Article Per Year (5 Year)
p-Index From 2021 - 2026
2.57
P-Index
This Author published in this journals
All Journal International Journal of Artificial Intelligence Research Hasanuddin Economics and Business Review Jurnal INSYPRO (Information System and Processing) AkMen JURNAL ILMIAH Jurnal Inovasi Pendidikan Ekonomi Jurnal Pengabdian kepada Masyarakat Nusantara Nusantara Hasana Journal Global Abdimas: Jurnal Pengabdian Masyarakat eProceedings of Engineering Prosiding Seminar Nasional Teknologi Informasi dan Bisnis Inspiration: Jurnal Teknologi Informasi dan Komunikasi Jurnal Manajemen Informatika, Sistem Informasi dan Teknologi Komputer (JUMISTIK) Jurnal MediaTIK
Aulia Rahmawati
Institut Teknologi Dan Bisnis Kalla
Agriculture, Biological Sciences & Forestry Humanities Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Mechanical Engineering Nursing Physics Public Health Social Sciences Transportation Other

Published : 17 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 17 Documents
Search

 1   2 
PENGEMBANGAN KETERAMPILAN DIGITAL KREATIF SISWA MELALUI WORKSHOP UI/UX DAN PROTOTYPING DENGAN FIGMA DI SMA ATHIRAH KAJAOLALIDO Rezty Amalia Aras; Furqan Zakiyabarsi; Aulia Rahmawati; Hany Alexandra; Muhammad Fachrul Salam
Nusantara Hasana Journal Vol. 5 No. 8 (2026): Nusantara Hasana Journal, January 2026
Publisher : Yayasan Nusantara Hasana Berdikari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59003/nhj.v5i8.1871

Abstract

Strengthening creative digital literacy at the high school level is necessary so that students can design digital solutions relevant to user needs and possess basic UI/UX skills to build their portfolios and prepare for study and careers. This activity addressed these needs through a Figma workshop facilitated at Athirah Kajaolalido High School. The workshop used focus group discussions (FGDs) to map needs and design learning scenarios, followed by a two-day workshop. The first day consisted of design thinking and project design sessions. The second day focused on mentoring prototype creation in Figma. The activity resulted in 28 groups of 3–5 students each, producing ideas and prototypes on various themes (education, school services, productivity, the environment, and mental health). Pitching was assessed using eight indicators: problem analysis to solution, user flow, usability, visual aesthetics, design consistency, creativity, pitch structure, and engagement and delivery. The questionnaire results showed an average score of 4.46 for satisfaction with the material, usefulness of the material in helping solve problems, and ease of use of Figma, using a scale of 1–5. The Figma workshop effectively improved students' basic understanding of the digital solution design process and their ability to produce prototypes and present ideas. A follow-up program with longer practice sessions and material reinforcement is recommended to optimize prototype quality and pitching skills.
PELATIHAN DESIGN THINKING DAN PROTOTYPING UI/UX UNTUK IDE STARTUP SISWA SMA Syamsul Rijal; Aulia Rahmawati; Rezty Amalia Aras; Furqan Zakiyabarsi; Hany Alexandria; Muhammad Fachrul Salam; Yogi Hady Afrizal; Andi Jamiati Paramita; Andi Hutami Endang; Kiki Resky Ramdhani Sucipto; Widia Febriyani
Nusantara Hasana Journal Vol. 6 No. 2 (2026): Nusantara Hasana Journal, July 2026
Publisher : Yayasan Nusantara Hasana Berdikari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59003/nhj.v6i2.2294

Abstract

The development of digital technology has created a new ecosystem that requires young people, particularly Generation Z, to become not only passive digital consumers but also creators of innovative solutions through the startup ecosystem. An empathy-based Design Thinking approach is considered effective in producing human-centered solutions while shaping resilient, solution-oriented young entrepreneurial character. However, students at SMA SPIDI Maros still faced difficulties in understanding business idea validation and UI/UX prototype design. This community service program aimed to provide Design Thinking and UI/UX Prototyping training to support students' startup idea development while enhancing their digital literacy. The method employed a two-session training and workshop, consisting of a Design Thinking presentation and a UI/UX Prototyping workshop using Figma, implemented through four stages: identifying participant needs, designing materials, conducting the activity, and evaluation with follow-up. The program was held on 28 January 2026 and attended by 32 participants from grades 10 to 12. Evaluation results showed all indicators fell into the "Very Good" category, with the overall usefulness indicator scoring highest at 4.84/5 (97% agreement), while ease of using Figma scored lowest at 4.41/5 due to limited workshop time. These findings underscore the importance of continuous, multi-session mentoring programs for high school students in the future.
Analisis Komparatif Artificial Neural Network dan Random Forest dalam Estimasi Nilai Penjualan SuperStore Andi Fany Febrina Jamal Putri; Astrid Kartika Dewi; Rezty Amalia Aras; Aulia Rahmawati
Prosiding Seminar Nasional Teknologi Informasi dan Bisnis Prosiding Seminar Nasional Teknologi Informasi dan Bisnis (SENATIB) 2026
Publisher : Fakultas Ilmu Komputer Universitas Duta Bangsa Surakarta

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

Abstract

Kesalahan dalam mengestimasi nilai penjualan dapat berdampak fatal bagi keuangan perusahaan retail, mulai dari penumpukan barang di gudang (overstock) hingga hilangnya peluang penjualan akibat stok kosong (stockout). Kondisi ini menuntut ketersediaan model estimasi yang akurat, khususnya yang mampu mempertimbangkan faktor keuangan seperti harga, biaya modal, dan keuntungan secara bersamaan. Oleh karena itu, penelitian ini bertujuan untuk membandingkan performa algoritma Artificial Neural Network (ANN) dan Random Forest dalam mengestimasi nilai penjualan pada dataset SuperStore, menggunakan sembilan fitur prediktor termasuk kuantitas, harga, biaya modal, dan keuntungan. Model ANN dibangun dengan tiga lapisan tersembunyi melalui serangkaian percobaan untuk memperoleh konfigurasi optimal, sedangkan Random Forest dibangun menggunakan seratus pohon keputusan. Hasil menunjukkan ANN memperoleh RMSE $69,87 dan R² 0,9844, sedangkan Random Forest memperoleh RMSE $83,26 dan R² 0,9778, namun unggul jauh lebih baik pada metrik MAE (13,21 dibandingkan 34,63). Analisis feature importance menunjukkan biaya modal dan keuntungan memberikan kontribusi paling dominan, melampaui harga produk. Kesimpulannya, performa kedua algoritma bergantung pada karakteristik kesalahan yang ingin diminimalkan, sehingga pemilihan model perlu disesuaikan dengan kebutuhan manajemen retail.
Analisis Komparatif antara Long Short-Term Memory (LSTM) dan XGBoost dalam Estimasi Penjualan Toko Retail Mohammad Hassanal Bolqia; Nurul Faiqah; Rezty Amalia Aras; Aulia Rahmawati
Prosiding Seminar Nasional Teknologi Informasi dan Bisnis Prosiding Seminar Nasional Teknologi Informasi dan Bisnis (SENATIB) 2026
Publisher : Fakultas Ilmu Komputer Universitas Duta Bangsa Surakarta

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

Abstract

Peramalan penjualan yang akurat merupakan kemampuan penting bagi bisnis modern karena menjadi dasar perencanaan persediaan, penjadwalan staf, dan proyeksi pendapatan. Penelitian ini membandingkan dua pendekatan peramalan yang banyak digunakan, yaitu jaringan Long Short-Term Memory (LSTM) dan Extreme Gradient Boosting (XGBoost), pada dataset penjualan ritel open-source. Data penjualan harian diagregasi dari data transaksi tingkat pesanan, kemudian direkayasa menjadi fitur kalender, fitur lag, dan fitur rolling-window untuk XGBoost, serta diformat menjadi jendela sekuensial yang telah diskalakan untuk LSTM. Kedua model dilatih pada rentang waktu pelatihan yang berurutan secara kronologis dan dievaluasi pada periode pengujian menggunakan Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), dan Mean Absolute Percentage Error (MAPE). Hasil eksperimen menunjukkan bahwa LSTM memperoleh MAE (Rp7.800) dan RMSE (10.800) yang sedikit lebih rendah dibandingkan XGBoost, namun justru menghasilkan MAPE (%25.100) yang lebih tinggi. Visualisasi prediksi menunjukkan bahwa LSTM cenderung menghasilkan prediksi yang hampir konstan mendekati rata-rata penjualan, sedangkan XGBoost dengan MAE (Rp8.600), RMSE (Rp11.500) dan MAPE (%23,200) mampu mengikuti sebagian fluktuasi jangka pendek meskipun kedua model masih kesulitan menangkap lonjakan penjualan ekstrem.
Analisis Performa Algoritma Decision Tree Berbasis SMOTE untuk Klasifikasi Membership Tier Pelanggan E-Commerce Nurul Faiqah; Andi Dwi Aprilya Bastiar; Rezty Amalia Aras; Aulia Rahmawati
Prosiding Seminar Nasional Teknologi Informasi dan Bisnis Prosiding Seminar Nasional Teknologi Informasi dan Bisnis (SENATIB) 2026
Publisher : Fakultas Ilmu Komputer Universitas Duta Bangsa Surakarta

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

Abstract

Penelitian ini bertujuan untuk mengklasifikasikan membership tier menggunakan algoritma Decision Tree Classifier dengan optimasi teknik SMOTE kustom yang proporsional. Menggunakan dataset dari Kaggle yang mencakup 8.000 profil pelanggan dan 25.000 riwayat transaksi, teknik SMOTE kustom berhasil menyeimbangkan data latih dari 6.400 menjadi 8.800 sampel guna mengeliminasi bias kelas mayoritas (Free). Hasil pemodelan dengan pre-pruning (max_depth=4) menunjukkan bahwa rata-rata nilai pesanan (avg_order_value_usd) dengan ambang batas 66.232 USD menjadi akar penentu utama (root node). Evaluasi akhir melalui 5-Fold Cross Validation membuktikan skenario SMOTE kustom menghasilkan lonjakan nilai F1-Score Macro yang signifikan dibandingkan model konvensional. Model ini terbukti memiliki kemampuan generalisasi yang adil dan seimbang dalam mengenali kelas-kelas minoritas (Silver, Gold, dan Platinum), sehingga dapat dijadikan landasan strategis manajemen hubungan pelanggan (Customer Relationship Management) pada industri retail digital.
Minimal Gated Recurrent Unit with Temporal Convolution Based Acoustic Modeling on Speech Recognition System for Evaluating the Recitation of Quran Isjhar Kautsar; Dessi Puji Lestari; Aulia Rahmawati
International Journal of Artificial Intelligence Research Vol 10, No 1 (2026): June
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v10i1.1613

Abstract

The use of future context in acoustic modeling seems to give an impact on system performance such us Bidirectional Long Short-Term Memory (BLSTM). It has been used as an acoustic model on Speech Recognition System for Quran recitation and show better result than Hidden Markov Model - Gaussian mixture model (HMM-GMM) with average Word Error Rate (WER) value 4.6%. but, the architectural complexity of BLSTM make the latency during decoding process is high.  To reduce the latency, Minimal Gated Recurrent Unit with Temporal Convolution (mGRUIPTC) acoustic model was used. Text data such as transcription, lexicon, and corpus used in training are represented at phone level to handle phone level detection. The transcription is generated using modified QScript to handle reciting rules in detail. In the test, the system can reduce decode process latency by up to 11 seconds with Phone Error Rate (PER) difference of up to 1.46% compared to BLSTM. However, our model still needs to be trained with more data to detect error recitation better.
Penerapan Algoritma Minimax Pada Game Fun Math Aulia Rahmawati
Jurnal MediaTIK Volume 7 Issue 2, Mei (2024)
Publisher : Jurusan Teknik Informatika dan Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/mediatik.v7i2.3283

Abstract

Maraknya penggunaan kecerdasan buatan pada disiplin ilmu saat ini, membuat orang berlomba untuk menerapkan kecerdasan buatan pada lini kehidupan seperti kesehatan, rumah tangga, pendidikan bahkan hiburan. Salah satu hiburan yang menarik segala usia adalah game (permainan). Pemanfaatan kecerdasan buatan pada game umumnya dengan menggunakan algoritma minimax, finite state machine, a star dan fuzzy logic. Pada penelitian ini mencoba menerapkan algoritma minimax pada fitur single player game Fun Math sebagai bentuk penerapan kecerdasan buatan pada ranah permainan digital. Algoritma minimax dipilih karena algoritma tersebut cocok diterapkan pada gameplay Fun Math yang berkonsepkan zero-sum. Fitur single player game Fun Math berhasil dirancang menggunakan algoritma minimax dan komputer mampu memenangkan 25 kali sesi permainan.
Co-Authors A Mudhoffar Shaddiq Al Falah A. Nurul Suci Amaliah Afrizal, Yogi Hadi Agung Nugroho Wibowo Akbar, Andi Makkulai Al Faqih, Shofwan Andi Dwi Aprilya Bastiar Andi Fany Febrina Jamal Putri Andi Hutami Endang, Andi Hutami ANDI JAMIATI PARAMITA Aras, Rezty Amalia Araz, Rezty Amalia Astrid Kartika Dewi Darwis, Analta Dessi Puji Lestari Dwi Nugroho H., Yabes Febriyani, Widia Furqan Zakiyabarsi Gia Septiana Hany Alexandra Hany Alexandria Isjhar Kautsar Khaerunnisa Nur Fatimah Syahnur Kiki Reski Ramdhani S. Kiki Resky Ramadani Sucipto Kiki Resky Ramdhani Sucipto Mohammad Hassanal Bolqia Nugroho H, Yabes Dwi Nurul Faiqah Nurul Faiqah Nuryono, Aninditya Anggari Ramdhani Sucipto, Kiki Reski Resky Ramdhani, Kiki Rezty Amalia Aras Rezty Amalia Aras Rimakka, Al Isra Denk Siswahyudianto Siti Aisyah Sucipto, Kiki Resky Ramdhani Syamsul Rijal Syamsul Rijal Yogi Hady Afrizal