cover
Contact Name
Alam Rahmatulloh
Contact Email
alam@unsil.ac.id
Phone
+6285223519009
Journal Mail Official
innovatics@unsil.ac.id
Editorial Address
Program Studi Informatika Fakultas Teknik Universitas Siliwangi Jl. Siliwangi No. 24 Tasikmalaya, Jawa Barat
Location
Kota tasikmalaya,
Jawa barat
INDONESIA
Innovation in Research of Informatics (INNOVATICS)
Published by Universitas Siliwangi
ISSN : -     EISSN : 26568993     DOI : -
Innovation in Research of Informatics (Innovatics) merupakan Jurnal Informatika yang bertujuan untuk mengembangkan penelitian di bidang: Machine Learning Computer Vision Internet of Things Information System and Technology Natural Language Processing Image Processing Network Security Geographic Information System Knowledge based Computer Graphic Cyber Security IT Governance Data Mining Game Development Digital Forensic Business Intelligence Pattern Recognization Virtual & Augmented Reality Virtualization Enterprise Application Self-Adaptive Systems Human Computer Interaction Cloud Computing Mobile Application Innovatics adalah jurnal peer-review yang ditulis dalam bahasa Indonesia yang diterbitkan dua kali dalam setahun mulai dari Vol. 1 No.1 Maret 2019 (Maret, dan September) dengan proses peninjauan menggunakan double-blind review.
Articles 10 Documents
Search results for , issue "Vol 7, No 2 (2025): September 2025" : 10 Documents clear
Automated Identification of Oil Palm’s 17th Leaf Using YOLOv12 and Spatial Positioning Rahmawan, Jihad; Yuliansyah, Herman; Yudhana, Anton; Irfan, Syahid Al
Innovation in Research of Informatics (Innovatics) Vol 7, No 2 (2025): September 2025
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v7i2.15766

Abstract

This study proposes an artificial intelligence–based approach for automatic identification of the 17th leaf in oil-palm trees (Elaeis guineensis), which serves as a key physiological indicator for nutrient monitoring. The method integrates YOLOv12 object detection with a spatial-positioning algorithm that estimates leaf order through vertical sorting of detected fronds. A total of 1,250 annotated field images were collected from farmer-recorded videos to train and evaluate the system. The proposed model achieved a mean average precision (mAP@0.5) of 92.4% and an average positional error of 10.6 pixels in locating the 17th leaf. Compared with manual identification that requires 3–5 minutes per tree, the automated system performs the entire process in under 15 seconds, providing over 95% time efficiency improvement. This work demonstrates a novel fusion of real-time deep-learning detection and spatial reasoning for nutrient-focused precision agriculture and establishes a practical foundation for scalable, automated leaf indexing in plantation management.
Comparison of Efficiency and Security of AES, Blowfish, and ChaCha20 Cryptographic Algorithms on Image and Document Files Bintang Timur, Muhammad Bagus; Royansyah, Royansyah; Kusumaningsih, Dewi
Innovation in Research of Informatics (Innovatics) Vol 7, No 2 (2025): September 2025
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v7i2.15748

Abstract

This study presents a comparative analysis of the Advanced Encryption Standard (AES), Blowfish, and ChaCha20 cryptographic algorithms in terms of their efficiency and security when applied to image and document files. The growing need for secure data transmission and storage has highlighted the importance of selecting suitable encryption algorithms based on specific file types and operational contexts. In this research, various sample files in image (JPG, PNG) and document (PDF, DOCX) formats were encrypted using the three algorithms. Performance was measured based on encryption and decryption time, CPU and memory usage, and file size changes after encryption. Security evaluation focused on resistance to brute-force attacks, key length strength, and algorithmic robustness. The experimental results indicate that ChaCha20 demonstrated superior performance in terms of processing speed and resource efficiency, especially on low-power systems. AES, while slightly slower, offered a high level of security and is widely trusted for sensitive document encryption. Blowfish, although fast, showed limitations in handling larger files and is less favored due to its shorter block size. This study concludes that no single algorithm is universally optimal; instead, the choice should depend on the specific use case, balancing efficiency and security requirements. These findings provide useful insights for practitioners and researchers in selecting appropriate cryptographic methods for protecting digital assets.
Forest Biomass Estimation through the Integration of UAV Imagery and Vegetation Indices: Toward Accurate and Efficient Monitoring Fadilah, Vira Hasna; Hadiana, Asep Id; Komarudin, Agus
Innovation in Research of Informatics (Innovatics) Vol 7, No 2 (2025): September 2025
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v7i2.14931

Abstract

Forest biomass estimation method using drone imagery and vegetation index, focusing on the effectiveness and efficiency of the approach. Using high-resolution drone imagery, this study analyzes vegetation structure and density, and supports the development of a more accurate biomass estimation model compared to traditional methods. Drone imagery has the advantage of collecting data quickly and in real time, especially in areas that are difficult to access manually. Vegetation indices, such as NDVI, are used to assess vegetation health and density, which are closely related to biomass estimation. The combination of drone imagery and vegetation indices can produce more detailed data, support 3D vegetation modeling, and help estimate biomass volume over time. This study is expected to produce data and biomass estimation models that support sustainable forest management as well as technical recommendations for the use of drones for vegetation monitoring. The findings of this study show that the proposed method produces an estimation accuracy of 85.2% based on field validation data calculated using simple linear regression. The findings of this study are expected to make a significant contribution to the development of drone-based technology for efficient and environmentally friendly natural resource management.
Liquefied Petroleum Gas (LPG) Leak Detection Mitigation System with MQ-6 Sensor based on the Internet of Things (IoT) Novitaningrum, Dian; Handayani, Yuni; Hidayat, Taufik
Innovation in Research of Informatics (Innovatics) Vol 7, No 2 (2025): September 2025
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v7i2.16705

Abstract

The community is beginning to shift from the use of petroleum fuel to Liquefied Petroleum Gas (LPG). In 2023, the Kendal Regency Statistics Agency recorded 53 cases of fire. One of the factors contributing to these fires was gas cylinder leaks, which require preventive measures, education, and mitigation efforts for the proper use of LPG. This research was conducted by designing an LPG gas leak detection system based on the Internet of Things (IoT) using an MQ-6 sensor to notify users of emergencies. The systems aims to notify users via the Blynk application to prevent gas leaks. The research method includes designing the device by assembling and testing components. Additionally, software was developed to connect the sensor to the notification application using Blynk. The system can detect LPG gas leaks within a range of 1-16 cm. A safe threshold is defined as gas levels < 40 ppm, while levels >45 ppm indicate a hazardous status. The conclusions from this research shows that the average gas concentration when the green LED is on 33 ppm with a detection time of 0 seconds, the yellow LED at 40.6 ppm with a detection time of 11.6 seconds, and the red LED at 50 ppm with a detection time of 25.3 seconds, accompanied by a buzzer sounding as a warning of a gas leak in the LPG cylinder. Further research focused on improving the accuracy of the system connected to users WhatsApp accounts.
Data Augmentation Strategies on Spectrogram Features for Infant Cry Classification Using Convolutional Neural Networks Alam, Alam; Setyoningrum, Nuk Ghurroh; Maududy, Robby; Damayanti, Dea Dewi; Rahmawati, Hilmi
Innovation in Research of Informatics (Innovatics) Vol 7, No 2 (2025): September 2025
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v7i2.16823

Abstract

Infant cry classification is an important task to support parents and healthcare professionals in understanding infants’ needs, yet the challenge of limited and imbalanced datasets often reduces model accuracy and generalization. This study proposes the application of diverse audio data augmentation strategies including time stretching, time shifting, pitch scaling, and polarity inversion combined with spectrogram representation to enhance Convolutional Neural Network (CNN) performance in classifying infant cries. The dataset from the Donate-a-Cry Corpus was expanded from 457 to 6,855 samples through augmentation, improving class balance and variability. Experimental results show that CNN accuracy increased from 85% before augmentation to 99.85% after augmentation, with precision, recall, and F1-score reaching near-perfect values across all categories. The confusion matrix further confirms robust classification with minimal misclassifications. These findings demonstrate that data augmentation is crucial to overcoming dataset limitations, enriching acoustic feature diversity, and reducing model bias, while offering practical implications for the development of accurate, reliable, and real-world applicable infant cry detection systems.
Design of Prototype Early Warning System for Ship Gas Leakage and Fire Using MQ-6 Sensor and Arduino Uno Microcontroller Chandra, Yudi Irawan; Sjafrina, Fitri; Irawati, Diyah Ruri; Riastuti, Marti
Innovation in Research of Informatics (Innovatics) Vol 7, No 2 (2025): September 2025
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v7i2.16382

Abstract

Maritime transportation is vital for global trade but faces risks from gas leaks and fires, which can endanger ships and crews. Many small and medium-sized vessels lack effective systems to detect hazardous gases early, raising the chance of accidents. This study focuses on developing a prototype early warning system to detect gas leaks and fires on ships using an MQ-6 sensor and an Arduino Uno microcontroller. The goal is to provide a low-cost, real-time monitoring solution to improve maritime safety. The research follows a hardware prototyping and software development process using a waterfall approach, including requirement analysis, system design, implementation, testing, and deployment. The MQ-6 sensor identifies flammable gases like LPG and butane, while the Arduino Uno processes the sensor data and triggers alarms when gas levels become dangerous. The prototype was tested in a simulated ship environment to assess its sensitivity, response time, and reliability. Test results show that the system detects gas concentrations above safe limits within 3 to 5 seconds, activating visual and audio alarms quickly. The device also operates continuously with low power consumption, making it suitable for long-term use on ships. The study shows that this prototype can serve as an affordable and reliable additional safety device for maritime settings. This research supports efforts to improve ship safety systems by offering a practical way to reduce risks from gas leaks and fires. The system’s simplicity and effectiveness make it a promising option for enhancing onboard hazard detection.
Enhancing YOLOv5s with Attention Mechanisms for Object Detection in Complex Backgrounds Environment Impron, Ali; Lestari, Dina; Sutriani, Linda; Anggraini, Syadza; Rizal, Randi
Innovation in Research of Informatics (Innovatics) Vol 7, No 2 (2025): September 2025
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v7i2.16833

Abstract

Enhancing performance for object detection in complex environments is essential for real-world applications that represent complexities, such as stacking objects in the same location or environment. Models for detecting objects developed to this day still have difficulties in detecting objects with environments that have complex backgrounds. The reason is that the model often experiences a decrease in accuracy when the object to be detected is occlusion by other objects and is small in size. Therefore, in this study, a model improvement method was carried out in detecting objects in a complex environment. The algorithm used in this study is YOLOv5s. Optimization is carried out by adding a CBAM (Convolutional Block Attention Module) attention mechanism layer which is integrated with the C3 layer (C3CBAM) in the backbone of the YOLOv5s model architecture. In addition, a P2 feature map is also added to the architecture head. The optimization results carried out were quite satisfactory, namely there was an increase in the precision value by 1.6 %, at mAP@0.5 an increase of 1.4 %, and also mAP@50-95 increased by 0.1%. This proves that the enhancement method applied to YOLOv5s in this study can improve the performance of the model. However, with the addition of the attention mechanism layer, it turns out that it can increase the computational load. Therefore, for future research, a method can be applied to reduce computing load, one of the methods is knowledge distillation.
Performance and Effectiveness Evaluation of the National Digital Samsat as a Public E-Government Service Using the PIECES Framework Fitria, Rahma; Syakhila, Amanda; Yulisda, Desvina; Hussain, Azham; Febriandirza, Arafat
Innovation in Research of Informatics (Innovatics) Vol 7, No 2 (2025): September 2025
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v7i2.15672

Abstract

The SIGNAL application is a digital service from the Korlantas Polri that makes it easier for people to take care of STNK validation online. However, some users still experience problems such as the verification process that is not always successful, slow delivery of physical documents, less rapid customer service response, and slow verification or login process. Therefore, this study aims to evaluate the performance of the SIGNAL application with the PIECES framework approach which includes six aspects: Performance, Information, Economic, Control, Efficiency, and Service. The data collection method was carried out through distributing questionnaires to 300 respondents who use the SIGNAL application. In addition, technical performance testing was also carried out using Apptim tools to measure application technical metrics. The results showed that overall, users were satisfied with the system based on the six aspects of PIECES with an average score of 3.9 on a scale of 5.76% of respondents stated that they were satisfied to very satisfied, 15% were undecided/neutral, and 9% were dissatisfied. This finding indicates that the majority of users consider this application to be quite effective and worth using. Performance testing using Apptim resulted in an average response time of 2.4 seconds, CPU usage of 18%, memory usage of 170MB, and no errors (error rate 0%), indicating that the application is quite stable and runs well on user devices. It is hoped that this research can be the basis for further development of the SIGNAL application, especially in improving service aspects and overall system efficiency.
Prediction of Dengue Fever Cases Using the Linear Regression Method Based on Open Data from West Java Province Firdaus, Muhammad Khysam; Yuliansyah, Herman
Innovation in Research of Informatics (Innovatics) Vol 7, No 2 (2025): September 2025
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v7i2.16143

Abstract

Dengue Hemorrhagic Fever (DHF) is a widespread disease in tropical regions, including Indonesia. West Java Province reports the highest number of cases, influenced by factors such as rainfall, population density, and total population. Accurate prediction of DHF cases is essential for effective prevention and control strategies. This study aims to propose a predictive model for DHF cases in West Java using the Linear Regression method and to evaluate its performance using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) metrics. The research utilizes secondary data from 2014 to 2023 on DHF cases, population density, and total population from the Open Data Jabar platform. Rainfall data were collected from Badan Meteorologi, Klimatologi, dan Geofisika (BMKG) and Badan Pusat Statistik Indonesia (BPS). The research process includes data collection, preprocessing, time series splitting, model training and iteration, prediction, and performance evaluation. The results show that among the five focus regions, Bandung City achieved the best prediction performance, with a MAPE of 45.82% and an RMSE of 1216.105. These findings indicate that Multiple Linear Regression is reasonably effective for predicting DHF cases, particularly in Bandung. Despite limitations in data availability especially rainfall data the model provides informative insights. Future work could improve prediction accuracy by incorporating additional independent variables and more advanced modeling techniques, such as machine learning.
Comparison Analysis of Equivalence Class Partitioning and Boundary Value Analysis Techniques in Software Quality Testing of ReservasiPolnep Application Alifiansyah, Zuhrie; Alkadri, Syarifah Putri Agustini; Insani, Rachmat Wahid Saleh
Innovation in Research of Informatics (Innovatics) Vol 7, No 2 (2025): September 2025
Publisher : Department of Informatics, Siliwangi University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/innovatics.v7i2.16789

Abstract

Software testing is a crucial phase before the official launch of an application to ensure its functionality and quality. This study compares two black box testing techniques—Equivalence Class Partitioning (ECP) and Boundary Value Analysis (BVA)—in identifying functional defects in the ReservasiPolnep application. The study involved testing key application features using both techniques, and results were measured using standard software testing metrics: test case coverage, success rates, test time, and cost per defect. The results showed that ECP is more time and cost-efficient, requiring only 26 test cases and 15 minutes 27 seconds per test, with a cost of Rp30 per defect and an 84.6% success rate. In contrast, BVA covers more test scenarios with 36 test cases, taking 27 minutes 5 seconds and costing Rp40 per defect, with a slightly higher success rate of 86.1%. The study concludes that each technique has advantages depending on the context, and highlights the need for input validation improvements in the application.

Page 1 of 1 | Total Record : 10