Lim Chee Chin
Thumbnail Image
Preferred name
Lim Chee Chin
Official Name
Lim, Chee Chin
Alternative Name
Lim, Chee Chin
Main Affiliation
Scopus Author ID
57201525827
Researcher ID
GNO-9181-2022

Research Output

Filters

14
Reset filters

Settings
Now showing 1 - 10 of 14
  • Publication
    Home-based ankle rehabilitation system: Literature review and evaluation
    ( 2017-09-01)
    Lim Chee Chin
    ;
    Shafriza Nisha Basah
    ;
    Marwan Affandi
    ;
    Muhammad Nazrin Shah Shahrol Aman
    ;
    Sazali Yaacob
    ;
    Yeap Ewe Juan
    ;
    Mohamad Yazid Din
    Ankle sprain Injury is one of the most common ankle injuries due to domestic or sporting accidents. There is a need for greater demand for quick and effective ankle rehabilitation system (ARS). Nowadays, research on ARS has gained a great attention than manual clinical method in medical areas such as orthopedic injuries, pediatrics sport medicine and industrial services. It can improve the treatment conditions by reducing the dependency of doctors’ supervision, help patient with less movable to have home-based rehab exercise and help to speeds up recovery. There are currently available ARS that can provide effective ankle rehabilitation treatment such as Visual, Non-Visual and Robot-aided. In this paper, the critical review of ARS is conducted to evaluate the effectiveness of ARS in terms of provided setting criteria. The strengths, weaknesses, opportunities and threats of each ARS is discussed and compared to identify the most suitable home application of ARS for ankle sprain patient. From the comparison, the most suitable home application ARS is the visual marker-less based ARS system which give user-friendly, efficiency, validity in performance and cheaper cost.
  • Publication
    Recognition of plant diseases by leaf image classification using deep learning approach
    ( 2023-02-21)
    Goy S.Y.
    ;
    Chong Y.F.
    ;
    Teoh T.K.K.
    ;
    Lim Chee Chin
    ;
    Vikneswaran Vijean
    Plant health is important in maintaining the sustainability of the foods crop. The key to prevent the loss of yield of plant crops is the identification of plant diseases. The process of monitor plant health manually is challenging as it required expert knowledge which is expensive and time-consuming. Hence, the image processing techniques can be useful for the detection and classification of plant leaf disease. In this project, the leaf images of 5 plant types in the PlantVillage dataset are used for plant type and plant disease classification. The original images are resized to the required input sized and the proposed background removal methods (improved HSV and GrabCut segmentation) are performed to reduce the background noise. The segmented images are then given to proposed models (AlexNet and DenseNet121) for training and classification. For plant type classification, DenseNet121 got a better validation accuracy of 99% compared to AlexNet with 91.2%. After that, the leaf image is given to plant disease models according to their species. All the plant disease models training with DenseNet121 can achieve high validation accuracy of 99%, 99%, 100%, 100% and 97% for apple, grape, potato, strawberry and tomato. Lastly, a user-friendly graphical user interface (GUI) is developed.
  • Publication
    Clinical validation of 3D mesh reconstruction system for spine curvature angle measurement
    ( 2023-02-21)
    Shanyu C.
    ;
    Lim Chee Chin
    ;
    Fook C.Y.
    ;
    Azizan A.F.
    ;
    Vikneswaran Vijean
    ;
    Ahmad Faizal Salleh
    ;
    Shafriza Nisha Basah
    Spine curvature disorders are scoliosis, lordosis, and kyphosis. These disorders are mainly caused by the bad habits of the person during sitting, standing, and lying. There are about 3 to 5 out of 1,000 people who are affected by spine curvature disorder. The current conventional method used for diagnose this disorder, such as radiography, goniometry and palpation. However, these conventional methods require human skills and can be time-consuming, resulting to exhaustion of logistic. Therefore, there is a need to solve this problem by creating a Graphical User Interface (GUI) to analyse the human body posture through the 3D reconstructed model of the person. Hence, 3D map meshing reconstruction of the human body method is proposed. This project divided into three parts, which are the development of the GUI for human posture analysis, clinical validation and posture analysis of the 3D model. The 3D model reconstructed from 3D mapping parameters shows 100% accuracy of the assessed point. The lowest difference of angle for the comparison between clinical method (goniometer) and the GUI for male is (A.Pe) 0.930±0.870 and 1.240±0.860 for female (P.Pe). This finding of 3D model assessment system can be helpful for medical doctor to diagnose patient who have spine problem.
  • Publication
    A review on contact lens inspection
    ( 2023-08-01)
    Mana N.A.M.A.
    ;
    Lim Chee Chin
    ;
    Fook C.Y.
    ;
    Haniza Yazid
    ;
    Ali Y.M.
    Over the year, contact lens detection has attracted attention and interest from many researchers to study further in this field of inspection. This paper provides a comprehensive review of the existing literature surrounding contact lens inspection methods. In this paper, contact lens-related, defects-related, and inspection methods related are described in detail. To detect contact lenses in a single image and also multi-image, numerous techniques have been developed and this paper is aimed at classifying and evaluating these algorithms. Also, contact lens inspection based on conventional and artificial intelligence methods will be discussed in detail. The industrial production process of contact lenses probably needs to be constructed with advanced tools based on recent technologies so that they can help in the inspection system to achieve accurate results of the inspection and reduce processing time.
  • Publication
    Performance analysis of multi-level thresholding for microaneurysm detection
    ( 2022-09-01)
    Choong K.H.
    ;
    Shafriza Nisha Basah
    ;
    Haniza Yazid
    ;
    Muhammad Juhairi Aziz Safar
    ;
    Fathinul Syahir Ahmad Sa'ad
    ;
    Lim Chee Chin
    Diabetic retinopathy (DR) – one of the diabetes complications – is the leading cause of blindness among the age group of 20–74 years old. Fortunately, 90% of these cases (blindness due to DR) could be prevented by early detection and treatment via manual and regular screening by qualified physicians. The screening of DR is tedious, which can be subjective, time-consuming, and sometimes prone to misclassification. In terms of accuracy and time, many automated screening systems based on image processing have been developed to improve diagnostic performance. However, the accuracy and consistency of the developed systems are largely unaddressed, where a manual screening process is still the most preferred option. The main contribution of this paper is to analyse the accuracy and consistency of microaneurysm (MA) detection via image processing by focusing on Otsu’s multi-thresholding as it has been shown to work very well in many applications. The analysis was based on Monte Carlo statistical analysis using synthetic retinal images of retinal images under variation of all stages of DR, retinal, and image parameters – intensity difference between MAs and blood vessels (BVs), MA size, and measurement noise. Then, the conditions – in terms of obtainable retinal and image parameters – that guarantee accurate and consistent MA detection via image processing were extracted. Finally, the validity of the conditions to guarantee accurate and consistent MA detection was verified using real retinal images. The results showed that MA detection via image processing is guaranteed to be accurate and consistent when the intensity difference between MAs and BVs is at least 50% and the sizes of MAs are from 5 to 20 pixels depending on measurement noise values. These conditions are very important as a guideline of MA detection for DR.
  • Publication
    Investigation on Medicated Drugs in ECG of Healthy Subjects
    ( 2022-01-01)
    Vikneswaran Vijean
    ;
    Abdul Ghapar Ahmad
    ;
    Syakirah Afiza Mohammed
    ;
    Razi Ahmad
    ;
    Wan Amiza Amneera Wan Ahmad
    ;
    Ragunathan Al Santiagoo
    ;
    Lim Chee Chin
    Heart diseases are now the leading cause of death worldwide, it is estimated that around 7 million patients who are living in developed countries, lost their lives due to diseases related to their cardiovascular system. In Malaysia, cardiovascular diseases represents one fifth of total deaths in the country in the past three decades. Currently patients need some sort of drugs that help them to stabilize and restore the regular patterns of their heart beat because if the patients cannot manage to restore the normal heart beat pattern, the undesired heart condition could lead life threatening situations. Advancement of biotechnology has enabled the creation of new medicated drugs to provide better treatment options. However, when this treatment option fails and there is a need to provide emergency intervention to the patients in hospitals, the medical experts often need to know about the patients' intake of any medications prior to hospital admittance for providing suitable treatments. Sometimes, this would be a difficult task as the patient might be admitted in semi-conscious or unconscious state. Therefore, this study focusses on identification of different medicated drugs usage through analysis of ECG data of the users. The data for the experiment was obtained from physionet library, which provides ECG data of subjects administered with a combination of Dofetilide, Mexiletine, lidocaine, Moxifloxacin and Diltiazem medicated drugs. The use of morphological and non-linear features derived from the ECG signals were able to provide prediction accuracy of 77.26% using SVM classifier.
  • Publication
    A visual tracking range of motion assessment system for lower limb joint
    ( 2016)
    Lim Chee Chin
    Accurate range of motion (ROM) measurement of lower limb joint motion is important for assessing the severity of human lower limb injuries. It is essential for assisting the medical doctor and physiotherapist to determine the suitable treatment and rehabilitation exercises that are required for lower limb injury patient specifically. Current medical measurement systems such as Universal Goniometer (UGM) has a large resolution of 1° which may cause to have observation error while Electrogoniometer (EGM) is affected by the inaccurate sensor’s position and detachment when moving due to its mechanical properties limitation. Thus, a visual tracking ROM assessment system (VTS) for lower limb joint measurement is proposed. The purpose of this investigation was to develop a method to quantify a ROM of the lower limb joint and examine the ROM obtained between the VTS with EGM and UGM, for the measurement of lower limb joint angles. There were three major experiments conducted i.e., Validation Experiment, Clinical Test and Clinical Case Study. Validation experiment was done on the developed visual tracking system before being applied on the real human subject to ensure the system performance and safety to be acceptable. The system had been tested under the several of light intensity level, camera distance, camera elevation angle and markers location to determine the optimum operating condition. In clinical test, there were two tests carried out; they were Healthy Control Test and Injured Subject Test. A total of 20 healthy control subjects’ findings proved that the left and right lower limbs of human were similar (99.80% ~ 97.64% of similarity) for the normal healthy subjects. Comparison between VTS, EGM and UGM found that the accuracy for each two systems compared to each other was significantly different for the VTS vs. EGM and the EGM vs. UGM. The VTS vs. UGM produced the highest accuracy for all the joint motions compared to VTS vs. EGM and the EGM vs. UGM; it was 99.46% for left knee flexion. In addition, total of 70 injured subjects (included ankle joint, knee joint, and hip joint) had undergone injured subject test to compare its severity level between illness and three measurement systems. In the injured subject test, VTS yielded the smallest coefficient of variation (CV) compared to the EGM and UGM for Knee flexion for moderate injuries which was 2.45%.
  • Publication
    Smart fall detection monitoring system using wearable sensor and Raspberry Pi
    ( 2024-02-08)
    Lim Chee Chin
    ;
    Mahmud N.F.A.
    ;
    Vikneswaran Vijean
    ;
    Ali Yeon Md Shakaff
    ;
    Tan X.J.
    ;
    Ahmad Faizal Salleh
    ;
    Shafriza Nisha Basah
    The Smart Fall Detection Monitoring System is the name of the programme that monitors everyday activities and falls. It has an accelerometer sensor (ADXL345) and Raspberry Pi 3 microcontroller board to recognise and classify the patient's fall. Python programming was done on the Raspberry Pi terminal to enable communication between the accelerometer sensor and the computer. There were 10 subjects (5 males and 5 females) collected. While daily living activities include standing, squatting, walking, sitting, and lying, the data on falling includes forward falls and falls from medical beds. The K-nearest Neighbour (kNN) classifier can categorise the data of falling and non-falling (everyday living activity). The accuracy of the kNN classifier was 100% for the combined feature and (>87%) for each feature during the categorization of the falling and non-falling classes. In the meantime, multiclass classification performance for combining features and for each feature separately was >85%. kNN classifier was used to assess the feature. The feature was chosen based on the k-NN classifier's accuracy score as a percentage. For feature selection for falling and non-falling, feature (AcclX, AcclY, AngX, AngY and AngZ) in City-block distance was selected as they performed high accuracy which was 100%. The performance of the AngZ (77%) was good during the sub-classification of the sub-class dataset. As a result, all feature characteristics were chosen to be incorporated in the IoT fall detection device. The system is real-time communication for classifying fall and non-fall conditions with 100% accuracy using kNN classifier with cityblock distance.
      1
  • Publication
    Color constancy analysis approach for color standardization on malaria thick and thin blood smear images
    ( 2021-01-01)
    Thaqifah Ahmad Aris
    ;
    Aimi Salihah Abdul Nasir
    ;
    Haryati Jaafar
    ;
    Lim Chee Chin
    ;
    Mohamed Z.
    Malaria is an extensively prevalent blood infection, the most severe and widespread parasitic disease that stirring millions of people in the world. Currently, microscopy diagnosis still the most widely used method for malaria diagnosis. However, this procedure contains the probability of miscalculation of parasites due to human error. Computerized system by using image processing is recognized as a quick and easy ways to analyze a lot of blood samples. However, because of the non-standard preparation of the blood slides which producing color varieties in different slides will result on low quality images. Hence, it is difficult to identify the existence of malaria parasites as well as observing its morphological characteristics to recognize malaria parasites. Therefore, this paper aims to analyze the standardization performance between six types of color constancy algorithms namely, gray world (GW), white patch (WP), modified white patch (MWP), progressive hybrid (PH), shades of gray (SoG) and gray edge (GE) on both thick and thin blood smear malaria images of P. falciparum and P. vivax species. Six types of color constancy algorithms standardization performance are analysed by using quantitative measure namely, peak signal to noise ratio (PSNR), normalized absolute error (NAE), mean square error (MSE) and root mean square error (RMSE). Based on the qualitative and quantitative findings, the results show that SoG algorithm is the best color constancy as compared to others proposed color constancy. SoG algorithm has achieved the highest PSNR and lowest NAE, MSE and RMSE values, thus proved that the quality of malaria images have been improved.
      1
  • Publication
    A fast and efficient segmentation of soil-transmitted helminths through various color models and k-means clustering
    ( 2021-01-01)
    Norhanis Ayunie Ahmad Khairudin
    ;
    Aimi Salihah Abdul Nasir
    ;
    Lim Chee Chin
    ;
    Haryati Jaafar
    ;
    Mohamed Z.
    Soil-transmitted helminths (STH) are one of the causes of health problems in children and adults. Based on a large number of helminthiases cases that have been diagnosed, a productive system is required for the identification and classification of STH in ensuring the health of the people is guaranteed. This paper presents a fast and efficient method to segment two types of STH; Ascaris Lumbricoides Ova (ALO) and Trichuris Trichiura Ova (TTO) based on the analysis of various color models. Firstly, the ALO and TTO images are enhanced using modified global contrast stretching (MGCS) technique, followed by the extraction of color components from various color models. In this study, segmentation based on various color models such as RGB, HSV, L*a*b and NSTC have been used to identify, simplify and extract the particular color needed. Then, k-means clustering is used to segment the color component images into three clusters region which are target (helminth eggs), unwanted and background regions. Then, additional processing steps are applied on the segmented images to remove the unwanted region from the images and to restore the information of the images. The proposed techniques have been evaluated on 100 images of ALO and TTO. Results obtained show saturation component of HSV color model is the most suitable color component to be used with the k-means clustering technique on ALO and TTO images which achieve segmentation performance of 99.06% for accuracy, 99.31% for specificity and 95.06% for sensitivity.
      2