Article Per Year (5 Year)
p-Index From 2021 - 2026
2.064
P-Index
This Author published in this journals
All Journal Syntax Jurnal Informatika Jurnal Pengabdian Pada Masyarakat Jurnal Sisfokom (Sistem Informasi dan Komputer) Equilibria Pendidikan : Jurnal Ilmiah Pendidikan Ekonomi Informatika : Jurnal Informatika, Manajemen dan Komputer Jurnal Elektronika Listrik dan Teknologi Informasi Terapan Jurnal Informa: Jurnal Penelitian dan Pengabdian Masyarakat Insyst : Journal of Intelligent System and Computation
Norma Puspitasari
Politeknik Indonusa Surakarta
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Other

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 19 Documents
Search

 1   2 
Stability Evaluation of the @akhyar11/ml-v1 Library for Training Recurrent Neural Networks on Indonesian Sentiment Classification Muhammad Akhyar; Devi Putri Febriyanti; Norma Puspitasari
Intelligent System and Computation Vol 8 No 1 (2026): INSYST: Journal of Intelligent System and Computation
Publisher : Institut Sains dan Teknologi Terpadu Surabaya (d/h Sekolah Tinggi Teknik Surabaya)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52985/insyst.v8i1.498

Abstract

The Python ecosystem currently dominates machine learning development, while machine learning libraries in TypeScript remain relatively limited, particularly for deep learning and sequence modeling tasks. This study evaluates the stability of @akhyar11/ml-v1, a TypeScript-native machine learning library, in training recurrent neural network architectures for Indonesian sentiment classification. Rather than focusing solely on identifying the best-performing model, this research positions RNN, LSTM, and GRU as evaluation instruments to assess the library training reliability, consistency, and robustness. Each architecture was trained independently across 10 repeated runs for 30 epochs using the same sentiment classification dataset and experimental configuration. The evaluation focuses on training stability indicators, including accuracy consistency, macro F1-score, weighted F1-score, performance variation across runs, convergence behavior, and the occurrence of training failures such as NaN values or extreme performance drops. The results show that @akhyar11/ml-v1 can run recurrent neural network training processes functionally and relatively stable on the tested configuration. Among the evaluated architectures, LSTM demonstrated the most consistent performance, while RNN showed stable but lower predictive performance. GRU exhibited higher sensitivity across repeated runs, indicating greater variance in training outcomes. These findings suggest that @akhyar11/ml-v1 has practical potential as a non-Python machine learning library for sequence-based natural language processing experiments, although further evaluation on broader datasets, architectures, and training configurations is still required.
Peran Aljabar Boolean dalam Ilmu Komputer dan Perancangan Rangkaian Logika Norma Puspitasari; Silvi Hindun Mayrohmah
Jurnal Informa : Jurnal Penelitian dan Pengabdian Masyarakat Vol. 9 No. 2 (2023): Desember
Publisher : Politeknik Indonusa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46808/informa.v9i2.258

Abstract

Boolean algebra has made major contributions to computer science, especially in areas such as logic gate modeling, simplification of microprocessor circuits, geographic information systems, and digital circuits. Boolean algebra is used to analyze and simplify digital circuits, as well as in applications such as computer programs, geographic information systems, and digital circuits. This research is library research, namely by studying, researching and investigating and studying scientific works presented in the form of thesis books or papers that are relevant to the research topic. Some implementations of Boolean Algebra in Computer Science and Logic Circuit Design are Logic Programming and Logic Gates. Boolean algebra provides an essential theoretical foundation in computer science. Boolean algebra is essential in computer science, from the creation of logic circuits to recent advances in computing.
Pembuatan Company Profile Sistem Informasi Gajah Putih (SIGATI) Surakarta Berbasis Website Norma Puspitasari; Canggih Ajika Pamungkas; Norhisma Zulfani Anggraheni
Jurnal Informa : Jurnal Penelitian dan Pengabdian Masyarakat Vol. 9 No. 2 (2023): Desember
Publisher : Politeknik Indonusa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46808/informa.v9i2.260

Abstract

Gajah Putih is a climate village located in Karangasem Village, Laweyan, Surakarta City. This village is one of the locations of the climate village program that is considered successful because it has received a certificate as a location of the Main Category Climate Village Program from the Ministry of Environment and Forestry in 2019. However, this village has not been optimized to convey information to the outside community. The village does not yet have a medium to efficiently convey information and education to the community, especially for people outside the area, making it difficult for people to find information about programs, activities and interesting activities that are running in this village. So far, to find complete information about the programs and activities being carried out by Gajah Putih, outsiders are still required to come directly to the location of this climate village. In this research, the method used is the Waterfall method which consists of five stages, namely: Needs Analysis, System Design, Coding, Testing or Implementation, and Maintenance. With this website-based company profile, it will be beneficial for Gajah Putih Village, because it is a medium of information between Gajah Putih and the community. This company profile was built using the PHP programming language and MySQL as a data delivery medium and the web server is localhost PHP Myadmin.
Pengembangan Website Dilan di Desa Sobayan Klaten Canggih Ajika Pamungkas; Norma Puspitasari; Ryan Junior
Jurnal Informa : Jurnal Penelitian dan Pengabdian Masyarakat Vol. 9 No. 2 (2023): Desember
Publisher : Politeknik Indonusa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46808/informa.v9i2.262

Abstract

The information on most village websites in Sobayan Village, Klaten, is rarely updated. This community service aims to equip village devices with the skills to present data digitally and enhance the disseminated information. The activity is carried out in three stages: preparation, training, evaluation, and instruction. Participants are assisted for one month, and their information will be updated on the village website. 90% of the village devices that undergo training update information on the website. The development methods used include stakeholder needs identification, sustainability analysis, user-friendly interface design, and implementation of appropriate technology. Continuous evaluation is conducted during the development process to ensure the effectiveness and sustainability of the website.Research results indicate that website development in villages can be an effective tool to expand information access, enhance community participation, and strengthen social connectivity at the local level. This activity provides valuable insights into how information technology can be strategically used to improve social and economic conditions in villages. Practical implications of these findings can guide website development efforts in other villages, reinforcing the role of technology in supporting sustainable development at the local level. This activity involves active collaboration between web developers, village governments, and local community members to ensure that the website can provide maximum benefits.
Perancangan Website Desa Karanggeneng serta Mengoptimalkan Limbah Plastik Guna Budidaya Hidroponik Norma Puspitasari; Canggih Ajika Pamungkas; Widar Fernando
Jurnal Informa : Jurnal Penelitian dan Pengabdian Masyarakat Vol. 9 No. 2 (2023): Desember
Publisher : Politeknik Indonusa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46808/informa.v9i2.263

Abstract

The effect of hydroponics using used goods in growing vegetables greatly influences the surrounding environment so that it is effective and efficient so that it can reduce plastic waste in the environment. In Karangjati Village, Karanggeneng, there is a Village Park which is a project of the Boyolali city government. This project is intended for the residents of Boyolali in each village to create a village garden planted with vegetables in order to improve children's nutrition in each village in the Boyolali area. In this activity, the village residents use the garden to plant all vegetables and when they are harvested they will be harvested and distributed to all residents. However, in its management, residents only use planting techniques using soil. In Karangjati Village, they are also not yet familiar with technology that could easily introduce the village and the park in the village. And in the end the village implemented it.
Analisis Pengaruh Chat Bot Berbasis Ai Terhadap Loyalitas Dan Kepuasan Pelanggan Di E-Commerce Ahmad Haidar; Indra Oktavian; Anggi Novellia Zulva; Norma Puspitasari
Jurnal Informa : Jurnal Penelitian dan Pengabdian Masyarakat Vol. 10 No. 2 (2024): Desember
Publisher : Politeknik Indonusa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46808/informa.v10i2.277

Abstract

Penelitian ini mengkaji pengaruh chatbot berbasis Artificial Intelligence (AI) terhadap loyalitas dan kepuasan pelanggan pada platform e-commerce. Dengan pendekatan deskriptif kuantitatif berbasis data sekunder, penelitian ini menyoroti berbagai aspek penting, termasuk kecepatan respons, personalisasi konten, keamanan data, dan tantangan dalam memahami bahasa alami (NLP). Temuan utama menunjukkan bahwa chatbot Artificial Intelligence (AI) meningkatkan pengalaman pelanggan melalui respons cepat dan personalisasi layanan, yang berdampak positif pada loyalitas dan kepuasan pelanggan. Di sisi lain, keamanan data juga menjadi faktor utama yang memperkuat kepercayaan pelanggan terhadap platform e-commerce.Penelitian ini juga mengidentifikasi tantangan dalam implementasi chatbot, seperti keterbatasan dalam memahami konteks percakapan kompleks. Untuk mengatasi hal ini, pengembangan kemampuan NLP menjadi kebutuhan penting. Selain itu, integrasi media sosial meningkatkan interaksi pelanggan dengan menyediakan pengalaman yang lebih holistik di berbagai saluran komunikasi. Dengan demikian, chatbot berbasis Artificial Intelligence (AI) tidak hanya memperbaiki efisiensi layanan, tetapi juga menjadi alat strategis dalam mempertahankan pelanggan di lingkungan bisnis digital yang semakin kompetitif. Secara keseluruhan penelitian ini memberikan gambaran mengenai potensi besar chatbot berbasis Artificial Intelligence (AI) dalam mendukung loyalitas dan pertumbuhan platform e-commerce. Penelitian ini menyarankan pengembangan lebih lanjut pada teknologi chatbot Artificial Intelligence (AI) untuk mendukung keberlanjutan dalam pengalaman pelanggan di e-commerce.
Prediksi Kelulusan Mahasiswa Menggunakan Algoritma Random Forest Studi Kasus Pada Data Akademik Prizca Asty Andreana; Anggi Novellia Zulva; Silvi Hindun Myrohmah; Awal Adi Saputra; Norma Puspitasari
Jurnal Informa : Jurnal Penelitian dan Pengabdian Masyarakat Vol. 11 No. 2 (2025): Desember
Publisher : Politeknik Indonusa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46808/informa.v11i2.294

Abstract

Tingkat kelulusan tepat waktu mahasiswa tetap menjadi masalah serius di perguruan tinggi karenadapat mempengaruhi kualitas akreditasi program studi. Penelitian ini bertujuan untuk memprediksikelulusan mahasiswa menggunakan algoritma Random Forest berdasarkan data akademik, sehinggadapat mendukung program studi dalam mengidentifikasi mahasiswa berisiko dan menyususn strategipendampingan yang tepat. Data penelitian ini diperoleh dari 200 mahasiswa dengan variabel utamameliputi Indeks Prediksi Kumulatif (IPK), tingkat kehadiran, keaktifan organisasi, dan jam belajarharian. Tahapan penellitian mencakup pengumpulan data, pembersihan dara, analisis deskriptif,pemodelan menggunankan algoritma klasifikasi, serta evaluasi model dengan metrik akurasi,precision, dan recall. Hasil analisis menunjukkan bahwa IPK, kehadiran, jam belajar, dan keaktifanorganisasi memiliki pengaruh signifikan terhadap ketepatan waktu kelulusan. Mayoritas mahasiswa(78,5%) lulus tidak tepat waktu, sedangkan hanya 2% yang berhasil cumlaude. Model klasifikasiRandom Forest memberikan performa prediksi dengan akurasi 92%. Temuan ini menegaskanpentingnya peran faktor akademik dan manajemen belajar dalam mendukung mahasiswamenyelesaikan studi tepat waktu
Analisis Penggunaan Media Sosial Populer Berbasis Probabilitas Pada Generasi Milenial Dan Generasi Z Devi Putri Febriyanti; Aliya Ratna Ningrum; Chiekan Denanta Alviani; Langgeng Ristri Fauzi; Norma Puspitasari
Jurnal Informa : Jurnal Penelitian dan Pengabdian Masyarakat Vol. 11 No. 2 (2025): Desember
Publisher : Politeknik Indonusa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46808/informa.v11i2.305

Abstract

Media sosial menjadi salah satu sarana utama dalam aktivitas komunikasi, hiburan sehingga pembentukan opini publik, terutama di kalangan generasi muda. Penelitian ini bertujuan untuk menganalisis kecenderungan penggunaan media sosial populer pada Generasi Milenial dan Generasi Z dengan pendekatan probabilitas. Metode penelitian menggunakan kuantitatif deskriptif melalui penyebaran kuesioner daring yang berhasil dihimpun dari 56 responden, terdiri atas 28 Generasi Milenial dan 28 Generasi Z. Data dianilis menggunakan rumus probabilitas sederhana untuk mengetahuo peluang penggunaan platform, durasi, waktu akses, tujuan, serta persepsi akurasi informasi pada media sosial. Hasil penelitian menunjukkan bahwa Generasi Milenial cenderung terfokus pada penggunaan WhatsApp dan Tiktok, dengan durasi penggunaan rata-rata adalah 1-2 jam per hari, serta memiliki probabilitas tinggi menilai informasi media sosial sebagai akurat (96,4% pada skor ≤3). Sementara itu, Generasi Z menunjukkan pola penggunaan yang lebih beragam pada platform WhatsApp, Instagram, dan TikTok dengan durasi penggunaan lebih panjang 2-4 jam dan >4 jam per hari. Generasi Z juga lebih kritis terhadap informasi, ditunjukkan dengan probabilitas menilai informasi kurang akurat sebesar 33,3%. Dengan demikian, terdapat perbedaan signifikan dalam perilaku digital kedua generasi, yang mengimplikasikan perlunya strategi literasi digital yang berbeda sesuai karakteristik generasi.
Metode Hybrid Deep Learning untuk Deteksi Serangan Siber pada Jaringan Komputer Ahmad Haidar; Agus Suprianto; Indra Oktavian; Bayu Aji Saputra; Norma Puspitasari
Jurnal Informa : Jurnal Penelitian dan Pengabdian Masyarakat Vol. 11 No. 2 (2025): Desember
Publisher : Politeknik Indonusa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46808/informa.v11i2.306

Abstract

Ancaman siber yang berevolusi dengan teknik yang semakin kompleks menghadirkan tantangan signifikan bagi sistem deteksi intrusi (IDS) tradisional, terutama dalam mengidentifikasi serangan baru dan polanya yang berubah-ubah. Penelitian ini bertujuan untuk melakukan tinjauan komprehensif terhadap metode deteksi serangan siber menggunakan kecerdasan buatan (AI), termasuk machine learning dan deep learning. Analisis berfokus pada efektivitasnya dalam meningkatkan akurasi deteksi dan kecepatan respons terhadap serangan. Studi ini menyajikan metode dan implementasi sistem keamanan berbasis AI terbaru, serta menganalisis efektivitasnya pada berbagai skenario serangan. Hasil penelitian menunjukkan bahwa adopsi AI secara signifikan meningkatkan kemampuan deteksi serangan. Berdasarkan temuan ini, penelitian ini merumuskan rekomendasi teknis untuk pengembangan sistem deteksi serangan siber yang adaptif dan tangguh demi menghadapi ancaman di masa mendatang
Co-Authors A Anditha Sari Agus Suprianto Ahmad Haidar Aliya Ratna Ningrum Anggi Novellia Zulva Awal Adi Saputra Ayu Nur Laila Lutfi Bayu Aji Saputra Canggih Ajika Pamungkas Chiekan Denanta Alviani Devi Putri Febriyanti DWI ISKANDAR Edy Susena Eko Purwanto Farid Adi Prasetya Indra Oktavian Jahid Syaifullah Langgeng Ristri Fauzi Muh Alif Fathoni Muhammad Akhyar Norhisma Zulfani Anggraheni Prizca Asty Andreana Ryan Junior Silvi Hindun Mayrohmah Silvi Hindun Myrohmah Suranto Suranto Tri Muhhamat Aji Widar Fernando Wiwit Supriyanti