Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Informatika

Penerapan Natural Language Processing dalam Pembuatan Aplikasi Penerjemah Bahasa Melayu Dialek Panai – Bahasa Indonesia Dar, Muhammad Halmi; Hasibuan, Mila Nirmala Sari; Nasution, Fitri Aini
Jurnal Informatika Vol 11, No 3 (2023): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v11i3.5887

Abstract

The Panai dialect of Malay is the mother tongue used by the speaking community in four sub-districts in Labuhanbatu Regency. The reduced number of native speakers who are skilled in the Panai Malay dialect can threaten the sustainability of this language. Efforts to preserve the Panai Malay dialect must be made to avoid extinction. One way that can be done is to document vocabulary in the form of a translator application. This study aims to create an application translator for the Panai-Indonesian dialect of Malay by applying natural language processing. As for the potential users of this application, they are the people of Labuhanbatu in general, especially those in the four sub-districts previously described. The stages of the research method used were: requirement analysis, design, implementation, testing, and maintenance. This research focuses on technology for improving information and communication technology content in the context of local wisdom (culture and language) in Indonesia. The focus of this research is in line with the Strategic Plan (RENSTRA) of Labuhanbatu University, which covers the fields of information and communication technology and cultural arts. From the results of this study, it is hoped that local wisdom in Labuhanbatu Regency will be maintained as social capital for the resilience of the Indonesian nation.
Penerapan Metode KNN untuk Menentukan Minat Calon Mahasiswa Riyanto, Tiara; Yanris, Gomal Juni; Hasibuan, Mila Nirmala Sari
Jurnal Informatika Vol 12, No 3: INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.6153

Abstract

This study focuses on the implementation of data mining to determine the interests of prospective male and female students in the Informatics Management Department using the K-Nearest Neighbors (KNN) method. The analysis process is carried out through the Knowledge Discovery in Databases (KDD) stages, which include data selection, pre-processing, transformation, data mining, and pattern evaluation. The KDD stage ensures that the data used has been prepared and processed properly to produce an accurate and relevant model. The KNN method is used to classify sample data consisting of 82 prospective male and female students. The results of this study indicate that 63 out of 82 prospective students are interested in the Informatics Management Department, while 19 other prospective students are not interested. This classification process shows that the KNN method is able to identify the interests of prospective students with a high level of accuracy, providing useful information for universities in understanding the preferences of their prospective students. Evaluation of the research results using two evaluation tools, namely Test and Score and Confusion Matrix, showed perfect results with an accuracy of 100%. Both of these evaluation tools are consistent in assessing the performance of the KNN model, confirming that this model works very well in classifying prospective student interests. In conclusion, the KNN method is proven to be effective and reliable in determining prospective students' interest in the Informatics Management Department, providing a strong foundation for similar applications in the future.
Implementasi Deep Learning Untuk Menentukan Harga Buah Sawit Manurung, Romtika; Sihombing, Volvo; Hasibuan, Mila Nirmala Sari
Jurnal Informatika Vol 12, No 3: INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.6029

Abstract

This study aims to analyze the price of palm oil using Convolutional Neural Network (CNN) method in deep learning. CNN was chosen for its ability to process complex data and recognize patterns from diverse data. The stages of research include data analysis, data pre-processing, predictive model design for CNN method, CNN classification model prediction results, CNN method evaluation, and CNN method evaluation results. This study aims to produce a model that can predict the price of oil palm with high accuracy, based on data covering a variety of characteristics of farmers and the quality of oil palm crops. Prediction results were conducted using data from 50 oil palm farmers. From the prediction, as many as 23 data farmers get a price of IDR 2,300, 13 other farmers get a price of IDR 2,000, and the remaining 14 data farmers get a price of IDR 1,800. The results of this prediction are based on data from farmers and the quality of oil palm crops they grow and produce. By utilizing the CNN method, the model can capture various factors that affect the price of palm oil, including the quality of palm fruit and agricultural conditions. Evaluation of the CNN method showed very good results, with almost perfect accuracy. This method managed to predict palm oil prices very precisely, showing that CNN can be an effective tool in the analysis of palm oil prices. The results of this evaluation confirmed that the CNN method can be relied upon to provide accurate predictions, helping farmers and palm oil industry players in determining prices that are in accordance with the quality and condition of the crop.