Browsing by Author "Hassan, Arif"

Now showing 1 - 2 of 2

A Comparative Study on M15 and M20 Concrete Strength Variation Using Hand Mixing and Machine Mixing Method
(Daffodil International University, 22-12-22) Islam, Daudul; Hassan, Arif; Kamal, Sadia; Shekh, Md. Nuralam
Concrete is one of the oldest and most widely used building materials in the world, mostly because it is inexpensive, readily available, has a long lifespan, and can withstand harsh weather conditions. There are many ways to produce concrete in this modern day like Ready mixing, Machine mixing and Hand mixing concrete. The primary goals of this experiment are to determine the most cost-effective concrete and to compare the effects of hand mixing and machine mixing on the compressive and split tensile strengths of concrete.In the current experimental study, concrete mixes with proportions M15 and M20 were used. A total of 72 cylinders, 4 inches in diameter and 8 inches high, were cast and tested experimentally. These cylinders were used to measure the compressive strength and tensile strength of concrete after 7, 14 and 28 days. Samples were removed from the curing tank just prior to testing. A compression test was performed using a compression tester (UTM). We found the maximum compressive strength is 2442 psi for M20 and 2151 psi for M15 concrete by using Machine mix procedure. The value of Hand mix concrete is 1619 psi for M20 and 1431 psi for M15 grade concrete. Again, in the split tensile strength test we get better value for Machine mix rather than Hand mix concrete. So, it is clear that the Machine mixing concrete is more effective than Hand mixing concrete for any types of constructions. Keyword: Hand mixing, Machine mixing, Compressive strength, Split tensile strength, Economical cost.
A deep learning approach for multi-class bus fitness classification using a modified faster R-CNN model
(BRAC University, 2025-10) Khurshid, Fahim; Islam, Samiha; Rahman, Mohammed Raqin; Nusrat, Sadia; Hassan, Arif; Dofadar, Dibyo Fabian; Rahman, Rafeed
The high rates of development of the public transportation systems have caused the necessity of the creation of a stable, scalable, and automated system to check the vehicles in order to eliminate additional risk to the passengers and reduce the costs of their maintenance. This paper will present a deep learning driven architecture that uses a customized Faster Region Based Convolutional Neural Network (Faster R-CNN) to classify the bus fitness into multiple classes and hence removes the timeconsuming, inaccurate, and subjective task of manually examining structural defects, body states, and missing parts including side mirrors and headlights. In contrast to the traditional Faster R-CNN models which employ the use of the standard region proposal networks (RPN) and fully connected heads, our design features specialized Multi Layer Perceptron (MLP) heads to enhance feature segregation in subtle defect classes. Pre-processing and augmentation strategies also enhance the methodology by providing resistance to noise and change of viewpoint. This paper further extends the Faster R-CNN architecture of vehicle inspection by tackling the domain-specific limitations, such as small objects of defect and high intra class similarity, and class imbalance, by applying MLP-based classification heads and transfer learning with pre-trained weights, and complementing this with anchor refinement to enhance localization performance. Through experimental tests which include the mean average precision and the recall curves and the confusion matrices, significant gains are achieved compared to the baseline models especially with small or partially visible defects. These works include an expansion of object detection algorithms to safety critical applications, demonstration of the usefulness of feature space expansion using multilayer perceptrons, and the future prospects of implementing these algorithms in roadside camera devices and depot inspection systems, thus providing a base to smart transportation systems that can be applied to trucks, trains and aircraft.