Thesis & Report, BSc (Computer Science and Engineering): Recent submissions

Now showing items 1-20 of 1492

    • Colorectal cancer detection using transformer-based approach with attention mechanism 

      Sarker, Showmen; Fardin, Sadman; Rahman, Saik; Islam, Md.Tanjimul; Sifat, Golam (Brac University, 2022-09)
      Image classification is the process of labeling and classifying pixels or vectors within an image according to preset rules. Classification can be done using spectral or textural features. Computer vision researchers ...

    • A deep learning approach for automated classification of Corneal Ulcers 

      Barua, Sumit; Saha, Samit; Bulbuli, Jannatul; Rahman, Akib; Fuad, Md.Ibna Salam (Brac University, 2023-09-25)
      Eye Corneal Ulcer(ECU) has been demonstrated to be the second most common cause of treatable blindness worldwide, after cataracts. It is an extremely prevalent ophthalmic ailment and can cause severe visual impairment ...

    • Enhancing security in software defined Networking using machine learning and networking algorithm 

      Nawrin, Mashaba; Aurid, Md. Ehtesham-ur-Rahman; Saad, Ehsan Abdullah Khan; Shrestha, Mariea Anjuman (Brac University, 2024-05)
      In Software Defined Networking (SDN), control planes and data planes work simultaneously; which offers flexibility and programmability, and also comes with security vulnerabilities. As big networking systems are planning ...

    • Predictive analysis of non fungible token price using deep learning 

      Rifat, Mohammad Redwan Arefin; Rupok, Tasfim Ahmed (Brac University, 2023-09)
      A form of digital asset called Non-fungible tokens can represent a wide range of objects, such as pieces of art, collectibles, and in-game items. Non-fungible tokens are also commonly referred to by their acronym, NFTs. ...

    • A predictive analysis of chronic kidney disease using machine learning 

      Khan, Md.Shafayet; Afrida, Nazihan; Rahman, Munia; Islam, Sujana; Banik, Ananya (Brac University, 2022-09)
      Chronic kidney disease (CKD) is a determined disease condition having critical grimness and death rate that influences the whole grown-up populace brought about by either renal pathology or diminished renal capabilities. ...

    • Efficient monitoring of illicit activities: identifying smokers through human activity recognition 

      Amin, Nafiun Al; Haider, Ayan; Naomi, Tasmia Tarannum; Rahman, Rafid Sadman; Zaman, Nusaiba (Brac University, 2024-07)
      The use of security surveillance systems is becoming more prevalent, causing them to become an excellent tool for major crime prevention. However, niche crimes such as the use of cigarettes and other forms of smoking ...

    • Sentiment analysis on COVID-19 tweets 

      Ayon, Shadman Sakib; Ishrat, Samira; Mallick, Sadia Afrin; Das, Prodip Chandra (Brac University, 2022-09)
      The global spread of COVID-19, as well as the emergence of platforms as for many people a key source of information, has resulted in a wide range of reactions. But it is hard to keep up with this mass scenario. A significant ...

    • Classification of hotel reviews using sentiment analysis and machine learning 

      Shifullah, Khalid; Islam, Nuzhat; Raihan, Hasin; Rakibullah, H.M.; Iqbal, Md. Ashik (Brac University, 2022-09)
      Social media has become essential for people all over the world. It has given a platform for people to share thoughts, emotions, opinions, and ideas, causing a huge deal of data upsurge. Such an amount of data could be ...

    • Introducing a cost-effective cancer registry system for Bangladesh 

      Hassan, Md. Tareq; Sujan, Rahmat Ullah; Sarkar, Tushar Imran; Mostafiz, Gazi Sharin; Talukder, Mohammad Jonayed (Brac University, 2022-09)
      Cancer is an internecine disease caused by uncontrollable cell growth. There are many types of cancer, some severe and untreatable. In Bangladesh, there are 13 to 15 lac cancer patients and 2 lac new cases each year. A ...

    • Enhancing software quality: Python code smell detection using machine learning techniques and refactoring long methods using extract method algorithm 

      Ferdoshi, Jannatul; Abdullah, Shabab; Knobo, Kazi Zunayed Quader; Uddin, Mohammed Sharraf (Brac University, 2024-05)
      Python has witnessed substantial growth, establishing itself as one of the world’s most popular programming languages. Its versatile applications span various software and data science projects, empowered by features ...

    • An end-to-end authentication method for NB-IoT devices over 5G network using whirlpool hash function and physical unclonable function 

      Anisuzzaman, Kazi; Khan, Mehreen (Brac University, 2021-01)
      The Narrow-band Internet of Things (NB-IoT) is a high throughput and Low Power Con- sumption Wide Area Network (LPWAN) radio technology, introduced by 3rd Generation Partnership Project (3GPP). The NB-IoT and LTE-M ...

    • Analyzing the security differential privacy provides and the trade-off between performance and privacy in medical image classification 

      Haque, Sumaiya; Mehraj, Mohammad Azim; Rahman, Mohammad Faiazur; Abedin, Mahmud (Brac University, 2024-05)
      One of machine learning’s main purposes is to draw out functional and practical information from a set of data while perpetuating the entire privacy by protecting all information. While it might seem a bit hard to maintain, ...

    • Artificial intelligence in nephrology: detecting chronic kidney disease using neural network 

      Hridoy, Md. Farhan Rakib; Asif, Ahnaf; Mahmud, Mashruf; Rahman, Rashad; Siraj, Md Sahin (Brac University, 2024-05)
      Chronic kidney disease (CKD) is a significant global health concern, impacting more than 800 million people globally. Prompt identification and precise categorization are crucial for optimal therapy. The primary objective ...

    • Electronic medical record security and access control using blockchain and IPFS 

      Ali, Md.Yeasin; Ahmed, Suhaib; Akter, Bany Binthe; Haq, A.F.M. Mejbahul (Brac University, 2021-01)
      An EMR or electronic medical records typically contains minor to sensitive medical data of a patient including their personal information, doctors' provided prescription and other physical history. Switching to this ...

    • A smart trip advising system based on opinion mining with emoji recognition 

      Hassan, Mohammed Ziad; Islam, Mohammad Shahmidul; Abir, Ahasanul Haque; Tanha, Anwara Iftesum; Jenia, Akifa (Brac University, 2021-01)
      Opinion mining is an interesting research field that is used for analyzing the opinion of people about any product, place, and so on. Because based on people’s opinion other people can make decisions about what they ...

    • Finding motifs from DNA sequence using heuristic approach 

      Zaman, Shurid Shahriar; Kabir, Tahseen Tayeb; Islam, Md. Al-Junaed; Alam, Syed Md. Shamsul (Brac University, 2021-01)
      Finding patterns of the short sequences in DNA, RNA protein sequence has immense biological signi cance. The characterization and recognition of motifs is therefore an important method for a more in-depth understanding ...

    • A performance comparison between machine learning models on zero-day attack detection 

      Awon, Ahmed Musa; Odree, Afid; Islam, Samia; Yeasmin, Afia; Biva, Bivasha Bashir (Brac University, 2021-01)
      Traditional IDS has been shielding against cyber threats for many years but it falls short on detecting zero-day attacks. These are the attacks that are unique with unknown attack patterns and mutating attack signatures ...

    • Cloud based management system for RMG and comparison of efficiency 

      Rubyat, Fahim; Banna, Mehedi Al (Brac University, 2021-01)
      From technology startups to multinationals companies are starting to use Cloud Computing System, and the transformation is drastic. According to recent search just about 20 percent of companies have implemented cloud ...

    • Reducing latency for mobile devices 

      Khan, Mohammed Farhan; Iskander, Md. Murad Ali; Rouf, Ishmam Raiyan; Shatil, Ekram Wasi (Brac University, 2021-01)
      The massive development of the web has caused the servers to be overloaded and causes heavy amounts of network traffic. A Lot of users around the world are concurrently accessing the web, hence due to insufficient bandwidth ...

    • Wi-Fi based supervised machine learning approach to detect objects activities 

      Suzana, Samia Salam; Prome, Israt Jahan; Siddique, Ahnaf Hossain; Rahman, Zakia; Nasrin, Farzana (Brac University, 2021-01)
      Wireless signal based movement detection technologies are emerging effectively. This type of technology is quite popular compared to other ones because it relieves people from the hassle of wearing sensors and coming in ...