Browsing by Author "Ataur Rahman, Md."

Now showing 1 - 3 of 3

Hydraulic model study of bed level changes of alluvial river
(Department of Water Resources Engineering, 2002-08) Ataur Rahman, Md.; Abdul Matin, Dr. Md.
The Saint-Venant equations describing unsteady flow in open channels and the continuity equation for the conservation of sediment mass are numerically solved to determine the aggradation-degradation of channel bottom due to an imbalance between water flow and sediment discharge. For this purpose the MacCormack explicit finite difference scheme is used. The scheme is second order accurate, handles shocks and discontinuities in the solution without any special treatment, and allows simultaneous solution of the water and sediment equations, thereby obviating the need for iterations. The sediment transport relationship in any form may be included in the computations. The mathematical model presented here is applied to predict the bed level changes of alluvial channel due to sediment over loading. To verify this model, the laboratory experiment is carried out at the Hydraulics and River Engineering Laboratory of Department of Water Resources Engineering, Bangladesh University of Engineering and Technology, Dhaka. The sediment transport equation qs = aub is calibrated through experimental rnns and the value of the coefficient 'a' and 'b' is detemiined, which are used in the mathematical model. Fifteen experimental runs were carried out for different water discharge (q), different bed slope (So) and different sediment over loading ratio. For each rnn, four transient bed profiles are plotted at onehour interval of flow. The computed results are compared with the experimental data. The agreement between the computed and experimental results is satisfactory.
Hydrologic determination of instream flow requirement of the Ganges river
(Department of Water Resources Engineering, 1998-08) Ataur Rahman, Md.; Bari, Dr. M Fazlul
For abstract please see full text
Machine Vision Based Local Hyacinth Bean Breed Recognition Using Convolutional Neural Network
(2024-04-22) Ali Khan, Md. Abbas; Ataur Rahman, Md.; Hossain, Md Liton; Habib, Md. Tarek
The classification is a significant one. This paper proposes a CNN-based Local Hyacinth Bean Breed Recognition (CNN-LHBR) approach along with a machine vision approach. Among the 52 breeds, we have taken only eight categories, namely Bashpaki Faridpur, Chaina Sada Patla Chela, Gochi, Kajoli, Katla, Lati, Noldub, and Pudi Aishna. There are many works done before about breed detection of different fruits as well as disease recognition. But no research has done such a work as LHBR, especially in Bangladesh. The interest of this research is the reason for the high protein and vitamin B complex; besides, each bean has a separate test, yield, seed, and nutrition level. More importantly, we have implemented 3 CNN models for the experiment of the breed recognition of 8 Hyacinth Bean specimens. For model accuracy, we have considered training, validation, and testing accuracy. As for performance evaluation, the confusion matrix has bean applied. Among the models, the customized CNN model gives the best accuracy. The customized CNN model's accuracy is 97.50%.