Mazlina Mamat
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mazlina Mamat has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Hoe Tung Yew
Faculty of Engineering, Universiti Malaysia Sabah, Kota Kinabalu 88400, Malaysia
5 shared publications Norfarariyanti Parimon
Faculty of Engineering, Universiti Malaysia Sabah, Kota Kinabalu 88400, Malaysia
3 shared publicationsRosminah Mustakim
Universiti Malaysia Sabah
3 shared publicationsFarrah Wong
Universiti Malaysia Sabah
2 shared publications- Farrah Wong
Universiti Malaysia Sabah
2 shared publications Nadhirah Johari
Universiti Malaysia Sabah
2 shared publications
Latest Publications
- 27 June 2026
- Published by Springer Nature in Journal of Food Measurement and Characterization
- Vol. 20 (8) , 15650-15672
Multi-space color histogram feature fusion for non-destructive milk quality assessment in visually homogeneous liquids
- 27 June 2026
- Published by Springer Nature in Journal of Food Measurement and Characterization
- Vol. 20 (8) , 15650-15672
Multi-space color histogram feature fusion for non-destructive milk quality assessment in visually homogeneous liquids
- Open Access
- 11 October 2025
- Published by JVE International Ltd. in Journal of Vibroengineering
- Vol. 27 (7) , 1174-1193
A vision-based deep learning approach for non-contact vibration measurement using (2+1)D CNN and optical flow
This paper introduces a proof-of-concept vision-based deep learning approach for vibration measurement, proposing a factorized (2+1)D Convolutional Neural Network (CNN) model to predict four vibration metrics: acceleration, velocity, displacement, and frequency, with a focus on rigid body motion. Unlike conventional neural network models that primarily focus on frequency prediction alone, this approach uniquely enables the simultaneous estimation of four critical vibration metrics, offering a comprehensive and cost-effective alternative to traditional contact-based sensors such as accelerometers. The framework relies on the visibility of a training fiducial marker, eliminates the need for calibration in controlled settings, enhancing scalability across specific environments. A curated dataset was generated using a controlled experimental setup comprising a single object in a lab-scale environment, augmented synthetically to enhance frequency diversity. An optical flow-based preprocessing algorithm synchronized motion features in recorded video inputs with measured vibration labels, improving measurement accuracy. The proposed model achieved an average Mean Absolute Percentage Error (MAPE) of 7.51 %, with acceleration predictions exhibiting the lowest error at 4.84 % and displacement the highest at 8.80 % across varying brightness levels and object-camera distances. Techniques such as Region of Interest (ROI) cropping and multi-section frame extraction were implemented to reduce computational complexity while further enhancing accuracy. These results highlight the framework’s potential for non-invasive vibration analysis, though its generalizability is limited by the single-object dataset. Future work will expand the dataset, integrate multi-sensor inputs, explore marker-less tracking methods, and enable real-time deployment for predictive maintenance and structural health monitoring.
- 11 October 2025
- Published by JVE International Ltd. in Journal of Vibroengineering
- Vol. 27 (7) , 1174-1193
Open AccessA vision-based deep learning approach for non-contact vibration measurement using (2+1)D CNN and optical flow
This paper introduces a proof-of-concept vision-based deep learning approach for vibration measurement, proposing a factorized (2+1)D Convolutional Neural Network (CNN) model to predict four vibration metrics: acceleration, velocity, displacement, and frequency, with a focus on rigid body motion. Unlike conventional neural network models that primarily focus on frequency prediction alone, this approach uniquely enables the simultaneous estimation of four critical vibration metrics, offering a comprehensive and cost-effective alternative to traditional contact-based sensors such as accelerometers. The framework relies on the visibility of a training fiducial marker, eliminates the need for calibration in controlled settings, enhancing scalability across specific environments. A curated dataset was generated using a controlled experimental setup comprising a single object in a lab-scale environment, augmented synthetically to enhance frequency diversity. An optical flow-based preprocessing algorithm synchronized motion features in recorded video inputs with measured vibration labels, improving measurement accuracy. The proposed model achieved an average Mean Absolute Percentage Error (MAPE) of 7.51 %, with acceleration predictions exhibiting the lowest error at 4.84 % and displacement the highest at 8.80 % across varying brightness levels and object-camera distances. Techniques such as Region of Interest (ROI) cropping and multi-section frame extraction were implemented to reduce computational complexity while further enhancing accuracy. These results highlight the framework’s potential for non-invasive vibration analysis, though its generalizability is limited by the single-object dataset. Future work will expand the dataset, integrate multi-sensor inputs, explore marker-less tracking methods, and enable real-time deployment for predictive maintenance and structural health monitoring.
- 5 June 2024
- Published by Springer Nature
- p. 103-118
Artificial Intelligence in Time Series Prediction, Classification, and Sequence-to-Sequence Problems
- 5 June 2024
- Published by Springer Nature
- p. 103-118
Artificial Intelligence in Time Series Prediction, Classification, and Sequence-to-Sequence Problems
- 5 June 2024
- Published by Springer Nature
- p. 143-165
Estimating Shelf Life of Packed Fresh Milk Using Odor and Machine Learning: A Feasibility Study
- 5 June 2024
- Published by Springer Nature
- p. 143-165
Estimating Shelf Life of Packed Fresh Milk Using Odor and Machine Learning: A Feasibility Study
- Open Access
- 5 December 2023
- Published by Global Academic Excellence (M) Sdn Bhd in International Journal of Entrepreneurship and Management Practices
- Vol. 6 (23) , 45-60
SERVICE QUALITY, AWARENESS AND AGE: FACTORS THAT INFLUENCE PENETRATION OF LIFE INSURANCE IN MALAYSIA
- 5 December 2023
- Published by Global Academic Excellence (M) Sdn Bhd in International Journal of Entrepreneurship and Management Practices
- Vol. 6 (23) , 45-60
Open AccessSERVICE QUALITY, AWARENESS AND AGE: FACTORS THAT INFLUENCE PENETRATION OF LIFE INSURANCE IN MALAYSIA
- Open Access
- 1 December 2022
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 12 (6) , 6806-6819
Internet of things based real-time coronavirus 2019 disease patient health monitoring system
The coronavirus disease (COVID-19) outbreak has led to many infected worldwide and has become a global crisis. COVID-19 manifests in the form of shortness of breath, coughing and fever. More people are getting infected and healthcare systems worldwide are overwhelmed as healthcare workers become exhausted and infected. Thus, remote monitoring for COVID-19 patients is required. An internet of things (IoT) based real-time health monitoring system for COVID-19 patients was proposed. It features monitoring of five physiological parameters, namely electrocardiogram (ECG), heart rate (HR), respiratory rate (RR), oxygen saturation (SpO2) and body temperature. These vitals are processed by the main controller and transmitted to the cloud for storage. Healthcare professionals can read real-time patient vitals on the web-based dashboard which is equipped with an alert service. The proposed system was able to transmit and display all parameters in real-time accurately without any packet loss or transmission errors. The accuracy of body temperature readings, RR, SpO2 and HR, is up to 99.7%, 100%, 97.97% and 98.34%, respectively. Alerts were successfully sent when the parameters reached unsafe levels. With the proposed system, healthcare professionals can remotely monitor COVID-19 patients with greater ease, lessen their exposure to the pathogen, and improve patient monitoring.
- 1 December 2022
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 12 (6) , 6806-6819
Open AccessInternet of things based real-time coronavirus 2019 disease patient health monitoring system
The coronavirus disease (COVID-19) outbreak has led to many infected worldwide and has become a global crisis. COVID-19 manifests in the form of shortness of breath, coughing and fever. More people are getting infected and healthcare systems worldwide are overwhelmed as healthcare workers become exhausted and infected. Thus, remote monitoring for COVID-19 patients is required. An internet of things (IoT) based real-time health monitoring system for COVID-19 patients was proposed. It features monitoring of five physiological parameters, namely electrocardiogram (ECG), heart rate (HR), respiratory rate (RR), oxygen saturation (SpO2) and body temperature. These vitals are processed by the main controller and transmitted to the cloud for storage. Healthcare professionals can read real-time patient vitals on the web-based dashboard which is equipped with an alert service. The proposed system was able to transmit and display all parameters in real-time accurately without any packet loss or transmission errors. The accuracy of body temperature readings, RR, SpO2 and HR, is up to 99.7%, 100%, 97.97% and 98.34%, respectively. Alerts were successfully sent when the parameters reached unsafe levels. With the proposed system, healthcare professionals can remotely monitor COVID-19 patients with greater ease, lessen their exposure to the pathogen, and improve patient monitoring.
- Open Access
- 29 October 2022
- Published by MDPI AG in Atmosphere
- Vol. 13 (11) , 1787
Towards On-Site Implementation of Multi-Step Air Pollutant Index Prediction in Malaysia Industrial Area: Comparing the NARX Neural Network and Support Vector Regression
Malaysia has experienced public health issues and economic losses due to air pollution problems. As the air pollution problem keeps increasing over time, studies on air quality prediction are also advancing. The air quality prediction can help reduce air pollution’s damaging impact on public health and economic activities. This study develops and evaluates the Nonlinear Autoregressive Exogenous (NARX) Neural Network and Support Vector Regression (SVR) for multi-step Malaysia’s Air Pollutant Index (API) prediction, focusing on the industrial areas. The performance of NARX and SVR was evaluated on four crucial aspects of on-site implementation: Input pre-processing, parameter selection, practical predictability limit, and robustness. Results show that both predictors exhibit almost comparable performance, in which the SVR slightly outperforms the NARX. The RMSE and R2 values for the SVR are 0.71 and 0.99 in one-step-ahead prediction, gradually changing to 6.43 and 0.68 in 24-step-ahead prediction. Both predictors can also perform multi-step prediction by using the actual (non-normalized) data, hence are simpler to be implemented on-site. Removing several insignificant parameters did not affect the prediction performance, indicating that a uniform model can be used at all air quality monitoring stations in Malaysia’s industrial areas. Nevertheless, SVR shows more resilience towards outliers and is also stable. Based on the trends exhibited by the Malaysia API data, a yearly update is sufficient for SVR due to its strength and stability. In conclusion, this study proposes that the SVR predictor could be implemented at air quality monitoring stations to provide API prediction information at least nine steps in advance.
- 29 October 2022
- Published by MDPI AG in Atmosphere
- Vol. 13 (11) , 1787
Open AccessTowards On-Site Implementation of Multi-Step Air Pollutant Index Prediction in Malaysia Industrial Area: Comparing the NARX Neural Network and Support Vector Regression
Malaysia has experienced public health issues and economic losses due to air pollution problems. As the air pollution problem keeps increasing over time, studies on air quality prediction are also advancing. The air quality prediction can help reduce air pollution’s damaging impact on public health and economic activities. This study develops and evaluates the Nonlinear Autoregressive Exogenous (NARX) Neural Network and Support Vector Regression (SVR) for multi-step Malaysia’s Air Pollutant Index (API) prediction, focusing on the industrial areas. The performance of NARX and SVR was evaluated on four crucial aspects of on-site implementation: Input pre-processing, parameter selection, practical predictability limit, and robustness. Results show that both predictors exhibit almost comparable performance, in which the SVR slightly outperforms the NARX. The RMSE and R2 values for the SVR are 0.71 and 0.99 in one-step-ahead prediction, gradually changing to 6.43 and 0.68 in 24-step-ahead prediction. Both predictors can also perform multi-step prediction by using the actual (non-normalized) data, hence are simpler to be implemented on-site. Removing several insignificant parameters did not affect the prediction performance, indicating that a uniform model can be used at all air quality monitoring stations in Malaysia’s industrial areas. Nevertheless, SVR shows more resilience towards outliers and is also stable. Based on the trends exhibited by the Malaysia API data, a yearly update is sufficient for SVR due to its strength and stability. In conclusion, this study proposes that the SVR predictor could be implemented at air quality monitoring stations to provide API prediction information at least nine steps in advance.
- 23 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Installation of High Resistance Grounding System on the Ungrounded System at Offshore Platform
Single line to earth fault usually can be seen in the ungrounded system. The ungrounded system is used widely in offshore platforms due to its advantages over the overvoltage whenever a fault occurs in the power systems. Continuous production with less interruption is vital in the oil and gas industry to achieve the production rate target. The grounding system has evolved for the past years and improvements have been made to the ungrounded system that has been around the years in the industry. The ungrounded system has been the best grounding system when the power system needs to maintain its operation with the presence of tolerable fault such as the single line to earth fault. Some facilities have included the feature of tripping the main circuit breaker whenever there is ground fault on the non-critical equipment. This has been unproductive to the operation and time consuming in restarting the plant facility after power failure or shutdown. Kikeh offshore platform is having the same situation whenever the ground fault occurs the main circuit breaker tripped and affects the operation badly. The High Resistance Grounding (HRG) design has proved to be able to sustain the fault and at the same time allows the plant to continue operating without any unnecessary shutdown. This improves the downtime and increases productivity. Furthermore, arc hazards to personnel and the classification flammable gas area can be minimized.
- 23 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Installation of High Resistance Grounding System on the Ungrounded System at Offshore Platform
Single line to earth fault usually can be seen in the ungrounded system. The ungrounded system is used widely in offshore platforms due to its advantages over the overvoltage whenever a fault occurs in the power systems. Continuous production with less interruption is vital in the oil and gas industry to achieve the production rate target. The grounding system has evolved for the past years and improvements have been made to the ungrounded system that has been around the years in the industry. The ungrounded system has been the best grounding system when the power system needs to maintain its operation with the presence of tolerable fault such as the single line to earth fault. Some facilities have included the feature of tripping the main circuit breaker whenever there is ground fault on the non-critical equipment. This has been unproductive to the operation and time consuming in restarting the plant facility after power failure or shutdown. Kikeh offshore platform is having the same situation whenever the ground fault occurs the main circuit breaker tripped and affects the operation badly. The High Resistance Grounding (HRG) design has proved to be able to sustain the fault and at the same time allows the plant to continue operating without any unnecessary shutdown. This improves the downtime and increases productivity. Furthermore, arc hazards to personnel and the classification flammable gas area can be minimized.
- Open Access
The Implementation of Application Software to Improve Verbal Communication in Children with Autism Spectrum Disorder: A Review
Autism-assistive apps offer therapists and caregivers new approaches for educating and assisting individuals with autism spectrum disorder (ASD), mainly in social interaction. Even though these apps are deemed effective, they are not. These autism-assistive apps are not highly customizable, which limits their usefulness. This article examined the application software that was applied to encourage verbal communication in the intervention for children with ASD. The aim was to determine the minimum requirements for a verbal communication intervention app that adequately satisfies children with ASD, caregivers, and therapists. Databases were searched, including Scopus, Springer, PubMed, Education Resources Information Centre, and Google Scholar, with the following free-text terms combining Boolean operators: autism, children, intervention, verbal communication, software, app, and technology. A total of fifteen studies were found relevant, and the following information was collected: participant characteristics, information on the devices and apps, target behaviors, intervention procedures, and intervention outcomes. The findings suggest that the autism-assistive apps effectively improve verbal communication of children with ASD. For that, the apps should be attractive and engaging to the children with ASD, able to identify the child’s capability and suggest appropriate lesson activities, as well as encompass specific learning outcomes with multilevel lesson strategy. The apps should also use systematic evidence-based intervention procedures in the activities, be able to evaluate the child’s learning progress, and allow caregivers or therapists to keep track of application usage and performance. The use of apps in intervention does provide many benefits. However, they should never replace qualified therapists. App-based interventions make home-based treatment more focused, systematic, and economical.
Open AccessThe Implementation of Application Software to Improve Verbal Communication in Children with Autism Spectrum Disorder: A Review
Autism-assistive apps offer therapists and caregivers new approaches for educating and assisting individuals with autism spectrum disorder (ASD), mainly in social interaction. Even though these apps are deemed effective, they are not. These autism-assistive apps are not highly customizable, which limits their usefulness. This article examined the application software that was applied to encourage verbal communication in the intervention for children with ASD. The aim was to determine the minimum requirements for a verbal communication intervention app that adequately satisfies children with ASD, caregivers, and therapists. Databases were searched, including Scopus, Springer, PubMed, Education Resources Information Centre, and Google Scholar, with the following free-text terms combining Boolean operators: autism, children, intervention, verbal communication, software, app, and technology. A total of fifteen studies were found relevant, and the following information was collected: participant characteristics, information on the devices and apps, target behaviors, intervention procedures, and intervention outcomes. The findings suggest that the autism-assistive apps effectively improve verbal communication of children with ASD. For that, the apps should be attractive and engaging to the children with ASD, able to identify the child’s capability and suggest appropriate lesson activities, as well as encompass specific learning outcomes with multilevel lesson strategy. The apps should also use systematic evidence-based intervention procedures in the activities, be able to evaluate the child’s learning progress, and allow caregivers or therapists to keep track of application usage and performance. The use of apps in intervention does provide many benefits. However, they should never replace qualified therapists. App-based interventions make home-based treatment more focused, systematic, and economical.