Mohd Nazrin Md Isa

Investigation of information fusion in face and palmprint multimodal biometrics

This paper reviews several information fusion techniques and strategies in the application of multimodal biometrics system using face and palmprint images. Multimodal biometric is able to overcome several limitations in single modal biometric such as intra-class variations, less discriminative power, noise data and redundant features. By consolidating two kinds of modality a better performance can be achieved. Information fusion in multimodal biometrics can be carried out at three possible levels, i.e. feature, matching score and decision levels. Fusions at these three levels have their own attributes, thus this paper is aimed to compare their effectiveness. A specific fusion rule is necessary to combine the information at each level. Several numbers of analyses on verification and identification shows matching score fusion is able to achieve the best performance which is 98% recognition rates and 98.5% GAR at 0.1% FAR when tested using AR face and PolyU palmprint datasets.

An efficient processing element architecture for pairwise sequence alignment

One of the most challenging tasks in sequence alignment is its repetitive and time-consuming alignment matrix computations. Alignment matrix scores are crucial for identifying regions of homology between biological sequences. In this paper, a parametrizable and area efficient processing element (PE) architecture for performing biological sequence alignment task especially for pairwise biological sequence alignment is designed. Its corresponding PE architecture realization was prototyped on Xilinx FPGA platform. FPGA has been chosen as it able to realize an array of systolic array-based PEs. Execution of the proposed parameterizable PE architecture have been conducted and comparison results have shown that the systolic arrays with parameterizable PE has gained at least 15x speed-up as compared to the well-known SSEARCH 35 solution.

Fusion of Low Frequency Coefficients of DCT Transform Image for Face and Palmprint Multimodal Biometrics

In this paper, we propose multimodal biometric feature fusion using alternating concatenation of DCT coefficients exist in face and plamprint images. Discrete cosine transform (DCT) is used to extract low frequency features which has high discrimination feature at the top left corner of the DCT transform image. The fuse feature vector is projected to the most principal component of eigenvector to produces low dimensional fused feature vector which contains important information about the face and palmprint images. Distance classifier is then implemented as a classifier to compute the nearest distance of test feature data point with a template to evaluate the recognition process. PolyU and FERET dataset is used to validate the propose method and the result shows fusion by using alternating concatenation of face and palmprint is able to produce a better recognition rates compare to concatenation method. The best recognition rate is 95%.

Combination of gait multiple features at matching score level

This paper focus to analyze several fusion rule at matching score level to combine important features extracted from gait sequence images for human identification system. Gait sequence image is a non-stationary data and can be modelled using a statistical learning technique. The propose technique consists of three different stages. The pre-processing stage computes the average silhouette images to capture the important information and get a better representation for gait silhouette data. Then a principle component analysis (PCA) technique is applied on the average silhouette to extract the important gait features and reduce a dimension of gait data. Three different features are fused at matching score level by using sum, product and max rule. The proposed algorithm has been tested using a benchmark CASIA datasets. The experimental results show that the best recognition rate is 90% when the fusion is performed using sum rule.

Score level normalization and fusion of iris recognition

Biometric traits such as an iris texture is one of the dependable physiological biometric traits because of its uniqueness. In this paper, we explore a different approach of matching score fusion and the effect of normalization method to the fusion process. Despite a plenty of work of iris recognition methods have been proposed in recent years, many are paying attention to the feature extraction process and classification method. Less number of method focuses on the information fusion of iris images. Fusion is believed to produce a better discrimination power due to the rich information can be utilized from both of iris images. We conduct an analysis to investigate which fusion rule is able to produce the best result for iris recognition system. Experimental analysis using CASIA dataset shows sum rule fusion produces 99% recognition accuracy. The verification analysis shows the best result is GAR = 95% at the FRR = 0.1% when using min-max normalization method to preprocess the matching score before the fusion process.

Carbon nanotubes based hydrogen sensor on paper using Langmuir-Blodgett technique

A homogeneous film of acid functionalized Carbon Nanotubes was deposited on the paper substrate using Langmuir-Blodgett technique. The palladium nanoparticles were dropped on the nanotubes network afterword for device enhancement. The sensitivity of the device towards hydrogen gas was tested at three temperatures; room temperature, 200 °C and 300 °C in atmospheric conditions. The results show that CNT network with Pd decorated has high sensing response up to 22 % recorded at room temperature.

High Efficiency 2.4 GHz CMOS Two Stages Class-F Power Amplifier for Wireless Transmitters

A design of CMOS class-F power amplifier (PA) at 2.4-GHz for wireless transmitters is presented. The class-F PA design is implemented by using 0.13-μm CMOS process. The proposed class-F PA employs cascade topology. The transistor’s on resistance is decreased by designing the transistors in parallel. Therefore, the efficiency is increased. The first stage is a common-source driver stage is biased in a class-AB to provide sufficient input voltage swing for the amplifier stage, while the amplifier stage is biased in cut-off region. Therefore, the transistor can operate as a switching-mode for high efficiency. The simulation results show that the power added efficiency (PAE) of 60% is obtained at 1.3 V power supply and the PA delivers 12 dBm output power. The chip area is 0.66 mm2.

Langmuir-Blodgett Film of Multi-Walled Carbon Nanotubes for Hydrogen Sensor on Paper

Langmuir-Blodgett technique was applied to build optically homogeneous film of functionalized multi-walled carbon nanotubes (MWCNTs) on paper substrate. The palladium (Pd) nanoparticles were drop-casted onto MWCNTs network films before being exposed in hydrogen (H2) gas molecules environment under vacuum and atmospheric pressure at room temperature. The results demonstrate that the functionalized MWCNTs dispersed with Pd nanoparticles show good H2 sensing response on paper substrate where the sensitivity of around 10 % was recorded at only 2 minutes exposure time.

An Efficient Scheduling Technique for Biological Sequence Alignment

Computing alignment matrix score to search for regions of homology between biological sequences is time consuming task. This is due to the recursive nature of the dynamic programming-based algorithms such as the Smith-Waterman and the Needleman-Wunsch algorithmns. Typical FPGA-based protein sequencer comprises of two main logic blocks. One for computing alignment scores i.e. the processing element (PE), while another logic block for configuring the PE with coefficients. During alignment matrix computation, the logic block for configuring the PE are left unused until the time consuming alignment matrix computation finished. Therefore, a new technique, known as overlap computation and configuration (OCC) is proposed to minimize the time overhead for performing biological sequence alignment. The OCC technique simultaneously updating substitution matrix in a processing element (PE) systolic array, while computing alignment matrix scores. Results showed that, the sequencer achieves more than two order of magnitude speed-up higher compared to the state of the art, at negligible area overhead, if any.