Browsing by Author "Tahsin, Fariha"

Now showing 1 - 3 of 3

Automatic Bengali image captioning using efficientNet-transformer network and vision transformer
(BRAC University, 2023-01) Kabir, Muhammad Khubayeeb; Labonno, Anindita; Amin, Sofia; Tahsin, Fariha; Rahman, Md. Khalilur; Mostakim, Moin
The task of image captioning is a complex process that involves generating textual descriptions for images. This technology is extremely beneficial for a wide range of applications, such as assisting people with visual impairments, monitoring surveil lance systems, content generation, image indexing, and automatic annotation of images for producing data for training AI-based image generation models. Much of the research done in this particular domain, especially using transformer models, has been focused on English language. However, there has been relatively little research dedicated to the context of the Bengali language. This study addresses the lack of research in the context of Bengali language and proposes a novel approach to auto matic image captioning that involves a multi-modal, transformer-based, end-to-end model with an encoder-decoder architecture. Our approach utilizes pre-trained Ef ficientNet Transformer Network. To evaluate the effectiveness of our approach, we compare our model with a Vision Transformer that utilizes a non-convolutional en coder pre-trained on ImageNet.The two models were tested on the BanglaLekhaIm ageCaptions dataset and evaluated using BLEU metrics.
E2E Technology Enhancement in Financial Lifecycle of REDX Logistics Ltd.
(Department of Business and Technology Management(BTM), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2023-05-30) Tahsin, Fariha
Public health risks of fresh fruit juices: bacterial isolation, fecal contamination assessment, and antibiotic resistance patterns
(BRAC University, 2025-04) Tahsin, Fariha; Haque, Fahim Kabir Monjurul
Fresh fruit juices are widely consumed across Bangladesh due to their nutritional value, taste, and accessibility in urban markets and roadside stalls. This study investigates the microbiological quality and health risks of freshly made fruit juices sold in nine locations across Dhaka city. 27 Juice were collected from vendors to count fecal coliform count (FCC) alongside aerobics plate count (APC). Also, samples are diluted and spread on selective media for isolation and identification. After that PCR-based identification revealed that juice samples are contaminated with Klebsiella pneumoniae, Vibrio spp., Salmonella spp., Escherichia coli, and Staphylococcus aureus which pose an entirely significant health risk. Moreover, 96.3% of the samples contained bacteria where Klebsiella pneumoniae leading as the dominant microorganism. Approximately 66.7% of the samples exceeded the acceptable limits for FCC, and 44.44%% failed to meet the standard microbiological safety threshold for APC. Among 147 bacterial isolates, Klebsiella pneumoniae exhibited high resistance to Ceftazidime. Multidrug resistance was also observed in Staphylococcus aureus (78.57%) and Salmonella spp. (75%). These findings highlight significant public health risks associated with pathogenic contamination and antibiotic resistance in fresh fruit juices.