Allan Melvin Andrew
Thumbnail Image
Preferred name
Allan Melvin Andrew
Official Name
Allan Melvin, Andrew
Alternative Name
Andrew, Allan Melvin
Andrew, Allan M.
Melvin, A. A.
Main Affiliation
Scopus Author ID
36469871200
Researcher ID
GDH-3820-2022

Research Output

Filters

46 1
46
Reset filters

Settings
Now showing 1 - 10 of 46
  • Publication
    Optimized Intelligent Classifier for Early Breast Cancer Detection Using Ultra-Wide Band Transceiver
    ( 2022-11-01)
    Halim A.A.A.
    ;
    Allan Melvin Andrew
    ;
    Wan Azani Wan Mustafa
    ;
    Mohd Najib Mohd Yasin
    ;
    Muzammil Jusoh
    ;
    Vijayasarveswari Veeraperumal
    ;
    Abd Rahman M.A.
    ;
    Zamin N.
    ;
    Mary M.R.
    ;
    Khatun S.
    Breast cancer is the most common cancer diagnosed in women and the leading cause of cancer-related deaths among women worldwide. The death rate is high because of the lack of early signs. Due to the absence of a cure, immediate treatment is necessary to remove the cancerous cells and prolong life. For early breast cancer detection, it is crucial to propose a robust intelligent classifier with statistical feature analysis that considers parameter existence, size, and location. This paper proposes a novel Multi-Stage Feature Selection with Binary Particle Swarm Optimization (MSFS–BPSO) using Ultra-Wideband (UWB). A collection of 39,000 data samples from non-tumor and with tumor sizes ranging from 2 to 7 mm was created using realistic tissue-like dielectric materials. Subsequently, the tumor models were inserted into the heterogeneous breast phantom. The breast phantom with tumors was imaged and represented in both time and frequency domains using the UWB signal. Consequently, the dataset was fed into the MSFS–BPSO framework and started with feature normalization before it was reduced using feature dimension reduction. Then, the feature selection (based on time/frequency domain) using seven different classifiers selected the frequency domain compared to the time domain and continued to perform feature extraction. Feature selection using Analysis of Variance (ANOVA) is able to distinguish between class-correlated data. Finally, the optimum feature subset was selected using a Probabilistic Neural Network (PNN) classifier with the Binary Particle Swarm Optimization (BPSO) method. The research findings found that the MSFS–BPSO method has increased classification accuracy up to 96.3% and given good dependability even when employing an enormous data sample.
  • Publication
    Phyton-Based Smart Algorithm for 3 × 3 Rubik’s Cube Solver
    ( 2021-01-01)
    Allan Melvin Andrew
    ;
    Nik Zainab Nik Azizan
    ;
    Amirah A.S.N.
    ;
    Ragunathan Al Santiagoo
    ;
    Tan Wei Hong
    ;
    Faridah Wahab
    ;
    Rezal S.
    Rubik’s cubes are exciting to be play with, but solving it can be a bit tricky, especially when we are not having the insight of how to solve it. There are many ways to solve it. This research is about creating a Phyton based- program to solve a physical Rubik’s cube. This research uses webcam as sensor, and Raspberry Pi microcontroller to generate solution from images to twist Rubik’s cube using servo actuators. To make it easy to be used, the program is equipped with Graphical User Interface (GUI) and Internet of Things (IoT). Hence, the program run in a smartphone, web- based systems through internet to give information about the performance of the project. The research is intended to create a Rubik’s cube solver which can be used for education purpose and to help people solving Rubik’s cube autonomously using Internet-of-things. The initial prototype is limited to solve 3 × 3 standard Rubik’s cube with dimension 5.7 × 5.7 × 5.7 cm. This project uses Python language to create improvised Kociemba program and GUI. The developed coding is tested on the 3D printed Rubik’s Cube Solver. Based on the test conducted with implementation in the prototype, the robot manage to solve the Rubik’s cube with an average of 21 moves.
  • Publication
    Fabrication and Mechanical Testing of Blended PVOH/Kenaf Reinforced Starch Composite for Future Packaging Application
    ( 2021-01-01)
    Ragunathan Al Santiagoo
    ;
    Nik Zainab Nik Azizan
    ;
    Allan Melvin Andrew
    ;
    Faridah W.
    ;
    Tan W.H.
    ;
    Amirah A.S.N.
    ;
    Othman N.S.
    The mechanical and morphological properties of PVOH/kenaf fibre thin film was studied. The additive used on this research was tapioca starch. Thin films were fabricated using method of solution casting. The thin films composites with different kenaf fibre loadings (0, 5, 10, 15, 20, 30 wt%) were mixed at a temperature of 80 °C with water bath for 1 h and casted on petri dish and let them oven dried at 50 °C for 24 h. The purpose of the current research was to determine the mechanical and morphological properties of PVOH/KF thin film composites with and without addition of starch. The results of this investigation show that the thin film with addition of 5 wt% of tapioca starch has better tensile strength, which is 35.15 MPa, compare to without tapioca starch, which is 29 MPa. The second major finding was that the morphological observed using scanning electron microscope (SEM) reveals improvement of adhesion between kenaf fibre with PVOH matric as addition of tapioca starch.
  • Publication
    Development of smart GPS-based nurse following robot
    ( 2021-07-21)
    Allan Melvin Andrew
    ;
    Faridah Wahab
    ;
    Tan Wei Hong
    ;
    Ragunathan Al Santiagoo
    ;
    Amirah A.S.N.
    ;
    Nik Zainab Nik Azizan
    ;
    Yi T.P.
    Hospital nurses regularly bring their medicines and healthcare items to the patients using trolley. They need to push or pull the cart to the patient's beds, and then, need to bring it back to the original position many times daily. It can be tiresome for nurses because in a day, they need to treat many patients in the hospital. Thus, many devices have been invented to assist the nurses in their daily work routines. This research is focusing on developing a nurse following mobile robot that follows and carries medical items. The mobile robot is integrated with microcontroller, Global Positioning System (GPS) module, digital compass module and Bluetooth module. To use the robot, the nurse firstly needs to connect her smartphone to the robot through Bluetooth connection. Once the connection is established, the robot will start to follow the nurse. The robot can carry a maximum load of 5 kg and uses two direct current geared motors and a caster wheel to move.
  • Publication
    Investigation on effect of gas concentration in distinguishing conventional plastic and bioplastic for plastic recycling
    ( 2022-12)
    Ragunathan Al Santiagoo
    ;
    Allan Melvin Andrew
    ;
    Wan Amiza Amneera Wan Ahmad
    ;
    Razi Ahmad
    ;
    Syakirah Afiza Mohammed
    ;
    Abdul Ghapar Ahmad
    ;
    Vikneswaran Vijean
    ;
    Mustaffa Zainal
    Distinguishing type of plastic was important for the recycling process. In this project, the effect on gas concentration released from composite was studied to distinguish between conventional plastic and bioplastic. This project involved the fabrication of a composite from polypropylene (PP), empty fruit bunches (EFB), and recycle acrylonitrile butadiene rubber (NBRr), with PP used as a conventional plastic and PP/NBRr/EFB used as a bioplastic. Trans-polyctylene (TOR) was used as a compatibilizer to evaluate the effect on the PP/NBRr/EFB. Tensile testing and SEM were conducted to study the mechanical properties and morphological properties on the PP/NBRr/EFB and the PP/NBRr/EFB/TOR composite. The gas sensor (MQ135) was used in this study to detect the presence of NH3 and CO2 released from heating conventional plastic and bioplastic. From the overall result, composite with TOR as compatibilizer has shown better performance than composite without TOR in mechanical, morphological and gas sensor testing. By using MATLAB software, it shows that from gas sensor testing, it can be verified to distinguish between conventional plastic and bioplastics for plastic recycling. The average classification obtained from the Probabilistic Neural Network (PNN) was 99.29 % accurate.
  • Publication
    The use of media filters in treatment of runoff pollution
    ( 2021-02-23)
    Amirah A.S.N.
    ;
    Ragunathan Al Santiagoo
    ;
    Nik Zainab Nik Azizan
    ;
    Allan Melvin Andrew
    ;
    Faridah Wahab
    ;
    Tan Wei Hong
    ;
    Salwa Mohd Zaini Makhtar
    The study will examine the ability of recycled aggregates and sand to classify wastewater in a manner that decreases the level of environmental pollution. The sample was taken from Kg Wang Ulu, Perlis agricultural district, Jejawi, Perlis industrial area and Taman Desa Katong, Perlis residential area. Water quality research has been investigated to find the characteristics of effluent such as suspended solids, BOD, COD and TSS. Three rainfall intensity values, of 5 LPM as low rainfall, 12.5 LPM as mean precipitation intensity, and 22.5 LPM as high-cut rainfall consisted of recycled aggregate and high-absorptive sand as drainage beds, were included in this operating system. Experimental findings indicate that the recycling of aggregates and sand filters has a positive effect on water in industrial and residential areas. It shows that the use of recycled aggregates as a drainage bed can increase the permeability of the region by reducing erosion, preventing flooding and promoting natural infiltration.
  • Publication
    Prototype Design for Rubik’s Cube Solver
    ( 2021-01-01)
    Allan Melvin Andrew
    ;
    Faridah Wahab
    ;
    Tan Wei Hong
    ;
    Ragunathan Al Santiagoo
    ;
    Amirah A.S.N.
    ;
    Nik Zainab Nik Azizan
    ;
    Lee F.S.
    Rubik’s cube is a modern day plastic material puzzle, where the one need to twist and turn to solve the multicolour squares. At the end, the puzzle need to be solved to make all the same colour cubes on the same surfaces. High intelligence is needed to solve it at a shorter time. Therefore, this research is to create a robot solver to solve the Rubik’s cube in short time smartly. Initially, the algorithm will scan the six surfaces of unsolved cube through a webcam and register the colours in the memory. Once it is completed, the solving algorithm will analyse and instruct the servo motors to twist and turn based on the computed solution. It is then pass it to the solving algorithm to identify the solving process and send the moving instruction to the motors by Raspberry Pi. The robot body was constructed using laser cutter. It is to make sure that the measurements are accurate and correct. To solve the cube, four servo motors with high efficiency were used to twist the cube in certain legit with the rules of the game. Another four servo motors are connected to the rack and pinion gears by clamping to hold the Rubik’s cube from falling when it is twisted. An improvised “Kociemba Algorithm”, also called as “The Two-Phase-Algorithm” is used. It reduced the required moves to solve the cube into a maximum of 25 moves and a minimum of 19. Conclusively, the final prototype discussed in this paper is tested with the solving algorithm. The results are presented.
  • Publication
    Mathematical Modelling Development of Sound Transmission Loss for Laminated Glass Using Response Surface Methodology
    ( 2021-01-01)
    Tan Wei Hong
    ;
    Faridah Wahab
    ;
    Allan Melvin Andrew
    ;
    Nik Zainab Nik Azizan
    ;
    Ragunathan Al Santiagoo
    ;
    Amirah A.S.N.
    ;
    Lim E.A.
    The purpose of this study is to identify parameters that affect the rate of sound transmission loss. Mathematical model of sound transmission loss (STL) is developed for laminated glass and maximize the STL of laminated glass by using response surface methodology (RSM). The main objective of this study is to determine the type of material and number of interlayers for laminated glass on the STL performance. The two-load transfer function method (TFM) coupled with LMS Test Lab Acoustic software to determine the STL. The analysis was made by observing the performance of STL with respect to different materials used, such as glass and Perspex. Besides that, number of interlayers for laminated glass also had been studied for the performance of STL. Next, the RSM will be applied to develop mathematical modelling of STL for laminated glass. Optimization on the variable of laminated glass also has been conducted to obtain optimum variable of laminated glass in order to deliver optimum STL performance.
  • Publication
    A study of water distribution near Taman Seri Wang, Arau, Perlis
    ( 2021-02-23)
    Nor Amirah Abu Seman @ Haji Ahmad
    ;
    Tan W.H.
    ;
    Faridah Wahab
    ;
    Allan Melvin Andrew
    ;
    Nik Zainab Nik Azizan
    ;
    Ragunathan Al Santiagoo
    ;
    Salwa Mohd Zaini Makhtar
    The water distribution system consists of a network of pipelines of different sizes with control valves for transporting water to all streets and providing water to consumers through the water distribution system. The water distribution system may either be continuous or intermittent. Water is available 24 hours a day and seven days a week throughout the continuous water distribution network. This study was conducted to access the water distribution near Taman Seri Wang (TSW) in Arau, Perlis. Research had been outlined to access the existing water distribution at RPA ARAU, to identify the head loss of water distribution at TSW ARAU and to determine the relationship between node demand and pressure of water distribution system at TSW ARAU. A quantitative method was used in this study, which gathers the data parameter from Syarikat Air Perlis (SAP) generated using EPANET software to calculate the head loss inside the pipe Hazen - William equation. The flow rate shows a declining value at nodes 42, 34, 54 and 46 after an analysis of 0700 hours. Simultaneously, a higher proportion of head loss is found in mainly link 1 of the water intake point and link 15 in the water tank near the study area.
  • Publication
    Characterization and Properties of Pp/Nbrr/Kenaf Composites with Epoxy Resin Compatibilizer
    ( 2021-01-01)
    Faridah Wahab
    ;
    Allan Melvin Andrew
    ;
    Nik Zainab Nik Azizan
    ;
    Ragunathan Al Santiagoo
    ;
    Amirah A.S.N.
    ;
    Tan Wei Hong
    ;
    Iqbal C.M.M.N.
    The incompatibility between the natural fiber and the polymeric matrix composite due to hydrophilic and hydrophobic characteristic of the respective materials results in lower mechanical properties of the composite. Epoxy resin (EP) compatibilizer was added into the polypropylene (PP)/ recycled acrylonitrile butadiene rubber (NBRr)/ kenaf composites and the effect to the tensile strength has been investigated. The composites were prepared by mix melt PP and NBRr with Kenaf filler by using heated two roll mill at temperature of 180 ºC with speed of 15 rpm for 9 min. The ratio of PP/NBRr was varied from 100:0 up to 40:60 phr while kenaf filler and EP remain constant at 15 phr and 4 phr respectively. The samples were molded to form 1 mm sheet by using a hot press at 180 ºC temperature before cut in-to dumbbell shape. The tensile testing was conducted according to ASTM D638 (2003) Standard Test Method by using Instron Universal Testing Machine 3366 with crosshead speed of 5 mm/min. The Fourier Transform infra-red (FTIR) analysis and swelling test were also performed. The results of tensile test show that the tensile strength and modulus of elasticity were decreased with the increasing of NBRr ratio but increased the elongation at break (Eb). The composite with EP showed a better performance in both tensile strength and modulus of elasticity with increment 4–28% and 29 to 50% respectively, along the varies ratio. But, the Eb had reduced about 0.9 to 1.65%. FTIR results showed the spectra of C ≡ N at peak 2237.87 cm-1 was lost due to the esterification of PP/EP compatibilizer with kenaf or PP/EP compatibilizer with NBRr. The swelling test indicated higher water uptake for non-compatibilized composites as compared to compatibilized with EP compatibilizer.