Mohd Wafi Nasrudin
Thumbnail Image
Preferred name
Mohd Wafi Nasrudin
Official Name
Mohd Wafi , Nasrudin
Alternative Name
Nasrudin, Mohd Wafi
Wafi, N. M.
Main Affiliation
Scopus Author ID
57193691419
Researcher ID
FMA-4535-2022

Research Output

Filters

11
4 2
11
Reset filters

Settings
Now showing 1 - 10 of 11
  • Publication
    Malaria Parasite Diagnosis Using Computational Techniques: A Comprehensive Review
    ( 2021-12-01)
    Wan Azani Wan Mustafa
    ;
    Hiam Alquran
    ;
    Muhammad Zaid Aihsan
    ;
    Mohd Saifizi Saidon
    ;
    Wan Khairunizam Wan Ahmad
    ;
    Aimi Salihah Abdul Nasir
    ;
    Mohamed Mydin Hj M.Abdul Kader
    ;
    Midhat Nabil Ahmad Salimi
    ;
    Mohd Wafi Nasrudin
    Malaria is a very serious disease that caused by the transmitted of parasites through the bites of infected Anopheles mosquito. Malaria death cases can be reduced and prevented through early diagnosis and prompt treatment. A fast and easy-to-use method, with high performance is required to differentiate malaria from non-malarial fevers. Manual examination of blood smears is currently the gold standard, but it is time-consuming, labour-intensive, requires skilled microscopists and the sensitivity of the method depends heavily on the skills of the microscopist. Currently, microscopy-based diagnosis remains the most widely used approach for malaria diagnosis. The development of automated malaria detection techniques is still a field of interest. Automated detection is faster and high accuracy compared to the traditional technique using microscopy. This paper presents an exhaustive review of these studies and suggests a direction for future developments of the malaria detection techniques. This paper analysis of three popular computational approaches which is k-mean clustering, neural network, and morphological approach was presented. Based on overall performance, many research proposed based on the morphological approach in order to detect malaria.
  • Publication
    Laguerre Krawtchouk moment invariants feature extraction technique for shape analysis
    ( 2019)
    Mohd Wafi Nasrudin
    The present study is concerned with the development of Feature Extraction (FE) based on the Moment Invariant techniques. The invariant properties errors were identified, when the shape is examined under the Rotation, Translation and Scaling (RTS) factors. Basically, the feature vector extracted from the original image and its counterpart variation should have similarities in their values. The feature vectors produced by the Moment Invariant techniques, that represent the images, are used as the input of classification. The performance of the percentage correct for image classification depends on the feature vectors from the image itself. Therefore, this study is motivated to develop a new algorithm based on the Moment Invariant by using the polynomials coefficients in order to reduce the invariant properties errors. The proposed technique is called as the Laguerre Moment Invariant (LGMI). The LGMI has been hybridized with the existing Moment Invariant techniques, the Zhi-Krawtchouk Moment Invariant (ZhiKMI) and Krawtchouk Moment Invariant (KMI). The new hybrid techniques are then, called as the Zhi-Laguerre Moment Invariant (ZhiLGMI) and the Laguerre-Krawtchouk Moment Invariant (LGKMI) techniques, respectively. There are five (5) existing Moment Invariant techniques that have been utilized in this work, namely the ZhiKMI, KMI, Racah-Krawtchouk Moment Invariant (RKMI), Legendre Moment Invariant (LMI) and Tchebichef Moment Invariant (TMI) techniques, which will be used to compare with the new proposed techniques. There are two main stages to examine the performance of the Moment Invariant techniques, namely the intraclass and interclass analysis. For the intraclass analysis, a set of equations has been implemented to identify the best technique between the Moment Invariants techniques based on the smallest value of Total Percentage Mean Absolute Error (TPMAE). Meanwhile, for the interclass analysis, three (3) types of Artificial Neural Network (ANN), namely Multilayer Perceptron (MLP), Simplified Fuzzy ARTMAP (SFAM) and Quality Threshold ARTMAP (QTAM), have been utilized to classify the shape images based on classes. From the intraclass results, it was found that the spatial quantization error is the main cause of the reduced Moment Invariants capability. However, the proposed LGKMI technique was found to be capable of producing the best feature vectors with the smallest value of TPMAE. The LGKMI technique is also able to classify different images with the highest percentage of correct classification with over 90% of accuracy for all the three (3) Neural Networks employed in the interclass analysis. Based on the results obtained from the intraclass and interclass analysis, it can be concluded that the proposed techniques, particularly the LGKMI technique, is found to be the best Moment Invariants technique in representing the shape feature.
  • Publication
    Classification of fish images based on shape characteristic
    ( 2015)
    Mohd Wafi Nasrudin
    This research work has been conducted to analyze and classify the types of fish image based on shape characteristic. The features of characteristic of fish image are extracted by using three Moment Invariants (MI) techniques and Fourier descriptors (FD). The types of Moment invariants are Geometric moment invariant (GMI), United moment invariant (UMI), Zernike moment invariant (ZMI). In the FD’s technique, there are two edge detection have been used to create the boundary of the image, namely Robert cross detection and Sobel cross detection. These feature extraction techniques have been used to analyze the image due to its invariant features of an image based on translation, scaling factor and rotation. There are two ways to examine the performance of feature extraction techniques, namely intra-class analysis and classification analysis. For the intra-class analysis, a set of equations has been implemented to find the best technique among the three different types of moments and Fourier descriptors based on the low value of Total Percentage Min Absolute Error (TPMAE). Meanwhile, for the classification analysis, the Artificial Neural Network (ANN) is explored and adapted to classify the fish images. The feature vectors produce by feature extraction techniques that represent the image are used as the input of classification. The results of the intraclass analysis indicate that the UMI was the best technique among the moment techniques while Fourier descriptor by using the Sobel edge detection shows the lower TPMAE as compared to Robert edge detection. For the classification part, two types of ANN’s which are Multilayer Perceptron (MLP) and Simplified Fuzzy ARTMAP (SFAM) neural networks have been used to classify the image based on fish category. The Leverberg-Marquardt (LM) algorithm is used to train the MLP network in order to check the applicability. Based on the classification that has been computed, the results show that all networks perform good classification performance with overall accuracy is around 90%. However, the MLP trained by Leverberg-Marquardt shows the highest classification performance in classifying the fish images as compared to the SFAM network.
  • Publication
    Using Unmanned Aerial Vehicle in 3D Modelling of UniCITI Campus to Estimate Building Size
    ( 2021-07-26)
    Mohd Saifizi Saidon
    ;
    Syahirah N.
    ;
    Wan Azani Wan Mustafa
    ;
    Hasliza A Rahim @ Samsuddin
    ;
    Mohd Wafi Nasrudin
    The drone mapping has a huge potential for numerous sectors including construction, agriculture, mining, infrastructure inspection and real estate. Drones are used as assisting tools in civil applications for large-scale aerial mapping of buildings, which is a difficult task for surveyors to do because of the unreachable access area, time consuming, and expensive due to limited resources and equipment. To address this issue, this paper introduces UAV-based mapping. Furthermore, when flying from a different flight plan, the UAV will capture and collect visual images. Then, the image from drone was process in Agisoft Metashape software to generate a 3D model of building. This process will go through several steps to analyze which method for capturing images can produce high-quality 3D mapping. The research results of this project are to determine which photogrammetry technique can generate a high quality of 3D mapping with accurate and fast.
  • Publication
    Moment Invariants Technique for Image Analysis and Its Applications: A Review
    ( 2021-07-26)
    Mohd Wafi Nasrudin
    ;
    Yaakob N.S.
    ;
    Nor Azura Abdul Rahim
    ;
    Mohd Zamri Zahir Ahmad
    ;
    Ramli N.
    ;
    Aziz Rashid M.S.
    The Moment invariant is a feature extraction technique used to extract the global features for shape recognition and identification analysis. There are many types of Moment Invariants technique since it was introduced. To date, many applications still use the Moment Invariant technique as feature extraction technique to extract the features of any images. The reason why the Moment Invariants still valid till today because its capabilities to analyze the image due to its invariant features of an image based on rotation, translation and scaling factors. Therefore, this review paper focuses to elaborate the history of Moment invariants and its applications in related fields. The summary about the advantages and disadvantages of Moment Invariants techniques will be described at the end of this review paper.
  • Publication
    An IoT-based automated gate system using camera for home security and parcel delivery
    ( 2024-02-08)
    Mohd Wafi Nasrudin
    ;
    Jamaluddin A.F.
    ;
    Ismail I.
    ;
    Norfatihah Bahari
    ;
    Vijayasarveswari Veeraperumal
    ;
    Wan Azani Wan Mustafa
    ;
    Abdul Syafiq Abdull Sukor
    ;
    Abdul Rahim A.N.
    The Internet of Things (IoT) has made it possible to set up smart home security and parcel delivery. Therefore, this work proposed an automated gate system using camera for home security and parcel delivery with integrated Internet of Things (IoT). An automated gate system will capture and identify the image of face visitors and delivery riders for admin authentication to open the gate and parcel box. This proposed work is controlled and monitored through mobile apps. The primary purpose and inspiration of this work are to help the delivery rider put the parcel into the parcel box provided if there is no person in the house, and the owner can pick up the parcel without being broken or robbed when she/he comes back home. When the delivery rider presses the button near the gate, the admin will receive the notification "Someone coming,". The admin will click the "okay"button and the system will take a picture using the camera in Blynk App. After the admin verifies that is the delivery rider, the admin will open the box and the delivery rider can access the parcel door box and put the goods inside the box. Another advantage of this work, it also allows familiar people to access our home. The same process with the delivery rider where the visitor needs to press the bell and the admin needs to verify before the visitor can access the single gate. The result indicates that this work is able to monitor and control the gate and parcel door box using an IoT application.
  • Publication
    Cervical cancer situation in Malaysia: A systematic literature review
    ( 2022-01-01)
    Wan Azani Wan Mustafa
    ;
    Halim A.
    ;
    Mohd Wafi Nasrudin
    ;
    Rahman K.S.A.
    Cervix cancer is one of Malaysia's most significant cancers for women (around 12.9%, with an age-standardised incidence rate of 19.7 per 100, 000). It was higher than other Asian, West, and even worldwide nations. The National Strategic Plan for Cancer Control Program 2016-2020 (Health Ministry) was presented to minimize cancer and mortality. The high incidence of cervical cancer in Malaysia is mainly due to women's insufficient knowledge about its prevention and importance. Compared with traditional literature reviews, the systemic analysis provides many advantages. A clearer review process, a more prominent field of study, and essential priorities that can manage research bias can all help to enhance these reviews. However, better integration, cooperation, and coordination between government and private sector as well as NGOs and professional organisations are essential for optimal cancer control and treatment across the country.
  • Publication
    Using Unmanned Aerial Vehicle in 3D Modelling of UniCITI Campus to Estimate Building Size
    ( 2021-07-26)
    Mohd Saifizi Saidon
    ;
    Syahirah N.
    ;
    Wan Azani Wan Mustafa
    ;
    Hasliza A Rahim @ Samsuddin
    ;
    Mohd Wafi Nasrudin
    The drone mapping has a huge potential for numerous sectors including construction, agriculture, mining, infrastructure inspection and real estate. Drones are used as assisting tools in civil applications for large-scale aerial mapping of buildings, which is a difficult task for surveyors to do because of the unreachable access area, time consuming, and expensive due to limited resources and equipment. To address this issue, this paper introduces UAV-based mapping. Furthermore, when flying from a different flight plan, the UAV will capture and collect visual images. Then, the image from drone was process in Agisoft Metashape software to generate a 3D model of building. This process will go through several steps to analyze which method for capturing images can produce high-quality 3D mapping. The research results of this project are to determine which photogrammetry technique can generate a high quality of 3D mapping with accurate and fast.
  • Publication
    Edge Enhancement and Detection Approach on Cervical Cytology Images
    ( 2022-09-01)
    Alias N.A.
    ;
    Wan Azani Wan Mustafa
    ;
    Mohd Aminudin Jamlos
    ;
    Mohd Wafi Nasrudin
    ;
    Mansor M.A.s.
    ;
    Alquran H.
    Cervical cancer is a prevalent and fatal disease that affects women all over the world. This affects roughly 0.5 million women annually and kills over 0.3 million people. Recently, a significant amount of literature has emerged around the advancement of technologies for identifying cervical cancer cells in women. Previously, diagnosing cervical cancer was done manually, which could lead to false positives or negatives. The best way of interpreting Pap smear images and automatically diagnose cervical cancer are still up for debate among the researchers. Method used in this study is the contrast enhancement technique for pre-processing and edge detection-based for segmentation of the nucleus. In this study, the average performance results of the method showed an accuracy of 96.99% in the seven-class problem using Herlev dataset. The present finding also support this study which concluded the results of accuracy achieved for the algorithm used for nucleus detection is improved by 6.15% when comparing to previous work. The accuracy value is in the lines of earlier literature that achieved accuracy of the approach used above 90% for seven class of cells. The major feature of the suggested approach is an improvement in the ability to anticipate which cells are aberrant and which are normal. Adding more classifiers could improve the suggested system even further. Therefore, a cervical cancer screening system might utilize this framework to identify women who have precancerous lesions.
  • Publication
    Smart Management Waiting System for Outpatient Clinic
    ( 2023-02-01)
    Mohd Wafi Nasrudin
    ;
    Zainuddin N.S.A.
    ;
    Raja Abdullah Raja Ahmad
    ;
    Rashidah Che Yob
    ;
    Mohd Zamri Zahir Ahmad
    ;
    Wan Azani Wan Mustafa
    ;
    Vijayasarveswari Veeraperumal
    ;
    Zulkifli N.D.M.
    Queuing has become a common occurrence in malls, train stations, and others. Queuing especially in healthcare intuitions has become a center of attraction because of the long waiting time either at the registration or in receiving treatments. Therefore, in solving this problem, a smart management waiting system for outpatient clinics is developed by using AppGyver and Backendless as the data storage. This system will be operating by QR code scanning for administrators to obtain patients’ personal information before patients obtain the queue number via MyQUEUE mobile application (patients’ interface). By providing queue numbers through the mobile application, patients don’t have to wait in a small uncomfortable waiting lounge instead patients can wait at their desired places such as cafeteria, in their car, and others. Patients also don’t have to worry about missing their turns because there will be a 10 minutes reminder before their turn. Other than that, there is a feature that digitalized the appointment details which means patients don’t have to worry about missing their appointment book or card. The performance of both systems which are the patients’ interface and administrators’ interface is successfully designed and the output obtained. The administrator is able to assign queue numbers, notify patients 10 minutes before consultation time, and assign follow-up appointments to patients.