scispace - formally typeset
Search or ask a question
Institution

Dhaka International University

EducationDhaka, Bangladesh
About: Dhaka International University is a education organization based out in Dhaka, Bangladesh. It is known for research contribution in the topics: Business & Computer science. The organization has 79 authors who have published 92 publications receiving 651 citations. The organization is also known as: DIU.


Papers
More filters
Journal ArticleDOI
TL;DR: An effort to compile and analyze epidemiological outbreak information on COVID‐19 based on the several open datasets on 2019‐nCoV provided by the Johns Hopkins University, World Health Organization, Chinese Center for Disease Control and Prevention, National Health Commission, and DXY.
Abstract: There is an obvious concern globally regarding the fact about the emerging coronavirus 2019 novel coronavirus (2019-nCoV) as a worldwide public health threat. As the outbreak of COVID-19 causes by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) progresses within China and beyond, rapidly available epidemiological data are needed to guide strategies for situational awareness and intervention. The recent outbreak of pneumonia in Wuhan, China, caused by the SARS-CoV-2 emphasizes the importance of analyzing the epidemiological data of this novel virus and predicting their risks of infecting people all around the globe. In this study, we present an effort to compile and analyze epidemiological outbreak information on COVID-19 based on the several open datasets on 2019-nCoV provided by the Johns Hopkins University, World Health Organization, Chinese Center for Disease Control and Prevention, National Health Commission, and DXY. An exploratory data analysis with visualizations has been made to understand the number of different cases reported (confirmed, death, and recovered) in different provinces of China and outside of China. Overall, at the outset of an outbreak like this, it is highly important to readily provide information to begin the evaluation necessary to understand the risks and begin containment activities.

146 citations

Journal ArticleDOI
TL;DR: A VGG-16 (Visual Geometry Group, also called OxfordNet) Network-based Faster Regions with Convolutional Neural Networks (Faster R-CNN) framework is introduced to detect COVID-19 patients from chest X-Ray images using an available open-source dataset.

94 citations

Journal ArticleDOI
20 Feb 2021-Sensors
TL;DR: In this paper, a feature fusion using the deep learning technique assured a satisfactory performance in terms of identifying COVID-19 compared to the immediate, relevant works with a testing accuracy of 99.49%, specificity of 95.7% and sensitivity of 93.65%.
Abstract: Currently, COVID-19 is considered to be the most dangerous and deadly disease for the human body caused by the novel coronavirus. In December 2019, the coronavirus spread rapidly around the world, thought to be originated from Wuhan in China and is responsible for a large number of deaths. Earlier detection of the COVID-19 through accurate diagnosis, particularly for the cases with no obvious symptoms, may decrease the patient’s death rate. Chest X-ray images are primarily used for the diagnosis of this disease. This research has proposed a machine vision approach to detect COVID-19 from the chest X-ray images. The features extracted by the histogram-oriented gradient (HOG) and convolutional neural network (CNN) from X-ray images were fused to develop the classification model through training by CNN (VGGNet). Modified anisotropic diffusion filtering (MADF) technique was employed for better edge preservation and reduced noise from the images. A watershed segmentation algorithm was used in order to mark the significant fracture region in the input X-ray images. The testing stage considered generalized data for performance evaluation of the model. Cross-validation analysis revealed that a 5-fold strategy could successfully impair the overfitting problem. This proposed feature fusion using the deep learning technique assured a satisfactory performance in terms of identifying COVID-19 compared to the immediate, relevant works with a testing accuracy of 99.49%, specificity of 95.7% and sensitivity of 93.65%. When compared to other classification techniques, such as ANN, KNN, and SVM, the CNN technique used in this study showed better classification performance. K-fold cross-validation demonstrated that the proposed feature fusion technique (98.36%) provided higher accuracy than the individual feature extraction methods, such as HOG (87.34%) or CNN (93.64%).

73 citations

Journal ArticleDOI
TL;DR: In this article, the authors provided a comprehensive study of the contemporary renewable energy scenario in Bangladesh in terms of distribution, research and infrastructural development in the country and provided an overview of utilizing renewable energy with higher reliability using concept of smart grids where we have used wind power, solar power, biogas, biomass and micro hydro power for rural and remote areas.
Abstract: Bangladesh is a densely populated country located at the South-East corner of Asia. Only 48.5% of people here have access to the grid electricity. This paper provides a comprehensive study of the contemporary renewable energy scenario in Bangladesh in terms of distribution, research and infrastructural development in the country. Renewable energy is the smartest solution of increasing energy crisis caused by using fossil fuels. But sometimes it faces question of reliability which can be overcome by using various renewable power sources which would also be cost effective for developing and under developed countries like Bangladesh. This is the ultimate solution to shorten power crisis instead of depending only on the national grid supply which is mostly run by fossil fuel. Â Especially in rural areas there is a scarcity of water during harvesting period and our proposed scheme is a great solution to overcome this problem which would led to an economic development of Bangladesh. We are providing an overview of utilizing renewable energy with higher reliability using concept of smart grids where we have used wind power, solar power, biogas, biomass and micro hydro power for rural and remote areas. We are proposing a hybrid system which is expected to run effectively both on grid and off grid operation to utilize maximum possible renewable resources. The overall load dispatch scenario is controlled by the availability of renewable power, total system load demand and the proper management of the battery bank. The incorporation of a battery bank makes the control operation more practical and relatively easier. A well designed hybrid energy system like smart grid can be cost effective, has a high reliability and can improve the quality of life in remote areas.

49 citations

Journal ArticleDOI
TL;DR: In this article, a new prediction model for the long-term performance of fiber reinforced polymer (FRP) bars is developed based on an existing model and the data collected in this paper.
Abstract: Fiber reinforced polymer (FRP) bars are being widely used in civil engineering applications to replace steel bars due to their excellent durability. Existing research on the durability of FRP bars mainly focuses on glass fiber reinforced polymer (GFRP) and basalt fiber reinforced polymer (BFRP) bars. Different conclusions have been drawn due to differences in fibers, resins, fiber volume fractions, solution concentrations, and aging temperatures adopted by researchers. Some results are even contradictory, especially between relatively recent and previous studies. In this paper, data of 557 experiments on tensile strength and elastic modulus of GFRP and BFRP bars exposed to different harsh environments are collected from existing literature, and the durability of GFRP and BFRP bars in the water, acid, salt, and alkali solutions are investigated. Different influence factors are considered including the matrix type, fiber volume fraction and exposure temperature, etc. Furthermore, a new prediction model for the long-term performance of FRP bars is developed based on an existing model and the data collected in this paper. The tensile strength of GFRP and BFRP bars degenerates faster in alkali, and water environments, followed by acid solution, and has the best durability in salt solutions. Except the water solution, GFRP bars show better corrosion resistance than BFRP bars in alkali, salt, and acid solution. The new prediction is simple in form and clear in the physical meaning and can be considered for both GFRP and BFRP bars.

47 citations


Network Information
Related Institutions (5)
Tribhuvan University
7.6K papers, 99K citations

78% related

Jahangirnagar University
3.8K papers, 55.2K citations

77% related

University of Dhaka
9.8K papers, 136.4K citations

76% related

Bahir Dar University
3.1K papers, 63.6K citations

75% related

Bangladesh University of Engineering and Technology
7.6K papers, 83.9K citations

74% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
202319
202269
202123
202017
201913
20186