Syed Muhammad Mamduh Syed Zakaria
Thumbnail Image
Preferred name
Syed Muhammad Mamduh Syed Zakaria
Official Name
Syed Muhammad Mamduh, Syed Zakaria
Alternative Name
Syed Zakaria, Syed Muhammad Mamduh
Syed Zakaria, S. M.M.
Zakaria, S. M.M.S.
Zakaria, Syed Muhammad Mamduh Bin Syed
Zakaria, Syed Muhammad Mamduh Syed
Main Affiliation
Scopus Author ID
55193486100
Researcher ID
AAY-1214-2020

Research Output

Filters

44
Reset filters

Settings
Now showing 1 - 10 of 44
  • Publication
    Odour source localization strategy for multiple robots using swarm intelligence with odour-gated anemotaxis
    ( 2017)
    Syed Muhammad Mamduh Syed Zakaria
    Animals such as silkworm moths, dogs and blue crabs have exhibited odour localization capabilities in nature. This amazing ability is exhibited in complex airflow conditions which produces highly dynamic and unpredictable gas dispersion. Harnessing this capability will enable robots to be deployed in critical and high-value applications such as search and rescue, entry point security applications, and environmental monitoring in industrial and urban settings. This thesis documents the research in swarm intelligence for gas source localization. Using swarm intelligence to achieve this task is envisaged to be more practical and economical compared to single robot implementations. Currently, few works have been presented on multi-robot systems in gas source localization; much less using swarm intelligence. This research aims to fill in the research gaps in gas source localization using swarm intelligence. However, current mobile olfaction experimental methods tend to oversimplify the actual problems thus reducing the findings’ impact in advancing this research field. Furthermore, lack of experimental realism reduces the reproducibility of the previously presented works in real world conditions. To overcome this limitation, this research uses recorded real-time gas dispersion in robot simulations. A real-time gas dispersion monitoring system consisting 72-gas sensors was built to record the gas dispersion in the experiment area. The recorded real-time data stream was then used in simulations to accurately recreate realworld experimental conditions in a simulation environment.
  • Publication
    Difference in effectiveness between the topical application of acidulated phosphate fluoride (APF) gel and casein phosphopeptide-amorphous calcium phosphate (CPP-ACP) paste in reducing plaque accumulation in children
    ( 2020)
    Kaswindiarti, Septriyani
    ;
    Finhartanti, Fianita
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Omar, Mohammad Iqbal
    Plaque accumulation is the buildup of bacterial substances on dental surface. Plaque can be controlled using anti-bacterial chemicals such as acidulated phosphate fluoride (APF) and casein phosphopeptideamorphous calcium phosphate (CPP-ACP). The function of APF and CPP-ACP is to inhibit the growth and adhesion of bacterial plaque colonization by S. mutans on the tooth’s surface. This study aims to identify differences in the effectiveness of the topical application of APF gel and CPP-ACP paste against plaque accumulation in children. The research applied a quasi-experimental method with a time-series design. The study was conducted at the Nur Hidayah and Ihsan Sakeena orphanages in Surakarta, where 30 children aged 6-12 were involved as research subjects, divided into two treatment groups namely the APF and CPP-ACP groups. Topical application of APF was given once on the first day, while that of CPP-ACP was administered once a day from the first until the seventh day. Plaque score data were obtained by PHP-M plaque score measurement. Total plaque scores were measured on day 1 before and after application, day 7 and day 14. Results show declining average plaque scores between the first day prior to topical application of APF and CPP-ACP and the fourteenth day afterwards. Independent samples tests reveal differences in effectiveness of topical APF gel and CPP-ACP paste application on plaque accumulation in children on day 7 and day 14, but no difference in plaque score change on day 1 ahead of and following application. Topical application of CPP-ACP paste decreases plaque accumulation in children more effectively than that of APF gel.
  • Publication
    Feasibility analysis of indoor 3D localization system with UWB using least squares trilateration
    (Iran University of Science and Technology, 2025-06)
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Ammar Zakaria
    ;
    Latifah Munirah Kamarudin
    ;
    Ali Yeon Md Shakaff
    ;
    Muhamad Naqib Mohd Shukri
    Accurate 3D Localization is very important for a wide range of applications, such as indoor navigation, industrial robotics, and motion tracking. This research focuses on indoor 3D positioning systems using ultra-wideband (UWB) devices. Two localization experiments were conducted using the Least Squares Trilateration method. In the first experiment, anchors were at the same height, while in the second, they were at varying heights. The lowest percentage errors in the first experiment were 0% at the x-axis, 0.21% at the y-axis, and 19.75% at the z-axis. In the second experiment, the lowest percentage errors in the experiment were 1.98% at the x-axis, 0.68% at the y-axis, and 17.86% at the z-axis, demonstrating improved accuracy with varied anchor heights at the axis. This work shows the z-axis measurements are unreliable and noisy due to the limited intersection of signal waves of each anchor in a same height anchors setup.
  • Publication
    Rice Grain Moisture Sensing Based on UHF RFID Tag
    ( 2022-06-24)
    Ainaa Syamim Mohd Radzi
    ;
    Latifah Munirah Kamarudin
    ;
    Latifah Mohamed
    ;
    Ammar Zakaria
    ;
    Mohd Hafiz Fazalul Rahiman
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Ndzi D.L.
    One of the critical steps in the post-production of paddy rice is to be stored in conditions that need to be controlled, especially the moisture content (MC) of the grains. The ability to determine and control moisture is a very important aspect of maintaining grain quality. This study aims to detect the MC of rice grain using UHF RFID technology. In this paper, three experiments have been carried out to detect the MC of rice in full rice grain-filled containers involving two conditions: with metal and without metal containers. The samples used consist of four 2 kg bags with MC levels of 11.875%, 16%, 20%, and 24%. The Received Signal Strength Indicator (RSSI) values were measured using a UHF handheld reader with two RFID tags to predict the MC. The results show an increasing RSSI pattern as the MC increases.
      1  23
  • Publication
    Predictive analysis of In-Vehicle air quality monitoring system using deep learning technique
    ( 2022)
    Abdul Syafiq Abdull Sukor
    ;
    Goh Chew Cheik
    ;
    Latifah Munirah Kamarudin
    ;
    Xiaoyang Mao
    ;
    Hiromitsu Nishizaki
    ;
    Ammar Zakaria
    ;
    Syed Muhammad Mamduh Syed Zakaria
    In-vehicle air quality monitoring systems have been seen as promising paradigms for monitoring drivers’ conditions while they are driving. This is because some in-vehicle cabins contain pollutants that can cause drowsiness and fatigue to drivers. However, designing an efficient system that can predict in-vehicle air quality has challenges, due to the continuous variation in parameters in cabin environments. This paper presents a new approach, using deep learning techniques that can deal with the varying parameters inside the vehicle environment. In this case, two deep learning models, namely Long-short Term Memory (LSTM) and Gated Recurrent Unit (GRU) are applied to classify and predict the air quality using time-series data collected from the built-in sensor hardware. Both are compared with conventional methods of machine learning models, including Support Vector Regression (SVR) and Multi-layer Perceptron (MLP). The results show that GRU has an excellent prediction performance with the highest coefficient of determination value (R2) of 0.97.
      1  20
  • Publication
    Deep Neural Network for Localizing Gas Source Based on Gas Distribution Map
    ( 2022-01-01)
    Zaffry Hadi Mohd Juffry
    ;
    Kamarulzaman Kamarudin
    ;
    Abdul Hamid Adom
    ;
    Mao X.
    ;
    Latifah Munirah Kamarudin
    ;
    Ammar Zakaria
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Abdulnasser Nabil Abdullah
    The dynamic characteristic of gas dispersal in uncontrolled environment always leads to inaccurate gas source localization prediction from gas distribution map. Gas distribution map is a representation of the gas distribution over an environment which helps human to observe the concentration of harmful gases at a contaminated area. This paper proposes the utilization of Deep Neural Network (DNN) to predict the gas source location in a gas distribution map. DNN learns from the previous gas distribution map data and patterns to generate a model that is able predict location of gas source. The results indicate that DNN is able to accurately predict the location within the range of 0.8 to 2 m from the actual gas source. This finding shows that DNN has a high potential for utilization in gas source localization application.
      1  32
  • Publication
    Improved mobile robot based gas distribution mapping through propagated distance transform for structured indoor environment
    ( 2020-05-18)
    Visvanathan R.
    ;
    Kamarulzaman Kamarudin
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Toyoura M.
    ;
    Ali Yeon A.S.
    ;
    Ammar Zakaria
    ;
    Latifah Munirah Kamarudin
    ;
    Mao X.
    ;
    Shazmin Aniza Abdul Shukor
    Mobile robot carrying gas sensors have been widely used in mobile olfaction applications. One of the challenging tasks in this research field is Gas Distribution Mapping (GDM). GDM is a representation of how volatile organic compound is spatially dispersed within an environment. This paper addresses the effect of obstacles towards GDM for indoor environment. This work proposes a solution by improvising the Kernel DM + V technique using propagated distance transform (DT) as the weighing function. Since DT computations are CPU heavy, parallel computing, using Compute Unified Device Architecture (CUDA) available in Graphics Processing Unit (GPU), is used to accelerate the DT computation. The proposed solution is compared with the Kernel DM + V algorithm, presenting that the proposed method drastically improves the quality of GDM under various kernel sizes. The study is also further extended towards the effect of obstacles on gas source localization task. The outcome of this work proves that the proposed method shows better accuracy for GDM estimation and gas source localization if obstacle information is considered.
      1  30
  • Publication
    2D LiDAR based reinforcement learning for Multi-Target path planning in unknown environment
    ( 2023)
    Nasr Abdalmanan
    ;
    Kamarulzaman Kamarudin
    ;
    Muhammad Aizat Abu Bakar
    ;
    Mohd Hafiz Fazalul Rahiman
    ;
    Ammar Zakaria
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Latifah Munirah Kamarudin
    Global path planning techniques have been widely employed in solving path planning problems, however they have been found to be unsuitable for unknown environments. Contrarily, the traditional Q-learning method, which is a common reinforcement learning approach for local path planning, is unable to complete the task for multiple targets. To address these limitations, this paper proposes a modified Q-learning method, called Vector Field Histogram based Q-learning (VFH-QL) utilized the VFH information in state space representation and reward function, based on a 2D LiDAR sensor. We compared the performance of our proposed method with the classical Q-learning method (CQL) through training experiments that were conducted in a simulated environment with a size of 400 square pixels, representing a 20-meter square map. The environment contained static obstacles and a single mobile robot. Two experiments were conducted: experiment A involved path planning for a single target, while experiment B involved path planning for multiple targets. The results of experiment A showed that VFH-QL method had 87.06% less training time and 99.98% better obstacle avoidance compared to CQL. In experiment B, VFH-QL method was found to have an average training time that was 95.69% less than that of the CQL method and 83.99% better path quality. The VFH-QL method was then evaluated using a benchmark dataset. The results indicated that the VFH-QL exhibited superior path quality, with efficiency of 94.89% and improvements of 96.91% and 96.69% over CQL and SARSA in the task of path planning for multiple targets in unknown environments.
      4  41
  • Publication
    Rice Grain Moisture Sensing Based on UHF RFID Tag
    ( 2022-06-24)
    Radzi A.S.M.
    ;
    Latifah Munirah Kamarudin
    ;
    Latifah Mohamed
    ;
    Ammar Zakaria
    ;
    Mohd Hafiz Fazalul Rahiman
    ;
    Syed Muhammad Mamduh Syed Zakaria
    ;
    Ndzi D.L.
    One of the critical steps in the post-production of paddy rice is to be stored in conditions that need to be controlled, especially the moisture content (MC) of the grains. The ability to determine and control moisture is a very important aspect of maintaining grain quality. This study aims to detect the MC of rice grain using UHF RFID technology. In this paper, three experiments have been carried out to detect the MC of rice in full rice grain-filled containers involving two conditions: with metal and without metal containers. The samples used consist of four 2 kg bags with MC levels of 11.875%, 16%, 20%, and 24%. The Received Signal Strength Indicator (RSSI) values were measured using a UHF handheld reader with two RFID tags to predict the MC. The results show an increasing RSSI pattern as the MC increases.
      2  40
  • Publication
    Predictive Analysis of In-Vehicle Air Quality Monitoring System Using Deep Learning Technique
    ( 2022-10-01)
    Abdul Syafiq Abdull Sukor
    ;
    Cheik Goh Chew
    ;
    Latifah Munirah Kamarudin
    ;
    Mao X.
    ;
    Nishizaki H.
    ;
    Ammar Zakaria
    ;
    Syed Muhammad Mamduh Syed Zakaria
    In-vehicle air quality monitoring systems have been seen as promising paradigms for monitoring drivers’ conditions while they are driving. This is because some in-vehicle cabins contain pollutants that can cause drowsiness and fatigue to drivers. However, designing an efficient system that can predict in-vehicle air quality has challenges, due to the continuous variation in parameters in cabin environments. This paper presents a new approach, using deep learning techniques that can deal with the varying parameters inside the vehicle environment. In this case, two deep learning models, namely Long-short Term Memory (LSTM) and Gated Recurrent Unit (GRU) are applied to classify and predict the air quality using time-series data collected from the built-in sensor hardware. Both are compared with conventional methods of machine learning models, including Support Vector Regression (SVR) and Multi-layer Perceptron (MLP). The results show that GRU has an excellent prediction performance with the highest coefficient of determination value (R2) of 0.97.
      2  36