cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Jumadi
Contact Email
indexsasi@apji.org
Phone
+6285885852706
Journal Mail Official
indexsasi@apji.org
Editorial Address
Jl. Waru no. 15 Rawamangun Jakarta Timur
Location
Kota adm. jakarta timur,
Dki jakarta
INDONESIA
JURNAL ILMIAH SAINS TEKNOLOGI DAN INFORMASI
Published by CV ALIMS PUBLISHING
ISSN : 29643090     EISSN : 29643104     DOI : https://doi.org/10.59024/jiti.v1i1.118
Core Subject : Science, Social,
Computer Science & IT Energy Environmental Science
JURNAL ILMIAH SAINS TEKNOLOGI DAN INFORMASI (JITI), untuk menyebarluaskan, mengembangkan dan menfasilitasi hasil penelitian inter-disiplin di bidang Teknologi Informasi dan Komunikasi, sistem komputer, informatika dan komunikasi sebagai media bagi para dosen, guru, peneliti dan para praktisi dalam bidang Teknologi Informasi dan Komunikasi, sistem komputer, informatika dan komunikasidari seluruh Indonesia, dalam melakukan pertukaran informasi tentang hasil-hasil penelitian terbaru yang telah dilakukan. Adapun ruang lingkup Jurnaladalah: 1. Software Engineering (Rekayasa Perangkat Lunak) 2. Information System (Sistem Informasi) 3. Artificial Intelligence (Kecerdasan Buatan) 4. Computer Based Learning (Pembelajaran Berbasis Komputer) 5. Computer Networking & Data Communication (Jaringan Komputer & Komunikasi Data) 6. Komunikasi Data 7. Desain Komunikasi Visual 8. Desain Multimedia . Jurnal ini terbit 1 tahun 4 kali (Januari, April, Juli dan Oktober).
Arjuna Subject : Teknik (semua kategori) - Teknologi Media
Articles 97 Documents
 6   7   8   9   10 
Graph Neural Networks for Financial Fraud Detection Endah Eka Setiawati
JURNAL ILMIAH SAINS TEKNOLOGI DAN INFORMASI Vol. 4 No. 3 (2026): Juli : Jurnal Ilmiah Sains Teknologi dan Informasi
Publisher : CV. ALIM'SPUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59024/jiti.v4i3.2312

Abstract

Financial fraud is becoming increasingly complex alongside the growth of digital financial ecosystems, causing conventional fraud detection approaches based on handcrafted rules and tabular machine learning models to face limitations in identifying coordinated fraudulent activities. This study aims to analyze the application of Graph Neural Networks (GNNs) for financial fraud detection by utilizing transaction attributes and graph structural information. A quantitative experimental approach was conducted using the publicly available Elliptic Bitcoin Transaction Dataset, where transactions were modeled as graph nodes and relationships between transactions as graph edges. The proposed method implemented a Graph Attention Network (GAT) and compared its performance with Graph Convolutional Networks (GCN), GraphSAGE, and Graph Isomorphism Networks (GIN). Data preprocessing involved feature normalization, graph construction, and supervised learning on labeled transaction data. Model evaluation was performed using Accuracy, Precision, Recall, F1-score, ROC-AUC, and PR-AUC metrics. The results show that attention-based graph learning provides superior performance in detecting fraudulent transactions by assigning adaptive importance to relevant neighboring nodes during information propagation. Furthermore, graph representation learning effectively captures interconnected fraud patterns that are difficult to identify using conventional machine learning methods. These findings highlight the potential of GNNs as an intelligent approach for improving financial fraud detection and supporting risk management systems in increasingly complex digital financial environments.
Smart Traffic Light Berbasis ESP32 dan Internet of Things menggunakan Logika Fuzzy untuk Pengendalian Kepadatan Lalu Lintas Haikal Septian Hadi Putra; Abdul Azis; Emidiana Emidiana
JURNAL ILMIAH SAINS TEKNOLOGI DAN INFORMASI Vol. 4 No. 3 (2026): Juli : Jurnal Ilmiah Sains Teknologi dan Informasi
Publisher : CV. ALIM'SPUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59024/jiti.v4i3.2315

Abstract

Traffic congestion and zebra crossing violations are common problems at road intersections due to fixed-time traffic light systems that are less adaptive to traffic conditions. This research aims to design and implement an ESP32 and Internet of Things (IoT)-based Smart Traffic Light system using the Mamdani Fuzzy Logic method to automatically regulate traffic light duration based on vehicle density. The system utilizes an inframerah sensor to detect vehicle density and an ultrasonic sensor to detect zebra crossing violations. Sensor data are processed by the ESP32 through fuzzification, inference, and defuzzification to determine the appropriate traffic light duration. The system is equipped with traffic light LEDs, a TM1637 countdown timer, a buzzer, and a Telegram Bot for real-time monitoring. Testing results showed that the inframerah sensor successfully detected vehicle density, while the ultrasonic sensor accurately detected objects at distances of 5–25 cm. The fuzzy logic system produced green light durations of 5, 20, and 30 seconds for low, medium, and high traffic densities, respectively. In addition, the Telegram Bot successfully sent real-time notifications of zebra crossing violations. The proposed system operates automatically, adaptively, and effectively to support traffic management and zebra crossing monitoring.
Implementasi Sensor VOC Digital pada Sistem Monitoring dan Pengendalian Asap Rokok dalam Ruangan Berbasis Internet of Things Muhammad Arif Hidayatullah; Abdul Azis; Perawati Perawati
JURNAL ILMIAH SAINS TEKNOLOGI DAN INFORMASI Vol. 4 No. 3 (2026): Juli : Jurnal Ilmiah Sains Teknologi dan Informasi
Publisher : CV. ALIM'SPUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59024/jiti.v4i3.2341

Abstract

Cigarette smoke is one of the sources of indoor air pollution that contains various harmful compounds, including Volatile Organic Compounds (VOC), which can reduce indoor air quality and negatively affect human health. This study aims to design and develop an indoor cigarette smoke control system based on the MiCS-5524 VOC sensor and Internet of Things (IoT) technology with monitoring through Telegram on an Android device. The proposed system uses an Arduino Uno as the main controller integrated with an ESP8266 module, MiCS-5524 VOC sensor, L298N motor driver, DC fan, activated carbon filter, buzzer, and 16×2 I2C LCD. The test results show that the MiCS-5524 sensor is capable of detecting changes in VOC concentration caused by cigarette smoke exposure, while the system automatically activates the fan and buzzer according to the detected air quality conditions. The ESP8266 module successfully transmits monitoring data to Telegram Android in real-time with an average transmission time of 2.3 seconds. Furthermore, the activated carbon filter contributes to reducing VOC levels, resulting in improved indoor air quality. The results indicate that the developed system is capable of performing automatic detection, control, and monitoring of indoor air quality.
Implementasi Sistem Pendukung Keputusan Pemilihan Produk Makanan Ringan Unggulan Kalimantan Selatan Menggunakan Metode Topsis Berbasis Web Muhammad Amin; Agus Setiawan; Fauzi Yusa Rahman
JURNAL ILMIAH SAINS TEKNOLOGI DAN INFORMASI Vol. 4 No. 3 (2026): Juli : Jurnal Ilmiah Sains Teknologi dan Informasi
Publisher : CV. ALIM'SPUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59024/jiti.v4i3.2343

Abstract

Pemilihan produk makanan ringan unggulan khas Kalimantan Selatan merupakan proses yang memerlukan evaluasi multi-kriteria untuk mengidentifikasi produk terbaik yang layak mendapat perhatian, pembinaan, dan promosi dari pemerintah daerah. Proses seleksi yang masih dilakukan secara manual dan subjektif sering menghasilkan keputusan yang tidak konsisten dan kurang transparan. Penelitian ini mengusulkan implementasi Sistem Pendukung Keputusan (SPK) menggunakan metode Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) berbasis web untuk menentukan produk makanan ringan unggulan Kalimantan Selatan. Metode TOPSIS dipilih karena kemampuannya menangani masalah Multi-Attribute Decision Making (MADM) secara efektif dengan mempertimbangkan jarak terhadap solusi ideal positif dan negatif secara bersamaan. Sistem dikembangkan menggunakan PHP 8 dan MySQL dengan fitur manajemen kriteria, sub kriteria, alternatif produk, penilaian, perhitungan TOPSIS enam langkah, serta manajemen pengguna dua level (Admin dan User). Kriteria yang digunakan meliputi daya tahan produk, ketersediaan bahan baku lokal, kapasitas produksi harian, dan biaya pengemasan. Hasil perhitungan menunjukkan Keripik Pisang Mahuli (A4) terpilih sebagai produk unggulan peringkat pertama dengan nilai preferensi tertinggi 0.7222, diikuti Amplang Ikan Kotabaru (A1) dengan nilai 0.7087. Sistem ini memberikan solusi praktis untuk otomatisasi proses pemilihan produk unggulan UMKM dengan tingkat transparansi perhitungan yang dapat dipertanggungjawabkan secara ilmiah.
Analisis Sentimen Ulasan Aplikasi Duolingo di Google Play Store Menggunakan Algoritma Bidirectional Long Short-Term Memory (Bi-LSTM) Muhammad Nasrullah; Abdul Azis; Intan Mila Hakim
JURNAL ILMIAH SAINS TEKNOLOGI DAN INFORMASI Vol. 4 No. 3 (2026): Juli : Jurnal Ilmiah Sains Teknologi dan Informasi
Publisher : CV. ALIM'SPUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59024/jiti.v4i3.2345

Abstract

Reviews posted by users on the Google Play Store provide valuable feedback that can be utilized to measure user satisfaction and assess the quality of mobile applications. However, the growing volume of reviews makes manual evaluation increasingly impractical, highlighting the need for automated sentiment analysis techniques. This research proposes the use of the Bidirectional Long Short-Term Memory (Bi-LSTM) algorithm to classify the sentiment of Indonesian-language reviews for the Duolingo application. The review dataset was obtained through web scraping from the Google Play Store and underwent several preprocessing steps, including case folding, text cleaning, word normalization, tokenization, stopword removal, and stemming. After preprocessing, the data were divided into 80% training data and 20% testing data for model development and performance evaluation. The effectiveness of the model was measured using accuracy, precision, recall, and F1-score. The experimental results yielded an accuracy of 94.05%, precision of 88.46%, recall of 92.15%, and an F1-score of 91.17%. These findings indicate that the Bi-LSTM model is capable of capturing sentiment patterns with a high level of reliability, although its ability to classify negative reviews is still influenced by the imbalance between sentiment classes. Overall, the study confirms that Bi-LSTM is a suitable deep learning approach for sentiment classification of application reviews and offers meaningful insights that can support Duolingo developers in evaluating user opinions and enhancing application quality.
Klasifikasi Keluhan Pengguna Berbasis Large Language Model untuk Layanan Digital Syarifah Akmal; Salahuddin Salahuddin; Hartanto Satyo Nugraha; Sumarsid Sumarsid
JURNAL ILMIAH SAINS TEKNOLOGI DAN INFORMASI Vol. 4 No. 3 (2026): Juli : Jurnal Ilmiah Sains Teknologi dan Informasi
Publisher : CV. ALIM'SPUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59024/jiti.v4i3.2353

Abstract

The rapid growth of digital services such as e-commerce applications, digital banking, and app-based public services has significantly increased the volume of user complaints, making manual complaint classification inefficient. This study aims to develop and evaluate a Large Language Model (LLM)-based approach for classifying user complaints on digital services using a zero-shot prompting scheme. A small sample of 60 user complaints was collected and grouped into five categories: customer service, application or technical issues, payment and transaction, delivery, and data security and privacy. The research method consists of data collection, text preprocessing, labelling, LLM-based classification, and model performance evaluation. Testing on the small sample shows that the LLM was able to classify complaints with an accuracy of 86.7%, a weighted precision of 87.2%, a weighted recall of 86.7%, and a weighted F1-score of 86.8%. Most misclassifications occurred between contextually overlapping categories, namely payment or transaction and application or technical issues. The findings indicate that LLMs have strong potential as an efficient and accurate solution to support automated user complaint handling in digital services.
Analisis Sentimen Pengguna Twitter terhadap Tren Cryptocurrency di Indonesia dengan Metode Support Vector Machine Muhammad Farhan Asshiddiq; Betha Nurina Sari; Garno Garno
JURNAL ILMIAH SAINS TEKNOLOGI DAN INFORMASI Vol. 4 No. 3 (2026): Juli : Jurnal Ilmiah Sains Teknologi dan Informasi
Publisher : CV. ALIM'SPUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59024/jiti.v4i3.2368

Abstract

The rapid growth of cryptocurrency as a digital asset has attracted increasing public attention in Indonesia, influened by the extensive adoption of the internet and social media. Among various social media platforms, Twitter (X) has become one of the primary platforms where users express opinions and engage in discussions about cryptocurrency. The information generated from these interactions can be utilized to identify public sentiment trends. This investigation intends to assess public opinion regarding cryptocurrency trends in Indonesia by applying the Support Vector Machine (SVM) algorithm. The research adopts the Knowledge Discovery in Database (KDD) methodology, which consists of data selection, preprocessing, transformation, data mining, and evaluation stages. Data were collected through a web crawling process using the Tweet Harvest application, resulting in 7,000 Indonesian-language tweets. After duplicate removal and preprocessing, 4,502 tweets were retained as the research dataset. Feature extraction was performed using the Term Frequency–Inverse Document Frequency (TF-IDF) method to convert textual data into numerical representations, while sentiment classification was conducted using a linear-kernel Support Vector Machine. Model performance was evaluated using a Confusion Matrix. The experimental results demonstrated that the proposed model achieved an accuracy of 82.35%, precision of 84%, recall of 83%, and an F1-score of 84%. These findings indicate that the combination of TF-IDF and Support Vector Machine provides effective performance for classifying public sentiment regarding cryptocurrency trends in Indonesia.

Page 10 of 10 | Total Record : 97

 6   7   8   9   10 

Filter by Year

2023 2026


Reset
Filter By Issues
All Issue Vol. 4 No. 2 (2026): Vol. 4 No. 2 (2026): April : Jurnal Ilmiah Sains Teknologi dan Informasi Vol. 4 No. 3 (2026): Juli : Jurnal Ilmiah Sains Teknologi dan Informasi Vol. 3 No. 2 (2025): April : Jurnal Ilmiah Sains Teknologi dan Informasi Vol. 3 No. 1 (2025): Januari : Jurnal Ilmiah Sains Teknologi dan Informasi Vol. 2 No. 4 (2024): Oktober : Jurnal Ilmiah Sains Teknologi dan Informasi Vol. 2 No. 3 (2024): Juli : Jurnal Ilmiah Sains Teknologi dan Informasi Vol. 2 No. 2 (2024): April : Jurnal Ilmiah Sains Teknologi dan Informasi Vol. 2 No. 1 (2024): Januari : Jurnal Ilmiah Sains Teknologi dan Informasi Vol. 1 No. 4 (2023): Oktober : Jurnal Ilmiah Sains Teknologi dan Informasi Vol. 1 No. 3 (2023): Juli : Jurnal Ilmiah Sains Teknologi dan Informasi Vol. 1 No. 2 (2023): April : Jurnal Ilmiah Sains Teknologi dan Informasi Vol. 1 No. 1 (2023): Januari : Jurnal Ilmiah Sains Teknologi dan Informasi More Issue