Fairul Azni Jafar

A novel graph computation technique for multi-dimensional curve fitting

Curve-fitting problems are widely solved using numerical and soft techniques. In particular, artificial neural networks (ANN) are used to approximate arbitrary input–output relationships in the form of tuned edge weights. Moreover, using semantic networks such as fuzzy cognitive map (FCM), single graph nodes could be directly associated with their actual grey scales rather than binary values as in ANN. This article examines a novel methodology for automatic construction of FCMs for function approximation. The main contribution is the introduction of nested-FCM structure for multi-variable curve fitting. There are step-by-step example cases along with the obtained results to serve as a guide to the new methods being introduced. It is shown that nested FCM derives relationship models of multiple variables using any conventional weight training technique with minimal computation effort. Issues about computational cost and accuracy are also discussed along with future direction of the research.

Investigation of Human Emotional State in Human-Robot Collaboration

In order for humans and robots to interact in an effective and instinctive manner, robots must obtain information about the human emotional state in response to the robot’s actions. This is important as the presence of robot in human living environment has become tremendously increasing. Consequently, we believed that it is necessary to investigate how human feel about this situation and if robot can understand those human emotions, collaboration with human can be much better. In order to investigate the human emotions, we applied a kansei survey method based on a kansei engineering technology. We request a number of participants to take part in our experiment where they will be in the same environment of where a robot is working on some tasks. The participants will answer those questions in the survey based on what they feel about working together with moving robot. The overall goal is, in fact, to predict in the least possible time which area in the vicinity of the robot the human is heading to. This paper describes the results of our findings about how human feel when collaborating with robot(s).

Development of genetic algorithm on multi-vendor integrated procurement-production system under shared transportation and just-in-time delivery system

One of the well-known inventory control techniques utilized in the supply chain is integrated inventory model. Recently, previous research [Z.X Chen and B.R Sarker, Multi-vendor integrated procurement-production system under shared transportation and just-in-time delivery system, Journal of the Operational Society 61 (2010) 1654-1666] have developed an integrated model to synchronize the production flow from multi-vendor to manufacturer through shared transportation. However, the model is complex to find the optimal solution. Because of these complexities, simplifications of the model are often based on limiting assumptions. Since the model is a non-linear integer programming type, this paper addresses genetic algorithm to overcome the limitations to find batch production lot size of vendors and manufacturer, delivery quantities and number of deliveries from different vendors to the manufacturer in order to minimize total cost of all parties involved in the supply chain. Furthermore, a numerical example is presented to illustrate the results.

Image Enhancement Filter Evaluation on Corrosion Visual Inspection

This project is focusing on corrosion inspection using image. Inspection which have particularly challenging environmental conditions and characteristics, increase the complexity of the inspection operation. By using software image filter to enhance the image data, it is believe that the object recognition technique will be able to analyse the image data accurately. A few software filters have been identified in this works based on textural feature and colour progression factor that are the characteristic of image corrosion. Therefore, in order to obtain suitable software image filter, neural network is use for optimization. The experiment result shows among those identified image enhancement filters for visual corrosion inspection, Wavelet De-noising gives desirable result in terms of Mean Square Error, Peak Signal to Noise Ratio and Neural Network optimization.

Robot and human teacher

In this day and age, robot teacher application in education system has been spread throughout the world. The usage of robot teacher is believed to improve the teaching lesson that delivered by human teacher. For human teacher, there are methods that can be used to measure the teaching effectiveness. What about the effectiveness of teaching by robot teacher? Therefore, a method that suitable to measure the effectiveness of teaching by robot teacher is discussed in this research. The method that will be used to measure the effectiveness is by giving quiz and questionnaire to selected students. A quiz is constructed according to elements that required in measuring the effectiveness for teaching that is observation and understanding. To measure the interaction between students to robot teacher and human teacher, a questionnaire is constructed and given to the students after a lesson is delivered by both teachers. The robot teacher was programmed to deliver teaching. The quiz and questionnaire was constructed and ready to hand out to audience. The important aspects in measuring effectiveness of teaching students by using robot teacher are observation, understanding, and interaction.

FCM Relationship Modeling for Engineering Systems

Semantic graphs like fuzzy cognitive map (FCM) are known as powerful methodologies commonly used in control applications, as well as in relationship modeling. Besides, FCM is used as a systematic way for analyzing real-world problems with numerous known, partially known and unknown factors. This chapter discusses FCM application in relationship modeling context using some agile inference mechanisms. A sigmoid-based activation function is discussed with application in modeling hexapod locomotion gait. The activation algorithm is then added with a Hebbian weight training technique to enable automatic construction of FCMs. A numerical example case is included to show the performance of the developed model. The model is examined with perceptron learning rule as well. Finally a real-life example case is tested to evaluate the final model in terms of relationship modeling.

Methodology On Investigating The Influences Of Automated Material Handling System In Automotive Assembly Process

A case study was selected as a method to collect data in actual industry situation. The study aimed to assess the influences of automated material handling system in automotive industry by proposing a new design of integration system through simulation, and analyze the significant effect and influence of the system. The method approach tool will be CAD Software (Delmia & Quest). The process of preliminary data gathering in phase 1 will collect all data related from actual industry situation. It is expected to produce a guideline and limitation in designing a new integration system later. In phase 2, an idea or concept of design will be done by using 10 principles of design consideration for manufacturing. A full factorial design will be used as design of experiment in order to analyze the performance measured of the integration system with the current system in case study. From the result of the experiment, an ANOVA analysis will be done to study the performance measured. Thus, it is expected that influences can be seen from the improvement made in the system.

Navigation method of PLC based mobile robot

For centuries, the revolution in technology undoubtedly is the robot. Starting from dream of a man to be free of the drudgery of manual labor using automatic device, until currently in 21st century where robot has been applied to almost all types of labor industries. This project is motivated by the lack of application in Programmable Logic Controller (PLC) as mobile robot navigation system. By developing an algorithm and analyzing the navigation of mobile robot using PLC, the mobile robot should be able to follow line hypothetically. An experiment was conducted as the method to prove the hypothesis. Starting with designing the program using PLC software until assigning the PLC into the mobile robot with complete circuit wiring. To analyze the navigation of mobile robot, navigation experiment is done in straight line which is repeated for 5 times and represented in line graph. From 20 mark points measured for each running time, it shows that error is lest then 18% which prove that the mobile robot able to navigate using PLC. At the end of the experiment, the result showed the ultimate goal of this project has been achieved by moving the mobile robot using PLC based controller mobile system and enable the mobile robot to read and following the line.

Analysis of human emotion in human-robot interaction

There is vast application of robots in human’s works such as in industry, hospital, etc. Therefore, it is believed that human and robot can have a good collaboration to achieve an optimum result of work. The objectives of this project is to analyze human-robot collaboration and to understand humans feeling (kansei factors) when dealing with robot that robot should adapt to understand the humans’ feeling. Researches currently are exploring in the area of human-robot interaction with the intention to reduce problems that subsist in today’s civilization. Study had found that to make a good interaction between human and robot, first it is need to understand the abilities of each. Kansei Engineering in robotic was used to undergo the project. The project experiments were held by distributing questionnaire to students and technician. After that, the questionnaire results were analyzed by using SPSS analysis. Results from the analysis shown that there are five feelings which significant to the human in the human...

Improvement of Corrosion Detection Using Vision System for Pipeline Inspection

Nowadays, the utilization of cameras as an inspection tool has been increasing. The flexibility functions of camera fits to get different kind of information. This research is focusing on developing a robust visual inspection system for corrosion detection that is able to detect corrosion in any environment, and the corrosion detection will be using visual data as primary tools. A review on current pipeline inspection would give a brief detail on the improvement of the proposed inspection system. Furthermore, the inadequacies of the proposed visual corrosion detection are identified and discussed from the reviewing process on existing researches and analysis on preliminary data obtained. It is expected that the output of the proposed system will be a new method of corrosion detection and pioneer for the inspection system on robust environment.