Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control

Power Quality Improvement in Micro Hydro Power Plant Based-ELC and VSI using Fuzzy-PI Controller

Ilham Pakaya, Zulfatman, Amrul Faruq, Muhammad Irfan — Sat, 01 Feb 2025 00:00:00 +0000

The stability of frequency and voltage in micro hydro power plants (MHPP) depends on the ability to maintain balance between active and reactive power while managing load variations. Active power is typically regulated by an Electronic Load Controller (ELC), while reactive power is managed by a Voltage Source Inverter (VSI), with the VSI specifically compensating for reactive power induced by inductive loads. This study aims to enhance the control of active and reactive power in an MHPP system under varying load conditions by improving the ELC and VSI using Fuzzy-PI controller. The Fuzzy-PI controller applied in the ELC ensures a more precise TRIAC firing angle, enabling accurate control of the ballast load to balance the active power. Similarly, Fuzzy-PI controller applied in the VSI provides precise reactive power compensation to counteract inductive load effects. The performance of the proposed Fuzzy-PI-based ELC and VSI was evaluated using a complete MHPP model simulated in Matlab. Results demonstrated that the improved ELC and VSI effectively enhanced the system performance. Specifically, the Fuzzy-PI controller enabled the ELC to achieve accurate active power balance, while the VSI delivered suitable reactive power compensation. Consequently, the system achieved improved frequency and voltage stability under load variations, leading to enhanced power quality in the MHPP.

Implementation of Deep Learning Based on Convolution Neural Network for Batik Pattern Recognition

Edi Sugiarto, Fikri Budiman, Amiq Fahmi — Sat, 01 Feb 2025 00:00:00 +0000

Batik as a cultural heritage is one of the heritages that needs to be preserved so that it continues to be recognized from generation to generation. Efforts to preserve batik can be made by using technology that can recognize batik motifs. Pattern recognition is a branch of science related to the identification, classification, and interpretation of patterns. Deep learning is one of the technologies that can be used very well for pattern recognition, especially for syllable and image recognition. Convolutional neural network (CNN) is one of the most popular deep learning methods and the most established algorithm for deep learning models. The main advantage of CNN over the preceding methods is its ability to automatically detect features, making the feature extraction and classification process highly organized. This study aims to apply CNN for batik pattern recognition. The batik patterns used were geometric patterns, divided into 7 batik classes. Experiments were conducted on 3100 data, consisting of 3000 for training set and 100 for testing set. At the preprocessing stage, the batik image was resized to 28x28, and the color was changed to grayscale. Training was carried out on 100, 200, and 300 epochs. The classification results prove that CNN can recognize batik patterns well with an accuracy rate of 95%.

Analyzing Perceptron Algorithm for Global Gold Price Prediction using Quantum Computing Approach

Solikhun, Muhammad Rahmansyah Siregar — Sat, 01 Feb 2025 00:00:00 +0000

The price of gold has garnered significant attention in the world of finance and investment due to its role as a safe haven asset and an indicator of global economic stability. An inherent risk of investing in gold is the daily fluctuation in prices, which can rise, fall, or remain stable. Investors are constantly seeking accurate ways to predict gold price movements in order to make informed investment decisions. While classic algorithms like artificial neural networks have been used for gold price prediction, they often struggle with analyzing complex data and identifying the hidden patterns within large datasets. It is widely acknowledged that accurately and consistently predicting the gold price movements, exchange rate, and whether the gold price will rise or fall is very challenging. To address this challenge, this study explored the use of quantum perceptron algorithm for predicting global gold prices. This approach harnesses the principles of quantum computing to improve the efficiency and performance of neural network models. Quantum computers can perform multiple computations simultaneously, enabling the solution of problems that are difficult for classical computers. This study utilized global gold data from January 2018 to December 2022, with 80:20 split of training and testing data; data from January 2018 to December 2021 for training and data from January 2022 to December 2022 for testing. This study aims to offer insights into the potential and application of quantum algorithms in predicting gold prices. The research involved an analysis of global gold price predictions using the quantum perceptron algorithm and quantum computing.

Detecting Acute Lymphoblastic Leukemia in Blood Smear Images using CNN and SVM

Nelly Oktavia Adiwijaya, Sultan Ardiansyah, Dwiretno Istiyadi Swasono — Sat, 01 Feb 2025 00:00:00 +0000

Acute Lymphoblastic Leukemia (ALL) is a common and aggressive subtype of leukemia that predominantly affects children. Accurate and timely diagnosis of ALL is critical for successful treatment, but it is hindered by the limitations of manual examination of peripheral blood smear images, which are prone to human error and inefficiency. This study proposes an improved diagnostic approach by integrating the EfficientNet architecture with a Support Vector Machine (SVM) classifier to enhance classification accuracy and address the performance inconsistencies of standalone EfficientNet models. Additionally, a novel CNN-based model with a reduced number of parameters is developed and evaluated. A dataset comprising 3.256 peripheral blood smear images across four classes (benign, early, pre and pro) was used for training and testing. The EfficientNet-SVM models achieved a peak accuracy of 97.35% using the EfficientNet-B3 architecture, surpassing previous studies. The improved CNN model achieved the highest accuracy of 99.18% while reducing parameters by 59.5% compared to the best prior models, with a negligible accuracy decrease of only 0.67%. These findings highlight the potential of combining EfficientNet with SVM and the efficiency of the improved CNN model for automated ALL detection, paving the way for more reliable, cost-effective, and scalable diagnostic tools.

Design and Implementation of Two-phase Boost Inverter using Interleaved Method to Increase Output Current

Fahrul Indra Setiyawan, Leonardus Heru Pratomo — Sat, 01 Feb 2025 00:00:00 +0000

The 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.

Integrating Ensemble Learning and Information Gain for Malware Detection based on Static and Dynamic Features

Ramadhan Rakhmat Sani, Fauzi Adi Rafrastara, Wildanil Ghozi — Sat, 01 Feb 2025 00:00:00 +0000

The rapid advancement of malware poses a significant threat to devices, like personal computers and mobile phones. One of the most serious threats commonly faced is malicious software, including viruses, worms, trojan horses, and ransomware. Conventional antivirus software is becoming ineffective against the ever-evolving nature of malware, which can now take on various forms like polymorphic, metamorphic, and oligomorphic variants. These advanced malware types can not only replicate and distribute themselves, but also create unique fingerprints for each offspring. To address this challenge, a new generation of antivirus software based on machine learning is needed. This intelligent approach can detect malware based on its behavior, rather than relying on outdated fingerprint-based methods. This study explored the integration of machine learning models for malware detection using various ensemble algorithms and feature selection techniques. The study compared three ensemble algorithms: Gradient Boosting, Random Forest, and AdaBoost. It used Information Gain for feature selection, analyzing 21 features. Additionally, the study employed a public dataset called ‘Malware Static and Dynamic Features VxHeaven and VirusTotal Data Set’, which encompasses both static and dynamic malware features. The results demonstrate that the Gradient Boosting algorithm combined with Information Gain feature selection achieved the highest performance, reaching an accuracy and F1-Score of 99.2%.

An Ensemble Learning Layer for Wayang Recognition using CNN-based ResNet-50 and LSTM

Candra Irawan, Eko Hari Rachmawanto, Heru Pramono Hadi — Sat, 01 Feb 2025 00:00:00 +0000

Wayang 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

Nenden Nuraeni, Muhammad Faisal — Sat, 01 Feb 2025 00:00:00 +0000

Sleep 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.

A Hybrid Encryption using Advanced Encryption Standard and Arnold Scrambling for 3D Color Images

Wellia Shinta Sari, Erna Zuni Astuti, Cahaya Jatmoko — Sat, 01 Feb 2025 00:00:00 +0000

Digital 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.

Performance Comparison of Machine Learning Algorithms for Ikat Weaving Classification

Moch. Sjamsul Hidajat, Dibyo Adi Wibowo, Ery Mintorini — Sat, 01 Feb 2025 00:00:00 +0000

Ikat weaving is a rich traditional heritage of Kota Kediri, Indonesia, with a diverse array of intricate motifs that reflect the cultural richness of the region. As new motifs emerge and information about older designs fades, manual identification becomes time-consuming and difficult. This study leverages machine learning technology, specifically XGBoost, Random Forest, and Neural Network algorithms, to automate the classification of these weaving patterns. The dataset consisted of 600 images, split into 480 images (80%) for training and 120 images (20%) for testing, representing four distinct weaving motifs: "Gumul Weaving, Bolleches Weaving, Kuda Kepang Weaving, and Sekar Jagad Weaving." The study achieves high accuracy, with precision, recall, and F1-score all reaching 100%, underscoring its potential to not only improve the efficiency of motif identification, but also play a crucial role in preserving and promoting Indonesia's cultural heritage. Future research should focus on further optimizing these algorithms and expanding datasets to capture a broader range of ikat motifs. Additionally, enhancing the application of this model can contribute to a deeper understanding and broader appreciation of Kota Kediri’s cultural wealth through digital platforms.

Aspect-based Multilabel Classification of E-commerce Reviews using Fine-tuned IndoBERT

Fahrendra Khoirul Ihtada, Rizha Alfianita, Okta Qomaruddin Aziz — Sat, 01 Feb 2025 00:00:00 +0000

In 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.

How HEXAD Types Influence Systemic and Finer-Grained Experiences in Gameful Educational Media: An Exploratory Study

Sugiarto, Pratama Wirya Atmaja, Eka Prakarsa Mandyartha — Sat, 01 Feb 2025 00:00:00 +0000

Education in the 21st century demands technology support, in which gameful media, such as educational games, can provide. Providing this support also requires the media to accommodate the different needs of the players, which can be identified by classifying the players’ type using HEXAD typology. However, the effect of HEXAD type classification on players’ experience in gameful media is still vague. This study aims to adress this vagueness by exploring the implementation of HEXAD in a more systemic and fine-grained manner using a playtest of an educational role-playing game. We measured the playtesters’ gameplay and learning experiences (n = 60) through a questionnaire developed based on HEXAD scale, GUESS, and EGameFlow. We also measured the correlation between the playtesters’ HEXAD types and their gameplay and learning experiences. Our analysis of the correlations uncovers exciting findings, including that the “achiever” type strongly appreciates playability features and that playability is among the essential gameplay factors for HEXAD types. We also propose design principles that can guide future research and development of the media.