Muhammad Naufal Mansor
Thumbnail Image
Preferred name
Muhammad Naufal Mansor
Official Name
Muhammad Naufal, Mansor
Alternative Name
Mansor, Muhammad Naufal
Mansor, N.
Naufal Mansor, Muhammad
Mansor, Muhammad Naufal Bin
Mansor, M. N.
Main Affiliation
Scopus Author ID
36469792500
Researcher ID
DHG-8694-2022

Research Output

Filters

19
4 1
19
Reset filters

Settings
Now showing 1 - 10 of 19
  • Publication
    Metal detector via KNN for vehicle robot
    ( 2020-12)
    Zaidi Lokman Awang
    ;
    Muhammad Naufal Mansor
    ;
    Nordiana Sharifuddin
    Through decades of use, several problems occur in the conventional metal detector where it becomes a burden when it is being carried for a long time, the price is so expensive and the user was exposed to the threat when using it at the dangerous site. In order to solve the problem, this research aims to develop a metal detector that is lighter, cheap and can be mobilized using a remote control. The frequency of different metal was classified via KNN Classifier where the obtained accuracy and sensitivity arehigher than 90%
      7  12
  • Publication
    Development of Surveillance Hovercraft via Arduino
    ( 2024-02-01)
    Muhammad Naufal Mansor
    ;
    Syahrul Affandi Saidi
    ;
    Wan Azani Wan Mustafa
    ;
    Roejhan Md Kawi
    ;
    Mohd Aminudin Jamlos
    ;
    Talib N.A.A.
    ;
    Mohd Zamri Hasan
    The current research focuses on the development of hovercraft via Arduino. The vehicle is designed with bag skirt structure in order to reduce friction for smooth operation. Nowadays, there are a lot of natural disaster occur in everywhere especially flood. However, hovercraft is a vehicle that need a driver to drive which can cause a danger to the rescuer. Based on this problem, a wireless hovercraft is needed to develop. This study explains a hovercraft which is able to control the movement of the hovercraft from the surface. The design of the hovercraft was successfully made by using AutoCAD software. Furthermore, the material of the body was made from the insulation foam while the microprocessor is Arduino UNO R3. There are two brushless DC motors and one servo motor that used for this hovercraft. The first brushless DC motor which is located below the hovercraft is used as a hover operation, while the second motor located behind it is used to ensure the hovercraft move forward. In addition, the performance of the hovercraft was successfully tested on the 3 different surfaces. As a result, the highest performance is on the cement while the lowest is on the grass.
      2  26
  • Publication
    Application System Development of Accident Prevention and Safety Assistance using IoT Application
    ( 2023-08-01)
    Muhammad Naufal Mansor
    ;
    Mohd Aminudin Jamlos
    ;
    Wan Azani Wan Mustafa
    ;
    Rahmat M.A.
    ;
    Syahrul Affandi Saidi
    ;
    Noor Anida Abu Talib
    ;
    Mohd Zamri Hasan
    The number of road accidents in Malaysia shows a steady increment from 2010 to 2019, reported by the Ministry of Transport Malaysia. This project aims to develop a system to prevent an accident by detecting aggressive driving. If an accident occurred, this system would send an alert for an immediate response, which is crucial to reduce the fatality rate. An accelerometer is utilized to detect aggressive driving and accident events. The method to detect aggressive driving is by determining an abrupt change in acceleration. For accident detection, the vehicle tilt angle and acceleration are monitored. An ESP32 SIM800L microcontroller processes the inputs and alert a web-based cloud service and a set phone number by Short Message Service (SMS). The microcontroller is used due to the embedded Global System for Mobile Communications (GSM) and other wireless communication modules. The small form factor gives an advantage in terms of mounting location flexibility. The alert contains the type of event, time, and location. This report contains the development of the proposed system, which includes the simulation for the system circuit and motion simulation. Accident detection, falls, SMS alerts and online alerts are consistently successful, while aggressive driving detection is inconsistent. Live tracking does not directly work during these detections. In conclusion, this project successfully detects accidents and sends alerts via SMS and internet using a Subscriber Identity Module (SIM) card.
      1  20
  • Publication
    Contrast virus microscopy images recognition via k-NN classifiers
    ( 2017-07-02)
    Afiq Ahmad Shakri
    ;
    Syahrul Affandi Saidi
    ;
    Muhammad Naufal Mansor
    ;
    Haryati Jaafar
    ;
    Ahmad Kadri Junoh
    ;
    Wan Azani Wan Mustafa
    One of the topics that are commonly in focus of object detection and image recognition is virus detection. It is well known that to learn and detecting virus proven to be a challenging and quite complex task for computer systems under different noise level. This research work investigates the performances of preprocessing stages with Contrast feature extraction with K-Nearest Neighbor (KNN) classifier under various levels of noise. The real time experiment conducted proved that the proposed method are efficient, robust, and excellent of which it has produced a results accuracy of up to 88% for biological viruses images classification.
      31  1
  • Publication
    Classification of the agitation level based on facial variation for ICU patients in hospitals
    (Universiti Malaysia Perlis (UniMAP), 2011)
    Muhammad Naufal Mansor
    A coma is a profound or deep state of unconsciousness. An individual in a state of coma is alive but unable to move or respond to his or her environment. Even though those patients in a persistent vegetative state lose their higher brain functions, when other key functions such as breathing and circulation remain relatively intact. However, spontaneous facial movements and expressions may occur in response to external stimuli. Clinicians regard the patient’s facial expression as a valid indicator for motion intensity. Hence, correct interpretation of the facial agitation of the patient and its correlation with motion is a fundamental step in designing an automated motion assessment system. Computer vision techniques can be used to quantify agitation in sedated Intensive Care Unit (ICU) patients. In particular, such techniques can be used to develop objective agitation measurements from patient motion. In the case of paraplegic and coma patients, whole body movement is not available, and hence, monitoring the whole body motion is not a viable solution. Hence in this case, measuring head motion and facial grimacing quantify facial patient agitation based on K-Nearest Neighborhood (k-NN), Fuzzy k-NN (f-kNN), Linear Discriminate Analysis (LDA) and Neural Network (NN). Using the proposed classifiers, some experimental results for different angle, distances and illumination levels have been obtained. It is found that the classification accuracy is higher than 90.00% for the proposed features and classification techniques. Finally, Graphical User Interface (GUI) Layout Editor is developed to minimize the tedious work of medical staff.
      9  1
  • Publication
    Breast Cancer Detection on X-Tray Mammogram Images
    ( 2023-01-01)
    Azmi M.A.A.
    ;
    Wan Azani Wan Mustafa
    ;
    Alquran H.
    ;
    Aziz A.A.
    ;
    Muhammad Naufal Mansor
    ;
    Alzubaidi L.H.
    ;
    Hussein A.H.A.
    Breast cancer (BC) is a common cancer affecting women everywhere in world. Mammography is identified and efficient technique to detect primary BC. The aim of project is for detect BC on mammogram in order to categorize disease by image processing when comparing with a previous technique. Through utilizing conventional methods, it creates it complex for radiology to detect cancer from patient's breast. In addition, there are environmental disturbances and technical problems if using the old method. Image processing techniques was separated to numerous elements. The elements are input, pre-processing, segmentation, morphological, object classification and classification. First pre-processing was done through Weiner and Median filter. Then, thresholding method on segmentation and finally, morphological will eliminate limitations at a segmentation. The image classified into 2 classes like normal and tumor. Both type of images analyzed based on elements. Additionally, it comprises a building of Graphical User Interface (GUI) which is utilized to generate the system as user-friendly. The developed model attain accuracy of 93.71 %, specificity of 82.53 % sensitivity of 94.36% for tumorous images.
      6  17
  • Publication
    Aquaponic Ecosystem Monitoring with IOT Application
    ( 2023-08-01)
    Muhammad Naufal Mansor
    ;
    Mohd Zamri Hasan
    ;
    Mohamed Mydin Hj M.Abdul Kader
    ;
    Wan Azani Wan Mustafa
    ;
    Syahrul Affandi Saidi
    ;
    Mohd Aminudin Jamlos
    ;
    Noor Anida Abu Talib
    Aquaculture is an agricultural technology that combines aquaculture (fish farming activities) with hydroponic activities (planting crops without soil media) in one circulation. The most important element in aquaculture is the existence of fish, plants, and bacteria. These three elements form a mutually beneficial relationship or symbiotic mutualism. The main purpose of the aquaculture system is to maintain water quality and reduce ammonia levels from the water so that it can be utilized by other organisms. In addition, aquaculture can also save space and can produce two types of human food simultaneously, plants and livestock. Agricultural technology design with Aquaculture also uses the concept of Internet of Things (IoT) as information from sensors and sensors of value generator is accessible through applications installed on smartphones from anywhere with an Internet connection. Development of monitoring of aquaponic ecosystems with IoT systems was developed using a program using micro-controls to control temperature, humidity, pH levels and water pumps. There are some improvements made to this project.
      2  31
  • Publication
    A modified retinex illumination normalization approach for infant pain recognition system
    ( 2014)
    Muhammad Naufal Mansor
    Pains in newborn babies are monitored in a Neonatal Intensive Care Unit (NICU) for medical treatment. Pain in newborns can be detected by studying their facial appearance. Even though the outcome is acceptable, it is not adequately vigorous to be used in unpredictable, non-ideal situations such as noise and varying illumination environment. First, to improve the noise cancellation robustness an adaptive median filter (AMF) is proposed. Mean and variance of median values are selected to generate a weight for each window part of the images such as 3x3, 5x5 or 7x7. Various linear and nonlinear filters are adopted to eliminate the noise in the images. Quantitative comparisons are performed between these filters with our AMF in terms of Peak Signal-to-Noise Ratio (PSNR), Mean Square Error (MSE), Image Enhancement Factor (IEF) and Mean Structural SIMilarity (MSSIM) Index. The average results show improvement in terms of 40.63 db for PSNR, 6.01 for MSE, 258.09 for IEF and 0.97 for MSSIM respectively. In this work a novel method of illumination invariant normalization known as Modified Retinex Normalization (MRT) for preprocessing of infant face recognition is proposed. This is based on a modified retinex model that combines with histogram normalization for filtering the illumination invariant. The proposed method is compared to other methods like Single scale Retinex (SSR), Homomorphic method (HOMO), Single Scale Self Quotient Image (SSQ), Gross and Brajovic Technique (GBT), DCT-Based Normalization (DCT), Gradientfaces-based normalization technique (GRF), Tan and Triggs normalization technique (TT), and Large-and small-scale features normalization technique (LSSF) for evaluation with Infant Classification of Pain Expressions (COPE) database. Several experiments were performed on COPE databases. Single PCA, LBP and DCT feature extraction information yielded a good recognition result. However, by summing these three, it gives more robustness to noise and illumination classification rate because the sum rule was the most resilient to estimate errors and gives higher than 90% accuracies of pain and no pain detection. The new illumination normalization and combination of features gives higher results of more than 90% on five different classifiers with various algorithms such as k-nearest neighbors (k-NN), Fuzzy k-nearest neighbors (FkNN), Linear Discriminat Analysis (LDA), Feed Forward Neural Network (FFNN), Probabilistic Neural Network (PNN), General regression Neural Network (GRNN), SVM Linear kernel (SVMLIN), SVM RBF kernel (SVMRBF), SVM MLP kernel (SVMMLP) and SVM Polynomial kernel (SVMPOL) with different performance measurement such as Sensitivity, Specificity, Accuracy, Area under Curve (AUC), Cohen's kappa (k), Precession , F-Measure and Time Consumption .
      2  26
  • Publication
    Fusion wind and solar generation forecasting via neural network
    ( 2021-08-27)
    Mahmoud Mustafa Yaseen Mohammed Al Asbahi
    ;
    Muhammad Naufal Mansor
    ;
    Mohd Rizal Manan
    ;
    Mohd Azri Abd Aziz
    ;
    Roejhan Md Kawi
    ;
    Farah Hanan Mohd Faudzi
    Wind and solar power are the most common renewable resources of energy and their usage for power generation is quickly growing all over the world. However, both wind and solar power are difficult to predict manually due to every time changes in weather condition; therefore. power output of wind and solar is associated with some uncertainty. A reliable wind-solar day ahead load prediction proposed in this paperwork to support a small microgrids system. The system is a combination of hardware of solar panel, wind turbine, hybrid charge controller, current sensor, voltage sensor circuit, battery, Arduino Mega and personal computer that is install with MATLAB along with artificial neural network model for load forecast. The prediction model is known as Feedforward back propagation (FFBP) artificial neural network (ANN), this method utilizes a learning relationship between wind-solar power output and predicted weather. The FFBP model trained ANN to recognize similar pattern and to predict the output power based on train and tested data and the results achieved 99.5 accuracy, 6.25% MAPE and 1.2 % MAD.
      1  23
  • Publication
    Extended median filter for salt and pepper noise
    ( 2017-01-01)
    Bilal Charmouti
    ;
    Ahmad Kadri Junoh
    ;
    Wan Zuki Azman Wan Muhamad
    ;
    Muhammad Naufal Mansor
    ;
    Mohd Zamri Hasan
    ;
    Mohd Yusoff Mashor
    Image have a significant importance in many fields in human life such as, in medicine, photography, biology, astronomy, industry and defence. Thus, it attracts the attention of large number of researchers, among them those interested in preserving the image features from any factors that may reduce the image quality. One of these factors is the noise which affects the visual aspect of the image and makes others image processing more difficult. Thus far, solving this noise problem remains a challenge point for the researchers in this field, a huge number of image denoising techniques have been introduced in order to remove the noise with taking care of the image featurs, in other words, get the best similarity to the original image from the noisy one. However, beside the enormous amount of researches and studies which adopt several mathematical concepts (statistics, probabilities, modeling, PDEs, wavelet, fuzzy logic, etc.), the findings proved to be inconclusive yet. From this point, the current study aims to introduce a new denoising method for removing salt & pepper noise from the digital image through developed Median filter, so as to overcome this problem of noise and achieve a good image restoration.
      2  27