Herman Herman
Universitas Ahmad Dahlan, Yogyakarta, Indonesia

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

K Value Effect on Accuracy Using the K-NN for Heart Failure Dataset Alya Masitha; Muhammad Kunta Biddinika; Herman Herman
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 22 No 3 (2023)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v22i3.2984

Abstract

Heart failure is included in the category of cardiovascular disease. Heart disease is not easy to detect, and its detection needs to be done by experienced and skilled medical professionals. Most patients with heart failure require hospitalization. Common symptoms of heart disease, such as chest pain and high or low blood pressure, vary from person to person. This study aims to find the most optimal k value based on the accuracy obtained based on calculations by testing different k values, namely 1, 3, 5, 7, and 9. After getting the results of the accuracy of the five k values, compare which accuracy has the highest value, best for K-Nearest Neighbor (K-NN) models. The classification process uses the K-NN algorithm. This algorithm is quite easy to use because some parameters work using distance metrics and k values. Therefore, the value of k in the K-NN algorithm greatly affects the accuracy that will be produced. In the results of this study, the accuracy obtained was k = 7 and k = 9, which are the most optimal results because they have the highest accuracy compared to other k values, with an accuracy of 88%. The expected benefit of this research is that it can make a scientific contribution to research in the field of machine learning classification, especially in predicting heart failure
Optimizing Inventory with Frequent Pattern Growth Algorithm for Small and Medium Enterprises Imam Riadi; Herman Herman; Fitriah Fitriah; Suprihatin Suprihatin
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 23 No 1 (2023)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i1.3363

Abstract

The success of a business heavily relies on its ability to compete and adapt to the ever-changing market dynamics, especially in the fiercely competitive retail sector. Amidst intensifying competition, retail business owners must strategically manage product placement and inventory to enhance customer service and meet consumer demand, considering the challenges of finding items. Poor inventory management often results in stock shortages or excess. To address this, adopting suitable inventory management techniques is crucial, including techniques from data mining, such as association rule mining. This research employed the FP-Growth algorithm to identify patterns in product placement and purchases, utilizing a dataset from clothing store sales. Analyzing 140 transactions revealed 24 association rules, comprising rules with 2-itemsets and frequently appearing 3-itemset rules. The highest support value in the final association rules with 2-itemsets was 10% with a confidence level of 56%, and the highest support value in the 3-itemsets was 67% with the same confidence level. Additionally, three rules had a confidence level of 100%. Thus, the association rules generated by the FP-Growth frequent itemset algorithm can serve as valuable decision support for sales of goods in small and medium-sized retail businesses.