Browsing by Author "Hossain, Md. Shazzad"

Now showing 1 - 6 of 6

Brain Tumor Auto-Segmentation on Multimodal Imaging Modalities Using Deep Neural Network
(Daffodil International University, 2022-02-16) Hossain, Elias; Hossain, Md. Shazzad; Hossain, Md. Selim; Jannat, Sabila Al; Huda, Moontahina; Alsharif, Sameer; Faragallah, Osama S.; Eid, Mahmoud M. A.; Rashed, Ahmed Nabih Zaki
Due to the difficulties of brain tumor segmentation, this paper proposes a strategy for extracting brain tumors from three-dimensional Magnetic Resonance Image (MRI) and Computed Tomography (CT) scans utilizing 3D U-Net Design and ResNet50, taken after by conventional classification strategies. In this inquire, the ResNet50 picked up accuracy with 98.96%, and the 3D U-Net scored 97.99% among the different methods of deep learning. It is to be mentioned that traditional Convolutional Neural Network (CNN) gives 97.90% accuracy on top of the 3D MRI. In expansion, the image fusion approach combines the multimodal images and makes a fused image to extricate more highlights from the medical images. Other than that, we have identified the loss function by utilizing several dice measurements approach and received Dice Result on top of a specific test case. The average mean score of dice coefficient and soft dice loss for three test cases was 0.0980. At the same time, for two test cases, the sensitivity and specification were recorded to be 0.0211 and 0.5867 using patch level predictions. On the other hand, a software integration pipeline was integrated to deploy the concentrated model into the webserver for accessing it from the software system using the Representational state transfer (REST) API. Eventually, the suggested models were validated through the Area Under the Curve–Receiver Characteristic Operator (AUC–ROC) curve and Confusion Matrix and compared with the existing research articles to understand the underlying problem. Through Comparative Analysis, we have extracted meaningful insights regarding brain tumour segmentation and figured out potential gaps. Nevertheless, the proposed model can be adjustable in daily life and the healthcare domain to identify the infected regions and cancer of the brain through various imaging modalities.
Deep Convolutional Comparison Architecture for Breast Cancer Binary Classification
(Springer, 2023-06-11) Roni, Nasim Ahmed; Hossain, Md. Shazzad; Hossain, Musarrat Bintay; Efat, Md. Iftekharul Alam; Yousuf, Mohammad Abu
Early discernment of breast cancer can significantly improve the prospect of successful recovery and survival, but it takes a lot of time that frequently leads to pathologists disagreeing. Recently, much research has tried to develop the best breast cancer classification models to help pathologists make more precise diagnoses. Consequently, convolutional networks are prominent in biomedical imaging because they discover significant features and automate image processing. Knowing which CNN models are optimal for breast cancer binary classification is crucial. This work proposed architecture for finding the best CNN model. Inception-V3, ResNet-50, VGG-16, VGG- 19, DenseNet-121, DenseNet-169, DenseNet-201, and Xception are analyzed as classifiers in this paper. We have examined these deep learning techniques on the breast ultra-sound image dataset. Due to limited data, a generative adversarial network is used to improve the algorithm’s precision. Several statistical analyses are used to determine the finest convolutional technique for premature breast cancer detection using improved images in binary class scenarios. This binary classification experiment evaluates each strategy across various dimensions to determine what aspects improve success. In both normalized and denormalized conditions, the Xception maintained 95% accuracy. Xception uses the complete knowledge-digging technique and is highly advanced. Therefore, the accuracy is considered to be better than that of others.
Design and Development of a Web Based Application for Smart House Rent Management System
(Daffodil International University, 2019-04) Rasel, Md.; Hossain, Md. Shazzad
In this project, we will share our house rent management system and also given an idea of our house rent management system. This house rent management system is the best time saving online web application which give very much benefit to Owners and also User’s (customers). The house rent management system is based on the house Owners and users (Customers) and also admin, where Admin can add Owners and fix the house rent date. The Owner can update the user's info and Owner can add, edit, delete the user, to-let, fix the paying date, payment history and also can send the message to users. The user can view all information and send the message to the Owner also. The house rent management system is best suitable the owners because of time save, smart online application, the easy online to-lets system etc. The house rent management system is the best application in the city place. The customer contacts an easily search for a suitable place of the house. This System is saving time also. The house rent management system is used to easily identify a suitable place in save time, cost also. The house rent management system is the best way to search the house to-let online system.
Efficient Data Transmission through Fiber Optic Communication System Using SOA.
(2014-09) Howlader, Sujan; Hossain, Md. Shazzad; Hasan, Raja Rashidul; Basak, Rinku
This paper represents the characteristic of Semiconductor Optical Amplifier (SOA) by varying frequency of Vertical Cavity Surface Emitting Laser (VCSEL) which is used as a source at the transmitter end and also injection current of SOA. It is observed that by varying the injection current up to 1 ampere, maximum output power of 0.74935 watt can be achieved at the frequency of VCSEL of 193.1 THz when the optical fiber length is 50 Km. By varying the frequency from 177 to 250 THz, maximum output power of 0.10551 watt can be obtained at 240 THz with injection current of 0.15 ampere. In this paper it also observed that SOA can only operates in between the range of 0 to 1 ampere injection current. At 0.042 ampere injection current we get the maximum quality factor of 5.34 with Good BER of 4.67e-8.
Investigating the Q-factor and BER of a WDM system in Optical Fiber Communication Network by using SOA.
(2015-01) Hossain, Md. Shazzad; Howlader, Sujan; Basak, Rinku
This paper represents the analysis of Quality-factor and Bit Error Rate of an Optical signal in WDM system of a Fiber Optic communication network by using SOA. Vertical Cavity Surface Emitting Laser (VCSEL) is used as a transmitter. It is observed that by varying the frequency of bandwidth up to 34GHz a low BER with a high Q-factor is obtained. At 34GHz bandwidth maximum Q-factor of 13.1248 and minimum BER of 1.16972e-039 is obtained for 100km optical fiber length.
Web Security & Analysis
(East West University, 2019-04-23) Saha, Nirjhar; Hossain, Md. Shazzad
Website has become a platform of so many problems in present time. More likely we can do so many things by only using a website. In this paper the process of gathering raw data of any website is described. Also, we have added some unique feature in this system to make it more acceptable. We also can compare two websites in terms of traffic they are using. Here, scanning also can be done and malware can be detected. We think our work will be in help for the people who want to be sure whether their website is free of malware and want to compare that with similar type of website.