Browsing by Author "Mahmud, Md. Nadim"

Now showing 1 - 4 of 4

Peripheral Blood Smear Image-Based Blood Cancer Detection Using Transfer Learning
(Springer Nature, 2024-03-30) Shaha, Sonjoy Prosad; Datta, Sajeeb; Mahmud, Md. Nadim; Ahmad, Md. Hassan; Johora, Fatema Tuj; Rahman, Md. Atiqur
The lymphatic, bone marrow, and blood systems are all affected by hematological malignancy, also known as blood cancer. Early detection is essential for improved blood medical care and better patient outcomes. In the recent past, deep learning algorithms have developed as useful tools for the analysis and diagnosis of medical images. Deep learning algorithms are used in this study to introduce a cutting-edge technique for identifying blood cancer. Our method involves training a convolutional neural network (CNN) with a large dataset of blood cell data to identify the presence of cancerous cells. We compare our CNN-based approach’s effectiveness with some other CNN-based approaches and demonstrate that it is more effective at detecting blood cancer. We used a variety of preprocessing techniques to provide highly trainable data for our algorithms in order to do this. Five CNN-based algorithms—VGG-19, VGG-16, MobileNet, InceptionV3, and ResNet50—as well as healthy and fragmented data are used in this study. With an accuracy of 95%, ResNet50 achieved the highest accuracy. Our study’s results suggest that deep learning algorithms could be helpful in detecting blood cancer early, leading to a more precise diagnosis and course of treatment for this fatal condition.
Peripheral Blood Smear Image-Based Blood Cancer Detection Using Transfer Learning
(2024-03-30) Shaha, Sonjoy Prosad; Datta, Sajeeb; Mahmud, Md. Nadim; Ahmad, Md. Hassan; Tuj Johora, Fatema; Rahman, Md. Atiqur
The lymphatic, bone marrow, and blood systems are all affected by hematological malignancy, also known as blood cancer. Early detection is essential for improved blood medical care and better patient outcomes. In the recent past, deep learning algorithms have developed as useful tools for the analysis and diagnosis of medical images. Deep learning algorithms are used in this study to introduce a cutting-edge technique for identifying blood cancer. Our method involves training a convolutional neural network (CNN) with a large dataset of blood cell data to identify the presence of cancerous cells. We compare our CNN-based approach’s effectiveness with some other CNN-based approaches and demonstrate that it is more effective at detecting blood cancer. We used a variety of preprocessing techniques to provide highly trainable data for our algorithms in order to do this. Five CNN-based algorithms—VGG-19, VGG-16, MobileNet, InceptionV3, and ResNet50—as well as healthy and fragmented data are used in this study. With an accuracy of 95%, ResNet50 achieved the highest accuracy. Our study’s results suggest that deep learning algorithms could be helpful in detecting blood cancer early, leading to a more precise diagnosis and course of treatment for this fatal condition.
Studies on the Changes of Twill and Denim Garments After Dyeing and Washing Process
(Daffodil International University, 2019-12-10) Apple, Md. Ashikur Rahman; Mahmud, Md. Nadim
Raw denim garments obtained after finishing is impossible to wear before dyeing and washing because of rigidity and stiffness of finished denim. Finished denim garments is also looking dull before dyeing and washing. Twill garments also looking dull and impossible to wear before dyeing and washing. So that the denim and twill garments have to wash properly for its great performance. Denim wash actually not chance garments physical property but also change aesthetic property of denim garments. This project is done for comparing the physical properties like rubbing fastness, weight, length wish shrinkage, width wise shrinkage, PH, tearing strength, tensile strength, gsm. We saw a twill garments for 4 pcs before wash this weightwas2.900kgandafterdifferentdyeingandwashingitgoesto3.100kg.Andgsmbeforewashwas 8.78 oz/yd2 and after wash it changes to 8.84 oz/yd2. This garments length wise shrinkage percentage after wash 2.70% and width wise shrinkage percentage 8.00%. PH need 6-8 but here PH was 6.78. Rubbing fastness for dry have 4-5 and wet have 3-4. And some body measurement change after garments dyeing and washing waist was before wash 31.5 and after wash 29.5.This all data collected from laboratory and quality control section of Standard Group Ltd. After comparing those changes of garments we can comments about reasons of change garments property. Enzyme, bleach, towel, stone, acid wash is the main reason for changing those property.
Study on Grid Connected Solar PV System
(Daffodil International University, 2019-07-16) Badsha, MD. Imran; Mahmud, Md. Nadim; Bakul, Md.Safayet Ahmed Safu
This paper presents the arrangement and diversions of a photovoltaic structure using trouble and watches methodology most extraordinary powerpoint following (MPPT) calculation with help converter. Furthermore, this paper deals with the arrangement and generation of a three-stage inverter in MATLAB SIMULINK condition which can be a bit of photovoltaic grid-related structures. At present, photovoltaic (PV) frameworks are playing a main job as sun based sustainable power source (RES) due to their extraordinary points of interest. This pattern is being expanded particularly in lattice associated applications due to the numerous advantages of utilizing RESs in appropriated age (DG) frameworks. This new situation forces the necessity for a successful assessment device of framework associated PV frameworks to anticipate precisely their dynamic execution under various working conditions so as to settle on an extensive choice on the plausibility of joining this innovation into the electric utility matrix. This suggests not exclusively to distinguish the qualities bends of PV modules or exhibits yet additionally the dynamic conduct of the electronic power molding framework (PCS) for associating with the utility matrix. To this point, this part talks about the full nitty-gritty displaying and the control structure of a three-stage network associated photovoltaic generator (PVG). The PV exhibit model permits anticipating high exactness the I-V and P-V bends of the PV boards/clusters. Additionally, the control plot is given the abilities of at the same time and freely managing both dynamic and responsive power trade with the electric lattice. The displaying and control of the three-stage matrix associated PVG are actualized in the MATLAB/Simulink condition and approved by trial tests.