Browsing by Author "Dr. Shazzad Hosain"

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    Embargo
    E-learning App with Augmented Reality
    (North South University, 2019-04-30) Md Nazmus Shakib; Safin Mahmud; Polash Chakrabarty; Abdullah All Noman Abir; Dr. Shazzad Hosain; 1511336042; 1510903042; 1520579042; ID # 1521047042
    Smartphone has become a great tool for teaching kids. As kids nowadays spend a lot of time on a smartphone. Preschool education is considered pivotal for a child’s development. Mobile learning is a new way to access learning content. Mobile learning is very popular among preschool kids. Because it really motivates kids to learn if they can use mobile phones or tablets. That's why we have developed a marker-based AR application, which will help children to learn or study the basics of Alphabets with fun. While using our app, kids will learn interactively with the help of Augmented Reality. Our app will help the parents teach their kids without much effort.
  • Thumbnail Image
    Item
    Open Access
    Early Fusion of CNN + BoVW Features for Facial Emotion Recognition on FER2013 without additional training data
    (North South University, 2023) Minhazul Abedin Toshin; Nashrah Haque; Md. Rifat Bin Yusuf; Labib Rahman; Dr. Shazzad Hosain; 1931672042; 1931857042; 1912217042; 1931740042
    Facial emotion recognition is an important research area with various applications such as human-computer interaction, psychology and social robotics. Consequently, there has been active research in the field using the approach of Convolutional Neural Networks (CNNs), for feature extraction and inference. In our paper, we explored the use of Bag of Visual Words(BoVW) and CNNs on the FER2013 dataset without any additional training data. To combine the features from both methods, we concatenated the feature vectors obtained from BoVW and CNN. Subsequently, we employed a Support Vector Machine (SVM) classifier to train and classify the concatenated feature vectors. The evaluation of our approach on the FER2013 dataset yielded an accuracy of 62%. Although this accuracy level indicates room for improvement, it demonstrates the potential of utilizing both BoVW and CNN in facial emotion recognition tasks. Overall, this study showcases the effectiveness of combining the BoVW approach with CNN for facial emotion recognition. The results obtained serve as a foundation for further investigations and advancements in this field.
  • Thumbnail Image
    Item
    Open Access
    Ecommerce Based Product Recommendation System
    (North-south University, 2021-11-30) Md. Mukith Al Alim; Md. Ashiqur Rahman Ovi; Md. Hasibul Hasan; Zeeshan Jamal; Dr. Shazzad Hosain; 1711376042; 1721444042; 1722351642; 1731699642
    This paper represents a noble approach to develop a Machine Learning method like Ecommerce Based Product Recommendation System for developing country like Bangladesh. The product recommendation system is a filtering system that seeks to predict and show the items that a user would like to purchase. Recommender systems have become increasingly popular in recent years and utilized in various areas, including movies, news, books, research articles, search queries, social tags, and products in general. It is an essential feature of the digital world. Because users are often overwhelmed by choice and need help finding what they are looking for. If a recommender system is set up and configured properly, it can be the reason for a significant boost in revenues, satisfied customers, and more sales. In this project, we have employed several machine learning algorithms (NCF, SVD, Encoder-Decoder, KNN) to build a recommender system for products and also have developed a website through which users can geta list of recommendations of products based on their preferences. These algorithms’ performancesare evaluated on different metrics. KNN has been selected to deploy on the website among all the algorithms.
  • Thumbnail Image
    Item
    Open Access
    IoT Based Self-Driving Car
    (North South University, 2020) Md. Tariqul Islam Shawon; Mukaddim Bhuyan Nabil; Dr. Shazzad Hosain; 1420635043; 1621848042
    Self-driving vehicles represent a technological leap forward that can offer solutions to current transportation problems and dramatically change how people approach mobility. While self-driving cars have the potential to improve safety and increase quality of life, many people appear reluctant to adopt the technology, because they are uncomfortable with safety, liabilities, and control. Public attitudes toward self-driving cars are increasingly important as the public shapes the demand for the technology, policies that govern them, and future investments in infrastructure. Moreover, the nature of the technology means that the truly transformative benefits are only realized once self-driving cars are adopted by mass. We find that individuals are most attracted to potential safety benefits, the convenience of not having to find parking, and amenities such as multitasking while end route; conversely, individuals were most concerned with liability, the cost of the technology, and losing control of the vehicle. Men are more likely to be concerned with liability, and less likely to be concerned with control than women. Individuals with higher income are most concerned with liability, and those with lower income appear to be more concerned with safety and control. Single-occupancy vehicle commuters and cyclists were most concerned with giving up control. All groups were concerned with costs. We present this paper to inform those creating this technology how self-driving cars will likely be perceived by the public.
  • Thumbnail Image
    Item
    Open Access
    MediCare- Mobile and Web Virtual Communication Application for Doctor and Patient
    (North South University, 2021-04-30) Aniket Banik; Rutton Chandra Sarker; B.M Yousuf; Md. Ali Haider Chowdhury; Dr. Shazzad Hosain; 1612719042; 1631065042; 1620286642; 1631541042
    Medical facilities are the most significant facilities for everyone. In the today’s modern world, everything is dependent on online technologies like software, android application, website and many more. So, it is so much necessary that people can get medical treatment from doctors virtually and online. There are many villages and remote areas in Bangladesh and in other places of the world, where medical facilities and treatment facilities from a doctor or professor, are not properly existed there. That’s why; we made an android application and a website which will help all kinds of people to get medical facilities like treatment and healthcare through online application and website. The title of our android application and website is “MediCare” which will help a lot to reduce the hassle of the patient or user who cannot easily get medical treatment during their emergency moment because of the lack of the existence of hospitals, health care centers, urgent care centers and doctor’s clinic at their areas or nearest areas. With the help of our android application and website, all kinds of people can book their appointment with a doctor of a specific department and then they can connect with a doctor through a video call to get treatment at their fixed appointment date and time. All users or patients must need to register and login to get appointment from a doctor for treatment purpose. Another important fact is doctors can see the medical reports of the patient and provide prescriptions to patients through online. This is how our “MediCare” will play a significant role in today’s world.
  • Thumbnail Image
    Item
    Open Access
    Shahajjor Chhaya
    (North South University, 2020) Sheikh Elhum Uddin Quadery; Refat Chowdhury; Md Shakib Ahmed; Shabab Rahman; Dr. Shazzad Hosain; 1721377042; 1711443042; 1620418642; 1712021042
    One of the main problems the world is facing right now is getting proper healthcare. There aren’t enough doctors out there to meet the demand. This crisis has led to a rise in telemedicine in recent years. Telemedicine is where a patient is taken care of remotely by a healthcare provider. However doctors are still not engaging in providing healthcare through an online platform as much as they should have been doing. The most likely reason for this is a lack of user friendly platform for the doctors. In order to solve the healthcare demand crisis we need online platforms where doctors can take appointments and communicate with patients with ease. Patients also need a platform where they can get trusted doctors of different medical fields. “Shahajjor Chhaya” aims to solve this problem with platforms supported on both smartphones and PCs and with a special focus on those who live in regions that are not of the urban populace
  • Thumbnail Image
    Item
    Embargo
    Vehicle Detection, Tracking, and Counting System with Number Plate Recognition in a Petrol Station
    (North South University, 2023) Shadman Sakib; Rahul Deb Roy; Moriom Islam Mou; Dr. Shazzad Hosain; 1931024042; 1931132042; 1931333042
    The efficient management of vehicles within a petrol station is a critical aspect of ensuring smooth operations, security, and customer service. In this technological age, the integration of vehicle tracking and number plate recognition systems has become imperative. The primary objective of this system is to provide real-time monitoring of vehicle entry and exit, enabling the station management to accurately track the number of vehicles on the premises at any given time. The system utilizes cameras equipped with license plate recognition software to capture and recognize vehicle number plates as vehicles enter and exit the station. Petrol stations, at the heart of transportation networks, serve as vital nodes for the distribution of fuel and energy resources. Efficiently managing the flow of vehicles through these stations is essential for ensuring smooth operations, enhancing security, and optimizing customer service. After conducting extensive market research, we identified a significant gap in the application of vehicle tracking, counting, and classification technology at petrol stations. Our analysis revealed that this technology had not been effectively implemented in the real world, despite its potential to bring substantial benefits to the industry. The intricate process of detecting, tracking, Bangla Number plate detection and tallying vehicle types within a CCTV surveillance system is an inherently sophisticated yet remarkably efficient operation. For the subsequent stage of vehicle counting, we harnessed the capabilities of Python, the Ultralights library, and OpenCV. Moreover, the datasets are collected from Kaggle and Roboflow for training purposes.