diseases. One of the most life-threatening and widespread chronic diseases is Type 2 Diabetes Mellitus (T2DM), characterized by impaired operation of glucose homeostasis. We used several cutting-edge machine learning algorithms including Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), Naive Bayes (NB) on diabetes data. A state-of-the-art Bayesian Optimization (BO) has been proposed to optimize the hyper-parameters of machine learning classifiers for the Diabetes Mellitus (DM). The optimized hyperparameters using BO achieved an accuracy of 77.60% with RF, 76.04% with SVM, 71.61% for DT, 73.96% for NB classifier. We also achieved 64.06% accuracy without BO optimized SVM. We justified our models using confusion matrix for each classifier. The statistical comparison among different classifier’s performances has been presented using the Boxplot and Analysis of variance (ANOVA) test.","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":"130056942","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}
Shidhartho Roy, Md. Salah Uddin Yusuf, Monira Islam, Tanbin Islam Rohan
{"title":"Age based Mood Swing Analysis and Brain Mapping for Music Genre","authors":"Shidhartho Roy, Md. Salah Uddin Yusuf, Monira Islam, Tanbin Islam Rohan","doi":"10.1109/ICAEE48663.2019.8975671","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975671","url":null,"abstract":"Music is a popular source of entertainment and a way of relief from stress. But with the elapse of time duration it may changes the mood of human being. In this paper, age based mood changes of human being will be analyzed with music stimulated potentials based on power spectral density (PSD). Music of different languages Bengali, English and Tamil are taken as chosen as stimuli. Rock, POP and Metal songs which are categorized with PSD are considered as music genre. Three age groups are selected as subjects and the EEG signals are taken while listening different music genres. Wavelet transformation is performed to denoise the signal and extract different EEG bands according to their frequency level. Stress and relax state of brain is determined from activation of alpha (α) and beta (β) EEG bands based on their power spectral density (PSD) while listening music. Stress is caused by the exposure of distinct genre of songs and languages. It is shown that while listening music at small time interval pressure is relieved but the increment of time changes the mood towards stress. Topographic plots are rendered to exhibit the active regions for alpha band activation. Tamil songs are less tempted to create relax whereas native language Bengali creates relax at beginning and leading to stress over time.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"38 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":"123185570","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}
K. Ahmed, Shuva Dasgupta Avi, M. Tanvir, Md. Mominur Rahman, Abu Shufian, Md. Hasanuzzaman Sagor, Omar Farrok
{"title":"Transportation in Between the Earth and Space by Using Carbon Nanotubes as the Elevator Cable","authors":"K. Ahmed, Shuva Dasgupta Avi, M. Tanvir, Md. Mominur Rahman, Abu Shufian, Md. Hasanuzzaman Sagor, Omar Farrok","doi":"10.1109/ICAEE48663.2019.8975533","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975533","url":null,"abstract":"The space elevator is a type of transportation objects from the earth to space. It would enable a cost-effective space ride for human to explore and exercise space science. The primary component of a space elevator is a cable. It would be extended into space from the Earth’s surface which would lift the elevator. Carbon nanotube is one of the potential materials for the cable. In this study, some electrical and mechanical properties of the carbon nanotube are analyzed. Simulations are carried out to illustrate the parameters which support the fact that carbon nanotube can be used as tether and sensor material in the space elevator projects. Information gained from this work would be useful for construction and related applications of carbon nanotube-based space elevator.","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":"127799855","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. Akash, M. Hossen, Md. Rakibul Hassan, M. Hossain
{"title":"Gateway Node-based Clustering Hierarchy for Improving Energy Efficiency of Wireless Body Area Networks","authors":"A. Akash, M. Hossen, Md. Rakibul Hassan, M. Hossain","doi":"10.1109/icaee48663.2019.8975604","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975604","url":null,"abstract":"Nowadays, wireless body area network (WBAN) is an emerging technology. WBAN devices play a vital role in health monitoring and patient observation process. Making WBAN more energy efficient is a major issue. The goal of this study is to design energy efficient WBAN where a gateway node is employed in a routing path among the clusters of a body called gateway node-based clustering hierarchy (GNCH). This protocol provides minimization of energy consumption and ultimately maximizes the lifetime of a WBAN. In this proposed GNCH protocol, the gateway node is responsible for transmitting data from cluster heads (CHs) to the base station. The CHs of the WBAN is selected based on the residual energy of the member nodes of the clusters. That means base station does not involve in the CH selection which reduces the energy consumption of the network. Moreover, in this paper, common node problem of two neighboring clusters has been resolved. The proposed GNCH protocol supports single hop communication inside a cluster that effectively eliminates energy consumption. The GNCH and conventional single and/ multi hop communication scenarios have been simulated. The proposed GNCH protocol provides less energy consumption than the conventional protocol because the size of WBAN is very small.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"64 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":"131405657","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":"Channel Modeling at Unlicensed Millimeter Wave V Band for 5G Backhaul Networks","authors":"Hussnin Binte Hamid Dutty, M. Mowla","doi":"10.1109/ICAEE48663.2019.8975439","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975439","url":null,"abstract":"The thirst raising of mobile traffic demand of next generation’s cellular communication (5G) is expected to be reduced by the use of mmWave spectrum. The use of mmWave band (10 to 300 GHz) is equally indispensable in backhaul (eNBs to core network) network as similar to access network (user equipment to eNBs). However, the channel modeling in backhaul network is still very difficult due to high propagation loss, environmental attenuation, absorption loss, and sensitivity of blockage. In this research, the spatial statistical channel modeling (SSCM) for 5G backhaul networks are investigated under unlicensed V band (60 GHz) in case of both line-of-sight (LOS) and non-line-of-sight (NLOS) environments. By using the simulator NYUSIM for urban macrocell scenario we analyze channel characteristics viz angle of departure (AoD), angle of arrival (AoA), power delay profiles (omnidirectional, directional, small scale) and path losses, showing the distinctions of allocating receiver locations in both LOS and NLOS conditions. These investigations demonstrate the potential of 60 GHz mmWave band and its suitability for future 5G backhaul network design.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"228 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":"124529565","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":"Prediction of Breast Cancer Using Ensemble Learning","authors":"Sunanda Das, Dipayan Biswas","doi":"10.1109/ICAEE48663.2019.8975544","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975544","url":null,"abstract":"Among all types of cancers, breast cancer is the most crucial and fatal cancer particularly for women as it is considered the second leading cause for cancer death among women. When it’s a question of survival, correct treatment is a vital requirement, and for proper treatment, the first requirement is to identify cancer accurately. Here, we are motivated to provide a highly reliant and consistent system for the prediction of breast cancer. In the proposed method, we have used ensemble learning for the desired accuracy. The ensemble voting system comprises a total of five machine learning (ML) classifiers which include Random Forest, Naive Bayes, SVM with two different kernels (rbf, polynomial), K-Nearest Neighbors and Decision Tree. We experimented on the Wisconsin Breast Cancer Dataset from UCI machine learning repository. We achieved a maximum testing accuracy of 99.28% and a maximum precision of 97.22% while using 5-fold cross-validation. The proposed system exhibited satisfying accuracy on the dataset and outperformed many of the prominent existing methods.","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":"125867403","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}
Hossain Mansur Resalat Faruque, Kamal Hosen, A. S. M. Jannatul Islam, M. S. Islam
{"title":"Halogen Doped Electronic Properties of 2D ZnO: A First Principles Study","authors":"Hossain Mansur Resalat Faruque, Kamal Hosen, A. S. M. Jannatul Islam, M. S. Islam","doi":"10.1109/icaee48663.2019.8975495","DOIUrl":"https://doi.org/10.1109/icaee48663.2019.8975495","url":null,"abstract":"In recent times, two dimensional (2D) ZnO has attracted a great attention in the field of nano-research due to its extraordinary electronic, thermal and optical properties. In this paper, we have explored the effects of halogen impurity doping such as F, Cl, and Br atoms on the electronic properties of 2D ZnO using first principles calculation. The pristine 2D ZnO exhibits a semiconducting behavior with a direct bandgap of 1.67 eV on the Γ point. However, when impurities such as F, Cl, or Br atoms are introduced, the 2D ZnO shows semi-metallic behavior with almost zero bandgap. It is perceived that, owing to the introduction of F impurity, the zero bandgap is exhibited at the K point of the electronic band structure. However, in the case of Cl and Br impurities, the nearly zero bandgap is observed elsewhere rather than on the K point. Moreover, due to the introduction of impurity atoms, the Fermi level also shifted towards the conduction band (CB) suggesting an increase of the carrier concentration in the density of states (DOS) results. These findings might be very much beneficial when doping effect, especially halogen impurity doping is considered to modulate the electronic properties of 2D ZnO in the near future.","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":"131051524","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":"Influence of CdCl2 Treatment Temperature on Structural and Optical Properties of CdTe Thin Films","authors":"S. A. Razi, N. K. Das, S. Farhad, M. Matin","doi":"10.1109/ICAEE48663.2019.8975511","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975511","url":null,"abstract":"In this work the influence of the CdCl2 treatment temperature on the structural, morphological, and optical properties of CdTe thin films were investigated. The CdTe films were grown on CdS coated borosilicate glass by Close- Spaced Sublimation (CSS) technique using a standard recipe. The CdS coating was done by RF sputtering. The deposited CdTe films were treated with aqueous CdCl2 solution of 0.3 M molar concentration at 380°C, 385°C, 390°C, 395°C and 400°C for 25 minutes each. All the treated films show polycrystalline nature with intense peak at (111) orientation. The highest prominent peak and the largest crystallite size were found for 395°C treatment temperature. The SEM study confirms that the film treated at 395°C temperature is compact and shows uniform surface morphology. Sharp transmittance edges are found at 830 nm wavelength for all treated films which also signifies the higher crystallinity, suitable for high performance CdTe solar cell application.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"61 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":"126999742","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. Rawshan Habib, Naureen Khan, K. Ahmed, Mahbubur Rahman Kiran, A. Asif, Mohaiminul Islam Bhuiyan, Omar Farrok
{"title":"Quick Fire Sensing Model and Extinguishing by Using an Arduino Based Fire Protection Device","authors":"Md. Rawshan Habib, Naureen Khan, K. Ahmed, Mahbubur Rahman Kiran, A. Asif, Mohaiminul Islam Bhuiyan, Omar Farrok","doi":"10.1109/ICAEE48663.2019.8975538","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975538","url":null,"abstract":"Fire protection is obvious for safety purposes in human life because mishandling of fire sources can be the cause of serious accidents. In this paper, an Arduino based automatic fire alarm provider with extinguishing device is proposed for fire protection. The thermal model of a house and explanation of the proposed system is presented where smoke detector and temperature sensor assist the flame sensor. The flame sensor generates electric signals and transmits via mobile phone to the corresponding person to get notified. Besides this, the signal also triggers the fire extinguishing system automatically to take quick action. Simulation results are obtained by using MATLAB software. An Arduino based prototype of the proposed device is built and tested by creating artificial smoke and flame. Test results prove that, the proposed fire protection system responses quickly and effectively.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"61 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":"130665764","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":"Efficient energy allocation in wireless sensor networks based on non-cooperative game over Gaussian fading channel","authors":"Suryaia Rahman, M. Rashid, M. Z. Alam","doi":"10.1109/ICAEE48663.2019.8975691","DOIUrl":"https://doi.org/10.1109/ICAEE48663.2019.8975691","url":null,"abstract":"In this paper, we solve the energy optimization of Lloyd quantizer (LQ) based Robust iterative water-filling (LQ-RIWF) for a multiple-input multiple-output (MIMO) channel by minimizing the gradient of the local cost function (LCF) of each node by canceling the cross-interference through assigning a nulling set. This technique is known as LCF-LQ-RIWF. Our goal of this work is to design a non-cooperative game for an arbitrary Gaussian channel while guaranteeing convergence into an Nash Equilibrium (NE) state at minimum energy constraint. We first present the LQ-RIWF power allocation in NE state, and then extend the result for LCF-LQ-RIWF with global power constraint. We compare the sum-rate performance of LCF-LQ-RIWF with conventional power allocation techniques. A sufficient condition for the convergence of the proposed algorithm in NE state is derived and verified under the assumption that each node approaches a common water level based on instantaneous channel gain. Based on the theoretical investigation, we have carried out Matlab simulations and the results show that our proposed power allocation provides better performance compare to general sub-optimal techniques.","PeriodicalId":138634,"journal":{"name":"2019 5th International Conference on Advances in Electrical Engineering (ICAEE)","volume":"7 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":"116061968","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}