BRAC University Institutional Repository
Preserving Knowledge, Advancing Research, Sharing Scholarship
A digital platform for collecting, preserving, and sharing BRAC University’s scholarly, academic, and institutional outputs.
Contribute to the Repository
Faculty members and students are invited to submit their research publications, theses, dissertations, and scholarly works to increase visibility, access, and long-term preservation.
Recent Submissions
COVID-19 and its implications to the assessment of sustainable palm oil supply chain management: An Indonesian perspective
(Frontiers Media S.A., 2021-01-01) Hafiz, Nusrat; Azmi K.M.; Nimfa D.T.; Latiff A.S.A.; Wahab S.A.; BRAC Business School
Motivated by the low sustainability index and pressure to meet the global demand for eco-friendly crude palm oil (CPO) in the pandemic-ridden environment, this research aims to investigate the implications of the COVID-19 pandemic to assess the drivers of sustainable supply chain management (SSCM) of the Indonesian CPO sector to tackle supply chain disruptions. To achieve this aim, the study seeks to determine the sustainability drivers to accommodate the pandemic-ridden environment and if sustainability indicators can help improve the supply chain management of the CPO sector. A methodology is divided into two interrelated parts: first, based on a careful review of extant literature of the CPO sector and sustainable supply chain in the light of pandemic. The proposed methodology is then tested using the response data of 108 oil mills' representatives collected through survey questionnaires and analyzed using statistical tools of reliability, distribution, Kaiser–Meyer–Olkin (KMO), Confirmatory Factor Analysis (CFA), and diagnostic tests of CFA. The findings designate the environmental costs, rapidity, and adaptability as core economic indicators; the social and workforce development, health, and safety workforce development and consumer issues as crucial social indicators; while energy and material efficiency, management of waste and emissions, and sustainable suppliers as the best environmental indicators. This study provides a holistic platform on the implications of the pandemic to assess the SSCM of the CPO sector. These findings are expected to aid the industrial managers in employee skills and health protocols, customer service, and environmental management. The study is also anticipated to guide the supply-chain partners and government policymakers to take initiatives on SSCM in the context of the pandemic.
CovRoot: COVID-19 detection based on chest radiology imaging techniques using deep learning
(Frontiers Media SA, 2024-01-01) Niloy, Ahashan Habib; Fahim, S. M. Farah Al; Parvez M.Z.; Shiba, Shammi Akhter; Faria, Faizun Nahar; Rahman, Md. Jamilur; Hussain, Emtiaz; Tamanna T.; Department of Computer Science and Engineering
The world first came to know the existence of COVID-19 (SARS-CoV-2) in December 2019. Initially, doctors struggled to diagnose the increasing number of patients due to less availability of testing kits. To help doctors primarily diagnose the virus, researchers around the world have come up with some radiology imaging techniques using the Convolutional Neural Network (CNN). Previously some research methods were based on X-ray images and others on CT scan images. Few research methods addressed both image types, with the proposed models limited to detecting only COVID and NORMAL cases. This limitation motivated us to propose a 42-layer CNN model that works for complex scenarios (COVID, NORMAL, and PNEUMONIA_VIRAL) and more complex scenarios (COVID, NORMAL, PNEUMONIA_VIRAL, and PNEUMONIA_BACTERIA). Furthermore, our proposed model indicates better performance than any other previously proposed models in the detection of COVID-19.
Automatic slice growing method based 3D reconstruction of liver with its vessels
(Institute of Electrical and Electronics Engineers Inc., 2014-12-23) Alom, Md. Zahangir; Mostakim, Moin; Biswas, Rubel; Chakrabarty, Amitabha; Department of Computer Science and Engineering
In the recent years, reconstructing 3D liver and its vessels from abdominal CT volume images becomes an inevitable and necessary research field. In this paper, a method of 3D reconstruction of liver with its vessels has been implemented, which involves volume preprocessing, de-noising, segmentation, contouring, and combination of different modalities. An advanced liver segmentation algorithms have been proposed: The first one is a 2.5D method that utilizes automatic Slice Growing Method (SGM) to segment liver part of each slice of a data set. It takes advantage of curvature control of level set segmentation method to distinguish liver and adjacent organs. It is proved that the result of this proposed method is much better than simple 3D level set method in liver segmentation. In the case of liver vessel segmentation, we have proposed an improved smoothing method dedicate to 3D vascular volume which results from region growing segmentation method. The cooperation of region growing method and proposed smoothing method has been demonstrated the possibility of efficient vessel segmentation with very accurate results. And the results indicate that our method is suitable for anatomical studying and surgical planning.
University course advising: Overcoming the challenges using decision support system
(Institute of Electrical and Electronics Engineers Inc., 2014-12-23) Roushan, Tanvir; Chaki, Dipankar; Hasdak, Onishim; Chowdhury, Md. Syeed; Rasel, Annajiat Alim; Rahman, M. Abdur; Arif, Hossain; Department of Computer Science and Engineering
Universities require a fast and reliable system to provide academic advising to its students, register them into different courses, and to manage change requests. Currently in Bangladesh, academic advising is done mostly on paper, as seen in many of the public and private universities. In this paper, we propose a unique online-based system that would make the university course advising and registration process easier and intelligent. The proposed online tool will work very closely and interdependently with each educational institution's own course curriculum, grading system, and university policies. The intention of this paper is to find key challenges in the system and to evaluate the efficiency of an easy-to-read web-based course advising and decision support tool. The tool expedites the academic advising process. It acts as an online advisor for the students, eases the task and save time of the advisors by automation of redundant tasks and reducing paper work. The recommended advising software through its decision support system aids both students and teachers with unique facilities. It also provides additional time for advisors to focus on students' development.
Evaluation of lettuce growth, yield, and economic viability grown vertically on unutilized building wall in Dhaka city
(Frontiers Media S.A., 2021-03-15) Islam R.; Solaiman A.H.M.; Kabir M.H.; Arefin S.M.A.; Azad M.O.K.; Siddiqee, Mahbubul H.; Alsanius B.W.; Naznin M.T.; Department of Mathematics and Natural Sciences
Production of safe food in the densely populated areas of the developing countries is the most challenging issue due to the speedy urbanization, fragile food transportation facilities, and reduced farmlands. Given this background, a study was conducted to evaluate the agronomic properties and economic viability of lettuce grown vertically in the wall of building in Dhaka city, Bangladesh. Two lettuce cultivars (V1: Green wave and V2: New red fire) and three organic growing media (P1: 40% soil + 40% vermicompost + 20% coir; P2: 50% soil + 50% vermicompost; P3: 20% soil + 40% vermicompost + 40% spent mushroom compost) along with control (P0:100% soil) were used. The results revealed that plant height, leaf area, fresh weight, dry weight, and total yield of leaf lettuce were significantly increased when the green-leafed cultivar (VI) was grown in the P1 compared to all other treatments, but V2 got maximum sensory attribute scores when grown in the P1. Lettuce leaves grown in the formulated growing media (P1, P2, and P3) had higher microbial infestation whereas, a lower content occurred in the P0. The higher economic return was observed in V1P1. These results provided baseline information for further study on urban commercial vertical farming on the building walls. These demonstrate the agronomic and economic potential for vertical farming in densely populated areas but emphasize the need for optimized food safety strategies.