Article Per Year (5 Year)
p-Index From 2020 - 2025
0.92
P-Index
This Author published in this journals
All Journal JTAM (Jurnal Teori dan Aplikasi Matematika) M A T H L I N E : Jurnal Matematika dan Pendidikan Matematika Journal Artificial: Informatika dan Sistem Informasi
Wafda, Andi
Unknown Affiliation
Computer Science & IT Education Mathematics

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
The Urgency of Developing Teaching Modules Based on Ethnomatics Learning for Numeracy Skills Fitriani, Fitriani; Baharuddin, Muhammad Rusli; Patmaniar, Patmaniar; Wafda, Andi
JTAM (Jurnal Teori dan Aplikasi Matematika) Vol 9, No 1 (2025): January
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jtam.v9i1.26846

Abstract

Numeracy is one of the essential foundational skills that students must master, yet the 2018 Programme for International Student Assessment (PISA) survey revealed that Indonesian students ranked 72nd out of 79 countries in numeracy skills, reflecting low mathematical literacy globally. This issue often stems from the presentation of mathematical material that is abstract and less relevant to everyday life contexts. This study aims to develop a teaching module based on ethnomathematics learning that integrates the local culture of Luwu to improve students' numeracy skills. This research employs the research and development (R&D) method with the 4D model, encompassing the stages of Define, Design, Develop, and Disseminate. In the Define stage, a needs analysis and identification of local cultural potential were conducted. In the Develop stage, the module was validated by experts using validation sheets to assess the relevance of the material, completeness of information, and clarity of presentation. The module's practicality was evaluated through questionnaires and observations to assess its ease of use and effectiveness in learning. The results indicate that the teaching module based on ethnomathematics learning is both valid and practical. The module achieved high validity based on expert assessments covering material relevance, completeness of information, and clarity of presentation. The module's practicality was measured through teacher and student responses, reflecting its ease of use and effectiveness in enhancing student engagement in numeracy learning. In conclusion, the teaching module based on ethnomathematics learning has proven effective in improving students' numeracy skills and successfully integrating local cultural values into learning. This study contributes to the development of relevant, meaningful, and contextual teaching materials in mathematics education.
Artificial Intelligence dalam Prediksi dan Manajemen Bencana: Tinjauan Literatur Komprehensif Wafda, Andi
Journal Artificial: Informatika dan Sistem Informasi Vol. 2 No. 1 (2024): April 2024
Publisher : Pustaka Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54065/artificial.542

Abstract

Peningkatan frekuensi dan intensitas bencana alam seperti banjir, gempa bumi, dan tsunami menuntut pengembangan sistem yang lebih baik untuk prediksi dan manajemen bencana. Artificial Intelligence (AI) menawarkan potensi besar dalam meningkatkan akurasi dan efektivitas prediksi bencana dengan menganalisis data besar dan kompleks. Namun, penerapannya menghadapi tantangan seperti keterbatasan data dan kebutuhan sumber daya komputasi. Penelitian ini bertujuan untuk mengeksplorasi aplikasi AI dalam prediksi dan manajemen bencana dengan menilai algoritma Machine Learning (ML) dan Deep Learning (DL), serta mengidentifikasi kekuatan dan kelemahan metode yang digunakan. Penelitian ini menggunakan metode tinjauan literatur sistematis dengan beberapa langkah utama. Pencarian literatur dilakukan melalui basis data akademis seperti IEEE Xplore, ScienceDirect, dan ArXiv, dengan kata kunci terkait penerapan AI dalam manajemen bencana. Artikel yang memenuhi kriteria inklusi dan eksklusi dipilih, kemudian melalui seleksi awal berdasarkan judul dan abstrak serta tinjauan teks penuh. Data dari artikel yang relevan diekstraksi, dikategorikan, dan disintesis untuk mengidentifikasi pola dan tren. Penelitian ini menemukan bahwa penerapan AI dalam prediksi bencana alam, seperti banjir, gempa bumi, dan tsunami, telah meningkatkan akurasi dan efektivitas sistem peringatan dini. Teknik deep learning seperti LSTM dan model hibrida efektif dalam prediksi banjir. Untuk gempa bumi, model seperti ELM dan 3D CNN meningkatkan akurasi prediksi. Teknik seperti CNN dan autoencoder menunjukkan hasil menjanjikan dalam memprediksi dan merekonstruksi tsunami. Meskipun demikian, tantangan terkait keterbatasan data dan kebutuhan sumber daya komputasi masih ada, mempengaruhi penerapan praktis AI dalam sistem manajemen bencana. Penerapan AI menunjukkan kemajuan signifikan dalam prediksi bencana, namun beberapa tantangan harus diatasi untuk meningkatkan efektivitasnya. Penelitian lebih lanjut dianjurkan untuk mengeksplorasi integrasi AI dengan sistem respons bencana yang ada dan memperbaiki teknik AI untuk menangani data yang tidak lengkap dan tidak seimbang.
Integrasi Machine Learning dalam Ritel: Tinjauan Komprehensif tentang Prediksi Harga, Analisis Data Pelanggan, dan Pemanfaatan Media Sosial Wafda, Andi
Journal Artificial: Informatika dan Sistem Informasi Vol. 2 No. 2 (2024): Oktober 2024
Publisher : Pustaka Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54065/artificial.543

Abstract

Penerapan teknologi machine learning dalam industri ritel telah memberikan dampak yang signifikan dalam beberapa aspek sehingga memiliki potensi besar untuk meningkatkan efisiensi operasional, meningkatkan kepuasan pelanggan, dan mengoptimalkan strategi pemasaran di sektor ritel. Tujuan dari tinjauan literatur ini adalah untuk mengevaluasi kontribusi penerapan machine learning dalam industri ritel, dengan fokus pada aspek Prediksi dan Optimasi Harga, Analisis Data Pelanggan dan Segmentasi Pasar RFM, serta Pemanfaatan Sosial Media. Metode yang digunakan melibatkan pencarian terhadap studi-studi terbaru yang relevan dan berkualitas tinggi dalam domain tersebut, dengan mempertimbangkan kriteria kebaruan, relevansi, dan kualitas metodologi penelitian. Selain itu, metode analisis lainnya mencakup evaluasi kritis terhadap setiap pendekatan dan teknik yang digunakan dalam setiap studi, untuk memastikan bahwa hasil yang dihasilkan dapat diandalkan dan dapat diterapkan secara praktis. Hasil tinjauan menunjukkan dalam aspek Prediksi dan Optimasi Harga, teknik seperti Artificial Neural Network (ANN) dan Random Forest telah terbukti meningkatkan akurasi prediksi harga produk, memungkinkan perusahaan ritel untuk menetapkan harga yang kompetitif dan merespons pasar secara efisien. Analisis Data Pelanggan dan Segmentasi Pasar RFM menggunakan algoritma clustering seperti K-Means dan Fuzzy C-Means untuk membagi pelanggan berdasarkan pola pembelian mereka, yang mendukung pengembangan strategi retensi pelanggan yang lebih efektif dan personalisasi pengalaman pelanggan. Sementara itu, Pemanfaatan Sosial Media melalui analisis sentimen dengan metode seperti Support Vector Machine (SVM) dan Naïve Bayes memberikan wawasan mendalam mengenai persepsi konsumen terhadap produk dan merek, yang membantu perusahaan untuk mengarahkan strategi pemasaran yang lebih tepat. Kesimpulan dari tinjauan literatur ini menegaskan pentingnya terus mengembangkan dan menerapkan teknologi machine learning dalam industri ritel. Meskipun telah ada kemajuan signifikan, masih ada beberapa gap penelitian yang perlu diisi, seperti integrasi data multi-channel yang lebih holistik, pengembangan personalisasi yang lebih mendalam, serta perlunya perhatian yang lebih besar terhadap aspek keamanan dan etika dalam penggunaan data konsumen. Selain itu, penelitian mendatang juga dapat mengeksplorasi kemungkinan penggunaan teknologi baru seperti deep learning dan ensemble learning untuk meningkatkan prediksi dan analisis dalam konteks ritel yang semakin dinamis dan kompetitif.
Development Of Teaching Modules Oriented Towards Realistic Mathematics Education With Luwu Cultural Context, Integrated With The Pancasila Student Profile and High Order Thinking Skills. Baharuddin, Muhammad Rusli; Taufiq, Taufiq; Fitriani, Fitriani; Patmaniar, Patmaniar; Wafda, Andi
Mathline : Jurnal Matematika dan Pendidikan Matematika Vol. 10 No. 1 (2025): Mathline : Jurnal Matematika dan Pendidikan Matematika
Publisher : Universitas Wiralodra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31943/mathline.v10i1.774

Abstract

The development of students' potential in learning must be carried out holistically and comprehensively. However, many teachers still struggle to design teaching modules that align with the Merdeka Curriculum and learning needs. This study aims to develop a Merdeka Curriculum Teaching Module oriented towards Realistic Mathematics Education (RME) with a Luwu Cultural context, integrated with the Pancasila Student Profile. The assessment results indicate that this teaching module is effective in improving students' Higher-Order Thinking Skills (HOTS). The validity score shows an average of 77.78%, classified as valid, reflecting the quality of the module in terms of material relevance, completeness of information, and clarity of presentation. The practicality assessment of the teaching module also scored an average of 88%, indicating that the module is highly practical and easy to implement in daily learning. The practicality aspects include ease of use, learning effectiveness, and time efficiency. In the evaluation of students' HOTS abilities, the NSI category indicates that 6% of students still require special intervention, while the Mastery category shows that around 5% of students have excellent HOTS. Most students fall into the Basic and Proficient categories, indicating that the module is effective in developing students' basic and intermediate skills. The practical implications of this research are that the developed teaching module can assist teachers in effectively implementing learning based on the Merdeka Curriculum, integrating local cultural values and the principles of the Pancasila Student Profile. Moreover, the module is considered practical for daily use in the classroom, making a tangible contribution to improving the quality of education in schools.
Transfer Learning Advancements: A Comprehensive Literature Review on Text Analysis, Image Processing, and Health Data Analytics Wafda, Andi
Journal Artificial: Informatika dan Sistem Informasi Vol. 3 No. 1 (2025): April 2025
Publisher : Pustaka Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54065/artificial.544

Abstract

This literature review delves into the recent advancements in transfer learning, examining its applications and enhancements across diverse domains. Focused on the conclusions drawn from various studies, the review highlights the evolution of transfer learning in three key areas: text analysis, image processing, and health data analytics. In text analysis, innovations such as BERT, CNN-BiLSTM, AdapterFusion, and T-BERT Framework showcase the ongoing efforts to improve efficiency and adaptability in understanding complex natural language tasks. Similarly, in image processing, the review emphasizes the varied use of pre-trained models, feature extraction techniques, and diversified datasets, leading to enhanced performance in tasks like image classification, object detection, and facial recognition. Furthermore, the application of transfer learning in health data analytics, particularly with CNN models like AlexNet, ResNet, GoogLeNet, and EfficientNet, reflects significant progress in tasks such as MRI brain image classification, skin lesion analysis, brain tumor detection, and other medical image analyses. The advantages of transfer learning, including consistent performance improvement and computational efficiency through the use of pre-trained models, are discussed. However, challenges such as overfitting in specific contexts and the need for careful adaptation in medical data analytics are acknowledged. The review concludes with recommendations for future research directions, urging a focus on improving domain-specific adaptation, exploring multi-modal model integration, enhancing transfer learning for limited health datasets, and investigating its potential for multi-task applications in text, image, and health data analytics. The comprehensive insights provided in this review contribute to the understanding and advancement of transfer learning in the current landscape of artificial intelligence research.
Co-Authors Baharuddin, Muhammad Rusli Fitriani Fitriani Patmaniar, Patmaniar Taufiq Taufiq