Research Output
1 - 6 of 6
-
PublicationAn Intelligent Classification System for Trophozoite Stages in Malaria Species( 2022-01-01)Malaria is categorised as a dangerous disease that can cause fatal in many countries. Therefore, early detection of malaria is essential to get rapid treatment. The malaria detection process is usually carried out with a 100x magnificat i on of t hi n bl ood smear usi ng mi croscope observat i on. However, t he microbiologist required a long time to identify malaria types before applying any proper treatment to the patient. It also has difficulty to differentiate the species in trophozoite stages because of similar characteristics between species. To overcome these problems, a computer-aided diagnosis system is proposed to classify trophozoite stages of Plasmodium Knowlesi (PK), Plasmodium Falciparum (PF) and Plasmodium Vivax (PV) as early species identification. The process begins with image acquisition, image processing and classification. The image processing involved contrast enhancement using histogram equalisation (HE), segmentation procedure using a combination of hue, saturation and value (HSV) color model, Otsu method and range of each red, green and blue (RGB) color selections, and feature extraction. The features consist of the size of infected red blood cell (RBC), brown pigment in the parasite, and texture using Gray Level Co-occurrence Matrix (GLCM) parts. Finally, the classification method using Multilayer Perceptron (MLP) trained by Bayesian Rules (BR) show the highest accuracy of 98.95%, rather than Levenberg Marquardt (LM) and Conjugate Gradient Backpropagation (CGP) training algorithms.
-
PublicationClassification System of Malaria Disease with Hu Moment Invariant and Support Vector Machines( 2022-01-01)Malaria is an infectious disease caused by a plasmodium parasite transmitted by the female Anopheles mosquito. According to the World Health Organization (WHO) in 2020 there are an estimated 241 million cases of malaria worldwide with an estimated global death stood at 627. 000. The standard method of malaria diagnosis is by conducting microscopic examination or laboratory test and Rapid Diagnostic Test (RDT). Laboratory tests have a high risk of human error whereas RDT has weaknesses in temperature sensitivity, genetic variation, and antigen resistance in the bloodstream. This research offers a classification system of malaria disease by applying the Hu moment invariant and Support vector Machine (SVM) method with 3 types of malaria parasitic objects, namely falciparum, Malaria and vivax. The classification system uses 3 SVM models, namely linear SVM, polynomial SVM and Gaussian SVM with the Falciparum class as a positive data and malaria and vivax as negative data. The best classification outcome is on the Gaussian SVM model with 96.67% sensitivity and 90% specificity. The mean accuracy of the Gaussian SVM model with a 5-fold cross Validation 90 image sample which is divided into 3 classes is 86.66%.
-
PublicationApplication of Watershed Algorithm and Gray Level Co-Occurrence Matrix in Leukemia Cells Images( 2020-06-01)A long with the development of technology, the image of a sample of leukemia can be digitally processed to reduce the level of human error in diagnosing the disease. This research conducted by designing the image processing system on two types of leukemia, there are Acute Myelogenous Leukemia (AML) and Normal cell images by applying Watershed segmentation methods and feature extraction Gray Level Co-Occurrence Matrix (GLCM). The system was designed to find out how effective these methods to be continue into the classification process. The results of testing the application of these methods are the accuracy of the watershed segmentation method for this kind of Normal class was 90.4% with the average computing time of 0.89 seconds, and for the class of AML is 100% with the average computation time of 0.94 seconds. Application of the method GLCM has a significant difference the two types of leukemia were examine for each value extraction features with faster computing time, average 0.0060 seconds of computing time for this kind of Normal images. Whereas, for the AML class with average computation time was 0.0054 seconds.
-
PublicationComparison between Support Vector Machine and K-Nearest Neighbor Algorithms for Leukemia Images Classification Using Shape Features( 2021-01-01)Leukemia occurs when the body produces abnormal white blood cells in amounts exceeding the normal limit, making them misfunctioning. It is highly influential on the human immune system. Currently, medical personnel require a long time to recognize leukemia, and it is difficult to distinguish between acute leukemia cells and normal cells. Hence, this study aims to build a system program using white blood cell images with image processing using feature extraction with the Hu moments invariant and the Support Machine Machine (SVM) and K-Nearest Neighbor (K-NN) classification methods. The samples used were 800 blood images divided into two classes, acute and normal, with each class consisting of 400 sample images. Based on the test results from comparing the average value of accuracy and training time in both methods, the highest accuracy value was in the SVM method, with an accuracy of 87.97% and the K-NN method of 83.96%. The fastest training time was in the K-NN method of 2.43 seconds and the SVM method of 3.73 seconds.
-
PublicationClassification of Parasite Malaria in Schizon Stage with GoogleNet and VGG-19 Pre-Trained Models( 2023-01-01)The development of artificial intelligence technology has currently given benefit for humans in various fields. In the medical field, artificial intelligence was developed to help medical experts to classify various diseases using medical images, including malaria. Early detection of malaria parasites is important to save the patients, thus this study developed a detection system for some malaria parasites (P. falciparum, P. vivax, and P. malariae) in the schizont stage. This system uses deep learning methods using GoogleNet and VGG 19 pre-trained models. This study performs accuracy, running time, and analysis based on the confusion matrix for testing result. The best training result is performed by the GoogleNet pre-trained model, with an average running time of 7 minutes 14 seconds and an average accuracy of 98.53% \pm 1.27\%. The best model for classifying malaria image in the blood is the GoogleNet model with an accuracy value of 97.41%, precision 100%, recall 93.75%, specificity 100% and f-score 99.53%.
-
PublicationIntelligent Classification Procedure for Plasmodium Knowlesi Malaria Species( 2022-01-01)Plasmodium knowlesi (PK) is the fifth most prevalent malarial parasite species that causes serious health problems. Generally, PK present in a thin blood smear is observed using a microscope to differentiate between trophozoites (PKT), schizonts (PKS), gametocytes (PKG), and white blood cells (WBCs). This process is time-consuming and strenuous for the human eye. This study developed an intelligent classification procedure for PK using image processing and classification methods. The processes involved starting from image acquisition, and contrast enhancement based on Combination Local and Global Statistical Data (CLGSD), and local contrast stretching (LCS). Subsequently, a segmentation procedure was developed to segment the malaria images into two regions, namely malarial parasites and background regions. The proposed 16 feature sets were extracted, which consisted of the size of the object, size ratio of the object per infected RBC, and seven moments for each object shape based on size and perimeter. Finally, to validate the procedure performance, the proposed procedure was tested using 800 malarial parasites and WBC images. The results showed that the proposed procedure can classify three stages of PK, namely PKT, PKS, and PKG, as well as WBCs with an accuracy of 99.56% for training and 98.84% for validation, using a multi-layer perceptron (MLP) trained using the Levernberg-Marquardt (LM) algorithm.
1