Search

The new students struggle to understand the introductory programming courses, due to its intricate nature, which results in higher dropout and increased failure rates. Despite implementing productive methodologies, the instructor struggles to identify the students with distinctive levels of skills. The modern institutes are looking for technology-equipped practices to classify the students and prepare personalized consultation procedures for each class. This paper applies decision tree-based machine learning classifiers to develop a prediction model competent to forecast the outcome of the introductory programming students at an early stage of the semester. The model is then transformed into an adaptive consultation framework which generates three types of colored signals; red, yellow, and green which illustrates whether the student is performing low, average, or high respectively. This provides an opportunity for the instructor to set precautionary measures for low performing students and set complicated tasks that help the highly skilled students to improve their skills further. The experiments compare a set of decision tree-based classifiers and conclude J48 as an efficient model in classifying students in all classes with high accuracy, sensitivity, and F-measure. Even though the aim of the research is to focus on introductory programming courses, however, the framework is flexible and can be implemented in other courses. [ABSTRACT FROM AUTHOR]

Massive paddy crops lost every year due to weather condition, plant disease and pest attack. Pest attack is among the main threat that reducing the quality and quantity of the paddy crops. Pesticide is used to control and eliminate the pest in paddy field. In order to determine the quantity of pesticide used, traditional method is based on manual counting where sticky trap is used to trap the pest and after that the pest was counted manually. However, this method is tedious and time consuming due to many crops generally found in paddy field. This can lead to imprecise counting through the process and delay in order to gain the accurate count. This paper proposed an image processing technique and artificial intelligent as an alternate method for identification and counting of pests. The suggested pest detection consists of four (4) consecutive steps; image acquisition, image segmentation, feature extraction and detection. The detection step contains two processes that are classification and counting of pest. A k-nearest neighbour (kNN) classifier is used in this step. The process is developed and implemented using MATLAB. Simulation results using 10 pest images indicated that the classification performance of brown planthopper using kNN provides better performance compared to decision tree. The kNN achieved precision 0.97, recall 0.96, accuracy 0.97 and F score 0.96. The system will be used in assisting paddy field worker to predict the type and amount of pesticide to be used for the pest control. [ABSTRACT FROM AUTHOR]