Mariam Md Ghazaly

Traffic Sign Detection and Classification for Driver Assistant System

In this paper we explain the proposed method of traffic sign detection and classification for driver assistant system (DAS). Color detection framework using RGB method is utilized in this study, whereas an artificial neural network (ANN) has been used as classifiers for classification. There are at least 100 types of Malaysian Traffic Signs have been employed in this research. Most of the images are taken at various places throughout the urban and suburban areas involved with scale, illumination and rotational changes as well as occlusion images. The experimental results are shown that the proposed framework achieved at least 80 % successful detection with 21 false positive images. On the other hand, the ANN gives strong rates where at least most of the signs can be classify with more than 85 % success.

Object classification and recognition using Bag-of-Words (BoW) model

This paper presents the findings on Object Recognition using Bag-of-words model done by the author. The introduction section covers the basic introduction to image processing and object recognition. Details description on the flow of experiment conducted as part of the research will be given in the methodology section. Clear explanation on Bag-of-Words model and Confusion Matrix is included in section III and section IV respectively. Finally, a preliminary result is shown together explanation and a brief conclusion is made at the end of this journal.

Individual processing speed analysis for traffic sign detection and recognition

Of late, traffic sign detection and recognition are becoming very prevalent topic as it enhances drivers towards safety and alert them with precaution information. This study reports about processing time of the individual color detection and recognition of the partial occlusion traffic sign that have been previously implemented using HSV and RGB color ratio and ANN and PCA method respectively for detection and recognition. The data set for detection and classification process has been successfully created in various places in Malaysia that involved with degradation and out of planes rotated of the signs. There are three standard types of colored images have been used in the study namely Red, Blue and Yellow signs. In this study, we analyze the system processing speed of individual color detection and classification respectively using red, green and blue (RGB) and hue, saturation and value (HSV) color segmentation techniques, supervised feed forward artificial neural network (ANN) and principal component analysis (PCA). The experimental result shown that processing time of individual color detection during daytime and at night using HSV method is slightly faster than RGB technique. On the other hand, supervised feed forward neural network has reached almost 1s in recognizing traffic sign images rather than PCA with only 0.0238s.

Local Binary Pattern (LBP) with application to variant object detection: A survey and method

This paper study about variants object detection by using local binary pattern. Local binary pattern is one of the famous method in object detection field because of its success used in object detection. The objective of object detection is to differentiate between object and background. However, LBP also has its own weaknesses in object detection. LBP modification that been proposed by a lot of researchers can overcome the weaknesses. In this paper, variants of local binary pattern method and modification has been study and analyze. All those local binary pattern modification has been extract its feature in term of object detection. The modifications are Non-Redundant Local Binary Pattern (NRLBP), Integral Local Binary Pattern (INTLBP), Multi-scale Block Local Binary Pattern (MBLBP) and Discriminative Robust Local Binary Pattern (DRLBP).

Design of a High Force Density Tubular Linear Switched Reluctance Actuator (TLSRA) Without Permanent Magnet

A novel tubular linear switched reluctance actuator (TLSRA) without permanent magnet that has 7:7 stator-to-mover pole pairs ratio is presented in this paper. A detailed analysis of the effect of mover parameters on the performances of proposed TLSRA is presented to determine the optimized actuator parameters. As comparison, the performances of the conventional TLSRA with 7:5 stator-to-mover pole pairs ratio is also designed and compared with the proposed TLSRA using the identical dimensions. The differences between the proposed and conventional TLSRA is number of available working pole pairs. The proposed TLSRA has four working pole pairs for a three phases actuator instead of two working pole pairs for conventional TLSRA. The additional working pole pairs in the proposed TLSRA exhibit force improvement, approximate two times higher compared to the conventional TLSRA. The static force characteristics for the proposed TLSRA is calculated and computed by using the three-dimensional finite element method (FEM) with ANSYS Maxwell software.

Optimization design and analysis of an underactuated dexterous robotic hand system

This paper presents the optimization of three-dimensional (3D) Printed Underactuated Dexterous Robotic Hand (UDRH) design and the analysis of the UDRH material. The UDRH design consists of three fingers and a thumb at which each finger has two links and two degrees of freedoms (DOF) and each joint of the finger is actuated by the DC Micromotor. The thumb has 3DOF to allow for adduction and abduction of the thumb. The robot hand is designed to be like human hand whereby higher performances in accuracy, stability and consistency can be achieved. The actuators are placed directly in each finger link so that the robot hand has several degrees of freedoms to achieve dexterous grasping. The angular rotation, speed, and torque have to be controlled for each individual joint to enable a more precise control. The structure of the UDRH robot hand is printed by using Flashforge Creator Pro 3D printer machine. In this paper, the optimization and analysis of fused deposition modeling (FDM) printed materials which are Acrylonitrile Butadiene Styrene (ABS), Polylactid Acid (PLA), Nylon, and Polycarbonate (PC) plastic are accomplished by testing for their stress and deformation through finite element analysis by using Solidworks software. From the analysis, the critical points and the parts of the UDRH design that are prone to damage under high force and temperature can be detected. In this study, ABS plastic material is chosen for UDRH prototype due to its properties which are resistance to heat which is 5.47 × 106N/m2, and high melting point of 210°C compared to the other materials.

Force Characterization of a Rotary Motion Electrostatic Actuator based on Finite Element Method (FEM) Analysis

Two types of rotary motion electrostatic actuators were designed and analyzed using Finite Element Method (FEM) analysis. This paper discussed the comparisons and detailed thrust force analysis of the two actuators. Both designs have similar specifications; i.e the number of rotor’s teeth to stator’s teeth ratio, radius and thickness of rotor, and gap between stator and rotor. Two structures were designed & evaluated; (a) Side-Driven Electrostatic Actuator and (b) Bottom-Driven Electrostatic Actuator. The paper focuses on comparing & analyzing the generated electrostatic thrust force for both designs when the electrostatic actuator’s parameters are varied. Ansys Maxwell 3D software is used to design and analyze the generated thrust force of the two rotary motion electrostatic actuators. The FEM analyses have been carried out by (i) varying the actuator size; (ii), varying the actuator thickness and (iii) varying the actuator teeth ratio. The FEM analysis shows that the Bottom-Drive Electrostatic Actuator exhibit greater thrust force, 4931.80μN compared to the Side-Drive Electrostatic Actuator, 240.96μN; when the actuator’s radius is 700μm, thickness is 50μm, gap between the stator and rotor is 2μm and the teeth ratio is 16:12.

Development of Passive Quarter Car Suspension Prototype

In this paper, a construction of a prototype to represent passive vehicle suspension system for quarter car model is considered. The prototype is represented by two degree-of freedom quarter-car model which are conventionally used by researchers. This laboratory equipment is developed in order to familiarize students with 2 DoF passive suspension system model. It consists of two masses, two springs and a damper. This equipment is easily dismantled and could be assembled with different spring and damper constants which contribute to different characteristics of the suspension system. A number of experiments have been carried out using the experiment setup in order to identify the suspension system characteristics i.e. experiments with different vehicle body mass, different period for one pulse and different pulse width of input pressure of the road excitation have been conducted. The experiment results are evaluated based on the vehicle body displacement and tire displacement of the prototype. Experiment results show that the pulse width of the input pressure or road profile is directly affected the characteristic of this passive suspension system. Lastly, simulations were done in order to compare the simulation and experimental results.