cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Moh Shidqon
Contact Email
Jurnalstmikwiduri@gmail.com
Phone
+6281574360223
Journal Mail Official
jurnalstmikwiduri@gmail.com
Editorial Address
Jl. Palmerah Barat No.353, RT.3/RW.5, Grogol Utara, Kec. Kby. Lama, Kota Jakarta Selatan, Daerah Khusus Ibukota Jakarta 11480
Location
Kota adm. jakarta selatan,
Dki jakarta
INDONESIA
Infotech: Journal of Technology Information
Published by STMIK Widuri
ISSN : 26205181     EISSN : 24602108     DOI : https://doi.org/10.37365/it
Core Subject : Science,
Computer Science & IT
Jurnal Infotech adalah jurnal ilmiah yang berisi hasil penelitian yang ditulis oleh dosen, peneliti dan praktisi. Jurnal ini diharapkan untuk mengembangkan penelitian dan memberikan kontribusi yang berarti untuk meningkatkan sumber daya penelitian di bidang Teknologi Informasi dan Ilmu Komputer. Infotech diterbitkan oleh Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Widuri dengan akses terbuka. Setiap artikel yang diterbitkan memiliki pengidentifikasi objek digital (DOI). ISSN 2620-5181 (Online) ISSN 2460-2108 (Print)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 31 Documents
 1   2   3   4 
Search results for , issue "Vol 11, No 2 (2025): NOVEMBER" : 31 Documents clear
PENGEMBANGAN SMART DOOR LOCK BERBASIS IOT UNTUK MONITORING AKSES KARYAWAN DI PT EKASA TEKNOLOGI NUSANTARA Bagaskara, Aditya; Pradana, Afu Ichsan; Hartanti, Dwi
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.415

Abstract

Traditional physical door locks have various limitations, including the risk of loss, unauthorized duplication, and the inability to log access in real time. In a dynamic work environment such as PT Ekasa Teknologi Nusantara, this poses potential security risks to valuable company assets. A more flexible, efficient, and digitally monitored security system is therefore required. This study aims to design an Internet of Things (IoT)-based Smart Door Lock system capable of automatically recording and managing access. The method used involved observation of employee access patterns and the Agile software development approach, consisting of planning, design, development, testing, deployment, review, and launch phases. The system was developed using an ESP32 microcontroller, RFID module, and solenoid lock, all integrated with a user interface for managing access data. Testing results showed that the system can log entry activity in real time, send notifications, and provide management with flexibility in granting or revoking access rights. Thus, the system enhances company asset security, reduces reliance on physical keys, and offers an adaptive digital solution for workspace access control. The system also has potential for further development to meet organizational needs.
KLASIFIKASI JENIS KULIT WAJAH MENGGUNAKAN ALGORITMA RANDOM FOREST Irwansyah, Irwansyah; Yudhana, Anton; Fadlil, Abdul
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.423

Abstract

Skin can be considered the largest organ in the human body. Healthy skin is not only good for the body, but alsoenhances the appearance. Good skin care is essential at any age. In the first few decades of life, the skin has aconsiderable supply of elastin and collagen, but it will gradually decrease. In addition, daily lifestyle can also directlyaffect the appearance of human skin. The purpose of the research is to develop a model that classifies facial skin typesbased on physiological data using random forest algorithm and measure the results of accuracy, precision, and recall.This research uses Rapidminer tools and four facial skin types namely dry, combination, normal, and oily. The resultsof random forest research obtained accuracy results of 93.25%. dry precision 98.02%, combination precision 92.94%,normal precision 93.46%, and oily precision 88.79%. While dry recall 99%, combination recall 79%, normal recall100%, and oily recall 95%. The findings of this research can help create a skincare recommendation system that ismore suited to the needs of each individual.
ANALISIS KINERJA ALGORITMA MACHINE LEARNING DALAM MENDETEKSI ANOMALI KETINGGIAN AIR LAUT: STUDI PERBANDINGAN ONE-CLASS SVM DAN ISOLATION FOREST Alifandra, Dhafa; Pratiwi, Nunik
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.405

Abstract

This study aims to compare the performance of two machine learning algorithms for anomaly detection One-Class SVM and Isolation Forest in identifying anomalies in sea level data in Indonesia, a region with high tsunami risk. The data were obtained from an official Indonesian government source over a one-year period and underwent preprocessing, including data cleaning and standardization. The models were evaluated using statistical analysis (Mann-Whitney U test), clustering metrics (Davies-Bouldin Index and Silhouette Score), and visual inspection. The results indicate that Isolation Forest outperformed the other algorithm with a Davies-Bouldin Index of 0.8124, while One-Class SVM achieved the highest Silhouette Score at 0.4381, although its Davies-Bouldin Index was higher at 0.9163. This study contributes to the selection of effective algorithms for ocean monitoring systems as part of disaster mitigation strategies in Indonesia.
OPTIMASI SMART FARMING HYDROPONIC NFT SYSTEM PADA BUDIDAYA TANAMAN PAKCOY SHANGHAI BERBASIS INTERNET OF THINGS MENGGUNAKAN ARDUINO UNO R4 WIFI Wahyu, Toni Rahmat; Sumaedi, Ade
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.424

Abstract

This study aims to develop a Smart Farming Hydroponic system based on IoT (Internet of Things) technology using the NFT (Nutrient Film Technique) for cultivating Shanghai Pakcoy. Utilizing the Arduino UNO R4 WiFi as the main microcontroller, the research integrates TDS and pH sensors to enable real-time monitoring of AB mix nutrient levels and water acidity. All data collected by the system is processed using the Arduino Cloud IoT Remote platform, allowing for remote monitoring and automated control. The study is conducted in Kampung Buah Tilu, Desa Cisaat Padarincang, focusing on optimizing limited land use in rural areas to introduce modern agricultural technology. The system is designed to enhance cultivation efficiency by maintaining nutrient and pH parameters within optimal ranges for plant growth. Additionally, the scope of the research is limited to technical aspects of nutrient management, excluding temperature and humidity control. The findings indicate that the Smart Farming Hydroponic NFT (Nutrient Film Technique) system successfully improves cultivation efficiency, provides real-time data visualization, and ensures optimal conditions for Shanghai Pakcoy growth. This research not only offers an efficient and eco-friendly agricultural solution but also opens up opportunities for developing similar technologies to empower rural communities. Through this innovation, IoT (Internet of Things) technology can be applied to sustainable farming systems to enhance productivity and improve agricultural product quality.
SISTEM MONITORING KUALITAS AIR BERBASIS INTERNET OF THINGS DI DESA WONOSARI Pradana, Gibran Arya; Maulindar, Joni; Srirahayu, Agustina
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.417

Abstract

Di daerah-daerah yang masih menggunakan inspeksi manusia sebagai norma, kesehatan masyarakat sangat berisiko akibat air berkualitas rendah. Dengan latar belakang tersebut, tujuan penelitian ini adalah untuk mengembangkan dan meluncurkan sistem pemantauan kualitas air di Desa Wonosari yang memanfaatkan Internet of Things (IoT). Untuk lebih melindungi penduduk dari bahaya kesehatan, sistem ini dimaksudkan untuk memberikan data akurat secara real-time tentang suhu air, kekeruhan, total padatan terlarut (TDS), pH, dan karakteristik lainnya. Teknik penelitian meliputi pengumpulan persyaratan, konstruksi prototipe, evaluasi sistem, dan pengujian. Berdasarkan hasil, sensor pH, kekeruhan, suhu air, dan total padatan terlarut (TDS) masing-masing memiliki akurasi 99,22% dan 98,26%. Perangkat tersebut juga lulus uji ketahanan dengan tingkat keberhasilan 96,66% dan margin kesalahan 3,33%. Hasil ini menunjukkan bahwa metode yang diusulkan meningkatkan efektivitas pemantauan kualitas air dan dapat meningkatkan aksesibilitas air, yang pada gilirannya meningkatkan kesehatan masyarakat. Hasilnya, teknologi ini memberikan pendekatan baru terhadap pemantauan kualitas air masyarakat yang aman dan efisien.
PREDIKSI HARGA DAN RISIKO SAHAM TELKOM DAN INDOSAT MENGGUNAKAN LSTM DAN VAR DENGAN VISUALISASI Alam, Indera Nurul; Pratiwi, Nunik
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.399

Abstract

Investment in Indonesia shows a growing trend, with Telkom (TLKM) and Indosat (ISAT) being among the mostactively traded stocks with high volatility. This condition raises the need for reliable stock price prediction andinvestment risk analysis. This study aims to develop a daily stock closing price prediction model using the Long Short-Term Memory (LSTM) algorithm with a Bidirectional LSTM architecture and to conduct risk analysis based on Valueat Risk (VaR) through parametric Monte Carlo simulation. Fourteen years of historical stock data were utilized andprocessed through feature engineering techniques (return, moving average, volatility) and 30-day windowing.Baseline models with one to four layers were tested, and the best model was further optimized through hyperparametertuning using the Random Search method. The results indicate that the single-layer Bidirectional LSTM modeldemonstrated the best performance on the testing data. Evaluation shows a significant performance improvement aftertuning, with RMSE decreasing from 69 to 67, MAPE from 1.61% to 1.59%, and R-Square remaining high at 0.97 forTelkom, as well as a reduction in RMSE from 91 to 74, MAPE from 2.81% to 2.27%, and an increase in R-Squarefrom 0.76 to 0.84 for Indosat. The VaR analysis reveals that the predicted daily and 80-day risk values show onlyminor deviations from the actual values, supporting the validity
PENGEMBANGAN SISTEM DETEKS EMOSI WAJAH MENGGUNAKAN ALGORITMA MACHINE LEARNING Pebriansyah, Dendi; Suroyo, Heri
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.420

Abstract

Facial emotion detection is one of the essential technologies in human–computer interaction. This study aims to compare the performance of the Convolutional Neural Network (CNN) and the CNN–Long Short-Term Memory (CNN-LSTM) algorithms in detecting emotions using three datasets: FER2013, CK+, and AffectNet. The research process involved data collection, preprocessing, model training with transfer learning, and evaluation using accuracy, precision, recall, F1-score, and confusion matrix metrics. The results show that CNN achieved only 60% accuracy with varying precision and recall, whereas CNN-LSTM reached an accuracy of 80–87% with more stable performance. Analysis of accuracy curves, loss, log loss, and radar charts indicates that CNN-LSTM outperforms CNN in classifying emotions more evenly and consistently, although it requires longer computational time. These findings emphasize that integrating CNN and LSTM can enhance the effectiveness of facial emotion detection systems, particularly in handling complex and dynamic expressions.
ANALISIS SENTIMEN TERHADAP MINAT MASYARAKAT JAKARTA YANG MEMILIH KENDARAAN UMUM MENGGUNAKAN ALGORITMA NAÏVE BAYES Dewanto, Yogga Tolly; Wiranata, Ade Davy; Sulaeman, Mia Kamayani
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.407

Abstract

The worsening traffic congestion in Jakarta highlights the need to understand public interest in using public transportation. Social media platforms such as X serve as valuable sources of real-time public opinion data. This study aims to analyze the sentiments of Jakarta residents toward public transportation to identify the factors influencing their interest in using it. Data was collected from X and analyzed using the Naïve Bayes algorithm through the RapidMiner application. The analysis was conducted by splitting the dataset into 60% training data and 40% testing data. The results of the study show 203 positive sentiment data, 135 negative sentiment data, and 138 neutral sentiment data. Positive sentiments were mostly associated with affordability and ease of access, while negative sentiments were related to discomfort and lack of punctuality. This research is expected to serve as a reference for policymakers in improving the quality of public transportation services in Jakarta.
IMPLEMENSTASI CONVOLUTIONAL NEURAL NETWORK UNTUK DETEKSI DAN KLASIFIKASI MOTIF BATIK SOLO SECARA OTOMATIS Ardiansyah, Muhammad Irfan; Srirahay, Agustina; Permatasari, Hanifah
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.421

Abstract

Batik is a recognized intangible cultural heritage of Indonesia, featuring diverse motifs and deep-rooted philosophical meanings. Solo is one of the regions known for its distinctive batik patterns. However, manual identification remains challenging due to visual similarities between motifs. This study aims to develop an automatic classification system for identifying four Solo batik motifs Parang, Sidoasih, Sidomukti, and Truntum using a Convolutional Neural Network (CNN). The dataset includes 250 labeled digital images collected from online repositories and prior research. The data were split into training, validation, and test sets. Preprocessing steps involved resizing to 224×224 pixels, normalization, and data augmentation. The CNN architecture comprises three convolutional layers, max pooling, a flatten layer, and two dense layers. The model was trained for 20 epochs using the Adam optimizer and categorical cross-entropy loss function. Evaluation results showed that the model achieved an accuracy of 89.36% and a loss value of 0.5172. The macro and weighted f1-scores exceeded 0.88, indicating high classification performance. These results demonstrate the potential of CNNs in recognizing complex batik motifs and highlight the role of AI in preserving cultural heritage through technology.
IMPLEMENTASI CHATBOT BERBASIS ARTIFICIAL NEURAL NETWORK UNTUK MENDUKUNG EFISIENSI LAYANAN KONSULTASI DI PT LOKAKITA KREATIF INDONESIA Harist, Muhammad Abdul; Sopingi, Sopingi; Irawan, Ridwan Dwi
Infotech: Journal of Technology Information Vol 11, No 2 (2025): NOVEMBER
Publisher : ISTEK WIDURI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/jti.v11i2.449

Abstract

The rapid development of information technology has driven companies to innovate in delivering faster and more efficient services. PT Lokakita Kreatif Indonesia, a company engaged in consulting and mapping services, often receives recurring questions from clients, which were previously handled manually. To address this issue, this study aims to design and develop a Chatbot system based on Artificial Neural Networks (ANN) that can understand user intent and provide automated responses. The system was developed through several stages, including data collection, text preprocessing, ANN model training using Keras, and integration into a web application built with Flask. The dataset was compiled from frequently asked questions submitted by clients and processed into a machine-readable format. Testing results show that the Chatbot can provide accurate answers with an accuracy rate of up to 87% and a relatively fast response time. These findings indicate that the system can assist the company in delivering initial consultation services in a consistent and autonomous manner. The Chatbot not only improves work efficiency but also opens opportunities for further development through integration with other communication platforms.

Page 1 of 4 | Total Record : 31

 1   2   3   4 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 11, No 2 (2025): NOVEMBER Vol 11, No 1 (2025): JUNI Vol 10, No 2 (2024): NOVEMBER Vol 10, No 1 (2024): JUNI Vol 9, No 2 (2023): NOVEMBER Vol 9, No 1 (2023): JUNI Vol 8, No 2 (2022): NOVEMBER Vol 8, No 1 (2022): JUNI Vol 7, No 2 (2021): NOVEMBER Vol 7, No 1 (2021): JUNI Vol 6, No 2 (2020): NOVEMBER Vol 6, No 1 (2020): JUNI Vol 5, No 2 (2019): NOVEMBER Vol 5, No 1 (2019): JUNI Vol 4, No 2 (2018): NOVEMBER Vol 4, No 1 (2018): JUNI Vol 3, No 2 (2017): NOVEMBER More Issue