Browsing by Author "Dr. Sifat Momen"

Now showing 1 - 10 of 10
  • Thumbnail Image
    Item
    Open Access
    A Lightweight Pruned DCNN Model with XAI for Skin Cancer Classification
    (North South University, 2024-08) MEHEDI HASAN; MAHIR SHAHRIAR ABIR; ABU TAYEB MOHAMMAD AYON; Dr. Sifat Momen; 2011425042; 2013640042; 2012547042
    Skin cancer is one of the most destructive types of cancer due to its immediate arrival and the potential for rapid spread. Sometimes, traditional diagnostic methods don’t react immediately because they need dermatologist expertise, some automation tools and time. This study explores one of the areas of artificial intelligencedeep learning, specifically Convolutional Neural Networks (CNNs), to enhance the efficiency and accuracy of skin cancer diagnosis. In this article, we introduce a lightweight pruned deep Convolutional Neural Network (dCNN) based method for skin cancer detection. With significantly lower trainable parameters, it surpasses recent state-of-the-art methods and shows competitive performance against 11 CNN-based pre-trained models, including Densenet121, DenseNet201, EfficientNetB2, InceptionV3, MobileNetV2, ResNet50, ResNet50V2, ResNet101V2, VGG16, VGG19, Xception. The proposed model demonstrates an accuracy of 98.07% with a notable precision of 98.15%, recall of 98.07%, and an F2 score of 98.02%. Even model interpretability perfectly works with Grad-Cam++. The proposed pruned model not only gets higher accuracy but also reduces computational cost, making it suitable for deploy on any device.
  • Thumbnail Image
    Item
    Open Access
    AI Virtual Assistant Robot for Youngsters
    (North South University, 2021) S.m. Nuruddin Ali Siam; Md. Zahidul Islam; Dr. Sifat Momen; 1610963043; 1711548042
    There are many voice-based AI assistant devices in markets. People are using those to their day to day lives. It has changed our lifestyle forever. We have gradually started to use these devices like our mobile phones. It is becoming one of our daily necessary tools. Sadly all of those devices are not youngsters friendly. Those devices are the source for adults only. In those device, there are some kinds of entertainment which are sometimes not suitable for youngsters. As a result our children are deprived from using modern technology. It is absolutely not a good sign for our future generation. Keeping this in mind we have built an AI assistant device or robot only for youngsters aged between 3 (three) to 12 (twelve) years. This robot has all the basic features a youngster needs. The robot will play Bengali and English poems, short stories, cartoon from youtube and history of Bangladesh. This will help youngsters to come close to the technology and learn something from it.
  • Thumbnail Image
    Item
    Open Access
    ALGORITHM VISUALIZATION
    (North-south University, 2022-12-31) Tabassum Rahman Aniqa; Shahriar Alam Tonmoy; Md. Tasnimul Hasan; Dr. Sifat Momen; 1811989042; 1812501642; 1813198642
    Abstract is not available in main pdf file.
  • Thumbnail Image
    Item
    Open Access
    Automatic Diabetic Retinopathy classification system based on CNN with the evaluation of different models
    (North-south University, 2021-12-31) Md.Tawfiq-Uz-Zaman; Anika Mehjabin Oishi; Mohammad Billal Hossain Emon; Dr. Sifat Momen; 1812832042; 1811399042; 1812447042
  • Thumbnail Image
    Item
    Open Access
    Blood Buddy: Blood Donation App for Android
    (North-south University, 2021-12-31) Mirza Sabbir Ahmed; Khandakar Faizul Haque Onim; Maruf Ahmed Khan; Dr. Sifat Momen; 1812680042; 1631707042; 1812640043
  • Thumbnail Image
    Item
    Open Access
    Collaborative Box Pushing by Swarms of Homogeneous Robots
    (North South University, 2018-12-31) Mostafa Shahriar Shohad; Atifur Rahman; Tanvir Ahsan Tantu; Sharmin Sultana; Dr. Sifat Momen
    Multi-robot systems in everyday use are the next big thing of the future. Division of workload is a very basic field of research in these type of systems that have many agents working together. This very basic phenomenon of load distribution is seen in many living organisms in the world, such as, ants, honey bees, termites, etc. When they are annoyed or disturbed by an internal or external factors, they show attractive abilities to distribute errors in order to counter the situation. Using these examples from nature, we can design new systems and build a framework that can handle complex real world issues by division of workload. This projects aim is to look at how swarms of homogeneous robots collaboratively carry out a task. The project is about a group of robots that can push a box while staying together in a flock. They will be able to detect obstacles in front of them and get past them. They will also be able to detect whether the obstacle in front of them is a robot or not. The main objective of this project is the distribution of workload among small homogeneous robots to execute a specific task, which is to push a box that is heavy enough for a single robot to push. In the near future, this project will help researchers to know more about swarm behavior and the allotment of task between multi-agent systems.
  • Thumbnail Image
    Item
    Open Access
    COVID-19 Severity Detection from Lung CT-Scan Images using CNN
    (North South University, 2022) Fahmida Sultana; Md. Abdullah Al Sayed; Sharmin Akter; Khandakar Mubarshar Uddin; Dr. Sifat Momen; 1812829042; 1822040642; 1812349042; 1711872042
    The severity of COVID-19 was detected in this project from Computed Tomography Scan (CT-scan) images of lungs using CNN. The world is devastated by the COVID- 19 epidemic, and the economy is in deep crisis. COVID-19 is one of the most recent high-risk issues worldwide. It is more risky and spreads very quickly through the respiratory tract. Anyone can get sick with COVID-19 and become seriously ill or die at any age. People who suffer from various diseases are more likely to become infected and develop more serious conditions. Most of the seniors are suffering from various lung problems, so they are becoming more infected and most of them have lost their lives. However, medical agencies do not have adequate equipment to detect COVID- 19 and its severity. Moreover, sometimes this tool has given wrong results. Therefore, it is very important to identify corona positive patients to prevent the spread of this virus. The best way to prevent this is to detect the severity of COVID-19 from a CT scan because it gives more accurate results and treats accordingly. People will be able to recognize the status of the infected person through this application. The condition may vary from critical, extent, minimal, moderate, normal or severe. The dataset was collected from the COVID-19 Infection Percentage Estimation Challenge arranged by CodaLab. They provided 3053 CT-scan images of lungs. These images have been classified into 6 classes. The classes are balanced by augmentation of the images. After augmentation 8614 images are created in the dataset. Some pre-trained models of CNN architecture like VGG16 and MobileNet have been used. Also, Convolutional Neural Network, densenet121 and Sequential CNN models have been applied for training. The accuracy found after applying these models are 85.92%, 80%, 76%, 69% and 63.87% from VGG16, Densenet121, Convolutional Neural Network, Mobilenet and Sequential models respectively. Among all the models the VGG16 has scored the highest accuracy. In the future, more models will be applied for training and for better accuracy.
  • Thumbnail Image
    Item
    Open Access
    Detecting Cancerous Nodules From Chest X-rays Using Deep Learning Techniques
    (North South University, 2022) Md. Tareq Mahmud; Nafis Iqbal; Shayam Imtiaz; Dr. Sifat Momen; 1811174042; 1811250642; 1811710642
    No abstract
  • Thumbnail Image
    Item
    Open Access
    Disaster Rescue AI: Advanced AI for Finding Alive People in Disasters and Alert System
    (North South University, 2025-04-30) Md. Adham Wahid; Fatema Afsan Ema; Istiak Ahasan; Dr. Sifat Momen; 2111177042; 2022281642; 2012082642
    A developmental illness that may manifest in early childhood is Attention Deficit Hyperactivity Disorder (ADHD). It may lead to poor self-esteem and social function in children if it’s not considered at an early age. Early detection and diagnosis of ADHD results in early interventions that improve social development, academic performance, and treatment outcomes among children. This is the first integrated framework that not only predicts ADHD in early childhood using Machine learning and Natural language processing techniques but also offers a Dialogflow-based therapeutic chatbot as a primary intervention an approach not addressed in existing literature. A total of fourteen Machine Learning and five BERT-based transformer algorithms with optimized hyperparameters have been applied to classify ADHD-positive and ADHD-free children identifying the key factors. The Stacking ensemble model came out with the best-performing metrics with 94.27% accuracy, 87.00% precision, 82.07% recall and 84.30% f1 score, and AUC of 0.97 that achieves state-of-the-art performance on CAHMI survey and dataset. While DistilBERT outshined among other BERT-based transformer models with 93.45% accuracy, 19.25s runtime, and AUC of 0.968 highlighting the natural language processing. LIME and SHAP have added enhanced transparency and dynamic decision-making interpretability. Unlike prior studies that focus solely on prediction, our model emphasizes both early diagnosis and immediate therapeutic support, bridging a critical gap between detection and intervention. Moreover, domain experts raw feedback and generalization through unseen datasetscontribute significantly to the novelty and practical relevance of the proposed system. This study presents a comprehensive statistical analysis through a well-structured machine learning and transformer pipeline, incorporating detailed visualizations alongside textual explanations.
  • Thumbnail Image
    Item
    Open Access
    IoT Based Automated Hydroponic Farming System
    (North South University, 2021-12-31) Sakib Asrar; Fahim Tanzil Takin; Ihfaz Tahmid Morshed; Tanvirul Azim; Dr. Sifat Momen; 1530620643; 1722192642; 1530879642; 1530617043
    The objective of this project is to control the environmental elements for farming using automated technology. An IoT based automated hydroponic system is proposed by which crops can grow in water with the necessary elements of the soil. The hydroponic method reduces water consumption up to 95% of regular farming, automates the regulation of the environment and nutrients in the farm to maximize production. Therefore, farmers can control all environmental elements with a minimum of time and effort. The proposed system can be remotely controlled and monitored via IoT. Using this farming method, crops can grow in any environment regardless of places and seasons.