• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.463-481
• /
• 2020

Cutter suction dredgers (CSDs) are widely used in various dredging constructions such as channel excavation, wharf construction, and reef construction. During a CSD construction, the main operation is to control the swing speed of cutter to keep the slurry concentration in a proper range. However, the slurry concentration cannot be monitored in real-time, i.e., there is a "time-lag effect" in the log of slurry concentration, making it difficult for operators to make the optimal decision on controlling. Concerning this issue, a solution scheme that using real-time monitored indicators to predict current slurry concentration is proposed in this research. The characteristics of the CSD monitoring data are first studied, and a set of preprocessing methods are presented. Then we put forward the concept of "index class" to select the important indices. Finally, an ensemble learning algorithm is set up to fit the relationship between the slurry concentration and the indices of the index classes. In the experiment, log data over seven days of a practical dredging construction is collected. For comparison, the Deep Neural Network (DNN), Long Short Time Memory (LSTM), Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and the Bayesian Ridge algorithm are tried. The results show that our method has the best performance with an R² of 0.886 and a mean square error (MSE) of 5.538. This research provides an effective way for real-time predicting the slurry concentration of CSDs and can help to improve the stationarity and production efficiency of dredging construction.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.77-87
• /
• 2023

Wind turbines playing a critical role in renewable energy generation, accurately assessing their operational status is crucial for maximizing energy production and minimizing downtime. This study conducts a comparative analysis of different neural network models for wind turbine condition diagnosis, evaluating their effectiveness using a dataset containing sensor measurements and historical turbine data. The study utilized supervisory control and data acquisition data, collected from 2 MW doubly-fed induction generator-based wind turbine system (Model HQ2000), for the analysis. Various neural network models such as artificial neural network, long short-term memory, and recurrent neural network were built, considering factors like activation function and hidden layers. Symmetric mean absolute percentage error were used to evaluate the performance of the models. Based on the evaluation, conclusions were drawn regarding the relative effectiveness of the neural network models for wind turbine condition diagnosis. The research results guide model selection for wind turbine condition diagnosis, contributing to improved reliability and efficiency through advanced neural network-based techniques and identifying future research directions for further advancements.

• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.4
• /
• pp.69-78
• /
• 2023

With the rapid growth of artificial intelligence, the demand for semiconductors is enormously increasing everywhere. To ensure the manufacturing quality and quantity simultaneously, the importance of automatic defect detection during the packaging process has been re-visited by adapting various deep learning-based methodologies into automatic packaging defect inspection. Deep learning (DL) models require a large amount of data for training, but due to the nature of the semiconductor industry where security is important, sharing and labeling of relevant data is challenging, making it difficult for model training. In this study, we propose a new framework for securing sufficient data for DL models with fewer computing resources through a divide-and-conquer approach. The proposed method divides high-resolution images into pre-defined sub-regions and assigns conditional labels to each region, then trains individual sub-regions and boundaries with boundary loss inducing the globally coherent and seamless images. Afterwards, full-size image is reconstructed by combining divided sub-regions. The experimental results show that the images obtained through this research have high efficiency, consistency, quality, and generality.

• International Journal of Computer Science & Network Security
• /
• v.23 no.10
• /
• pp.147-156
• /
• 2023

Electronic voting machines (EVMs) are replacing research ballots due to the errors involved in the manual counting process and the lengthy time required to count the votes. Even though these digital recording electronic systems are advancements, they are vulnerable to tampering and electoral fraud. The suspected vulnerabilities in EVMs are the possibility of tampering with the EVM's memory chip or replacing it with a fake one, their simplicity, which allows them to be tampered with without requiring much skill, and the possibility of double voting. The vote data is shared among all network devices, and peer-to-peer verification is performed to ensure the vote data's authenticity. To successfully tamper with the system, all of the data stored in the nodes must be changed. This improves the proposed system's efficiency and dependability. Elections and voting are fundamental components of a democratic system. Various attempts have been made to make modern elections more flexible by utilizing digital technologies. The fundamental characteristics of free and fair elections are intractability, immutability, transparency, and the privacy of the actors involved. This corresponds to a few of the many characteristics of blockchain-like decentralized ownership, such as chain immutability, anonymity, and distributed ledger. This working research attempts to conduct a comparative analysis of various blockchain technologies in development and propose a 'Blockchain-based Electronic Voting System' solution by weighing these technologies based on the need for the proposed solution. The primary goal of this research is to present a robust blockchain-based election mechanism that is not only reliable but also adaptable to current needs.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.49-56
• /
• 2023

This study proposed a damage location estimation method for automated image-based port infrastructure inspection. Memory efficiency was improved by calculating the homography matrix using feature detection technology and outlier removal technology, without going through the 3D modeling process and storing only damage information. To develop an algorithm specialized for port infrastructure, the algorithm was optimized through ground-truth coordinate pairs created using images of port infrastructure. The location errors obtained by applying this to the sample and concrete wall were (X: 6.5cm, Y: 1.3cm) and (X: 12.7cm, Y: 6.4cm), respectively. In addition, by applying the algorithm to the concrete wall and displaying it in the form of an exterior damage map, the possibility of field application was demonstrated.

• Journal of IKEEE
• /
• v.28 no.1
• /
• pp.53-64
• /
• 2024

With the advancement of NLP(Natural Language Processing) models, conversational AI such as ChatGPT is becoming increasingly popular. To enhance processing speed and reduce power consumption, it is important to implement the Transformer algorithm, which forms the basis of the latest natural language processing models, in hardware. In particular, the multi-head attention and feed-forward network, which analyze the relationships between different words in a sentence through matrix multiplication, are the most computationally intensive core algorithms in the Transformer. In this paper, we propose a new variable systolic array based on the number of input words to enhance matrix multiplication speed. Quantization maintains Transformer accuracy, boosting memory efficiency and speed. For evaluation purposes, this paper verifies the clock cycles required in multi-head attention and feed-forward network and compares the performance with other multipliers.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.213-220
• /
• 2024

This paper proposes an optimization strategy for performing Federated Learning between devices and edge clouds using WebAssembly (WASM). The proposed strategy aims to maximize efficiency by conducting partial training on devices and the remaining training on edge clouds. Specifically, it mathematically describes and evaluates methods to optimize data transfer between GPU memory segments and the overlapping of computational tasks to reduce overall training time and improve GPU utilization. Through various experimental scenarios, we confirmed that asynchronous data transfer and task overlap significantly reduce training time, enhance GPU utilization, and improve model accuracy. In scenarios where all optimization techniques were applied, training time was reduced by 47%, GPU utilization improved to 91.2%, and model accuracy increased to 89.5%. These results demonstrate that asynchronous data transfer and task overlap effectively reduce GPU idle time and alleviate bottlenecks. This study is expected to contribute to the performance optimization of Federated Learning systems in the future.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.39 no.3
• /
• pp.59-64
• /
• 2002

In the RFID system using ISM-band, The tag mounted at the object has used the DC power by rectifying the RF signals of the small antenna for operating the micro-controller and memory. The performance of the tag would be reduced because of the second harmonics generated by the nonlinearity of the semiconductor and the spurious signal excited the high order mode of the antenna. This paper has realized the novel type low-pass filter with "the Stub-I type DGS slot structure" to improve the efficiency of the tag by suppressing the harmonics. The optimized frequency character at the pass-band/stop-band has obtained by tuning the stub width and slit width of I type slot. The measured result of the LPF has the cutoff frequency 3.25 GHz, the insertion loss about -0.29~-0.3 dB at pass-band 2.4 GHz~2.5 GHz, the return loss about -27.688~-33.665 dB at pass-band with a good performance, and the suppression character is about -19.367 dB at second harmonics frequency 4.9 GHz. This DGS LPF may be applied the various application as the RFID, WLAN to improve the efficiency of the system by suppressing the harmonics and spurious signals. 

• Journal of Korea Multimedia Society
• /
• v.10 no.11
• /
• pp.1367-1383
• /
• 2007

A sensor network consists of a network of sensors that can perform computation and also communicate with each other through wireless communication. Some important characteristics of sensor networks are that the network should be self administered and the power efficiency should be greatly considered due to the fact that it uses battery power. In sensor networks, when large amounts of various stream data is produced and multiple queries need to be processed simultaneously, the power efficiency should be maximized. This work proposes a technique to create an index on multiple monitoring queries so that the multi-query processing performance could be increased and the memory and power could be efficiently used. The proposed SMILE tree modifies and combines the ideas of spatial indexing techniques such as k-d trees and R+-trees. The k-d tree can divide the dimensions at each level, while the R+-tree improves the R-tree by dividing the space into a hierarchical manner and reduces the overlapping areas. By applying the SMILE tree on multiple queries and using it on stream data in sensor networks, the response time for finding an indexed query takes in some cases 50% of the time taken for a linear search to find the query.

• Journal of Korea Water Resources Association
• /
• v.51 no.6
• /
• pp.503-514
• /
• 2018

In recent, the hydrological regime of the Mekong river is changing drastically due to climate change and haphazard watershed development including dam construction. Information of hydrologic feature like streamflow of the Mekong river are required for water disaster prevention and sustainable water resources development in the river sharing countries. In this study, runoff simulations at the Kratie station of the lower Mekong river are performed using SWAT (Soil and Water Assessment Tool), a physics-based hydrologic model, and LSTM (Long Short-Term Memory), a data-driven deep learning algorithm. The SWAT model was set up based on globally-available database (topography: HydroSHED, landuse: GLCF-MODIS, soil: FAO-Soil map, rainfall: APHRODITE, etc) and then simulated daily discharge from 2003 to 2007. The LSTM was built using deep learning open-source library TensorFlow and the deep-layer neural networks of the LSTM were trained based merely on daily water level data of 10 upper stations of the Kratie during two periods: 2000~2002 and 2008~2014. Then, LSTM simulated daily discharge for 2003~2007 as in SWAT model. The simulation results show that Nash-Sutcliffe Efficiency (NSE) of each model were calculated at 0.9(SWAT) and 0.99(LSTM), respectively. In order to simply simulate hydrological time series of ungauged large watersheds, data-driven model like the LSTM method is more applicable than the physics-based hydrological model having complexity due to various database pressure because it is able to memorize the preceding time series sequences and reflect them to prediction.