Shahnorbanun Sahran

A fast scheme for multilevel thresholding based on a modified bees algorithm

Image segmentation is one of the most important tasks in image processing and pattern recognition. One of the most efficient and popular techniques for image segmentation is image thresholding. Among several thresholding methods, Kapurs (maximum entropy (ME)) and Otsus methods have been widely adopted for their simplicity and effectiveness. Although efficient in the case of bi-level thresholding, they are very computationally expensive when extended to multilevel thresholding because they employ an exhaustive search for the optimal thresholds. In this paper, a fast scheme based on a modified Bees Algorithm (BA) called the Patch-Levy-based Bees Algorithm (PLBA) is adopted to render Kapurs (ME) and Otsus methods more practical; this is achieved by accelerating the search for the optimal thresholds in multilevel thresholding. The experimental results demonstrate that the proposed PLBA-based thresholding algorithms are able to converge to the optimal multiple thresholds much faster than their corresponding methods based on Basic BA. The experiments also show that the thresholding algorithms based on BA algorithms outperform corresponding state-of-the-art metaheuristic-based methods that employ Bacterial Foraging Optimization (BFO) and quantum mechanism (quantum-inspired algorithms) and perform better than the non-metaheuristic-based Two-Stage Multi-threshold Otsu method (TSMO) in terms of the segmented image quality. In addition, the results show the high degree of stability of the proposed PLBA-based algorithms.

Patch-Levy-based initialization algorithm for Bees Algorithm

The Bees Algorithm (BA) is a population-based metaheuristic algorithm inspired by the foraging behavior of honeybees. This algorithm has been successfully used as an optimization tool in combinatorial and functional optimization fields. In addition, its behavior very closely mimics the actual behavior that occurs in nature, and it is very simple and easy to implement. However, its convergence speed to the optimal solution still needs further improvement and it also needs a mechanism to obviate getting trapped in local optima. In this paper, a novel initialization algorithm based on the patch concept and Levy flight distribution is proposed to initialize the population of bees in BA. Consequently, we incorporate this initialization procedure into a proposed enhanced BA variant. The proposed variant is more natural than conventional variants of BA. It mimics the patch environment in nature and Levy flight, which is believed to characterize the foraging patterns of bees in nature. The results of experiments conducted on several widely used high-dimensional benchmarks indicate that our proposed enhanced BA variant significantly outperforms other BA variants and state-of-the-art variants of the Artificial Bee Colony (ABC) algorithm in terms of solution quality, convergence speed, and success rate. In addition, the results of experimental analyses conducted indicate that our proposed enhanced BA is very stable, has the ability to deal with differences in search ranges, and rapidly converges without getting stuck in local optima.

Aligning an information system strategy with sustainability strategy towards sustainable campus

Sustainability has increasingly become important for Higher Education Institutions (HEIs). A number of researches have acknowledged the HEIs transformation towards sustainable campus. However, there is a lack of research contribution focused on alignment process between sustainability and information system (IS) strategies. This research issue inhibits achievement of sustainability objectives and values. In this study, therefore, the authors propose a sustainability transformation framework, which involves alignment process between sustainability and IS strategies, for sustainability transformation. The authors engage three phases to gain the objective of this study. These phases include problem definition, define objectives of a solution, and framework development. The proposed framework provides a sequential and rigorous approach to effectively transforming HEIs towards sustainable campus. However, there is a need of future works to validate and assess the applicability of the framework in HEIs.

ERP Implementation Challenges in Small and Medium Enterprise: A Framework and Case Study

The Malaysian small to medium enterprises (SMEs) market has big influences in the business world which is becoming more competitive. Therefore, Enterprise Resource Planning (ERP) as a functional unit integrated system is needed to streamline the business processes to achieve greater work efficiency. However, an in depth understanding about ERP system is needed to ensure the successful system implementation. This paper seeks to explore the challenges of ERP system implementation in order to deepen the knowledge on ERP system implementation in SMEs. The research method is based on a single-case design within Malaysian SME to obtain a process model of ERP system implementation adoption by SMEs. The conceptual framework for ERP system implementation, which was validated by a number of SMEs in Malaysia, is proposed in order to attempt the minimize ERP project failure in SMEs.

Gender Differences in Computer Literacy Level Among Undergraduate Students in Universiti Kebangsaan Malaysia

This study was conducted to assess gender differences in computer literacy levels of undergraduate students in UKM. Responses from 2,591 students were analyzed. Students were surveyed on software and application use, self‐perceived control and programming skills. There is a significant difference in computer literacy level between male and female students; overall mean score for male was 2.62 (N = 734, SD = 0.71) while female score was 2.34 (N = 1570, SD = 0.58). Male students had greater computer experience and use computer more frequently. They also reported a higher computer ability and slightly higher percentage of them own a computer. Males had greater self‐perceived control and higher programming skills and better ability in computer repair and maintenance than females. Other factors such as computer experience, and computer ownership also affect computer literacy level as was shown by the interaction effect existed among gender, computer experience, and computer ownership. Implication from this study indicates that increasing the computer experience and encouraging students to own a computer will give more opportunity to female students to achieve a higher level of computer literacy.

Soft computing applications and intelligent systems: Second international multi-conference on artificial intelligence technology, m-cait 2013 shah alam, august 28-29, 2013 Proceedings

The determination of real world coordinate from image coordinate has many applications in computer vision. This paper proposes the algorithm for determination of real world coordinate of a point on a plane from its image coordinate using single calibrated camera based on simple analytic geometry. Experiment has been done using the image of chessboard pattern taken from five different views. The experiment result shows that exact real world coordinate and its approximation lie on the same plane and there are no significant difference between exact real world coordinate and its approximation.

An investigation of lead benchmarking implementation: A comparison of small/medium enterprises and large companies

Purpose – The purpose of this paper is to explore current levels of lead benchmarking implementation and lead performance indicators among Malaysian organizations. Comparing small and medium enterprises (SMEs) with large companies, it identifies what benefits and difficulties are present during benchmarking implementation. Design/methodology/approach – Descriptive analyses, one-way ANOVAs between and within groups, and parametric and non-parametric tests are used to compare responses obtained from small, medium and large Malaysian manufacturing organizations. Findings – Findings suggest that larger organizations have a more progressive approach to lead benchmarking. Strategy and employee development are dominant lead performance indicators of continuous improvement. Large companies experience fewer challenges when implementing benchmarking projects. Perceptions of key benchmarking implementation barriers shift from mere lack of resources toward lack of knowledge and training, information sharing, commitme...

Solar cell panel crack detection using Particle Swarm Optimization algorithm

A solar cell panel as an efficient power source for the production of electrical energy has long been considered. Any defect on the solar cell panels surface will be lead to reduced production of power and loss in the yield. In this case, inspection of the solar cell panel is essential to be performed to obtain a product of high quality. Some inspection methods have been developed, but in any event non-contact, non-destructive and efficient testing methods are necessary. This paper proposes an automated inspection system based on an image-processing approach for solar cell panel application in order to detect any cracks which may be appeared on the surface of solar cell panel. The Particle Swarm Optimization (PSO) algorithm as a main constituent of our proposed method is used for edge detection in the solar cell panel. Subsequently, some features like cracks and bus bars will be extracted and we will classify defected products and cracks based on the positions of the bus bars using Fuzzy logic. In this proposed method, an automated inspection system of solar cell panel proposed which has potential to get good results based on Particle Swarm optimization algorithm.

The variants of the Bees Algorithm (BA): a survey

The Bees Algorithm (BA) is a bee swarm intelligence-based metaheuristic algorithm that is inspired by the natural behavior of honeybees when foraging for food. BA can be divided into four parts: parameter tuning, initialization, local search, and global search. Since its invention, several studies have sought to enhance the performance of BA by improving some of its parts. Thus, more than one version of the algorithm has been proposed. However, upon searching for the basic version of BA in the literature, unclear and contradictory information can be found. By reviewing the literature and conducting some experiments on a set of standard benchmark functions, three main implementations of the algorithm that researchers should be aware of while working on improving the BA are uncovered. These implementations are Basic BA, Shrinking-based BA and Standard BA. Shrinking-based BA employs a shrinking procedure, and Standard BA uses a site abandonment approach in addition to the shrinking procedure. Thus, various implementations of the shrinking and site-abandonment procedures are explored and incorporated into BA to constitute different BA implementations. This paper proposes a framework of the main implementations of BA, including Basic BA and Standard BA, to give a clear picture of these implementations and the relationships among them. Additionally, the experiments show no significant differences among most of the shrinking implementations. Furthermore, this paper reviews the improvements to BA, which are improvements in the parameter tuning, population initialization, local search and global search. It is hoped that this paper will provide researchers who are working on improving the BA with valuable references and guidance.

Adaptive image segmentation based on peak signal-to-noise ratio for a license plate recognition system

The objective of this paper is to propose an adaptive threshold method based on peak signal to noise ratio (PSNR). Nowadays, PSNR has been widely used as stopping criteria in multi level threshold method for segmenting images. Alternatively, we apply the PSNR as criteria to find the most suitable threshold value. We evaluate this proposed method on license plate recognition application. At the same time, we compare this proposed algorithm with multi-level and multi-threshold methods as the benchmark. Via the proposed technique, it could relatively change according to environment such as when there is a high or low contrast situation.