Chittagong University of Engineering & Technology

About: Chittagong University of Engineering & Technology is a education organization based out in Chittagong, Bangladesh. It is known for research contribution in the topics: Computer science & Renewable energy. The organization has 1200 authors who have published 1444 publications receiving 10418 citations. The organization is also known as: Engineering College, Chittagong & Bangladesh Institute of Technology, Chittagong.

Remote ECG Monitoring and Syncope Detection System Using Deep Learning

Abstract: With the growth of life expectancy, most people are facing health problems and most of these are causing by heart disease frequently It is more important to design an effective system that can diagnose the forthcoming happening of heart disease In this paper, a system is developed to detect atrial fibrillation arrhythmia and syncope due to arrhythmia This system uses the Recurrent Neural Network with Long Short-Term Memory (LSTM) algorithm for detecting atrial fibrillation The system provides various features to the user, such as detecting arrhythmia possibility through symptoms and sending a notification to the doctors or family members according to the stage of the possibility of disease It also detects syncope caused by arrhythmia and sends alerts to family members A 3-axis accelerometer uses for identifying syncope A SparkFun AD8232 sensor senses the patient's ECG signal and those signals processed in Raspberry Pi 3 by a deep learning algorithm model Estimation of result claims that the system can accomplish a positive impact on the healthcare system

A Semi-supervised Approach to Detect Malicious Nodes in OBS Network Dataset Using Gaussian Mixture Model

Abstract: In this study, we have followed a semi-supervised approach for the classification of optical burst switching (OBS) network traffics generated by the network’s edge nodes. We used expectation maximization (EM) technique for Gaussian mixture model (GMM) to obtain a probabilistic classification of the OBS nodes. For this purpose, we used a trustworthy OBS network dataset from UCI machine learning repository. Preprocessing and principal component analysis were applied to the dataset for arranging the data so that GMM can play its role fairly. Only 1% (10 samples) of labeled data from OBS dataset was used to initialize the parameters of GMM and the rest 99% was used for testing performance of the model. We found a maximum accuracy of 69.7% on the test data using just 1% labeled data with the tied covariance type of the constructed GMM. The significance of this result is that it shows the GMM can be used in classification of OBS networks and other similar networks in semi-supervised way when one has very few labeled data and when labeling a huge dataset is not feasible.

A comparative analysis of the characterization methods for submicron silicon waveguide propagation loss

Abstract: An important parameter in integrated optical device is the propagation loss of the waveguide. Its characterization gives the information of the fabrication quality as well as the information of other passive devices on the chip as it is the basic building block of the passive devices. Although, over the last three decades many methods have been developed, there is not a single standard present yet. This paper presents a comparative analysis of the methods existing from the past as well as methods developed very recently in order to provide a complete picture of the pros and cons of different types of methods and from this comparison the best method is suggested according to the authors opinion. To support the claim, apart from the analytical comparison, this paper also presents a comparison performed with the experimental results between the suggested best method which is recently proposed by Massachusetts Institute of Technology (MIT) researchers based on undercoupled all-pass microring structure and the popular cut-back method.

Application of Rheology Modeling to Natural Rubber and Lead Rubber Bearings: a Simplified Model and Low Temperature Behavior

Abstract: A rheology originally proposed for high damping rubber bearing (HDRB) is applied to natural rubber bearing (RB) and lead rubber bearing (LRB) along with its simplified form. Comparing HDRB, the elasticplastic equilibrium responses were found to be more dominant than the rate-dependent response due to viscosity for RB and LRB. Moreover, the overstress in loading/unloading was found to be analogous. The dependency of nonlinear viscosity on current strain was found to be weak in contrast to the existence of considerable nonlinearity in elastic response. The original rheology model considers the nonlinear elastoplastic and viscosity induced rate-dependent behavior into account, while the viscosity effect is eliminated in the simplified version. The models are implemented in a finite element code. The modeling effects of bearings on the seismic responses of a multi-span continuous highway bridge are investigated via nonlinear dynamic analyses for two strong earthquake ground motions. Three analytical models of isolation bearings are considered for comparison: the conventional design models and the proposed two models. Model parameters for the bearings were determined for two temperature conditions: the room temperature (+23 ◦ C) and the low temperature ( 20 ◦ C) based on experimental data. The implication of the rheology models for response prediction of a prototype bridge is studied by comparing the rotation of a plastic hinge in pier and shear strain at the top of the bearing. The comparison suggests that the modeling of RB and LRB considering rheology properties is important for rational prediction of the seismic response of highway bridges, particularly at low temperature condition.

A smart review on the gas transportation model of coalbed methane gas based on the optimized pipeline network

Abstract: Coalbed methane is extracted from the adsorbed state in coal seams with lower pressure & production rate. In previous studies, researchers only focused on the methods that were developed for making a relationship between the underground production rate & surface flow rate without any type of optimization procedure. In this study, the main purpose is to do a review on finding out of surface layout plan to optimize the maximum gas flow rate by developing an improved pipeline network. The more the optimization of the layout plan for designing pipeline network, the lower the amount of investment need to provide. Here, a mathematical model is proposed for the gas transportation based on the hydraulic & thermodynamic calculations of the pipeline network. Not only that, but also the filtration mechanism of depressurization & desorption for the gas flow through pipe section are evaluated here. After that, the pressure drop & pipeline efficiency are explored to find out the best design of pipeline network from the observed results. Finally, based on this study, many uncertainties can be reduced associated with the installation of pipeline network for gas transportation.