Azrina Abd Aziz

ORCID: 0000-0003-0972-4761
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Energy Efficient Wireless Sensor Networks
  • Energy Harvesting in Wireless Networks
  • EEG and Brain-Computer Interfaces
  • Mobile Ad Hoc Networks
  • Artificial Intelligence in Healthcare
  • IoT-based Smart Home Systems
  • Face and Expression Recognition
  • Face recognition and analysis
  • Fault Detection and Control Systems
  • Biometric Identification and Security
  • Imbalanced Data Classification Techniques
  • Indoor and Outdoor Localization Technologies
  • Water Quality Monitoring Technologies
  • Security in Wireless Sensor Networks
  • IoT and Edge/Fog Computing
  • Cryptographic Implementations and Security
  • Chaos-based Image/Signal Encryption
  • Risk and Safety Analysis
  • Video Surveillance and Tracking Methods
  • Physical Unclonable Functions (PUFs) and Hardware Security
  • Quality and Safety in Healthcare
  • Underwater Vehicles and Communication Systems
  • Medical Image Segmentation Techniques
  • Green IT and Sustainability
  • Heavy Metals in Plants

Universiti Teknologi Petronas
2015-2024

Petronas (Malaysia)
2018-2024

Universiti Malaysia Pahang Al-Sultan Abdullah
2024

Universiti Sains Malaysia
2022-2023

Cloud Computing Center
2021

University of Oxford
2017

John Radcliffe Hospital
2017

Monash University
2012

Large-scale, self-organizing wireless sensor and mesh network deployments are being driven by recent technological developments such as The Internet of Things (IoT), Smart Grids Environment applications. Efficient use the limited energy resources (WSN) nodes is critically important to support these advances, application topology control methods will have a profound impact on efficiency hence battery lifetime. In this survey, we focus issue present comprehensive study techniques for extending...

10.1109/surv.2012.031612.00124 article EN IEEE Communications Surveys & Tutorials 2012-04-11

Cardiovascular diseases (CVDs) kill about 20.5 million people every year. Early prediction can help to change their lifestyles and ensure proper medical treatment if necessary. In this research, ten machine learning (ML) classifiers from different categories, such as Bayes, functions, lazy, meta, rules, trees, were trained for efficient heart disease risk using the full set of attributes Cleveland dataset optimal attribute sets obtained three evaluators. The performance algorithms was...

10.3390/app11188352 article EN cc-by Applied Sciences 2021-09-09

Assessing cognitive load during a learning phase is important, as it assists to understand the complexity of task. It can help in balancing postlearning and actual Here, we used electroencephalography (EEG) assess multimedia EEG data were collected from 34 human participants at baseline state. The analysis was based on feature extraction partial directed coherence (PDC). Results revealed that frequency bands activated brain regions contribute differed depending We concluded be assessed using...

10.1109/access.2017.2731784 article EN cc-by-nc-nd IEEE Access 2017-01-01

Communication in industrial wireless networks necessitates reliability and precision. Besides, the existence of interference or traffic network must not affect estimated properties. Therefore, data packets have to be sent within a certain time frame over reliable connection. However, working scenarios characteristics itself make it vulnerable node link faults, which impact transmission overall performance. This article aims introduce developed multipath routing model, leads cost-effective...

10.3390/app12020544 article EN cc-by Applied Sciences 2022-01-06

The placement of wireless mesh routers is a significant matter in enhancing the performance network. Therefore, it essential that are optimally placed to guarantee strong connectivity and coverage for ensuring best network accessibility. importance this issue has motivated researchers pursue more investigation on optimizing networks' performance. Various optimization algorithms have been developed literature identify trade-offs between client coverage. This work aimed at implementing novel...

10.1109/access.2022.3173316 article EN cc-by IEEE Access 2022-01-01

Developing a reliable and accurate indoor localization system is crucial step for creating seamless interactive user-device experience in nearly all intelligent internet of things (IIoTs) smart applications. Indoor systems based on WiFi fingerprinting have been considered as promising alternative to model-based approaches owing their accuracy, low cost, availability, ease configuration. However, recent studies revealed that complex environments, techniques are faced with lot challenges the...

10.1109/access.2024.3360228 article EN cc-by-nc-nd IEEE Access 2024-01-01

Wireless sensor networks (WSNs) have received considerable interest in recent years. These nodes can gather information from the surrounding environment and transmit it to a designated location. Each node WSN typically has battery with limited capacity. Due their large number because of various environmental challenges, is sometimes hard replace this finite battery. As result, energy-efficient communication seen as critical aspect extending lifespan node. On other hand, some applications...

10.3390/s22072598 article EN cc-by Sensors 2022-03-29

Medical science-related studies have reinforced that the prevalence of coronary heart disease which is associated with and blood vessels has been most significant cause health loss death globally. Recently, data mining machine learning used to detect diseases based on unique characteristics a person. However, these techniques often posed challenges due complexity in understanding objective datasets, existence too many factors analyze as well lack performance accuracy. This research work...

10.3390/app13010118 article EN cc-by Applied Sciences 2022-12-22

Cardiovascular diseases (CVDs) are killing about 17.9 million people every year. Early prediction can help to change their lifestyles and endure proper medical treatment if necessary. The data available in the healthcare sector is very useful predict whether a patient will have disease or not future. In this research, several machine learning algorithms such as Decision Tree (DT), Discriminant Analysis (DA), Logistic Regression (LR), Naïve Bayes (NB), Support Vector Machines (SVM), K-Nearest...

10.1109/icias49414.2021.9642676 article EN 2021-07-13

This work presents an approach for combining texture and shape feature sets towards age-invariant face recognition. Physiological studies have proven that the human visual system can recognise familiar faces at different ages from outline alone. Based on this scientific fact, phase congruency features analysis were adopted to produce a edge map. was beneficial in tracking craniofacial growth pattern each subject. Craniofacial is common during childhood years, but after age of 18, variations...

10.1049/iet-bmt.2014.0018 article EN public-domain IET Biometrics 2015-03-27

Plastic surgery is considered as a challenging research issue in the field of face recognition. Nevertheless, it has yet to be studied from theoretical and experimental perspectives. In this study, authors proposed facial recognition system for recognising faces after plastic surgery, which fuses scores two feature‐based texture‐based algorithms. The feature based algorithm image GIST global descriptor local binary pattern (LBP) silence points. First, texture LBP was applied over set key...

10.1049/iet-cvi.2014.0263 article EN IET Computer Vision 2016-02-25

A wireless sensor network (WSN) deploys hundreds or thousands of nodes that may introduce large-scale data over time. Dealing with such an amount collected is a real challenge for energy-constraint nodes. Therefore, numerous research works have been carried out to design efficient clustering techniques in WSNs eliminate the redundant before transmitting them sink while preserving their fundamental properties. This paper develops new error-aware (EDC) technique at cluster-heads (CHs)...

10.3390/s20041011 article EN cc-by Sensors 2020-02-13

LED is an ultra-lightweight block cipher targeting resource-constrained devices. The current hardware architectures of this utilize large logic area, operate in low frequencies and have throughput. To improve the trade-offs between area utilization performance, iterative round-based architecture implemented paper. algorithm available 64-bit 128-bit key sizes. In paper, focus on with size. This various Field Programmable Gate Array (FPGA) design verified several Altera Xilinx devices using...

10.1109/icoice48418.2019.9035193 article EN 2019-12-01

The design of cryptographic engines for the Internet Things (IoT) edge devices and other ultralightweight is a crucial challenge. emergence such resource-constrained raises significant challenges to current algorithms. PHOTON an ultra-lightweight hash function targeting low-resource devices. currently implemented hardware architectures utilize large amount resources have low operating frequencies with rate throughputs. Maximum frequency throughput architecture can be improved but at cost...

10.1109/access.2020.3038219 article EN cc-by IEEE Access 2020-01-01

Aim: The study aimed to investigate the impact of rainwater on acidity levelsto monitor acid deposition and identify sources pollutant that affect concentrations rainwater. Methodology Results: One unit sampler in each location was employed, andsamples were taken National Research Innovation Agency laboratory (BRIN) for analysis quality including acidity/pH degree, conductivity, ion concentrations. results show high rainfall intensity (>300 mm/month) April December 2019 led a decrease...

10.25105/urbanenvirotech.v6i1.14051 article EN INDONESIAN JOURNAL OF URBAN AND ENVIRONMENTAL TECHNOLOGY 2023-02-04

This paper implements a region identification to automatically detect vehicles on the road using Convolutional Neural Network (CNN) for autonomous vehicles. The is essential ensure vehicle can safely navigate without having collision with other Existing works highlighted problem of poor detection in (AV) during night scene and bad weathers. develops technique improve (poor lighting condition) weathers CNN approach. dataset 301 from KITTI Vision, Intercity Roads Adverse Driving Scenarios...

10.1109/icias.2018.8540563 article EN 2018-08-01

Whilst facial recognition systems are vulnerable to different acquisition conditions, most notably lighting effects and pose variations, their particular level of sensitivity aging is yet be researched. The face vendor test (FRVT) 2012's annual statement estimated deterioration in the performance due aging. There was about 5% degradation accuracies for each single year age difference between a image probe image. Consequently, developing an age-invariant platform continues significant...

10.1142/s0218001415560066 article EN International Journal of Pattern Recognition and Artificial Intelligence 2015-04-08

Recently, Wireless Sensor Network (WSN) has received increased interest of research due to its many real-life applications. In WSNs, the sensor nodes sense different phenomenon from surrounding area and forward data sink. Among available routing protocols (RP), most them used Low Energy Adaptive Clustering Hierarchy (LEACH) but did not consider battery energy level while selecting cluster head (CH). This paper proposed a multi-energy threshold-based protocol based on LEACH, which provides...

10.1109/icsgrc.2019.8837090 article EN 2019-08-01

This paper presents an energy-efficient algorithm based on the connected dominating set (CDS) for a wireless sensor networks (WSN). A CDS has been widely used virtual backbone construction to support routing and minimize communication overheads in network. Our algorithm, single-phase single initiator (SPSI), only requires phase construct distributed manner using localized information. It generates small with low message overhead lower energy consumption. Furthermore, it does not rely global...

10.1109/icias.2012.6306195 article EN 2012-06-01

Energy efficiency plays a significant role for the network lifetime extension in wireless sensor networks (WSNs). On other hand, higher priority information requires Quality of Service (QoS) to ensure their delivery with minimized delay. Furthermore, WSN nodes are low powered devices by small battery where capacity is limited. Therefore, there need establish an energy-efficient Medium Access Control (MAC) protocol minimum packet delays. In this paper, we propose adaptive synchronous MAC...

10.1109/iscaie51753.2021.9431806 article EN 2021-04-03

The aim of this research work is to design a smart city simulator. proposed simulator contains the 3D model several locations with each location equipped multiple types virtual sensors node. mainly include Noise Sensor, Air Pollution, Ultrasonic Humidity Temperature Sensor and Video Camera. These continuously monitor collect data from environment upload it public cloud for further analysis through gateway node provides communication hosted server. In addition, also mapping interface that...

10.1109/roma.2017.8231826 article EN 2017-09-01
Coming Soon ...