UniMAP RIS :: Browsing Publications 2019 by Department "Universiti Malaysia Perlis"

Publication

A 28 GHz 0.18-μm CMOS cascade power amplifier with reverse body bias technique

( 2019-08-01)

;

A 28 GHz power amplifier (PA) using CMOS 0.18 μm Silterra process technology is reported. The cascade configuration has been adopted to obtain high Power Added Efficiency (PAE). To achieve low power consumption, the input stage adopts reverse body bias technique. The simulation results show that the proposed PA consumes 32.03mW and power gain (S21) of 9.51 dB is achieved at 28 GHz. The PA achieves saturated power (Psat) of 11.10 dBm and maximum PAE of 16.55% with output 1-dB compression point (OP1dB) 8.44 dBm. These results demonstrate the proposed power amplifier architecture is suitable for 5G applications.

6 36

Publication

A Fuzzy-Based Angle-of-Arrival Estimation System (AES) Using Radiation Pattern Reconfigurable (RPR) Antenna and Modified Gaussian Membership Function

( 2019-01-01)

Jais M.I.

;

Thennarasan Sabapathy

;

Muzammil Jusoh

;

R Badlishah Ahmad

;

Jamaluddin M.H.

;

Kamarudin M.R.

;

Ehkan P.

;

Murukesan Loganathan L.

;

Soh P.J.

Angle-of-arrival (AOA) estimation is an important factor in various wireless sensing applications, especially localization systems. This paper proposes a new type of AOA estimation sensor node, known as AOA-estimation system (AES) where the received signal strength indication (RSSI) from multiple radiation pattern reconfigurable (RPR) antennas are used to calculate the AOA. In the proposed framework, three sets of RPR antennas have been used to provide a coverage of 15 regions of radiation patterns at different angles. The salient feature of this RPR-based AOA estimation is the use of Fuzzy Inferences System (FIS) to further enhance the number of estimation points. The introduction of a modified FIS membership function (MF) based on Gaussian function resulted in an improved 85% FIS aggregation percentage between the fuzzy input and output. This later resulted in a low AOA error (of less than 5%) and root-mean-square error (of less than 8°).

46 1

Publication

A general framework for improving electrocardiography monitoring system with machine learning

( 2019-03-01)

Khairuddin A.M.

;

Ku Nurul Fazira Ku Azir

;

Eh Kan P.

As one of the most important health monitoring systems, electrocardiography (ECG) is used to obtain information about the structure and functions of the human heart for detecting and preventing cardiovascular disease. Given its important role, it is vital that the ECG monitoring system provides relevant and accurate information about the heart. Over the years, numerous attempts were made to design and develop more effective ECG monitoring system. Nonetheless, the literature reveals not only several limitations in conventional ECG monitoring system but also emphasizes on the need to adopt new technology such as machine learning to improve the monitoring system as well as its medical applications. This paper reviews previous works on machine learning to explain its key features, capabilities as well as presents a general framework for improving ECG monitoring system.

Publication

A Review on the efficiency and accuracy of localization of moisture distributions sensing in agricultural silos

( 2019-12-03)

Almaleeh A.A.

;

Ammar Zakaria

;

Zakaria S.M.M.S.

;

Latifah Munirah Kamarudin

;

Mohd Hafiz Fazalul Rahiman

;

Sukor A.S.A.

;

Yuzairi Abdul Rahim

;

Abdul Hamid Adom

The moisture distribution in the silos depends upon various seeds parameters such as type and size of seeds, amount of storage, external weather, and storage period as well as structural and environmental factors. It is very difficult to predict moisture distribution in silos effectively while taking all the above aspects into consideration. This study aims to investigate the efficiency and accuracy of localization of moisture distributions sensing in agricultural silo. The work is mainly focussed on three major elements: Radio Frequency (RF), tomographic imaging and classification process using machine learning. In particular, RF-based signal and volume tomographic images are used to predict the moisture distribution. Furthermore, computational intelligence techniques such as artificial neural network (ANN) is applied to develop models based on previous data. The generalization of these models towards new set of data is discussed in making sure a successful application of a model. A detailed study of the relative performance of computational intelligence techniques has been carried out based on different statistical performance criteria.

2 30

Publication

A study of two dimensional metal carbide MXene Ti3C2 synthesis, characterization conductivity and radiation properties

( 2019-01-01)

Rasid Z.A.M.

;

Omar M.F.

;

Muhammad Firdaus Mohd Nazeri

;

Saidi S.A.

;

Sandu A.V.

;

Mohd. Mustafa Al Bakri Abdullah

Since the discovery of exceptional properties of graphene, a lot of researchers focused on the discovery of another nobel two-dimensional (2D) materials. Recently, an elegant exfoliation approaches was proposed as a method to synthesis a new family of transitional 2D metal carbide or nitrades of MXene from a layered MAX phase. A layered MAX phase of Ti3AlC2 was synthesized through pressureless sintering (PLS) the initial powder of 3TiH2/1.1Al/2C without preliminary dehydrogenation under argon atmosphere at 1350°C. An elegant exfoliation approach was used to eliminates Al from its precursor to form a layered-structure of Ti3C2. In this study, thermal conductivity of MAX phase and MXene were studied using absolute axial heat flow method to measure the abilities sample to conduct heat and the data was collected using Picolog 1216 Data Logger. Electrical conductivity of these two materials was also compared by using two-point probe, due to its simplicity. Radiation properties of 2D MXene Ti3C2 was studied by using an established radon monitor, placed in closed, fabricated container. Morphological and structural properties of this 2D material were also studied using an established FESEM and XRD apparatus. SEM images shows two types of morphology which is a layer of Ti3C2 and the agglomerates Al2O3 with graphite. XRD pattern reveals three phases in this material which is a rhombohedral Al2O3, rhombohedral graphite and rhombohedral Ti3C2 phases, respectively. Thermal and electrical conductivity of MXene were proven higher than MAX phase. Radon concentration for this material for five consecutive days explains the radiation level of this material which is under the suggestion value from US Environmental Protection Agency (EPA). From this finding, it is can conveniently say that the MXene material can be promising material for electronic application.

Publication

Aluminosilicate Nanocomposite on Genosensor: A Prospective Voltammetry Platform for Epidermal Growth Factor Receptor Mutant Analysis in Non-small Cell Lung Cancer

( 2019-12-01)

Ramanathan S.

;

Subash Chandra Bose Gopinath

;

Mohd Khairuddin Md Arshad

;

Prabakaran A/L Poopalan

;

Anbu P.

;

Lakshmipriya T.

;

Kasim F.H.

Lung cancer is one of the most serious threats to human where 85% of lethal death caused by non-small cell lung cancer (NSCLC) induced by epidermal growth factor receptor (EGFR) mutation. The present research focuses in the development of efficient and effortless EGFR mutant detection strategy through high-performance and sensitive genosensor. The current amplified through 250 µm sized fingers between 100 µm aluminium electrodes indicates the voltammetry signal generated by means of the mutant DNA sequence hybridization. To enhance the DNA immobilization and hybridization, ∼25 nm sized aluminosilicate nanocomposite synthesized from the disposed joss fly ash was deposited on the gaps between aluminium electrodes. The probe, mutant (complementary), and wild (single-base pair mismatch) targets were designed precisely from the genomic sequences denote the detection of EGFR mutation. Fourier-transform Infrared Spectroscopy analysis was performed at every step of surface functionalization evidences the relevant chemical bonding of biomolecules on the genosensor as duplex DNA with peak response at 1150 cm−1 to 1650 cm−1. Genosensor depicts a sensitive EGFR mutation as it is able to detect apparently at 100 aM mutant against 1 µM DNA probe. The insignificant voltammetry signal generated with wild type strand emphasizes the specificity of genosensor in the detection of single base pair mismatch. The inefficiency of genosensor in detecting EGFR mutation in the absence of aluminosilicate nanocomposite implies the insensitivity of genosensing DNA hybridization and accentuates the significance of aluminosilicate. Based on the slope of the calibration curve, the attained sensitivity of aluminosilicate modified genosensor was 3.02E-4 A M−1. The detection limit of genosensor computed based on 3σ calculation, relative to the change of current proportional to the logarithm of mutant concentration is at 100 aM.

1 21

Publication

Ambient Cues of Kitchen Counter in Guiding Cooking Activities for Alzheimer's Patient

( 2019-03-01)

Basharudin N.W.

;

Ku Nurul Fazira Ku Azir

;

Khairuddin A.M.

;

Ehkan P.

Loss of memory is among the first symptoms reported by patients suffering from Alzheimer's disease (AD). The individual pattern of impaired memory functions correlates with functional brain integrity will result in the inability of the patient to complete a particular task. This research focuses on designing the ambient cues in the kitchen counter to guide Alzheimer's patient to complete cooking activities based on the concept of Stimulus-Response Compatibility (SRC) and whereas the activity is focus on the sequential workflow of cooking activities based on the Hierarchical Task Analysis (HTA). Wizard-of-Oz is used to simulate the behavior of theoretical intelligent ambient cues. The results show with the aid of ambient cues in the kitchen, patient be able to complete the task until the end even if there is confusing or disruption in the middle of the activity. The effectiveness of ambient cues show that patient can easily understood the cues of guiding the cooking flow when mistakes happened.

Publication

An overview of the fundamental approaches that yield several image denoising techniques

( 2019-12-01)

Charmouti B.

;

Ahmad Kadri Junoh

;

Mashor M.Y.

;

Ghazali N.

;

Wahab M.A.

;

Wan Muhamad W.Z.A.

;

Yahya Z.

;

Beroual A.

Digital image is considered as a powerful tool to carry and transmit information between people. Thus, it attracts the attention of large number of researchers, among them those interested in preserving the image features from any factors that may reduce the image quality. One of these factors is the noise which affects the visual aspect of the image and makes others image processing more difficult. Thus far, solving this noise problem remains a challenge for the researchers in this field. A lot of image denoising techniques have been introduced in order to remove the noise by taking care of the image features; in other words, getting the best similarity to the original image from the noisy one. However, the findings are still inconclusive. Beside the enormous amount of researches and studies which adopt several mathematical concepts (statistics, probabilities, modeling, PDEs, wavelet, fuzzy logic, etc.), there is also the scarcity of review papers which carry an important role in the development and progress of research. Thus, this review paper intorduce an overview of the different fundamental approaches that yield the several image-denoising techniques, presented with a new classification. Furthermore, the paper presents the different evaluation tools needed on the comparison between these techniques in order to facilitate the processing of this noise problem, among a great diversity of techniques and concepts.

25 2

Publication

Analysis particle trajectory and air flow on hopper for swiftlet feeding machine using computational fluid dynamics (CFD)

( 2019-07-30)

Radhwan Hussin

;

Shayfull Zamree Abd. Rahim

;

Muhamad Farizuan Rosli

;

Effendi M.S.M.

;

Irfan Abd Rahim

Currently, the bird house entrepreneur feeds the bird manually, and there is the opportunity to develop the feeding machine for swiftlets with good efficiency. This research is focused on analyzing the flow of the particle for the mechanism of the machine. The methodology of this project includes the collection of data, brainstorming and interprets data, design concept, analysis, fabrication, and testing. The design of the automatic swiftlets feeding machine is using Solidworks software. With this software, the structure can be analyzed to Finite Element Analysis (FEA) directly. The flow of the air from the blower that acts as the mechanism in this machine can be analyzed by using the Computational Fluid Dynamis (CFD) simulation. The result of the analysis is shown in the form of the finite element analysis, particle trajectory of food, and the air flow from the blower.

1 27

Publication

Analysis performance on original Wing 2 HLK168 drone controller using DFMA approach

( 2019-07-30)

Farahin K.

;

Muhamad Farizuan Rosli

;

Radhwan Hussin

This project explores the design enhancements by applying the techniques of Manufacturing and Assembly Design (DFMA). This project explores the design enhancements by applying the techniques of Manufacturing and Assembly Design (DFMA). The drone control components were isolated to obtain data. By using the Boothroyd-Dewhurst method, the data obtained will be analyzed to verify the design efficiency during manual handling and manual insertion time. Using the Computer Aided Three-Dimensional Application (CATIA) software, the components of the original and improvement products were separated and drawn. The data next that have been generated by differentiate these two products is next been analysed. Through the analysis, the results tell that the design efficiency of enhancement product is better than the existing design. This is because of the reducing in number of parts, manual handling and manual insertion times and also due to the design costs. Finally, the improvement in the design of the drone control can meet the needs of consumers and may providing satisfaction to them.

18 1

Publication

Bandwidth and gain enhancement of a circular microstrip antenna using a DNG split ring resonator radome

( 2019-06-01)

Rasheed O.

;

Mohd Aminudin Jamlos

;

Soh Ping Jack

;

Jamlos M.

;

Muzamir Isa

This paper present the design of a circular patch microstrip antenna with enhancement in terms of bandwidth and gain using a dielectric double negative (DNG) split ring metamaterial radome. This radome is positioned on top of the CP antenna operating from 5.2 GHz to 6.4 GHz. The metamaterial radome comprises of two alternate split rings of negative permittivity, permeability and refractive index. The circular microstrip antenna bandwidth of 430 MHz has been realized by the presence of DNG metamaterial radome compared to 220 MHz without the radome. The gain has been increased as well from 1.84 dBi to 3.87 dBi.

1 32

Publication

Compact broadband triple-ring five-port reflectometer for microwave brain imaging applications

( 2019-01-01)

Hossain T.M.

;

Jamlos M.F.

;

Mohd Aminudin Jamlos

;

Soh Ping Jack

;

Ibrahim S.Z.

;

Muammar Mohamad Isa

;

Schreurs D.M.M.P.

;

Narbudowicz A.

;

Mohd Fathullah Ghazli@Ghazali

The broadband five-port reflectometer (FPR) is proposed using a triple-ring based technique. The design introduces a tapering in the inter-ring transmission lines (TLs), which provides additional degrees of freedom for optimization and contributes to increased bandwidth. The miniaturization strategy allows incorporating the third ring without significant size increase. In addition, a method for expressing the effective physical dimension of a planar symmetric FPR is also presented in an easily comprehensible way, which can be implemented for other symmetric planar junctions with more than four ports. The proposed design comprises three concentric rings with phase-shifting arrangements between the inter-ring TLs and outer matching arm sections. Inter-ring TLs are shifted by 36° (half factorized value of the inter-port angular distance of 72°) in three different optimizing steps. Tapered TLs have been used between two consecutive rings to achieve very wide bandwidth of at least 88% in simulations and at least 85% in measurements. Curved matching TLs are used in the final design, yielding a compact size of 0.397λg × 0.377 λg with 43% reduction in length and 43% in width compared to its non-compact counterpart. Genetic algorithm and quasi-Newton algorithm are used in optimizing the final prototype for operation in the frequency band used for brain microwave imaging. The proposed FPR realized a fractional bandwidth of at least 85% (from 0.96 to 2.38 GHz) with a reflection coefficient below-20 dB and a-6 ± 1 dB transmission coefficient with the required phase shift of ±120° between different ports. The measured results agree well with the simulation. Finally, the overall imaging system setup and image construction algorithm are presented and discussed for possible incorporation with this FPR for brain microwave imaging.

22 16

Publication

Computational fluid dynamic (CFD) of air conditioning system for human thermal comfort analysis: A simulation study

( 2019-04-08)

Ali A.M.

;

Shazmin Aniza Abdul Shukor

;

Rahim N.A.

;

Zuradzman Mohamad Razlan

;

Zul Azhar Zahid Jamal

;

Kohlhof K.

Human thermal comfort is very important especially in an indoor environment because it may effect human's health and welfare. Air conditioning (AC) system has become a necessary tool for indoors to maintain human comfort. This is especially applied to places with high strength of solar radiation, high relative humidity, high air temperature, and low air speed areas which are considered the most critical climate effect for indoors such as in Thailand, Malaysia, and Singapore. However, the current mechanism of the AC system allows the user to set it into maximum cooling, i.e. at the lowest temperature with highest fan speed. This setting does not necessarily create a thermally comfortable environment inside the room, but could contribute towards negative impact to human. Thus, there is a need to study the possibility of integrating the element of thermal comfort with the AC system. This project will concentrate on a case study of the effect of AC towards human thermal comfort in an indoor environment by using computational fluid dynamic (CFD) flow simulation. It adapts an enhanced Predicted Mean Vote (PMV)-based algorithm in creating the thermal comfort environment. The simulation uses SOLIDWORKS software and concentrates on a small sized room with one person doing sedentary work. The flow simulation is done on four conditions-maximum cooling setting and other three that is based on the enhanced PMV algorithm, which were then analyzed and compared. Based on the results, it is shown that the enhanced PMV-based algorithm could provide a thermally comfortable environment compared to the maximum cooling setting.

1 30

Publication

Determination of blind spot zone for motorcycles

( 2019-12-02)

Mohd Sani Mohamad Hashim

;

Hamati A.A.A.

;

Mohd Hafzi M.I.

;

Shahriman Abu Bakar

;

Abdul Halim Ismail

;

Muhamad Safwan Muhamad Azmi

;

Azizi Harun

;

Zuradzman Mohamad Razlan

;

Nur Saifullah Kamarrudin

;

Ishak Ibrahim

;

Mohd Khairul Faizi Abd Rahman

;

Mohd Asrul Md Saad

;

Mohd Afendi Rojan

The problem of the blind spot zone (BSZ) for motorcycles is common, as it causes many accidents that occur between motorcycles and cars, or motorcycles with other vehicles. The problem of BSZ is occurring for many reasons, such as if the motorcyclist wants to change the lane or manoeuvre or turn without realizing the presence of other vehicle which may cause a terrible collision and leads to casualties, either because of darkness, the full dependence on side mirrors that give a limited scope of vision, or due to a malfunction in the front lights of the car that prevented the motorcyclists from recognizing it. However there were limited research on identifation of BSZ for motorcycle, even though most vehicle accidents in Malaysia involved motorcycles. This paper discusses the initial works on the identification of BSZ for motorcyles. Three types of motorcycles were used to determine the BSZ using grid-based technique. From the data collected, the BSZ was identified for the motorcycles.

2

Publication

Digital image watermarking algorithm based on texture masking model

( 2019-01-01)

Taha D.B.

;

Taha T.B.

;

Al Dabagh N.B.

;

Ruzelita Ngadiran

;

Ehkan P.

The trade-off between invisibility and robustness in image watermarking algorithms is considered as one of the major issues in designing watermark-based copyright protection systems. Accordingly, different models had been proposed in the literature to obtain robust watermarked images while maintaining the perceptual quality. However, most of these studies are involved with complex algorithms as using multiple signal transformation tools within hybrid systems. In this paper, a low complexity texture-masking model based on Lifting Wavelet Transform (LWT) is utilized to find the blocks with the highest texture and choose them for watermark embedding. Choosing highly textured places helps to insert the watermark with a further intensity that leads to higher robustness and at the same time the Human Visual System (HVS) is less sensitive to changes in these areas. As a result, high quality watermarked images were produced in terms of objective and subjective evaluations, as the structural similarity value (SSIM) for tested images was larger than 0.99.

43 1

Publication

Distance weighted K-means algorithm for center selection in training radial basis function networks

( 2019-03-01)

Aik L.E.

;

Hong T.W.

;

Ahmad Kadri Junoh

The accuracies rates of the neural networks mainly depend on the selection of the correct data centers. The K-means algorithm is a widely used clustering algorithm in various disciplines for centers selection. However, the method is known for its sensitivity to initial centers selection. It suffers not only from a high dependency on the algorithm's initial centers selection but, also from data points. The performance of K-means has been enhanced from different perspectives, including centroid initialization problem over the years. Unfortunately, the solution does not provide a good trade-off between quality and efficiency of the centers produces by the algorithm. To solve this problem, a new method to find the initial centers and improve the sensitivity to the initial centers of K-means algorithm is proposed. This paper presented a training algorithm for the radial basis function network (RBFN) using improved K-means (KM) algorithm, which is the modified version of KM algorithm based on distance-weighted adjustment for each centers, known as distance-weighted K-means (DWKM) algorithm. The proposed training algorithm, which uses DWKM algorithm select centers for training RBFN obtained better accuracy in predictions and reduced network architecture compared to the standard RBFN. The proposed training algorithm was implemented in MATLAB environment; hence, the new network was undergoing a hybrid learning process. The network called DWKM-RBFN was tested against the standard RBFN in predictions. The experimental models were tested on four literatures nonlinear function and four real-world application problems, particularly in Air pollutant problem, Biochemical Oxygen Demand (BOD) problem, Phytoplankton problem, and forex pair EURUSD. The results are compared to proposed method for root mean square error (RMSE) in radial basis function network (RBFN). The proposed method yielded a promising result with an average improvement percentage more than 50 percent in RMSE.

Publication

Effect of graphene oxide on microstructure and optical properties of TiO2 thin film

( 2019-01-01)

Azani A.

;

Dewi Suriyani Che Halin

;

Razak K.A.

;

Mohd. Mustafa Al Bakri Abdullah

;

Mohd Salleh M.A.A.

;

Abdul Razak M.F.S.

;

Norsuria Mahmed

;

Ramli M.M.

;

Ayu Wazira Azhari

;

Chobpattana V.

GO/TiO2 thin films have been synthesized from titanium (IV) isopropoxide (TTIP) by a sol-gel method. The films were deposited onto a glass substrate using spin coating deposition technique then were subjected to annealed process at 350 °C. The different amount of graphene oxide (GO) was added into the parent solution of sol in order to investigate the microstructure, topography, optical band gap and photocatalytic activity of the thin films. The prepared thin films were characterized by atomic force microscopy (AFM), scanning electron microscopy (SEM), UV-VIS spectrophotometry and degradation of methylene blue (MB). AFM images reveal a rougher surface of GO/TiO2 thin film than bare TiO2 thin film due to GO particles. Moreover, the SEM images showed the formation of semispherical microstructure of bare TiO2 changes to some larger combined molecules with GO addition. The UV-Vis spectrophotometer results show that with optical direct energy gap decreases from 3.30 to 3.18 eV after GO addition due to the effect of high surface roughness and bigger grain size. Furthermore, the optical results also indicated that GO improved the optical properties of TiO2 in the visible range region.

1 29

Publication

Gain enhancement of microstrip patch antenna using artificial magnetic conductor

( 2019-03-01)

Norfatihah Bahari

;

Jamlos M.F.

;

Muammar Mohamad Isa

The paper presents an artificial magnetic conductor (AMC) structure to enhance the gain of the double microstrip patch antenna. By placing this kind of metamaterial in between the two Rogers RT5880 substrates, the antenna achieved lots of improvement especially in terms of size miniaturization, bandwidth, return loss, gain and efficiency. The antenna is intended to operate at 16 GHz where the prospect fifth generation (5G) spectrum might be located. Integration of AMC structure into the proposed antenna helps to improve nearly 16.3% of gain and almost 23.6% of size reduction.

28 1

Publication

Human Location Classification for Outdoor Environment

( 2019-12-03)

Talib M.T.M.

;

Mohd Hafiz Fazalul Rahiman

;

Latifah Munirah Kamarudin

;

Nishizaki H.

;

Ammar Zakaria

Outdoor localisation can offer great capabilities in security and perimeter surveillance applications. The localisation of people become more challenges when involving with the nonlinear environment. GPS and CCTV are two localisation techniques usually use to localise human in an outdoor environment. However, they have weaknesses which result in low localisation accuracy. Therefore, the application of Device-free localisation (DFL), together with the Internet of things (IoT) is more appropriate due to their capability to detect the human body in all environmental conditions, and there is no problem losing signals as faced by GPS. This system offers excellent potential in humans localisation because humans can be detected wirelessly without any tracking device attached. In developing the DFL system, the main concern is the localisation accuracy. Although the existing DFL system gives significant result to the localisation, the accuracy is still low due to the large variation in RSSI values. Hence, a Radio Tomographic Imaging-based ANN classification (RTI-ANN) approach is proposed to increase the localisation accuracy. This Artificial Neural Network (ANN) is designed to learn the Radio Tomography imaging (RTI) input for classification purpose. Even though the RTI gives a good result to the localisation, however, it suffers from smearing effect. To eliminates this smearing area and background noise, pre-processing of the RTI image is required. Thus, extracting the valuable information technique from the RTI image has been proposed. By extracting the valuable information data from the RTI image, about 61% to 66% of the smearing noise is removed depending on the size of the RTI image. Only data directly associated with human attenuation used for training and learning of ANN. The experimental results show ANN system can localise human in the right zone for a given dataset.

Publication

Investigating the Applicability of Several Fuzzy-Based Classifiers on Multi-Label Classification

( 2019-01-01)

Al-luwaici M.

;

Ahmad Kadri Junoh

;

Ahmad F.K.

: In the last few decades, fuzzy logic has been extensively used in several domains such as economy, decision making, logic and classification. In specific, fuzzy logic which is a powerful mathematical representation has shown a superior performance with uncertainty real-life applications comparing with other learning approaches. Many researchers utilized the concept of fuzzy logic in solving the traditional single label classification problems of both types: binary classification and multi-class classification. Unfortunately, veiy few researches have utilized fuzzy logic in a more general type of classification that is called Multi-Label Classification (MLC). Hence, this study aims to examine the applicability of fuzzy logic to be used with MLC through evaluating several fuzzy-based classifiers on five different multi-label datasets. The results revealed that the utilizing fuzzy-based classifiers on solving the problem of MLC is promising comparing with a wide range of MLC algorithms that belong to several learning approaches and strategies.

1 25

Publications 2019

Permanent URI for this collection

Browse

Browse

Browsing Publications 2019 by Department "Universiti Malaysia Perlis"

Results Per Page

Sort Options