cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Arif Budiman
Contact Email
pustakateknologiai@gmail.com
Phone
+6281374373837
Journal Mail Official
pustakateknologiai@gmail.com
Editorial Address
Jl. Batu Kasek Blok E 11 Padang
Location
Kota padang,
Sumatera barat
INDONESIA
Jurnal Pustaka AI : Pusat Akses Kajian Teknologi Artificial Intelligence
Published by Pustaka Galeri Mandiri
ISSN : -     EISSN : 28094069     DOI : https://doi.org/10.55382/jurnalpustakaai
Core Subject : Science, Education, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Mathematics
Jurnal Pustaka AI adalah sebuah jurnal Double blind peer-review yang didedikasikan untuk publikasi hasil Penelitian yang berkualitas khusus bidang ilmu Teknologi Artificial Intelligence . Semua publikasi di Jurnal Pustaka AI bersifat akses terbuka yang memungkinkan artikel tersedia secara bebas online tanpa berlangganan apapun. Jurnal Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) menerima naskah artikel setiap saat yang akan diterbitkan secara berkala tiga kali setahun yaitu pada bulan April, Agustus, dan Desember.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 106 Documents
 7   8   9   10   11 
Sistem Cerdas Pemilihan Makanan Sehat Berbasis Case-Based Reasoning dan SMART untuk Edukasi Pemenuhan Gizi Masyarakat Hamidani, Syafiul; Yanto, Robi
Jurnal Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 5 No 2 (2025): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence)
Publisher : Pustaka Galeri Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55382/jurnalpustakaai.v5i2.1209

Abstract

Gizi memiliki peran penting dalam kesehatan perkembangan manusia. Kekurangan atau kelebihan gizi dapat menyebabkan berbagai masalah kesehatan seperti malnutrisi, obesitas, dan penyakit kronis. Ketidaktahuan masyarakat dalam memilih dan mengonsumsi makanan bergizi menjadi salah satu penyebab utama. Pemerintah telah membuat program makanan bergizi gratis yang bertujuan meciptakan masyarakat yang sehat. Namun banyak tantangan dalam implementasi program tersebut diantaranya keterbatasan tenaga ahli gizi, serta bagaimana memastikan makanan yang dikonsumsi sesuai dengan kebutuhan gizi. Oleh karena itu, diperlukan upaya edukasi dan kebijakan kesehatan untuk meningkatkan kesadaran masyarakat tentang pola hidup sehat. Dalam hal ini, penggunaan teknologi pada sistem pakar memungkinkan integrasi data kesehatan masyarakat dan sistem pemantauan gizi. Pengembangan system pakar pemenuhan gizi menjadi solusi inovatif yang dapat membantu menentukan rekomendasi makanan bergizi secara otomatis sesuai dengan standar gizi. Adapun tujuan dari penelitian ini adalah membangun sistem cerdas pemilihan makanan sehat menggunakan kecerdasan buatan dengan basis pengetahuan dari para ahli gizi. Selain itu, sistem cerdas ini dapat memberikan rekomendasi makanan sehat dari banyak alternative kepada masyarakat untuk pemenuhan gizi. Serta dengan sistem cerdas ini dapat membantu dalam memberikan edukasi tentang hidup sehat melalui informasi pemenuhan gizi dengan memilih makanan yang tepat.
Sistem Identifikasi Citra Huruf Aksara Minangkabau Berbasis Convolutional Neural Network Saputra, Riyan; Ramadhanu, Agung; Sovia, Rini
Jurnal Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 5 No 2 (2025): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence)
Publisher : Pustaka Galeri Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55382/jurnalpustakaai.v5i2.1214

Abstract

Pelestarian aksara daerah penting untuk menjaga warisan budaya bangsa. Aksara Minangkabau, sebagai salah satu kekayaan budaya Indonesia, masih minim penelitian dan belum memiliki sistem digitalisasi memadai. Penelitian ini merupakan tahap awal eksplorasi pengenalan aksara Minangkabau menggunakan pendekatan Convolutional Neural Network (CNN) sebagai upaya mendokumentasikan dan menguji potensi digitalisasi aksara tersebut. CNN merupakan salah satu model deep learning yang dirancang untuk memproses data grid terstruktur seperti citra. Penelitian sebelumnya menunjukan kinerja CNN sangat baik dalam pengenalan tulisan tangan. Citra aksara yang digunakan dalam penelitian ini diperoleh dari sumber museum dan tulisan tangan dari 31 sukarelawan. Dataset terdiri dari 4.650 citra karakter dari 75 kelas dengan berbagai kombinasi tanda baca pada lima huruf vokal, yang kemudian diproses melalui konversi grayscale, peningkatan kontras, segmentasi, dan augmentasi hingga menghasilkan total 8.537 citra. Model CNN yang dirancang mengklasifikasikan karakter ke dalam 75 kelas. Hasil pengujian mengindikasikan bahwa model dapat mengenali karakter dengan sangat baik. Pengujian menunjukkan akurasi 99% dalam skenario pengujian terbatas pada 500 data uji. Temuan ini memberikan landasan awal untuk digunakan dalam kajian akademis lanjutan maupun diskusi kultural yang lebih luas terkait keberadaan aksara Minangkabau.
Segmentasi Tunggakan Pelanggan Menggunakan Algoritma K-Means Cluster pada Perusahaan Air Minum Daerah Akbar, Syifa Chairunnissa Deliva; Defit, Sarjon; Hendrik, Billy
Jurnal Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 5 No 2 (2025): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence)
Publisher : Pustaka Galeri Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55382/jurnalpustakaai.v5i2.1215

Abstract

Perusahaan Air Minum Daerah (Perumdam) Tirta Anai is a Regional Elected Business Entity providing clean water services to customers, but based on the BPKP performance report, this company is categorized as an unhealthy BUMD. One of the factors causing this is due to the high arrears of customers which have an impact on the company's revenue, while efforts in the form of late fines have not been able to provide a deterrent effect to customers. Based on this, this research was carried out with the aim of segmenting customer arrears at the Tirta Anai Regional Drinking Water Company. Segmentation is carried out using the K-Means Clustering algorithm. K-Means Clustering is a data mining algorithm used in grouping data based on its similarity in characteristics. The data in this study is sourced from the database of customers who are in arrears at the Tirta Anai Regional Drinking Water Company as of May 2025 which focuses on the Household group, with as many as 20,646 customer arrears data. From this population, samples were taken using the Slovin formula with an error rate of 5% so that 392 data were analyzed. The parameters used in analyzing this study are the number of months of customer arrears and total customer arrears. Based on the K-Means Clustering method, it is proven to be able to group customers based on their payment patterns. The results are divided into C0 (Low) containing 327 data, C1 (High) containing 6 data, and C2 (Medium) containing 59 data. The contribution of this research has an impact on companies in taking strategies for handling customer service in managing existing connections.
Diagnosa Penyakit Tuberkulosis Paru Menggunakan Metode Forward Chaining dan Certainty Factor Wirdawati, Wira; Sovia, Rini; Hendrik, Billy
Jurnal Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 5 No 2 (2025): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence)
Publisher : Pustaka Galeri Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55382/jurnalpustakaai.v5i2.1217

Abstract

Tuberculosis (TB) is an infectious disease that can affect people of all ages, including children, adolescents, and the elderly, and can cause illness and death in over one million people. The disease is spread through coughs or sneezes by people with pulmonary TB, through contaminated saliva, and inhalation by healthy people with weakened immune systems. Therefore, this study aims to develop an expert system to assist in the diagnosis of pulmonary tuberculosis using the Forward Chaining and Certainty Factor methods. This process begins by identifying symptoms reported by the user and then searching for rules in the knowledge base that match those symptoms. This method allows the system to follow a logical flow of reasoning similar to the way a doctor diagnoses a disease. This study used data from 100 patients from 2023 at the Pariaman Community Health Center. Using the Forward Chaining and Certainty Factor methods, three patient data sets with three types of tuberculosis were tested. The percentage results for each type of disease were 100% positive for pulmonary tuberculosis, 0.91% negative for pulmonary tuberculosis, and 0.92% latent for pulmonary tuberculosis, with a confidence level of Very Confident. This research contributes to increasing knowledge and understanding in the field of expert systems, particularly in the application of the Forward Chaining and Certainty Factor methods for diagnosing tuberculosis.
Sistem Deteksi Kepuasan Pelanggan dengan Teknik Pengelolaan Citra Menggunakan Convolutional Neural Networks Saputra, Randy; Yuhandri; Arlis , Syafri
Jurnal Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 5 No 2 (2025): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence)
Publisher : Pustaka Galeri Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55382/jurnalpustakaai.v5i2.1219

Abstract

Advancements in computer vision and facial expression recognition provide a new, objective, and non-intrusive method for measuring customer satisfaction in real time. This study develops a customer satisfaction detection system at Rumah Diskusi ALCO Café using Convolutional Neural Networks (CNN) with a mixed-methods approach, combining quantitative and qualitative analysis. The RAF-DB dataset containing 15,339 labeled images (12,271 for training and 3,068 for testing) across seven emotion classes was processed through image acquisition, preprocessing, and ResNet50 fine-tuning. The resulting model achieved an accuracy of 80.34%, with a Precision of 83.55%, Recall of 81.78%, and F1-Score of 82.32% on the test data. Field implementation over four weeks successfully recorded and analyzed thousands of customer facial expressions in key areas such as the cashier and main seating area in real time. Results showed a customer satisfaction distribution of approximately 72% “Satisfied,” 16% “Quite Satisfied,” and 12% “Not Satisfied,” with a declining trend during peak hours in the afternoon. Cross-validation with customer surveys demonstrated a strong correlation between the system’s predictions and reported satisfaction, proving the effectiveness of this method as a real-time monitoring tool. The study contributes a practical technical and methodological framework that can be replicated in other service industries for objective and real-time customer satisfaction monitoring.
Expert System Diagnosa Anak Penderita Autism Dengan Metode Forward Chaining Menggunakan Bahasa Pemograman Java Dan Database MySQL Oktavia, Eva; Ramadini, Yane; Wahyuni, Widya
Jurnal Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 5 No 2 (2025): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence)
Publisher : Pustaka Galeri Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55382/jurnalpustakaai.v5i2.1239

Abstract

Autism Spectrum Disorder (ASD) is a developmental disorder that affects communication, social interaction, and behavior. In Indonesia, autism diagnostic services still rely entirely on experts, thus limiting service effectiveness, particularly at the Disability Services and Inclusive Education Unit (UPTD). This study aims to develop an expert system based on the forward chaining method to diagnose autism quickly, precisely, and accurately. The methods used include data collection through field observations, interviews with experts, and literature review. The system was built using the Java programming language and a MySQL database, with 46 symptoms and four types of disorders as its knowledge base. The inference process was carried out using if-then rules and forward chaining techniques to generate initial diagnoses and recommendations. The results showed that this expert system was capable of independently diagnosing based on user symptom input and producing diagnostic output with high efficiency. This system also simplifies the expert's task because it can be used as an aid, not a replacement, in the diagnostic process. In conclusion, the expert system developed can improve service effectiveness, accelerate the diagnostic process, and reduce dependence on the presence of in-person experts. This system can be an innovative solution to support technology-based inclusive services. Keywords: expert system, autism, forward chaining, diagnosis, UPTD disability services

Page 11 of 11 | Total Record : 106

 7   8   9   10   11 

Filter by Year

2021 2025


Reset
Filter By Issues
All Issue Vol 5 No 2 (2025): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 5 No 1 (2025): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 4 No 3 (2024): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 4 No 2 (2024): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 4 No 1 (2024): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 3 No 3 (2023): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 3 No 2 (2023): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 3 No 1 (2023): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 2 No 2 (2022): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) Vol 2 No 1 (2022): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence Vol 1 No 1 (2021): Pustaka AI (Pusat Akses Kajian Teknologi Artificial Intelligence) More Issue