Publications | Abu Noman Md Sakib

2023

STI
Segmentation of Hemorrhagic Areas in Human Brain from CT Scan Images

Abu Noman Md Sakib, Nipa Anjum, and Sk. Md. Masudul Ahsan

In 4th International Conference on Sustainable Technologies for Industry 4.0 (STI), Dhaka, Bangladesh, 2023

Abs DOI Bib PDF Code Website

Brain hemorrhage is potentially a fatal condition that results from internal bleeding in the human brain. In this study, Computed Tomography (CT) scan images have been used for segmentation tasks to pinpoint the area of hemorrhage. Unique data augmentation techniques using non-linear transformations like, Twirl and Spherical have been used along with traditional data augmentation techniques to increase variation in the dataset. The hemorrhagic portion of the brain in images that are easy to distinguish have been annotated to perform the segmentation task. The segmentation task was applied using U-Net and U-Net++ architecture. U-Net architecture has shown 84.33% Intersection over Union (IoU) and 91.34% dice coefficient score whereas U-Net++ has achieved 17.06% IoU and 28.27% dice coefficient score after applying some non-linear transformations on the dataset.
@inproceedings{10103333, location = {Dhaka, Bangladesh}, author = {Md Sakib, Abu Noman and Anjum, Nipa and Ahsan, Sk. Md. Masudul}, booktitle = {4th International Conference on Sustainable Technologies for Industry 4.0 (STI)}, doi = {10.1109/STI56238.2022.10103333}, isbn = {978-1-6654-9045-0}, publisher = {IEEE}, pages = {1-5}, title = {Segmentation of Hemorrhagic Areas in Human Brain from CT Scan Images}, year = {2023} }
ICICTD
Classification of Brain Hemorrhage Using Deep Learning from CT Scan Images

Nipa Anjum, Abu Noman Md. Sakib, and Sk. Md. Masudul Ahsan

In Proceedings of International Conference on Information and Communication Technology for Development, Singapore, 2023

Abs DOI Bib PDF Code Website

Brain hemorrhage is a life-threatening problem that happens by bleeding inside human head. In this study, computed tomography (CT) scan images have been used to classify whether the case is hemorrhage or non-hemorrhage. Different convolutional neural network (CNN) models have been observed along with some pre-trained deep learning models such as VGG16, VGG19, ResNet150, ResNet152 and InceptionV3. Pre-trained models have performed well on the dataset but all of them are heavyweight architectures in terms of number of total parameters. But the proposed model is a lightweight architecture as well as a well performing one. After evaluating the model performance, it has been observed that the proposed model gave 96.67% accuracy, 97.08% sensitivity and 96.25% specificity which is the best among other custom CNN models.
@inproceedings{10.1007/978-981-19-7528-8_15, author = {Anjum, Nipa and Sakib, Abu Noman Md. and Masudul Ahsan, Sk. Md.}, editor = {Ahmad, Mohiuddin and Uddin, Mohammad Shorif and Jang, Yeong Min}, booktitle = {Proceedings of International Conference on Information and Communication Technology for Development}, title = {Classification of Brain Hemorrhage Using Deep Learning from CT Scan Images}, year = {2023}, publisher = {Springer Nature Singapore}, location = {Singapore}, doi = {10.1007/978-981-19-7528-8_15}, pages = {181-193}, isbn = {978-981-19-7528-8}, }
ICSISCET
Corn Leaf Disease Identification via Transfer Learning: A Comprehensive Web-Based Solution

P. Goswami, A. Al Safi, A.N.M. Sakib, and 1 more author

In International Conference on Sustainable and Innovative Solutions for Current Challenges in Engineering & Technology. ICSISCET 2023. Algorithms for Intelligent Systems., Singapore, 2023

Abs DOI Bib PDF Code Website

Effective crop disease prevention is essential to ensure global food security and early disease detection is a vital part of this protection. Traditional techniques of identifying disease are lengthy process, costly, sometimes require specialized knowledge, and nevertheless may produce erroneous outcomes. Artificial intelligence offers the best answer in this situation. Deep learning has become essential for analyzing images and classification. This study proposes a website that uses deep learning for classifying three major diseases of maize leaves: blight, common rust, and grey leaf spot as well as for identifying healthy leaves. Additionally, it conducts a comparative analysis of various state-of-the-art models using the same dataset to determine the most suitable approach for website development considering metrics such as accuracy, precision, recall, F1 score, training time, and model size. All the used models (MobileNetV2, AlexNet, ResNet18, VGG16, VGG19, and SqueezeNet) have been optimized for faster operation and lower storage consumption. The models were trained using the “Corn or Maize Leaf Disease Dataset” on Kaggle, which included 2930 images of maize leaves. After that, the models were tested using a separate set of 422 images, categorized into four classes: three representing diseases (blight, common rust, and grey leaf spot) and the fourth representing healthy leaves. Out of all the models, ResNet18 has the highest accuracy (96.45%). ResNet18 has several evaluation matrices that make it ideal for this investigation, including quick training and a small model size. As ResNet18 provides the best result, the website can accurately classify disease class and display the probability of identification for uploaded corn leaf images using this model. The model’s performance is found satisfactory for its real-world application in automatically detecting maize leaf diseases.
@inproceedings{10.1007/978-981-97-0327-2_32, author = {Goswami, P. and Al Safi, A. and Sakib, A.N.M. and Datta, T.}, booktitle = {International Conference on Sustainable and Innovative Solutions for Current Challenges in Engineering & Technology. ICSISCET 2023. Algorithms for Intelligent Systems.}, doi = {10.1007/978-981-97-0327-2_32}, isbn = {978-981-97-0327-2}, location = {Singapore}, publisher = {Springer Nature Singapore}, pages = {429--441}, title = {Corn Leaf Disease Identification via Transfer Learning: A Comprehensive Web-Based Solution}, url = {https://link.springer.com/chapter/10.1007/978-981-97-0327-2_32}, year = {2023} }

2022

IJCACI
An End-to-End Web-Based System for Rice Leaf Disease Classification Using Deep Learning

P. Goswami, A.B.M. Aowlad Hossain, and A.N.M. Sakib

In Proceedings of International Joint Conference on Advances in Computational Intelligence. IJCACI 2022. Algorithms for Intelligent Systems., Singapore, 2022

Abs DOI Bib PDF Code Website

The smart agriculture or intelligent farming is getting popularity day by day since the machine learning (ML)-based technologies are using as proven effective tools. Disease of rice plant leaf is one of the most common obstacles in the production of rice to meet the huge amount of demand all over the world. This paper represents a website framework using deep learning to classify three common rice leaf diseases: Bacterial Leaf Blight, Brown Spot, Leaf Smut, and also can identify the Healthy one. Moreover, it provides an insight comparison analysis in results (accuracy, training time, model size, and parameters) of different state of art methods using same dataset and we have chosen the best one among them for website development. All the used models (InceptionV3, MobileNetV2, VGG19, ResNet50, VGG16, and AlexNet) have been customized for faster operation and lower storage. Preprocessing comprises organizing images in a uniform manner in order to maximize accuracy. The models were trained using Bahri’s dataset of 9600 images of rice leaves, validated with 2400 images and tested with 4000 images. MobileNetv2 and VGG16, out of all the models, had greater accuracy results (98.05% and 99.3%, respectively). However, other evaluation matrices such as speedy training, small model size, and lower parameters have made MobileNetV2 perfect for this study. In the developed website, for each uploading rice leaf image, it can identify the disease class using MobileNetV2 model.
@inproceedings{10.1007/978-981-97-0180-3_40, author = {Goswami, P. and Aowlad Hossain, A.B.M. and Sakib, A.N.M.}, booktitle = {Proceedings of International Joint Conference on Advances in Computational Intelligence. IJCACI 2022. Algorithms for Intelligent Systems.}, doi = {10.1007/978-981-97-0180-3_40}, isbn = {978-981-97-0180-3}, location = {Singapore}, publisher = {Springer Nature Singapore}, pages = {517--531}, title = {An End-to-End Web-Based System for Rice Leaf Disease Classification Using Deep Learning}, url = {https://link.springer.com/chapter/10.1007/978-981-97-0180-3_40}, year = {2022} }

2021

WSCG
A Deep CNN Model for Skin Cancer Detection and Classification

Masum Shah Junayed, Nipa Anjum, Abu Noman Md Sakib, and 1 more author

2021

Abs DOI Bib PDF Website

Skin cancer is one of the most dangerous types of cancers that affect millions of people every year. The detection of skin cancer in the early stages is an expensive and challenging process. In recent studies, machine learning-based methods help dermatologists in classifying medical images. This paper proposes a deep learning-based model to detect and classify skin cancer using the concept of deep Convolution Neural Network (CNN). Initially, we collected a dataset that includes four skin cancer image data before applying them in augmentation techniques to increase the accumulated dataset size. Then, we designed a deep CNN model to train our dataset. On the test data, our model receives 95.98% accuracy that exceeds the two pre-train models, GoogleNet by 1.76% and MobileNet by 1.12%, respectively. The proposed deep CNN model also beats other contemporaneous models while being computationally comparable.
@article{10.24132/csrn.2021.3002.8, author = {Junayed, Masum Shah and Anjum, Nipa and Sakib, Abu Noman Md and Islam, Md Baharul}, booktitle = {International Conference on Computer Graphics, Visualization and Computer Vision}, title = {A Deep CNN Model for Skin Cancer Detection and Classification}, volume = {29}, pages = {71--80}, publisher = {Computer Science Research Notes, Journal of WSCG}, year = {2021}, doi = {10.24132/csrn.2021.3002.8}, url = {https://doi.org/10.24132/csrn.2021.3002.8}, }

2020

ICCIT
SkNet: A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes

Afsana Ahsan Jeny, Abu Noman Md Sakib, Masum Shah Junayed, and 3 more authors

In 23rd International Conference on Computer and Information Technology (ICCIT), 2020

Abs DOI Bib PDF Website

Skin Cancer is one of the most common types of cancer. A solution for this globally recognized health problem is much required. Machine Learning techniques have brought revolutionary changes in the field of biomedical researches. Previously, It took a significant amount of time and much effort in detecting skin cancers. In recent years, many works have been done with Deep Learning which made the process a lot faster and much more accurate. In this paper, We have proposed a novel Convolutional Neural Networks (CNN) based approach that can classify four different types of Skin Cancer. We have developed our model SkNet consisting of 19 convolution layers. In previous works, the highest accuracy gained on 1000 images was 80.52%. Our proposed model exceeded that previous performance and achieved an accuracy of 95.26% on a dataset of 4800 images which is the highest acquired accuracy.
@inproceedings{9392716, author = {Jeny, Afsana Ahsan and Sakib, Abu Noman Md and Junayed, Masum Shah and Lima, Khadija Akter and Ahmed, Ikhtiar and Islam, Md Baharul}, booktitle = {23rd International Conference on Computer and Information Technology (ICCIT)}, title = {SkNet: A Convolutional Neural Networks Based Classification Approach for Skin Cancer Classes}, year = {2020}, pages = {1-6}, doi = {10.1109/ICCIT51783.2020.9392716}, }
IPAS
EczemaNet: A Deep CNN-based Eczema Diseases Classification

Masum Shah Junayed, Abu Noman Md Sakib, Nipa Anjum, and 2 more authors

In IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), 2020

Abs DOI Bib PDF Website

Eczema is the most common among all types of skin diseases. A solution for this disease is very crucial for patients to have better treatment. Eczema is usually detected manually by doctors or dermatologists. It is tough to distinguish between different types of Eczema because of the similarities in symptoms. In recent years, several attempts have been taken to automate the detection of skin diseases with much accuracy. Many methods such as Image Processing Techniques, Machine Learning algorithms are getting used to execute segmentation and classification of skin diseases. It is found that among all those skin disease detection systems, particularly detection work on eczema disease is rare. There is also insufficiency in eczema disease dataset. In this paper, we propose a novel deep CNN-based approach for classifying five different classes of Eczema with our collected dataset. Data augmentation is used to transform images for better performance. Regularization techniques such as batch normalization and dropout helped to reduce overfitting. Our proposed model achieved an accuracy of 96.2%, which exceeded the performance of the state of the arts.
@inproceedings{9334929, author = {Junayed, Masum Shah and Sakib, Abu Noman Md and Anjum, Nipa and Islam, Md Baharul and Jeny, Afsana Ahsan}, booktitle = {IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS)}, title = {EczemaNet: A Deep CNN-based Eczema Diseases Classification}, year = {2020}, pages = {174--179}, doi = {10.1109/IPAS50080.2020.9334929}, }