Browsing by Author "Abdullah"

Now showing 1 - 8 of 8

Audio recognition using feed forward neural network optimized by principle component analysis
(BRAC University, 4/18/2017) Momo, Nusrat Suzana; Abdullah; Uddin, Dr. Jia
In our proposed model we have used PCA as dimension reduction technique and neural network for pattern recognition. Our goal was to recognize audios of two vowels spoken by Parkinson’s disease Patient. The vocal of these patients becomes unclear in later stage of the disease, therefore understanding them becomes difficult and hence our model is targeted to help them communicate. PCA was run to get the finest number of features to train the classifier. The classifier takes 30 percent of the feature to train and the rest 70% for testing and validation. Our model has yield a very high accuracy compared to other models.
Av Machine Learning-Based Lightweight Consensus Framework for Blockchain-Enabled IoT Systems
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2025-10-25) Dihan, Mubtasim Kamal; Abdullah; Amina
The integration of blockchain with the Internet of Things (IoT) offers a promising ap proach to address the limitations of centralized IoT architectures. However, existing blockchain consensus mechanisms are often unsuitable for resource-constrained IoT devices and dynamic network conditions due to high computational demands or re liance on monetary-based participant selection.. In this work, we propose Dynamic& Periodic Proof of Evolutionary Model (DP-POEM), a lightweight, machine learning based consensus mechanism tailored for blockchain-based IoT systems. DP-POEM selects a group of block producers for defined periods using supervised learning, re ducing redundant computation while ensuring security through randomized block productionwithinthegroup. Itincorporatesbothstaticanddynamicallychangingde vice features, such as battery level and CPU usage, to select capable nodes efficiently, and implements fair participation mechanisms to balance network involvement over time. Theoretical analysis and experimental evaluation demonstrate that DP-POEM achieves high scalability, low latency, enhanced security, and improved applicability compared to traditional and state-of-the-art consensus protocols in dynamic IoT en vironments.
Blood Bank Management System
(Daffodil International University, 2021-09) Pranta, Mithun Ahmed; Abdullah; Sohag, Md. Shajjad Hossain
Blood is an essential component of all living organisms. In the event of an emergency, it proves to be a lifesaving component. The blood bank management system's job is to collect blood from a variety of donors. It is based on a mobile application that searches for blood supply from registered donors using a mobile search engine. These contain information like Donor Name, Blood Group, City living, Contact details, etc. It's not a lack of donors that's the issue; it's finding a willing donor at the proper time. We want to create a network of people who can assist one another in an emergency. The administrator has access to all donor-related information from the blood bank administration system using this application. In an emergency, the app can help you locate blood banks, determine if a specific or similar blood group fits, and navigate to the appropriate location.
Designing and Construction of Solar Tracker
(Department of Mechanical and Production Engineering (MPE),Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2017-11-15) Abdullah; Muhammad, Jebreel
The crucial purpose of our systematic experimental technique is to concentrate the solar radiation on the solar panel i.e. to construct a solar tracker system which will be capable of converting maximum sun light to electrical energy in accordance with the direction of the sun. Finally our Create a non-soldering, inexpensive, "smart" computer controlled, dual axis tracker for school and home use.
Fuel Injector Tester
(Department of Technical and Vocational Education, Islamic University of Technology, Board Bazar, Gazipur, Bangladesh, 2017-11-15) Kusada, Abdullahi Idris; Hassani, Chahardine Ali; Abdullah; Ali, Hammam; Khan, Muhammad Usman
The exponential development in technology and industry boosted the productivity of industries to such unprecedented level that caused an increase in the number of automobile produced for both industrial and personal use. As the amount of fuel is limited more studies are directed to reduce the fuel consumption of the automobile. One way of reducing the fuel consumption is the use of efficient and accurate fuel injector and to ensure that the fuel injector is efficient and accurate the fuel injector tester is quite handy tool to provide that platform. Another aspect is the environment concern that the emission of unburn fuel, CO and Co2 can be reduced by using accurate and efficient fuel injector. The purpose of our project is to construct a fuel injector tester to verify if a fuel injector is accurate to the manufacturer standards or not.
Optimized Plasmonic On-Chip Refractive Index Sensor for Biosensing Applications
(Department of Electrical and Elecrtonics Engineering(EEE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2024-06-25) Rahman, Asma; Ishrat, Samiha; Abdullah
This thesis focuses on designing plasmonic nanosensors for high-sensitivity detection of molecular interactions at the nanoscale, using SPPs and light-matter interaction. Two sensor designs, utilizing silver and ZrN materials, demonstrate significant sensitivity improvements via FEM analysis and Drude-Lorentz Model. Applications include medical diagnostics (e.g., cancer cell classification, detection of anemia and diabetes). The use of ZrN enhances sensor performance due to its exceptional optical and electrical properties, making it compatible with CMOS technology. OBE requirements are discussed regarding health, socio-cultural factors, and environmental sustainability.
Performance analysis of intrusion detection systems using the PyCaret machine learning library on the UNSW-NB15 dataset
(BRAC University, 2021-06) Abdullah; Iqbal, Faisal Bin; Biswas, Srijon; Urba, Rubabatul; Chakrabarty, Amitabha
As one of the fastest growing technologies on earth, the Internet of Things (IoT) is being embraced almost everywhere. From smart home technology to industrial automation, IoT is revolutionizing almost everything around us. It has enabled humans and organizations to do more with less, both in terms of time, as well as - nances. This feat of the Internet of Things, however, has also led to an alarming rise in attacks on IoT networks. Among these attacks, botnet intrusions are perhaps the most worrying ones. And with the advancement of time and technology, attackers are getting more creative. Hence, it is important to use better and more e cient machine learning technologies to identify these attacks and detect these intrusions before they can paralyze the system. This research aims to identify a more e cient machine learning approach for detecting botnets in IoT networks by utilizing the Py- Caret machine learning library and analyzing its overall performance. The research will encompass di erent classi ers and analyze the di erent performance metrics for each of them. It will also shed light on the feasibility of using the PyCaret library and how well suited it is for such usage.
Real Time Classification and Localization of Herb’s Leaves Using Yolo
(Daffodil International University, 2020-07) Shoreef Uddin, Md.; Abdullah
Day by day the usage of Artificial Intelligence makes our life easier and comfortable. Machines are started to learn as like human. Complex Problems can be solved easily by Artificial Intelligence. A machine can only do computing. By using the computing technique a machine can detect or classify objects. Getting higher accuracy and reducing prediction times are always the biggest challenges for image classification. Herbs have played a major parts in medical science for thousands year. Herbs have the ability to combat with diseases. People have less amount of knowledge about herbs as a result it becomes an issue to recognize them. Using poisonous plant as medication might increase the risk of life in serious way. In this paper we will discuss about how to classify and localize five types of herbs. Those five types of herbs are Mehdi, Betel, Mint, Basil and Aloe Vera. We will build a Neural Network model and train the model to classify the herbs. In Future we can implement the trained model into a mobile application which will help user to learn about herbal remedies. Therefore, we are proposing a novel approach for classifying herbs and also localizing the individual herb by using artificial intelligence.