Garuda - Garba Rujukan Digital

PENERAPAN TECHNOLOGY READINESS ACCEPTANCE MODEL (TRAM) DALAM MENGUKUR KESIAPAN DAN PENERIMAAN TEKNOLOGI CASHLESS Priambodo, Wisnu; Munna, Aliyatul; Pratama, Dicky Yudha; Supriyanto, Aji
SOSCIED Vol 7 No 2 (2024): SOSCIED - November 2024
Publisher : LPPM Politeknik Saint Paul Sorong

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32531/jsoscied.v7i2.750

In the era of globalization and industrial revolution 4.0, information and communication technology (ICT) has created major changes, especially in financial transactions. This phenomenon has led to the emergence of cashless payment systems as the dominant trend, including in the education sector. Schools in Semarang, as part of their efforts to adapt to such developments, need to shift from traditional payment methods to cashless payment technologies to improve efficiency and convenience. This study aims to understand the acceptance of Cashless technology among school teachers and employees in Semarang using the Technology Readiness Acceptance Model (TRAM) approach. Through Structural Equation Modeling (SEM) analysis, the results show that insecurity plays a major role in influencing perceived ease of use. Although the insecurity factor did not have a significant effect, security also had a positive effect on users' assessment of the usability of Cashless technology.

DROUGHT PREDICTION USING LSTM MODEL WITH STANDARDIZED PRECIPITATION INDEX ON THE NORTH COAST OF CENTRAL JAVA Supriyanto, Aji; Zuliarso, Eri; Suharmanto, Eko Taufiq; Amalina, Hana; Damaryanti, Fitri
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 6 (2024): JUTIF Volume 5, Number 6, Desember 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.6.4159

Fluctuating weather can trigger hydrometeorological disasters, especially affecting farmers and fishermen on the north coast of Central Java. Weather predictions including drought are very important to anticipate drought disasters. Deep learning-based prediction models such as Long Short Term Memory (LSTM) are used in an effort to reduce the impact of drought. The purpose of this study is to prove the level of accuracy of the LSTM model and determine the drought index with the Standardized Precipitation Index (SPI). The LSTM model is used to predict drought based on the SPI, while the SPI acts as a drought index that considers precipitation (rainfall) for a period of 1, 3, and 6 months. Predictions use rainfall data obtained from online data from the Central Java BMKG UPT Indonesia for the period 2010-2023 in the Tegal City and Semarang City station areas. The results of data treatment with LSTM can effectively analyze and capture complex patterns in meteorological data to predict drought events accurately. The effectiveness of the model is shown by the relatively small MAE and RMSE results, namely MAE 0.163 - 0.352 and RMSE 0.247-0.515. The best prediction result is the 3-month SPI in the Semarang area with MAE 0.163 and RMSE 0.274. While the prediction result with the largest error is the 1-month SPI in the Tegal area. Drought modeling using LSTM has been successfully implemented for the northern coast of Central Java using the Streamlit Framework and can process and visualize the drought prediction system well.

DROUGHT PREDICTION USING LSTM MODEL WITH STANDARDIZED PRECIPITATION INDEX ON THE NORTH COAST OF CENTRAL JAVA Supriyanto, Aji; Zuliarso, Eri; Suharmanto, Eko Taufiq; Amalina, Hana; Damaryanti, Fitri
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 6 (2024): JUTIF Volume 5, Number 6, Desember 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.6.4159

Fluctuating weather can trigger hydrometeorological disasters, especially affecting farmers and fishermen on the north coast of Central Java. Weather predictions including drought are very important to anticipate drought disasters. Deep learning-based prediction models such as Long Short Term Memory (LSTM) are used in an effort to reduce the impact of drought. The purpose of this study is to prove the level of accuracy of the LSTM model and determine the drought index with the Standardized Precipitation Index (SPI). The LSTM model is used to predict drought based on the SPI, while the SPI acts as a drought index that considers precipitation (rainfall) for a period of 1, 3, and 6 months. Predictions use rainfall data obtained from online data from the Central Java BMKG UPT Indonesia for the period 2010-2023 in the Tegal City and Semarang City station areas. The results of data treatment with LSTM can effectively analyze and capture complex patterns in meteorological data to predict drought events accurately. The effectiveness of the model is shown by the relatively small MAE and RMSE results, namely MAE 0.163 - 0.352 and RMSE 0.247-0.515. The best prediction result is the 3-month SPI in the Semarang area with MAE 0.163 and RMSE 0.274. While the prediction result with the largest error is the 1-month SPI in the Tegal area. Drought modeling using LSTM has been successfully implemented for the northern coast of Central Java using the Streamlit Framework and can process and visualize the drought prediction system well.

PENERAPAN PEMBELAJARAN BERBASIS KONVENSIONAL DENGAN TEKNOLOGI INFORMASI PADA TPQ RAUDHATUL ‘ULUM MANYARAN KOTA SEMARANG Razaq, Jeffri Alfa; Supriyanto, Aji; Budiarso, Zuly; Suharmanto, Eko Taufiq; Kasprabowo, Teguh
Intimas Vol 5 No 1 (2025)
Publisher : Fakultas Teknologi Informasi dan Industri Unisbank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/intimas.v5i1.9931

One of the places for community-based Islamic Religious Education (PAI) is through the Quran Education Park (TPQ). Not all TPQs implement qualified and modern learning methods and media according to the needs of today's education to realize the goals of PAI. The purpose of this service is to realize the goals of PAI at TPQ Raudahtul 'Ulum with conventional-based learning assistance and training methods with Information and Communication Technology (ICT) and digital. Assistance is carried out by installing ICT and digital devices with TPQ teachers. Meanwhile, training is carried out by combining ICT and digital-based learning media with Reading and Writing the Quran (BTA), books and Educational Game Tools (APE) with Islamic themes. The use of a combination of learning media aims to make learning easy, complete, interesting, creative and innovative, and can be done online and students can learn through their own gadgets. As a result, TPQ teachers have become proficient in installing ICT and digital devices and are able to understand and teach combination learning.

Perbandingan Deep Learning YOLOv5 dan YOLOv8 Untuk Deteksi Penyakit Daun Tanaman Tomat siti choiriyah; aji supriyanto
JITSI : Jurnal Ilmiah Teknologi Sistem Informasi Vol 6 No 1 (2025)
Publisher : SOTVI - Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/jitsi.6.1.357

Agriculture is one of the mainstays of the country's economy, especially the horticulture sub-sector such as fruits and vegetables. Tomato plants are one of the leading commodities. However, the failure of tomato cultivation due to the many types of diseases that exist is still an obstacle and interferes with plant growth, reduces yields, and even causes tomato plant death. This study aims to detect tomato leaf diseases by comparing the performance of the two YOLOv5 and YOLOv8 models. The purpose of comparing models is to determine the level of accuracy and to conclude which version of YOLO provides a better level of accuracy in the hope of helping to determine which method is most appropriate and appropriate to needs. The results showed that both YOLOv5m and YOLOv8m models performed very well in detection. Both models showed high precision, recall, and mAP values. YOLOv8m is better able to detect all objects in the image where the precision value is superior to YOLOv5m. YOLOv8m is superior in precision with a value of 0.95%, a difference of 0.02% with YOLOv5m and mAP50:95 which is 0.92%, a difference of 0.02% with YOLOv5m which means that YOLOv8m is better at identifying objects very precisely and objects of various sizes, but YOLOv8m requires a slightly longer training time than YOLOv5m. YOLOv8m is better able to detect all objects in the image where the precision value is 0.02% superior to YOLOv5m

Online clothing Menggunakan Metode Design Thinking Dila Aprilia Lestari; Aji Supriyanto
bit-Tech Vol. 7 No. 3 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v7i3.2042

Platform e-commerce telah membuka peluang besar bagi pelaku usaha, termasuk Usaha Mikro Kecil dan Menengah (UMKM), untuk memperluas jangkauan pasar secara signifikan. Namun, banyak UMKM masih menghadapi tantangan, seperti keterbatasan pemahaman terhadap teknologi digital, desain yang kurang ramah pengguna, dan fitur yang tidak sepenuhnya responsif terhadap kebutuhan pelanggan. Penelitian ini bertujuan untuk merancang dan mengembangkan website e-commerce berbasis Design Thinking yang mengutamakan kebutuhan pengguna melalui pendekatan iteratif. Sebanyak 30 responden dari berbagai kelompok usia dan latar belakang profesi dilibatkan sebagai partisipan utama dalam proses pengumpulan data, yang dilakukan melalui wawancara dan kuesioner. Proses penelitian mengacu pada lima tahap Design Thinking: empati, definisi masalah, ideasi, pembuatan prototipe, dan pengujian. Data yang terkumpul digunakan untuk mengidentifikasi permasalahan utama, merumuskan solusi kreatif, dan mengembangkan prototipe website yang sesuai. Prototipe diuji oleh partisipan untuk mengungkap keunggulan dan kekurangan desain yang diusulkan. Hasil penelitian menunjukkan bahwa fitur seperti notifikasi pengiriman barang, keamanan transaksi, kemudahan navigasi, dan transparansi proses merupakan kebutuhan utama pengguna. Tingkat kepuasan pengguna mencapai nilai indeks 3,53 yang menunjukkan tingkat kepuasan cukup baik, namun masih terdapat ruang untuk pengembangan lebih lanjut. Penelitian ini berkontribusi pada pengembangan platform e-commerce yang lebih responsif terhadap kebutuhan pengguna, sekaligus memberikan panduan praktis bagi UMKM dalam menghadapi tantangan transformasi digital. Dengan pendekatan ini, UMKM diharapkan dapat meningkatkan daya saing dan menciptakan pengalaman belanja online yang lebih baik bagi konsumen.

Performance Comparison of Manual and Automatic Rain Gauge Using XGBoost and Random Forest Regression Indri Budiarto; Aji Supriyanto
Electronic Journal of Education, Social Economics and Technology Vol 6, No 1 (2025)
Publisher : SAINTIS Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33122/ejeset.v6i1.955

This study aims to compare the performance of automatic and manual rain gauges in the Central Highlands of Central Java using a machine learning approach based on Extreme Gradient Boosting (XGBoost) and Random Forest Regression (RFR) algorithms. Daily rainfall data were collected from five regencies Banyumas, Banjarnegara, Wonosobo, Temanggung, and Pemalang between 2021 and 2024. Preprocessing involved merging data from two types of instruments (Automatic Rain Gauge/AWS and manual ombrometer), correcting anomalies, and standardizing date-time formats. The models were developed using feature engineering techniques, including multi-lag and moving averages, and evaluated using MAE, RMSE, and R-squared (R²) metrics. The results show that the XGBoost model with automatic data achieved the best performance, with a Mean Absolute Error (MAE) of 17.3632 mm, Root Mean Squared Error (RMSE) of 27.0282 mm, and R² of 0.5050. In comparison, the Random Forest model with automatically generated data produced an MAE of 16.6307 mm, an RMSE of 28.5286 mm, and an R² of 0.4485. Models with manual data showed lower performance, with R² values below 0.30. These findings indicate that automatic measurement data are more stable and effective for building predictive rainfall models using machine learning. This supports the use of automatic instruments as the primary data source in rainfall forecasting and hydrometeorological disaster mitigation systems.

Strategic Planning of Work Training Center Information System Using TOGAF ADM and ITIL M. Norman Fither; Aji Supriyanto
Eduvest - Journal of Universal Studies Vol. 4 No. 11 (2024): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v4i11.44741

This study aims to develop an implementation model of TO-GAF and ITIL frameworks in enterprise architecture (EA) for the Technical Implementation Unit (UPTD) of the Tegal Re-gency Vocational Training Center (BLK) and determine the improvement of services provided by BLK after the develop-ment of enterprise architecture. This type of research is a case study research where data collection is done by direct observation or observation, interviews and surveys using questionnaires. The population in this study were employees and students of BLK Tegal Regency, totaling 100 people. While the sample was 15 people. TOGAF ADM is used to un-derstand the strategic planning process systematically, from problem identification to the development of measurable solutions. Analysis and design of enterprise architecture is prelimenary phase, requirement management, architecture vision, business architecture, information systems architecture and opportunities and solutions. While the ITIL approach in addition to providing practical guidance in managing BLK IT services, ITIL is also used to test the level of maturity of the system against the blueprint produced so that a tested sys-tem design is obtained. The results of the maturity level of the service operation domain system are at level 4 with a value of 3.94 and have not yet reached level 5 which means that some activities have not been fully carried out to the maximum. To achieve the expected maturity process, management must always supervise every decision making in accordance with existing procedures.

Comparative evaluation of AlexNet, SqueezeNet, VGG16, and ResNet50 for gender and hijab detection Aji Supriyanto; Theresia Dwiati Wismarini; Herny Februariyanti; Arief Jananto; Fitri Damaryanti; Hilmy Nurakmal Satria
Bulletin of Electrical Engineering and Informatics Vol 15, No 1: February 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i1.9936

This study aims to detect gender based on facial images with and without hijab features, with the expected outcome of distinguishing gender from these facial features. The method involves comparing the performance of four convolutional neural network (CNN) architectures: AlexNet, SqueezeNet, VGG16, and ResNet50. A total of 170 facial images were directly collected using smartphone cameras. The dataset consists of two classes: 68 male faces and 102 female faces, among which 78 images of females feature hijabs, while 24 do not. The validation stage with 40 images (15 males and 25 females) showed that the AlexNet architecture achieved the highest validation accuracy at 100%, followed by ResNet50 with 97.50%, VGG16 with 95%, and SqueezeNet with 92.50%. The testing stage with 40 images (20 males and 20 females, including 10 females with hijabs and 10 without) showed that ResNet50 classified 38 images correctly, achieving 95% accuracy. AlexNet classified 37 images correctly with 92.50% accuracy, SqueezeNet classified 36 images correctly with 90% accuracy, and VGG16 classified 34 images correctly with 85% accuracy. The contribution of this research shows that AlexNet achieves the highest validation accuracy, while ResNet50 provides the best accuracy in facial image detection for determining gender and hijab features.

SYSTEMATIC LITERATURE REVIEW KERENTANAN LANSIA TERHADAP SERANGAN PHISHING PADA SISTEM DANA PENSIUN DIGITAL Hanacahyani Widya Asih; Lintang Amarul Fatah; Mukti Diananingsih; Djoko Pitoyo; Eka Ardhianto; Aji Supriyanto
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8356

The digital transformation of financial systems has improved efficiency while simultaneously expanding the cybersecurity attack surface, particularly for phishing threats in pension fund distribution. Elderly individuals, as primary beneficiaries, are considered highly vulnerable due to limited digital literacy, cognitive decline, and a strong trust bias toward authority. This study aims to identify phishing attack patterns, risk factors, and effective mitigation strategies targeting elderly populations through a Systematic Literature Review (SLR) approach following the PRISMA framework. Literature was sourced from IEEE Xplore, Scopus, SpringerLink, and Google Scholar (2015–2025). A total of 120 articles were initially identified, with 35 studies meeting the inclusion criteria after rigorous screening. The findings indicate that elderly individuals are particularly susceptible to email phishing, smishing, and vishing, with significantly higher success rates compared to younger populations. Key contributing factors include low cybersecurity literacy, cognitive limitations, trust bias, and non-inclusive interface design. Effective mitigation strategies include user-centered security design, biometric multi-factor authentication (MFA), and simulation-based security training. This study contributes to a comprehensive risk mapping of phishing threats among elderly pension beneficiaries and provides actionable insights for designing more secure and inclusive digital pension systems.

Title

Found 42 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 42 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 42 Documents
Search