Garuda - Garba Rujukan Digital

Prediksi Jumlah Produksi Sablon Tahun Menggunakan Algoritma Regresi Linear di Nolbas SVNR Muhammad Fadhilah; Martanto Martanto; Irfan Ali
INTERNAL (Information System Journal) Vol. 6 No. 1 (2023)
Publisher : Masoem University

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

Nolbas svnr is a business engaged in the clothing industry which refers more to t-shirt screen printing. This business carries out its activities based on customer orders received through orders from individuals, shops, and schools. With the many types of screen printing that are made, the number of orders received and executed by Nolbas Svnr increases. Screen printing production at Nolbas Svnr is always changing every year. The main objective of this research is to obtain a predictive model for the amount of screen printing production using the Linear Regression method based on the number of orders obtained each year. The results that can be obtained in research can help for the supply of raw materials, the amount of raw materials, paint and so on. This study uses the linear regression method to process sales data using attributes such as year, customer name, price of goods, price of materials and the number of orders. of 0.5601. The results of the constant values ??and regression coefficients are used to predict the amount of screen printing production in 2023 at Zerobas SVNR and the predicted value is 3391. Evaluation of the multiple linear regression model shows an MAE value of 3.7247, an MSE value of 17.8633 and an R2 score of 87% .

PENERAPAN ALGORITMA SUPPORT VECTOR MACHINE UNTUK ANALISIS SENTIMEN ULASAN PELANGGAN TOKO LIVIA CIREBON DI SHOPPE Syaeful Annas; Nana Suarna; Irfan Ali; Heliyanti Susana
Jurnal Ilmiah Informatika Komputer Vol 29, No 3 (2024)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2024.v29i3.13109

Analisis sentimen adalah proses yang bertujuan untuk memahami opini pelanggan dengan mengklasifikasikan ulasan menjadi sentimen positif, netral, atau negatif. Penelitian ini bertujuan untuk mengembangkan model analisis sentimen berbasis algoritma Support Vector Machine (SVM) terhadap ulasan pelanggan Toko Livia Cirebon di platform Shopee. Pendekatan penelitian dilakukan secara kuantitatif, dengan tahapan meliputi pengumpulan data, pra-pemrosesan teks (cleansing, normalisasi slang, tokenisasi, penghapusan stopword, dan stemming), pelabelan menggunakan Inset Lexicon, transformasi data teks menjadi vektor numerik dengan metode TF-IDF, pelatihan model SVM, serta evaluasi performa menggunakan metrik akurasi, precision, recall, dan F1-score. Model yang dikembangkan mencapai akurasi sebesar 91% dengan performa terbaik pada sentimen positif (F1-score 95%), meskipun performa pada kategori netral dan negatif masih memerlukan peningkatan. Hasil penelitian ini menunjukkan bahwa algoritma SVM efektif untuk analisis sentimen dalam e-commerce, memberikan wawasan strategis bagi pemilik usaha untuk menyusun strategi pemasaran dan meningkatkan kualitas layanan.

Optimalisasi Layanan Kesehatan di Puskesmas Melalui Pengembangan Chatbot Berbasis Web Menggunakan Flowise AI Mulyawan Mulyawan; Raditya Danar Dana; Agus Bahtiar; Irfan Ali
Jurnal Teknologi Informasi dan Multimedia Vol. 6 No. 3 (2024): November
Publisher : Sekawan Institut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35746/jtim.v6i3.617

The development of a web-based chatbot service for Puskesmas presents a potential solution to improve the accessibility and efficiency of healthcare services. This research uses Flowise AI, a chatbot development platform that leverages machine learning technology to support dynamic information processing and provide accurate and relevant responses to users. Flowise AI is integrated with Langchain Retriever to further enhance dynamic information processing, ensuring accurate and relevant responses to users. Using the Rapid Application Development (RAD) methodology, the chatbot development follows a fast-paced cycle, enabling early prototyping and continuous user feedback. The chatbot is tested using Black Box Testing to verify functionality and System Usability Scale (SUS) to evaluate usability. The test results show that the chatbot is able to provide accurate responses to patient queries, especially on relevant health topics, with an SUS score of 75, which falls within the "good" category. This score reflects that the chatbot is easy to use and acceptable to users. This technology allows the chatbot to provide more accurate, relevant, and contextual responses to patient inquiries, while dynamically accessing information from various sources, thereby improving the efficiency and effectiveness of healthcare services.

ANALISIS POLA KETERKAITAN PRODUK TOKO SEMBAKO IBU IYU DENGAN ALGORITMA FP-GROWTH Suripno; Nining Rahaninsih; Irfan Ali; Martanto; Odi Nurdiawan
INFOTECH journal Vol. 11 No. 2 (2025)
Publisher : Universitas Majalengka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31949/infotech.v11i2.16632

Toko Sembako Ibu Iyu merupakan toko ritel tradisional yang menghasilkan data transaksi dalam jumlah besar setiap hari, sehingga diperlukan teknik pengolahan data yang mampu mengekstraksi informasi bernilai guna mendukung pengambilan keputusan. Penelitian ini menerapkan metode data mining menggunakan algoritma association rule mining, khususnya FP-Growth, untuk mengidentifikasi pola keterkaitan produk dan memahami kecenderungan pembelian konsumen. Data yang digunakan mencakup transaksi periode Januari hingga Juni 2024 yang berisi kode transaksi, tanggal, serta daftar produk yang dibeli. Tahapan penelitian meliputi seleksi data, pembersihan duplikasi, standarisasi penamaan, dan transformasi ke format basket transaction sebelum dianalisis menggunakan FP-Growth dengan minimum support 0,01 dan minimum confidence 0,6. Hasil penelitian menghasilkan 11 aturan asosiasi, dengan aturan terbaik menunjukkan bahwa konsumen yang membeli Marlboro Kretek cenderung membeli Cheetos BBQ/Jagung Bakar, dengan nilai support 1,2% dan confidence 95,7%. Temuan ini dapat dimanfaatkan untuk strategi penataan produk, promosi bundling, dan optimalisasi manajemen persediaan sehingga mendukung peningkatan efisiensi operasional toko ritel tradisional.

Penguatan Kompetensi Lulusan SMK Kota Cirebon Melalui Pelatihan Junior Network Administrator Irfan Ali; Kaslani; Sri Ayuningsih; Firda Pardiana
AMMA : Jurnal Pengabdian Masyarakat Vol. 3 No. 3 : April (2024): AMMA : Jurnal Pengabdian Masyarakat
Publisher : CV. Multi Kreasi Media

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

In today's increasingly advanced digital era, the need for skilled personnel in network administration is growing. This Community Partnership Program aims to provide junior network administrator training for graduates of Vocational High Schools (SMK) in Cirebon City. This training is designed to equip participants with essential basic knowledge and skills in managing and maintaining computer network infrastructure. The material presented includes basic network concepts, network device configuration, fundamental network security principles, and common troubleshooting techniques. It is hoped that this program can enhance the competence of SMK graduates, making them more prepared to enter the workforce in the field of information technology.

PKM: Kewirausahaan Digital Untuk Karang Taruna Desa Kedawung Fatihanursari Dikananda; Irfan Ali; Nizar Fazari Hidayat; Rheznandya Fahreza
AMMA : Jurnal Pengabdian Masyarakat Vol. 2 No. 3 (2023): AMMA : Jurnal Pengabdian Masyarakat
Publisher : CV. Multi Kreasi Media

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

The The rapid development of digital technology has opened new opportunities in the entrepreneurial field, especially among the youth. This study, titled “Digital Entrepreneurship for the Karang Taruna of Desa Kedawung,” is designed to identify existing digital potentials and to develop an innovative digital entrepreneurship model aimed at empowering Karang Taruna members by generating job opportunities and enhancing the welfare of the local community. The study employs a mixed-method approach by integrating both qualitative and quantitative methods to analyze the barriers, potentials, and optimal strategies in harnessing digital technology as an economic empowerment tool. The research methodology includes field surveys, in-depth interviews with business practitioners and community leaders, and a comprehensive literature review from various relevant sources. The findings indicate that the digital divide and insufficient training are the primary obstacles to effective digital entrepreneurship implementation. In response, an intensive mentoring program combined with digital literacy training emerges as an effective solution to overcome these challenges. This program not only improves technical skills related to digital platforms but also enhances managerial competencies and entrepreneurial creativity. Furthermore, strategic partnerships with industry players and local academics are expected to foster a sustainable business ecosystem. The implications of this research are significant, as it provides a replicable model for digital entrepreneurship development that can be adapted to similar rural contexts. Active involvement from both governmental and private sectors is crucial to support the program’s sustainability through funding, infrastructure development, and market access. Consequently, this study contributes not only to local economic development but also to reducing youth unemployment, raising community welfare, and accelerating digital transformation in rural areas.

Pelatihan Desain Grafis Menggunakan Canva Untuk Promosi Produk Lokal Irfan Ali; Fatihanursari Dikananda; Ridho Nugraha; Sri Ayuningsih
AMMA : Jurnal Pengabdian Masyarakat Vol. 2 No. 3 (2023): AMMA : Jurnal Pengabdian Masyarakat
Publisher : CV. Multi Kreasi Media

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

The advancement of digital technology provides significant opportunities for micro, small, and medium enterprises (MSMEs) to enhance the competitiveness of local products through engaging visual promotions. This study aims to evaluate the effectiveness of graphic design training using the Canva platform to support the promotion of local products by rural communities. The training program was conducted as part of a community service initiative focusing on improving digital literacy and design skills, especially among housewives and youth from local organizations. The program utilized a participatory approach with stages including observation, training, mentoring, and evaluation. Initial observations indicated that most participants lacked graphic design skills but showed high enthusiasm for learning. The training materials covered the basics of visual design, the use of graphic elements, and hands-on practice in creating posters, product catalogs, and social media content using Canva. Evaluation results showed significant improvement in both technical abilities and creative output among participants. Many were able to produce promotional content suitable for online publication. These findings suggest that accessible online design platforms such as Canva can effectively enhance community capacity in local product promotion. This initiative contributes to the empowerment of the village creative economy and strengthens local product identity through professional and appealing visualization. For sustainability, collaboration with related institutions and the development of local design communities are highly recommended.

Analisa Penggunaan Metode Lexicon Based Dan Algoritma Naive Bayes Pada Sentimen Ulasan Aplikasi Duolingo Muhammad Abib Allesdio; Ade Irma Purnamasari; Irfan Ali; Nana Suarna; Agus Bahtiar
Jurnal Sistem Informasi dan Teknologi Vol 6 No 2 (2026): Jurnal Sistem Informasi dan Teknologi (SINTEK)
Publisher : LPPM STMIK KUWERA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56995/sintek.v6i2.261

Peningkatan jumlah ulasan pengguna pada aplikasi mobile membuka peluang untuk memahami persepsi dan pengalaman pengguna melalui analisis sentimen. Penelitian ini bertujuan untuk menganalisis sentimen ulasan pengguna aplikasi Duolingo yang diambil dari Google Play Store menggunakan dua pendekatan, yaitu metode lexicon-based dan algoritma Naive Bayes berbasis Python. Metode lexicon-based digunakan untuk memberikan skor polaritas berdasarkan leksikon sentimen, sedangkan Naïve Bayes diterapkan sebagai model klasifikasi dengan dukungan fitur TF-IDF. Proses penelitian meliputi tahapan pengumpulan data, preprocessing teks (cleaning, case folding, tokenisasi, stopword removal, dan stemming), pembobotan sentimen, pelatihan model, serta evaluasi performa menggunakan accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa metode lexicon-based mampu memberikan gambaran umum polaritas ulasan, namun performanya sangat dipengaruhi oleh kelengkapan leksikon dan variasi bahasa informal pengguna. Sementara itu, algoritma Naive Bayes menunjukkan performa yang lebih stabil dan akurasi lebih tinggi dalam mengklasifikasikan sentimen dibandingkan pendekatan leksikon. Perbandingan kedua metode memperlihatkan bahwa Naive Bayes lebih efektif dalam menangani data teks pendek, tidak terstruktur, serta mengakomodasi variasi kata dan ejaan. Temuan penelitian ini memberikan pemahaman yang lebih dalam mengenai persepsi pengguna terhadap Duolingo serta menjadi referensi metodologis bagi penelitian sentiment analysis selanjutnya, khususnya yang melibatkan kombinasi metode leksikon dan klasifikasi probabilistik.

ADAPTIVE CLASS WEIGHTING DAN AUGMENTATION UNTUK KLASIFIKASI BATIK KERATON Witriyani Witriyani; Dian Ade Kurnia; Yudhistira Arie Wijaya; Mulyawan Mulyawan; Irfan Ali
Informatika: Jurnal Teknik Informatika dan Multimedia Vol. 6 No. 1 (2026): MEI : JURNAL INFORMATIKA DAN MULTIMEDIA
Publisher : LPPM Politeknik Pratama Kendal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/informatika.v6i1.1516

This study aims to improve the performance of Batik Keraton motif classification on an imbalanced dataset through the integration of adaptive class weighting and data augmentation within a transfer learning framework. The dataset consists of 1,799 images across four classes (Kawung, Mega Mendung, Parang, Truntum), preprocessed to 224×224 pixels and split stratifiedly into training, validation, and test sets (80/10/10). Three transfer learning architectures—ResNet50V2, VGG16, and EfficientNetB0—were evaluated with adaptive class weighting and geometric augmentation to enhance minority-class representation. The results indicate that ResNet50V2 with pretrained weights achieved the best performance, reaching a test accuracy of 92.78%, macro precision of 93.13%, macro recall of 92.79%, and a macro F1-score of 92.83%. Adaptive class weighting improved sensitivity toward minority classes, while augmentation contributed to model stability and generalization. These findings demonstrate that combining adaptive weighting and augmentation effectively enhances Batik Keraton motif classification under imbalanced data conditions.

Analisa Penggunaan Metode Lexicon Based Dan Algoritma Naive Bayes Pada Sentimen Ulasan Aplikasi Duolingo Muhammad Abib Allesdio; Ade Irma Purnamasari; Irfan Ali; Nana Suarna; Agus Bahtiar
Jurnal Sistem Informasi dan Teknologi Vol 6 No 2 (2026): Jurnal Sistem Informasi dan Teknologi (SINTEK)
Publisher : LPPM STMIK KUWERA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56995/sintek.v6i2.261

Peningkatan jumlah ulasan pengguna pada aplikasi mobile membuka peluang untuk memahami persepsi dan pengalaman pengguna melalui analisis sentimen. Penelitian ini bertujuan untuk menganalisis sentimen ulasan pengguna aplikasi Duolingo yang diambil dari Google Play Store menggunakan dua pendekatan, yaitu metode lexicon-based dan algoritma Naive Bayes berbasis Python. Metode lexicon-based digunakan untuk memberikan skor polaritas berdasarkan leksikon sentimen, sedangkan Naïve Bayes diterapkan sebagai model klasifikasi dengan dukungan fitur TF-IDF. Proses penelitian meliputi tahapan pengumpulan data, preprocessing teks (cleaning, case folding, tokenisasi, stopword removal, dan stemming), pembobotan sentimen, pelatihan model, serta evaluasi performa menggunakan accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa metode lexicon-based mampu memberikan gambaran umum polaritas ulasan, namun performanya sangat dipengaruhi oleh kelengkapan leksikon dan variasi bahasa informal pengguna. Sementara itu, algoritma Naive Bayes menunjukkan performa yang lebih stabil dan akurasi lebih tinggi dalam mengklasifikasikan sentimen dibandingkan pendekatan leksikon. Perbandingan kedua metode memperlihatkan bahwa Naive Bayes lebih efektif dalam menangani data teks pendek, tidak terstruktur, serta mengakomodasi variasi kata dan ejaan. Temuan penelitian ini memberikan pemahaman yang lebih dalam mengenai persepsi pengguna terhadap Duolingo serta menjadi referensi metodologis bagi penelitian sentiment analysis selanjutnya, khususnya yang melibatkan kombinasi metode leksikon dan klasifikasi probabilistik.

Title

Found 32 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 32 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 32 Documents
Search