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
Thumbnail Image
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.

View
Thumbnail Image
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.

View
Thumbnail Image
Publication

User specific weights based on score distance and EER for weighted sum rule fusion

2017-01-01 , Nordiana Mukahar , Haryati Jaafar , Bakhtiar Affendi Rosdi

In weighted sum rule fusion, proper weights assignment for different biometric sources is very important. The effective weights assignment procedure based on individual score performance is the vital key in adaptive weighted sum fusion. In this paper, an adaptive user specific weighted sum based on score distance is devised to determine optimal weights. It integrates the performance of the biometric source represented by its Equal Error Rate (EER) and score distance in weights estimation procedure. Although the designated weighted sum fusion requires less setting and less exhaustive search of fusion parameters, it can obtain better performance than previous approaches. The proposed technique outperforms the existing user specific weighted fusion schemes in all experiments by consistently achieves a minimum EER value.

View
Thumbnail Image
Publication

An Application of Principal Component Analysis in Aspergillus Species Identification

2022-01-01 , Nur Rodiatul Raudah Mohamed Radzuan , Haryati Jaafar , Farah Nabilah Zabani

Aspergillus sp. is one of the filamentous fungi that has a number of benefits in the food industry. Despite its important roles in industry level, they have several shortcomings especially to immunocompromised individuals that appear to be highly susceptible to disease or infection. Normally, the identification of species was manually screened by the trained microscopists but, the machine learning application becomes as an alternative to identify the species of Aspergillus. However, the development of machine learning is not straightforward and time consuming if the data is not well presented. In order to fasten the identification process of Aspergillus while retaining its characteristics, principal component analysis (PCA) and principal component analysis and Histogram of Oriented Gradient (PCAHOG) were employed to reduce the dimensionality of the dataset. Different values of eigen in PCA were executed and the classification by support vector machine (SVM) with two different kernels such as polynomial and radial basis function (RBF) was done afterwards. Based on the performance evaluation, PCAHOG-SVM (Polynomial) with eigenvalue of 48 outperformed the others with accuracy of 99.43% for training number of 18. Moreover, three Aspergillus sp. have been recorded 100% of accuracy with the same number of trainings.

View
Thumbnail Image
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.

View
Thumbnail Image
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.

View
Thumbnail Image
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.

View
Thumbnail Image
Publication

Entropy virus microscopy images recognition via neural network classifiers

2017-07-02 , Afiq Ahmad Shakri , Syahrul Affandi Saidi , Haryati Jaafar , Muhammad Naufal Mansor , Wan Azani Wan Mustafa , Ahmad Kadri Junoh

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 Entropy feature extraction with Feed Forward Neural Network (FFNN) classifier under various levels of noise. The real time experiment conducted proved that the method proposed are efficient, robust, and excellent of which it has produced a results accuracy of up to 88% for biological viruses images classification.

View
Thumbnail Image
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.

View
Thumbnail Image
Publication

Comparability of edge detection techniques for automatic vehicle license plate detection and recognition

2021-01-01 , Fatin Norazima Mohamad Ariff , Aimi Salihah Abdul Nasir , Haryati Jaafar , Zulkifli A.N.

License plate recognition system is one of the famous topics in image processing to identify the vehicle registration number. This system has been given a lot of beneficial toward transportation system, especially for security system. However, to get the perfect segmentation on alphabet shape for recognition purpose is quite challenging due to the non-uniform condition of image acquisition. Hence this paper proposes a methodology for segmentation of license plate number by using edge-based segmentation. In this study, image segmentation based on edge detection has been chosen due to the sharpness and detail in detecting the shape of an object. Since there are various types of edge detection techniques have been proposed by the previous researchers, several edge detection techniques from the most commonly used techniques have been chosen to be compared and analyze the results of various edge detection for license plate recognition. In this paper, several types of edge detection techniques such as Approxcanny, Canny, Chan-Vese, Kirsch, Prewitt, Robert, Sobel, Quadtree and Zero Crossing edge detector have been compared through greyscale images. Grayscale image has been enhancing before by modified white patch. Then, the holes area of the segmented license plate image are filled to obtain the characters, followed by step for removing the unwanted objects from the segmented license plate images. Later, the characters of the license plate are recognized based on template matching approach. This recognition analysis consists of two stages. First stage is all edge detector techniques have been used same standard values in removing the noise. Five edge detectors with best performance have been selected for next stage. In the second stage, the unwanted objects have been removed with appropriate values which are suitable for each of the edge detection techniques. The final result shows that Chan-Vese conquers the analysis with highest accuracy of edge detection obtained in license plate recognition.

View