scispace - formally typeset
Search or ask a question
Author

Nasrul Humaimi Mahmood

Other affiliations: Alliance University
Bio: Nasrul Humaimi Mahmood is an academic researcher from Universiti Teknologi Malaysia. The author has contributed to research in topics: Image processing & 3D reconstruction. The author has an hindex of 14, co-authored 105 publications receiving 724 citations. Previous affiliations of Nasrul Humaimi Mahmood include Alliance University.


Papers
More filters
Journal ArticleDOI
TL;DR: In this article, the authors investigated the possibility of enhancing hydroxyapatite (HA) bioactivity by co-substituting it with zinc and silver, and the proposed Zn-Ag-HA nanoparticles were found to be compatible with in vitro experiments and having potential antibacterial properties.

79 citations

Journal ArticleDOI
TL;DR: In this article, a rapid method for synthesizing nano-sized Ag-doped hydroxyapatite (Ag-HA) [Ca10 � xAgx(PO4)6(OH)2 ]( x¼ 0.03 − 0.5) using microwave irradiation for 10 min at 800 W is proposed.

70 citations

Proceedings ArticleDOI
03 Dec 2013
TL;DR: A method to count a total number of RBC in peripheral blood smear image by using circular Hough transform (CHT) method, which shows that from ten samples of peripheralBlood smear image, the accuracy using CHT method is 91.87%.
Abstract: In medical field, the number of red blood cells (RBC) are used as an indicator to detect the type of diseases such as malaria, anemia, leukemia and etc. The problems using manual counting of RBC under the microscope is tend to give inaccurate result and errors. This paper proposed a method to count a total number of RBC in peripheral blood smear image by using circular Hough transform (CHT) method. The process involves preprocessing and segmentation a single cell image of RBC after cropping it to get the minimum and maximum radius of cell. Then, CHT method is applied to detect and count the number of RBC based on the range radius of cells. The results show that from ten samples of peripheral blood smear image, the accuracy using CHT method is 91.87%.

62 citations

Journal ArticleDOI
TL;DR: The aim of this research is to produce a computer vision system that can detect and estimate the number of red blood cells in the blood sample image using Morphological, a very powerful tool in image processing, and it is been used to segment and extract thered blood cells from the background and other cells.
Abstract: The number of red blood cells contributes more to clinical diagnosis with respect to blood diseases The aim of this research is to produce a computer vision system that can detect and estimate the number of red blood cells in the blood sample image Morphological is a very powerful tool in image processing, and it is been used to segment and extract the red blood cells from the background and other cells The algorithm used features such as shape of red blood cells for counting process, and Hough transform is introduced in this process The result presented here is based on images with normal blood cells The tested data consists of 10 samples and produced the accurate estimation rate closest to 96% from manual counting

62 citations

Journal ArticleDOI
TL;DR: The results demonstrated that VGGNet-19 has better performance than histogram of oriented gradients, background subtraction, and optical flow and shows higher detection accuracy than other pre-trained networks: GoogleNet, ResNet50, AlexNet, and V GGNet-16.
Abstract: Today, machine learning and deep learning have paved the way for vital and critical applications such as abnormal detection. Despite the modernity of transfer learning, it has proved to be one of the crucial inventions in the field of deep learning because of its promising results. For the purpose of this study, transfer learning is utilized to extract human motion features from RGB video frames to improve detection accuracy. A convolutional neural network (CNN) based on Visual Geometry Group network 19 (VGGNet-19) pre-trained model is used to extract descriptive features. Next, the feature vector is passed into Binary Support Vector Machine classifier (BSVM) to construct a binary-SVM model. The performance of the proposed framework is evaluated by three parameters: accuracy, area under the curve, and equal error rate. Experiments performed on two different datasets comprising highly different context abnormalities accomplished an accuracy of 97.44% and an area under the curve (AUC) of 0.9795 for University of Minnesota (UMN) dataset and accomplished an accuracy of 86.69% and an AUC of 0.7987 for University of California, San Diego Pedistrain1 (UCSD-PED1) dataset. Moreover, the performance of the pre-trained network VGGNet-19 with handcrafted feature descriptors and with other CNN pre-trained networks, respectively, has been investigated in this study for abnormal behavior detection. The results demonstrated that VGGNet-19 has better performance than histogram of oriented gradients, background subtraction, and optical flow. In addition, the VGGNet-19 shows higher detection accuracy than other pre-trained networks: GoogleNet, ResNet50, AlexNet, and VGGNet-16.

45 citations


Cited by
More filters
Journal ArticleDOI
10 Jun 2014-Sensors
TL;DR: This paper explores how these various motion sensors behave in different situations in the activity recognition process, and shows that they are each capable of taking the lead roles individually, depending on the type of activity being recognized, the body position, the used data features and the classification method employed.
Abstract: For physical activity recognition, smartphone sensors, such as an accelerometer and a gyroscope, are being utilized in many research studies. So far, particularly, the accelerometer has been extensively studied. In a few recent studies, a combination of a gyroscope, a magnetometer (in a supporting role) and an accelerometer (in a lead role) has been used with the aim to improve the recognition performance. How and when are various motion sensors, which are available on a smartphone, best used for better recognition performance, either individually or in combination? This is yet to be explored. In order to investigate this question, in this paper, we explore how these various motion sensors behave in different situations in the activity recognition process. For this purpose, we designed a data collection experiment where ten participants performed seven different activities carrying smart phones at different positions. Based on the analysis of this data set, we show that these sensors, except the magnetometer, are each capable of taking the lead roles individually, depending on the type of activity being recognized, the body position, the used data features and the classification method employed (personalized or generalized). We also show that their combination only improves the overall recognition performance when their individual performances are not very high, so that there is room for performance improvement. We have made our data set and our data collection application publicly available, thereby making our experiments reproducible.

426 citations

Posted Content
TL;DR: In this article, a spatiotemporal architecture for anomaly detection in videos including crowded scenes is proposed, which includes two main components, one for spatial feature representation, and one for learning the temporal evolution of the spatial features.
Abstract: We present an efficient method for detecting anomalies in videos. Recent applications of convolutional neural networks have shown promises of convolutional layers for object detection and recognition, especially in images. However, convolutional neural networks are supervised and require labels as learning signals. We propose a spatiotemporal architecture for anomaly detection in videos including crowded scenes. Our architecture includes two main components, one for spatial feature representation, and one for learning the temporal evolution of the spatial features. Experimental results on Avenue, Subway and UCSD benchmarks confirm that the detection accuracy of our method is comparable to state-of-the-art methods at a considerable speed of up to 140 fps.

332 citations

Journal ArticleDOI
TL;DR: In this paper, the influence of the electrolyte, process parameters, pretreatment and post-treatment on the coating characteristics (surface micrograph, adhesion strength and biological compatibility etc.) is detailed.

243 citations

Journal ArticleDOI
TL;DR: Two deep learning architectures have been proposed that automatically detect positive COVID-19 cases using Chest CT X-ray images and it is proved that the proposed architecture shows outstanding success in infection detection.

228 citations

Journal ArticleDOI
TL;DR: Investigation of their antibacterial mechanism shows that these three metal ions all show antibacterial property through a mechanism of damaging bacterial cell membranes by the generation of reactive oxygen species but surprisingly preserving the integrity of bacterial genomic DNA.
Abstract: Antibacterial metal ions, such as Ag+, Zn2+ and Cu2+, have been extensively used in medical implants and devices due to their strong broad spectrum of antibacterial activity. However, it is still a controversial issue as to whether they can show the desired antibacterial activity while being toxic to mammalian cells. It is very important to balance their antibacterial effectiveness with minimal damage to mammalian cells. Toward this end, this study is to identify the suitable concentrations of these three ions at which they can effectively kill two types of clinically relevant bacteria (Staphylococcus aureus (S. aureus) and Escherichia coli (E. coli)) but show no obvious cytotoxicity on fibroblasts. Such concentration ranges are found to be 2.5 × 10–7 M–10–6 M, 10–5 M–10–4 M, and 10–5 M–10–4 M for Ag+, Zn2+, and Cu2+, respectively. Investigation of their antibacterial mechanism shows that these three metal ions all show antibacterial property through a mechanism of damaging bacterial cell membranes by the...

178 citations