Browsing by Author "Tasnim, Zarin"

Now showing 1 - 20 of 31

A case study on Lion Cinemas
(BRAC University, 2024-01) Tasnim, Zarin; Hossain, Saif
Mirza Abdul Khaled, Director of Lion Cinemas Pvt Ltd., is in a situation where he wants to grow his new business to more widespread. At present, the cinema hall is running but he wants to increase the number of customers. Lion Cinemas exhibits three types of movies which are Bengali, Hindi and English. Normally, the customers are less interested in local Movies rather than foreign movies. So, the main challenge of Lion Cinemas is to increase the number of spectators in the Local Cinema. This may lead to high profits in the business of Lion Cinemas if a high number of customers can be attracted to Local movies. It started its journey in 1930, it was closed due to some losses in 2002, later it was reopened in 2022. Though Lion Cinemas was not reestablished a long time ago, Mirza Abdul Khaled confronted that his activities were little delayed due to COVID-19 pandemic which began in 2019. Mirza Abdul Khaled should make important decisions for Lion Cinemas to find a sustainable and successful model for his business. Although the case details are very specific to the context of a developing country like Bangladesh, the general principals which are involved into this case can be applied to any kind of Cinema Hall in Bangladesh. It is not applicable through the whole worldwide Cinema Hall.
A domain and noise adversarial bird tune classification pipeline using deep neural network
(BRAC University, 9/29/2022) Riya, Aparna Sarker; Roy, Arpita; Fahim, Md. Abrar; Tasnim, Zarin; Islam, Rakibul; Mostakim, Moin; Reza, Md Tanzim
Birds are an important category of animals that ecologists keep track of utilizing autonomous recording units as a key indication of environmental health. Because of the consequences of climate change and the rising number of endangered species, many experts suggested developing an animal species recognition system to help them in specialized research. Researchers can improve their ability to assess the state of biodiversity and its patterns in crucial ecosystems by precise sound detection and categorization, which is supported by machine learning, allowing them to better support global conservation efforts. However, producing analysis outputs with high precision and recall remains a difficulty. Due to a lack of appropriate methods for efficient and accurate extraction of interest signals, the vast bulk of data remains unexplored (e.g., bird calls). Moreover, due to strong source-domain specific features and artificial/natural noises, these acquired raw data create different distributions in datasets. So, to ensure a generalized feature learning, domain adaptation [1] techniques will be implemented in this work to make the networks familiar towards both acquisition sensor noises and background noises without having to do intensive dataset specific augmentations. We used 3 popular and powerful DNN models, including CNN, VGG19 and ResNet50. Out of them, for the bird species classification task VGG19 achieved the best accuracy of 96.02% in testing and 94.01% in training. To the best of our knowledge, this will guide towards convenient and deployable in real life models which will allow future works into the pipeline to ensure better coverage.
A Recommender System Based Job Application
(East West University, 2019-09-05) Tasnim, Zarin; Islam, Nazifa
Work is an important function of the human being and without work life is impossible. With job we can either fulfill our desires or family needs but the important one is we gradually attain confidence, self-respect & social status which makes us feel the part of society. When we work, we can develop new skills and can learn new things. Job is something where we can continuously discover ourselves and our potential. So, this is very important to stablish an easy way to find out jobs. In spite of this to make it more effective there are so many algorithms to make a recommender system where jobs will be suggested to the users. There are so many algorithms of recommendation system but here in our thesis we have tried to build a personalized recommendation system. Importance of recommendation in searching job is very important as it will save time and also be helpful to know the neighbor member's preferences. This application contains history of similar users’ job preference lists. This application also contains admin panel for the recruiters. So, the recruiters can easily post, view, edit and delete jobs. Without recommendation people can also see their desired jobs by searching with the company name or job name. When the app has been used by someone more than one time then their previous search jobs will also be shown in their respective homepage.
A study on the prevalence and associated risk factors for depression among geriatric population in Bangladesh
(BRAC University, 2025-05) Tasnim, Zarin; Islam, Md. Rabiul
Mental health is an important component which includes overall well-being, encompassing emotional, psychological, and social variables that impact individuals' thoughts, feelings, and behaviors in day-to-day life. Various surveys show that a good number of adult populations in Bangladesh is suffering from various kinds of mental health conditions. But the most concerning thing is that people with mental disorders are mostly left untreated, and this led to various kinds of physical health-related problems. In Bangladesh, the mental health of the elderly is an urgent need, particularly in regard to the country’s rapidly aging population and the high incidence of mental health disorders within this age range. Depression in Bangladesh’s geriatric population is a serious yet sometimes underestimated problem. A diversified strategy is required for combating depression in Bangladesh’s elderly population. Now it is necessary to increase the availability of mental health interventions in primary healthcare.
An Analysis of Recruitment and Selection Process of Dutch Bangla Bank Limited
(Daffodil International University, 2018-12-22) Tasnim, Zarin
Based on the c and selection process, I have tried to highlight the activities performed by the Dutch Bangla Bank Limited. Limiting the activities of the Mirpur branch and the entire Dutch Bangla Bank I have tried my best to highlight each category of different activities I learned during the preparation of the report but each At the time of collecting brief information about the department There are some limitations Human Resource Management HRM has influenced the literature that the organization should appoint an analysis and the selection process should be integrated with its strategic choices. Every support and operation of other operations will be done in a horizontally organized organization. Many argue that the high strategic coordination M power to make the damage I would like to make strategic choices for organizing temporary organizations such as project-based agency projects and programs, so that its historical role can be resolved with relevant directors who are able to solve their problems. Here I can see the Dutch Bangla Bank limited history and its corporate social responsibility and social banking activities.
An Analysis of Recruitment and Selection Process of Dutch-Bangla Bank Limited
(Daffodil International University, 2018-12-22) Tasnim, Zarin
Based on the c and selection process, I have tried to highlight the activities performed by the Dutch Bangla Bank Limited. Limiting the activities of the Mirpur branch and the entire Dutch Bangla Bank I have tried my best to highlight each category of different activities I learned during the preparation of the report but each At the time of collecting brief information about the department There are some limitations Human Resource Management HRM has influenced the literature that the organization should appoint an analysis and the selection process should be integrated with its strategic choices. Every support and operation of other operations will be done in a horizontally organized organization. Many argue that the high strategic coordination M power to make the damage I would like to make strategic choices for organizing temporary organizations such as project-based agency projects and programs, so that its historical role can be resolved with relevant directors who are able to solve their problems. Here I can see the Dutch Bangla Bank limited history and its corporate social responsibility and social banking activities.
An extensive study on the Employee job satisfaction in SQUARE Pharmaceuticals Ltd (CHQ Branch)
(BRAC University, 6/19/2022) Tasnim, Zarin; Ahmed, Md. Shamim
The main topic of this internship report is SQUARE Pharmaceuticals Employee job satisfaction and the HR practices. This report consists of 3 chapters. Firstly, this paper contains the internship experience of SQUARE Pharmaceutical Ltd, the job scope, responsibilities etc on the first chapter. Secondly, the next chapter consists of the background of SQUARE Pharmaceuticals Ltd, vision, mission, History, Departments, products etc. In this report, the competitive analysis has been done by using Porter’s Five model in order to measure the current market condition of the Pharmaceutical Industry. The report also consists of the SWOT analysis, in order to measure the strength, weakness, opportunities and threats of the company in this respective industry. Moreover, an overview of SQUARE Pharmaceuticals HR Practices, recruitment & Selection process has been discussed in this report. The main focus of the report was the Recruitment & Selection process timeline and the survey on Employee job Satisfaction of the SQUARE Pharmaceuticals industry. The survey discussion has provided an in-depth employee job satisfaction scenario of SQUARE Pharmaceuticals. Finally, the necessary recommendations and suggestions has been also provided based on the survey record and competitive analysis for future betterment in this paper.
An Intelligent System for Fresh Bitter Gourd Detection Using CNN
(Daffodil International University, 2021-09-20) Tasnim, Zarin
Agriculture development is not only a normal development sector but also a vital sector all over the world. Convolution Neural Network is one of the most advanced algorithms in Machine Learning. In my study, I have built up a strong relationship between agriculture and Image processing system, bitter gourd freshness detection and automation system using multi-layer automation process. I have used 5*3 training layers for the dataset and relevant output process. In this study, I show 4 types of output like Fresh, Moderate, Wrong and rotten bitter gourd. After analyzing data and method implementation I get 91.56% model accuracy which is better than the other image processing algorithm. In the modern era agriculture development is the highly contribute field of food security. This study will allow farmers to choose the proper crop in the right market condition, which will play a key role in strengthening the economy of the country. Technology on the other hand is a huge blessing in people's lives. In today's world, the introduction of information technology in agriculture has led to great improvements in this field.
Automate crime news segmentation, knowledge-based generation and public opinion mining for social awareness
(BRAC University, 2021-06) Sabit, Ahmed Bin; Ahsan, Asif; Tasnim, Zarin; Rasel, Annajiat Alim; Alam, Md. Golam Rabiul
In the context of the crime scenario in Bangladesh, people face enormous crime situations which can be eradicated by applying some technological solution. For this a research work needs to be conducted by news segmentation and knowledge base generation. This study aims to determine how authority can target crime scenarios based on public opinion for increasing social awareness. Based on this context there will be an algorithm which will sort out the data sheet as well as the mined data will figure out solutions for respective crime scenarios. These data will be collected from news articles from which a data library will be generated by using natural language processing. After analyzing all data, it will automatically notify the authority with a precise report. Further research is needed to identify other factors that could strengthen the effectiveness of this report.
Brain Stroke Prediction Application
(Daffodil International University, 2021-05) Tasnim, Zarin; Mahmud, Md Said; Kabir, Erina
In this modern era everyone wants to live a healthy and smart life, and day by day people are being dependent on their smart phone. And this world now requires some smart technology which provides excellent health system to assure that people community can live healthy life. It is true that day by day we getting smart and modern but it is also true that people are suffering much than before from many kinds of health issues, like Cancer, Heart Attack, Brain Stroke etc. So, it is very important for everyone to get instant healthcare. So, here we made an application which is called “Brain Stroke Prediction Application”, by using this application people can get idea about the condition of their brain by measuring their brain stroke possibilities. This is an web based android application where a user have to get access first with their required information and after that they have to fill the requirement form for getting the result of their brain stroke possibilities. And after that there is a neurologist has been suggested in case user needs any suggestion. The ambition of making this project is to provide an instant report or medical direction for a patient who needs to know about their brain’s condition.
Building investor confidence: overcoming credit rating limitations SME financing in Bangladesh in the fintech era
(BRAC University, 2026-01) Tasnim, Zarin; Siddiqui, Sayla Sowat
The internship report seeks to discuss how credit evaluation models using Fintech can meet the shortcomings of traditional credit ratings to the Small and Medium Enterprises (SMEs) in Bangladesh. Conventional credit scoring processes can be inaccurate in characterizing risk of SMEs thus limiting access to finance and investors losing interest due to these factors. This paper explores how new Fintech technology can support the promise of more complete and accurate credit decision-making by adding additional data sources to the equation. This study has concentrated on surveying the following stakeholders in the sector such as investors, Fintech operators and the owners of SMEs to see their opinions on the incorporation of non-conventional information into the system of credit scoring. Based on Fintech case studies and the applicable literature, the paper suggests that by utilizing these technologies it is possible to enhance the process of assessing the credit worthiness and the confidence of investors. Finally, the report aims to provide quality research knowledge to fill the financing gap of the SMEs in Bangladesh, bring them financial inclusion and economic sustainability by providing better credit evaluation techniques.
Contact Us Portal
(Independent University, Bangladesh, 2023-01-19) Tasnim, Zarin
Sonali Bank Limited is the principal state-owned leading public commercial bank in Bangladesh. It is the largest bank in the country. Sonali Bank always provides priority to their customers and would like to be their clients' first choice as a differentiated financial service provider, trusted, respected, and cherished by all stakeholders in the region and beyond, and to pursue an unending quest for excellence in all areas. I had to finish my learning sessions before working on any project, and in this learning session, I was assigned by my supervisor Mrs. Sabrina Alam to work on a project where my task was to develop a website portal called Contact Us Portal. In this portal, customers can send messages or ask queries about their account or in general banking questions directly to the admin.
Criminal activity detection using deep learning algorithms
(BRAC University, 2021-01) Tasnim, Zarin; Shahid, Syeda Sanjana; Quayum, Sofana; Barsha, Umme Habiba; Chakrabarty, Amitabha
Criminal activities using guns and knives occur very frequently. The quick and accurate detection of a criminal activity is paramount to securing a place where people usually gather every day. More and more security systems are being developed as the number of cities are growing rapidly. This creates a backlog of video data that is being monitored under human supervision but usually human error happens in such cases. This also creates a huge amount of workload for the supervising team. There are several solutions in computer science that can be implemented for immediate and accurate criminal activity detection without any human intervention. Human behavior and pattern recognition is a challenge when it comes to criminal detection as there are several people who act in an abnormal way but aren’t suspicious. In such cases it might generate a false alarm. As we proceed further with our research, most of the crimes take place with the use of handguns or knives. There are many more studies from di↵erent countries that show that, most dangerous crimes took place using weapons of di↵erent sorts. So, in order to detect a criminal from a live crime scene, the first and the quickest step is to determine whether a person is carrying an arm or not. For such detection method, Convolutional Neural Networks is very useful. That’s why among all di↵erent types of Deep Learning approaches, we opted for Convolutional Neural Network (CNN) to identify a criminal using object detection method. The major challenge of our research was the unavailability of datasets. We created our own image dataset and classified them into four different classes in order to train our model. We have 4,180 images in our dataset which are collected from di↵erent crime scenes. There are several CNN models that give efficient results in terms of object detection from image datasets. In our work, we implemented five di↵erent CNN models which are MobileNetV2, Inception-v3, Xception, VGG16, ResNet50 and as a result accuracy for each model is 98%, 98%, 94%, 70% and 60% respectively. The accuracy in MobileNetV2 and Inception-v3 was the highest.
Customer perception on general banking activities of Prime Bank Limited Banani branch
(BRAC University, 4/27/2017) Tasnim, Zarin; Islam, Md. Tamzidul
After completing the various course work of four years undergrad life, learning through the practical knowledge is the second step. The internship program of three months gives that opportunity to every student. As per the requirement of BBA program, I did my internship in Prima Bank Banani branch. I have performed ninety days internship, which helped me to improve myself in the practical field. As per the requirement of internship program, I have prepared this report. To prepare this report I have done some data analysis. Both from the primary and secondary sources I collected the data. As I was assigned in the General Banking division I tried to reflect my knowledge about that department in this report thoroughly. To measure the customer perception about general banking activities of Prime Bank I have conducted a research, where the customers were my respondents. This report gives details explanation about the general banking activities of Prime Bank, the second generation bank which came into being in 1995. PBL was established with the objective of bringing about a qualitative change in the sphere of banking and financial management. At present the bank contributes effectively in the economy of Bangladesh by collecting funds from the surplus units and mobilizes to the deficit unit in the form of credit. At present the bank serves its customers with 140 branches around the country.
Customer’s perceptions on foreign remittance activities of Bangladesh Krishi Bank
(BRAC University, 2021-09) Tasnim, Zarin; Akhter, Rahma
This report is based on Internship experience and feedback on customer’s perception on foreign Remittance activities of Bangladesh Krishi Bank. From the customer's perspective, remittance is significant since it is simple, inexpensive, and reduces risk. From the perspective of a banker, remittance is essential because it generates non-interest income for the bank, which is beneficial to other businesses and encourages sustained economic growth. The majority of remittances are handled by the parties listed below. The scope of the report is limited in several ways. In order to meet the report's goals,. I attempted to examine BKB's foreign exchange performance in this report. I collected primary through face-to-face conversations, direct observation, and work experience as a normal employee at Bangladesh Krishi Bank. The bank's management and customers were the major sources. Websites, brochures, instruction circulars, and the Bangladesh Krishi Bank's annual report book were used as secondary sources. According to the customer survey conducted for this research, Bangladesh Krishi Bank delivers moderate service to its clients when it comes to remittance operations. The rationale for offering modest customer service is that qualified manpower is required to deliver the finest and fastest service. I perform an online survey with several questionnaires to check client satisfaction and analyze it using SPSS. Customer relationship management is hampered by face-to-face contact and psychological tension among employees, according to the findings of the studied study. Finally, BKB must devise a plan for handling client relationship management
Detection of prodromal parkinson’s disease with fMRI data and deep neural network approaches
(BRAC University, 2021-06) Shahriar, Farhan; Dey, Amarttya Prasad; Rahman, Naimur; Tasnim, Zarin; Tanvir, Mohammad Zubayer; Parvez, Zavid
Parkinson’s Disease is the second most common neurological disease after Alzheimer’s Disease. The disease is incurable. However, if the disease can be detected earlier, then the consequences of it’s effect can be relieved. The early phase of PD is called by Prodromal Parkinson’s Disease. The symptoms of the Prodromal phase includes hyposmia, constipation, mood disorders, REM sleep behavior disorder, olfaction dis orders etc. RBD or REM sleep behavior disorder is the most common symptom of Prodromal PD. In this study, we used various deep convolutional neural network architectures and trained them to detect Prodromal PD patients. We collected 20 Prodromal patients and 20 healthy control subject data from the PPMI website and applied CNN architecture mobilenet v1, incception v3, vgg19 and inception resnet v2 to achieve our goal. We ensembled inception resnet v2 and mobilenet v1 with the hope of getting a better result as well. However, we successfully carried out our training and with mobilenet v1 we gained the highest classification accuracy of 81.22%. Inception resnet V2, inception v3, vgg19 and ensemble model achieved respectively 75.30%, 62.55% and 63.32% accuracy.
Enhancing cancer care: strategies for improved patient outcomes
(BRAC University, 2025-06) Anjar, Khan Md Saifullah; Nidhi, Ramisa Sharar; Tasnim, Zarin; Shammobroti, Nijhum; Shaikat, Md.Shariar Emon; Mukta, Jannatun Noor
Cancer remains a leading cause of death in Bangladesh, where systemic challenges such as limited infrastructure, high treatment costs, and lack of access to specialists hinder timely and effective care. This study addresses these challenges by proposing and developing a mobile health (mHealth) platform designed specifically for cancer patients in Bangladesh. Informed by a qualitative study involving 32 participants including patients, caregivers, and oncologists. The research explores existing gaps in cancer care delivery, such as delays in emergency response, fragmented communication, and insufficient patient involvement. Key themes and subthemes were derived from interviews and surveys, highlighting the need for stronger doctor–patient communication, improved staging practices, and robust data protection mechanisms. Based on these findings, we developed a digital health prototype that includes a real-time communication module using WebRTC, a TNM-based cancer staging system integrated via API from a clinical database, a rule-based severity tagging module for patient triage, and secure, role-based authentication using token-based mechanisms. The platform allows patients to request consultations, submit symptom data through structured questionnaires, upload reports, and receive prioritized care based on clinical urgency, all while ensuring data privacy through time-limited session storage. Designed with culturally sensitive and accessible UI considerations for users of all background, this system demonstrates the potential of context-aware, scalable digital solutions to enhance clinical outcomes, reduce systemic burdens, and improve the overall patient experience in cancer diagnosis and care. Our findings contribute to the growing field of digital oncology by bridging qualitative user insight with system-level design and implementation.
Experience of television journalism & editing broadcast news
(BRAC University, 2019-08) Tasnim, Zarin; Huda, Roohi Andalib
Exploring different dimensions of social media at Dhaka Tribune
(BRAC University, 2018-04) Tasnim, Zarin; Huda, Roohi
Fostering of critical thinking skills through reading text
(BRAC University, 2020-09) Tasnim, Zarin; Ahmed, Sabreena
This study explored how the strategies of critical thinking skills have been implemented by the participants while reading an English reading text. This strategy of the implementation of critical thinking skills can be used to foster critical thinking skills in English academic reading classes in ESOL contexts such as Bangladesh. This is the qualitative multiple case study approach where the researcher chose four students of the secondary level school for the purposive sampling technique of the reading session. All of the participants came from the mainstream Bengali school where the critical thinking skills of students are not much focused on. The think-aloud is one of the important part of the study where the main sources of data is about the reading strategies of the participants. In this process, the students verbalize their thoughts rather reading that silently. Students were instructed to have one piece of paper beside their reading text, so that while after reading each line where they have paused, they could note down their own thinking point of view that what they have understood from each line of the text. It explains the procedure of the strategies briefly which is used in taking reading comprehension texts (Jesson, 2011).In this study , at first there was two training sessions for the students as they were not familiar with the critical thinking strategies of reading texts through think –aloud protocol. The training sessions were held so that they can participate in a proper way in the final session of reading. The reading sessions and interviews were taken through zoom learning platform which took a total of four days to complete. The findings of the study revealed that the students used interpretation strategies of critical thinking skills more rather than other five strategies as it seemed that, they find it easier to do. The next strategies which were used by most of the students were analyzing, self-regulating respectively. It was seen that the inference skill was least used by the students. This study is significant for English language teachers of Bangladesh and any ESOL country because it will encourage teachers to use the think –aloud protocol to teach students how to think while reading. The reliability of the study wills other researchers implement the same methodology for future study. After completing the session of reading, the major issues that came out is that students feel difficulty in case of evaluation strategy, no matter whether he/she used to read English text or not, they find it more difficult to implement for which they need more practice. Besides, in case of other strategy such as analysis and explanation, it has also to be noted that they try to generate their ideas but they could not understand that how and from where they formed a new sentences through their ideas for presenting it. Though, all four of them used inferences and self- regulation. Therefore, they need more practice for having a smooth skill of the strategies of critical thinking skills for implementing that in the reading text.