Article Per Year (5 Year)
p-Index From 2020 - 2025
0.947
P-Index
This Author published in this journals
All Journal JITK (Jurnal Ilmu Pengetahuan dan Komputer) JOMLAI: Journal of Machine Learning and Artificial Intelligence Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen)
Sundari Retno Andani
STIKOM Tunas Bangsa, Pematangsiantar, Indonesia
Computer Science & IT Control & Systems Engineering Engineering

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

Found 4 Documents
Search

 1 
Implementation of K-Means Algorithm for Clustering Books Borrowing in School Libraries Daud Siburian; Sundari Retno Andani; Ika Purnama Sari
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 1 No. 2 (2022): June
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (594.364 KB) | DOI: 10.55123/jomlai.v1i2.725

Abstract

The school library is an important resource in an effort to support the process of improving the quality of education in schools. Through the library a lot of information can be extracted and used for educational purposes. The library is expected to play its function as a vehicle for education, research, preservation, information, and recreation to improve the nation's intelligence. This study aims to cluster the borrowing of library books at SMA Assisi Pematangsiantar. The research data was obtained from the school library. The algorithm used for the clustering process is K-Means Clustering which is one of the data mining algorithms. The data was processed using Microsoft Excel and Rapid Miner 5.3 to determine the value of the centroid in 2 clusters, namely the highest and lowest clusters. Based on manual calculations with Microsoft Excel and testing with Rapid Miner, this study resulted in the same value, namely the highest cluster produced 6 types of books including Mathematics,. Geography, Chemistry, Civics, Physical Education and Computers. As for the lowest cluster, there are 6 types of books, namely Indonesian, English, Biology, Physics, Religion and Cultural Arts. So it can be concluded that the K-Means method in this study can cluster school library book borrowing well, referring to manual calculations and testing which have the same results
Implementation of the SMART Algorithm in Determining Patient Satisfaction Levels with Outpatient Services Patar Simbolon; Muhammad Zarlis; Sundari Retno Andani; Fitri Anggraini
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 2 No. 1 (2023): March
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v2i1.159

Abstract

This study aims to implement the SMART algorithm in determining the level of patient satisfaction with outpatient services at Vita Insani Hospital Pematangsiantar. This study uses four evaluation criteria, namely speed of service, friendliness of staff, clarity of information, and comfort of the room. There are nine alternatives evaluated, namely registration, polyclinic, doctor, cashier, laboratory, radiology, pharmacy, emergency room, and security guard. This study uses the SMART method (Simple Multi-Attribute Rating Technique) in determining the level of patient satisfaction with outpatient services. Calculations are performed either manually or computerized. The results showed that the two calculation methods yielded the same results, namely alternative A9 (Security Guard) was selected as an alternative that needed to improve its services in improving outpatient services at Vita Insani Hospital. By using the SMART algorithm, it is hoped that the hospital can identify service areas that need to be improved to increase patient satisfaction in outpatient services. This research provides valuable information for hospital management in making strategic decisions to improve service quality and meet patient expectations.
Optimasi Rute Menggunakan Vehicle Routing Problem (VRP) Dengan Algoritma Genetika Sundari Retno Andani
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 4, No 1 (2023): Edisi Januari
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v4i1.125

Abstract

Transportasi merupakan salah satu kegiatan distribusi logistik yang sangat mempengaruhi harga barang. Optimasi rute dan waktu transportasi dengan memaksimalkan kendaraan yang tersedia dapat mengurangi biaya transportasi. Permasalahan tersebut dapat dimodelkan dengan vehicle routing problem (VRP). VRP memberikan solusi dengan meminimalkan biaya yang direpresentasikan oleh total jarak tempuh dan jumlah kendaraan yang digunakan. VRP merupakan non-polynimonal hard (NP-hards) yang menggunakan pendekatan heuristik dalam mencari solusi. Dalam penyelesaian permasalahan VRP ini digunakan algoritma genetika. Algoritma genetika merupakan salah satu merode heuristik rute terpendek. Hasil penelitian ini menghasilkan rute terbaik yaitu kromoson dengan probabilitas terkecil dan pencarian waktu terkecil ditentukan berdasarkan jarak dibagi dengan kecepatan dalam melewati rute-rute yang sudah ditemukan.
ENHANCING HERBAL PLANT LEAF IMAGE DETECTION ACCURACY THROUGH MOBILENET ARCHITECTURE OPTIMIZATION IN CNN Anan Wibowo; Rahmat Zulpani; Agus Perdana Windarto; Anjar Wanto; Sundari Retno Andani
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 4 (2025): JITK Issue May 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i4.6498

Abstract

Herbal plants have various health benefits, but their type identification remains challenging for the general public. This study aims to improve the accuracy of herbal plant leaf classification using Convolutional Neural Network (CNN) based on MobileNetV2 architecture. To enhance model performance, various optimization techniques including fine-tuning, batch normalization, dropout, and learning rate scheduling were implemented. The experimental results showed that the proposed optimized model achieved an accuracy of 100%, significantly outperforming previous studies that used standard MobileNet with an accuracy of 86.7%. While these perfect results warrant additional validation with more diverse datasets to confirm generalizability, this study contributes to the development of a more accurate herbal plant classification system that is readily accessible to the general public. Future work should explore model performance under varying environmental conditions and with expanded plant species datasets.
Co-Authors Agus Perdana Windarto Anan Wibowo Daud Siburian Fitri Anggraini Ika Purnama Sari Muhammad Zarlis Patar Simbolon Rahmat Zulpani Wanto, Anjar