Haryati Jaafar
Thumbnail Image
Preferred name
Haryati Jaafar
Official Name
Jaafar, Haryati
Alternative Name
Jaafar, Haryati
Jaafar, H.
Main Affiliation
Scopus Author ID
55357649900
Researcher ID
ILC-1943-2023

Research Output

Filters

23
Reset filters

Settings
Now showing 1 - 10 of 23
  • Publication
    Frog sound identification using extended k-nearest neighbor classifier
    ( 2017-09-21)
    Nordiana Mukahar
    ;
    Bakhtiar Affendi Rosdi
    ;
    Dzati Athiar Ramli
    ;
    Haryati Jaafar
    Frog sound identification based on the vocalization becomes important for biological research and environmental monitoring. As a result, different types of feature extractions and classifiers have been employed to evaluate the accuracy of frog sound identification. This paper presents a frog sound identification with Extended k-Nearest Neighbor (EKNN) classifier. The EKNN classifier integrates the nearest neighbors and mutual sharing of neighborhood concepts, with the aims of improving the classification performance. It makes a prediction based on who are the nearest neighbors of the testing sample and who consider the testing sample as their nearest neighbors. In order to evaluate the classification performance in frog sound identification, the EKNN classifier is compared with competing classifier, k -Nearest Neighbor (KNN), Fuzzy k -Nearest Neighbor (FKNN) k - General Nearest Neighbor (KGNN)and Mutual k -Nearest Neighbor (MKNN) on the recorded sounds of 15 frog species obtained in Malaysia forest. The recorded sounds have been segmented using Short Time Energy and Short Time Average Zero Crossing Rate (STE+STAZCR), sinusoidal modeling (SM), manual and the combination of Energy (E) and Zero Crossing Rate (ZCR) (E+ZCR) while the features are extracted by Mel Frequency Cepstrum Coefficient (MFCC). The experimental results have shown that the EKNCN classifier exhibits the best performance in terms of accuracy compared to the competing classifiers, KNN, FKNN, GKNN and MKNN for all cases.
  • Publication
    Deep neural network approach to frog species recognition
    ( 2017-10-10)
    Norsalina Hassan
    ;
    Dzati Athiar Ramli
    ;
    Haryati Jaafar
    Automatic frog species recognition based on acoustic signal has received attention among biologists for environmental studies as it can detect, localize and document the declining population of frog species efficiently compared to the manual survey. In this study, we investigate the possibility of the use of Deep Neural Network (DNN) as a classifier for a frog species recognition system. The Mel-Frequency Cepstral Coefficients (MFCCs) is utilized as features and prior to the feature extraction, we also investigate the capability of automatic segmentation of syllables based on the Sinusoidal Modulation (SM), Energy with Zero Crossing Rate (E+ZCR) and Short-Time Energy with Time Average Zero Crossing Rate (STE+STAZCR). We also evaluate several DNN parameter's setting so as to discover the optimum parameter values for our developed system. 55 different species of frog with 2674 syllables from our in-house database have been tested. Experimental results based on DNN classifier showed that the STE+STAZCR method gives the accuracy of 99.03%, which reveals the viability of DNN as a classifier. In future, further research on DNN parameter optimization will be conducted for system improvement.
  • Publication
    Automatic detection of embolic signal for stroke prevention
    ( 2017-01-01)
    Noor Salwani Ibrahim
    ;
    Ng Yan Duan
    ;
    Dzati Athiar Ramli
    ;
    Haryati Jaafar
    Transcranial Doppler (TCD) ultrasound is an essential tool in clinical diagnosis to determine the occurrence of embolism in stroke patients. However, it requires manual attention and the accuracy will deteriorate due to fatigue factor. Instead of depending on human observer as a gold standard to detect the emboli, this study proposes an automated emboli detection system based on three detection methods i.e. time-domain intensity, frequency-domain intensity and time-frequency intensity hybrid. Experimental studies of 240 samples of six data sets were employed. The performance evaluations of each method are measured in term of accuracy percentage and processing speed while human observation is also done as the golden standard for accuracy comparison. The best result is achieved by the time-frequency intensity hybrid method where 90.74 % of the embolic signals and 100 % of the non-embolic signals were successfully identified. The performance of this method is promising as the accuracy achieved by human observation was 87.45 and 100 % for embolic signals and non-embolic signals, respectively.
  • 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.
  • Publication
    A methodology of nearest neighbor: Design and comparison of biometric image database
    ( 2017-01-06)
    Haryati Jaafar
    ;
    Nordiana Mukahar
    ;
    Dzati Athiar Ramli
    The nearest neighbor (NN) is a non-parametric classifier and has been widely used for pattern classification. Nevertheless, there are some problems encountered that leads to the poor performance of the NN i.e. the samples distribution, weighting issues and computational time for large databases. Hence, various classifiers i.e. k Nearest Neighbor (kNN), k Nearest Centroid Neighborhood (kNCN), Fuzzy k Nearest Neighbor (FkNN), Fuzzy-Based k Nearest Centroid Neighbor (FkNCN) and Improved Fuzzy-Based k Nearest Centroid Neighbor (IFkNCN) were proposed to improve the performance of the NN. This paper presents a review of aforementioned classifiers including the taxonomy, toward the implementation of classifiers in biometric image database. Two databases i.e. finger print and finger vein have been employed and the performance of classifiers were compared in term of processing time and classification accuracy. The results show that the IFkNCN classifier owns the best accuracies to the kNN, kNCN FkNN and FkNCN with 97.66% and 96.74% for fingerprint and finger vein databases, respectively.
  • Publication
    An Identification of Aspergillus Species: A Comparison on Supervised Classification Methods
    ( 2022-01-01)
    Nur Rodiatul Raudah Mohamed Radzuan
    ;
    Haryati Jaafar
    ;
    Aimi Salihah Abdul Nasir
    Aspergillus is one of the well-known existed saprophytic fungi that can withstand with various environments. Other can be beneficial in food industry, it also can be infectious to human and animals and normally, it attacks those with low immunity level. In order to keep the treatment in track with more accurate analysis, identification of Aspergillus plays an important role. Identification of Aspergillus is solely based on its characteristic and currently, there are two methods used which are microscopic and macroscopic examinations to observe its features. It handled by experienced microscopist and a few confirmations had to be done before presenting out the final result. Therefore, to prevent misidentification, an automated based identification is proposed. In this paper, different supervised classifiers are tested and compared to observe their ability to detect different 162 of Aspergillus images. The features have been extracted by using Principal component analysis (PCA) and several classifiers such as k- nearest neighbour (kNN), Sparse Representation Classifier (SRC), Support Vector Machine (SVM), Improved Fuzzy-Based k Nearest Centroid Neighbor (IFkNCN) and Kernal Sparse Representation Classifier (KSRC) are employed. Based on its accuracy, Aspergillus flavus recorded 80% of accuracy for all the classifiers.
      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.
      1  13
  • Publication
    Home Service Robot Based on Image Recognition System
    ( 2022-01-01)
    Syed Muhamad Akid Syed Zainal Abidin
    ;
    Haryati Jaafar
    ;
    Seng Lee Yeng
    In a modern world with the hectic schedules, finding and delivering the object becomes a crucial task for some people. It can be troublesome to some people who has memory problem, tight schedule and disable person. Thus, an indoor autonomous face recognition and object tracking robot is proposed. The robot is created to detect and find small scale object in order to reduce time in finding the user’s personal belongings that missing. Three stages will be developed which are face recognition, searching object and pick and place. At the initial stage, the face recognition system is investigated to avoid misused by the unknown user. Once the user is identified, the avoidance obstacle robot will be functioned to find the particular object. The image of the object that has been captured initially is then processed by using image processing in this stage. The object detection is based on the template matching process. If the target object is false, it will search for the next object until the right one is detected. Once the object detected match the object instructed to be found, it would pick up that certain object. Three objects from different size and shape of object has been tested to determine the accuracy, specificity and sensitivity of the robot. The results shows the robot is able to perform with 80% accuracy and above for all objects.
      1
  • Publication
    An Adaptive Decision Weighted Fusion-based Strategy in Multibiometric System for Face Recognition
    ( 2023-01-01)
    Ariff F.N.M.
    ;
    Haryati Jaafar
    Face recognition system has been foremost since the advent of computers as it involves low-cost installation, non-invasive equipment, and the ease of data collection process. However, the development of face recognition system is not straightforward due to the changes of facial expression, face feature and pose. These changes lead to the performance degradation. Therefore, a multibiometric system is explored and an adaptive decision weighted fusion-based strategy is proposed to tackle the poor performance of single biometric system. The proposed strategy is divided into two parts. In part one, the adaptive weighted is considered where the weighted value is determine based on distance metric of Euclidean Distance (ED). In part two, the decision of fusion process is employed to select the optimum weightage based on distance that obtained in part one. Two feature extractions which are Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) have been employed to investigate the effectiveness of proposed fusion technique in face identification process. In order to evaluate the effectiveness of the proposed strategy, the face image of benchmark database and collected database are used for the performance evaluations. The results show an adaptive decision weighted fusion-based strategy comes out as an outstanding fusion technique compared to other tested rules with the performances of 95.33% is achieved from the benchmark database and collected database, respectively.
      1  8
  • Publication
    Implementation of Fuzzy Gamma Adaptive Histogram Equalization for Penicillium and Aspergillus Species
    ( 2022-01-01)
    Farah Nabilah Zabani
    ;
    Haryati Jaafar
    ;
    Harun A.
    This paper proposes a new approach in image enhancement method to enhance the structure of fungi namely, Penicillium and Aspergillus. The new approach combines the methods of adaptive histogram equalization (AHE), gamma correction and fuzzy logic. Previous methods of enhancing the structure of fungi is barely available as the current conventional method of identifying a fungi species relies on detecting the fungi directly from a microscope instead of examining it in the form of an image. It is widely known that microscopic images of fungi are usually low in contrast. Plus, the structure of fungi is complex and changes according to its level of maturity. Thus, a new approach in image enhancement is investigated to improve the appearance of the structure of fungi. The performance of the proposed method is evaluated on the collected database consisting of 194 microscopic coloured image of fungi. The result obtained shows that the proposed method, Fuzzy Gamma Adaptive Histogram Equalization (FGAHE) has a better performance in terms of enhancing the structure of fungi by obtaining a PSNR value of 14.28 dB, 20.37 dB and 21.60 dB from the species of Penicillium, Aspergillus fumigatus and Aspergillus terreus respectively.
      1