Claim Missing Document
Check
Articles

Found 3 Documents
Search

Kegiatan Charity Himasi Untuk Membentuk Rasa Kepedulian Mahasiswa Dengan Cara Berbagi Takjil Di Panti Asuhan Daarus Sholihin Kota Cirebon Raden Muhamad Rama Poetra Ardiningrat; Dwi Pasha Anggara Putra; Marsani Asfi
Gotong Royong Vol. 2 No. 2 (2025)
Publisher : CV. Akira Java Bulu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63935/gr.v2i2.130

Abstract

University students play a vital role as agents of change, not only by achieving academic excellence but also by contributing meaningfully to society. One such contribution is through charity activities that foster empathy and social awareness. The 2025 charity event organized by the Information Systems Student Association (HIMASI) of UCIC aimed to cultivate students’ social concern through direct interaction with children at the Daarus Sholihin Orphanage in Cirebon. The implementation method consisted of three stages: planning, execution, and evaluation. The main activities included the distribution of takjil (light meals for breaking the fast), social interaction sessions, and evaluation through group discussions. The results showed that students experienced increased empathy, teamwork skills, and social awareness. Meanwhile, the children responded positively to the attention and engagement provided. This activity not only benefited the recipients but also served as a medium for character development among students. In conclusion, this charity activity effectively fosters social concern and can be developed into a sustainable program through various other forms of social engagement.
AYUNDA: Hybrid Agentic AI dan Sistem Multi-Agen dengan LSTM untuk Prediksi Pembelian Layanan dan Optimalisasi Kebutuhan Bisnis ISP Dwi Pasha Anggara Putra; Lena Magdalena; Muhammad Hatta
Jurnal Teknologi Sistem Informasi Vol 7 No 2 (2026): Jurnal Teknologi Sistem Informasi
Publisher : Program Studi Sistem Informasi, Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jtsi.v7i2.17381

Abstract

Penyedia Layanan Internet memerlukan peramalan yang akurat dan optimalisasi bisnis yang cerdas untuk mendukung perencanaan operasional serta alokasi sumber daya. Penelitian ini mengusulkan AYUNDA, platform optimalisasi bisnis cerdas berbasis web yang mengintegrasikan dua model Long Short-Term Memory (LSTM) dengan Collaborative Multi-Agent System untuk memprediksi pembelian layanan internet dan pendapatan perusahaan sekaligus menghasilkan rekomendasi bisnis terintegrasi. Kedua model LSTM tersebut diproses oleh LLM Orchestrator berbasis OpenAI GPT-4o-mini yang mengoordinasikan empat agen khusus, yaitu Marketing Agent, Finance Agent, Network Engineer Agent, dan Technician Agent, untuk menerjemahkan hasil peramalan menjadi rekomendasi bisnis yang dapat ditindaklanjuti. Data transaksi historis PT CIO Network Solution yang diperoleh melalui observasi, wawancara, dokumentasi, dan studi literatur digunakan untuk melatih dan memvalidasi model. Hasil penelitian menunjukkan model peramalan pembelian mencapai MAE 2,94, MSE 12,49, RMSE 3,53, dan MAPE 11,92% dengan akurasi 88,08%, sementara model peramalan pendapatan menghasilkan MAE 3,94, MSE 20,52, RMSE 4,53, dan MAPE 10,65% dengan akurasi 89,35%. Kedua model LSTM menunjukkan kinerja prediktif yang baik dengan tingkat kesalahan rendah. Platform AYUNDA mengintegrasikan peramalan, penalaran multi-agen, dan interaksi bahasa alami dalam satu dashboard untuk menghasilkan rekomendasi estimasi pendapatan, perencanaan infrastruktur, penganggaran operasional, dan alokasi teknisi.
Actor-Critic Reinforcement Learning for Personalized STEM Learning Path Optimization Muhammad Hatta; Lena Magdalena; Dwi Pasha Anggara Putra; Yohanes Michael Fouk Runa; Ananda Irfansyah; Fernando Valentino
Journal of Information System and Informatics Vol 7 No 3 (2025): September
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51519/journalisi.v7i3.1270

Abstract

This study addresses the critical need for adaptive learning in non-formal education settings, particularly Community Learning Centres (PKBM) in Indonesia, where student heterogeneity and limited resources challenge conventional teaching methods. We developed a personalized learning path optimization model using Actor-Critic Reinforcement Learning (RL) to enhance STEM competency development. The novel framework integrates cognitive, affective, and personality features to dynamically adjust material difficulty based on real-time analysis of student cognitive states (quiz performance, completion rate) and affective conditions (emotional level), moving beyond static predictive approaches. Experimental results on a synthetic dataset demonstrate that the Actor-Critic agent achieves statistically significant higher rewards (-2.92 vs -3.01, p<0.05) and greater output stability compared to a random baseline. Although the absolute reward difference is modest, it reflects more consistent adaptive policy performance, despite limited effect size (Cohen's d=0.0317). Feature importance analysis confirms that quiz_score and emotion_level are the dominant factors influencing adaptive recommendations, while personality traits show negligible impact. The framework offers a viable pathway for scalable, personalized learning in resource-constrained environments. Future work should validate the model with real-world student data and refine reward functions to strengthen practical impact.