No abstract

This paper discusses the potential of applying VGG16 model architecture for plant classification. Flower images are used instead of leaves as in other plant recognition model because the structure of shape and color of leaves are similar in nature. This might be disadvantageous when we want to use only leaves images as a sole feature of plants to classify the species. Previous work has demonstrated the effectiveness of using transfer learning, dropout and data augmentation as a method to reduce overfitting problem of convolutional neural network model when applied in limited amount of images data. We have successfully build and train the VGG16 model with 2800 flower images. The model able to achieve a classification accuracy score of 96.25% for training set, 93.93% for validation set and 89.96% for testing set.

This study investigates the performance of using grid search cross validation as a hyperparameter tuning method for support vector classifier in classifying the quality of agarwood oil. The data of agarwood oil sample were obtained from Forest Research Institute Malaysia (FRIM) and Universiti Malaysia Pahang, Malaysia. The chemical compound abundances of agarwood oil sample are used as its input whiles the quality of agarwood oil of high quality and low quality as the output. The parameter used to train the support vector machine classifier by using the grid search cross validation is the parameter C, gamma and kernel. Based on the results of the study, it shows that by using combination of C with value of 1, gamma value of 10 and radial basis function kernel gives the best classification accuracy of 100% and performance measure scores of 1.0.

No abstract

A new online business platform is needed in Malaysia. The proposed system aims to provide B40 household income group with the necessary knowledge for increasing readiness in online business, and equip them with access to available financing, e-commerce, and logistic solutions. Prior to project commencement, a review is performed on e-commerce and development life cycle models. The adopted approach includes issues such as client engagement, development team, duration of project, requirement of prototype, and scale of deployment. In this case, a modified Rapid Application Development model is suitable for monitoring project progress and delivery.