Claim Missing Document
Check
Articles

Development of irtawsi: A User-Friendly R Package for IRT Analysis Susanto, Hari Purnomo; Agus Maman Abadi; Haryanto; Retnawati, Heri; Ali, Rade Muhammad; Djidu, Hasan
JP3I (Jurnal Pengukuran Psikologi dan Pendidikan Indonesia) Vol. 14 No. 1 (2025): JP3I
Publisher : FAKULTAS PSIKOLOGI UIN SYARIF HIDAYATULLAH JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jp3i.v14i1.32091

Abstract

The complexity of the IRT analysis makes it difficult to perform manually, therefore requiring easy-to-use software. While many software options exist for IRT analysis, the high cost of paid software can make it inaccessible for many students and lecturers in Indonesia. While the mirt package provides a complete, free option for IRT analysis, proficiency in the R programming language is required. This study aims to develop an R package for IRT analysis, equipped with a user-friendly interface based on the mirt package, designed to be easy to use for beginners in IRT analysis. The System Development Life Cycle (SDLC) model is used for development and includes five stages: Planning, Analysis, Design, Implementation, and System. The resulting package is named irtawsi and includes functionality comparable to paid software. This package can calibrate both test and non-test instruments using various IRT models, such as the Rasch, 2PL, 3PL, 4PL, GRM, PCM, and GPCM models. The irtawsi package functionality includes: (1) an easy-to-use user interface, (2) automatic interpretation of analysis results, (3) a guide for IRT analysis, (4) recommendations when assumptions are not met, (5) an HTML report format for analysis results,(6) support for two languages (Indonesian and English), (7) it is free, and (8) can be installed on Windows, macOS, and Linux operating systems. The results of this development contribute to the calibration process, making it easier for practitioners and researchers to calibrate the instruments being developed, especially for beginners who are learning IRT.
The Influence of the STEM Approach on High School Students' Mathematical Problem Solving Ability in Trigonometry Zulfa Lailaturrosidah; Agus Maman Abadi
International Journal of Mathematics and Science Education Vol. 2 No. 4 (2025): November : International Journal of Mathematics and Science Education
Publisher : Asosiasi Riset Ilmu Matematika dan Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/ijmse.v2i4.244

Abstract

This study aims to analyze the effectiveness of the STEM approach and the scientific approach in learning Trigonometry in terms of students’ mathematical problem-solving ability and self-efficacy. The research employed a quasi-experimental method with a nonequivalent comparison group design. The study population consisted of all Grade X MIPA students at MA Al-Ma’had An-Nur in the 2023/2024 academic year, with the sample taken from classes X MIPA 1 and X MIPA 2. Data collection instruments included pre-test and post-test assessments of mathematical problem-solving ability and a student self-efficacy questionnaire. Effectiveness criteria were based on post-test averages exceeding 75 for problem-solving ability and self-efficacy scores above 72, as well as improvements from pre-test results. Data were analyzed using the t-test at a 5% significance level to determine learning effectiveness in both groups. Differences in students’ initial conditions and treatment effects were examined using Hotelling’s T² and the N-Gain score test. An independent-sample t-test of N-Gain was used to compare the superiority between the two approaches. The results indicated that both the STEM and scientific approaches were effective in improving students’ mathematical problem-solving ability and self-efficacy. The STEM approach significantly influenced both variables and was superior in enhancing problem-solving ability, although not superior in improving students’ self-efficacy.
Prediksi Rate of Penetration pada Pengeboran Minyak Bumi dengan Elman Recurrent Neural Network AIZIYAH, ELSA; LUKMANA, ALLEN HARYANTO; ABADI, AGUS MAMAN
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 10, No 2 (2025): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v10i2.145-161

Abstract

ABSTRAKPenelitian ini bertujuan memprediksi laju penetrasi (ROP) guna mempercepat waktu pengeboran dan menekan biaya operasional. Metode yang digunakan adalah Elman Recurrent Neural Network (ERNN) dengan algoritma backpropagation, yang dipilih karena kemampuannya dalam mengenali pola data sekuensial pada data pengeboran. Data yang digunakan 2613 data ASCII Mudlogging minyak bumi dari PT Geotama Jogja dengan 5 variabel input, yaitu Kedalaman Vertikal Sejati atau TVD (m), Beban Mata Bor atau WOB (klbs), Kepadatan Sirkulasi Ekuivalen atau ECD (SG), Mud Weight in atau MWI (SG), dan Total Kecepatan Rotasi Pahat atau TRPM. Sedangkan variabel outputnya yaitu laju penetrasi atau ROP (m/hr). Data dihaluskan menggunakan Savitzky-Golay filter dan dibagi data training dan data testing yang sebesar 90% dan 10%. Model ERNN terbaik yang diperoleh yaitu 5 variabel input, 17 neuron tersembunyi, dan 1 variabel output. Nilai MAPE data training sebesar 16.18%, dengan akurasi 83.82%. Sedangkan nilai MAPE data testing sebesar 15.48%, sehingga akurasinya 84.52%.  Kata kunci: Elman Recurrent Neural Network, laju penetrasi, prediksi, minyak bumi, MAPE ABSTRACTThis study aims to predict the rate of penetration (ROP) to speed up drilling time and reduce operational costs. The method used is the Elman Recurrent Neural Network (ERNN) with the backpropagation algorithm, which was chosen because of its ability to recognize sequential data patterns in drilling data. The data used are 2613 ASCII Mudlogging data from PT Geotama Jogja with 5 input variables, namely True Vertical Depth or TVD (m), Drill Bit Load or WOB (klbs), Equivalent Circulation Density or ECD (SG), Mud Weight in or MWI (SG), and Total Tool Rotation Speed or TRPM. While the output variable is the rate of penetration or ROP (m/hr). The data is smoothed using the Savitzky-Golay filter and divided into training data and testing data of 90% and 10%. The best ERNN model obtained is 5 input variables, 17 hidden neurons, and 1 output variable. The MAPE value of the training data is 16.18%, so the accuracy is 83.82%. Meanwhile, the MAPE value for the testing data was 15.48%, resulting in an accuracy of 84.52%.  Keywords: Elman Recurrent Neural Network, penetration rate, prediction, petroleum, MAPE
The Development of Interactive Learning Media Based on Discovery Learning Oriented to Students’ Concept Understanding and Mathematical Disposition Tiara Saharani; Agus Maman Abadi
AL-ISHLAH: Jurnal Pendidikan Vol 16, No 4 (2024): AL-ISHLAH: JURNAL PENDIDIKAN
Publisher : STAI Hubbulwathan Duri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35445/alishlah.v16i4.5681

Abstract

Interactive learning media that enhance active student participation are essential for optimizing mathematics learning and developing mathematical competencies. This research focused on designing interactive media based on discovery learning to improve students' conceptual understanding and mathematical disposition, ensuring their validity, practicality, and effectiveness. The study utilized the ADDIE development model, encompassing Analysis, Design, Development, Implementation, and Evaluation phases. The research involved 35 students from class XI SMA Negeri 4 Yogyakarta and assessed the media's validity, implementation practicality, and learning effectiveness. The interactive media were developed following discovery learning principles and made accessible via laptops and smartphones. Validation confirmed their effectiveness, achieving a 92.3% implementation rate. Wilcoxon and proportion tests revealed significant improvements in students' conceptual understanding and mathematical disposition. The average concept understanding test score exceeded the KKTP threshold (75), while the mathematical disposition questionnaire average surpassed the high criteria minimum (102). Furthermore, 88.5% of students reached the KKTP (75) threshold in conceptual understanding, and 94.2% met the high criteria (102) for mathematical disposition. The findings indicate that discovery learning-based interactive media significantly enhance students' conceptual understanding and disposition. The accessibility and engagement features align well with effective learning strategies for high school mathematics. Discovery learning-based interactive media are valid, practical, and effective tools for improving mathematical understanding and disposition in high school settings, supporting broader adoption in similar educational contexts.
PENGARUH LKPD BERBASIS ETNOMATEMATIKA DENGAN PENDEKATAN REALISTIC MATEMATIC ADUCATION TERHADAP KETERAMPILAN PROBLEM SOLVING, SELF EFFICACY DAN COLLABORATION Wati, Ronalia; Abadi, Agus Maman; Jailani, Jailani; Chrisdiyanto, Endar
AKSIOMA: Jurnal Program Studi Pendidikan Matematika Vol 14, No 4 (2025)
Publisher : UNIVERSITAS MUHAMMADIYAH METRO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24127/ajpm.v14i4.7589

Abstract

Pada era abad 21 peserta didik harus dapat memilki kemampuan yang mampu mengasah diri nya sehingga dapat bersaing diera globalisasi. Salah satu kemampuan yang harus d miliki siswa  adalah problem solving, self efficacy dan collaboration. Tujuan dari studi ini untuk mengetahui ada pengaruh lembar kerja peserta didik berbasis etnomatematika dengan pendekatan realistic mathematic education terhadap kemampuan problem solving, self efficacy  dan collaboration. Jenis penelitian ini adalah eksperimen quasi dengan desain penelitian menggunakan One Group Pretes-Post -Test Design. Penelitian ini dilaksanakan di kelas VIII SMP Negeri 3 Kota Bengkulu semester genap pada materi Lingkaran  dengan jumlah sampel sebanyak 34 siswa. Instrument jenis tes adalah tes kemampuan problem solving berupa pretest dan post test sedangkan instrument jenis non tes adalah angket self efficacy dan collaboration. Hasil penelitian ini adalah 1) Pembelajaran dengan menggunakan LKPD berbasis etnomatematika menunjukan adanya perbedaan yang signifikan pada kemampuan problem solving, self efficacy serta collaboration siswa sebelum dan sesudah pembelajaran, 2) Pembelajaran matematika menggunakan LKPD berbasis etnomatematika.efektif untuk meningkatkan kemampuan problem solving, self efficacy serta collaboration siswa. In the era of the 21st century, students must be able to have skills that can hone themselves so they can compete in the era of globalization. One of the abilities that students must have is problem solving, self-efficacy and collaboration. The aim of this study is to determine the influence of ethnomathematics-based student worksheets with a realistic mathematical education approach on problem solving abilities, self-efficacy and collaboration. This type of research is a quasi-experiment with a research design using One Group Pretest-Post-Test Design. This research was carried out in class VIII of SMP Negeri 3 Bengkulu City, even semester on Circle material with a sample size of 34 students. The test type instrument is a problem solving ability test in the form of a pretest and post test, while the non-test type instrument is a self-efficacy and collaboration questionnaire. The results of this research are 1) Learning using ethnomathematics-based LKPD shows that there are significant differences in students' problem solving abilities, self-efficacy and collaboration before and after learning, 2) Mathematics learning using ethnomathematics-based LKPD is effective in improving problem solving abilities and self-efficacy. as well as student collaboration.