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: Renewable energy & Dielectric. 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.

Isolated Bangla word recognition and speaker detection by semantic modular time delay neural network (MTDNN)

Abstract: Speaker recognition is the identification of a person from characteristics of his/her voices and speech recognition concerns the recognizing of what is being said by the speaker. This paper presents a framework to recognize the isolated Bangla words and the corresponding speaker by proposing a semantic modular time delay neural network (MTDNN). Underlying acoustic fuzziness of human utterance and fluctuations of data due to environmental disturbance are managed by well-known Fuzzy C Means clustering technique. We have used MFCC features to recognize Bangla words and speaker detection. Experimental result with different individuals show that the proposed framework is functioning quite satisfactory with average accuracy of 82.66%.

A 2×2 MEMS Optical Switch Based on Piezoelectric Actuation

Abstract: A fully micromachined single mode 2times2 cross-bar optical switch based on noble piezoelectric actuation has been designed and simulated for small volume, low insertion loss and low switching voltage Piezoelectric unimorph bender was used for actuating the micromirror of the switch The performance of the switch was simulated in MATLAB The required tip displacement of the micromirror had found 3448mum at 50V For 1462mum input and output fiber end separation the insertion loss (IL) of the designed switch had found 07102dB, 16919dB and 2219dB at 800nm, 1310nm and 1550nm wavelength respectively

Numerical analysis of MHD free convection boundary layer flow of heat and mass transfer in case of air and water

Abstract: The present work has been studied the effect of various parameters on MHD boundary layer flow of heat and mass transfer in case of air and water. The governing partial differential equations are transformed to higher order ordinary differential equations by using similarity transform. This coupled ordinary differential equations are performed by shooting iteration technique along with Runge-Kutta integration scheme. The effects of various parameters on velocity, temperature and concentration profiles are discussed numerically and shown graphically. Therefore, the results of velocity field decreases for increasing values of magnetic parameter and chemical reaction parameter in case air and salt water but increases for Grashof number and modified Grashof number. The temperature field decreases in the presence of magnetic parameter but significant increasing effect for chemical reaction parameter, Grashof number and modified Grashof number in case of air and salt water. Also, the concentration profile is slightly increased for increasing the values of magnetic parameter and slightly decreased for Grashof number and modified Grashof number but significant decreasing effect are observed for reaction parameter. Finally, the numerical values of the shear stress, rate of temperature and rate of concentration are also shown in a tabular form Bangladesh J. Sci. Ind. Res. 51(2), 139-146, 2016

Hydrodynamics of Microalgae and CO 2 flow in a Tubular Photobioreactor and consequent effects on Microalgae growth

Abstract: In biofuel technology from microalgae, the main optimal factors for microalgae cultivations are light, CO 2 and temperature. As microalgae are photosynthetic microorganisms thus they convert sunlight, water and CO 2 to algal biomass. We consider a two phase flow for CO 2 and Microalgae suspension to understand fluid dynamics phenomena after injecting CO 2 gas inside a tubular Photobioreactor (PBR).The growth rate of the microalgae cell is taken as a function of available sun light at Chittagong University of Engineering & Technology (CUET) in our study. A 20.94m long and 0.025m tubular PBR is considered for the simulation. To observe the microalgae cell growth, we selected the 21st June for a bright sunny and the longest day of a year. From the simulation after day seven we observed a very slow growth for the microalgae culture. It is noted that the growth related to concentration of microalgae is increased by day length with respect to continuous sunlight. A small fluctuation of shear rate around Uloop area is also found in our simulation which may be caused to reduce the volumetric production due to cell fragility. From the velocity profile we found that, the velocity is generally higher in the middle of the tube gives a parabolic shape of the suspension flow.

Performance Analysis of Bearing fault diagnosis using Convolutional Neural Network

Abstract: Rolling element bearing is the most important and critical mechanical device of rotating machinery. Identifying and trouble-shooting bearing faults in an early stage is necessary to prevent possible damage. The traditional intelligent bearing fault diagnosis method usually need preprocess the signal, manually extracting the features and pattern classification. The process of feature extraction requires much professional knowledge and complex feature extraction for this reason the model does not achieve satisfactory result. To overcome the complexity of traditional method, In this paper, the authors propose a deep learning algorithm for detection and classification of bearing faults based on Convolutional Neural Network, which does not need any feature extraction method. To evaluate the proposed CNN model, the bearing fault diagnosis experiment were carried out using transfer learning method and also compared with four other models. Finally, on CWRU's bearing dataset, we implemented the proposed model. The achieved accuracy indicates that the proposed CNN model is highly reliable in bearing fault diagnosis.