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.

A Deep Neural Network Model for Predicting Electric Fields Induced by Transcranial Magnetic Stimulation Coil

Abstract: This article proposes a deep neural network (DNN) model to predict the electric field induced by a transcranial magnetic stimulation (TMS) coil under high-amplitude and low-frequency current pulse conditions. The DNN model is comprised of an input layer with 6 neurons, three non-linear hidden layers with a total of 1088 neurons, and a linear single output layer. The model is developed in Google Colaboratory environment with TensorFlow framework using six features including coil turns of single wing, coil thickness, coil diameter, distance between two wings, distance between head and coil position, and angle between two wings of coil as the inputs and electric field as the output. The model performance is evaluated based on four verification statistic metrics such as coefficient of determination (R2), mean squared error (MSE), mean absolute error (MAE), and root mean squared error (RMSE) between the simulated and predicted values. The proposed model provides an adequate performance with $\text{R}^{2} =0.766$ , MSE = 0.184, MAE = 0.262, and RMSE = 0.429 in the testing stage. Therefore, the model can successfully predict the electric field in an assembly TMS coil without the aid of electromagnetic simulation software that suffers from an extensive computational cost.

The presence of radioactive and metal contaminants in wild mushrooms grown in Chattogram hill tracts, Bangladesh

Abstract: Wild mushrooms are considered as bioindicators of environmental pollution. Different species of mushrooms (edible and medicinal), commonly available in Chattogram hill tracts (CHT) area of Bangladesh, were analyzed for prevailing concentrations of heavy metals and radioactive materials via atomic absorption spectroscopy and γ-ray spectrometry, respectively. The metal contents in some species show higher than the levels recommended by WHO/FAO for metals in food and vegetables. In case of terrestrial radionuclides, the concentrations of 232Th and 40K exceeded the global average value of 82 Bq/kg and 310 Bq/kg, respectively (UNSCEAR, 2000). Since the studied mushroom grew naturally, the obtained results provide useful information on the presence of radioactive-, toxic- and essential elements in the CHT area which may require for any further study of other environmental matrices in this area.

Computational Investigation of Turbulent Flow Development in 180° Channel with Circular Cross Section

Abstract: The present study focuses on the analysis of flow characteristics inside a 180° bent channel by adopting two distinct RANS model namely, Realizable k-ϵ and Reynolds Stress Model (RSM). The computation results, obtained from both case study have been validated against experimental data at different cross-sections throughout the bend region and downstream tangent for velocity distribution. The anisotropic behavior of turbulent flow was illustrated for both case study inside the bend region and it has been established that after 3° the flow gradually became more intense at the outer core. Pressure coefficient throughout the u-channel was depicted for both turbulence model and a characteristic feature has been obtained. Due to centrifugal force and high inlet Reynolds number, a pair of counter-rotating Dean vortices were constructed at different stations inside the bend region. From both demonstrations, it was revealed that, Realizable k-ϵ model provided relatively better approximation.

Applying Machine Learning Classifiers on ECG Dataset for Predicting Heart Disease

Abstract: Sudden demise from heart disease is rising in a terrible rate and this disease has become a common cause of death worldwide. But it is a matter of hope that heart diseases are avertible by making simple lifestyle changes coupled with early prognosis which can greatly improve its recovery. Identifying high risk patients is difficult due to the multifaceted characteristic of various threat factors such as high cholesterol, high blood pressure, diabetes etc. Most of the time, diagnosis of heart disease depends on doctor’s observation and expertise instead of utilizing the large amount of knowledge-rich medical dataset. To change the situation, scientists and doctors have turned to machine learning techniques to evaluate screening results along with other medical parameters to predict heart disease. For heart disease prediction, this study implements five machine learning algorithms including Support Vector Machine, Logistic Regression, K-nearest Neighbor, Naive Bayes, and Ensemble Voting Classifier on a dataset with 1190 records accumulated from UCI repository. The dataset combines five independent ECG dataset which gives us an extra edge to achieve our objectives. Relation among the attributes in the dataset is analyzed before the accuracy is calculated. Among the five classification algorithms, Support Vector Machine outperforms other classifiers with the accuracy of 85.49%. We hope this study will ensure early diagnosis of heart disease and increase the chance of survival.

Optimal design and performance study of a low-index-contrast MMI optical coupler

Abstract: The multimode interference (MMI) coupler is a versatile component for photonic signal processing applications. In present day, research scenarios based on low-index-contrast MMI couplers give more scope of study as it has certain advantages over high-index-contrast MMI couplers. In this work we presented an optimal design for the low-index-contrast MMI coupler. From various possible structures, we considered Silica-on-Silicon based 4×4 MMI coupler. Various techniques such as conventional self imaging, improved self-imaging and Genetic algorithm are used here, with numerical analysis such as mode propagation analysis, beam propagation method for evaluating optimal performance by adjusting the parameters of the structure. The optimum structure is finally selected one from them by comparing the results of these different techniques.