WCWan Yoke Chin

Wan Yoke Chin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wan Yoke Chin has a total of 12 co-authors. Here are the top co-authors by number of shared publications:

  • Khai Yin Lim

    2 shared publications
  • Khai Yin Lim

    Department of Research and Development, Tunku Abdul Rahman University of Management and Technology, Lorong Lembah Permai 3, Pulau Pinang 11200, Malaysia

    2 shared publications
  • Bee Wah Loo

    Department of Mathematical and Data Science, Faculty of Computing and Information Technology, Tunku Abdul Rahman University of Management and Technology, Setapak, 53300 Kuala Lumpur, Malaysia

    1 shared publication
  • I. Yeo

    Lee Kong Chian Faculty of Engineering and Science, Department of Mathematical and Actuarial Sciences, Tunku Abdul Rahman University, Sungai Long Campus, Jalan Sungai Long, Bandar Sungai Long, Cheras 43000, Kajang, Selangor, Malaysia

    1 shared publication
  • Pei Ling Tan

    Department of Mathematical and Data Science, Faculty of Computing and Information Technology, Tunku Abdul Rahman University of Management and Technology, Setapak, 53300 Kuala Lumpur, Malaysia

    1 shared publication
  • Siew Kian Tey

    Department of Mathematical and Data Science, Faculty of Computing and Information Technology, Tunku Abdul Rahman University of Management and Technology, Setapak, 53300 Kuala Lumpur, Malaysia

    1 shared publication

Latest Publications

  • Open Access

    Authentication Methods Selection in Information Security through Hybrid AHP and EGT

    by Bee Wah Loo, Pei Ling Tan, Siew Kian Tey, Wan Yoke Chin

    The information security leader frequently encounters the challenge of choosing the appropriate defence strategy. Effective multi-criteria decision-making (MCDM) is essential in the field of information security for determining the optimal strategies that involve more than one party. To address this challenge, we propose a hybrid model that combines the strengths of the Analytic Hierarchy Process (AHP) with Evolutionary Game Theory (EGT). The hybrid model helps the information security leader assess the criteria for security controls and make the optimal decisions to protect the organization's data. Initially, the AHP is utilized to assess the criteria of information security control. Subsequently, the priority of the alternatives is established through evaluating these criteria. Furthermore, we will construct a defence-attack circumstance using the EGT framework, which involves formulating strategies and determining payoffs for both the information security leaders and attackers involved. We utilize the replicator dynamic to examine the process of evolution in the game, resulting in the determination of the optimal strategy. A case study is conducted to determine the optimal strategy for information security leaders and attackers. The result indicates that the best defence strategy is password protection, followed by token-based and biometric-based protections. On the other hand, the optimal strategy for attackers is no attack, followed by attack and moderate attack. This study contributes to the multi-criteria decision-making (MCDM) problem’s solving by considering the dynamic aspect between both defender and attacker in the context of information security.


  • Social network analysis (SNA) on Twitter contributes customer engagement on the cosmetic industry in Malaysia

    by Wai Beng Tan, Wan Yoke Chin

    The study shows Twitter’s analysis and visualization for a campaign organized by a cosmetic brand, Loreal Parisin Malaysia. It aimed to obtain insights into use The study shows Twitter’s analysis and visualization for a campaign organized by a cosmetic brand, Loreal Parisin Malaysia. It aimed to obtain insights into use

  • Open Access

    An economic production quantity (EPQ) model with rework process and reworked items sold in secondary markets

    by Soo Lin Lee, I. Yeo, Wan Yoke Chin

    A sustainable inventory system aims to increase the quality of its production and reduce its impact on the environment without increasing its costs. This study presents an economic production quantity (EPQ) model with a rework process where the production of good quality items is used to fulfil primary market demand, whereas the reworked defective items are used to fulfil secondary market demand. There are five cases being observed during the simultaneous production process and reworking process, and a generalised model that minimises the total cost per unit time (TCUT) is developed. The proposed model is experimented with using a variety of numerical examples, and a numerical sensitivity analysis that studies how different system parameters affect costs is performed. This analysis suggests that the proposed model is fairly robust to changes in parameters; however, the higher the proportion of defective items in a production lot size, the more serious the impact on the optimal cost. The results show that the TCUT is increasing exponentially with respect to the proportion of defective items in a production lot size.

  • Open Access

    Content-Based Image Retrieval for Painting Style with Convolutional Neural Network

    by Wei Sheng Tan, Wan Yoke Chin, Khai Yin Lim

    With the availability of large paintings dataset on the online platform in recent years, it opens up a new research perspective and researcher started to investigate paintings in a new and different ways. While Convolutional Neural Networks (CNN) have been successfully applied in computer vision domains, several researchers started to investigate the possibility of utilizing CNN for artwork classification and retrieval system. Image retrieval has been one of the most difficult disciplines in digital image processing because it requires scanning a large database for images that are comparable to the query image. It is commonly known that retrieval performance is largely influenced by feature representations in trained algorithm and similarity measures. Deep Learning has recently advanced significantly, and deep features based on deep learning have been widely used because it has been demonstrated that the features have great generalisation. In this paper, a convolutional neural network (CNN) is utilised to classify painting’s style and extract deep and high-level features from the paintings. Next, were used as an image retrieval system to retrieve similar images in artwork style of content which is useful for search or recommendation systems in online art collection. Our experiments show that this strategy significantly improves the performance of content-based image retrieval for the style retrieval task of painting and beat the current state-of-art for painting style classification.


  • Content-Based Image Retrieval for Painting Style with Convolutional Neural Network

    by Wei Sheng Tan, Wan Yoke Chin, Khai Yin Lim

    With the advancement of digital paintings in online collection platform, new image processing algorithms are required to manage digital paintings saved on database. Image retrieval has been one of the most difficult disciplines in digital image processing because it requires scanning a large database for images that are comparable to the query image. It is commonly known that retrieval performance is largely influenced by feature representations and similarity measures. Deep Learning has recently advanced significantly, and deep features based on deep learning have been widely used because it has been demonstrated that the features have great generalisation. In this paper, a convolutional neural network (CNN) is utilised to extract deep and high-level features from the paintings. Next, the features were used for similarity measure between the query image and database images; subsequently, similar images are ranked by the distance between both pair features. Our experiments show that this strategy significantly improves the performance of content-based image retrieval for the style retrieval task of painting. Keywords: Content-based Image Retrieval, Deep Learning, Convolutional Neural Network

  • Forecasting Facebook User Engagement using Hybrid Prophet and Long Short-Term Memory Model

    by Yih Hern Kong, Khai Yin Lim, Wan Yoke Chin

    Business forecasting remains a popular topic these days. A reliable business forecast often plays a vital part in an advertising campaign. The amount of attention acquired by posting an advertisement is one of the most essential criteria in determining the efficacy of the advertisement. The number of times that public users engage with a content signifies the amount of attention received, was measured by user engagement. With a good forecast, the advertisement could be promoted to a larger number of people. Facebook, as the most popular social media site, is favoured by majority of the advertisers. Therefore, this study addresses Facebook user engagement by forecasting the optimum date to post an advertisement. Different forecasting models, each with its own strengths and weaknesses, are used to model time series data with various properties. The objective of this study is twofold: to investigate the accuracy of the proposed Hybrid Prophet-LSTM that combines Long Short Term Memory (LSTM) and FBProphet (Prophet) and to study the holiday impact on user engagement forecasting on Facebook brand pages. Data from 3 popular brand pages in the period of June 2018 to March 2019 was used in the experiments. The results show that the proposed hybrid model outperforms both the standalone LSTM and Prophet across the datasets. Besides, it is found that holiday effect could generally increase forecast accuracy. The optimum date for an advertisement campaign can therefore be determined based on the most forecasted user engagement, which consequently enhances the business income. Keywords: Time Series forecasting, Hybrid forecasting, Business forecasting, Prophet, LSTM, Holiday effect