Attribute selection which is also known as feature selection is an essential process that is relevant to predictive analysis. To date, various feature selection algorithms have been introduced, nevertheless they all work independently. Hence, reducing the consistency of the accuracy rate. The aim of this paper is to investigate the use of bio-inspired search algorithms in producing optimal attribute set. This is achieved in two stages; 1) create attribute selection models by combining search method and feature selection algorithms, and 2) determine an optimized attribute set by employing bio-inspired algorithms. Classification performance of the produced attribute set is analyzed based on accuracy and number of selected attributes. Experimental results conducted on six (6) public real datasets reveal that the feature selection model with the implementation of bio-inspired search algorithm consistently performs good classification (i.e higher accuracy with fewer numbers of attributes) on the selected data set. Such a finding indicates that bio-inspired algorithms can contribute in identifying the few most important features to be used in data mining model construction.

ABSTRACT

ABSTRACT

Attribute selection which is also known as feature selection is an essential process that is relevant to predictive analysis. To date, various feature selection algorithms have been introduced, nevertheless they all work independently. Hence, reducing the consistency of the accuracy rate. The aim of this paper is to investigate the use of bio-inspired search algorithms in producing optimal attribute set. This is achieved in two stages; 1) create attribute selection models by combining search method and feature selection algorithms, and 2) determine an optimized attribute set by employing bio-inspired algorithms. Classification performance of the produced attribute set is analyzed based on accuracy and number of selected attributes. Experimental results conducted on six (6) public real datasets reveal that the feature selection model with the implementation of bio-inspired search algorithm consistently performs good classification (i.e higher accuracy with fewer numbers of attributes) on the selected data set. Such a finding indicates that bio-inspired algorithms can contribute in identifying the few most important features to be used in data mining model construction.

Lighthouse is a tower with a strong light which gives navigators a continuous signal. There are about six lighthouses under the responsibility of the Central Region Marine Department of Malaysia. These lighthouses experienced severe construction defects and internal defects. Predictive maintenance, therefore, is performed manually to preserve the lighthouses. Lighthouse Maintenance Management Mobile Apps System (LMMS) is an Android mobile application developed for the Assistant Engineer, Technician, Marine Officer and Division Head of the Central Region Marine Department of Malaysia, responsible for the maintenance of lighthouses. Currently, the Central Region’s Marine Department of Malaysia lacks a computerised maintenance management system for the lighthouses, especially to manage maintenance schedules, work orders and maintenance-related records. In addition, the technician still uses a manual guide for troubleshooting tools and spare parts. Thus, LMMS was developed to solve these problems as a fully functioning mobile application by designing and developing a system for lighthouse maintenance management according to user needs. The methodology used to develop this mobile application is agile. The LMMS provides complete features for scheduling maintenance, orders for maintenance work, records related to maintenance, a list of tools and spare parts, and management of lighthouse information. The result shows that LMMS contributes to ease of use by using the mobile platform, quick and simple modules, systematic storage of historical records, efficient workload distribution, rapid reporting, updated list of tools and spare parts, and providing the latest information on the lighthouses. Deploying LMMS helps the Central Region Marine Department of Malaysia manage and maintain the lighthouses more effectively.