Browsing by Author "Haque, Md. Samiul"

Now showing 1 - 3 of 3

Analysis of genetic polymorphisms in somaclonal variants of strawberry by RAPD markers
(Bioscience Research, 2018) Bir, Md. Shahidul Haque; Haque, Md. Samiul; Haque, M. Mahbubul; Nath, Uzzal Kumar; Khatun, Roushan Ara; Ali, Mohammad; Soh, ,EunHee; Park, Kee Woong
The understanding of the importance of dietary berries of maintaining human health has led to unrestrained increase of global strawberry crop production. The present work was conducted for molecular characterization and selection of genetically pure somaclonal variants of strawberry. For molecular characterization, RAPD (Random Amplified Polymorphic DNA) markers namely instead OPK 01, OPK-02, and OPK-03, showed good technical resolution and sufficient variations among the somaclonal variants. A total of 29 RAPD bands were scored, of which 27 (94.87%) by using these arbitrary primers were obtained by polymorphic amplification products. OPK-01 produced the number of polymorphic bands of 100-700 bp compared to OPK-02 and OPK-03. All the somaclonal variants produced polymorphic bands with three RAPD markers suggesting that the somaclonal variants were different from each other and genetic divergence were present among them. Thus, these markers could be used for comparison of the genetic relationships, determination of patterns of genetic variation, and measurement of genetic distance among the somaclonal variants of strawberry.
Prostate cancer detection using deep learning neural network with transfer learning approach
(BRAC University, 2021-10) Badhon, Ariful Islam Mahmud; Hasan, Md. Sadman; Haque, Md. Samiul; Pranto, Md. Shafayat Hossain; Ghosh, Saurav; Alam, Md. Golam Rabiul; Rashid, Warida
Prostate cancer is a ubiquitous form of cancer detected among men all over the world. It is currently the second leading cause of cancer death worldwide among men. Research shows that about 11% of men worldwide are affected by prostate cancer at some point during their lives. In our thesis, we have used a Transfer Learning approach for the Deep Learning model to compare the precision in results using machine learning classifiers. We have also evaluated performance in terms of classification with different evaluation measures using a Deep Learning pre-trained network (VGG16). Parameters such as Precision, Recall, F1 score and Loss vs Accuracy were assessed thoroughly as different performance measures. After applying the Transfer Learning approach, we have recorded the peak performance using the VGG16 architecture. We used the convolutional block and dense layers of VGG16 architecture to extract features from image datasets. We forwarded those features to Machine Learning classifiers for the final classification result. We have procured outstanding accuracy using the Deep Machine Learning method in our research.
Studies on the molecular basis of environmental stress tolerance in jute
(© University of Dhaka, 2025-04-24) Haque, Md. Samiul