Mohd Nordin Abdul Rahman

Detecting Mango Fruits by Using Randomized Hough Transform and Backpropagation Neural Network

A new method for mango detection is presented in this paper. This method is based on preprocessing operators on image which includes converting to gray image, finding edges, calculating distances to edges, opening morphology and converting to binary color image. To take advantage of oval shaped mango fruit, we apply Randomized Hough Transform method to detect potential places for mango fruit in input images. By using Back propagation Neural Network, we recognize mango fruits from these potential places. The dataset used to implementing this paper is 50 RGB images captured of mango fruits on trees. As shown in experimental results, in the case of clear fruit in input images, the detection rates up to 96.26% while it decreases in the case of partially covering or overlapping. However, this method can be applied to detect other fruits in varied sizes and colors.

Data Mining for Churn Prediction: Multiple Regressions Approach

The rapid development in the telecommunications industry contributed to the increased rivalry among the competitors. Customers switch to competitors or move out from the service provider become critical concerns for companies to retain customer loyalty. Churn prevention through churn prediction is one of the methods to ensure customer loyalty with the service provider. Detect and analyze early churn is a proactive step to ensure that existing customers did not move out or subscribe to the product from competitors. Selection of customer characteristics is one of the core issues to forecast customer churn in the telecommunications industry. This paper proposes multiple regressions analysis to predict the customers churn in the telecommunications industry based on recommended features. The results have shown that the performance of multiple regressions for predicting customer churn is acceptably good.

A New Customer Churn Prediction Approach Based on Soft Set Ensemble Pruning

Accurate customer churn prediction is vital in any business organization due to higher cost involved in getting new customers. In telecommunication businesses, companies have used various types of single classifiers to classify customer churn, but the classification accuracy is still relatively low. However, the classification accuracy can be improved by integrating decisions from multiple classifiers through an ensemble method. Despite having the ability of producing the highest classification accuracy, ensemble methods have suffered significantly from their large volume of base classifiers. Thus, in the previous work, we have proposed a novel soft set based method to prune the classifiers from heterogeneous ensemble committee and select the best subsets of the component classifiers prior to the combination process. The results of the previous study demonstrated the ability of our proposed soft set ensemble pruning to reduce a substantial number of classifiers and at the same time producing the highest prediction accuracy. In this paper, we extended our soft set ensemble pruning on the customer churn dataset. The results of this work have proven that our proposed method of soft set ensemble pruning is able to overcome one of the drawbacks of ensemble method. Ensemble pruning based on soft set theory not only reduce the number of members of the ensemble, but able to increase the prediction accuracy of customer churn.

Selection of the Most Significant Variables of Air Pollutants Using Sensitivity Analysis

This study was conducted to determine the most significant parameters for the air-pollutant index (API) prediction in Malaysia using data covering a 7-year period (2006–2012) obtained from the Malaysian Department of Environment (DOE). The sensitivity analysis method coupled with the artificial neural network (ANN) was applied. Nine models (ANN-API-AP, ANN-API-LCO, ANN-API-LO3, ANN-API-LPM10, ANN-API-LSO2, ANN-API-LNO2, ANN-API-LCH4, ANN-API-LNmHC and ANN-API-LTHC) were carried out in the sensitivity analysis test. From the findings, PM10 and CO were identified as the most significant parameters in Malaysia. Three artificial neural network models (ANN-API-AP, ANN-API-LO, and ANN-API-DOE) were compared based on the performance criterion [R2, root-mean-square error (RMSE), and squared sum of all errors (SSE)] for the best prediction model selection. The ANN-API-AP, ANN-API-LO, and ANN-API-DOE models have R2 values of 0.733, 0.578, and 0.742, respectively; RMSE values of 8.689, 10.858, and 8.357, respectively; SSE values of 762,767.22, 1,191,280.60, and 705,600.05, respectively. The findings exhibit the ANN-API-LO model has a lower value in R2 and higher values in RMSE and SSE than others. ANN-API-LO model was considered as the best model of prediction because of fewer variables was utilized as input and far less complex than others. Hence, the use of fewer parameters of the API prediction has been highly practicable for air resource management because of its time and cost efficiency.

Ant colony optimisation for solving university course timetabling problems

Course timetabling is one of the most important activities faced by any educational institution. Furthermore, the course timetabling process is time-consuming and tiresome as it needs to be prepared for each regular semester. This paper aims to apply the Ant Colony Optimisation (ACO) method to solve the course timetabling problem. This approach is to optimise the properties of the course requirement and minimise various conflicts for the time slot assignation. This method is based on the life of the ant colony in generating automatic timetabling according to the properties (pheromones) such as time, student, lecturer and room, besides satisfying the constraints. The implementation of this method is to find an effective and better solution for university course timetabling. The result and performance evaluation is used to determine whether it is reliable in providing the feasible timetable.

The Reconstructed Heterogeneity to Enhance Ensemble Neural Network for Large Data

This paper present an enhanced approach for ensemble multi classifier of Artificial Neural Networks (ANN). The motivation of this study is to enhance the ANN capability and performance using reconstructed heterogeneous if the homogenous classifiers are deployed. The clusters set are partitioned into two sets of cluster; clusters of a same class and clusters of multi class which both of them were using different partition techniques. Each partitions represented by an independent classifier of highly correlated patterns from different classes. Each set of clusters are compared and the final decision is voted by using majority voting. The approach is tested on benchmark large dataset and small dataset. The results show that the proposed approach achieved almost near to 99% of accuracy which is better classification than the existing approach.

Adoption of near field communication in S-Library application for information science

Purpose – The purpose of this paper is to first review the implementation of automatic identification and data capture) technologies in library/information science, focusing on barcode technology, radio frequency identification (RFID) and near field communication (NFC). This paper then presents S-Library, a new android-based application, to enable users to perform a wide range of information science-related transactions, such as borrowing, searching, returning and viewing transaction records. Design/methodology/approach – This paper presents the design process and the database and software components. For analysis, the authors used application testing, and also usability testing, with a questionnaire distributed to 343 users. Findings – The implementation of NFC technology means that S-Library has a number of technical advantages over other approaches. It was also shown with user acceptance testing that there was a high degree of user satisfaction with S-Library. Research limitations/implications – Althou...