cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
I Gede Iwan Sudipa
Contact Email
iwansudipa@instiki.ac.id
Phone
+6281933054911
Journal Mail Official
krisnadana@sidyanusa.org
Editorial Address
Jl. Gunung Cemara No. 64, Sapta Bumi,Kel./Ds. Tegal Harum, Kec. Denpasar Barat, Denpasar
Location
Kota denpasar,
Bali
INDONESIA
Jurnal Krisnadana
Published by Yayasan Sinergi Widya Nusantara
ISSN : 28083520     EISSN : 28083563     DOI : 10.58982
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering
Jurnal Krisnadana merupakan jurnal yang dapat menjadi wadah bagi civitas akademika dan kalangan profesional dalam mempublikasikan karya ilmiah ataupun hasil penelitiannya dengan tetap mengutamakan orisinalitas karya, pengembangan kelimuan dan kontribusi dalam berbagai bidang. Jurnal Krisnadana berfokus pada bidang Ilmu Komputer, Sistem Kendali, dan Jaringan. Fokus dan Ruang lingkup pada Jurnal Krisnadana (Komputer, Sistem Kendali, & Jaringan) yang dapat menjadi topik makalah atau penelitian meliputi berbagai bidang minat, diantaranya: 1) Rekayasa perangkat lunak; 2)Sistem Informasi; 3) Sistem Pendukung Keputusan (SPK); 4) Sistem Pakar; 5) Kecerdasan Buatan; 6) Aplikasi Mobile; 7) Pengolahan Citra; 8) Robotika; 9) Smarts System; 10) Cloud Technology; 11) Image Processing; 12) Internet Of Things (IOT); 13) Jaringan Komputer; 14) Komputasi Paralel; 15) Sistem Terdistribusi; 16) Data Analytic; 17) Audit Teknologi Informasi; 18) Telekomunikasi dan Pemrosesan Sinyal; 19) Otomasi kontrol (Control Automation); 20) Topik studi relevan lainnya.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 145 Documents
 11   12   13   14   15 
Multi-Time Frame Gold Price Forecasting Using Long Short-Term Memory Mohammad Zainuddin; Rachmat Rachmat
Jurnal Krisnadana Vol 5 No 2 (2026): Jurnal Krisnadana- January 2026
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/krisnadana.v5i2.1110

Abstract

Forecasting gold prices is essential for investors to minimize risks in investment decision-making. This study aims to predict gold closing prices using the Long Short-Term Memory (LSTM) method with weekly and monthly time frames. The data used were obtained from investing.com, covering the period from February 2015 to February 2025. The model's performance was evaluated using MAPE, RMSE, and R² metrics. The results show that the LSTM model has a good accuracy level, with MAPE values of 1.83% for the weekly time frame and 3.60% for the monthly time frame. The R² values of 0.9721 and 0.9134, respectively, indicate a high capability of the model in explaining data variability. Forecast results for the next 22 weeks indicate a stable trend with slight increases, while the 12-month forecast suggests a gradual downward trend in gold prices. These findings are expected to assist investors in planning more effective and measured investment strategies.
Deep Learning Models for Financial Time Series Forecasting in Investment Contexts Hamid Wijaya; Lalu Puji Indra Kharisma; Yusuf Aliyu Madamu
Jurnal Krisnadana Vol 5 No 2 (2026): Jurnal Krisnadana- January 2026
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/krisnadana.v5i2.1111

Abstract

Stocks represent an investment instrument that reflects ownership in a company, offering opportunities for profit through dividends or capital gains. However, stock prices often fluctuate due to various economic, social, and political factors, making price prediction a challenging task. This study applies the Long Short-Term Memory (LSTM) method, a deep learning architecture, to forecast the stock prices of Apple Inc. (AAPL) based on historical data obtained from Yahoo Finance covering the period from December 12, 1980, to September 20, 2024. The research process includes data cleaning, normalization using MinMaxScaler, data splitting with an 80:20 ratio for training and testing, and hyperparameter optimization through Grid Search. The optimal LSTM model configuration achieved 50 epochs, a batch size of 64, and a learning rate of 0.0001. Evaluation results demonstrate high accuracy, with a MAPE of 1.70%, RMSE of 3.030, and R-squared of 0.9975. Forecasts indicate a gradual decline in AAPL stock prices over the next 12 months, from $173.83 in October 2024 to $111.34 in September 2025. This research provides valuable insights for investors to better understand market dynamics and make informed investment decision.
Risk Management Analysis of Information Systems at Amertha Sanjiwani Store in Using ISO 31000 Based E-Purchasing Application I Wayan Ady Juliantara; Wayan Eka Ariawan
Jurnal Krisnadana Vol 5 No 2 (2026): Jurnal Krisnadana- January 2026
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/krisnadana.v5i2.1112

Abstract

The development of information technology has driven digitalization in various sectors, including government procurement of goods and services through the E-purchasing system. Toko Amertha Sanjiwani is one of the businesses that utilizes the e-Catalog and Mbizmarket platforms to process transactions with government agencies. However, in its implementation, the information system used also creates various operational risks that can disrupt business continuity. This study aims to analyze the information system risk management implemented by Toko Amertha Sanjiwani using the ISO 31000:2018 framework. The method used is a descriptive qualitative approach with data collection techniques in the form of interviews, observation, and documentation. The results show that there are ten main risks identified, including internet connection disruptions, application inaccessibility, and delays in product data updates and delivery of goods. These risks are then analyzed based on their likelihood and impact, so that mitigation priorities are obtained. Control measures are carried out through strategies such as increasing staff training, providing backup networks, and implementing dual authentication and data backup SOPs. By conducting regular evaluation and monitoring, the implementation of ISO 31000-based risk management has proven effective in helping Toko Amertha Sanjiwani identify, analyze, and control information system risks systematically and sustainably.
Comparison of Rotational Interpolation Methods for Sign-Language Avatar Animation Ahmad Asroni; Komang Kurniawan Widiartha; Daniel Kevin Alexander
Jurnal Krisnadana Vol 5 No 3 (2026): Jurnal Krisnadana May - July 2026
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/9da84z43

Abstract

Sign-language learning media based on 3D avatars store sign motions as bone-rotation keyframes and replay them through interpolation. Common web-based systems use linear interpolation of Euler angles (LERP-Euler), which does not follow the shortest rotational path and yields unnatural angular velocity. Because movement is a meaning-bearing phonological parameter in sign language, interpolation quality affects sign legibility. This study objectively compares four methods LERP-Euler, quaternion SLERP, SLERP with smoothstep easing, and Catmull-Rom without human raters, grounding quality on the minimum-jerk and shortest-path principles. Eighty dictionary sign words were tested with an automated harness recording each bone's orientation and the fingertip position at 240 Hz. Eight metrics (Normalized Jerk, SPARC, path-length ratio, geodesic deviation, angular-speed CV, C1 jump, fingertip path length, and computation cost) were analysed using the Friedman test with post-hoc Wilcoxon (Bonferroni). No method dominates all dimensions: Catmull-Rom and eased SLERP are the smoothest (p < 0.001), while SLERP and eased SLERP best follow the shortest path (ratio ? 1.000) at the lowest cost; Catmull-Rom overshoots (ratio ? 1.13) and is costliest. Overall, eased SLERP is recommended as the best compromise for real-time web deployment.
IoT-Based Automatic Watering and Flow Detection System via Telegram Ketut Gde Manik Karvana; Ni Ketut Utami Nilawati; Evi Dwi Krisna
Jurnal Krisnadana Vol 5 No 3 (2026): Jurnal Krisnadana May - July 2026
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/y56hb388

Abstract

Gardens are an important part of the surrounding environment, so they need to be maintained regularly. Manual watering systems are often inefficient. An automatic watering system based on the ESP 8266 was created which offers a more efficient solution, and plants get an adequate water supply. The system will water the plants according to the schedule that has been designed. This system is also equipped with a no-water flow detector to prevent plants from being watered during the watering schedule, and will provide a warning if there is no water flow. This warning is then sent via Telegram Messenger. Of the 20 tests of the automatic watering system, the watering start notification was sent successfully 17 times (80%), while the watering stop notification was successfully sent 18 times (90%). The main obstacle occurs on normal lecture days. Checking via the Wireshark application proved that there were several very high packet loss values (2.8514), which indicates that many data packets were lost during transmission. The water flow meter sensor only detected no water flow on one occasion out of 20 tests. This research shows that an automatic watering system and detection of no water flow can make the work of INSTIKI employees easier.
SOC Implementation for Cybersecurity Incident Handling Optimization I Gede Adnyana Adnyana; I Nyoman Buda Hartawan Hartawan; I Nyoman Arnawan; Mahesa Rama Aditya
Jurnal Krisnadana Vol 5 No 3 (2026): Jurnal Krisnadana May - July 2026
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/kjvrk872

Abstract

Cybersecurity incidents continue to increase in complexity and impact, requiring institutions to improve their monitoring and response capabilities. This study implements a simple Security Operations Center (SOC) workflow to support cybersecurity incident handling through endpoint monitoring, alert generation, workflow automation, and real-time notification. The system integrates Wazuh as a Security Information and Event Management platform, Wazuh Agent as an endpoint log collector, n8n as a workflow automation tool, and Telegram as a notification channel. The implementation was carried out by deploying the required services using Docker, registering monitored endpoints through Wazuh Agent, configuring Wazuh alerts, forwarding alerts to n8n through webhook integration, parsing important alert fields, and sending structured notifications to administrators through Telegram. The system was evaluated through several test scenarios, including agent connectivity, failed SSH login detection, malware detection, Wazuh-to-n8n alert delivery, alert parsing, and Telegram notification delivery. The results show that the implemented SOC workflow successfully receives endpoint logs, generates security alerts, processes alert data automatically, and sends real-time notifications to administrators. This implementation demonstrates that open-source tools can be integrated to build a practical SOC workflow for improving initial cybersecurity incident awareness and response.
Tuna Eye Image Classification for Freshness Detection Using PCA and SVM I Made Dwi Putra Asana; I Wayan Aldinata; Made Leo Radhitya; Ni Putu Suci Meinarni; Ida Bagus Gede Anandita
Jurnal Krisnadana Vol 5 No 3 (2026): Jurnal Krisnadana May - July 2026
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/tegv3p18

Abstract

Freshness assessment of tuna (Auxis thazard) in traditional markets still relies mainly on subjective visual inspection, which introduces inconsistency and food-safety risk. This study proposes an objective, low-cost classification pipeline for tuna freshness based on eye images. Six hundred forty fish-eye images were acquired at Kedonganan Fish Market and labeled through a 30-panelist organoleptic test based on SNI 2729:2013. The pipeline segments the eye Region of Interest using U-Net, extracts HSV color features from the segmented eye, reduces dimensionality using Principal Component Analysis (PCA), and classifies freshness with a Support Vector Machine (SVM). A Group K-Fold (k=8) validation scheme and per-fold standardization are used to prevent data leakage across acquisition groups. Grid search over target cumulative variance (50%-95%) and SVM regularization (C=0.1, 1, 10) yields a best configuration at cumulative variance of 55% and C=1, achieving 96.72% accuracy, 97.76% precision, 96.72% recall, and 96.51% F1-score. Compared with SVM without PCA (95.47% accuracy, 215.82 s), the PCA-SVM model reaches equivalent or higher accuracy with 47% lower classification time, supporting deployment on resource-constrained devices.
Image Classification of Traditional Musical Instruments from East Nusa Tenggara Using CNN and VGG19 Marvin Gilbrand Adu; I Gede Totok Suryawan; Ida Bagus Ary Indra Iswara
Jurnal Krisnadana Vol 5 No 3 (2026): Jurnal Krisnadana May - July 2026
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/tt9bdq83

Abstract

This research is motivated by the declining ability of the younger generation to recognize the physical forms of traditional musical instruments from East Nusa Tenggara (NTT). This study aims to apply a Convolutional Neural Network (CNN)- based Deep Learning algorithm to classify seven types of musical instruments: Sasando, Moko, Gong, Gendang, Foydoa, Jungga, and Knobe Oh. A dataset of 610 images was used, split 80% for training and 20% for testing, and subjected to preprocessing steps, including resizing and data augmentation. The performance of a Custom CNN architecture was compared against VGG19 (fine-tuning) across variations of learning rates (0.001, 0.0001, and 0.00001). The results showed that the Custom CNN achieved optimal performance at a learning rate of 0.0001, with a training accuracy of 91.63% and a validation accuracy of 82.50%. Meanwhile, the fine-tuned VGG19 model achieved 100% training accuracy and 93.33% validation accuracy. Confusion Matrix evaluation on the test data demonstrated that the best model achieved 100% accuracy, indicating that the system successfully extracts and recognizes the visual features of each instrument.
Performance Comparison of FastText and Bi-LSTM for Multilabel Sentiment Analysis on Indonesian Social Media Data: A Case Study of the Asset Confiscation Bill Theresia Hendrawati; Ni Luh Wiwik Sri Rahayu G; Made Sena Dwi Tenaya
Jurnal Krisnadana Vol 5 No 3 (2026): Jurnal Krisnadana May - July 2026
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/k3vftr13

Abstract

Public opinions expressed on social media are often multidimensional, making conventional single-label sentiment analysis insufficient for capturing the complexity of public discourse. Multilabel sentiment analysis enables a text instance to be associated with multiple categories simultaneously, providing a more comprehensive representation of public perceptions. This study presents a comparative analysis of FastText and Bidirectional Long Short-Term Memory (Bi-LSTM) for multilabel sentiment classification using Indonesian social media data related to the Asset Confiscation Bill (RUU Perampasan Aset). Data were collected from X (formerly Twitter) and YouTube and annotated into twelve predefined labels encompassing legal, political, economic, administrative, and governance dimensions. The proposed framework consisted of data collection, text preprocessing, multilabel annotation, model development, and performance evaluation using Hamming Score. Three experimental scenarios were conducted for each model to evaluate the impact of Label Attention and architectural optimization. Experimental results demonstrated that FastText consistently outperformed Bi-LSTM across all scenarios. FastText combined with Label Attention and Label Normalization achieved the highest Hamming Score of 0.987450, while Bi-LSTM attained its best performance of 0.967833 using Dense Layer Optimization and Label Attention. The findings indicate that FastText is more effective in handling noisy Indonesian social media texts due to its subword embedding capability. This study contributes empirical evidence regarding the effectiveness of lightweight embedding models for multilabel sentiment analysis and provides insights for future applications in public policy monitoring and social media analytics.
Educational Game Development for Middle School Students' English Vocabulary Learning Made Dona Wahyu; Ni Made Lisma Martarini; I Gede Made Yudi Antara; Ni Kadek Damayanti
Jurnal Krisnadana Vol 5 No 3 (2026): Jurnal Krisnadana May - July 2026
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/3186m063

Abstract

Student interest and participation in learning will influence learning success. Because the higher the student's interest, the better their ability and understanding of the subjects being studied. English learning at the junior high school level still faces various obstacles, one of which is low vocabulary skills or vocabulary in English. Vocabulary serves as the basis for communication and contributes to language skills. The application of technology-based learning media such as educational games can be used to improve the quality of the teaching and learning process in schools. This study aims to develop an Android educational game as a medium for learning English vocabulary. The development of this educational game uses the Game Development Life Cycle (GDLC) method.The results of the Black Box test show that all the main functions of the application, starting from the process of opening the application, menu navigation, character and camera control, mission completion mechanism, game time management, to the function of repeating the game and exiting the application, have run according to the designed specifications.

Page 14 of 15 | Total Record : 145

 11   12   13   14   15 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol 5 No 3 (2026): Jurnal Krisnadana May - July 2026 Vol 5 No 2 (2026): Jurnal Krisnadana- January 2026 Vol 5 No 1 (2025): Jurnal Krisnadana- in Progress September-October 2025 Vol 4 No 3 (2025): Jurnal Krisnadana May - July 2025 Vol 4 No 1 (2024): Jurnal Krisnadana – September 2024 Vol 3 No 3 (2024): Jurnal Krisnadana – Mei 2024 Vol 3 No 2 (2024): Jurnal Krisnadana – Januari 2024 Vol 3 No 1 (2023): Jurnal Krisnadana - September 2023 Vol 2 No 3 (2023): Jurnal Krisnadana – Mei 2023 Vol 2 No 2 (2023): Jurnal Krisnadana - Januari 2023 Vol 2 No 1 (2022): Jurnal Krisnadana - September 2022 Vol 1 No 3 (2022): Jurnal Krisnadana - Mei 2022 Vol 1 No 2 (2022): Jurnal Krisnadana - Januari 2022 Vol 1 No 1 (2021): Jurnal Krisnadana - September 2021 More Issue