Faculty of Computing and Informatics

Human emotions rely upon the ability to correctly attribute beliefs, goals and percepts to other people or social respond. Many of the quests to model human emotions derived from diverse aspects of research themes. Most of the research works related to the work of ...

A distance based classification is one of the popular methods for classifying instances using a point-to-point distance based on the nearest neighbour or k-NEAREST NEIGHBOUR (k-NN). The representation of distance measure can be one of the various measures available (e.g. Euclidean distance, Manhattan distance, Mahalanobis distance or other specific distance measures). In this paper, we propose a modified nearest neighbour method called Nearest Neighbour Distance Matrix (NNDM) for classification based on unsupervised and supervised distance matrix. In the proposed NNDM method, an Euclidean distance method coupled with a distance loss function is used to create a distance matrix. In our approach, distances of each instance to the rest of the training instances data will be used to create the training distance matrix (TADM). Then, the TADM will be used to classify a new instance. In supervised NNDM, two instances that belong to different classes will be pushed apart from each other. This is to ensure that the instances that are located next to each other belong to the same class. Based on the experimental results, we found that the trained distance matrix yields reasonable performance in classification.

Researchers have shown that although traditional direct classifier algorithm can be easily applied to multiclass classification, the performance of a single classifier is decreased with the existence of imbalance data in multiclass classification tasks. Thus, ensemble of classifiers has emerged as one of the hot topics in multiclass classification tasks for imbalance problem for data mining and machine learning domain. Ensemble learning is an effective technique that has increasingly been adopted to combine multiple learning algorithms to improve overall prediction accuraciesand may outperform any single sophisticated classifiers. In this paper, an ensemble learner called a Direct Ensemble Classifier for Imbalanced Multiclass Learning (DECIML) that combines simple nearest neighbour and Naive Bayes algorithms is proposed. A combiner method called OR-tree is used to combine the decisions obtained from the ensemble classifiers. The DECIML framework has been tested with several benchmark dataset and shows promising results.

Feature selection for data mining optimization receives quite a high demand especially on high-dimensional feature vectors of a data. Feature selection is a method used to select the best feature (or combination of features) for the data in order to achieve similar or better classification rate. Currently, there are three types of feature selection methods: filter, wrapper and embedded. This paper describes a genetic based wrapper approach that optimizes feature selection process embedded in a classification technique called a supervised Nearest Neighbour Distance Matrix (NNDM). This method is implemented and tested on several datasets obtained from the UCI Machine Learning Repository and other datasets. The results demonstrate a significant impact on the predictive accuracy for feature selection combined with the supervised NNDM in classifying new instances. Therefore it can be used in other applications that require feature dimension reduction such as image and bioinformatics classifications.

Malaysian medicinal plants may be abundant natural resources but there has not been much research done on preserving the knowledge of these medicinal plants which enables general public to know the leaf using computing capability. This study proposes a framework to identify and classify tropical medicinal plants in Malaysia based the extracted patterns from the leaf. The extracted patterns from medicinal plant leaf are obtained based on several angle features. Five classifiers, obtained from WEKA and an ensemble classifier, called Direct Ensemble Classifier for Imbalanced Multiclass Learning (DECIML), are used to compare their performance accuracies over this data. In this experiment, five species of Malaysian medicinal plants are identified and classified in which each species will be represented by using 65 images. This study is important in order to assist local community to utilize the knowledge discovery and application of Malaysian medicinal plants for future generation.

Malaysian medicinal plants may be abundant natural resources but there has not been much research done on preserving the knowledge of these medicinal plants which enables general public to know the leaf using computing capability. Therefore, in this preliminary study, a novel framework in order to identify and classify tropical medicinal plants in Malaysia based on the extracted patterns from the leaf is presented. The extracted patterns from medicinal plant leaf are obtained based on several angle features. However, the extracted features create quite large number of attributes (features), thus degrade the performance most of the classifiers. Thus, a feature selection is applied to leaf data and to investigate whether the performance of a classifier can be improved. Wrapper based genetic algorithm (GA) feature selection is used to select the features and the ensemble classifier called Direct Ensemble Classifier for Imbalanced Multiclass Learning (DECIML) is used as a classifier. The performance of the feature selection is compared with two feature selections from Weka. In the experiment, five species of Malaysian medicinal plants are identified and classified in which will be represented by using 65 images. This study is important in order to assist local community to utilize the knowledge and application of Malaysian medicinal plants for future generation.

Travel time is a measure of time taken to travel from one place to another. Global Positioning System (GPS) navigation applications such as Waze and Google Maps are easily accessible presently and allow users to plan a route based on travel time from one place to another. However, these applications can only estimate general travel time based on a vehicle’s total distance and average safe speed without considering route curvature. A parametric cubic curve has shown a potential result in travel-time estimation through geometric properties. In this paper, travel time has been estimated using the curvature value obtained from the Hermite Interpolation curve fitted to each section of the selected road. Design speed is determined from the curvature value, and thus an algorithm for travel-time estimation incorporating initial driving information is developed. The proposed method’s accuracy was compared to the existing method’s accuracy using a real-life driving test. This comparison demon...

Cloud storage is becoming an option for users in keeping their data online, but it comes with the security requirements and challenges of protecting their data from threats. Many security frameworks have been suggested by existing studies, governing bodies, industry standards etc. as guidelines to be implemented by cloud service providers (CSPs) but the complete set of controls cannot be fully implemented due to several challenges such as decreasing availability, less user convenience, need of a robust infrastructure etc. Therefore, there is a need to investigate the security requirements and threats which will enable efficient security protection to protect data in cloud storage. This paper will discuss security requirements and analyses existing cloud security threats. The threats will be modelled in a cloud storage scenario.

Information Technology (IT) plays an important role in enabling education services be delivered to users. Most education online services in universities have been run on the cloud to provide services to support students, lecturers, researchers and administration staff. These are enabled with the emergence of cloud computing in the world of IT. Cloud computing offers on demand Internet-based computing services. This paper presents an overview of cloud computing adoption in higher education, mainly tertiary institutions and universities. The focus of the paper is the challenges of cloud computing in higher education. It introduces the background to cloud computing and reviews research on adoption challenges in higher education institutions. These challenges are important as they provide an overview of the adoption of cloud in higher education. The authors proposed an integrated reference model based on the challenges in the literature integrated with TAM model to investigate the factors influence the users' attitudes and behaviours toward using cloud education services in universities ICT provision.

The purpose of this paper is to explore the important security factors for protecting data in cloud storage from the perspective of security practitioners. The study consist of 43 security variables (or indicator items) from a survey participated by security practitioners in Malaysia. Exploratory factor analysis (EFA) is conducted to understand the clusters of variables (or indicator items) and the interrelationships constructing the security factors (or components). Most of the respondents are from public sector organisations (government and higher education organisations) in Malaysia. The clusters of variables resulting from this analysis can be used as a reference for security practitioners planning to produce security policies to protect data stored in a cloud storage. The top security factors identified from this study are shown in terms of policy implementation and controls in confidentiality, integrity, availability, non-repudiation, authenticity, reliability, accountability and auditability of data services in cloud storage.

Assessing the security of data stored in cloud storage can be carried out by developing goal-based measurement items. The measurement items can be utilized to construct a security assessment model based on practical needs. The measurement items can assist in acquiring support decision making on the implementation of a security frameworks. This paper discusses the Goal-Question-Metrics (GQM) approach and its application towards constructing measurement items for a security metric. It also attempts to provide practical guidance and example of measurements using GQM. An application of the GQM paradigm towards the development of a security metric is presented. The metrics obtained will assist organizations to meet their requirements for a cloud storage security framework.

More and more data is stored in personal cloud storage and it is expected to grow further. As cloud storage is becoming an option for user in keeping their data online, it comes with the security threats and the challenges of protecting their data from unauthorised access. Many security controls have been implemented by cloud storage providers (CSPs) as a security measure but although encryption is known as one of the solution, it cannot be fully implemented due to the need of a robust and costly infrastructure. Therefore, we foresee the need to implement protection based on categorisation of data determined by users. This paper will discuss recent security threats and also the levels of data protection in cloud storage. We propose a security framework that protects data in cloud storage based on the level of protection it needs.

Currently, Malaysian education system is being transformed to create a new generation of students who are ready to adapt with new technologies and able to manage the information explosion. Thus, the need to incorporate ICT in teaching and learning at all levels of education is deemed essential. Multimedia Technology is playing an important role in the classroom as an interactive courseware in presenting and delivering the course material to the students. Most of the interactive coursewares available in the market now are focusing on Languages subjects, Mathematics and Science. This paper investigates the perception of form 5 history teachers and students in using interactive multimedia courseware as their teaching and learning channel in history subject. This research identified the features which influence student's interest in learning history, as well as the possible challenges and constraints that might be encountered by their teachers in using interactive courseware. Furthermore, this study also highlighted some considerations before designing and developing the interactive multimedia courseware for history subject.

This study attempted to explore and investigate the types of retail technologies used among retailers in Labuan, Malaysia. It also examined whether the same group of retailers were willing to invest their companies' time, money and employees' energy/effort to innovate their business processes/routine. The study was conducted in Labuan F. T. of Malaysia. Convenient sampling was used to gather data from the respondents. Based on the findings, the respondents were doing businesses related to five categories namely, "ICT related", "Supermarket and grocery related", "Fashion and accessories related", "Electrical and electronic home appliances" and "Printing services related" type of businesses. The researchers found that there were eleven systems of hardware and software application used by the respondents i.e. i) accounting system, ii) inventory billing system, iii) payroll and HRM system, iv) POS system including barcoding/scanner and digital receipt system, v) MS Office packages, vi) mobile applications vii) quick response coding (QR) viii) computer networking of internet and intranet for data transfer and communication between employees ix) CRM database x) ERP and xi) Asset registration with depreciation of fixed assets. There were 50 percent respondents using accounting system and also the POS system. This seemed the most preferred system among the respondents. The findings also showed that technologies based on hardware and soft wares were adopted by only a handful and it differ among the respondents between 50 percent to 8 per cent adoption rates. There is a need for them to make comparisons and learn from other retailers from the same area, be it the type of business as well as the geographical location so as to get the benefits of the technologies available in the market.

The internet has emerged as an important marketing tool in the retailing industry. However, there are retailers whom have not fully utilized or have not fully understood the importance of the Internet as a marketing tool. The objective of this study was to examine the utilization of the Internet as a marketing tool among retailers in Labuan, Malaysia. This study was based on qualitative interviews among retailers and content analysis of retailers' websites in the business hub in Labuan. 18 retailers participated in this study. The findings showed, only 56% of respondents have their company's website, 83% respondents do have company social networking account and 78% respondents register their company details to a local online directory site. Company profile was identified as the most common attribute which was found in all company's website, beside products and services information. The major lacking attributes in most website were found in transactional means element which is relating to online purchasing service. However, only one respondent provide online shopping service. Several factors were identified as the limitations to internet marketing utilization. Lack of ICT knowledge and skills among employees was the most reported limitation to fully optimize the use of internet marketing. This study offers an opportunity to relevant shareholders of the retail business, government agencies and business consultants to view or plan future diverse training programmes in nurturing internet marketing awareness, and to help retailers in increasing the use of Internet as their business platform to drive businesses by marketing their products to the global market while increasing their productivity. Findings also provide an important insight for retailers on website content design practices considerations for new or existing company website.

The focal point of this paper is to: (a) present the pilot profiles of ICT-based SMEs operating in Sabah and Labuan; (b) identify the descriptive component of the technology or business focus of these ICT-based SMEs; and (c) to contribute type of important knowledge stream that is perceived to be significance for ICT-based SMEs' competitiveness. This preliminary study of