Browsing by Author "Rahman, Moshiur"

Now showing 1 - 9 of 9

A blockchain-driven framework designed for pharmaceutical community to secure and trace the trail of drug supply chain
(BRAC University, 2021-09) Rahman, Samiha; Aquib, Arif Awasaf; Jyoty, Watry Biswas; Rahman, Moshiur; Dewan, Tamanna; Hossain, Muhammad Iqbal
Our quality of life relies heavily on health products, which marks our dependence on the pharmaceutical industry. Drug safety is very important to ensure that our life-savers do not turn out to be the cause of our death. Due to the complicated and non-transparent supply-chain management that exists within this industry, we have to face the unfortunate risks of counterfeit drugs. Moreover, drug counterfeiters are taking advantage of people's vulnerabilities during COVID-19 and are making the situation even worse. A blockchain-based platform can make the process of drug de- velopment, production and marketing far more e cient and trackable compared to the existing system. Everything can be planned out, recorded and traced by a decen- tralized and distributed ledger technology. This will give end-consumers the control to monitor the products they receive. Our thesis paper aims to observe the issue with the existing supply-chain of pharmaceutical drugs and create a trustworthy infras- tructure which will e ectively make the overall process easier, while ensuring drug safety. We have used Hyperledger fabric, an open source enterprise-grade framework under the Hyperledger umbrella, to execute secure and well-planned transactions of drugs.
A multimodal approach of sentiment analysis to predict customer emotions towards a product
(BRAC University, 2019-12) Islam, Shadman; Rahman, Moshiur; Ali, Samina Tuz Zohura; Shahrior, Tawhid; Akhond, Mostafijur Rahman
Begun roughly a decade ago, Sentiment analysis, the science of understanding human emotions, can trace its roots back to the middle of the 19th century. The motive of sentiment analysis is to extract and predict human emotions through facial expressions, speech or even text in some cases. Being inspired by the existing ideas, we propose a multi-modal model in the market that uses both facial cue and speech to forecast customers’ sentiments and satisfaction towards a certain product. Our model helps various companies get key insights for specific market regions and their customers, and to gain a competitive advantage over the other. In this study, we estimate product perception of a demography based on emotions that were extracted from customers’ facial expressions and speech. Although many researches have been made in the eld, but very few of them are multifaceted, integrated systems, where the different components rely on each other to produce an absolute result. We extract the emotions of people by recording their facial cues and speech patterns as they interact with a specific product of the market, such as a mobile phone in our case. We analyzed their facial expressions using AWS Rekognition. For the textual part, we analyze the sentiments using an algorithm which has a mixture of Tensorflow, Keras, Sequential model and RNN. Finally, we merge the previously obtained emotions from the video section with the textual sentiment to get the features for our predictive model. The model was generated using an algorithm named XGBoost. We have achieved an average accuracy of 81 percent approximately with 0.065 standard deviation by implementing cross validation of k-fold nature with folds of 3 and also 5 different iterations.
Designing And Evaluating An Educational Video Game For Children: A Blend Of Learning And Fun
(Daffodil International University, 2025-12-10) Rahman, Moshiur
This study, “Designing And Evaluating An Educational Video Game For Children: A Blend Of Learning And Fun”, aims to develop an interactive learning software product for children aged 3 to 7 based on game-based education. The main aim of this project is to bring fun and learn together by making a game that will educate the children in terms of relating alphabets, objects with numbers in an amusing way as well as it will improve their memory, attention and problem-solving ability. The game is programmed in Unity 3D and currently supported for Mobile(Android) as well as PC. Players will be able to choose a character and roam through four interactive scenes: (1) Alphabet Adventures where kids collect letters and avoid obstacles, (2) Word Wonders where items correspond with real world objects like “A for Airplane” and “B for Bus,” (3) Number Kingdom where they gather numbers while learning them and (4) Quiz Challenge where players can try to answer quiz challenges. Reasoning interactions include such features as sound effects, animations and scoring to ensure interactivity and motivation
Impact of Non-Productive Time on Productivity of Basic, Semi-Critical and Critical Garments in Sewing Section
(Daffodil International University, 23-05-08) Rahman, Moshiur
Garments business is one of the most challenging businesses in the world. To survive in this competitive market, it is necessary to consider various techniques both before and during the start-up of the business. Product design, sampling, cutting, sewing, embellishment, finishing, and other processes are all part of the garment manufacturing process. To achieve the desired productivity, all of these activities must be performed in a synchronized, planned, and timely manner. Sewing is a crucial part of the manufacturing process. The purpose of this study was to investigate the effect of non-productive time (NPT) on sewing production at various efficiency levels (55, 65, and 75%). However, not only does efficiency influence NPT, but so does the complexity of the garment. Therefore, in this study, basic (T-shirts), semi-critical (hoodies), and critical (jackets) products were chosen to identify the NPT of a renowned garment factory, namely Oxford Knit Composite Ltd. (Pretty Group). The time study method, one of the most effective tools, was used in this study. This study reveals that at the highest efficiency level (75%), the production deviation due to NPT for T-shirts, hoodies, and jackets was 19.7, 8.8, and 6.3 pcs/h, respectively. However, if NPT is not controlled, output will not increase significantly. The NPT of T-shirt, hoodie, and jacket was about 0.4, 0.8, and 2.9 min, respectively. Additionally, NPT has a proportional relationship with SAM and product’s complexity. It is worthy to mention an annual loss of 21465, 25927, and 29640 USD for T-shirts, hoodies, and jackets, respectively, that occurs at a 75% efficiency level. Therefore, it is recommended to reduce the NPT to maximize profit and productivity.
Perception of secondary level English language teachers of Bangla medium schools regarding English as a Medium of Instruction (EMI) in Dhaka, Bangladesh
(BRAC University, 2022) Chowdhury, Eshita; Rahman, Moshiur
English as a medium of instruction has emerged as one of Bangladesh's most pressing educational concerns at the university level. Although English is used as a language of teaching in several private universities in Bangladesh, students have difficulty speaking and listening because they are mostly from Bangla-speaking backgrounds. English as a medium of teaching is not well established in Bangla medium schools or colleges. The purpose of this study is to learn about secondary-level English language instructors' attitudes on English as a medium of instruction in Bangla medium schools in Dhaka, Bangladesh. A recommendation has been made for teachers, students, and policymakers after a thorough investigation using both qualitative and quantitative methodologies.
Real Time Flower Identification by Artificial Intelligence
(IEEE, 2024-03-21) Rahman, Moshiur; Joy, Taushik Ahmed; Akter, Samia; Sattar, Abdus
In the realm of flower-rich Bangladesh, the presence of these blossoms enriches our everyday experiences, whether encountered during leisurely strolls, along railway tracks, or within our gardens. However, the beauty of these flowers often remains unexplored due to our limited knowledge about their names and attributes. To address this, a project was initiated to close this gap and acquaint people with these unfamiliar yet frequently encountered blooms. Our endeavor involves an innovative mobile application that employs real-time camera recognition to identify flowers, powered by neural networks, particularly the Tensorflow-based image classifier on the Android platform. Machine learning's expansive applications in computer science have propelled our interest in this arena, specifically focusing on Convolutional Neural Networks (CNN) and Tensorflow for image classification. While our current application marks the inception, aspiration to further enrich and refine our system for the future. Our ultimate aim is to share the benefits of our work, enabling individuals to gain profound insights into the enchanting floral world that envelops them daily.
Real Time Flower Identification by Artificial Intelligence
(Scopus, 2024-03-21) Rahman, Moshiur; Joy, Taushik Ahmed; Abdus Sattar, Samia Akter
In the realm of flower-rich Bangladesh, the presence of these blossoms enriches our everyday experiences, whether encountered during leisurely strolls, along railway tracks, or within our gardens. However, the beauty of these flowers often remains unexplored due to our limited knowledge about their names and attributes. To address this, a project was initiated to close this gap and acquaint people with these unfamiliar yet frequently encountered blooms. Our endeavor involves an innovative mobile application that employs real-time camera recognition to identify flowers, powered by neural networks, particularly the Tensorflow-based image classifier on the Android platform. Machine learning's expansive applications in computer science have propelled our interest in this arena, specifically focusing on Convolutional Neural Networks (CNN) and Tensorflow for image classification. While our current application marks the inception, aspiration to further enrich and refine our system for the future. Our ultimate aim is to share the benefits of our work, enabling individuals to gain profound insights into the enchanting floral world that envelops them daily
The impact of social media marketing on brand awareness: a case study of New Zealand Dairy
(BRAC University, 2024-10) Rahman, Moshiur; Khan, Tanzin
This internship report, "The Impact of Social Media Marketing on Brand Awareness: Shining the Spotlight on the New Zealand Dairy Industry—Effects of Using Social Media Marketing as Brand Awareness: A Case Study of New Zealand Dairy,” examines brand recognition in specific demographics in the New Zealand dairy industry: undergraduates, non-consumers of dairy products, and postgraduate students, consumers of dairy products. The study seeks to establish the extent to which social media marketing can be useful in increasing brand awareness of sports organizations among the two groups. The report also focuses on understanding consumer engagement activities done on social media by the dairy brands and assess the effectiveness of advertising placement on social media for the specific consumer segments. The research also shows that students utilize mainly Facebook and YouTube and that undergraduate students use varieties of social media platforms more than postgraduate students. As for brand familiarity, both groups rated themselves in the middle ground, but undergraduates acknowledged being more involved with the brand’s social media accounts than postgrads. Of all the content types, undergraduate students most interacted with product information and promotions content types. For instance, social media networks had a positive effect on brand image, particularly among the undergraduate students, and also determined the purchase behavior among these students. However, the study identified that both groups tended to show low actual levels of interaction with New Zealand Dairy’s content across the site, suggesting that more interactive approaches need to be employed. Based on the findings of the report, the following recommendations are proposed with a view to improving the social media marketing strategies used by the New Zealand dairy industry: targeted content to the audiences, concentrating on the mainstream platforms such as Facebook and Instagram, embracing market engagements, using analytical data, and testing various content types. By implementing these recommendations, the New Zealand dairy industry can effectively leverage social media to enhance brand awareness, drive consumer engagement, and ultimately, increase sales.
Transfer learning architectures with fine-tuning for brain tumor classification using magnetic resonance imaging
(Daffodil International University, 2023-12) Islam, Md. Monirul; Barua, Prema; Rahman, Moshiur; Ahammed, Tanvir
Deep learning methods in artificial intelligence are used for brain tumor diagnosis as they handle a huge amount of data. Compared to computerized tomography (CT), Ultrasound, and X-ray imaging, Magnetic Resonance Imaging (MRI) is effectively used for machine vision-based brain tumor diagnosis. However, due to the complex nature of the brain, brain tumor diagnosis is always challenging. This research aims to study the effectiveness of deep transfer learning architectures in brain tumor diagnosis. This paper applies four transfer learning architectures- InceptionV3, VGG19, DenseNet121, and MobileNet. We used a dataset with data from three benchmark databases of figshare, SARTAJ, and Br35H to validate the models. These databases have four classes: pituitary, no tumor, meningioma, and glioma. Image augmentation is applied to make the classes balanced. Experimental results demonstrate that the MobileNet outperforms competing methods by exhibiting an accuracy of 99.60%.