Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Unraveling the relationships among essential oil compounds in Aquilaria species using GC-MS and GC-FID techniques
Get PDFAgarwood, a prized non-timber resource from the Aquilaria genus, is highly valued for its aromatic and medicinal properties, playing a significant role in the healthcare, fragrance, and pharmaceutical industries. This research analyzes essential oils from four Aquilaria species-A. beccariana, A. malaccensis, A. crassna, and A. subintegra-using gas chromatography-mass spectrometry (GC-MS) and gas chromatography-flame ionization detection (GC-FID). The primary objective is to optimize classification efficiency by reducing computational time and reducing multicollinearity through feature selection. Pearson correlation analysis revealed strong relationships among six chemical compounds-β-selinene (A), dihydro-β-agarofuran (B), δguaiene (C), 10-epi-γ-eudesmol (D), γ-eudesmol (E), and pentadecanoic acid (F). Through feature selection, the three most significant compoundsdihydro-β-agarofuran (B), γ-eudesmol (D), and 10-epi-γ-eudesmol (E)-were identified, achieving a remarkable 90.02% reduction in computational time (from 0.0403 to 0.0040 seconds). These findings highlight the effectiveness of structured feature selection in refining essential oil profiling and enhancing species classification accuracy. Future research directions include exploring machine learning-based feature selection techniques to further streamline feature reduction processes and expand the scope of essential oil authentication. This study contributes to advancing the scientific understanding and practical utilization of agarwood essential oils, paving the way for more efficient and reliable analytical frameworks
The design of an electronic load for mitigating transient overvoltage in the track circuits of railway signaling systems
Get PDFThe research presented the design of safety electronic load suppression (SELS) for mitigating transient overvoltage in the track circuits of railway signaling systems while changing the track occupancy in the track circuits of the signaling system that caused damage to the BR966F2 relay. The analysis of the average failure of the electronic devices, the failure modes and effect analysis (FMEA), and the performance test of electronic devices were conducted. and the performance test of electronic devices were conducted. which can control the operation with 2oo3 processing mode (two out of three voting) under the series circuits pattern to resolve the damage caused by the application. Results illustrated that the mean operating time of the SELS between failures was 9,399 hours. In addition, regarding the performance of the electronic load for mitigating transient overvoltage of 1 kV at 31.4 V and overvoltage 50 VDC at 178.6 °C within 83 seconds at 35.4 V. Additionally, the SELS could function adequately without failure or causing any damage. Therefore, the SELS was more reliable
Interrogative insights into depression detection via social networks and machine learning techniques
Get PDFAs users on social networks (SNs) interact with one another by exchanging information, giving feedback, finding new content, and participating in discussions; thus, generating large volumes of data each day. This data includes images, texts, videos and can be used to help the user find out how they have been doing, when they were depressed, how not to be depressed, and other similar insights. Depression is one of the most common chronic illnesses and it has emerged as a global mental health problem. But the lack of these data is incomplete, sparse and sometimes inaccurate, and so the task of diagnosing depression using automated systems is still proving a challenge. Various techniques have been used to detect depression through the years however, machine learning (ML) and deep learning (DL) techniques offer better ways. In the context of that, this study reviews state-of-the-art ML and DL approaches for the detection of depression using systematic literature review (SLR) method as well as highlight fundamental challenges in literature, which future works can focus on. We hope that this survey will provide a better understanding of these strategies for the readers and researchers in the ML and DL fields, when it comes to diagnosis of depression
Improved counterplan for interference in same-band information transmission and reception
Get PDFWireless communication technologies operating in the 2.4 GHz band, such as Wi-Fi, Bluetooth, ZigBee, and others, often face challenges related to mutual interference. These technologies share the same unlicensed frequency spectrum, which can lead to various types of interference, affecting performance, reliability, and data throughput. This paper addresses the issue of mutual interference in communications occurring within frequency bands commonly used in daily life. Through this, it conducts an in-depth study on information processing between wireless devices and the control of communication components. Specifically, it examines interference phenomena in the widely used 2.4 GHz band by analyzing communication methods where such interference is likely to occur. By investigating the characteristics of Wi-Fi, Bluetooth, and ZigBee, this study analyzes interference phenomena and proposes an algorithm to mitigate them. To mitigate this, this paper proposes a multi-layered method integrating adaptive filtering, dynamic frequency allocation, advanced error correction, and intelligent scheduling mechanisms
Autoencoder-based Gaussian mixture model for diagnosing early onset of diabetic retinopathy
Get PDFThe current study presents a simplified yet innovative solution towards effective early diagnosis of diabetic retinopathy (DR) that leads to irreversible blindness. A review of current literature shows a considerable number of machine learning and deep learning approaches have been presented; however, there are significant issues with the early detection of DR. Hence, the proposed study deploys a novel architecture using an autoencoder that extracts a hidden representation of retinal images while binary classification is carried out using a Gaussian mixture model. The prime contribution is the joint integration of deep learning with statistical modelling towards efficient feature extraction and anomaly detection, supporting early determination of DR. The study outcome shows a proposed system to significantly exhibit 96.5% accuracy, 94.2% sensitivity, and 98.3% specificity on two standard benchmarked datasets in comparison to existing models frequently used for the diagnosis of DR
Analysis and modeling of a pneumatic artificial muscle system
Get PDFHysteresis is a common challenge in achieving precise position control of pneumatic artificial muscles (PAMs). Accurate modeling of this phenomenon is essential for the development of efficient PAM control systems. This study evaluates four mathematical models for modeling PAM dynamics: Nonlinear AutoRegressive with eXogenous inputs (NARX), BoxJenkins (BJ), Prandtl-Ishlinskii (PI), and second-order underdamped system and one zero (P2UZ). To assess the effectiveness of these models, experiments were conducted with reference input signals of varying amplitudes. The accuracy and goodness of fit of these models were evaluated based on root mean square error (RMSE) and coefficient of determination. Results show that the P2UZ model achieved the highest fitness (97.15%) and the lowest RMSE (1.80 mm), followed closely by the NARX model with 96.83% fitness and an RMSE of 1.90 mm. The PI and BJ models demonstrated lower performance, with the BJ model showing the lowest fitness (90.79%) and the highest RMSE (3.25 mm). These findings provide valuable insights for improving PAM control and PAM-based automation systems by highlighting the strengths and limitations of each model
Random forest method for predicting discharge current waveform and mode of dielectric barrier discharges
Get PDFThis study addresses the classification of Homogeneous and Filamentary discharge modes in dielectric barrier discharge (DBD) systems and predicts the Homogeneous current waveform using machine learning (ML). The motivation stems from the need for accurate modelling in non-thermal plasma systems. The problem tackled is distinguishing between these two modes and predicting the current waveform for Homogeneous discharge. A random forest classification algorithm is applied, using experimental features such as applied voltage, frequency, gas gap, dielectric material, and gas type. An exponential model is proposed for the discharge current, with Gaussian regression transforming the model’s parameters. The classification results are evaluated through a confusion matrix, showcasing 80% accuracy in distinguishing discharge modes. The regression analysis reveals strong Pearson correlation coefficients between predicted and experimental waveforms. In conclusion, the results demonstrate the efficacy of ML techniques in enhancing DBD system modelling, though improvements can be made by expanding the dataset and refining feature selection for better classification and prediction performance
Neural control of DVR for wind turbine grid fault mitigation with PIL validation
Get PDFPower quality issues that include voltage sag and swell challenge grid stability, not least for renewable energy systems such as wind turbines (WTs). Occurrence of these voltage disturbances impacts severely the performance of WT systems, compromising their fault ride-through (FRT) capabilities. This work investigates the application of an artificial neural network (ANN) as a controller mechanism for a dynamic voltage restorer, aimed at improving the FRT capabilities of a WT equipped with a permanent magnet synchronous generator. The approach includes employing series compensation to maintain the terminal voltage of the WT during fault conditions. This is performed by injecting voltage at the interface where the system connects to the grid, thus stabilizing the terminal voltage within the wind energy system. The control of the dynamic voltage restorer (DVR) is fundamental to improve the FRT capability. An ANN approach, as control technique is applied to drive the DVR. Training data used for ANN are obtained from a proportional-integral controller, and the proposed system is comprehensively modeled with MATLAB/Simulink. The proposed method demonstrates effective voltage restoration, under two fault scenarios: voltage sag and swell. Besides, the processor in-the-loop (PIL) test proves that the suggested control is practically implementable
RIBATS: RSSI-based adaptive tracking system with ASEKF for indoor WSN
Get PDFWireless indoor tracking systems face challenges due to environmental conditions and signal attenuation, affecting location accuracy, crucial in wireless sensor network (WSN) applications. Many tracking techniques rely on specific path loss models proposed by previous researches, but these models are susceptible to changes in environmental conditions, impacting estimation outcomes. In order to solve these problems, this paper propose adaptive tracking system using received signal strength indicator (RSSI) measurement parameter called as RIBATS. Adaptive in this system refers to the reliability of an algorithm for obtaining the accurate location without any path loss modelling at dynamic indoor environments. The enhancement of weighted centroid localization (eWCL) scheme calculates the location estimation only using RSSI data measurement without propagation characterisic determination. However, estimation result from eWCL still have high error at certain area. Hence, by defining a multiplier factor as adaptive scaled to the covariance matrix of EKF can eliminate distortion effects from eWCL called as adaptive scaled extended Kalman filter (ASEKF) algorithm. An effective variance estimation algorithm for adaptive indoor tracking system using eWCL and ASEKF combination achieve 0.82 meters mean square error (MSE) value with 55.67% error reduction. Then, without using multiplier scale factor at EKF algorithm only reduce previous eWCL at 3.78% with 1.78 meters MSE value
An improved conversation emotion detection using hybrid f-nn classifier
Get PDFEmotion recognition from text is a crucial task in natural language processing (NLP) with applications in sentiment analysis, human-computer interaction, and psychological research. In this study, we present a novel approach for text-based emotion recognition using a modified firefly algorithm (MFA). The firefly algorithm is a swarm intelligence method inspired by the bioluminescent communication of fireflies, and it is known for its simplicity and efficiency in optimization tasks. In this paper MFAbased model is evaluated on the international survey on emotion antecedents and reactions (ISEAR) dataset, which includes text entries categorized by various emotions. Experimental results indicate that our approach achieved promising outcomes. Specifically, the proposed method, which combines the firefly algorithm with a multilayer perceptron (MLP), attained an accuracy of 92.07%, surpassing most other approaches reported in the literature