Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Computer Science and Informatics Engineering
Muhammad Zarwin Syahputra
Universitas Islam Negeri Sumatera Utara
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : journal of computer science and informatics engineering

 1 
Sieva: K-Means And 360-Degree Feedback For Sugarcane Harvest Evaluation at PTPN II Kwala Madu Muhammad Zarwin Syahputra; Raissa Amanda Putri; Muhamad Alda
Journal of Computer Science and Informatics Engineering Vol 5 No 4 (2026)
Publisher : Ali Institute of Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/cosie.v5i4.1966

Abstract

Sugarcane harvest yields at PT Perkebunan Nusantara II (PTPN II) Kwala Madu often fall short of targets, and harvest evaluation is still largely manual, slow, and open to subjective bias. This study developed SIEVA, a web-based harvest evaluation information system that combines two evaluation perspectives: K-Means clustering of plot-level average harvest results (outcome-based) and 360-Degree Feedback on employee competencies (competency-based). The system was built with the Rapid Application Development model using PHP and MySQL, based on weighing-station records and employee assessment data collected from September 2022 to April 2023. K-Means with three clusters (good, fair, and poor) grouped 30 plots into 10, 11, and 9 plots after five iterations, with final centroids of 5,812, 5,278, and 4,601 [VERIFY FROM SIEVA OUTPUT: the reported centroids and the Silhouette and Davies–Bouldin indices must be checked against the final system output before submission.]. Black-box testing by one expert across ten function groups indicated that the functions performed as specified. The contribution is applied: an information-system model that digitalizes outcome-based and competencybased evaluation in plantation operations, not a new algorithm. Quantitative validation of the cluster structure, tests with more users, and evidence of the system's effect on management decisions remain future work.
Co-Authors Muhamad Alda Raissa Amanda Putri