Article Per Year (5 Year)
p-Index From 2020 - 2025
0.751
P-Index
This Author published in this journals
All Journal Journal of Artificial Intelligence and Engineering Applications (JAIEA) Blend Sains Jurnal Teknik
Hasibuan, Wilda Rina
Unknown Affiliation
Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Mechanical Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Linear Regression Analysis in Predicting the Amount of Stock of HP Sparepart Goods in GMT Gilang Aryudha; Hasibuan, Wilda Rina
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 1 (2024): October 2024
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i1.676

Abstract

The rapid advancement of the digital era has made smartphones an essential part of daily life, making the availability of high-quality spare parts crucial for their seamless operation. GMT, a store specializing in smartphone spare parts, faces challenges in predicting fluctuating consumer demand, often leading to either stock shortages or excesses. To address this issue, this research develops a stock prediction system based on linear regression, which analyzes sales data to accurately forecast stock needs. The implementation of this method has resulted in improved accuracy in stock management, enabling GMT to optimize inventory, minimize potential losses, and enhance both customer satisfaction and operational efficiency.
Rainfall Prediction Analysis Using the Fuzzy Time Series Method in Medan City Zikri, Syaftial; Hasibuan, Wilda Rina
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 1 (2024): October 2024
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i1.685

Abstract

The increasingly significant climate change causes high rainfall variability, thus requiring an accurate prediction method for disaster mitigation planning and water resource managment. This study aim to analyze rainfal prediction in Medan City using Fuzzy Time Series (FTS) methode. Historical rainfall data for Medan City for a certain period is collected and processed to build an FTS model. The fuzzification process is carried out to convert numerical data into fuzzy values, then the time series relationship is identified to predict the next rainfall value. Based on Chen's fuzzy time series with the detemination of the average-based interval, the Medan City rainfall forecast based on January 2019-December 2023 data obtained the forecast results for January 2024 is 386.7 mm. From the result of tests that have caried out, the best number of sampels be used in the Medan City rainfall case is 60 data, namely the period January 2019 - December 2023.
Analysis and Comparison of the Performance of K-Means Algorithm and X-Means Algorithm in Disease Type Clustering in Mitra Medika Hospital Herdawani Afdilla; Hasibuan, Wilda Rina
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 1 (2024): October 2024
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i1.696

Abstract

The system used by the hospital is currently still manual in managing patient data and information. What happened at Mitra Medika Hospital is that it is difficult to provide medical needs related to the patient's illness, considering the many types of illnesses that provide many medical needs. Several inpatients have used BPJS facilities with various illnesses suffered by patients to undergo further examinations in order to recover from the illness they are suffering from. Mitra Medika Hospital only sees medical needs based on the illness suffered by the patient, but seeing the large amount of patient history data makes it very difficult for Mitra Medika Hospital to find out the group of illnesses that patients often experience. This study uses a quantitative approach which starts from a theoretical framework, expert ideas, or researchers' understanding based on their experience, then developed into problems and their solutions that are submitted to obtain justification (verification) or assessment in the form of empirical data support in the field. Here, a data mining pattern is applied where this data mining is a very large data mining (big data). Cluster 0: From 245 Men (Suffering Between Diseases 1-5) Cluster 1: From 255 Women (Suffering Between Diseases 6-10) By using the K-Means Algorithm and the X-Means Algorithm, clustering can be produced. By using the Disease History data, the K-Means Algorithm and the X-Means Algorithm methods can be applied to determine clusters. By using web programming, it can produce an Analysis and Comparison of the Performance of the K-Means Algorithm and the X-Means Algorithm in Clustering Types of Diseases at Mitra Medika Hospital.
Klasifikasi Kerusakan (Cacat) pada Biji Kopi Arabika Menggunakan Algoritma KNN (K-Nearest Neighbor) Hasibuan, Wilda Rina; Sari, Indah Purnama; Basri, Mhd
Blend Sains Jurnal Teknik Vol. 3 No. 4 (2025): Edisi April
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/blendsains.v3i4.781

Abstract

Penelitian ini mengkaji klasifikasi cacat pada biji kopi Arabika menggunakan metode K-Nearest Neighbor (KNN) di Koperasi Usaha Tani Gayo, Aceh Tengah. Kopi Arabika, dengan nilai ekonomis tinggi, sering kali dinilai secara subyektif oleh petani menggunakan indra manusia, yang kurang efektif. Oleh karena itu, penelitian ini menggunakan metode KNN untuk meningkatkan akurasi klasifikasi cacat biji kopi. Metode KNN, yang merupakan algoritma supervised, mengklasifikasikan objek berdasarkan kategori tetangga terdekatnya. Penelitian ini menggunakan citra digital berwarna yang diolah dengan web-tools Teachable Machine dan dataset MNIST. Dataset ini dibagi menjadi tiga bagian: pelatihan, validasi, dan pengujian. Gambar cacat biji kopi diklasifikasikan ke dalam 16 kelas, seperti Full Sour Bean, Full Black Bean, dan lainnya. Evaluasi menunjukkan bahwa model KNN memiliki akurasi tinggi dalam klasifikasi cacat biji kopi, meskipun membutuhkan waktu komputasi yang signifikan. Hasil penelitian diimplementasikan dalam aplikasi mobile berbasis Flutter dan bahasa pemrograman Dart, yang mempermudah proses klasifikasi cacat biji kopi Arabika di Koperasi Tani Gayo, meningkatkan kualitas dan efisiensi penentuan biji kopi.
Co-Authors Basri, Mhd Gilang Aryudha Herdawani Afdilla RR. Ella Evrita Hestiandari Zikri, Syaftial