Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control
Not a member yet
424 research outputs found
Sort by
Evaluation of Traffic Distribution Performance of ECMP and PCC+CAKE for Multi-ISP Load Balancing on Real Networks Based Using Mikrotik
No full textImbalance in bandwidth utilization among Internet Service Providers (ISPs) is a major challenge in network management within educational institutions, especially when differences in ISP capacity cause overload on one main path. To address this issue, this study proposes the application of load balancing methods using Equal-Cost Multi-Path (ECMP) and Per-Connection Classifier (PCC) optimized with the CAKE queue type. The implementation is carried out using MikroTik devices, which support the flexible configuration of both methods. Testing is conducted on a real network using a combination of passive monitoring approach—through the analysis of actual traffic and ISP utilization—and active monitoring. The evaluation results show that the ECMP method still produces an uneven traffic distribution, with a tendency to concentrate the load on one path. In contrast, PCC+CAKE is able to distribute traffic more evenly according to the ISP bandwidth ratio. In addition, PCC+CAKE shows more stable performance on throughput, RTT, and jitter, and has very low packet loss. Therefore, PCC+CAKE is recommended as a more effective load balancing method to increase the efficiency of ISP utilization and overall network quality in a multi-ISP environment
XGBoost-Powered Ransomware Detection: A Gradient-Based Machine Learning Approach for Robust Performance
No full textRansomware remains a rapidly evolving cyber threat, causing substantial financial and operational disruptions globally. Traditional signature-based detection systems are ineffective against sophisticated, zero-day attacks due to their static nature. Consequently, machine learning-based approaches offer a more effective and adaptive alternative. This study proposes an approach utilizing XGBoost for highly effective ransomware detection. We conducted a rigorous comparative analysis of prominent ensemble learning algorithms—XGBoost, Random Forest, Gradient Boosting, and AdaBoost—on the RISS Ransomware Dataset, comprising 1,524 instances. Our experimental results unequivocally demonstrate XGBoost as the superior ensemble model, achieving an impressive 97.60% accuracy and F1-Score. This performance surpassed Gradient Boosting (97.20%), Random Forest (96.94%), and AdaBoost (96.50%). Furthermore, this study benchmarked XGBoost against established state-of-the-art (SOTA) methods, including Support Vector Machine (SVM) and the SA-CNN-IS deep learning approach. The comprehensive results underscore the core contribution of this study: by applying XGBoost with a carefully structured machine learning pipeline, our approach consistently outperforms two state-of-the-art methods (SVM and SA-CNN-IS) as well as other ensemble algorithms. This highlights the critical role of methodological precision in maximizing detection performance against evolving ransomware threats
Design and Implementation of Two-phase Boost Inverter using Interleaved Method to Increase Output Current
Get PDFThe advancement of technology is rapidly evolving, particularly in the field of electronics, namely power electronics. One of the applications is the use of new and renewable energy. The converters required in new and renewable energy are inverters with good quality and performance. The step-down (buck) inverter is commonly used in this application. Different from the normal inverter, the step up (boost) inverter is proposed to be analyzed, simulated, and implemented in this paper. The proposed inverter uses a two-phase interleaved boost inverter (TP DC-AC IBI) consisting of a full bridge inverter and dual AC-AC interleaved boost converter. The inverter part always converts DC voltage to AC voltage, while the dual AC-AC interleaved boost converter part serves to increase the output voltage. The inverter consists of three arms: the first and second arms are controlled by Sinusoidal Pulse Width Modulation (SPWM) using 180° phase-shifted carrier signal, and the third arm is controlled by a zero-crossing detector. Pulse Width Modulation (PWM) is used to control dual AC-AC interleaved boost converter. By combining this inverter with dual AC-AC interleaved boost converter, a new topology is created. This study specifically investigated the strategy to control this new topology using current controls. The actual current was obtained by installing an HX-10P current sensor on the output side. The output current was compared with the reference current, and the next stage was controlled using a proportional plus integral controller. The control signals output was modulated using SPWM signals on the inverter side and PWM at the AC-AC interleaved boost converter side to drive many power switches. To guarantee that the desired current control can always be achieved, the actual current and reference current must always match. The proportional plus integral controller was chosen due to its simplicity, high accuracy, and quick response time. The analysis involved verifying simulation tests using Power Simulator (PSIM) software. The hardware implementation was conducted in the laboratory and tested using standardized equipment. A couple of inductors were installed to reduce harmonic current on the output side and obtained THD of 3.3%, which according to the IEEE 519-2014, has met the standard as it was less than 5%. Thus, this new topology can be used in new and renewable energy for its good performance
An Ensemble Learning Layer for Wayang Recognition using CNN-based ResNet-50 and LSTM
Get PDFWayang is commonly used to tell epic stories of Mahabharata and Ramayana, as well as local legends and myths. There are various types of wayang, such as wayang kulit (made of buffalo or goat leather), wayang golek (made of wood), and wayang klithik (combination of leather and wood). Although it indicates cultural richness, such diversity also makes it difficult for the general public to identify the character of wayang they are seeing because each type has unique characteristics and details. Recognizing wayang characters is a challenging task due to their intricate designs and subtle variations. This research addresses this problem by leveraging machine learning technology, specifically CNN-based classification methods, to accurately identify wayang characters. This study proposed a novel method that integrates ResNet-50 transfer learning with LSTM, enhancing the model's ability to capture both spatial and sequential features of wayang images. The proposed model achieved an impressive accuracy of 97.92%, with precision, recall, and F1-scores all reaching 100%. Despite the extended training time of 188 minutes and 21 seconds, the results demonstrate the model's superior performance. This advancement can significantly aid in the preservation and educational dissemination of Indonesian cultural heritage. Future research can focus on optimizing the training process to reduce the time while maintaining or even improving the accuracy, potentially expanding the model's application scope and effectiveness
Classification of Sleep Disorders using Support Vector Machine
Get PDFSleep disorders become a severe concern in our busy modern lifestyles, which are often overlooked and can cause significant negative impacts on an individual's health and quality of life. This research explores the implementation of machine learning, specifically Support Vector Machine, to facilitate quick and accurate sleep disorder diagnosis. Data shows that sleep deprivation or disturbed sleep is becoming common in society, with 62% of the adult population experiencing dissatisfaction with their sleep quality. This has a significant economic impact and affects the health and productivity sectors. This study uses Kaggle Sleep Health and Lifestyle dataset of 400 data samples, applying Support Vector Machine to classify sleep disorders using three testing scenarios. The results showed an accuracy rate of 92%, confirming that Support Vector Machine can potentially improve the diagnosis of sleep disorders, enabling early intervention and better treatment for patients. Thus, this research contributes to understanding and treating sleep disorders, improving people's overall quality of life
Cybersecurity Management Strategies for Smart Cities in Indonesia: Cultural Factors and Implementation Challenges
No full textThe implementation of smart cities in Indonesia presents significant cybersecurity challenges, particularly amid bureaucratic complexity, low digital literacy, and limited institutional capacity. This study explores cybersecurity management strategies in the context of Jakarta Smart City (JSC), emphasizing sociotechnical dynamics and embedded cultural-institutional factors. Employing a qualitative approach and the Actor-Network Theory (ANT) framework, this research examines four key moments in the stabilization of cybersecurity networks: problematization, interessement, enrollment, and mobilization. Empirical findings reveal that challenges such as fragmented governance, security awareness gaps, and limitations in technological adaptation are addressed through context-specific strategies. These include regulatory reforms, multi-stakeholder collaboration, hybrid governance models, and the localization of international standards, particularly ISO/IEC 27001. The study also incorporates Indonesia’s Personal Data Protection Law (Law No. 27/2022) as a foundational legal framework that supports the integration of regional cybersecurity policies. Rather than focusing solely on technical solutions, this research emphasizes the importance of aligning cybersecurity strategies with local norms, leadership structures, and user practices. The proposed strategic model contributes to the cybersecurity governance literature by integrating ANT perspectives with empirical insights from a developing country. It offers a locally adapted and scalable framework to guide policymakers and smart city administrators in building resilient and culturally sensitive cybersecurity systems
A Hybrid Encryption using Advanced Encryption Standard and Arnold Scrambling for 3D Color Images
Get PDFDigital security ensuring the confidentiality and integrity of visual data remains a paramount challenge. The escalating sophistication of cyber threats necessitates robust encryption methods to safeguard sensitive information from unauthorized access and manipulation. Despite the development of various encryption techniques, inherent vulnerabilities exist within conventional methods that can be exploited by attackers. Therefore, this research aims to investigate the effectiveness of the combined approach of Arnold Scrambling and Advanced Encryption Standard (AES) in mitigating these vulnerabilities and providing a more secure solution. The primary goal of this research is to enhance the security of digital images by mitigating vulnerabilities associated with conventional encryption methods. Arnold Scrambling introduces chaotic mapping to disperse pixel values, while Advanced Encryption Standard (AES) provides robust cryptographic strength through its substitution-permutation network. By combining these methods in an ensemble fashion, the encryption process achieves heightened resilience against various cryptographic attacks. The proposed methodology was evaluated by using standard metrics including Unified Average Changing Intensity (UACI), Number of Pixels Change Rate (NPCR), and entropy analysis. Results indicate consistent performance across multiple test images, namely: Lena, Mandrill, Cameraman, and Plane with Unified Average Changing Intensity (UACI) averaging 33.6% and Number of Pixels Change Rate (NPCR) nearing 99.8%. Entropy values approached maximum, affirming the efficacy of the encryption in generating highly randomized outputs
Efficient Thoracic Abnormalities Detection Using Mobile Deep Learning Models
No full textIndonesia faces a critical shortage of radiologists, with only 1.2 radiologists per 100,000 individuals. This shortage leads to delays in diagnosing thoracic abnormalities such as pneumothorax, cardiomegaly, nodule/mass, consolidation, and infiltration. Chest X-ray (CXR) interpretation remains challenging due to overlapping radiological features, necessitating AI-assisted solutions. This study evaluates three lightweight deep learning models—MobileNetV2, ShuffleNetV2, and EfficientNetB0—for automated thoracic abnormality detection using the ChestX-ray8 dataset. We assessed model performance using accuracy, precision, recall, F1-score, and AUC-ROC, selecting the best model based on the highest per-fold F1-score. EfficientNetB0 emerged as the top-performing model, achieving a macro-average F1-score of 0.556 and AUC-ROC of 0.765, outperforming MobileNetV2 (0.494, 0.719) and ShuffleNetV2 (0.481, 0.713). Grad-CAM analysis revealed strong localization for pneumothorax and consolidation but misclassifications in cardiomegaly and nodule/mass detection due to poor feature differentiation. The findings highlight EfficientNetB0’s potential as an AI-assisted diagnostic tool for low-resource settings while also underscoring the need for segmentation-based pretraining and multi-scale feature extraction to enhance detection accuracy. Future work should focus on optimizing sensitivity to subtle abnormalities and ensuring clinical trust through improved interpretability techniques
Post Attack Mitigation on Open Journal System Services Using Knowledge Understanding Assessment Defense (KUAD) Method
No full textThis research was conducted to investigate evidence of an attack and to restore data after an attacker compromised an Open Journal System (OJS) service on a computer server. The method used in this research is a new approach developed from the Network Forensic Digital Life Cycle (NFDLC) method. This new method, known as KUAD, has several stages for collecting cyber-attack evidence and restoring it after the Gacor attack has occurred. The stages in the KUAD method include initiation, acquisition, execution, mitigation, and disposition. The novelty of this method, compared to the previous one, lies in the inclusion of the mitigation stage, which aims to restore data or documents after an attack. The tool used to detect the attack and find evidence of the attack is Tripwire, whereas the tools used to restore lost data include crontab, which runs backup commands with rsync in four steps. Tripwire can optimally detect attacks by displaying the number of data entries that were added, deleted, or modified. A total of 15,135 files in .docx, .pdf, and .jpg formats, deleted by the attacker, were successfully restored using this backup technique. The success rate of using this technique for post-cyber attack mitigation reached 100%
Aspect-based Multilabel Classification of E-commerce Reviews using Fine-tuned IndoBERT
Get PDFIn recent years, e-commerce has experienced rapid growth. A significant change in consumer behavior is marked by the ease of access and time flexibility offered by e-commerce platforms, as well as the existence of the review feature to assess products and services. However, with the ever-increasing number of reviews, consumers and store owners face challenges in sorting out relevant information. This research focuses on the multilabel classification of Indonesian e-commerce reviews. This research was undertaken because the application of multilabel classification, especially for e-commerce reviews in Indonesia, has received little attention. This research compares three classification models: end-to-end IndoBERT, IndoBERT-CNN, and IndoBERT-LSTM, to determine the most effective model for multilabel aspect classification of customer reviews. The multilabel classification method was applied to determine the aspect categories of the reviews, such as product, customer service, and delivery, using different thresholds for evaluation. Results show that 0.6 threshold is optimal, with the IndoBERT-LSTM model as the best-performing model for the multilabel aspect classification of these e-commerce reviews. Optimal classification of the model enables more precise information extraction from customer reviews. This can be useful for e-commerce businesses to gain insight from the reviews they get from customers. This insight can be used to find out which aspects need to be improved from the e-commerce business which leads to increased customer satisfaction and trust