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.

Bangladeshi Banknote Recognition in Real-time using Convolutional Neural Network for Visually Impaired People

Abstract: Visually impaired people face extreme difficulties in recognizing paper currencies for day-to-day transactions as the texture and shape of many currencies are very similar. In this paper, an automated system for identifying the Bangladeshi banknotes using a convolutional neural network has been proposed for helping visually impaired people. A new dataset has been created consisting of more than 70,000 images of currently available Bangladeshi banknotes. The development of the system includes dataset building, creating and training the convolutional neural network model, and testing it in real-time. For verifying the efficacy of the proposed method, it has been tested in various backgrounds. The system can identify the eight banknotes used in Bangladesh with an average accuracy of 92% and exhibit the result with both textual and auditory output. Moreover, the system is invariant of the orientation and sides of notes. Visually impaired people will be able to easily use it in daily transactions.

Semantic Meaning Based Bengali Web Text Categorization Using Deep Convolutional and Recurrent Neural Networks (DCRNNs)

Abstract: Web text categorization is a procedure of deliberately assigning a web text document into one of the pre-defined classes or categories. It is a very challenging task to manipulate, organize, and categorize an enormous amount of web text data in manually. This paper proposes an automatic text categorization framework to classify Bengali web text data using deep learning. The proposed framework comprises of three key constituents: text to feature extraction, training, and testing. The categorization framework is trained, validated, and tested at 120K, 12K, and 36K datasets, respectively. The proposed system achieved \(99.00\%\) accuracy in the training phase, \(96.00\%\) in the validation phase, and \(95.83\%\) in the testing phase, respectively.

Heart rate variability analysis using approximate entropy and detrended fluctuation for monitoring heart condition

Abstract: Variation in time between two successive heart beats occurring due to internal and external stimulation causes Heart Rate Variability (HRV). HRV is a tool for indirect investigation of both cardiac and autonomic system function in both healthy and diseased condition. It has been speculated that HRV analysis by nonlinear method might bring potentially useful prognosis information into light which will be helpful for assessment of cardiac condition. In this study, HRV from two types of data sets (normal sinus rhythm and sinus arrhythmia) are analyzed which are stored in MIT-BIH (Massachusetts Institute of Technology - Beth Israel hospital) database, an extended collection of recorded physiological signals. Then two nonlinear methods, approximate entropy (ApEn) and detrended fluctuation analysis (DFA), have been applied to analyze HRV of both Arrhythmia patients and people having normal sinus rhythm. It has been clearly shown that nonlinear parameters obtained from these two methods reflect the opposite heart condition of the two types of subjects under study, healthy and diseased, by HRV measures. Thus, value of the nonlinear parameters found in this work can be used as standard when treating suspected patients for diagnosis of Arrhythmia. Also, by measuring these nonlinear parameter values, heart condition can be understood.

Multi-agent system modeling for managing limited distributed generation of microgrid

Abstract: This paper focuses on operation of small scale renewable plants so that the energy produced can be utilized to its highest potential Energy crisis being one of the main problems is leading the researchers to find fossil fuel replacement which is eventually renewable energy In most cases, renewable energy is unpredictable as tehy rely on the nature Besides, in developing countries it is discouraged to install renewable technology due to their random nature In order to design a reliable microgrid where renewable resources contribute to its grid power supply, multi-agent system has been incorporated to add intelligence to the system The various loads to be fed are divided according to importance The proposed concept also allows sharing of load among utility supply and renewable sources during normal operation

Total phenolic contents and free radical scavenging activity of different parts of jatropha species

Abstract: Jatropha species is a worldwide important crop. Each part of this species is used in traditional medicine to treat the various diseases. In this research, antioxidant activity and total phenolic content of different parts of Jatropha species were investigated by using two extraction processes: ultrasound-assisted extraction and maceration. Based on the antioxidant activity and phenolic content, it can be summarized that the extracts obtained by ultrasound-assisted extraction process showed potent antioxidant activity and may be related to their phenolic content. The root extracts of J. gossypiifolia obtained by ultrasound-assisted extraction process showed the highest antioxidant activity and leaves of J. curcas showed highest phenolic contents as compared to maceration process. Among the different parts of these species, all the parts of J. gossypiifolia showed the higher activity as compared to J. curcas. Finally, Jatropha species’ by-products with strong radical scavengers can be considered as potential sources of natural antioxidants.