School of Mechatronic Engineering (Articles)http://dspace.unimap.edu.my:80/xmlui/handle/123456789/21582024-03-29T09:31:23Z2024-03-29T09:31:23ZAtrial Fibrillation Identification through ECG SignalsNg Joe, YeeVikneswaran, VijeanSaidatul Ardeenawatie, AwangChong Yen, FookLim Chee, Chinhttp://dspace.unimap.edu.my:80/xmlui/handle/123456789/690332020-12-16T08:34:57Z2019-01-01T00:00:00ZAtrial Fibrillation Identification through ECG Signals
Ng Joe, Yee; Vikneswaran, Vijean; Saidatul Ardeenawatie, Awang; Chong Yen, Fook; Lim Chee, Chin
This paper presents an algorithm formulated to identify the atrial fibrillation
complications through electrocardiogram (ECG) signals. The ECG data for the study was
retrieved from Physio Net which consists of normal, atrial fibrillation and other rhythms. The
Discrete Wavelet Transform (DWT) was used to remove baseline wanders. Pan Tompkins
algorithm was utilized to detect the P, Q, R, S and T peak and thus the ECG signals were
segmented based on each cycle. The morphological features were extracted directly from the
time-series while statistical features were extracted after Stockwell transform (S- transform) was
applied to the data. Genetic Algorithm (GA) and reliefF algorithm have been applied separately
to select the optimum features for classification purpose. Bagged Tree ensemble algorithm,
Decision Tree and k-Nearest Neighbour (KNN) algorithm were used as classifiers to identify
atrial fibrillation through ECG signals. The classification results with and without feature
selection techniques are presented. Prior to the feature selection, Bagged Tree is the classifier
best performing classifier with 86.50% of accuracy, 84.38% of sensitivity and 91.94% of
specificity. After feature selection, all the three classifiers have almost the same performance
which is nearly 100% of accuracy, sensitivity and specificity. This shows that the proposed
combinations of algorithms are reliable and able to improve the identification rate of the normal,
atrial fibrillation and other rhythms using lesser number of features.
Link to publisher's homepage at https://iopscience.iop.org/
2019-01-01T00:00:00ZDifferentiate Characteristic EEG Tobacco Smoking and NonsmokingLim Chee, ChinAsmiedah, Muhamad ZazidChong Yen, FookVikneswaran, VijeanSaidatul Ardeenawatie, AwangMarwan, AffandiLim Sin, Chehttp://dspace.unimap.edu.my:80/xmlui/handle/123456789/690322020-12-16T08:34:28Z2019-01-01T00:00:00ZDifferentiate Characteristic EEG Tobacco Smoking and Nonsmoking
Lim Chee, Chin; Asmiedah, Muhamad Zazid; Chong Yen, Fook; Vikneswaran, Vijean; Saidatul Ardeenawatie, Awang; Marwan, Affandi; Lim Sin, Che
Electroencephalogram (EEG) signal is non-stationary signal that have low frequency component and amplitude compared to stationary signal. Therefore, present of unwanted substance (nicotine) in Tobacco smoking will alter the brain electrical activity. This paper is proposed to investigate the changes of EEG signal with the present of nicotine and identify the difference brain signal between smoker and non-smoker. There are 20 males (10 smokers, 10 non-smokers) are selected. The subjects are
chosen based on inclusion criteria (abstained from smoking within 6 hours before experiment, and do not
take any medication and caffeine). The recorded EEG signal contain a lot of noise such as head moving,
muscle movement, power line, eyes blinks and interference with other device. Butterworth filter are
implemented to remove the unwanted noise present in the original signal. Bandpass filter is used to
decompose the EEG signal into alpha, theta, delta and beta frequency. Then, eight features (mean,
median, maximum, minimum, variance, standard deviation, energy and power) have been extracted by
using Fast Fourier Transform (FFT) and Power Spectral Density (PSD) method. Then, four different type
of kernel function (‘Linear’, 'BoxConstraint', ‘Polynomial’ and ‘RBF’) of SVM classifier are used to
identify the best accuracy. As a result, PSD (97.50%) have higher performance accuracy than FFT
(97.33%) by using Radial Basis Function (RBF) of Support Vector Machine (SVM). Smoking activity
caused slightly increase theta and delta frequency. Smoking is activated of five electrode channels (Fp1,
Fp2, F8, F3 and C3) and caused additional emotion such as deep rest, stress releasing and losing
attention. The attention of smokers can be measure by using stroop test. After smoking activity, smokers
become more energetic and increase the time response (1.77 s) of stroop test compared to non-smokers
(2.96 s). The result is calculated by using statistical analysis (t-test). The p-value is 0.037 which is less
than 0.05. Thus, the null hypothesis is rejected and conclude there is significant different between
smokers and non-smoker performance before and after smoking task.
Link to publisher's homepage at https://iopscience.iop.org/
2019-01-01T00:00:00ZDesign and Fabrication of Biodegradable Microneedle Using 3D Rapid Prototyping PrinterNur Hazwani Azyan, MansorMarni Azira, MarkomErdy Sulino, Mohd Muslim TanAbdul Hamid, Adomhttp://dspace.unimap.edu.my:80/xmlui/handle/123456789/690312020-12-16T08:34:03Z2019-01-01T00:00:00ZDesign and Fabrication of Biodegradable Microneedle Using 3D Rapid Prototyping Printer
Nur Hazwani Azyan, Mansor; Marni Azira, Markom; Erdy Sulino, Mohd Muslim Tan; Abdul Hamid, Adom
Microneedle is known as transdermal drug delivery (TDD) devices that uses to deliver biological fluid into veins and needle that use to tear skin to collect blood sample. It involves with various parameters and designs. This device gain attention as its benefit can eliminate pain and more convenient compared to intravenous injection due to its micron size. Typically,
microneedle is fabricated using MEMS technology. However, this technology requires few
processes such as deposition, etching and moulding, as well as consume much times. This paper
presents a work of design and fabrication of solid microneedle using 3D rapid prototype printing.
A few types of microneedles are designed and they are analysed in terms of stress and force
characteristics. Also, it will study the ability of a few materials to withstand stress while force
exerted on it. The selected materials are polyvinyl alcohol (PVA), polylactic acid (PLA),
polyester resin and acrylonitrile butadiene styrene (ABS). The results show that PVA has the
highest ability to withstand force compared other materials. As conclusion, the design and
fabrication of microneedle using 3D rapid prototyping printer is succeed using PVA material and
real post-analysis can be conducted to test the capability for medical practice.
Link to publisher's homepage at https://iopscience.iop.org/
2019-01-01T00:00:00ZInternet of Things (IoT) Fall Detection using Wearable SensorLoh Mei, YeeLim Chee, ChinChong Yen, FookMaslia, DaliShafriza Nisha, Basahhttp://dspace.unimap.edu.my:80/xmlui/handle/123456789/690302020-12-16T08:33:27Z2019-01-01T00:00:00ZInternet of Things (IoT) Fall Detection using Wearable Sensor
Loh Mei, Yee; Lim Chee, Chin; Chong Yen, Fook; Maslia, Dali; Shafriza Nisha, Basah
The IoT fall detection system detects the fall through the data classification of
falling and daily living activity. It includes microcontroller board (Arduino Mega 2560),
Inertial Measurement Unit sensor (Gy-521 mpu6050) and WI-FI module (ESP8266-01). There
total ten (10) subjects in this project. The data of falling and non-falling (daily living activity)
can be identified. The falling is the frontward fall, while the daily living activity includes
standing, sitting, walking and crouching. K-nearest neighbour (k-NN) classifiers were used in
the data classification. The accuracy of k-NN classifiers were 100% between falling and nonfalling class. The feature was selected based on the percentage of accuracy of the k-NN
classifier. The features of the Aareal.z (97.14%) and Angle.x (97.24%) were selected due to
the good performance during the classification of the falling and non-falling class. The
performance of the Aareal.z (58.41%) and Angle.x (57.78%) were satisfactory during the subclassification of the non-falling class. Hence, the feature of Aareal.z and Angle.x were
selected as the features which were implemented in the IoT fall detection device.
Link to publisher's homepage at https://iopscience.iop.org/issue/1742-6596/1372/1
2019-01-01T00:00:00Z