Jurnal Nasional Teknik Elektro dan Teknologi Informasi

Learning Rate Analysis for Pain Recognition Through Viola-Jones and Deep Learning Methods

2024-06-26T13:27:53+07:00

Deep learning is growing and widely used in various fields of life. One of which is the recognition of pain through facial expressions for patients with communication difficulties. Viola-Jones is a simple algorithm that has real-time detection capabilities with relatively high accuracy and low computational power requirements. The learning rate is a significant number that has an impact on the deep learning result. This study recognized pain using the Viola-Jones and deep learning methods. The dataset used was a thermal image from the Multimodal Intensity Pain (MIntPAIN) database. The steps taken consisted of segmentation, training, and testing. Segmentation was conducted using the Viola-Jones method to get the significant area of the face image. The training process was carried out using four deep learning benchmarks model, which were DenseNet201, MobileNetV2, ResNet101, and EfficientNetb0. Besides that, deep learning has a very important number to determine that is learning rate, which impact the deep learning results. There were five learning rates, which were 10^-1, 10^-2, 10^-3, 10^-4, and 10^-5. Learning rate values were then compared with four deep models learning to obtain high accuracy results in a short time and simple algorithm. Finally, the testing process was carried out on test data using a deep learning benchmark model in accordance with the training process. The research results showed that a learning rate of 10^-2 from the MobileNetV2 method produced an optimal performance with a training validation accuracy of 99.60% within a time of 312 min and 28 s.

Electric Boat Propulsion with IPM BLDC Motors: Performance and Efficiency Analysis

2024-06-26T13:27:47+07:00

Air pollution, particularly the presence of PM2.5 particles, remains a global health concern. While Indonesia exhibits lower PM2.5 levels than the global average, vehicular emissions significantly contribute to air pollution. In light of environmental and health considerations, adopting eco-friendly electric motors, mainly interior permanent magnet brushless direct current (IPM BLDC) motors, represents a promising solution for cleaner and more efficient boat propulsion systems, benefiting both the environment and the livelihoods of fishermen. This study thoroughly examines the efficiency and performance of IPM BLDC motors in boat propulsion, utilizing finite element analysis (FEA) through ANSYS Maxwell. The FEA simulations in ANSYS Maxwell were tailored to focus on crucial design variables such as motor torque, speed, and thermal management. It aimed to ensure that the motor specifications meet electric boats’ operational needs in fishing and search operations. Notably, at the desired speed of 5,000 rpm, the motor achieved a torque of 15 Nm with a cogging torque of just 7% and maintained an average efficiency of 89%. Significantly, it operated at a safe temperature without requiring additional cooling systems. Furthermore, simulation outcomes suggested that the motor could effectively function at higher speeds, specifically 6,300 rpm, presenting an exciting opportunity to enhance boat propulsion systems through increased motor speed.

Confusion and Diffusion Techniques for Image Encryption Process Based on Chaos System

2024-06-26T13:27:43+07:00

Face recognition uses biometric technologies to identify humans based on their facial characteristics. This method is commonly used to restrict information access control. The benefits of face recognition systems encompass their ease of use and security. The human face recognition process consists of face detection, face tracking, and face recognition. The process uses some algorithms: the Viola-Jones for face detection, the Kanade-Lucas-Tomasi (KLT) for face tracking, and the principal component analysis (PCA) for face recognition. Furthermore, this research proposed face recognition with an encryption process to protect the data stored in a database. The encryption process consists of two main processes: confusion and diffusion. The confusion process is randomizing the position of the original image pixels. This research utilized the Arnold’s cat map (ACM) for the confusion process, and the diffusion process was performed using the XOR operation with the key generated from the 1D chaos system. Three different 1D chaos systems, namely logistic map, Bernoulli map, and tent map, were compared to see which chaos system had the best encryption results. Tests were conducted by comparing various parameters on the three proposed 1D chaos systems, including correlation coefficient, histogram analysis, entropy value, number of pixel rate changes (NPCR), and unified average change intensity (UACI). Based on testing the image encryption results, the diffusion process utilizing the tent map produced the best image encryption compared to other chaotic systems.

Performance Analysis of gNMI Streaming Telemetry-Based Monitoring Systems Using Containerlab Network Simulation

2024-06-26T13:27:33+07:00

The rapid growth of the Internet has impacted the digital service development. This surge in demand has created opportunities for digital service industry players. Despite its positive impact, the growth of the Internet also poses technical challenges. In managing the increasing data traffic, resource monitoring plays a vital role. One of the latest methods for monitoring these resources is the utilization of the Google’s Remote Procedure Call (gRPC) Network Management Interface (gNMI) streaming telemetry system. While it seems superior to current protocols, there is a need for further exploration into the implementation of streaming telemetry systems. This paper specifically investigates the trade-offs and performance of gNMI streaming telemetry. The design and simulation were conducted utilizing containerlab, a Docker-based networking lab tool. In the Docker-based simulation, integration between the monitoring system and network topology was implemented. The results from observing each protocol indicate that the monitoring system’s metric retrieval activity had minimal impact on network conditions. This is evident in the consistently low average network latency and nearly uniform throughput, except in instances of packet loss and congestion. Simulation observations indicate that the gNMI monitoring system utilized input/output (I/O) resources more intensively compared to other protocols. The research also examined the integration of gNMI streaming telemetry and log monitoring, revealing a 70 MB rise in memory usage and a 33% increase in Disk I/O resources. Furthermore, the study uncovered signs of a 50% increase in CPU utilization by the gNMI monitoring system compared to the average data recorded in the observations.

Optimization of the KNN Algorithm through Outlier Analysis Comparison (Distance, Density, LOF-Based)

2024-06-26T13:27:38+07:00

The current data growth affects data analysis in various fields, such as astronomy, business, medicine, education, and finance. The collected and stored data contain extreme values or observation values different from most other observation value results. These extreme values are called outliers. Outliers on some data often hold valuable information, necessitating thorough examination to determine whether to retain or discard them prior to data mining application. Outlier detection can be performed as a part of data preprocessing using outlier analysis techniques. Commonly utilized outlier analysis techniques encompass distance-based methods, density-based methods, and the local outlier factor (LOF) method. k-nearest neighbors (KNN) are a data mining algorithm susceptible to outliers due to its reliance on the value of k. Hence, having an appropriate handling mechanism is essential when employing KNN on datasets that contain outliers. The experimental method was selected to apply the proposed approach, aiming to optimize the KNN algorithm through a comparison of outlier analysis methods (KNN-distance, KNN-density, and KNN-LOF). The results revealed that KNN-density outperformed the others significantly: achieving an average accuracy of 99.34% at k=3 and k=5 for Wisconsin Breast Cancer, 85.25% at k=7 for Glass, and 85.45% at k=5 for Lymphography. Moreover, both the Friedman and Nemenyi tests validate a notable distinction between KNN-density and KNN-LOF.

Performance Evaluation of 600 kWp On-Grid Solar Power Plant on Gili Trawangan

2024-06-26T13:27:29+07:00

Indonesia is one of the countries that remains reliant on the utilization of fossil energy. The increasing demand for fossil energy is causing a decrease in the availability of fossil energy, consequently leading to an increase in fossil fuel prices. Therefore, one of the efforts that can be undertaken involves establishing new renewable energy (NRE) plants to diminish reliance on the use of fossil-fueled plants. One of the NRE plants built by the government is the 600 kWp Gili Trawangan On-Grid solar power plant. After ten years of operation, an evaluation of the 600 kWp Gili Trawangan On-Grid solar plant is necessary to assess its performance in meeting electricity load requirements. The power and electrical energy generated by a solar power plant can be evaluated by comparing its current power and energy production with the potential power and energy that should be generated. To determine the current power and energy production generated by the solar power plant, the measurement results from the PLN. Additionally, to ascertain the potential power and energy that the solar power plant should be capable of producing at this time, simulation results from Homer software were employed. The results demonstrate that the power and energy measured by PLN are lower than the potential power and energy that should be achievable using Homer software for solar power plants. According to PLN measurement, the average power production and energy were 196.72 kW and 765.92 kWh, respectively. Meanwhile, based on the simulation results were 207.10 kW and 840.39 kWh.

Effects of Codebook Design Weighting on Sparse Code Multiple Access System Performance

2024-06-26T13:27:25+07:00

Sparse code multiple access (SCMA) can support the system when overloading on the receiving side, thereby improving the system’s spectral efficiency by designing mapping symbols appropriately. The performance of SCMA is assessed through the utilization of a sparse codebook, wherein bits are directly mapped to multidimensional codewords influenced by both the energy diversity and the minimum Euclidean distance of the multidimensional constellation (MC). The codebook design simulation was conducted using both Latin and non-Latin generators with phases of 60° and 45°, incorporating weighting values of w₁ = 0.6; w₂ = 0.3; w₃ = 0.1. The simulation also included line constellation with additive white Gaussian noise (AWGN) channel, Rayleigh fading, and Rician channel. This study presented the optimal results across three channels: Latin 60° with BER 10⁻³in the AWGN channel, non-Latin 60° with BER 10⁻³in the Rayleigh fading, and non-Latin 45° with BER 10⁻³ in the Rician channel. Then, the results on the codebook design weighting were as follows: Latin 60° with BER 10⁻¹ in the AWGN channel, non-Latin 45° with BER 10⁻¹in the Rayleigh fading, and Latin 45° with BER 10⁻³in the Rician channel. The simulation results state the effect of weighting on each channel. It was found that Latin generators could improve BER performance by suppressing overlap at constellation points and eliminating errors occurred in SCMA codebooks. However, this improvement was observed only in AWGN channels and not for non-Latin generators.

Modeling Climate Change Issues in Indonesia Based on Media Headlines

2024-06-26T13:27:21+07:00

Climate change has become a global issue affecting all countries in the last decades. This phenomenon poses a concern to Indonesia as it is one of the climate change’s epicenters. Various studies have shown that climate change can harm multiple community activities, such as unstable agricultural production, decreased people’s health, and global warming. This study tried to model and analyze climate change topics discussed in the media. Finding hidden topics from texts can provide clues and information regarding public conversation surrounding climate change, such as public thoughts, perceptions, and readiness to mitigate the possible adverse effects of climate change. In order to identify hidden subjects from the corpus, this work modeled climate change issues in Indonesia using the latent Dirichlet allocation (LDA) algorithm to analyze texts from Indonesian media headlines. As many as 7,000 headline data from five online media were collected from 2017 to 2021 using web scraping techniques. The proposed approach produced eight topics related to climate change, which were determined by the highest coherence value of 0.560. Those topics were renewable energy, carbon emissions, environmental management, development economics, international cooperation, policy/regulation, rehabilitation, and disaster. Based on the results, the model could sufficiently describe the theme of discussion in society and photograph public thoughts and the government’s readiness in the form of policies and regulations in dealing with the climate change phenomenon.

Entity and Relation Linking for Knowledge Graph Question Answering Using Gradual Searching

2024-06-26T13:27:17+07:00

Knowledge graph question answering (KGQA) systems have an important role in retrieving data from a knowledge graph (KG). With the system, regular users can access data from a KG without the need to construct a formal SPARQL query. KGQA systems receive a natural language question (NLQ) and translate it into a SPARQL query through three main tasks, namely, entity and relation detection, entity and relation linking, and query construction. However, the translation is not trivial due to lexical gaps and entity ambiguity that may occur during entity or relation linking. This research proposed an approach based on multiclass classification of NLQ whose entity occurrences are detected into categories based on KG relations to address the lexical gap challenge. Next, to solve the entity ambiguity challenge, this research proposed a three-stage searching procedure to determine appropriate KG entities associated with the NLQ entities, given the correspondence between the NLQ and a particular KG relation. This three-stage searching consisted of text-based searching, vector-based searching, and entity and relation pairing. The proposed approach was evaluated on the SimpleQuestions and LC-QuAD 2.0 datasets. The experiments demonstrated that the proposed approach outperformed the state-of-the-art baseline. For the relation linking task, the proposed approach reached 89.87% and 74.83% recall for the SimpleQuestions and LC-QuAD 2.0, respectively. This approach also achieved 91.74% and 61.96% recall on the entity linking tasks for the SimpleQuestions and LC-QuAD 2.0, respectively.

AHP TOPSIS Analysis in Selecting Waste Processing Technology Based on Energy Justice

2024-06-26T13:27:13+07:00

The amount of waste in Bantul Regency increased by 4.96% from 2020 to 2021, indicating that the capacity of final disposal sites (FDS) in Piyungan District, Bantul Regency, was decreasing. The peak occurred from 23 July 2023 to 5 September 2023, during which the Piyungan FDS could not provide waste disposal services. The high poverty rate in Bantul Regency forces the government to process waste into energy as a sustainable waste management effort. However, numerous criteria make it difficult to determine which technology is most suitable for this purpose. Energy justice criteria need to be considered when choosing technology and efforts to improve the welfare of Bantul Regency's residents. This research aimed to present an assessment of each alternative technology for processing waste into energy and decide one suitable alternative for sustainable waste management in Bantul Regency using a combination of AHP and TOPSIS methods based on energy justice. AHP was used to assess the level of importance of each criterion, while TOPSIS was used to determine the optimal alternative based on the criteria by considering costs and benefits. The findings showed that the preference value for three alternatives was 0.579, 0.414, and 0.341 for incineration, pyrolysis, and gasification, respectively. According to these preference value, incineration was identified as the foremost viable alternative technology for implementation in Bantul Regency. Gasification and pyrolysis ranked as the subsequent and third alternatives, respectively.

Front Pages

2024-06-27T13:06:58+07:00

Back Pages

2024-06-27T13:11:36+07:00