@ftkek.utem.edu.my
Assoc. Prof. in Computer Engineering/Faculty of Electronics and Computer Technology and Engineering
Universiti Teknikal Malaysia Melaka
Electrical and Electronic Engineering, Artificial Intelligence, Computer Vision and Pattern Recognition
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Fahd Saad Abuhoureyah, Yan Chiew Wong, and Ahmad Sadhiqin Bin Mohd Isira
Elsevier BV
Chia Yee Saw and Yan Chiew Wong
Elsevier BV
Fahd Abuhoureyah, Yan Chiew Wong, Ahmad Sadhiqin Mohd Isira, and Joon Huang Chuah
IEEE
This work presents an exceptional approach to address the location dependency challenge in Human Activity Recognition (HAR) using Channel State Information (CSI). HAR using CSI has shown promise in capturing fine-grained motion information; however, the performance of models varies significantly across different locations or positions. To mitigate this limitation, we propose an innovative solution based on 3D Continuous Wavelet Transform (CWT) that simultaneously captures spatial and temporal information. Experimental results demonstrate the effectiveness of the proposed approach in reducing location dependency and improving activity recognition accuracy across diverse environments.
Yan Chiew Wong, Ranjit Singh Sarban Singh, and Syafeeza Ahmad Radzi
Elsevier
A. H. Nurul Hidayah, Syafeeza Ahmad Radzi, Norazlina Abdul Razak, Wira Hidayat Mohd Saad, Y. C. Wong, and A. Azureen Naja
Universitas Muhammadiyah Yogyakarta
Traditionally, the farmers manage the crops from the early growth stage until the mature harvest stage by manually identifying and monitoring plant diseases, nutrient deficiencies, controlled irrigation, and controlled fertilizers and pesticides. Even the farmers have difficulty detecting crop diseases using their naked eyes due to several similar crop diseases. Identifying the correct diseases is crucial since it can improve the quality and quantity of crop production. With the advent of Artificial Intelligence (AI) technology, all crop-managing tasks can be automated using a robot that mimics a farmer's ability. However, designing a robot with human capability, especially in detecting the crop's diseases in real-time, is another challenge to consider. Other research works are focusing on improving the mean average precision and the best result reported so far is 93% of mean Average Precision (mAP) by YOLOv5. This paper focuses on object detection of the Convolutional Neural Network (CNN) architecture-based to detect the disease of solanaceous crops for robot vision. This study's contribution involved reporting the developmental specifics and a suggested solution for issues that appear along with the conducted study. In addition, the output of this study is expected to become the algorithm of the robot's vision. This study uses images of four crops (tomato, potato, eggplant, and pepper), including 23 classes of healthy and diseased crops infected on the leaf and fruits. The dataset utilized combines the public dataset (PlantVillage) and self-collected samples. The total dataset of all 23 classes is 16580 images divided into three parts: training set, validation set, and testing set. The dataset used for training is 88% of the total dataset (15000 images), 8% of the dataset performed a validation process (1400 images), and the rest of the 4% dataset is for the test process (699 images). The performances of YOLOv5 were more robust in terms of 94.2% mAP, and the speed was slightly faster than Scaled-YOLOv4. This object detection-based approach has proven to be a promising solution in efficiently detecting crop disease in real-time.
Dze Rynn Chen and Yan Chiew Wong
Institute of Advanced Engineering and Science
Conventional techniques of off-chip processing for wearable devices cause high hardware resource usage which leads to heat generation and increased power consumption. <span>Hence, edge computing methods such as neuromorphic computing are considered the most promising modern technology to replace conventional processing. It is beneficial to employ neuromorphic processing in electrocardiogram (ECG) classification, enabling engineers to overcome the constraints of heat generation caused by hardware utilization. Thus, this work aims to investigate common building blocks in a spiking neural network (SNN), analyze the spike-based plasticity mechanism and implement ECG classification on a neuromorphic circuit. The MIT-BIH Arrhythmia database (MITDB) is preprocessed in MATLAB, then used to train and test an SNN designed for field programmable gate arrays (FPGA), employing spike-based plasticity and Izhikevich neurons. The behaviour of spike timing dependent plasticity (STDP) in a neuromorphic circuit is also visualized in this work. The state-of the-art performance of this work lies in providing a generic mechanism to adapt ECG classification into a neuromorphic solution, a non-Von Neumann architecture. The proposed digital design utilizes 1.058% of hardware resources on a Zedboard. Application-wise, this work provides a foundation for development of neuromorphic computing in wearable medical devices that perform continuous monitoring of ECG</span>.
Mohammad Haziq Bin Ishak, Mohd Syafiq Mispan, Yan Chiew Wong, Muhammad Raihaan Kamaruddin, and Mikhail Korobkov
IEEE
Arbiter-PUF is a promising candidate to provide security in resource-constrained Internet of Things (IoT) devices. However, Arbiter-PUF is vulnerable to modeling assaults. A promising technique that has been proposed in the past, known as a random challenge permutation technique, has advantages of low area overhead and resilience against ML-attack. However, the performance of this technique was only evaluated at the simulation level. Therefore, in this study, we implement an Arbiter-PUF with random challenge permutation technique on the Digilent Nexys-4 Artix-7 field-programmable gate array (FPGA) board. We prove that the susceptibility of conventional Arbiter-PUF against machine learning (ML) attacks reduce from ≈98% to ≈44% by implementing this technique. In addition, we also prove that the implementation of the random challenge permutation technique in FPGA introduced no area overhead in terms of the number of lookup tables (LUTs), slices, and flip-flops used.
Yee Tan, Yan Wong, and Syafeeza Radzi
ScopeMed
Joe Keek, , Ser Loh, Yan Wong, Xiu Woo, Wei Lee, , , , and
The Intelligent Networks and Systems Society
R. Nur Syahindah Husna, A. R. Syafeeza, Norihan Abdul Hamid, Y. C. Wong, and R. Atikah Raihan
Penerbit UTM Press
Autism Spectrum Disorders (ASDs) define as a scope of disability in the development of certain conditions such as social communication, imagination, and patients' capabilities to make some connection. In Malaysia, the number of ASD cases diagnosed is increasing each year. Typically, ASD patients are analyzed by doctors based on history and behavior observation without the ability to diagnose instantaneously. This research intends to study the ASD biomarker based on neuroimaging functional Magnetic Resonance Imaging (fMRI) images, which can aid doctors in diagnosing ASD. This study applies a deep learning method from Convolutional Neural Network (CNN) variants to detect either the patients are ASD or non-ASD and extract the robust characteristics from neuroimages in fMRI. Then, it interprets the performance of pre-processed images in the form of accuracy to classify the neural patterns. The Autism Brain Imaging Data Exchange (ABIDE) dataset was used to research the brain imaging of ASD patients. The results achieved using CNN models namely VGG-16 and ResNet-50 are 63.4% and 87.0% accuracy, respectively. This method also assists doctors in detecting Autism from a quantifiable method that is not dependent on the behavioral observations of suspected autistic children.
Chia Yee Saw, Yan Chiew Wong, Ser Lee Loh, and Haoyu Zhang
Universitas Ahmad Dahlan
Wireless sensor network (WSN) consists of distributed nodes deployed for monitoring the physical conditions and organizing collected data at the central control unit. Power consumption is the challenges in WSN as the network consists of wireless sensor nodes becomes denser. By utilizing WSN and visible light technology, a simple health monitoring system design can be approached that are smaller in size, faster and lower power consumption. This work focuses on design a low power optical wake-up receiver to reduce the energy consumption of each node in WSN. A wake-up receiver is designed to be always-on for detecting incoming signal and switches on the stand by protocol controller and WSN network for data transmission process. The characteristic of optical transmission and functional circuit of a wake-up receiver has been investigated. A low power optical wake-up receiver has been designed in 180nm Silterra CMOS process technology. The proposed wake-up receiver consumes only 443pW in standby mode and 1.89nW in active mode. The proposed optical wake-up receiver drastically reduces the power consumption by more than one third compared to other wake-up receivers which could be a milestone in the medical field if successfully conducted.
N A Bakhari, N A Hamid, A R Syafeeza, Y C Wong, and M Ibrahim
IOP Publishing
Abstract Recently, an interest of thermoelectric generator (TEG) to manipulate and change heat waste into electrical energy has increased. The heat from electrical appliances, sun, human body, and natural environments can convert into electrical energy using TEG. However, typical conventional TEGs in the market have a hard and solid construction structure, hence difficult to bend according to curved surfaces of the heat sources. To overcome this problem, polymer-based material is proposing as the new packaging and substrate structure for the TEG. Besides, the thermoelectric conductor layer also changed using different types of pyroelectric for better heat absorption performance with low cost in mass-scale fabrication. Therefore, the simulation of eight pairs segmented conductive layer insulated with thin-film polymer due to standard modelling equation is present. The comparison of simulation with reference TEG to get the optimum output of temperature difference were also explaining. At the end of the simulation, polyimide as a packaging substrate with a conductive layer of Graphene (P-type legs) and Bismuth Telluride (N-type legs) has chosen for the best performance material for the flexible thermoelectric generator. The highest temperature difference produced by this design is 542˚C for 0.945V input voltage and 120˚C input temperature at the hot side.
Yan Chiew Wong, Szi Hui Tan, Ranjit Singh Sarban Singh, Haoyu Zhang, A. R. Syafeeza, and N. A. Hamid
Institute of Advanced Engineering and Science
Wireless sensor network (WSN) consists of base stations and sensors nodes to monitor physical and environmental conditions. Power consumption is a challenge in WSN due to activities of nodes. High power consumption is required for the main transceiver in WSN to receive communication requests all the time. Hence, a low power wake-up receiver is needed to minimize the power consumption of WSN. In this work, a low power wake-up receiver using ultrasound data communication is designed. Wake-up receiver is used to detect wake-up signal to activate a device in WSN. Functional block modelling of the wake-up receiver is developed in Silterra CMOS 130nm process technology. The performance of the wake-up receiver has been analyzed and achieving low power consumption which is 22.45μW. A prototype to demonstrate a wireless sensor node with wake-up receiver has been developed incorporating both ultrasonic and RF for internal and external communication respectively. We achieve 99.97% of power saving for 10s operation in the experimental setup for the WSN with and without wake-up receiver. Wake-up receiver used in WSN save power and prolong the lifetime of batteries and thus extending the operational lifetime of WSN.
Alphonsos A Masius and Yan Chiew Wong
Elsevier BV
Jim Hui Yap and Yan Chiew Wong
Institute of Advanced Engineering and Science
This paper presents a fully-integrated on chip battery-less power management system through energy harvesting circuit developed in a 130nm CMOS process. A 30mV input voltage from a TEG is able to be boosted by the proposed Complementary Metal-Oxide-Semiconductor (CMOS) voltage booster and a dynamic closed loop power management to a regulated 1.2V. Waste body heat is harvested through Thermoelectric energy harvesting to power up low power devices such as Wireless Body Area Network. A significant finding where 1 Degree Celsius thermal difference produces a minimum 30mV is able to be boosted to 1.2V. Discontinuous Conduction Mode (DCM) digital control oscillator is the key component for the gate control of the proposed voltage booster. Radio Frequency (RF) rectifier is utilized to act as a start-up mechanism for voltage booster and power up the low voltage closed loop power management circuit. The digitally control oscillator and comparator are able to operate at low voltage 600mV which are powered up by a RF rectifier, and thus to kick-start the voltage booster.
Yan WONG
ScopeMed
Astrie Nurasyeila Fifie and Yan Chiew Wong
Universitas Ahmad Dahlan
A low dropout (LDO) voltage regulator with high power supply rejection ratio (PSRR) and low temperature coefficient (TC) is presented in this paper. Large 1µF off-chip load capacitor is used to achieve the high PSRR. However, this decreases the gain and pushes the LDO’s output pole to lower frequency causing the circuit to become unstable. The proposed LDO uses rail-to-rail folded cascode amplifier to compensate the gain and stability problems. 2nd order curvature characteristic is used in bandgap voltage reference circuit that is applied at the input of the amplifier to minimize the TC. The characteristic is achieved by implementing MOSFET transistors operate in weak and strong inversions. The LDO is designed using 0.18µm CMOS technology and achieves a constant 1.8V output voltage for input voltages from 3.2V to 5V and load current up to a 128mA at temperature between -40°C to 125°C. The proposed LDO is targeted for RF application which has stringent requirement on noise rejection over a broad range of frequency.
Astrie Nurasyeila Fifie Asli and Yan Chiew Wong
Institute of Advanced Engineering and Science
<span>This paper presents a high voltage conversion at high sensitivity RF energy harvesting system for IoT applications. The harvesting system comprises bulk-to-source (BTMOS) differential-drive based rectifier to produce a high efficiency RF energy harvesting system. Low-pass upward impedance matching network is applied at the rectifier input to increase the sensitivity and output voltage. Dual-oxide-thickness transistors are used in the rectifier circuit to maintain the power efficiency at each stage of the rectifier. The system is designed using 0.18µm Silterra RF in deep n-well process technology and achieves 4.07V output at -16dBm sensitivity without the need of complex auxiliary control circuit and DC-DC charge-pump circuit. The system is targeted for urban environment.</span>
Mohammed Abdul Raheem Esmail Alselwi, Yan Chiew Wong, and Zul Atfyi Fauzan Mohammed Napiah
Institute of Advanced Engineering and Science
This article presents a review of the CMOS rectifier for radio frequency energy harvesting application. The on-chip rectifier converts the ambient low-power radio frequency signal coming to antenna to useable DC voltage that recharges energy to wireless sensor network (WSN) nodes and radiofrequency identification (RFID) tags, therefore the rectifier is the most important part of the radio frequency energy harvesting system. The impedance matching network maximizes power transfer from antenna to rectifier. The design and comparison between the simulation results of one- and multi-stage differential drive cross connected rectifier (DDCCR) at the operating frequencies of 2.44GHz, and 28GHz show the output voltage of the multi-stage rectifier doubles at each added stage and power conversion efficiency (PCE) of rectifier at 2.44GHz was higher than 28GHz. The (DDCCR) rectifier is the most efficient rectifier topology to date and is used widely for passive WSN nodes and RFID tags.