Claim Missing Document
Check
Articles

Found 17 Documents
Search

Generative artificial intelligence as an evaluator and feedback tool in distance learning: a case study on law implementation Nurdiana, Dian; Maulana, Muhamad Riyan; Hasanah, Siti Hadijah; Chairunnisa, Madiha Dzakiyyah; Komuna, Avelyn Pingkan; Rif'an, Muhammad
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i3.pp2490-2505

Abstract

The development of generative artificial intelligence (GAI) has impacted various fields, including higher education. This research examines the use of GAI as an evaluator and feedback provider in distance legal education. This study tested five GAI models: ChatGPT, Perplexity, Gemini, Bing, and You, using a sample of 20 students and evaluations from legal experts. Descriptive statistical analysis and non-parametric tests, including Wilcoxon, intraclass correlation coefficient (ICC), Kappa, and Kendall's W, were used to assess accuracy, feedback quality, and usability. The results showed that ChatGPT was the most effective GAI, with the highest mean scores of 4.22 from experts and 4.12 from students, followed by Gemini with scores of 4.15 and 4.07. In terms of binary judgement accuracy, Gemini scored 80%, ChatGPT 60%, while Perplexity, Bing, and You had lower scores. Statistical analysis showed moderate agreement (ICC=0.439) and low alignment (Kappa=-0.058) between the GAIs and expert evaluations, with a Kendall's W value of 0.576 indicating moderate consistency in judgements. These findings emphasize the importance of selecting effective GAIs such as ChatGPT and Gemini to improve academic evaluation and learning in legal education, and pave the way for further innovations in the use of AI.
CLASSIFICATION SUPPORT VECTOR MACHINE IN BREAST CANCER PATIENTS Hasanah, Siti Hadijah
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 16 No 1 (2022): BAREKENG: Jurnal Ilmu Matematika dan Terapan
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (719.413 KB) | DOI: 10.30598/barekengvol16iss1pp129-136

Abstract

Support vector machine is one of the supervised learning methods in machine learning that is used in classification. The purpose of this study is to measure the accuracy of classification by using 3 hyperplane functions in SVM, namely linear, sigmoid, polynomial, and radial basis function (RBF). Based on the simulation results of training data and testing data on female breast cancer patients, SVM with hyperplane RBF has better accuracy than hyperplane polynomial, linear and sigmoid. The RBF results for the training and testing data were 89.1% and 73.2%, respectively. Based on the results of the classification of training data for female breast cancer patients, 88.07% had no recurrence and 93.33% had recurrence events. Meanwhile, based on the results of the classification of testing data, female patients did not recurrence events and recurrence events was 72.55% and 80.00%, respectively. So from this article, it can be concluded that SVM with hyperplane RBF is one of the best methods in the application of the method of classifying female breast cancer patients.
Peramalan Jumlah Sampah di Kabupaten Lombok Timur dengan Metode ARIMA dan Dekomposisi Nurmayanti, Wiwit Pura; Kertanah, Kertanah; Hasanah, Siti Hadijah; Rahim, Abdul; hendrayani, hendrayani
Jambura Journal of Probability and Statistics Vol 4, No 2 (2023): Jambura Journal Of Probability and Statistics
Publisher : Department of Mathematics, Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jjps.v4i2.19954

Abstract

AbstractForecasting is the science of predicting events that will occur using historical data and projecting them into the future with some form of mathematical model that aims to handle and policy in the future. In forecasting there are several methods, two of which are Autoregeressive Integrated Moving Average (ARIMA) and Decomposition. ARIMA is a method developed by George Box and Gwilym Jenkins in 1970. The Decomposition Method is a method that decomposes (breaks) time series data into several patterns, namely trend, cyclical and seasonal, and identifies each of these components separately. Both of these methods can be applied in various fields, one of which is in the field of environmental health, especially data on the amount of waste. Problems related to the amount of waste in East Lombok are still a concern of the government because as the population increases and the needs of the community each year have the potential to cause waste problems. The final disposal site (TPA) in East Lombok is located in Ijo Balit, this TPA is the only one in East Lombok. The purpose of this research is to see which method is the best between ARIMA and Decomposition, and to see the forecasting results of the amount of waste entering TPA Ijo Balit from the best method. Based on the results of the analysis carried out by the Decomposition model, it gives the best performance in terms of the smallest error value so that it can be used for Forecasting and produces an RMSE value of 5201.694, a MAPE of 0.955827 and a MASE of 0.0129691. The results of forecasting using the Decomposition method are that the highest forecast occurs in December, while the lowest occurs in January with a total of 1,439,439 (tons) and 1,117,000 (tons). Keywords:  Forecasting, ARIMA, Decomposition, Waste
Analisis Data Transaksi Penjualan Obat di Apotek X Samarinda Menggunakan Algoritma Apriori dan FP-Growth Berbasis Association Rule Mining: Analysis of Drug Sales Transaction Data at Pharmacy X Samarinda Using Apriori and FP-Growth Algorithms Based on Association Rule Mining Nurmayanti, Wiwit Pura; Hasanah, Siti Hadijah; Rahim, Abdul
Jurnal Sains dan Kesehatan Vol. 6 No. 3 (2024): J. Sains Kes.
Publisher : Fakultas Farmasi, Universitas Mulawarman, Samarinda, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25026/jsk.v6i3.2353

Abstract

Association Rule Mining is a data mining technique that is used to search for a group of items that often appear together in an event and is often analogous to a market basket. Algorithms in the association rule include apriori and frequent pattern growth (fp-growth). We can apply these two algorithms in various fields, one of which is in the pharmaceutical sector, namely related to drug sales transactions in pharmacies. The aim of this research is to see a picture of drug sales transactions at Pharmacy X, Samarinda City, and to find out the best algorithm for determining drug sales transaction patterns at the pharmacy. Based on the results of the analysis, information was obtained that out of 100 drug sales transactions at Pharmacy The product that consumers purchased the most was the ChargeR type of medicine, namely 7 transactions and the one that was purchased the least was Grape Tempra Syrup 60 ml which was purchased in only 1 transaction, and seen from the higher support and confidence values, the fp-growth algorithm could produce rules better to the apriori algorithm. Keywords:          association rule, fp-growth algorithm, apriori algorithm, pharmacies   Abstrak Association Rule Mining merupakan teknik data mining untuk menemukan aturan asosiasi antara suatu kombinasi item. Algoritma dalam Association Rule dapat diterapkan diberbagai bidang, salah satunya adalah bidang farmasi terkait transaksi penjualan obat di Apotek, adapun algoritma tersebut adalah Apriori dan Frequent pattern Growth (Fp-Growth). Tujuan penelitian ini adalah untuk melihat gambaran transaksi penjualan obat di Apotek X Kota Samarinda, dan mengetahui algoritma terbaik dalam menentukan pola transaksi penjualan obat di apotek tersebut. Berdasarkan hasil analisis diperoleh informasi bahwa dari 100 transaksi penjualan obat di Apotek X kota Samarinda, obat yang paling banyak terjual dalam 1 transaksi terdapat pada transaksi ke 41 dengan jenis obat sebanyak 17 jenis. Produk yang paling banyak dibeli konsumen adalah jenis obat ChargeR yaitu sebanyak 7 transaksi dan yang paling sedikit dibeli adalah Sirup Tempra Anggur 60 ml yang dibeli hanya dalam 1 transaksi, dan dilihat dari nilai support dan confident yang lebih tinggi algoritma fp-growth mampu menghasilkan aturan algoritma yang lebih baik dibandingkan dengan algoritma apriori. Kata Kunci:         association rule, apriori, frequent pattern growth, apotek
Development of Website-Based Statistics Learning Videos Dewi Juliah Ratnaningsih; Hasanah, Siti Hadijah
JTP - Jurnal Teknologi Pendidikan Vol. 24 No. 2 (2022): Jurnal Teknologi Pendidikan
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat, Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/jtp.v24i2.27153

Abstract

One source of learning in the learning process is learning materials. In distance education, learning resources prepared for students must be able to be studied independently. The separation of lecturers and students needs to be bridged by learning materials that can be understood by students. A video is a form of learning materials that can be used to help students understand the material. Through videos, students can learn anywhere and anytime according to the time available. In the video, the duration of the material delivery is very significant. Likewise, components such as intro, greeting, and outro greatly support student motivation. The effective video duration in learning website-based statistical data analysis is 10-15 minutes. The component of presenting material that is in great demand by students in the discussion of sample questions and their application using R software.
Analysis of CART and Random Forest on Statistics Student Status at Universitas Terbuka Hasanah, Siti Hadijah; Julianti, Eka
INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi Vol 6 No 1 (2022): February 2022
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (249.763 KB) | DOI: 10.29407/intensif.v6i1.16156

Abstract

CART and Random Forest are part of machine learning which is an essential part of the purpose of this research. CART is used to determine student status indicators, and Random Forest improves classification accuracy results. Based on the results of CART, three parameters can affect student status, namely the year of initial registration, number of rolls, and credits. Meanwhile, based on the classification accuracy results, RF can improve the accuracy performance on student status data with a difference in the percentage of CART by 1.44% in training data and testing data by 2.24%.
Analisis perbandingan K-Means, K-Medoids, dan Fuzzy C-Means untuk pengelompokan provinsi di Indonesia berdasarkan produksi padi tahun 2024 Mujahidin, Ilham; Hasanah, Siti Hadijah
Jurnal Statistika dan Sains Data Vol 3, No 1 (2025): Jurnal Statistika dan Sains Data
Publisher : Universitas Negeri Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/jssd.v3i1.25385

Abstract

Padi menjadi salah satu komoditas penting dalam sektor pertanian Indonesia yang berperan krusial dalam menjaga ketahanan pangan nasional. Tujuan dari penelitian ini adalah untuk melakukan pengelompokan terhadap 38 provinsi di Indonesia berdasarkan kemiripan produksi padi guna memahami variasi spasial kinerja pertanian di berbagai provinsi. Dalam analisis ini digunakan tiga metode clustering yaitu K-Means, K-Medoids, dan Fuzzy C-Means. Analisis dilakukan dengan mempertimbangkan dua variabel utama yakni luas panen dan jumlah produksi padi tahun 2024 yang datanya bersumber dari Badan Pusat Statistik. Evaluasi kualitas klaster dilakukan menggunakan Davies-Bouldin Index (DBI). Berdasarkan hasil analisis, diketahui bahwa metode K-Means menghasilkan clustering paling optimal dengan memperoleh nilai DBI terendah sebesar 0,276 saat jumlah klaster , dibandingkan dengan K-Medoids (0,279 pada ) dan Fuzzy C-Means (0,285 pada ). Klaster yang terbentuk menunjukkan adanya pemisahan yang jelas antara provinsi dengan tingkat produksi tinggi sampai rendah. Provinsi dengan intensifikasi pertanian tinggi dan kontribusi besar terhadap produksi tergabung dalam klaster utama, sedangkan wilayah dengan keterbatasan sumber daya dan produksi rendah membentuk klaster tersendiri. Beberapa klaster lainnya mencerminkan karakteristik produksi sedang sampai tinggi dengan potensi pengembangan yang bervariasi. Temuan ini mencerminkan adanya keragaman kondisi agrikultur yang dipengaruhi oleh infrastruktur, intensifikasi, serta faktor geografis dan iklim.