Amiza Amir
Thumbnail Image
Preferred name
Amiza Amir
Official Name
Amiza, Amir
Main Affiliation
Scopus Author ID
36170326400
Researcher ID
EKV-8568-2022

Research Output

Filters

3 1
23
Reset filters

Settings
Now showing 1 - 10 of 23
Thumbnail Image
Publication

Design of Passive RFID Tag Using Frequency Selective Surface with Polarization Insensitive

2023-10-06 , Saidatul Norlyana Azemi , Ibrahim N.A. , Amiza Amir , Mohd Rashidi Che Beson , Abdul Aziz M.E.

RFID is not a new technology. It has been applied in various industries such as for wearable applications. Common RFID tags especially for those that have been designed and are available are not independent of the incident receiver angle. Numerous wearable antennas on the market are only designed for a certain received angle. For example, a wearable RFID antenna is used in medical as a pulse reading detector. If the patient makes any movement, the patient's pulse reading is no longer accurate or there may be no pulse reading. Hence, the purpose of this project is to design and RFID antennas using Frequency Selective Surface, FSS for wearable applications that are independent towards the incident angle and small in size. In this project, several antennas design with Frequency Selective Surface (FSS) is proposed. The design for this antenna is round, square, and hexagonal. This antenna has an operating frequency from 2.4 GHz to 5.8GHz, bandwidth efficiency> 50%, dielectric constant 1.30, independent incident angle up to 60 degrees, and has a high gain of around 2 to 3dB.

View
Thumbnail Image
Publication

Image classification for snake species using machine learning techniques

2017-01-01 , Amiza Amir , Nik Adilah Hanin Zahri , Naimah Yaakob , R Badlishah Ahmad

This paper investigates the accuracy of five state-of-the-art machine learning techniques — decision tree J48, nearest neighbors, knearest neighbors (k-NN), backpropagation neural network, and naive Bayes — for image-based snake species identification problem. Conventionally, snake species identification is conducted manually based on the observation of the characteristics such head shape, body pattern, body color, and eyes shape. Images of 22 species of snakes that can be found in Malaysia were collected into a database, namely the Snakes of Perlis Corpus. Then, an intelligent approach is proposed to automatically identify a snake species based on an image which is useful for content retrieval purpose where a snake species can be predicted whenever a snake image is given as input. Our experiment shows that backpropagation neural network and nearest neighbour are highly accurate with greater than 87% accuracy on CEDD descriptor in this problem.

View
No Thumbnail Available
Publication

Automated detection of Printed Circuit Boards (PCB) defects by using machine learning in electronic manufacturing: current approaches

2020 , S. S. Zakaria , Amiza Amir , Naimah Yaakob , S Nazemi

The manufacturing of a printed circuit board in the SMT assembly line goes through multiple phases of automatic handling. To ensure the quality of the board and reduce the number of defects, inspection tasks such as solder paste inspection and automatic optical inspection are conducted. The inspection tasks are carried out at various phases of the assembly line. The paper aims to answer the questions of how machine learning technology can contribute for better PCB fault detection in the assembly line and at which parts of the assembly line this technology has been applied. The paper discusses the PCB defect detection by using machine learning and other approaches. The current research shows that PCB defect detection using machine learning are miniscule. Early detection is still unexplored and experimented in the industry.

View
Thumbnail Image
Publication

Analysis of the effectiveness of Metaheuristic methods on Bayesian optimization in the classification of visual field defects

2023 , Masyitah Abu , Nik Adilah Hanin Zahri , Fumiyo Fukumoto , Amiza Amir , Muhammad Izham Ismail , Yoshimi Suzuki , Azhany Yaakub

Bayesian optimization (BO) is commonly used to optimize the hyperparameters of transfer learning models to improve the model’s performance significantly. In BO, the acquisition functions direct the hyperparameter space exploration during the optimization. However, the computational cost of evaluating the acquisition function and updating the surrogate model can become prohibitively expensive due to increasing dimensionality, making it more challenging to achieve the global optimum, particularly in image classification tasks. Therefore, this study investigates and analyses the effect of incorporating metaheuristic methods into BO to improve the performance of acquisition functions in transfer learning. By incorporating four different metaheuristic methods, namely Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC) Optimization, Harris Hawks Optimization, and Sailfish Optimization (SFO), the performance of acquisition function, Expected Improvement (EI), was observed in the VGGNet models for visual field defect multi-class classification. Other than EI, comparative observations were also conducted using different acquisition functions, such as Probability Improvement (PI), Upper Confidence Bound (UCB), and Lower Confidence Bound (LCB). The analysis demonstrates that SFO significantly enhanced BO optimization by increasing mean accuracy by 9.6% for VGG-16 and 27.54% for VGG-19. As a result, the best validation accuracy obtained for VGG-16 and VGG-19 is 98.6% and 98.34%, respectively.

View
Thumbnail Image
Publication

Performance Analysis of Congestion Control Mechanism in Software Defined Network (SDN)

2017-12-11 , Rahman M.Z.A. , Naimah Yaakob , Amiza Amir , R Badlishah Ahmad , Yoon See Ki , Abd Halim A.H.

In the near future, the traditional networks architecture will be difficult to be managed. Hence, Software Defined Network (SDN) will be an alternative in the future of programmable networks to replace the conventional network architecture. The main idea of SDN architecture is to separate the forwarding plane and control plane of network system, where network operators can program packet forwarding behaviour to improve the network performance. Congestion control is important mechanism for network traffic to improve network capability and achieve high end Quality of Service (QoS). In this paper, extensive simulation is conducted to analyse the performance of SDN by implementing Link Layer Discovery Protocol (LLDP) under congested network. The simulation was conducted on Mininet by creating four different fanout and the result was analysed based on differences of matrix performance. As a result, the packet loss and throughput reduction were observed when number of fanout in the topology was increased. By using LLDP protocol, huge reduction in packet loss rate has been achieved while maximizing percentage packet delivery ratio.

View
No Thumbnail Available
Publication

Large neighbourhood search based on mixed integer programming and ant colony optimisation for car sequencing

2019 , Dhananjay Thiruvady , Kerri Morgan , Amiza Amir , Andreas T. Ernst

We investigate the problem of scheduling a sequence of cars to be placed on an assembly line. Stations, along the assembly line install options (e.g. air conditioning), but have limited capacities, and hence cars requiring the same options need to be distributed far enough apart. The desired separation is not always feasible, leading to an optimisation problem that minimises the violation of the ideal separation requirements. In order to solve the problem, we use a large neighbourhood search (LNS) based on mixed integer programming (MIP). The search is implemented as a sliding window, by selecting overlapping subsequences of manageable sizes, which can be solved efficiently. Our experiments show that, with LNS, substantial improvements in solution quality can be found.

View
Thumbnail Image
Publication

Design and Implementation of True Parallelism Quad-Engine Cybersecurity Architecture on FPGA

2022-01-01 , Mohammed N.Q. , Amiza Amir , Salih M.H. , R Badlishah Ahmad

Applications, such as Internet of Things, deal with huge amount of transmitted, processed and stored images that required a high computing capability. Therefore, there is a need a computing architecture that contribute in increasing the throughput by exploiting modern technologies in both spatial and temporal parallelisms. This paper conducts a parallel quad-engine cybersecurity architecture with new configuration to increase the throughput. using DE1-SoC and Neek FPGA boards and HDL. In this architecture, each engine operates with 600MHz maximum frequency. Each image is divided into four parts of equal size and each part processed by single engine concurrently to achieve spatial parallelism. Internally, engine is handling image’s part in temporal parallelism and deep pipelining abstraction applied in every engine by dividing it to sub modules to execute different tasks concurrently. All data processed in engines is encrypted via AES algorithm that implemented as a significant part of engine architecture. The obtained results increased the throughput by four times, with 153,600Mbps, that make this computing architecture efficient and suitable for fast applications such as IoT and cybersecurity level of processing

View
Thumbnail Image
Publication

The Performance Analysis of K-Nearest Neighbors (K-NN) Algorithm for Motor Imagery Classification Based on EEG Signal

2017-12-11 , Nurul E’zzati Md Isa , Amiza Amir , Mohd Zaizu Ilyas , Mohammad Shahrazel Razalli

Most EEG-based motor imagery classification research focuses on the feature extraction phase of machine learning, neglecting the crucial part for accurate classification which is the classification. In contrast, this paper concentrates on the classifier development where it thoroughly studies the performance analysis of k-Nearest Neighbour (k-NN) classifier on EEG data. In the literature, the Euclidean distance metric is routinely applied for EEG data classification. However, no thorough study has been conducted to evaluate the effect of other distance metrics to the classification accuracy. Therefore, this paper studies the effectiveness of five distance metrics of k-NN: Manhattan, Euclidean, Minkowski, Chebychev and Hamming. The experiment shows that the distance computations that provides the highest classification accuracy is the Minkowski distance with 70.08%. Hence, this demonstrates the significant effect of distance metrics to the k-NN accuracy where the Minknowski distance gives higher accuracy compared to the Euclidean. Our result also shows that the accuracy of k-NN is comparable to Support Vector Machine (SVM) with lower complexity for EEG classification.

View
No Thumbnail Available
Publication

Real-time drowsiness detection system for driver monitoring

2020 , M Arunasalam , Naimah Yaakob , Amiza Amir , Mohamed Elshaikh Elobaid Said Ahmed , N F Azahar

Nowadays, the rate of road accidents due to microsleep has been alarming. During microsleep, people might doze off without realizing it. For many decades, drowsiness detection system for vehicles was not among the major concerns though it turns out as one of imperative features that could have avoid microsleep and thus should be implemented in all vehicles in order to ensure safety of drivers and other vehicles on the road. To the best of our knowledge, enforcements on driving restriction during drowsiness state is yet to be implemented. The absence of such system in the current transportation systems expose drivers to great danger especially at night because accidents are highly likely to happen at night due to drowsy and fatigue drivers. Therefore, this project proposes a real-time drowsiness detection system for vehicles, featuring ignition lock to reduce accidents. An eye blink sensor is embedded in a wearable glasses and heart beat sensor is used to detect drowsiness level of drivers. The system also includes SMS notification system to relatives or friends with location details of the drowsy driver. This project is able to detect and react based on 3 levels of drowsiness by alerting the driver through buzzer. Ignition lock will be applied when high level of drowsiness is detected. Consequently, the vehicle will be slowed down and eventually stopped when dangerous level of drowsiness is detected as a safety precaution.

View
Thumbnail Image
Publication

Evaluating Tree-based Ensemble Strategies for Imbalanced Network Attack Classification

2024-01-01 , Soon H.F. , Amiza Amir , Nishizaki H. , Nik Adilah Hanin Zahri , Latifah Munirah Kamarudin , Saidatul Norlyana Azemi

With the continual evolution of cybersecurity threats, the development of effective intrusion detection systems is increasingly crucial and challenging. This study tackles these challenges by exploring imbalanced multiclass classification, a common situation in network intrusion datasets mirroring realworld scenarios. The paper aims to empirically assess the performance of diverse classification algorithms in managing imbalanced class distributions. Experiments were conducted using the UNSW-NB15 network intrusion detection benchmark dataset, comprising ten highly imbalanced classes. The evaluation includes basic, traditional algorithms like the Decision Tree, KNearest Neighbor, and Gaussian Naive Bayes, as well as advanced ensemble methods such as Gradient Boosted Decision Trees (GraBoost) and AdaBoost. Our findings reveal that the Decision Tree surpassed the Multi-Layer Perceptron, K-Nearest Neighbor, and Naive Bayes in terms of overall F1-score. Furthermore, thorough evaluations of nine tree-based ensemble algorithms were performed, showcasing their varying efficacy. Bagging, Random Forest, ExtraTrees, and XGBoost achieved the highest F1-scores. However, in individual class analysis, XGBoost demonstrated exceptional performance relative to the other algorithms. This is confirmed by achieving the highest F1-scores in eight out of the ten classes within the dataset. These results establish XGBoost as a predominant method for handling multiclass imbalance classification with Bagging being the closest feasible alternative, as Bagging gains an almost similar accuracy and F1-score as XGBoost.

View