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.

Gender Identification from Bangla Name Using Machine Learning and Deep Learning Algorithms

Abstract: The names of people have a large significance in various types of computing applications. In general, people’s names usually have a potential distinction between genders. Detecting genders from names with higher accuracy could be very challenging for Bangla and English character-based Bangla names. In this article, we showed the machine learning and deep learning-based characterization system which can recognize sexual orientations from the Bangladeshi people’s names. The Bangla character-based name placed with an exceptionally higher exactness of 91% and for the English name, it was 89%. We likewise consolidated diverse machine learning and deep learning classifiers techniques like random forest, SVM, Naive Bayes, impact learning, CNN, LSTM, etc., to break down which calculations give better outcomes. Besides, a Python pre-trained model on gender identification by Bangla’s name has been revealed.

Speech Based Deception Detection Using Bispectral Analysis

Abstract: Speech is considered as one of the most efficient and effective way to communicate with each other. However, a deception is a very common phenomenon in speech communication. It is difficult to detect if anyone is actually telling the truth or not. This study proposes a neural response based novel technique to identify the true or false from speech. In this study, the speech signal is used as the input to the auditory nerve model. This technique applies the higher order statistics called bispectrum to the auditory neurogram to distinguish the true and false from speech. Different parameters of the bispectrum are used as a feature to detect a deception from speech. Deceptive speech can be detected accurately by using the 'normalized bispectral entropy' of the bispectrum feature parameters for the envelope information (ENV) data and the 'maximum bispectrum' of the bispectrum feature parameter for the temporal fine structure (TFS) data. Speech based deception detection is a speech processing method which provides better accuracy to detect deception than many other deception detection techniques. This technique could be applied effectively for the national security systems.

Design and Implementation of Automated Ankle Foot Orthosis for Foot Drop Patients Using Gait Cycle EMG Analysis

Abstract: Foot drop is known as gait abnormality in which the dropping of the forefoot happens due to the weakness of Tibialis Anterior Muscle for the damage of the common fibular nerve in the anterior portion of the lower leg. In this research, those patients are considered who have foot drop for Guillain–Barre syndrome (GBS). GBS is a peripheral nerve disorder for which bilateral foot drop happens to the patients. So, the aim of this research is to develop an automated Ankle Foot Orthosis (AFO) which will aid the GBS patients in their gait cycle while walking. For the development of this AFO, an EMG analysis has been conducted on both normal people (20 persons, Male 20-45 years) and GBS patients (10 patients, Male 20-45 years) and compared to find out the deviation of the patient’s one from the normal people. The findings of the EMG study show that the stance phase of the gait cycle is not affected by the GBS as correlation coefficient values are in between 0.95 to 1 where the swing phase very much deviates from the normal pattern as the coefficient values are in between 0.6 to 0.7 as well as short swing phase and no heel strike during walking. Considering these, automated AFO has been developed and implemented to test the feasibility and effectiveness on patients. The experimental results show that the effect of GBS on swing phase can be lessened as the value of correlation coefficient increases to 0.85 to 0.9 with long swing phase and proper heel strike on terminal swing phase.

Effects of carrier gas flow-rate and oxygen admixture ratio on particle parameters in Ar-O 2 plasma

Abstract: Taking into account the strong plasma-particle interactions and particle loading effects, a model of plasma-particle interaction of argon-oxygen plasma has been developed for the numerical predict the particle temperature, velocity, trajectory and plasma temperature isotherm during the in-flight treatment. In this model the conservative equations solves the conservative equations to predict the plasma trajectories under local thermal equilibrium condition. It is found that the carrier gas flow-rate strongly affects the particle temperature and the admixture ratio of oxygen to argon affects the plasma temperature isotherm as well as the particle temperature.

Predicting Individual Substance Abuse Vulnerability Using Machine Learning Techniques

Abstract: Substance abuse is the unrestrained and detrimental use of psychoactive chemical substances, unauthorized drugs, and alcohol. Continuous use of these substances can ultimately lead a human to disastrous consequences. As patients display a high rate of relapse, prevention at an early stage can be an effective restraint. We therefore propose a binary classifier to identify any individual’s present vulnerability towards substance abuse by analyzing subjects’ socio-economic environment. We have collected data by a questionnaire which is created after carefully assessing the commonly involved factors behind substance abuse. Pearson’s chi-squared test of independence is used to identify key feature variables influencing substance abuse. Later we build the predictive classifiers using machine learning classification algorithms on those variables. Logistic regression classifier trained with 18 features can predict individual vulnerability with the best accuracy.