Mei Choo Ang

Minimum-time motion planning for a robot arm using the Bees Algorithm

The problem of determining the minimum motion time for a robot arm is not new. Several approaches have been successfully proposed to solve this problem. One of these approaches involves generating a fixed number of joint displacements to construct the joint trajectories via cubic spline functions before scaling the travel time to avoid violating kinematic constraints such as the maximum permissible velocity, acceleration and jerk. Conforming to these kinematic constraints is necessary to prevent trajectories that are undulant and normally unsuitable for robotic motion. This paper presents a Pareto-based multi-objective Bees Algorithm to determine the minimum travelling time for a SCARA-type robot arm that takes consideration of trajectory smoothness. The results obtained are better than those reported for solutions using the genetic algorithm (with breeder genetic algorithm operators and the path redistribution with relaxation operator), the Nelder-Mead flexible polyhedron search and the improved polytope algorithm with a penalty function.

TRIZ-inspired Asymmetrical Search Neighborhood in the Bees Algorithm

The Bees Algorithm, a heuristic optimization procedure that mimics bees foraging behavior, is becoming more popular among swarm intelligence researchers. The algorithm involves neighborhood and global search and is able to find promising solutions to complex multimodal optimization problems. The purpose of neighborhood search is to intensify the search effort around promising solutions, while global search is to enable avoidance of local optima. Normally, a symmetrical search neighborhood is employed in the Bees Algorithm. As opposed to this practice, a TRIZ-inspired asymmetrical search neighborhood was tried in this work to explore the significance of neighborhood symmetry. The algorithm with an asymmetrical search neighborhood was tested on an engineering design problem. The analysis verified that under certain measurements of asymmetry, the proposed algorithm produced a similar performance as that of the Bees Algorithm.

Combining the Bees Algorithm and shape grammar to generate branded product concepts

Generating product design concepts to meet functional requirements while maintaining a specific brand identity is a daunting task for a designer. Shape grammars have been applied to describe the creation of branded product shapes via a set of shape rules and were manually used to create a family of new design concepts, which maintain the product brand identity. Nevertheless, shape grammars are not able to evaluate whether the generated new product concepts can fulfil specified functional requirements of a product. In this research work, shape grammar is combined with an optimisation technique known as the Bees Algorithm to derive a computational architecture for generating branded design concepts that can meet a specified functional requirement. This combination approach allows shape rules to evolve while evaluating how well the outcomes of the new design concepts meet a specified functional requirement. This paper describes how the combination of the Bees Algorithm with shape grammar is created to generate branded product concepts, and shows that this approach can outperform a combination of shape grammar with an evolutionary algorithm.

Applying TRIZ to Support Designers in a Descriptive Design Framework

Designing a new product can be a challenging task particularly for a novice designer. This paper explores the application of TRIZ to assist a designer in performing this task within a descriptive design framework. The descriptive design framework permits the designer to track his ideas throughout the design process. The ‘technical contradiction matrix’ of TRIZ is integrated into this framework to allow it to provide support to designers. This contradiction matrix is adapted to enable designers to assign their levels of belief or preference to contradicting features to solve design problems. This preference assignment allows more emphasis to be placed on the critical features of a design problem. The proposed TRIZ-based system was tried out on a novice designer in a case study to design a scheme to support concrete filling between beams.Copyright

Simulations of PCB Assembly Optimisation Based on the Bees Algorithm with TRIZ-Inspired Operators

The process of assembling electronic components on a printed circuit board (PCB) with moving board time delay characteristic involves complex co-ordination of a component feeding system, a pick and place system and the positioning movement of the PCB board. Different component arrangements in the feeder system and different assembly paths influence the total assembly time. Reducing the total assembly time can deliver significant cost savings. In this research work, the application of simulation to component assembly enables process engineers to visualise, compare assembly paths and the arrangement of the feeders as well as to verify the total assembly time achieved. This allows the process engineers to make better decision on the planning of the PCB assembly process. The paper shows that simulation when coupled with optimisation techniques enable process engineers to make and plan improvements in PCB assembly times.

A parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos

Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these methods, the spatiotemporal saliency detection approach reported promising results in the context of moving target detection. However, it is not accurate for moving target detection when visual tracking is performed under appearance variations. In this study, a visual tracking method is proposed based on spatiotemporal saliency and discriminative online learning methods to deal with appearance variations difficulties. Temporal saliency is used to represent moving target regions, and it was extracted based on the frame difference with Sauvola local adaptive thresholding algorithms. The spatial saliency is used to represent the target appearance details in candidate moving regions. SLIC superpixel segmentation, color, and moment features can be used to compute feature uniqueness and spatial compactness of saliency measurements to detect spatial saliency. It is a time consuming process, which prompted the development of a parallel algorithm to optimize and distribute the saliency detection processes that are loaded into the multi-processors. Spatiotemporal saliency is then obtained by combining the temporal and spatial saliencies to represent moving targets. Finally, a discriminative online learning algorithm was applied to generate a sample model based on spatiotemporal saliency. This sample model is then incrementally updated to detect the target in appearance variation conditions. Experiments conducted on the VIVID dataset demonstrated that the proposed visual tracking method is effective and is computationally efficient compared to state-of-the-art methods.

Enhancing calculus learning via a student-centred web project

Calculus is not a subject that interests many students. However, it is an important fundamental subject to a broad range of education courses particularly, engineering, physics and information technology. This research looks into ways to instill and enhance the interest of students to Calculus using a student-centered web project. In this research, students who were taking the subject Calculus were divided into groups and were assigned to a web project in addition to the conventional lectures and tutorials. This project basically requires students to develop websites to present their modeling and integration application of their chosen product. They are required to derive the cross-section and volume of the product and then validate their results. This project aims to connect the contents in the Calculus course with the real world whereby a problem from the real world was introduced and solved using Calculus techniques. Two surveys were conducted, one at the beginning of the course and the other at the en...

Using TRIZ to Generate Ideas to Solve the Problem of the Shortage of ICT Workers

With the ever competitive global market swamped with more choices of high-tech gadgets from smartphones to head-mounted display eyewear like “Google Glass”, Information and Communication Technology (ICT) is one of the key factors to engineering and technological advancement and the bridge to the future. In view of such significant importance, the government of Malaysia has been embarking on national policies to prioritise the education and the programmes on ICT to train and produce highly skilled ICT workers to achieve the nation’s ambition to become a developed country. Despite the government efforts, studies have shown that Malaysia is still currently facing shortage of skilled ICT workers. In view of this shortage of skilled ICT worker problem, a systematic engineering problem solving theory known as TRIZ is applied to generate ideas and potential solutions to solve this problem in this research.

Investigation of Threading Building Blocks Framework on Real Time Visual Object Tracking Algorithm

Object tracking plays important roles in various applications such as surveillance, search and rescue, augmented reality and robotics. This paper presents an investigation on multi-threading framework capability for color-based object tracking applications. A multi-threading framework based on Threading Building Blocks (TBB) was implemented on a multi-core system to enhance the image processing performance on a real-time visual object tracking algorithm. Intel Parallel Studio was used to implement this parallel framework. The performance between sequential and multi-threading framework was evaluated and compared. We demonstrated the multi-threading framework was approximately two times faster when compared to the sequential framework in our experiments.