and conference attendees, Ladies and Gentlemen, Assalamu'alaikum Wr. Wb. May peace and health be upon us all.First of all, let us express our utmost gratitude to God Almighty (SWT) for His blessings and grace so that even though in this coronavirus pandemic atmosphere, we can all still participate in the third iSriti

No abstract

Software defect prediction is crucial used for detecting possible defects in software before they manifest. While machine learning models have become more prevalent in software defect prediction, their effectiveness may vary based on the dataset and hyperparameters of the model. Difficulties arise in determining the most suitable hyperparameters for the model, as well as identifying the prominent features that serve as input to the classifier. This research aims to evaluate various traditional machine learning models that are optimized for software defect prediction on NASA MDP (Metrics Data Program) datasets. The datasets were classified using k-nearest neighbors (k-NN), decision trees, logistic regression, linear discriminant analysis (LDA), single hidden layer multilayer perceptron (SHL-MLP), and Support Vector Machine (SVM). The hyperparameters of the models were fine-tuned using random search, and the feature dimensionality was decreased by utilizing principal component analysis (PCA). The synthetic minority oversampling technique (SMOTE) was implemented to oversample the minority class in order to correct the class imbalance. k-NN was found to be the most suitable for software defect prediction on several datasets, while SHL-MLP and SVM were also effective on certain datasets. It is noteworthy that logistic regression and LDA did not perform as well as the other models. Moreover, the optimized models outperform the baseline models in terms of classification accuracy. The choice of model for software defect prediction should be based on the specific characteristics of the dataset. Furthermore, hyperparameter tuning can improve the accuracy of machine learning models in predicting software defects.

Leaf geometric properties play an important role in plat study. This paper aims to propose a method to measure leaf geometric properties, including area, perimeter, length, and width, using a computer vision system. The proposed method measured the properties by capturing leaf image from the top view using a calibrated camera. The captured image was processed to produce a binary image. The properties were extracted from the binary image based on camera parameters. The camera parameters were used to convert the unit of the properties from pixel to cm. Thirty leaf samples from three types of leaf were used to validate the proposed method in an experiment. The experiment result shows that the leaf measurement result using the proposed method has good accuracy with average absolute relative error less than or equal 2.27% and has strong linear relationship with manual measurement indicated by the coefficient of determination greater than 0.999.