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
Characterizing the co-existence of metallo-β-lactamase-producing and extended-spectrum β-lactamase-producing Escherichia coli and Klebsiella pneumoniae isolates in community wastewater samples of Dhaka, Bangladesh
(IWA Publishing, 2025-04-01) Ahmad Zahra, Maftuha; Tasnim Toma, Tasfia; Nasreen, Shamima; Zarin, Zarin Tasnim Rafia; Khan, Zerin Tasnim Siddiqa Elma; Haque, Fahim Kabir Monjurul; Department of Mathematics and Natural Sciences
Escherichia coli and Klebsiella pneumoniae isolates with multiple antibiotic-resistance genes in wastewater pose serious public health risks, as they can potentially contaminate the food and water supply. The main aim of this study was to isolate and identify E. coli and K. pneumoniae from community wastewater samples, and determine their antibiotic-resistance profiles and their antibiotic-resistant genes. From the northern part of Dhaka, Bangladesh, 36 wastewater samples were collected across 11 different areas, which were then serially diluted, and cultured using selective media. Isolates were identified via polymerase chain reaction. Out of the 197 isolates identified, E. coli and K. pneumoniae accounted for 55.8% (n = 110) and 44.2% (n = 87), respectively. Antibiotic susceptibility tests revealed multidrug resistance (MDR) in 30% of E. coli and 35.56% of K. pneumoniae isolates. Among E. coli, the prevalence of antibiotic-resistance genes included blaNDM-1 (8.9%), blaSHV (13.9%), and blaCTX-M (7.6%). In K. pneumoniae, the percentages were blaNDM-1 (12.8%), blaSHV (4.3%), and blaCTX-M (5.0%). Co-existence of multiple antibiotic-resistance genes was observed in 4.54% of E. coli isolates (n = 5) and 5.74% of K. pneumoniae isolates (n = 5). This suggests the escalating issue of infectious species becoming increasingly resistant to antibiotics in wastewater systems.
Smart voice signature: A machine learning approach to speaker identification
(Institute of Electrical and Electronics Engineers Inc., 2025-01-01) Mazumder S.I.; Mollah M.T.; Tahia, Labiba; Rafin, Tawsif Mustasin; Al Amin, Nafiun; Saifkabir, N.M.; Farhan, Fahim Islam; Chowdhury, Md Tanvir; Department of Computer Science and Engineering; Department of Electrical and Electronic Engineering
Speaker identification is recognizing individuals based on their unique vocal characteristics. This paper explores the enhancement of speaker identification systems through machine learning techniques, focusing on Mel-Frequency Cepstral Coefficients (MFCC) for feature extraction and the application of K-Nearest Neighbors (K-NN) and Decision Tree algorithms using the 'Weka' software tool. This study aims to develop a robust system valuable in forensic science, security, and other areas where verifying an individual's claimed identity based on their voice is crucial. By leveraging these sophisticated algorithms, the system enhances the accuracy and efficiency of voice-based identity verification. This research seeks to improve the precision of speaker recognition. It aims to enhance the visualization tools that aid in analyzing voice data, thus facilitating a more intuitive understanding of the results. This integration of advanced machine learning techniques with practical visualization enhancements is expected to broaden the applicability of speaker identification technologies, making them more effective in diverse real-world environments where quick and reliable identification is needed. Through this study, the system is anticipated to contribute significantly to security and forensic analysis, providing a dependable method for identity confirmation in various applications.
Comparative analysis of diverse architectures for accurate blood cancer cell classification
(Institute of Electrical and Electronics Engineers Inc., 2024-01-01) Md. Muttakin G.K.; Yesmin F.; Alam S.S.; Ashraf, Md Sadi; Akuthota V.; Quader M.A.; Department of Computer Science and Engineering
Blood cancer cell diagnosis is crucial in medical diagnostics. It demands accurate classification of blood cell images. Proper classification of blood cancer cells is fundamental for accurately diagnosing the specific type and subtype of blood cancer as well as efficient treatment planning. It provides specific information, helping healthcare professionals predict the prognosis, survival rates, and the potential for disease recurrence. On this basis, deep learning models have demonstrated remarkable performance. In this paper, we have introduced a comprehensive research into blood cancer cell classification, employing a diverse dataset encompassing various blood cell types. We explore the effectiveness of VGG19 with batch normalization, Vision Transformer (ViT), Ensemble Adversarial Inception-ResNetV2, DenseNet201, and ResNeXt50 architectures in this challenging task. In order to enhance the model performance, we integrate essential data preprocessing techniques, including resizing, cropping, and normalization. Additionally, novel data augmentation strategies, such as random cropping, and flipping are introduced to augment the training dataset and improve model generalization. Remarkably, VGG19 with batch normalization has shown tremendous success by achieving 99.86% accuracy. Moreover, the DenseNet201 model has performed brilliantly by achieving an accuracy of 98.55%. The ResNeXt50 model shows excellent performance with an accuracy of 98.31%. The Vision Transformer (ViT) achieves a solid accuracy of 98.91%. Lastly, Ensemble Adversarial Inception-ResNet V2 also performed no-tably achieving 96.38%. In this context, VGG19 with batch normalization is able to show more excellent performance than other models by achieving the highest accuracy.
Developing an IoT based wheelchair: Biomedical data logging emergency contingency services
(Institute of Electrical and Electronics Engineers Inc., 2021-01-10) Ashraf, Tahmidul; Islam, Nadia; Costa, Shanto Lawrence; Arefin M.S.; Azad, A. K. M. Abdul Malek; Department of Electrical and Electronic Engineering
Wheelchair being a common medium of transport among disabled and handicapped people, this paper solely focuses on the development of electrical wheelchair. Both sensor and IoT implementations are considered for a motorized wheelchair. This project was a collaborated attempt to achieve independent operations of the electrical wheelchair, with Centre for the Rehabilitation of the Paralyzed (CRP) and Control Applications Research Centre (CARC), Brac University. The objective of this paper is to provide a module for proximity sensor, heart rate sensor, torque sensor, GPS and posture detection systems for the patient. Heart rate sensors always helps the patient to keep pulses on check while posture detection system gives reminder to change lower body posture periodically. Proximity sensors are attached on the wheelchair to detect any incoming danger and alert the passenger, also in case of any danger the user can call for help pressing the SOS button. The GPS location will be received through an online platform by the caretaker. Torque sensor system allows the wheelchair to actively function longer hours using mechanical energy, and not just being dependent on battery power. Availability of such additional features makes the existing wheelchair safer and more reliable for patients, encouraging a more independent lifestyle with assured safety for outdoor activities like going to job place, marketing and attending educational institute. Supporting CRP to provide medical treatment and rehabilitation for disabled people essential requirements are met.
An integrated framework for waterfront development to recognize nature-based solutions (NBS) in urban areas: Evaluating the condition of two projects in Bangladesh
(IWA Publishing, 2024-12-01) Zaman K.M.U.A.B.; Tumpa R.T.; Chowdhooree, Imon; Department of Architecture
Nature-based solutions (NBS) often suggest improving the degraded urban environment through the implementation of projects for revitalizing water bodies and adjacent areas. Among various concepts of developing waterfront urban spaces, ‘water sensitive urban design (WSUD)’ asks for integrated design and management of urban water resources and water cycle, following a holistic approach. This research proposes a framework that assimilates the components of WSUD with the concept of ‘integrated urban water management (IUWM)’ that mainly focuses on governance, management, and stakeholders’ engagement. This integrated approach emphasizes the need for developing a holistic framework for the management of planning and design of waterfront development projects. The framework includes detailed criteria for water sensitive approach and acts as a holistic checklist for evaluating or designing waterfront development projects. Such comprehensive guidelines that includes planning, governance, and design challenges are rare in the current body of literature. To test the framework, the research conducts a comparative study among two waterfront projects in Bangladesh and through a scored evaluation based on the proposed framework, reveals the lack of water sensitive planning, design and management processes of the projects, which has narrowed down the scope and the opportunities of practicing NBS through reviving lost urban waterbodies.