Browsing by Author "Assaduzzaman, Md"

Now showing 1 - 6 of 6

A Comparative Study for Measuring the Quality of Dhaka City Transportation System
(IEEE, 2023-09-01) Rejuan, Md Arifur Rahman; Bandan, Sheikh Sadi; Rakib, Md. Abdur; Assaduzzaman, Md
Dhaka is the capital of Bangladesh and one of the most populous countries in the world. The population of Dhaka has grown at a huge rate in the last few decades and is expected to grow similarly in the coming decades. As a result, population density is increasing, meaning that a large population has to be accommodated in a small area. This is disrupting other activities of Dhaka city. Among the disrupted activities, the condition of the Dhaka Transportation System is absolutely pathetic. Because of this, traffic jams are constantly being created in Dhaka city and people spend their necessary time sitting in traffic jams for hours. Our research paper discusses the Dhaka Transport System. We have worked with 104 data sets and a research paper based on feedback from all of them. By discussing with them, several problems were found, such as: overpopulation, more vehicles, non-observance of the traffic system, not driving carefully, poor mechanical condition of vehicles etc. All these problems have been discussed in the research paper and solutions have been given to make the transportation system in Dhaka city work well in a systematic way.
A Real-Time Deep Learning Approach for Classifying Cervical Spine Fractures
(Elsevier, 2023-09-24) Paul, Showmick Guha; Saha, Arpa; Assaduzzaman, Md
The first seven vertebrae of our spine are called the cervical spine. It supports the weight of our head, encloses and safeguards our spinal cord, and permits a variety of head motions. The seven cervical vertebrae are joined at the rear of the bone by a kind of joint known as a facet joint. These joints enable us to move our necks forward, backward, and twist. Fractures of the cervical spine are a medical emergency that may lead to lifelong paralysis or even death. If left untreated and undetected, these fractures can worsen over time. Using computed tomog- raphy, a cervical spine fracture in individuals can be accurately diagnosed. Given the scarcity of research on the practical use of deep learning methods in detecting spine fractures in persons, it is imperative to address this gap. This study uses a dataset containing fracture and normal cervical spine computed tomography images. This study proposed modified transfer-learning-based MobileNetV2, InceptionV3, and Resnet50V2 models. An ablation study was also conducted to determine the optimal custom layers for models and data augmentation techniques. In addition, evaluation metrics have been used to analyze and compare the model’s performance. Among all the approaches, MobileNetV2 with augmentation has achieved the highest accuracy of 99.75%. Furthermore, the best-performing model has been deployed in a smartphone-based Android application
DESIGN AND DEVELOPMENT OF AN ANDROID APPLICATIONS FOR LOST-FOUND
(Daffodil International University, 2018-12-01) Assaduzzaman, Md; Mamun, Abdullah Al; Muttakin, Md
The time of portable innovation opens the windows to the android application. The sites are vanishing and the cell phone is rising it. It has turned into a piece of our everyday life. It gives us more agreeable and a superior UI. These days, everybody loses or loses things or items all over. In any case, there are a few people who will, in general, be in a steady condition of looking for lost things. We frequently observe a few people who loses his keys, ID card, wallet, or telephone and so forth at any rate once every day. They need to get back those. Some of the time it would be exceptionally troublesome for anybody to get those items or things. That’s why we have developed an Android application for finding missing products or things. This application contains functionality to add the complaint about both lost user and found a user. Users can add their product details like product name, model, IMEI number and others specific things. It will store in the database. Similarly, if any user finds that product he or she can also add product details by using this app. Then they can both check their data if someone already has found or lost. Actually, it will be matched from the system and let the user know whether it is matched or not. If matched, the user can contact through email or phone.
Effect of particle size and relative density on dynamic resistance and subgrade modulus of clean sand
(2014-08-16) Assaduzzaman, Md; Alam, Dr. Md. Jahangir
The present study was aimed at developing an alternative indirect method which can be used to determine Relative Density, Initial Tangent Modulus and Modulus of Subgrade Reaction for clean sand of any particle size. To know the height of fall and hole diameter of sand discharging bowl for a desired Relative Density of a specific sand, the air pluviation method was calibrated in the first stage. Then in the second stage sand deposits of different relative densities were prepared in calibration chamber and Dynamic Probing Light (DPL), Dynamic Cone Penetrometer (DCP) tests and Plate Load Test (PLT) were performed on the prepared sand deposit. Correlation between Pindex (rate of penetration in mm/blow) and Relative Density was made from the test results in calibration chamber. Based on the test results, resistance of sand increase exponentially with increasing Relative Density for different mean diameter (D50) of particles but the larger mean diameter of particles of sand shows the higher resistance at same Relative Density than the smaller mean diameter of particles. Correlation among Initial Tangent Modulus (EPLT(i)), Subgrade Modulus (Ks), Relative Density and Pindex was made from the test result in calibration chamber. It was found that Initial Tangent Modulus (EPLT(i)) and Subgrade Modulus (Ks) increases with increasing Relative Density. On the other hand, mean diameter (D50) of particles has large effect on the Initial Tangent Modulus (EPLT(i)) and Subgrade Modulus (Ks). Larger mean diameter (D50) of particle shows the higher value of Initial Tangent Modulus (EPLT(i)) and Subgrade Modulus (Ks) at same Relative Density. Therefore, Initial Tangent Modulus (EPLT(i)) and Subgrade Modulus (Ks) decrease exponentially with increasing Pindex for different mean diameter of particle. In the third stage, the correlation was verified for three dredge fill sites where DCP and DPL results were compared with the result from Sand Cone Method. At the last stage, CBR test was performed at laboratory at field density to make the correlation among CBR value, Relative Density (%) and field Pindex for DPL and DCP. CBR value decreases exponentially with increasing Pindex value for both DPL and DCP. A generalized correlation between Pindex and Relative Density for clean sand of any particle size was found from this study. To determine in situ Relative Density of sand deposit, it is concluded that the proposed method (DCP and DPL) can be used as an alternative indirect method which is suitable up to 2 m depth.
Handwritten Changma Numerals Recognition Using Capsule Networks
(2019 5th International Conference on Advances in Electrical Engineering, IEEE, 2019-09-28) Hasan, Md Zahid; Hasan, K. M. Zubair; Hossain, Shakhawat; Al Mamun, Abdullah; Assaduzzaman, Md
Handwritten digit recognition is assumed to be a huge part in numerous authentication applications in the state-of-art technologies. As the manually written digits are not always found in similar size, thickness, style and orientation, recognition of handwritten digits is hardly possible in many cases. To address this recognition tasks using handwritten digits, a great deal of work has been conducted with different image processing technologies on a variety of non-Indic's languages. However, this paper represents a handwritten digit recognition system of recognizing Changma Vaj Digit Recognition (CVDR). The digit recognition approach used in this paper is capsule network, an improved version of Convolutional Neural Network (CNN). The proposed system has been trained with more than 3440 sample image and been tested with more than 860 images. The proposed paper also presents a graphical comparison between the recognition accuracy performed by CNN and CapsNet, which in other terms demonstrates the supremacy of CapsNet's accuracy by 5.7%.
Tuberculosis Disease Detection from Chest X-rays Using Deep Learning Techniques
(Daffodil International University, 2023-12) Rabby, Mehedi Hasan; Islam, Oahidul; Assaduzzaman, Md; Dutta, Monoronjon
Millions of cases of tuberculosis (TB) are recorded each year, making it a significant worldwide health concern. Early and accurate TB detection is essential for the disease to be effectively treated and controlled. Deep learning methods have recently become effective tools for analyzing medical images, and they have a lot of potential for use in the field of TB detection. This study describes a revolutionary deep-learning method for detecting TB illness. We used a dataset of 3500 chest X-ray images from individuals with tuberculosis. There are two classes in the dataset: Tuberculosis and Normal. We used the highly regarded deep learning models VGG16, VGG19, MobileNetV2, and InceptionV3 to categorize such elements. Out of all of them, MobileNetV2 has obtained the highest accuracy, which is accurate in training of 99.99% and a test's reliability of 98.93%. Furthermore, in VGG16, VGG19, and Inception-V3, we achieved test accuracy of 98.90%, 99.14%, and 97.87%, respectively.