Conference Publications

Permanent URI for this collection

https://hdl.handle.net/20.500.14170/1588

Browse

Browsing Conference Publications by Title

  • Publication
    Abnormality Detection Approach in Smart Homes using Case-based Reasoning
    ( 2020-06-01)
    Abdul Syafiq Abdull Sukor
    ;
    Rossi Setchi
    ;
    Ze Ji
    Today, the population of elderly people is dramatically increasing. To help with the problem, smart homes provide technologies and services that can help elderly people to live independently and comfortably in their own homes. One such service in smart homes is the detection of abnormal situations based on individuals' daily routine. This is important as some situations can lead to serious health issues if they have not been detected in the early stage. This paper presents a conceptual model for abnormality detection using case-based reasoning. It utilizes previous cases, which are built from a publicly available smart home dataset. To evaluate the performance, the cases are divided into two case-based sizes which contain seven and fourteen days of monitoring task. To avoid bias, the performance is also measured against two voluntary individuals who have no knowledge of the dataset. The results show that the system is able to detect abnormal situations with the best accuracy of 81.3%.
      3  1
  • Publication
    Analysis hairdryer using design for manufacturing and assemble (DFMA)
    ( 2021-07-21)
    Nasir S.M.
    ;
    Muhamad Farizuan Rosli
    ;
    Shayfull Zamree Abd. Rahim
    ;
    Shafeeq Ahmad Shamim Ahmad
    ;
    Mohd Effendi Muhammad Suandi
    ;
    Muhammad Azam Asri
    ;
    Nur Syahirah Mohd Tamizi
    ;
    Nur Adila Mohd Haris
    ;
    Siti Aminah Zawawi
    For this project, analysis of the redesign of original product hair dryer, the project is focused on the Hair dryers design, size, color, material and cost. Hair dryer are electromechanical device designed to dry the hair. This project is not only intended to analyze its body, but is also recognized as the part, element and component with a systematic function to analyze in detail the innovation method of product system design, which is taken as its concept to carry out the analysis on the component elements of hairdryers and the overall analysis and review of the system design process of hair dryers. Most people are familiar with the daily routine of washing, drying, and styling their hair. Although hair will eventually dry on its own if given enough time, most people reach for a hair dryer to speed up the process. Hair dryer are commonly used and can cause hair damage such as roughness, dryness and loss of hair color. The design of hairdryer is using CAD software and then transfer to Finite Element Analysis (FEA) to analyses the capabilities of part design. At the end of this project, this research will give understanding about design using CAD software and do analysis that improved the hairdryer equipment.
      3  2
  • Publication
    Analysis of an assembly process and environmental impact for a new design of food grater
    ( 2021-05-03)
    Mohd Effendi Muhammad Suandi
    ;
    Shayfull Zamree Abd. Rahim
    ;
    Radhwan Hussin
    ;
    Zuhanis Mansor
    ;
    Shafeeq Ahmad Shamim Ahmad
    ;
    Hidayatul Husna Al Rashid
    ;
    Nurin Syuhada Noorazman
    ;
    Muhammad Iqbal Talib
    ;
    Muhammad Adam Al-Modthaqim Muhammad Basri
    This research analyses and evaluate food grater components in order to reduce the required quantity and to consider the improvement of possible sustainable design based on various material selection, particularly to specific parts. This study will use integration methodology to achieving sustainability which is Design for Manufacturing Assembly (DFMA), and Life Cycle Analysis (LCA). The analysis result will show the reduction of the part numbers from 20 parts to only four parts respectively to the significant alteration for specific components. Furthermore, the Life Cycle Analysis (LCA), the weight is reduced by 12.46 gram after changing the material from PPE to ABS. Also, the carbon footprint effect reduced by 40% while air acidification effect is reduced by 21.9%. Besides the material changes also reduced the total energy consumed by 36.4%. This study found that both methods are capable of reducing production costs assembly time, and consequently can enhance the environmental impact of a product.
      2  1
  • Publication
    ARx modeling of flexible beam system using bat algorithm
    ( 2021-05-03)
    Mohd Sazli Saad
    ;
    Noor Fadhilah Mat Ros
    ;
    Mohd Zakimi Zakaria
    ;
    Mohamad Ezral Baharudin
    ;
    Azuwir Mohd Nor
    This paper describes the development of dynamic model of flexible beam system using system identification method based on nature inspired algorithm i.e. bat algorithm. At first, input-output data from the experimental rig of flexible beam were collected such that input signal is taken from piezo actuator and output signal from the laser displacement sensor. Then, linear parametric model structure is accomplished using auto regressive with exogenous inputs (ARX). The optimal parameters of the ARX model are identified using bat algorithm. The best parameter setting estimation is selected based on the best fit criterion i.e mean square error (MSE). The identified model is compared with the model from conventional estimation approach. Simulation results show that bat algorithm can outperform the least square algorithm in parametric modelling of the flexible beam.
      4  2
  • Publication
    Design and development of fire escape window grille keyless locking system
    ( 2021-07-21)
    Mohd Shuhidan Saleh
    ;
    Ng Kuan Yee
    ;
    Noorhafiza Muhammad
    ;
    Muhamad Farizuan Rosli
    ;
    Mohd Fathullah Ghazli@Ghazali
    ;
    Norshah Afizi Shuaib
    The most fire-related fatalities are due to the smoke inhalation of the toxic gases. It is related to the victims being trapped in the building when the building was on fire. It was also reported that major deaths from fire related are from the toxic gases inhalation produced by the fire while the deaths due to fire flames and burning was about one third of the total deaths. The access to the exit door was blocked and they could not exit through the window due to the permanent grille installation. It was well aware that most Malaysian homeowners installed grilles on their house windows or doors for security reason since there are lots of break-ins incidences. To overcome the issue, this work introduces a window grille with keyless locking system. The design incorporated keyless system that can be operated or opened without a key. Several designs for implementing this solution have been described. These designs are divided into three sections, which is a grille design, expansion designs which use to accommodate a wide range of window-sized and keyless locking systems. The size and type of grille suitable for Malaysian residents as well as the more efficient keyless locking system has been studied in detail using the method of case study and survey method. Step of patent research, market analysis and benchmarking are used as methods for collecting reference data. The most effective fire escape window grille keyless locking system has been studied and designed from this project. An important factor in designing a fire window grille is the design that can be opened and does not require a key operation. The results of the design and analysis tested are presented such that they can be used as an aid to the design of fire escape features.
      3  3
  • Publication
    Development of In-situ Sensing System and Classification of Water Quality using Machine Learning Approach
    ( 2022-01-01)
    Abdul Syafiq Abdull Sukor
    ;
    Mohamad Naim Muhamad
    ;
    Ab Wahab M.N.
    Quality of water applied to the agriculture sector is one of the factors for agriculture farming to be successful. The use of bad quality irrigation water can cause soil problems. In general, determining water quality model is one of the many interests as it can be used to classify the conditions of water. This project focuses on developing the in-situ sensing system of water quality sensors that can detect parameters of water quality such as pH level, electric conductivity, temperature and total dissolved solid. To validate the approach, there are three types of water samples in a dataset that was collected which include water pipes, soap water and drain water. The types of machine learning models used for classification process are Artificial Neural Network (ANN), Support Vector Machine (SVM), and Decision Tree. The performance showed that SVM model was the highest, ANN was intermediate, and Decision Tree was the lowest. This shows that the SVM model of machine learning approach is the most suitable to be used as the classification model to classify the status of water quality.
      1
  • Publication
    Enhancing the environmental impact of alarm clock using DFMA and sustainable design analysis
    ( 2021-07-21)
    Mohd Effendi Muhammad Suandi
    ;
    Shayfull Zamree Abd. Rahim
    ;
    Radhwan Hussin
    ;
    Shafeeq Ahmad Shamim Ahmad
    ;
    Nazirul Mubin Abd Aziz
    ;
    Muhammad Zahier Mohd Zubir
    ;
    Muhammad Azri Rosli
    ;
    Muhammad Syauqi Mohamad
    ;
    Tengku Ashraf Tengku Wasa
    This study focuses on evaluating a new alarm clock components and function to reduce the necessary quantities and to determine the potential to enhance sustainable design. The project aims to create a new alarm clock to enhance or improvise the alarm clock. To evaluate the built component, the CAD programme is used to create the new alarm clock and then transferred to FEA. The research will lead to understanding the use of CAD tools for the design and study of alarm clock enhancement by carrying out the project. This new approach shows that the tools that are to be used to reduce the cost of creating a new alarm clock and to enhance the environmental aspects of product design are successful.
      5  2
  • Publication
    Image Processing Approach for Detection and Quantification of Corrosion Behaviour of AZ91D Magnesium Alloy
    ( 2022-01-01)
    Zuraila Iberahim
    ;
    Mohd Zamzuri Mohammad Zain
    ;
    Abdul Halim Ismail
    ;
    Alias J.
    ;
    Muhammad Aiman Ahmad Fozi
    ;
    Nooraizedfiza Zainon
    ;
    Marina Marzuki
    The AZ91D magnesium alloy is known for its high strength-to-weight ratio, excellent machinability and good castability making it an ideal material to be used in automotive components fabrication. But due to its weak corrosion resistance towards the environment, identifying and quantifying AZ91D magnesium alloy corrosion behaviour before any manufacturing processes can be a huge impact and may provide useful information to the manufacturers. The limitation of conventional corrosion detection and quantification methods also justify the further needs of image processing approach in this study. This paper study the feasibility of an image processing approach using the automatic thresholding method and various manual thresholding level in order to identify the corrosion attack on the AZ91D magnesium alloy. This method converts the original colour image to grayscale image and then convert it to binary image. Then through image processing approach, the image will be segmented to non-corroded and corroded area and labelled as 0 (black) and 1 (white) and make it easier to analyze. The white dots (1) distribution was then presented in percentage to shows that the pitting corrosion on the surface can be identified better by using the Otsu’s method of automatic thresholding. The resulting image of various thresholding shows which thresholding values successfully portray similarity of the original corrosion image. Thus, this increases the reliability of AZ91D magnesium alloy corrosion detection and quantification via image processing approach.
      1
  • Publication
    Improvement of Corrosion Resistance of Rare-Earth Element (REE) – Based Anodic Coating on Biodegradable Magnesium Alloy
    ( 2021-01-01)
    Nursyifa' Hamir Hamzah
    ;
    Nur Liyana Mohd Rosli
    ;
    Nooraizedfiza Zainon
    ;
    Siti Khalijah Kamarudin
    AZ91D alloy has been widely used in fields of materials science, tissue engineering, biomedicine, and analytical science due to its simple preparation, low-cost, and high biocompatibility. To overcome their weaknesses which low corrosion resistance due to high surface reactivity. The effectiveness of the lanthanum (La) on corrosion resistance, has exhibited great potentials for improving its protective properties. AZ91D alloy has been coated with lanthanum nitrate and magnesium nitrate through anodizing at fixed concentration and treatment time, with various current density. Surface roughness, elemental compositional analysis, surface morphology analysis, and corrosion behavior were analyzed for the corrosion response at various current density. JIS H 0541 Standard was used to determine the corrosion rate of the samples. It is showed that the sample undergoing 10 mA/ cm2 current density indicated the highest corrosion resistance due to their value on corrosion rate 8.6 mm/year was the lowest value and their surface roughness 0.199 µm was in the range of recommended roughness for a biomedical implant.
      3  1
  • Publication
    Optimization of heating rate on hybrid microwave sintering of the PM Fe-Cr MMCs reinforced with Al2O3particle
    ( 2021-07-21)
    Rahman W.
    ;
    Shayfull Z.
    ;
    Radhwan H.
    ;
    Farizuan R.M.
    ;
    Fathullah M.
    ;
    Darus M.
    This study reports the optimization of heating rate on the microwave sintered Fe-Cr-Al2O3 metal matrix composite (MMC). The heating rate was selected between 10°C/min to 60°C/min with increment of 10°C/min respectively. The samples were fabricated via PM route and microwave sintering was carried out in a tubular microwave furnace HAMiLab-V3 in N2 atmosphere purposely to avoid any oxidation and chemical reaction to samples. The microstructure of sintered samples was evaluated using SEM and bulk density and porosity were determined based on ASTM B962 - 17 and the microhardness were determined based on ASTM E384. The optimized heating rate of the sample was selected based on the micro hardness value and total porosity percentage as well as based on SEM microstructure analysis. The results revealed that the optimum heating rate occurred at 20°C/min due to the highest value of hardness achieved which is about 119.28 HV with at the highest bulk density about 6.07 g/cm3 and at the lowest total porosity about 14.55%. SEM micrographs also showed that the diffusion was mostly effective at 20°C/min heating rate compared to others, indicated that significant grain boundary diffusion of Fe matrix into Al2O3 particle was occurred.
  • Publication
    Product simplification design improvement by using DFMA method DFMA analysis on measuring tape
    ( 2021-07-21)
    Muhamad Farizuan Rosli
    ;
    Shayfull Zamree Abd. Rahim
    ;
    Mohd. Nasir Mat Saad
    ;
    Shafeeq Ahmad Shamim Ahmad
    ;
    Muhammad Harris Al-Hakeem Zuhdi Lokman
    ;
    Nursyafikah Marzuki
    ;
    Muhammad Ilham Saidi
    ;
    Nur Alia Hidayati Che Mat
    For this project, it is focused on the improving design and analysis measuring tape. Measuring tape is not a new thing to us. It is a high demand product in surveyor industry. Currently, they are a lot of measuring tape design are selling in the market. The objectives of this project are to design the measuring tape and to decrease the time to assembly the product. Besides, it also learn on to analyse the cost of manufacturing of the product. The design of measuring tape is using CAD software and then transfer to Finite Element Analysis (FEA) to analyses the capabilities of part design. At the end of this project, this research will give understanding about design using CAD software and do analysis that improved the measuring tape.
      10  4
  • Publication
    Smart Waste Management System
    ( 2022-01-01)
    Ab Wahab M.N.
    ;
    Tay S.C.
    ;
    Abdul Syafiq Abdull Sukor
    ;
    Mohamed A.S.A.
    ;
    Mahinderjit Singh M.
    The increasing amount of waste in landfill has created a serious environmental problem which demands a more reliable solution in handling the collection of wastes. To this date, recycling is one of the solutions to manage the waste as it collects and processes recyclable materials into new products instead of throwing the trash to the landfill. However, the consciousness of recycling in our society is still devastatingly lower than expected as people are faced with many challenges that impede them to recycle. One of the challenges is to segregate the waste according to its group. People are still having difficulty to clearly distinguish recyclable materials due to the lack of recycling knowledge. Thus, this paper aims to develop a system that can separate the waste automatically and channel them to the proper bins. To do that, a camera is used to capture the image of the waste. Then, image classification using deep learning model is used to classify different types of wastes. The developed model is then embedded in Raspberry Pi and a servo motor is used to direct the waste to the respective bins for real-world implementation. Experimental results show that the proposed system can identify the categories of waste within the accuracy of 77–85%. This system is expected to deliver the importance of recycling and cultivate recycling practices to the public and finally reduced waste generation on land.
      1