Siti Azirah Asmai

Exam timetabling using graph colouring approach

Timetabling at large covering many different types of problems which have their own unique characteristics. In education, the three most common academic timetabling problems are school timetable, university timetable and exam timetable. Exam timetable is crucial but difficult to be done manually due to the complexity of the problem. The main problem includes dual academic calendar, increasing student enrolments and limitations of resources. This study presents a solution method for exam timetable problem in centre for foundation studies and extension education (FOSEE), Multimedia University, Malaysia. The method of solution is a heuristic approach that include graph colouring, cluster heuristic and sequential heuristic.

A Framework of an Intelligent Maintenance Prognosis Tool

The technology of prognosis has become a significant approach but its implementation in maintenance has a major extension. The ability prognosis in the medical area has been established to estimate the future of human health. However, in maintenance, application of prognosis is not yet seen as a practical use for making better maintenance decision. To date, research in this area has been done in proposing prognosis techniques or model but leaving the implementation of prognosis as their future work. In this paper, an overview of prognosis in maintenance is presented. By using the data-driven approach, a framework for implementing of an intelligent maintenance prognosis tool is introduced. The framework utilizes the existing equipment operating performance data in the industry for prognosis process. Next, the framework combines the ability of prognosis in estimating remaining useful life (RUL) of equipment with the maintenance action knowledge to generate a well-received maintenance plan.

Application of multi-step time series prediction for industrial equipment prognostic

The use of prognostics is critically to be implemented in industrial. This paper presents an application of multi-step time series prediction to support industrial equipment prognostic. An artificial neural network technique with sliding window is considered for the multi-step prediction which is able to predict the series of future equipment condition. The structure of prognostic application is presented. The feasibility of this prediction application was demonstrated by applying real condition monitoring data of industrial equipment.

The integration of simple Markov model in solving single line production system

Small and Medium Enterprise (SME) has limitations in capital to upgrade the production process especially in installing new machines in parallel line. Generally the machines are installed in single-line and not equipped with a modern technology. If any machines in the series are breakdown and stopped, the whole production system also stopped. By understanding the condition, most of SMEs struggle to reduce the overhead cost and increase the companys profit by escalating the availability of the machines. A simple yet powerful Markov model is used in this study to identify the prime cost involves in production line downtimes. The influence of the performance of a single machine on a line is investigated. A case study in the production of the tamarind juice drink, obviously when the failure rate of the machines is reduced, the cost of lost also can be reduced.

An Enhanced Malay Named Entity Recognition using Combination Approach for Crime Textual Data Analysis

Named Entity Recognition (NER) is one of the tasks in the information extraction. NER is used for extracting and classifying words or entities that belong to the proper noun category in text data such as persons name, location, organization, date and others. As seen in todays generation, social media such as web pages, blogs, Facebook, Twitter, Instagram and online newspapers are among the major contributors to the generation of information. This paper presents an enhanced Malay Named Entity Recognition model using combination fuzzy c-means and K-Nearest Neighbours Algorithm method for crime analysis. The results showed that this combination method could improve the accuracy performance on entity recognition of crime data in Malay. The model is expected to provide a better method in the process of recognizing named entities for text analysis particularly in Malay.

Digraph Representations of Machine Vision Workspace for Monitoring Worker’s Behavior

If motions are repeated normally for every few seconds, and for prolonged periods about an 8-h shift, fatigue and muscle strain may occur. Suppose that we have a worker who is operating a machine. We need to monitor the worker’s behavior through real-time video streaming. Our challenge is to approximate the locations to place the tripods. We propose workspace geometry and workspace configuration so that, there is a proper methodology for designating the operator’s initial position, the machine position as the origin of the workspace. We deduce that, for a typical local manufacturing setting, there is a generalized workspace configuration usable for a wide-ranging machine operators’ height measurement. Implementing the proposed procedures, the camera placement is therefore defined by digraphs.

Comparison on Techniques for Multiple Video Streaming via Webcam for Manufacturing Engineering Purpose

Multiple video streaming can be used for many functions and there are two techniques that can be used for streaming. The first is the use of the on-the shelf software which is ready-made and can be downloaded. The second technique is a self-programming technique using open source software. In this paper, both techniques were compared to investigate their capabilities in the manufacturing process. Some experiments were conducted to verify the affordability of the techniques. The focus of comparison for both techniques is to detect the image of real-time motion and generate report of the motion. In this research, the capabilities and differences between the two techniques are also identified.

Neural network prognostics model for industrial equipment maintenance

This paper presents a new prognostics model based on neural network technique for supporting industrial maintenance decision. In this study, the probabilities of failure based on the real condition equipment are initially calculated by using logistic regression method. The failure probabilities are subsequently utilized as input for prognostics model to predict the future value of failure condition and then used to estimate remaining useful lifetime of equipment. By having a time series of predicted failure probability, the failure distribution can be generated and used in the maintenance cost model to decide the optimal time to do maintenance. The proposed prognostic model is implemented in the industrial equipment known as autoclave burner. The result from the model reveals that it can give prior warnings and indication to the maintenance department to take an appropriate decision instead of dealing with the failures while the autoclave burner is still operating. This significant contribution provides new insights into the maintenance strategy which enables the use of existing condition data from industrial equipment and prognostics approach