Syed Zulkarnain Syed Idrus
Thumbnail Image
Preferred name
Syed Zulkarnain Syed Idrus
Official Name
Syed Zulkarnain, Syed Idrus
Alternative Name
Syed Idrus, Syed Zulkarnain
Idrus, Syed Zulkarnain Syed
Idrus, S. Z.S.
Syed Idrus, S. Z.
Idrus, Syed Zulkarnain Bin Syed
Main Affiliation
Scopus Author ID
57215416897

Research Output

Filters

3
18
Reset filters

Settings
Now showing 1 - 10 of 18
  • Publication
    Correlation Impact by Random Forest towards Prediction of Phishing Website
    ( 2020-09-21)
    Mardhiah Ishak A.
    ;
    Mustapha A.
    ;
    Syed Zulkarnain Syed Idrus
    ;
    Helmy Abd Wahab M.
    ;
    Mostafa S.A.
    Phishing is an online identity theft that lure unsuspecting victims into phishing website that asks for their personal information such as financial credentials or online access. The most obvious phishing attacks use spam emails to lure victims into visiting its phishing website. The less obvious attack is when a phisher spoofes legitimate sites to bring the victims to the phishing website by presenting a visually similar websites. To address this issue, this paper focuses on the effectiveness of the Random Forest algorithm in predicting a website whether a phishing or lieitimate website. The prediction model is developed using the classfication methodology and the results revealed that the prediction accuracy of Random Forest in only 66.66%. This is due to potential high correlation among the features when training the dataset since each Random Tree in the forest should protect each other from individual errors. In the future, this project is hoped to investigate features selection of the same dataset because the phishing website prediction model requires features that at least some predictive power.
  • Publication
    A Review of Human Graphology Analysis and Brainwaves
    ( 2020-09-21)
    Akila N.F.
    ;
    M Nasir E.M.N.E.
    ;
    Fuad N.
    ;
    Helmy Abd Wahab M.
    ;
    Syed Zulkarnain Syed Idrus
    This paper will do a study about brain, electroencephalograph (EEG) and also brainwriting. There are four types of frequency bands produces by human brain like delta, alpha, beta and theta. Every bands have their own spectrum of frequency where it be used for analysing brain activities. Electroencephalogram (EEG) is a method to measure signal by studying and evaluating the pattern of the brainwaves. The neuron will transfer the signals in the brain and the populations of neurons form pattern of network that form a brainwaves detectable in EEG. While graphology analysis is about the handwriting pattern that will illustrate the personality traits of the person. Everything that is written by the hand is processed from brain where is can give certain frequency bands or waveform for the personality.
  • Publication
    Crude Oil Price Forecasting Using Hybrid Support Vector Machine
    ( 2020-09-21)
    Jo Xian L.
    ;
    Ismail S.
    ;
    Mustapha A.
    ;
    Helmy Abd Wahab M.
    ;
    Syed Zulkarnain Syed Idrus
    Crude oil price is strongly impacting the world economy. However, it is very fluctuated and difficult for investor to make decision. Hence, forecasting is one of the ways to minimizing risks arise from indecision on future. This paper will apply Support Vector Machine (SVM) and Artificial Neural Network (ANN) and a proposed hybrid model name Empirical mode decomposition-Support Vector Machine (EMD-SVM) forecasting crude oil price. After obtaining the forecasting result, performance evaluation is carry out to show which method can better forecast the crude oil price. The result shows that the performance of cruel oil price forecasting can be significantly increased by using the proposed hybrid EMD-SVM model. Thus proven the hybrid model are out-perform than individual forecasting model.
  • Publication
    Computerized integer programming method: Menu scheduling for critical illness patients
    ( 2020-09-21)
    Ai Lee O.
    ;
    Firdaus Sufahani S.
    ;
    Helmy Abd Wahab M.
    ;
    Syed Zulkarnain Syed Idrus
    ;
    Surono S.
    ;
    An. Ahmad
    In this paper, critical illness patients are referred to breast cancer patients. This cancer is developed from the breast tissue. It is developed due to the erratic growth of cells of the breast tissue. In Malaysia, according to the statistics in 2017, one out of 20 individuals has the breast cancer in their life. In order to help the breast cancer patient in choosing the best food in their meal of a whole day, the way on how to use different mathematical programming methods to prepare a proper and healthy planning diet menu that fulfil all the nutrients constraints with the minimum cost for the breast cancer patient will be showed out. In the literature review, previous research for the menu planning, approaches used for the optimization are being reviewed in detail. In methodology, there are two mathematical programming methods that will be applied which are integer programming and binary integer programming methods. There are two sets of data which is 100 food items for small data model and 426 food items for big data model. At the end of this research, it should be able to provide a minimum cost one day menu and weekly menu for the breast cancer patients with the sufficient nutritional value.
  • Publication
    Smart Accident Notification and Tracker (SANAT)
    ( 2020-09-21)
    Mohd Saufi N.
    ;
    Ahmad N.
    ;
    Mohd Sobri N.
    ;
    Nabilla Risal N.
    ;
    Helmy Abd Wahab M.
    ;
    Syed Zulkarnain Syed Idrus
    Road accident is a major concern in automobile powered world and road safety. Most of the accidents are not attended or treated quickly due to the lack of best emergency facilities and late information of the accident to rescue team especially in rural area. This paper aims to design Smart Accident Notification and Tracker (SANAT) by using Arduino Uno as a microcontroller with Global Positioning System (GPS) via Global System for Mobile communication (GSM) technology. This system detects an accident immediately after an impact sense by shock sensor and notified the emergency contact list as well as the rescue team with the precise location of the accident covering geographical coordinates in which a vehicle accident had occurred obtain from the GPS module after the shock sensor receive an impact from the accident. Signal from the sensor would be send to microcontroller and compares with the threshold set value and immediately sends an alert message using GSM modem to the first aid centre as a receiver. The receiver would receive the location in a link that could directly view the location and start navigate through Google Maps. This system would provide an optimum alert that could help reducing the loss of life due to vehicle accident.
  • Publication
    Multiple Fusions Approach for Keystroke Dynamics Verification System with Soft Biometrics
    ( 2020-09-21)
    Mohd Noorulfakhri Yaacob
    ;
    Syed Zulkarnain Syed Idrus
    ;
    Wan Azani Wan Mustafa
    ;
    Mohd Aminudin Jamlos
    ;
    Helmy Abd Wahab M.
    Computer security is a process that controls the entire information system, including network, system and hardware. Important information that must be controlled in a system is the data or information contained in a system. Various methods have been used to ensure that only users with legitimate access to data can use a system. Usernames and passwords have been a common practice by many systems as the first requirement to be fulfilled to access the system, but some systems use the secondary verification for additional confirmation. In this article, Keystroke Dynamics has been used as the user's second level authentication for the systems that use the keyboard to login into a system. A common problem of system intrusions is that the system fails to identify the user who signs in using the keyboard when the login is correct. There is a possibility that someone else tries to break into the system. To ensure and improve users' recognition who use the keyboard to enter their logins into the system, Keystroke Dynamics is used as a next-level verification if the login is correct. Soft biometrics is used in the user authentication process using KD method in this study. The soft biometric elements used in this study are culture, gender, educational level (CGPA - Cumulative Grade Point Average) and region of birth (ROB). All of these four soft biometric elements are expected to enhance capabilities in the user authentication process.
  • Publication
    Optimal method of optimizing risk of portfolio
    ( 2020-09-21)
    Jayeola D.
    ;
    Sufahani S.
    ;
    Akinmoji O.
    ;
    Helmy Abd Wahab M.
    ;
    Syed Zulkarnain Syed Idrus
    ;
    Mamat M.
    Diversification is a strategic method that investors use to optimize risk of portfolio. It is an opportunity by which investors move from micro-firm into macro-firm. The investors' aim is to make an optimal choice that leads to minimization of risk and maximization of return, but the methods that lead to these objectives are not easily achieved. The purpose of this paper is to propose a method to minimize risk of portfolio. Firstly, this paper investigates the risk reduction strength of each asset and secondly, it explores the impact of each asset in minimizing risk of portfolio. The assets allocations divulge by Black Litterman model are used to estimate risk of both portfolios and assets. We explore DataStream (Yahoo finance) of Gold, Oil and Natural gas which spans from January, 2010 to September, 2016. It is observed that investing on Gold minimizes higher risk and achieve more benefits than other assets in the portfolio. In view of these facts, it means diversifying in gold acts as hedge/safe haven for investors during economic crisis.
  • Publication
    Binary Time-Frequency Mask for Improved Malay Speech Intelligibility at Low SNR Condition
    ( 2020-09-21)
    Jamal N.
    ;
    Fuad N.
    ;
    Sha'Bani M.
    ;
    Helmy Abd Wahab M.
    ;
    Syed Zulkarnain Syed Idrus
    A binary masking is often seen as a medium to enhance speech signal especially in hearing aid and speech recognition applications due to its simplicity and efficient approach for supervised source separation. High intelligibility could be obtained by applying the binary time-frequency masking to noisy speech signal. Since the issue of linear filtering algorithms might affect the intelligibility of noisy speech signal, so, this paper presents the binary time-frequency mask for improved Malay speech intelligibility at low SNR condition. The clean Malay speech signals that were contaminated by car and train noise with different signal to noise ratio (SNR) and local criterion (LC) level in forming the binary mask are analysed. The performance of intelligibility improvement was evaluated using a normalized sub band enveloped correlation (nSec). Overall results showed that the proposed approach produces slightly improved speech intelligibility at low SNR value.
  • Publication
    The Analysis of EEG Distribution for Human Brainwave due to Mobile Phone Usage
    ( 2020-09-21)
    Fuad N.
    ;
    Rahim A.A.
    ;
    Marwan M.E.
    ;
    Helmy Abd Wahab M.
    ;
    Syed Zulkarnain Syed Idrus
    Brain is the most amazing thing that god create, without brain humans are just like living zombies. Brain generate electrical impulse that create brainwave. Therefore, from the brainwave there are four type of spectrum which are Delta, Theta, Alpha and Beta. Each spectrum has their own special meaning. For instance, there will be slight change in the brainwave pattern if that person answers a phone call. With the references of previous research, there is radiation in mobile phone that can cause headache. This headache can occur during the phone call. Thus, an experiment based on the different type of phone is conducted. In this research project, the different pattern of brainwave between answering phone call through GSM phone and smartphone are needed. This is to find out which phone give more radiation to the user. This experiment will take placed at one of the laboratories in the Faculty of Electrical and Electronic Engineering. Other than that, 20 subjects are needed for this experiment. The first step of this experiment is to collect data using EMOTIV Insight equipment. Next, the data is process in the SPSS and then, it will transfer to Microsoft Excel for better understanding of the result. In addition, the result obtain from this research project is that GSM phone cause more effect to the subject rather than smartphone. This is why nowadays, most of the people use smartphone compared to GSM phone. This because smartphone is user friendly and have less radiation.
  • Publication
    A Study of Named Data Networking as Communication Protocol for Multi-hop Wireless Ad Hoc Network
    ( 2020-09-21)
    Muchtar F.
    ;
    Lukuman Saheed A.
    ;
    Helmy Abd Wahab M.
    ;
    Syed Zulkarnain Syed Idrus
    Named Data Networking (NDN) has been repeatedly quoted in numerous past and existing literature reviews to have replaced Host Centric Networking (HCN) due to its ability to solve energy efficiency issues inherent in Multi-hop Wireless Ad-hoc Networks (WAHN). However, this claim is proven to be wholly unsubstantiated and is not justified by academic proof in said articles. Therefore, this study take the initiative to fill in this gap by presenting a comparative study of NDN based MWAHN and HCN based MWAHN through the use of real implementation by measuring two parameter metric that are related to energy efficiency, namely energy consumption and file transfer completion time. For this study, NDN-based MWAHN is compared with two type of actively developed HCN routing protocol implementation, namely Babeld and BMX6. The results obtained from this experiment is crucial for MWAHN researchers to gain better understanding of the real potential of the NDN based routing that can be used as a solution for energy consumption issues that exist in wireless multi-hop ad-hoc network.