Papers by Mohd Azwarie Mat Dzahir
Development of Al-Quran sign language classification based on convolutional neural network
Nucleation and Atmospheric Aerosols, 2021
Sign language is the main form of communication used by deaf people. Most of their activities, li... more Sign language is the main form of communication used by deaf people. Most of their activities, like; speaking, reading, and learning, involved sign languages. For reading Al-Quran, deaf people used Arabic sign language to read the ayah Al-Quran. For them, assistive technologies to aid them in the process of learning and teaching of Al-Quran is very important, since the traditional method is very difficult and challenging. One of the reasons is that, traditionally, teachers need to know Arabic Sign Languages (ArSL) first in order to teach them to learn Al-Quran. Currently, assistive technology, it still considered to be relatively new and not well developed. In Malaysia and Indonesia, most of the developed technologies are mobile app, and web-based device, which both of them required continuous internet connection and only suitable for personal used. Previous research on assistive technologies can be classified into two types of devices. First, a sensor-based device, and second is the image-based device. Both of them have their advantages and disadvantages. For this project, the only image-based device is focused since the scope of this project is limited to supervised machine learning (Convolution neural network, CNN) that developed with accuracy above 80% in training and testing. The accuracy of CNN model can be explained based on the resulting pattern obtained from the training and testing. Next, the resulting pattern can be described as overfitting, underfitting, or optimum. This project shows that, with the appropriate tuning of hyperparameters based on the resulting pattern, the accuracy of the model can be improved. This CNN model is developed from scratch through trial and error tuning method since there are no formal techniques. Lastly, the CNN model is converted into a Tensorflow Lite format, which can ready to be integrated with mobile applications.
Quantification process of carbon emissions in the construction industry
Energy and Buildings
A Methodology to Evaluate the Effectiveness of Designers’ Cognitive Process when Using Multi-user Virtual Reality
IOP Conference Series: Earth and Environmental Science
This paper proposed the mixed-mode methodology to evaluate the effectiveness of the cognitive pro... more This paper proposed the mixed-mode methodology to evaluate the effectiveness of the cognitive process when using Multi-user Virtual Reality (VR) in the design review sessions. The research explains that the design review is an essential part of the planning process. It evaluates the client’s requirements against the designers’ design before the construction starts. Quality communication among the designers and clients plays a central role in enhancing the output of the design review session, apart from the quality in visualisation during the presentation. A multi-user VR system with a head-mounted display allows users to fully immerse into the virtual environment (VE) during the design review process and subsequently achieve quality discussion and decision-making. This paper describes the process of data collection in quantitative and qualitative methods, where questionnaires will be distributed to determine the state-of-the-art of the designers’ cognitive processes when they are in...
Leveraging Prefabricated Construction Supply Chain Management Through Building Information Modelling
Communications in computer and information science, 2022
![Research paper thumbnail of Hysteresis Modelling of Pneumatic Artificial Muscle using General Cubic Equation and Factor Theorem Prediction Method / Mohd Azuwan Mat Dzahir...[et al.]](https://attachments.academia-assets.com/112331392/thumbnails/1.jpg)
Due to inherent hysteresis in a pneumatic artificial muscle, the accompanying control of this com... more Due to inherent hysteresis in a pneumatic artificial muscle, the accompanying control of this compliant actuator becomes more complicated. In literature, only a few implementations of the hysteresis modelling in the associated position control system could be found. In addition, the high complexity of the contraction-force and contraction-pressure models when accounting for hysteresis effect, the implementation of such model is limited in its use in the pneumatic muscle position control only. However, implementing a complicated control algorithm does not always indicate the best solution that could be used to control the pneumatic artificial muscles. There are arguments in the field of rehabilitation robotics regarding what was the best control system to the orthotic problem for rehabilitation. It is preferred that the control system should be simplified as much as possible; multiple sensors and impedances are only increase the complexity of the control system. Rather than using a very complicated algorithm for control system of the pneumatic artificial muscle, a simple and noble prediction method using general cubic equation and factor theorem is proposed for the hysteresis modelling at different loads. The methodology used to establish the hysteresis modelling and prediction method of the pneumatic artificial muscle are as follows; first is the characterization of the pneumatic artificial muscle at different loads and pressures; second is to develop a prediction brought to you by CORE View metadata, citation and similar papers at core.ac.uk provided by Universiti Teknologi MARA Institutional Repository Mohd Azuwan Mat Dzahir et al. 2 method for generating constraint models of hysteresis data at a different loads using general cubic equation and factor theorem; third is to establish a simple theorem or algorithm to extract the hysteresis models (i.e., contraction and expansion) of a pneumatic artificial muscle at different loads based on the generated constraint models; and the final stage of the research is to obtain the hysteresis models at different loads. The generated hysteresis models and hysteresis data obtained from experimental study were compared to verify the reliability of the proposed hysteresis modelling prediction method. The simulation results shows that the hysteresis modelling was able to generate an apropriate constraint models at a different loads.
CMAR: A Conceptual Framework for Designing Mobile Augmented Reality Learning Module for Construction Measurement
Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2022
arXiv (Cornell University), Sep 3, 2014
In this paper we give a new control model based on the so called computedtorque method for the co... more In this paper we give a new control model based on the so called computedtorque method for the control of a 2 degrees of freedom orthosis for the rehabilitation of the lower limb, the AIRGAIT exoskeleton's leg orthosis. The actuation of the AIRGAIT is made through self-made pneumatic muscles. For this reason this work starts with the static and dynamic characterization of our pneumatic muscles. The followed approach is based on the analytical description of the system. For this, we describe the pneumatic muscles behaviour with an easy-invertible polynomial fit function in order to model its non-linear trend. We give a geometrical model of the mechanical system to compute the length between the attachments of the pneumatic muscles to the structure for every angles assumed by the two joints. We evaluate through Newton-Euler equation the couples at the joints for each values of the angles. At last we show some validation tests in order to characterize the functioning of the proposed control model on the actuation of the orthosis.
Differences of spinal kinematics contribution between cervical and multi-segmental thoracic spine during Sit-To-Stand (STS) Stand-To-Flexion (STF)
IOP Conference Series: Materials Science and Engineering, 2020
Understanding the actual spinal kinematics in completing critical daily activities is utmost impo... more Understanding the actual spinal kinematics in completing critical daily activities is utmost important for human being as it can lead for better quality of life. Two of the most common functions which are necessary for human being are standing up and bend forward. Researchers tried to explore the kinematics of human spine during Sit-to-Stand (STS) and Stand-to-Flexion (STF) but most of them only focussed on thoracic and lumbar spine. Literatures of similar study within thoracic spine only divide the region up to three segments thus reducing the accuracy of actual thoracic multi segments behaviours in completing daily task. This paper aims to study the differences of spinal kinematics contribution between cervical and multi-segmental thoracic spine during STS & STF among healthy Asian adults using non-invasive approach. Interclass correlation coefficient (ICC) for both tasks specified during the study showed excellent reliability with all ICC value were above 0.90 (0.932-0.976). Duri...
International Journal of Innovative Technology and Exploring Engineering, 2019
An electronic braille (eBraille) Quran is a braille display that is use to aid the visually impai... more An electronic braille (eBraille) Quran is a braille display that is use to aid the visually impaired and blind Muslims in their journey of understanding and appreciating the Quran in a much more convenient way. It is an invention of University of Technology Malaysia (UTM) since 2009 for the blind people to recite Quran through the Braille system. However, current architecture of eBraille Quran comprises of too many modular components, numerous microcontrollers and complexly designed. Another vital issue is that its architecture still uses old technologies where the firmware updating or data correction process cannot be done remotely. This makes it hard to maintain, repair, costly and time consuming. This study proposed an enhancement of current architecture with the latest technology of single board computer named Raspberry Pi 3B+. The architecture is first designed according to the existing features of the eBraille Quran. Then, a prototype circuit is developed and fabricated for te...
MATEC Web of Conferences, 2017
Nowadays, medical rehabilitation system has become a requirement due to increment in national reh... more Nowadays, medical rehabilitation system has become a requirement due to increment in national rehabilitation centres and medical hospitals. An assistive rehabilitation orthosis becomes essential and was used for rehabilitation therapy, condition monitoring, and physical strengthening. This study focused on the lower limb assistive rehabilitation orthosis development using pneumatic artificial muscle. To successfully control this orthosis system which consists of antagonistic mono-and biarticular muscle actuators, it is necessary to construct a reliable control algorithm. The suitable control scheme and strategy to manoeuvre this orthosis system similar to human musculoskeletal system have yet to be fully developed and established. Based on the review study, it is said that the co-contraction controls of anterior-posterior pneumatic muscles was able to improve the joint stiffness and stability of the orthosis as well as good manoeuvrability. Therefore, a characterization model of an antagonistic mono-and bi-articular muscles activities of human's lowerlimb during walking motion will be necessary. A healthy young male subject was used as test subject to obtain the sEMG muscle activities for antagonistic mono-and bi-articular muscles (i.e., Vastus Medialis-VM, Vastus Lateralis-VL, Rectus Femoris-RF, and Bicep Femoris-BF). The tests were carried out at different speeds of 2km/h, 3km/h, and 4km/h for one minute walking motion on a treadmill. Then, the patterns of the sEMG muscle activities were modelled and characterised using fifth order polynomial equation. Based on the results, it is shown that the anterior and posterior muscles were exhibited a muscle synergy in-between multiple anterior or posterior muscles and muscle co-contraction between anteriorposterior muscles in order to control the movements at the joints during walking motion. As conclusion, it is proven that the sEMG muscle activities of the antagonistic mono-and bi-articular muscles were follow a certain contraction-expansion patterns during walking motion even when it were tested at different gait cycle speeds.
Antagonistic mono- and bi-articular pneumatic muscle actuator control for gait training system using contraction model
2013 ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living (BRC)
ABSTRACT In recent years, the use of the pneumatic muscle actuator (PMA) to acquire greater power... more ABSTRACT In recent years, the use of the pneumatic muscle actuator (PMA) to acquire greater power from the actuation system especially for the development of medical rehabilitation robotic for gait training system has increased. Usually, the biarticular actuators are treated as a redundancy in actuation since the number of actuators is greater than the number of joints. However, these actuators are able to generate a strong force due to wider range of motion compared to the mono-articular actuators and it is thought to generate instantaneous force. In the case of lower orthotic gait training system, the implementation of antagonistic bi-articular actuators along with mono-articular actuators plays a major role to achieve the required afferent input for the lower limb and hip joint as well as smooth and precise movements at the endpoint. One of the important characteristics of PMA is based on its muscle contraction. In this study, we modelled mathematical equations to determine the muscle contraction pattern for the antagonistic mono- and biarticular PMAs as a function of the hip and knee angles in which its magnitude is influenced by the anterior and posterior muscle activation levels. From this model, we are able to determine the input pressure for each of the antagonistic mono- and bi-articular PMAs and then control the system using a feedback controller.
Jurnal Teknologi, 2015
This paper looked into optimal tuning of a Proportional-Integral-Derivative (PID) controller used... more This paper looked into optimal tuning of a Proportional-Integral-Derivative (PID) controller used in Electro-mechanical Dual Acting Pulley Continuously Variable Transmission (EMDAP-CVT) system for controlling the output obtained, and hence, to minimize the integral of absolute errors (IAE). The main objective was to obtain a stable, robust, and controlled system by tuning the PID controller by using Particle Swarm Optimization (PSO) algorithm. The incurred value was compared with the traditional tuning techniques like Ziegler-Nichols and it had been proven better. Hence, the results established that tuning the PID controller using PSO technique offered less overshoot, a less sluggish system, and reduced IAE.
Development of Al-Quran sign language classification based on convolutional neural network
PROCEEDINGS OF 8TH INTERNATIONAL CONFERENCE ON ADVANCED MATERIALS ENGINEERING & TECHNOLOGY (ICAMET 2020), 2021
Sign language is the main form of communication used by deaf people. Most of their activities, li... more Sign language is the main form of communication used by deaf people. Most of their activities, like; speaking, reading, and learning, involved sign languages. For reading Al-Quran, deaf people used Arabic sign language to read the ayah Al-Quran. For them, assistive technologies to aid them in the process of learning and teaching of Al-Quran is very important, since the traditional method is very difficult and challenging. One of the reasons is that, traditionally, teachers need to know Arabic Sign Languages (ArSL) first in order to teach them to learn Al-Quran. Currently, assistive technology, it still considered to be relatively new and not well developed. In Malaysia and Indonesia, most of the developed technologies are mobile app, and web-based device, which both of them required continuous internet connection and only suitable for personal used. Previous research on assistive technologies can be classified into two types of devices. First, a sensor-based device, and second is th...
Journal of Mechanical Engineering and Sciences, 2020
The change of the spinal curvature in completing a variety of daily tasks is essential to indepen... more The change of the spinal curvature in completing a variety of daily tasks is essential to independent living. There is still a lack of studies highlighting the lumbar segmental contribution during sit-to-stand (STS) and stand-to-flexion (STF) using non-invasive study. The purpose of this study is to compare the spine kinematics by defining lumbar as a single and multi-segmental during continuous daily motion in healthy Asian adults using a non-invasive approach. During STS, most subjects implemented kyphotic lumbar curve during the early stage of motion which revealed poor posture implementation and significant differences in the lumbar kinematics which were only noticeable at specific phases between both approaches. A significant difference in multi-segmental behaviour was observed only at the end of the motion. All three segments displayed different time responses during the transition from kyphotic to lordotic curve. Passive/delayed behavior within the lower lumbar segment was ob...
This research investigates the performance of dynamic modeling using identification techniques of... more This research investigates the performance of dynamic modeling using identification techniques of an Electromechanical Dual Acting Pulley Continuously Variable Transmission (EMDAP CVT) system for development of intelligent control. In this paper, the implementation details are described and the experimental studies conducted in this research are analyzed. The input and output speed data of the system were first acquired through the experimental studies using Integrated Measurement and Controls (IMC) data acquisition system. In this study, we applied engine speed to the EMDAP CVT and investigated the dynamic response of the system. The modeling of the system was developed using the Genetic Algorithm (GA). The validation and verification of the obtained model was evaluated using mean squared error (MSE) and correlation test. The performance of the nonlinear approach was compared and discussed based on MSE value. The prediction ability of the model was further observed with unseen data...
Building Information Modelling Analysisof Proposed Skycourt Apartmentprototype and Conventional Affordableapartment in Malaysia
This paper proposes ÂSkycourt Apartment as a solution for more socially sustainable high-rise ... more This paper proposes ÂSkycourt Apartment as a solution for more socially sustainable high-rise residential and considerably more cost-effective in comparison with Malaysian conventional affordable apartments. The provision of skycourt is proven to be a socially sustainable and environmentally viable option for high-rise living, as numerous previous researchers have shown the potential for this green communal space. The principal contribution of this paper includes the cost feasibility validation of skycourt apartment prototype to be applied specifically in MalaysiaÂs affordable apartment typology. The validation process is carried out by having a comparison of Bill of Quantity between the proposed prototypes of skycourt apartment with a selected conventional affordable apartment in Johor Bahru as the base comparator. Both buildings are modelled in Revit before cost simulation is employed on each of the Building Information Model as the tool to generate the Bill of Quantity. The r...
Towards a framework of automated resource model for post contract cost control of construction projects
International Journal of Construction Management
Real-time control of on-site construction cost has been a major concern as every client demand va... more Real-time control of on-site construction cost has been a major concern as every client demand value for the money invested in procuring a construction project. The design team and other stakeholde...
Mini-Review on Technology in Safety Training Delivery
IOP Conference Series: Materials Science and Engineering
The construction site is in a constant state of fluidity. This constant change presents challenge... more The construction site is in a constant state of fluidity. This constant change presents challenges for construction players who must be able to foresee hazardous conditions before they cause injuries or fatalities on the construction site. Nowadays, technology continuously improves the way the construction industry works. In line with the industrial revolution, technology evolution will improve the effectiveness of construction industry operation. Embracing technologies would benefits inefficiencies, diminishing cost and improve health and safety levels. Therefore, this paper sought to review the technologies that can be implemented in training delivery, especially for safety training. A systematic literature review has been conducted to determine suitable technology in assisting safety training. Based on the deductive content analysis, there are three types of technologies that can be used as an approach in training delivery. The findings of the study prevail which technology parti...
Jurnal Teknologi, Dec 11, 2015
This paper investigates the performance of clamping force at the secondary pulley actuator of Ele... more This paper investigates the performance of clamping force at the secondary pulley actuator of Electro-mechanical Dual Acting Pulley Continuously Variable Transmission (EMDAP CVT) using an identification technique for development of intelligent control. The implementation details are described and the experimental studies conducted in this research are analyzed. To investigate the dynamic response of the system, step input was applied to the EMDAP CVT and clamping forced was measured. The modeling of the system was developed using the Genetic Algorithm (GA). The validation and verification of the obtained model were evaluated using mean squared error (MSE) and correlation test. The performance of the nonlinear approach was compared and discussed based on MSE value. The predictive ability of the model was further observed with unseen data. The result shows that, Nonlinear ARX (NARX) model converges to an optimum solution faster with increasing of model order and the obtained dynamic model also described the system well.
Remote control of hand arm robotic system
Uploads
Papers by Mohd Azwarie Mat Dzahir