Salina Abdul Samad

National University of Malaysia, Putrajaya, Putrajaya, Malaysia

Are you Salina Abdul Samad?

Claim your profile

Publications (177)26.78 Total impact

  • S.M.A.K. Rajin · S.A. Samad · A.M. Muad
    [Show abstract] [Hide abstract]
    ABSTRACT: Over the past decades, electronic nose has opened a variety of possibilities and is becoming one of the most important non-destructive odour inspection technologies in the food industry. The objective of this study is to determine the quality degradation of the fruit by monitoring the change in the volatile compound while kept in storage using a lab manufactured electronic nose. Here, grapes are chosen as the fruit sample for experiment. Principal component analysis (PCA) is used to determine the ability of the electronic nose to distinguish the different quality of the fruit stored over an interval of time. The result shows that using PCA analysis, the electronic nose is able to identify a clear distinction between the aromas of grapes stored for different time intervals.
    No preview · Article · Oct 2015
  • Sayf A. Majeed · HAFIZAH HUSAIN · SALINA ABDUL SAMAD · TARIQ F. IDBEAA
    [Show abstract] [Hide abstract]
    ABSTRACT: Mel Frequency Cepstral Coefficients (MFCCs) are the most widely used features in the majority of the speaker and speech recognition applications. Since 1980s, remarkable efforts have been undertaken for the development of these features. Issues such as use suitable spectral estimation methods, design of effective filter banks, and the number of chosen features all play an important role in the performance and robustness of the speech recognition systems. This paper provides an overview of MFCC's enhancement techniques that are applied in speech recognition systems. The details such as accuracy, types of environments, the nature of data, and the number of features are investigated and summarized in the table combined with the corresponding key references. Benefits and drawbacks of these MFCC's enhancement techniques have been discussed. This study will hopefully contribute to raising initiatives towards the enhancement of MFCC in terms of robustness features, high accuracy, and less complexity.
    No preview · Article · Sep 2015 · Journal of Theoretical and Applied Information Technology
  • Roshahliza M Ramli · Salina Abdul Samad · Ali O. Abid Noor
    [Show abstract] [Hide abstract]
    ABSTRACT: The properties of noise signals can be the main problem associated with noise cancellation systems. In order to overcome this problem, high complexity algorithms have to be used in order to reduce the noise embedded in the useful signals such as speech. This method can be impractical, especially in real-time applications where the computational power is a crucial issue. Adaptive filters give applicable solutions, but most literature proposed a single, yet complex algorithm to removing the noise. This paper proposes an alternative approach to eliminate background noise in corrupted speech signals. The method is achieved by letting the system assigns an appropriate algorithm according to the characteristics of the noise. The criterion used here is based on the calculation of eigenvalue spread in the autocorrelation matrix of the input signal. In addition, an algorithm derived from set-membership filtering is also used among the selected algorithms. This approach showed its potential capability in eliminating different types of environmental noise from corrupted speech signals. The technique presented here exhibited fast convergence speed and improvement in signal-to-noise ratio compared with other single adaptive algorithms.
    No preview · Article · Mar 2015
  • Tarik Faraj Idbeaa · Salina Abdul Samad · Hafizah Husain
    [Show abstract] [Hide abstract]
    ABSTRACT: Steganographic techniques with varying degrees of embedding capacity, perceptual transparency, and security are presented. These techniques have been developed to protect privileged or confidential information restricted to public access and to replace cryptography methods. In this study, three embedding algorithms, namely, least significant bit insertion, bit-plane complexity segmentation, and enhanced version of pixel value difference (EPVD) were implemented and analyzed in terms of the main steganography issues (payload, invisibility, and security) using a different proper performance metrics. This study was motivated by the minimal research focus accorded to hiding data in compression domain for the class of video-based embedding methods. Therefore, analyzing steganographic algorithms is generally based on hiding information in the quantized AC-Coefficients of the frames during the MPEG-2 compression process. Simulation results reveal that EPVD provides better embedded payload and acceptable visual quality, but lower PSNR value.
    No preview · Article · Jan 2015
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a hybrid speaker verification system based on the Hidden Markov Models (HMMs) and Vector Quantization(VQ) and Least Mean-Square (LMS) adaptive filtering. The aim of using hybrid speaker verification is to improve the HMMs performance, while LMS adaptive filtering is to improve the hybrid speaker verification performance in noisy environments. A Malay spoken digit database is used for the training and testing. It is shown that, in a clean environment a Total Success Rate (TSR) of 99.97% is achieved using hybrid VQ and HMMs. For speaker verification, the true speaker rejection rate is 0.06% while the impostor acceptance rate is 0.03% and the equal error rate (EER) is 11.72%. In noisy environments without LMS adaptive filtering TSRs of between 62.57%-76.80% are achieved for Signal to Noise Ratio (SNR) of 0-30 dBs. Meanwhile, after LMS filtering, TSRs of between 77.31%-76.87% are achieved for SNRs of 0-30 dB.
    No preview · Article · Jan 2015
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Content-based medical image retrieval (CBMIR) system enables medical practitioners to perform fastdiagnosis through quantitative assessment of the visual information of various modalities. In this paper, a more robust CBMIR system that deals with both cervical and lumbar vertebraeirregularity is afforded. It comprises three main phases, namely modelling, indexing and retrievalof the vertebrae image. The main tasks in the modelling phase are to improve, enhance thevisibility of the x-ray image for better segmentation results using active shape model (ASM). Thesegmented vertebral fractures are then characterized in the indexing phase using region-based fracturecharacterization (RB-FC) and contour-based fracture characterization (CB-FC). Upon a query, thecharacterized features are compared to the query image. Effectiveness of the retrieval phase isdetermined by its retrieval, thus, we propose an integration of the predictor model based crossvalidation neural network (PMCVNN) and similarity matching (SM) in this stage. The PMCVNN task is to identify the correct vertebral irregularity class through classification allowing the SM process tobe more efficient. Retrieval performance between the proposed and the standard retrieval architecturesare then compared using an retrieval precision (Pr@M) and average group score (AGS) measures. Experimental results show that the new integrated retrieval architecture performs better than those ofthe standard CBMIR architecture with retrieval results of cervical (AGS > 87%) and lumbar (AGS >82%) datasets. The proposed CBMIR architecture shows encouraging results with high Pr@M accuracy. As a result,images from the same visualization class are returned for further used by the medical personnel.
    Full-text · Article · Jan 2015 · BioMedical Engineering OnLine
  • Sayf A. Majeed · Hafizah HUSAIN · Salina A. SAMAD
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a new feature-extraction method is proposed to achieve robustness of speech recognition systems. This method combines the benefits of phase autocorrelation (PAC) with bark wavelet transform. PAC uses the angle to measure correlation instead of the traditional autocorrelation measure, whereas the bark wavelet transform is a special type of wavelet transform that is particularly designed for speech signals. The extracted features from this combined method are called phase autocorrelation bark wavelet transform (PACWT) features. The speech recognition performance of the PACWT features is evaluated and compared to the conventional feature extraction method mel frequency cepstrum coefficients (MFCC) using TI-Digits database under different types of noise and noise levels. This database has been divided into male and female data. The result shows that the word recognition rate using the PACWT features for noisy male data (white noise at 0 dB SNR) is 60%, whereas it is 41.35% for the MFCC features under identical conditions.
    No preview · Article · Jan 2015 · Archives of Acoustics
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Radiography images are used usually for diseases detection and fracture that can be visible on lateral view. Poor contrast of x-ray images do not provide momentous information concerning pathologies that are of interest to the radiologist. Magnification of contrast and sharpness of x-ray images will afford plenty and satisfactory visual information to radiologist and clinician and thus, allow better segmentation and indexing subsequent modules in the computer aided diagnosis (CAD) system for an autonomous disease diagnosis. Therefore, in this paper it intends to describe a new strategy to cater for under-specified queries enhancement using retrieval and classification platforms. In the retrieval platform (RPF), gamma correction (GC) function was employed on the under-specified query (USQ) image to generate dispersion versus location (DL) descriptor that measures the relationship between the local contrast and the local brightness, measured respectively with the help of estimators of location and dispersion. Subsequently, it employs appropriate near optimal search between the DL features of the USQ image and the corresponding similarity measurement in the archive database. In the classification platform (CPF), an approach was examined to predict the gain value of GC function using statistical pixel-level (SPL) features extracted from the radiography images along with the ANNs model classifier. The quality of the retrieved image is determined by referring to the USQ image. In addition, the problem of gain value estimation is transformed to a classification problem solved using an ANN model with three different measurement modes. Results indicated that the proposed approach can significantly improved image quality as confirmed by the DL descriptor which shown a more balance condition.
    Full-text · Conference Paper · Dec 2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: Orthogonal frequency-division multiplexing is now one of the most important modulation techniques due to its advantages. Despite its ability to overcome the equalization problem, multipath fading channels, and other issues, this system has a serious problem concerning the high output peaks with respect to the average power, which is called the peak-to-average power ratio (PAPR). Selected mapping (SLM), partial transmitted sequence, and amplitude clipping and filtering are some efficient methods to reduce the PAPR. In a previous work, we slid a single-phase rotation vector on the data sequence in the frequency domain to reduce the PAPR and the complexity compared to the conventional SLM. In this paper, we present a novel method that utilizes the same approach of our previous work, but it processes the data after the inverse fast Fourier transform block (time-domain operations) using a modified version of the SLM scheme, which has less computational complexity than the conventional one. The mathematical derivations and the simulation results show that the PAPR, the computational complexity, and the side information were reduced significantly by the proposed method.
    No preview · Article · Aug 2014 · Circuits Systems and Signal Processing
  • Roshahliza M Ramli · Ali Noor · Salina Abdul Samad

    No preview · Conference Paper · Jun 2014
  • Source
    Saad Mutashar · M. A. HANNAN · S. A. SAMAD · A. HUSSAIN
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper deals with the development of bio-implanted micro-system with low-power and high data rate based on amplitude shift keying (ASK) modulation technique to stimulate nerves and muscles. The modified system is operated by a low-frequency band 13.56 MHz according to the industrial-scientific-medical (ISM) bands to avoid the biological tissue damage. The data rate on the demodulator side is from 1 Mb/s and up to 1.5 Mb/s depending of generating binary signal (TBIT = 1 μs or 0.5 μs) with modulation index of 13% and modulation rate 7.3%, 9% and 11%, respectively. The proposed inductive coupling link achieves 73% of link efficiency. The modified rectifier with self-threshold voltage cancellation techniques and voltage regulator without thermal protection circuit and without passive elements occupies small area that is modified to generate adequate and stable DC voltages of 1.8 V. A new ASK demodulator structure based on two comparators is developed to extract a synchronized demodulated signal with minimum error. Thereby no need for clock recovery circuit and delay-locked loops (DLL) circuits for data synchronization at 1 Mb/s and 1.250 Mb/s of speed. The system designed using OrCAD Pspice 16.2 is based on 0.35 μm technologies.
    Full-text · Article · Apr 2014 · Journal of Mechanics in Medicine and Biology
  • [Show abstract] [Hide abstract]
    ABSTRACT: OFDM is an important modulation technique currently in development in the field of communications systems. OFDM signals can combat multipath propagation and fading channels and can support large data rates. However, OFDM systems are multicarrier systems and experience problems due to the required summation of sinusoids when the in-phase subcarriers are combined, which produces high power peaks. The large power envelope fluctuations that occur at the output cause in-band and out-of-band distortions that result in degraded BER performance. The literature contains many qualified approaches to resolving the peak-to-average power ratio problem, including selected mapping, partial transmit sequence, and amplitude clipping techniques. The simplest technique is the amplitude clipping technique, and the selected mapping and partial transmit sequence techniques are excessively complicated for real-time implementation. In this paper, we suggest a modification to the amplitude clipping method to produce a novel clipping technique called the side information supported amplitude clipping (SI-SAC) method. The SI-SAC technique involves sending certain bits of extra information so that the receiver can recover all of the clipped data. The SI-SAC technique does not add computational complexity to the system, and simulation results show that the proposed method is superior to the conventional method. The peak-to-average power ratio was reduced by ≈2.5 dB, and the magnitude of the mean squared error vector is the same as that of the original signal that is not clipped. In contrast, the conventional amplitude clipping method produces a mean squared error vector with a large magnitude. Copyright © 2012 John Wiley & Sons, Ltd.
    No preview · Article · Apr 2014 · International Journal of Circuit Theory and Applications
  • Source
    Saad Mutashar · M. A. HANNAN · S. A. SAMAD · A. HUSSAIN

    Full-text · Article · Mar 2014
  • Source
    Saad Mutashar · M. A. HANNAN · S. A. SAMAD · A. HUSSAIN

    Full-text · Article · Mar 2014 · Journal of Mechanics in Medicine and Biology
  • R.M. Ramli · A.O.A. Noor · S.A. Samad
    [Show abstract] [Hide abstract]
    ABSTRACT: In most speech processing systems, speech signals degrade significantly in noisy environments. Therefore, noise cancellation methods are necessary to eliminate noise from signals. This paper presents a development technique to improve the performance of a noise cancellation system called Adaptive Line Enhancer (ALE) in variable noise environments. The method is based on using a modified and simplified version of the set-membership Affine Projection algorithm (AP) adaptive filter. The modification introduced here is to make the adaptive algorithm, work with a dynamically variable step-size, as a substitute for the commonly used Least Mean Square (LMS) algorithm in ALE system. The performance of the developed ALE in variable noise is illustrated here, and the results are compared to similar ALE systems based on the classical adaptive algorithms, such as the Least-Mean-Square (LMS), the Normalized LMS (NLMS) and the Affine Projection (AP) algorithms. The developed adaptive line enhancer using the simplified affine projection algorithm showed a better performance than those based on conventional algorithms.
    No preview · Article · Jan 2014 · International Review on Computers and Software
  • Source
    Saad Mutashar · Mahammad A. Hannan · Salina Abdul Samad · Aini Hussain
    [Show abstract] [Hide abstract]
    ABSTRACT: Abstract|This paper deals with the design of small-sized bio- implanted spiral circular coils (pancake) with an operating frequency of 13.56 MHz. The external and internal coils' geometric dimensions are dout = 56 mm, din = 10mm and dout = 11:6 mm, din = 5 mm, respectively, in which the electrical performance is veri¯ed through the commercial ¯eld solver High Frequency Structural Simulator (HFSS 13.0), which employs the ¯nite-element method (FEM) technique. Mathematical models for the proposed coils are developed. The simulation is performed-based on the developmental model in the air and at depths 6mm in a human biological tissue of dry and wet skin. The results demonstrate that the external and internal coils have maximum near-¯eld gains of 54.15 dB and 53.30 dB in air. The maximum gains of the external coil contacted the wet and dry skin are 49.80 dB and 48.95 dB, respectively. The maximum gains of the internal coil at depths of 6mm in the wet and dry tissue are 41.80 dB and 41.40 dB, respectively. However, the external coil radiation e±ciencies on wet- and dry-skin are 92% and 90%, respectively, compared with that on air. The internal coil radiation e±ciencies on wet- and dry-skin are 78.4% and 77.6%, respectively, compared with that on air. In this study, the speci¯c absorption rate (SAR) and radiated power results of the internal coil are investigated using SEMCAD 16.4 software. The SAR and power loss studies show that the designed implanted coil has a negligible e®ect on the wet and dry skin and can be ignored.
    Full-text · Article · Aug 2013 · Progress In Electromagnetics Research M
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Peak power reduction techniques in orthogonal frequency division multiplexing (OFDM) has been an important subject for many researchers for over 20 years. In this letter, we propose a side-information-free technique that is based on the concept of random variable (RV) transformation. The suggested method transforms RVs into other RVs, aiming to reshape the constellation that will consequently produce OFDM symbols with a reduced peak-to-average power ratio. The proposed method has no limitation on the mapping type or the mapping order and has no significant effect on the bit error rate performance compared to other methods presented in the literature. Additionally, the computational complexity does not increase.
    Full-text · Article · Aug 2013 · Etri Journal
  • Tarik Faraj Idbeaa · Salina Abdul Samad · Hafizah Husain

    No preview · Article · Jul 2013 · International Journal of Advancements in Computing Technology
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a novel technique that can be effectively used to reduce the peak-to-average power ratio (PAPR) of the orthogonal frequency division multiplexing (OFDM) system is proposed. The proposed technique, called sliding selected mapping (SSLM), is considered a modified version of the conventional selected mapping (CSLM) scheme. SSLM uses a window with a predefined size of less than N, which carries the phase rotation vector (PRV). In contrast to the CSLM, SSLM uses length-f N PRVs (0<f<1). The window is shifted by a step size (sliding) on the data sequence. At each shift, the modified data sequence undergoes IFFT operations to check the PAPR, similar to the CSLM. Thereafter, the shift index that corresponds to the minimum PAPR is chosen as the side information. Meanwhile, for comparison, the CSLM uses the PRV index as side information. Simulation results and mathematical computations show that our proposed technique requires less computational complexity. In addition, the corresponding amount of side information is significantly reduced compared with that of CSLM.
    No preview · Article · May 2013
  • Mohd Ridzuwary Mohd Zainal · Aini Hussain · Salina Abdul Samad
    [Show abstract] [Hide abstract]
    ABSTRACT: An endpoint detection algorithm is utilised for segmentation of audio video Malay utterances. An audio visual Malay speech database of subjects uttering numerical digits is used. Synchronization between video frames and audio signals is taken into considerations for audio visual speech processing. The proposed system is able to group together the individual syllables that make up each of the uttered Malay digits.
    No preview · Chapter · Jan 2013

Publication Stats

511 Citations
26.78 Total Impact Points

Institutions

  • 1-2015
    • National University of Malaysia
      • • Department of Electrical, Electronic and Systems Engineering
      • • Faculty of Engineering and Built Environment
      Putrajaya, Putrajaya, Malaysia
  • 2003
    • Multimedia University
      • Faculty of Information Science and Technology
      Kuala Lumpor, Kuala Lumpur, Malaysia