MODIFICATION OF K-MEANS AND K-MODE ALGORITHMS TO ENHANCE THE PERFORMANCE OF CLUSTERING STUDENT LEARNING STYLES IN THE LEARNING MANAGEMENT SYSTEM

During the Corona Virus Disease (COVID-19) pandemic, many access to learning used the e-learning system through the Learning Management System (LMS) platform. One of the weaknesses of the learning process through e-learning is that it cannot detect student learning styles based on actual behavior patterns during online learning. Most of the methods used to study automatic detection techniques use classification methods. One of the weaknesses of the classification method is the determination of class labels, so a learning style detection model was developed using the concept of clustering before classification to produce class labels with a high level of validation. This study focuses on increasing the validity of the clustering method by comparing the performance of the modified K-Means and K-Mode algorithms. The proposed modification of the two algorithms is carried out at the initial centroid determination stage. The performance of the two modified algorithms was carried out by measuring the validation values of the Davies-Bouldin Index (DBI) and Silhouette Index (SI) using log file data from 88 students taking computer programming courses. The validation results of the DBI and SI values indicate that the proposed model has better performance when implemented in the K-Mode algorithm than the K-Means algorithm. © 2023 ICIC International.

Transformational Leadership and Gender of the Leader for Government Insurance Worker in Covid Situation

This research aims to determine the effect of transformational leadership, employee engagement, job satisfaction on job performance with gender moderation from the leader on Health Social Security Administering Agency employees. This research was conducted in Indonesia with a total of 329 respondents. Research respondents were selected using the purposive sampling method. The research sample is Health Social Security Administering Agency employees at branch offices in Indonesia in region DKI Jakarta, Bogor, Depok, Tangerang, and Bekasi with a minimum of 2 years. This research is a quantitative research using the Structural Equation Model (SEM) method. This study proves that there is no effect between transformational leadership and job performance and no gender moderating effect of transformational leadership on job performance. This study also confirms the impact of transformational leadership on employee engagement and job satisfaction. In addition, it also proves the effect of job satisfaction and employee engagement on job performance. The contribution of this research is to add information at the theoretical level of human resource management and positive managerial implications, especially for company management, to determine the proper steps to improve job performance. © Ecological Chemistry and Engineering A 2020.