Claim Missing Document
Check
Articles

Integrasi Tamadun Melayu dalam Kurikulum Madrasah Ibtidaiyah sebagai Upaya Penguatan Pendidikan Karakter Susiandri; Jasril; Alifiyoni Rahmat Umara; M. Muda
Journal of Practice Learning and Educational Development Vol. 6 No. 2 (2026): Journal of Practice Learning and Educational Development (JPLED)
Publisher : Global Action and Education for Society

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58737/jpled.v6i2.1059

Abstract

Character education has become a major focus in basic education, including in Madrasah Ibtidaiyah (MI), in line with the increasing moral and social challenges faced by students in the era of globalization. One relevant approach to strengthening character is the integration of local wisdom values, particularly Malay civilization, into the learning curriculum. Malay civilization contains noble values such as religiosity, politeness, mutual cooperation, responsibility, and respect for customs and the social environment. This study aims to describe the integration of Malay civilization into the Madrasah Ibtidaiyah curriculum as an effort to strengthen students' character education. The research used a qualitative approach with a case study design. Data collection techniques included learning observation, interviews with teachers and madrasah principals, and documentation of learning tools and school activities. Data analysis was carried out through data reduction, data presentation, and conclusion drawing. The results show that the integration of Malay civilization values into the MI curriculum can be done through the development of teaching materials, contextual learning strategies, school cultural habits, and teacher role models. This integration has been proven to contribute to strengthening students' religious character, discipline, responsibility, and social awareness. Thus, Malay civilization can be an effective cultural foundation in supporting character education at Madrasah Ibtidaiyah.
Sistem Tanya-Jawab Berbasis Chatbot Telegram Tentang Fiqih Kontemporer Menggunakan Langchain Dan LLM Muhammad Mulky Mar'arif; Nazruddin Safaat Harahap; Jasril Jasril; Muhammad Affandes
TEKNIKA Vol. 19 No. 2 (2025): TEKNIKA
Publisher : Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.15437200

Abstract

Informasi mengenai fiqih kontemporer sangat susah didapatkan, terkhusus berasal dari ustadz Syekh Al-Qardhawi. Perlunya sebuah layanan informasi yang bisa memberikan jawaban dari pertanyaan seputar fiqih kontemporer, salah satunya yaitu memanfaatkan teknologi saat ini seperti chatbot yang ada pada telegram. Dengan memanfaatkan chatbot pada telegram dapat menghasilkan sebuah sistem tanya-jawab mengenai fiqih kontemporer. Jadi, penelitian ini bertujuan untuk menerapkan sistem tanya-jawab berbasis chatbot Telegram mengenai fiqih kontemporer. Penelitian ini juga memanfaatkan metode langchain dan large language model (LLM) agar dapat menciptakan sistem tanya-jawab yang optimal. Penelitian ini berhasil menunjukkan keefektifan nya dalam memberikan jawaban mengenai fiqih kontemporer yang mana hasil pengujian User Acceptance Test (UAT) dan Black Box Testing menunjukkan bahwa sistem ini dapat memberikan informasi yang akurat dan juga berfungsi sebagaimana mestinya sebagai sistem tanya-jawab tentang fiqih kontemporer.
Evaluation of Information Gain Feature Selection on Support Vector Machines Performance in Craniometric Sex Classification Sonya Aulia Febriana; Iis Afrianty; Jasril Jasril; Eka Pandu Cynthia
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 2 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Oktober 2026
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v10i2.28622

Abstract

Sex classification is a fundamental stage in forensic anthropology because it provides the basis for constructing an individual's biological profile during the identification process. Although Support Vector Machine (SVM) has demonstrated high performance for craniometric sex classification, previous studies have primarily focused on classification performance using the complete feature set, with limited evaluation of the trade-off between feature reduction and predictive performance. Therefore, this study aims to evaluate the influence of Information Gain feature selection on SVM performance, identify the optimal combination of Information Gain threshold and SVM kernel configuration, and analyse the trade-off between feature reduction and classification performance. The proposed approach was evaluated using the William W. Howells Craniometric Dataset consisting of 2,524 skull samples. After removing identification attributes, 82 predictor features were used for classification. The research process included data preprocessing, label transformation, Z-score normalization, Information Gain feature selection using threshold values of 0.01, 0.05, and 0.1, followed by classification using SVM with Linear, Radial Basis Function (RBF), Polynomial, and Sigmoid kernels. Model performance was evaluated using 10-fold cross-validation based on Accuracy, Precision, Recall, and F1-score. The baseline SVM model without feature selection achieved an accuracy of 89.59% using 82 features. Experimental results show that Information Gain effectively reduced feature dimensionality while maintaining competitive classification performance. The best feature-selection result was obtained using an Information Gain threshold of 0.01, which retained 68 features. The optimal configuration used the RBF kernel with C = 1 and gamma='auto', achieving an Accuracy of 89.42%, Precision of 90.73%, Recall of 89.69%, and F1-score of 90.17%. Compared with the baseline model, the Information Gain-based model reduced the number of features by 17.07% while producing an accuracy difference of only 0.17 percentage points. These findings indicate that Information Gain primarily contributes to feature reduction and model simplification rather than improving classification accuracy. The results demonstrate that a moderate reduction in craniometric features can maintain classification performance close to the baseline model and highlight the trade-off between feature reduction and predictive performance in computer-assisted forensic sex classification.
Prediksi Remaining Useful Life Mesin Turbofan Menggunakan Metode Deep Layer Recurrent Neural Networks Kevin Maulana Risky; Fitri Insani; Jasril Jasril; Suwanto Sanjaya; Lestari Handayani
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol. 7 No. 1 (2025): Maret
Publisher : Universitas Wahid Hasyim

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In recent years, the development of prognostic and health management in engines and systems has grown rapidly, with one form of interaction being predicting the remaining useful life of aircraft turbofan engines. In this study, chose to use the Deep Learning RNN method with LSTM architecture.  And in its limitation, the C-MAPSS FD001 dataset is used as a modeling dataset in which there is complex multivariate data. The main objective in this analysis and modeling process is to obtain the remaining useful life prediction results that can be a benchmark in analyzing the Remaining Useful Life (RUL) of the turbofan engine. The test results involved many criteria and parameters that were tested. Analysis of the results shows that the model with learning rate criteria of 0.001, number of epochs of 50, hidden unit of 12, Min-max normalization method, and Adam optimizer tested can understand quite accurately the RUL data pattern and follow the movement of the predetermined RUL target. Although there is a decrease and a slight spike in the unit level of machines 81 to 84, with an error value in RMSE of 26.48, but overall the model can be considered optimal in learning the prediction pattern of the RUL target. This research shows that the RNN-LSTM model has great potential in aircraft turbofan engine prognostic applications.
Hubungan Pembiasaan Nilai Karakter Islami dan Disiplin Belajar Siswa Berdasarkan Uji Chi-Square Jasril; Mhmd Habibi
Journal of Practice Learning and Educational Development Vol. 6 No. 2 (2026): Journal of Practice Learning and Educational Development (JPLED)
Publisher : Global Action and Education for Society

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58737/jpled.v6i2.1071

Abstract

The habit of Islamic character values is one of the strategic efforts in shaping the behavior and attitudes of students, including in improving learning discipline. Islamic values such as honesty, responsibility, discipline, and obedience to rules are believed to be closely related to student learning behavior at school. This study aims to determine the relationship between the habit of Islamic character values and student learning discipline. This study used a quantitative approach with a correlational design. Data were collected through questionnaires on the instillation of Islamic character values and student learning discipline. Data analysis techniques used the Chi-Square test to determine the relationship between two categorical variables. The results showed that there was a significant relationship between the instillation of Islamic character values and student learning discipline (p < 0.05). These findings indicate that the better the habit of Islamic character values, the higher the level of student learning discipline. Therefore, the habit of Islamic character values needs to be continuously strengthened as an integral part of the educational process in schools.