Browsing by Author "Hasan, Fahim"

Now showing 1 - 5 of 5

Design and development of a cost effective urban resedential solar PV system
(BRAC University, 2010-12) Hasan, Fahim; Hossain, Jakir; Rahman, Maria; Ar Rahman, Sazzad
Detecting misleading information from Large Language Models responses
(BRAC University, 2025-02) Ador, Muntasir Ahmed; Hasan, Fahim; Mahamud, Syed Ashik; Nazmin, Iffat Ara; Muntasir Arin, Md. Mahim; Azmain, Md. Aquib; Anwar, Md. Tawhid
The arrival of large language models (LLMs) have been a game-changer in natural language processing (NLP). It revolutionized the way we comprehend and generate content. However, LLMs can hallucinate-that is, contradict the reality or input provided by the user. This is a big problem because these models are being used these days in many diverse industries, including for medical and legal purposes where accuracy is paramount. Hallucinations can damage user trust and lead to the spread of incorrect facts. Although it is not a major issue in ordinary situations, it raises serious concerns in sensitive areas like healthcare and legal advice. Also it can inadvertently become part of the training corpus for future models if not carefully filtered. This creates a feedback loop where errors in one generation of models can propagate and potentially amplify in subsequent iterations. To solve this problem, we have created an all-rounded dataset with questions from SQuAD (Stanford Question Answering Dataset), HotpotQA, and TriviaQA, among other datasets. We will use the state-of-the-art LLM GPT-4o mini to generate answers. Finally, to this end, the paper describes several rules for the annotation of a corresponding dataset, its resulting characteristic properties and the classification quality that can be achieved when using the dataset for fine-tuning different models.
E-commerce Merchant Fraud Detection using Machine Learning Approach
(Daffodil International University, 2022-06-20) Hasan, Fahim; Mondal, Sourov Kumar; Kabir, Md Rayhan; Al Mamun, Md Abdullah; Hossen, Md. Sagar; Rahman, Nur Salman
At present, e-commerce has become a global phenomenon. With the great achievement of ecommerce, many are cruel Promotional services are also increasing: with the aim of growing sales, spiteful marketers try to improve their target spectators by improving the outcomes of an illegal search using false travel, shopping, etc. In this report, we read about the problem of deception in major commerce platforms. First, we want to list the merchant fraud, the names of those who have previously committed fraud in the business will be marked on the list. And will train machines using machine learning approach. So that, if a merchant id is given in the system, it can detect whether the id is fraud or not. Our lesson here paper is predictable to hut light on the defense in contradiction of e-commerce fraud of active commerce platforms. In this research report, we proposed a machine learning model to analyze and identify merchant fraud. As a machine learning model, we choose the Random forests, decision tree and logistic regression algorithm for our model.
Local Fruit Classification and Recognition using Transfer Learning Models
(IEEE, 2023-11-23) Dey, Udoy Chandra; Hasan, Fahim; Papel, Md. Habibur Rahman; Turza, Toufiq Hasan; Hasan, Md. Mehedi; Kabir, Md. Rayhan
The practice of automatically classifying images is gaining popularity. Many of us have very little knowledge of the local fruits, yet even in that case, we can vouch to their quality. In our study, we'll talk about a deep learning based system that can distinguish local fruits automatically. Fruit identification is a highly common activity, but automatically classifying fruits based on their placements, shapes, colors, and other attributes is a difficult task. Our study involved the collection of samples from several local areas, followed by the use of various transfer learning models, including VGG-19, Inception-v3, MobileNet, etc. MobileNet provided us with the highest accuracy of 99.53% among them. A top model was also suggested depending on the accuracy of our training. We used 60% of the image data from the 3240 total samples for training, for the purpose of validation we use 20% of the image data, and 20% of the total image data for testing. We received a satisfactory outcome after training and testing. Local fruits are classified as a consequence of this research model, which can be useful for everyday fruit identification.
Using RFID for inventory management and operations of R-pac
(BRAC University, 2019-11) Hasan, Fahim; Habib, Md. Mamun
R-Pac is a packaging accessories manufacturer for garments industry. R-Pac basically produces different types of labels, packaging items, tags, and RFID tags. They have six different departments and they are offset, PFL, Weaving, HTL, flexo, and thermal and RFID department. While I was doing my internship at R-Pac I was assigned to every department for a specific period of time and gain a practical experience of their operation. Offset department produces tags and packaging items. PFL and weaving department produces printed labels. HTL department produces heat sensitive labels. These labels are directly attached on the fabric with heat and pressure. Flexo department mainly produces sticker items. R-Pac’s one of the most efficient and productive department is thermal and RFID department. Thermal and RFID department mainly produce barcode and tags attached with RFID. RFID is the updated version of barcode which has a microchip attached with the barcode. These microchip contains specific information and can be tracked without manual labor. RFID can ensure the security of the and also gives us the capability of continuous monitoring of the product.