Nur Ayuni Mohamed

Dr. Nur Ayuni Mohamed

National University of Malaysia

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2020 in IAES International Journal of Artificial Intelligence (IJ-AI)
Verified
Journal Article
Open access
PDF file
SZSiti Zulaikha Muhammad Zaki
Siti Zulaikha Muhammad Zaki
MZMohd Asyraf Zulkifley
Mohd Asyraf Zulkifley
MSMarzuraikah Mohd Stofa
Marzuraikah Mohd Stofa
NKNor Azwan Mohamed Kamari
Nor Azwan Mohamed Kamari
NMNur Ayuni Mohamed
Nur Ayuni Mohamed
Tomato is a red-colored edible fruit originated from the American continent. There are a lot of plant diseases associated with tomatoes such as leaf mold, late blight, and mosaic virus. Tomato is an important vegetable crop that contributes to the world economically. Despite tremendous efforts in plant management, viral diseases are notoriously difficult to control and eradicate completely. Thus, accurate and faster detection of plant diseases is needed to mitigate the problem at the early stage. A computer vision approach is proposed to identify the disease by capturing the leaf images and detect the possibility of the diseases. A deep learning classifier is utilized to make a robust decision that covers a wide variety of leaf appearances. Compact deep learning architecture, which is MobileNet V2 has been fine-tuned to detect three types of tomato diseases. The algorithm is tested on 4,671 images from PlantVillage dataset. The results show that MobileNet V2 is able to detect the disease up to more than 90% accuracy.

1 August 2019 in Biomedical Signal Processing and Control
Verified
Journal Article
Closed access
NMNur Ayuni Mohamed
Nur Ayuni Mohamed
MZMohd Asyraf Zulkifley
Mohd Asyraf Zulkifley
WZWan Mimi Diyana Wan Zaki
Wan Mimi Diyana Wan Zaki
AHAini Hussain
Aini Hussain

11 April 2019 in IEEE Access
Verified
Journal Article
Open access
MZMohd Asyraf Zulkifley
Mohd Asyraf Zulkifley
NMNur Ayuni Mohamed
Nur Ayuni Mohamed
NZNuraisyah Hani Zulkifley
Nuraisyah Hani Zulkifley
Squat exercise is frequently used in physiotherapy rehabilitation for stroke patients. In the early stage of rehabilitation, patients are urged to avoid performing any deep squat as the strains on tendon and ligament are much higher compared to the half-squat exercise. Therefore, it is important for patients to be aware of their squat depth. One of the ways to measure squat depth is by using a wearable device which adds unnecessary weight to the patients and makes them feel uncomfortable. Thus, we propose a single camera system that captures video from the frontal view to measure the squat angle continuously according to the number of frames per second. The system will provide knee angle measurements for every frame taken based on a combined approach of deep learning tracking and deep belief networks regressor. The proposed system requires just a bounding box input of the whole test subject taken at an upright position, which will later be the input to a convolutional neural networks-based tracker. Both the head and upper body parts of the exerciser will be tracked independently. The resultant tracked points will be normalized with the test subject height to find the ratio of height to the corresponding points. The ratio features are then will be the input to multiple deep belief networks’ regressors to predict the knee angle. The mean of ratio features will be used to segregate the input frame into its respective regressor. The experimental results show that the system produces the lowest mean error angle of 8.64° based on the setup of five regressors with each of them consists of five hidden layers. Hence, it is suitable to be implemented in a squat angle monitoring system to notify the patients of their squat angle depth.

27 September 2020
Verified
Conference Paper
Closed access
NMNur Ayuni Mohamed
Nur Ayuni Mohamed
MZMohd Asyraf Zulkifley
Mohd Asyraf Zulkifley
SASiti Raihanah Abdani
Siti Raihanah Abdani
Disease screening through the fundus image is one of the hottest research topics in biomedical engineering. There are various diseases that can be screened through human retinal information, which include glaucoma, myopia, macular degeneration, diabetic retinopathy, and cataracts. Hence, an automated system to screen all these diseases will be beneficial to health practitioners. Previously, each of the disease features needs to be designed by hand if the traditional machine learning approach is used. It is hard to process various diseases as a single system through this approach, especially if a new disease that needs to be added to the system does not fit well with the handcrafted features. Thus, a deep learning approach that utilizes learned features is the better alternative as the model can be updated easily if a new disease wants to be added to the system. This paper proposes a modified MobileNet architecture by replacing the top layers with a spatial pyramid pooling module. Three parallel flows of max-pooling operation through kernel sizes of $\times$$,\times$, and $\times$ are implemented to improve the algorithm robustness towards multi-scale input. Atrous convolution is also employed by adding the dilation rate to each of the pointwise convolution operators. The results show that a dilation rate of 4 produces the best mean accuracy of 0.7433 for the 5-fold cross-validation test. The algorithm retains its lightweight nature where the total number of parameters used is around 3 million. The model can be trained better if the number of data among the classes is more or less the same, which will reduce the training bias.

24 April 2021 in Diagnostics
Verified
Journal Article
Open access
PDF file
MZMohd Asyraf Zulkifley
Mohd Asyraf Zulkifley
NMNur Ayuni Mohamed
Nur Ayuni Mohamed
SASiti Raihanah Abdani
Siti Raihanah Abdani
NKNor Azwan Mohamed Kamari
Nor Azwan Mohamed Kamari
AMAsraf Mohamed Moubark
Asraf Mohamed Moubark
Ahmad Asrul IbrahimAhmad Asrul Ibrahim
Ahmad Asrul Ibrahim
Skeletal bone age assessment using X-ray images is a standard clinical procedure to detect any anomaly in bone growth among kids and babies. The assessed bone age indicates the actual level of growth, whereby a large discrepancy between the assessed and chronological age might point to a growth disorder. Hence, skeletal bone age assessment is used to screen the possibility of growth abnormalities, genetic problems, and endocrine disorders. Usually, the manual screening is assessed through X-ray images of the non-dominant hand using the Greulich–Pyle (GP) or Tanner–Whitehouse (TW) approach. The GP uses a standard hand atlas, which will be the reference point to predict the bone age of a patient, while the TW uses a scoring mechanism to assess the bone age using several regions of interest information. However, both approaches are heavily dependent on individual domain knowledge and expertise, which is prone to high bias in inter and intra-observer results. Hence, an automated bone age assessment system, which is referred to as Attention-Xception Network (AXNet) is proposed to automatically predict the bone age accurately. The proposed AXNet consists of two parts, which are image normalization and bone age regression modules. The image normalization module will transform each X-ray image into a standardized form so that the regressor network can be trained using better input images. This module will first extract the hand region from the background, which is then rotated to an upright position using the angle calculated from the four key-points of interest. Then, the masked and rotated hand image will be aligned such that it will be positioned in the middle of the image. Both of the masked and rotated images will be obtained through existing state-of-the-art deep learning methods. The last module will then predict the bone age through the Attention-Xception network that incorporates multiple layers of spatial-attention mechanism to emphasize the important features for more accurate bone age prediction. From the experimental results, the proposed AXNet achieves the lowest mean absolute error and mean squared error of 7.699 months and 108.869 months2, respectively. Therefore, the proposed AXNet has demonstrated its potential for practical clinical use with an error of less than one year to assist the experts or radiologists in evaluating the bone age objectively.

1 April 2015
Verified
Conference Paper
Closed access
NMNur Ayuni Mohamed
Nur Ayuni Mohamed
MZMohd Asyraf Zulkifley
Mohd Asyraf Zulkifley
AHAini Hussain
Aini Hussain
In building an automated glaucoma detection system, optic disc segmentation is the first step that needs to be implemented follows by optic cup segmentation in order to quantify the severity level of glaucoma. Glaucoma is an ocular eye disease that can lead to gradual vision loss and permanent blindness if it is not treated in the early stage. Many glaucoma patients are unaware of their disease since they rarely encounter any symptom that can lead to glaucoma. Thus, detecting glaucoma during the early stage is very important to reduce the treatment risk. This paper proposes optic disc segmentation by using local binary patterns operator (LBP), a feature for textural classification in image processing. LBP is utilized only on red channel of RGB fundus image because of higher contrast between optic disc and its surrounding area compared to the blue and green channels. Smoothing technique, specifically, histogram equalization is performed to improve the quality of input image before LBP method is applied. Lastly, morphological operation and filtering are applied to filter out the artifacts and remove the noise from the segmented image. RIM-One database is used to validate the simulation results with Exponential distribution achieve better performance with average accuracy and precision of 0.8951 and 0.7390 respectively.