KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 20

Some of the metrics are blocked by your
consent settings
Comparative Analysis of Deep Learning Models for Daily Solar Indices Forecasting in Solar Cycle 25
(2025-01-01)
Min Myint, Lin Min
;
Mutasov, Gleb
;
Supnithi, Pornchai
;
Budtho, Jirapoom
Accurate forecasting of solar activity indices, particularly the Sunspot Number (SSN) and the F10.7 solar radio flux index (F10.7), is essential for effective space weather monitoring, as severe solar and ionospheric disturbances can significantly impact satellite operations, radio communications, and navigation systems. This paper presents a comparative analysis of deep learning models - Long Short-Term Memory (LSTM), Temporal Convolutional Networks (TCN), and encoder-only Transformer architectures - for daily forecasting of SSN and F10.7 up to 14 days ahead based on past 27 days. Considering relatively simple model structures, both single-step and multi-step prediction strategies are explored to evaluate the models' capability in handling short-and long-term dependencies in time series data. Daily solar activity data spanning seven solar cycles (Cycles 19-25), obtained from the GFZ Helmholtz Centre for Geosciences, are used for model training and evaluation. Experimental results show that LSTM consistently achieves the best performance across most forecast horizons, particularly in short-to medium-term predictions. The Transformer model delivers competitive and stable results, while TCN performs relatively less effectively, indicating the need for more complex architecture and optimization strategies. These findings highlight the strengths and limitations of each architecture for solar activity forecasting applications.
Some of the metrics are blocked by your
consent settings
Predicting Equatorial Ionospheric Total Electron Content Using the Transformer-based Model with Observations From Ground GNSS Receivers and COSMIC-2 Satellites
(2025-01-01)
Mutasov, Gleb
;
Supnithi, Pornchai
;
Budtho, Jirapoom
;
Perwitasari, Septi
;
Nishioka, Michi
Ionospheric Total Electron Content (TEC) is a key parameter for monitoring and studying the ionosphere, which induces significant delays in radio signals. Equatorial ionospheric irregularities, such as Equatorial plasma bubbles (EPB), can severely disrupt satellite navigation and communication. Predicting TEC is, therefore, essential for space weather monitoring and high-precision positioning applications. This study employs a Transformer-based model to predict TEC 24 hours in advance for specific satellites based on observations from a ground station and COSMIC-2 satellites. Unlike other approaches, our model directly forecasts TEC values for visible satellites within predefined longitude-latitude ranges. To enhance predictive accuracy, we also integrate additional features: ionospheric pierce points (IPP), geomagnetic (HP60), and solar activity indices, utilizing time-series Transformer architecture, and we consider a long-short-term memory (LSTM) model as a baseline. The proposed approach provides promising results for local TEC forecasting in the specific coverage area, with potential for further enhancements using additional GNSS or TEC measurements.
Some of the metrics are blocked by your
consent settings
ASR Error Correction in Low-Resource Burmese with Alignment-Enhanced Transformers Using Phonetic Features
(2025-01-01)
Lin, Ye Bhone
;
Aung, Thura
;
Thu, Ye Kyaw
;
Oo, Thazin Myint
This paper investigates sequence-to-sequence Transformer models for automatic speech recognition (ASR) error correction in low-resource Burmese, focusing on different feature integration strategies including IPA and alignment information. To our knowledge, this is the first study addressing ASR error correction specifically for Burmese. We evaluate five ASR backbones and show that our ASR Error Correction (AEC) approaches consistently improve word- and character-level accuracy over baseline outputs. The proposed AEC model, combining IPA and alignment features, reduced the average WER of ASR models from 51.56 to 39.82 before augmentation (and 51.56 to 43.59 after augmentation) and improving chrF++ scores from 0.5864 to 0.627, demonstrating consistent gains over the baseline ASR outputs without AEC. Our results highlight the robustness of AEC and the importance of feature design for improving ASR outputs in low-resource settings.
Some of the metrics are blocked by your
consent settings
MS-PatchTST: Leveraging Multi-Scale Temporal Features for Water Level Forecasting
(2025-01-01)
Zhang, Dong
;
Pasupa, Kitsuchart
;
Liu, Zongying
;
Pan, Mingyang
Accurate water level forecasting is essential for navigation, enabling safe sailing, effective drought management, optimized route planning, and efficient port operations. However, traditional statistical approaches and conventional machine learning models often struggle to capture adaptive, multi-scale temporal features, thereby limiting forecasting accuracy. In recent years, patch-based forecasting methods have demonstrated strong capabilities in modeling consecutive temporal features. Building on this foundation, we propose Multi-Scale PatchTST (MS-PatchTST), a framework designed to enhance the perception of multi-scale information. The model incorporates a newly developed multi-scale parallel convolutional network (Multi-Scale ConvNet) to extract interaction features across different time scales. These features are then fused through a Transformer Encoder with relative positional encoding to capture temporal dependencies more effectively. Finally, the kernel mean squared error loss function is employed in place of the conventional mean squared error loss, improving the optimization process and enhancing overall training performance. Experiments on four real-world water level datasets demonstrate that MS-PatchTST consistently outperforms state-of-the-art baselines, achieving an average reduction of approximately 13% in both MAE and SMAPE compared with PatchTST.
Some of the metrics are blocked by your
consent settings
Fourier Latent Transformer for Anomaly Signal with High-Frequency Reconstruction
(2025-01-01)
Chalongvorachai, Thasorn
;
Woraratpanya, Kuntpong
Anomaly-related applications play a crucial role in real-world systems. However, developing effective solutions remains challenging, particularly due to missing data caused by system errors during anomaly events. Several approaches have been proposed to address this issue, including statistical methods, autoencoders, and deep learning models such as Transformers and Latent Transformers. Despite their potential, these methods often struggle to preserve high-frequency signal characteristics or require extensive training time and computational resources. To overcome these challenges, this paper proposes the Fourier Latent Transformer for Anomaly Signal with High Frequency Reconstruction. The method integrates Fourier positional encoding, which enhances the model's ability to retain high-frequency components, with a Latent Transformer architecture that reduces the need for computational resources and shortens training time. This approach not only effectively reconstructs missing highfrequency anomaly signals, but also improves overall training efficiency. Experimental results on real-world datasets show that the proposed method tremendously reduces error in anomaly data imputation, while maintaining training time comparable to baseline models.
Some of the metrics are blocked by your
consent settings
FastThaiCaps: A Transformer Based Capsule Network for Hate Speech Detection in Thai Language
(2023-01-01)
Maity, Krishanu
;
Bhattacharya, Shaubhik
;
Saha, Sriparna
;
Janoai, Suwika
;
Pasupa, Kitsuchart
The advent of technology has led to people sharing their views openly like never before. Parallelly, cyberbullying and hate speech content have also increased as a side effect that is potentially hazardous to society. While plenty of research is going on to detect online hate speech in English, there is very little research on the Thai language. To investigate how noisy Thai posts can be handled effectively, in this work, we have developed a two-channel deep learning model FastThaiCaps based on BERT and FastText embedding along with a capsule network. The input to one channel is the BERT language model, and that to the other is the pre-trained FastText embedding. Our model has been evaluated on a benchmark Thai dataset categorized into four categories, i.e., peace speech, neutral speech, level-1 hate speech, and level-2 hate speech. Experiments show that FastThaiCaps outperforms state-of-the-art methods by up to 3.11% in terms F1 score.
Some of the metrics are blocked by your
consent settings
Biological Insulating Liquids: New Insulating Liquids for High Voltage Engineering
(2023-01-01)
Pagger, Ernst Peter
;
Pattanadech, Norasage
;
Uhlig, Frank
;
Muhr, Michael
This book describes the state-of-the-art use of biological insulating liquids in detail. In recent years, more and more transformers filled with esters have been put into operation. This is because people recognize the benefits of ester liquids in terms of their fire safety (high flash and fire points) and environmental characteristics, judging from their biodegradability, their low CO2 footprint (only valid for natural ester) and their beneficial interactions with solid insulation, etc. One of the main reasons is that the water adsorption and absorption characteristics of these liquids are excellent and very different compared to mineral oil. The today’s discussion about climate change and global warming is an additional driver for using natural ester. Another advantage is that transformers filled with biological insulating liquids can operate with an overload of up to 150%. This is advantageous in the case of volatile energy generation from wind and solar power and in the supply of electrical energy for electromobility. Liquid inside electrical equipment is the lifeblood that serves both as a dielectric and a cooling medium. Some properties of these liquids differ from mineral oil, which had to be considered in the transformer design. The dielectric liquid is always in direct contact with transformer materials; therefore, the interaction should be very well understood, especially when retrofilling an existing mineral oil filled device. There are several natural ester fluids derived from various seeds and fruits on the market, and their properties may differ more or less. In the book, the most important properties of the different biological insulating fluids and mineral oil are compared. Ester fluids have already found their way into various standards. The condition of the device can be verified very well from the contents of the insulating liquids. For analysis and testing, the same equipment and devices that are commonly used for mineral oil are used for ester liquid. The chemical and physical behaviors of ester fluids compared to mineral oil are different. This must always be considered when interpreting test results stemming from ester fluids. The book is a guideline for students, original equipment manufacturers, users, laboratories and authorities in the use of biological insulating liquids.
Some of the metrics are blocked by your
consent settings
Comparison of various mother wavelets for fault classification in electrical systems
(2020-02-01)
Pothisarn, Chaichan
;
Klomjit, Jittiphong
;
Ngaopitakkul, Atthapol
;
Jettanasen, Chaiyan
;
Asfani, Dimas Anton
This paper presents a comparative study on mother wavelets using a fault type classification algorithm in a power system. The study aims to evaluate the performance of the protection algorithm by implementing different mother wavelets for signal analysis and determines a suitable mother wavelet for power system protection applications. The factors that influence the fault signal, such as the fault location, fault type, and inception angle, have been considered during testing. The algorithm operates by applying the discrete wavelet transform (DWT) to the three-phase current and zero-sequence signal obtained from the experimental setup. The DWT extracts high-frequency components from the signals during both the normal and fault states. The coefficients at scales 1-3 have been decomposed using different mother wavelets, such as Daubechies (db), symlets (sym), biorthogonal (bior), and Coiflets (coif). The results reveal different coefficient values for the different mother wavelets even though the behaviors are similar. The coefficient for any mother wavelet has the same behavior but does not have the same value. Therefore, this finding has shown that the mother wavelet has a significant impact on the accuracy of the fault classification algorithm.
Some of the metrics are blocked by your
consent settings
Comparison of dissolved gases in natural ester under partial discharges
(2019-06-01)
Jongvilaikasem, Korraya
;
Maneerot, Sakda
;
Jariyanurat, Kittipod
;
Pattanadech, Norasage
Currently, natural ester is alternative liquid insulation applied for both distribution and power transformers. Generally, transformers are expected to operate stably and reliably. However, their functions may fail during operation. Dissolved gases analysis is one of the worldwide accepted diagnostic techniques to examine the insulation integrity of the transformers. This paper presents the analysis of dissolved gases generated from partial discharge (PD) experiments i.e. corona discharge, surface discharge and internal discharge which were conducted in the test cell filled with natural ester (FR3). To simulate corona discharge, a needle electrode with a tip radius of 10, 20, and 40 micrometers was used as high voltage electrode and the plane electrode with a diameter of 45 mm was used as a grounded electrode. The gap distance was fixed at 32 mm. The corona discharge experiment was performed for 2 hours at the test voltage level of 35, 40, 45 kV respectively. In case of surface discharge, the pressboard samples i.e. non-impregnated pressboards, 8-hour impregnated pressboards, and 16-hour impregnated pressboards were inserted between the 20-micrometer tip radius needle and grounded plane. Then, the test voltage of 25 kV was applied to the electrode system for 1 hour. Besides, the surface discharge was tested at 35 and 45 kV respectively. For internal discharge, the pressboard samples i.e. non-impregnated pressboards, 8-hour impregnated pressboards, and 16-hour impregnated pressboards were inserted between the plane-plane electrodes. Then the test voltage of 25 kV was applied to the electrode system for 1 hour. Moreover, the internal discharge was tested also at 35 and 45 kV. Their natural ester samples were sampling from the test cell for each experiment and the dissolved gases were measured and analyzed. From the test results, it was found that the types and quantity of dissolved gases depended strongly on the type of discharge and material samples.
Some of the metrics are blocked by your
consent settings
Fault classification in transformer using low frequency component
(2017-12-13)
Jettanasen, Chaiyan
;
Ngaopitakkul, Atthapol
;
Asfani, Dimas Anton
;
Negara, I. Made Yulistya
Transform is a vital equipment in power system that need protection system in order to provide fast and correct response when disturbance occur in system. So, this paper proposed internal and external fault classification in Transformer using algorithm based on discrete wavelet transform (DWT). Low frequency component from DWT has been used to create condition for algorithm. The proposed algorithm has been test using transmission line connected to transformer experimental setup on laboratory level. The result from proposed algorithm shown satisfactory result with 100% accuracy in both internal and external fault in transmission line connected transformer system.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results