• Current Optics and Photonics
• /
• v.6 no.2
• /
• pp.137-142
• /
• 2022

Leak detection is one of the most important challenges in condition monitoring of water pipelines. Fiber Bragg grating (FBG) sensors offer an attractive technique to detect leak signals. In this paper, leak measurements were conducted on a water distribution pilot plant with a length of 270 m and a diameter of 100 mm. FBG sensors were installed on the pipeline surface and used to detect leak vibration signals. The leak was demonstrated with 1-, 2-, 3-, and 4-mm diameter leak holes in four different pipe types. The frequency response of leak signals was analyzed by fast Fourier transform analysis in real time. In the experiment, the frequency range of leak signals was approximately 340-440 Hz. The frequency shifts of leak signals according to the pipe type and the size of the leak hole were demonstrated at a pressure of 1.8 bar and a flow rate of 25.51 m³/h. Results show that frequency shifts detected by FBG sensors can be used to detect leaks in pipelines.

• Journal of Platform Technology
• /
• v.11 no.4
• /
• pp.71-79
• /
• 2023

In this paper, we analyze the characteristics of machine learning workloads and, based on them, propose a distributed in-memory caching technique to improve the performance of machine learning workloads. The core of machine learning workload is model training, and model training is a computationally intensive task. Performing machine learning workloads in a Kubernetes-based cloud environment in which the computing framework and storage are separated can effectively allocate resources, but delays can occur because IO must be performed through network communication. In this paper, we propose a distributed in-memory caching technique to improve the performance of machine learning workloads performed in such an environment. In particular, we propose a new method of precaching data required for machine learning workloads into the distributed in-memory cache by considering Kubflow pipelines, a Kubernetes-based machine learning pipeline management tool.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.510-512
• /
• 2023

In order to enhance a model's capability for detecting facial expressions, this research suggests a pipeline that makes use of the GradCAM component. The patching module and the pseudo-labeling module make up the pipeline. The patching component takes the original face image and divides it into four equal parts. These parts are then each input into a 2Dconvolutional layer to produce a feature vector. Each picture segment is assigned a weight token using GradCAM in the pseudo-labeling module, and this token is then merged with the feature vector using principal component analysis. A convolutional neural network based on transfer learning technique is then utilized to extract the deep features. This technique applied on a public dataset MMI and achieved a validation accuracy of 96.06% which is showing the effectiveness of our method.

• Journal of Computational Design and Engineering
• /
• v.1 no.3
• /
• pp.173-186
• /
• 2014

The failure of a subsea production plant could induce fatal hazards and enormous loss to human lives, environments, and properties. Thus, for securing integrated design safety, core source technologies include subsea system integration that has high safety and reliability and a technique for the subsea flow assurance of subsea production plant and subsea pipeline network fluids. The evaluation of subsea flow assurance needs to be performed considering the performance of a subsea production plant, reservoir production characteristics, and the flow characteristics of multiphase fluids. A subsea production plant is installed in the deep sea, and thus is exposed to a high-pressure/ low-temperature environment. Accordingly, hydrates could be formed inside a subsea production plant or within a subsea pipeline network. These hydrates could induce serious damages by blocking the flow of subsea fluids. In this study, a simulation technology, which can visualize the system configuration of subsea production processes and can simulate stable flow of fluids, was introduced. Most existing subsea simulations have performed the analysis of dynamic behaviors for the installation of subsea facilities or the flow analysis of multiphase flow within pipes. The above studies occupy extensive research areas of the subsea field. In this study, with the goal of simulating the configuration of an entire deep sea production system compared to existing studies, a DES-based simulation technology, which can logically simulate oil production processes in the deep sea, was analyzed, and an implementation example of a simplified case was introduced.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.29 no.5
• /
• pp.466-472
• /
• 2009

An acoustic leak monitoring system(ALMS) using acoustic emission(AE) technique was applied for leakage detection of nuclear power plant's pipeline which is operated in high temperature and pressure condition. Since this system only monitors the existence of leak using the root mean square(RMS) value of raw signal from AE sensor, the difficulty occurs when the characteristics of leak size and shape need to be evaluated. In this study, dual monitoring system using AE sensor and accelerometer was introduced in order to solve this problem. In addition, artificial neural network(ANN) with Levenberg.Marquardt(LM) training algorithm was also applied due to rapid training rate and gave the reliable classification performance. The input parameters of this ANN were extracted from varying signal received from experimental conditions such as the fluid pressure inside pipe, the shape and size of the leak area. Additional experiments were also carried out and with different objective which is to study the generation and characteristic of lamb and surface wave according to the pipe thickness.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.21
• /
• pp.9439-9444
• /
• 2014

Purpose: To identify prostate cancer lncRNAs using a pipeline proposed in this study, which is applicable for the identification of lncRNAs that are differentially expressed in prostate cancer tissues but have a negligible potential to encode proteins. Materials and Methods: We used two publicly available RNA-Seq datasets from normal prostate tissue and prostate cancer. Putative lncRNAs were predicted using the biological technology, then specific lncRNAs of prostate cancer were found by differential expression analysis and co-expression network was constructed by the weighted gene co-expression network analysis. Results: A total of 1,080 lncRNA transcripts were obtained in the RNA-Seq datasets. Three genes (PCA3, C20orf166-AS1 and RP11-267A15.1) showed a significant differential expression in the prostate cancer tissues, and were thus identified as prostate cancer specific lncRNAs. Brown and black modules had significant negative and positive correlations with prostate cancer, respectively. Conclusions: The pipeline proposed in this study is useful for the prediction of prostate cancer specific lncRNAs. Three genes (PCA3, C20orf166-AS1, and RP11-267A15.1) were identified to have a significant differential expression in prostate cancer tissues. However, there have been no published studies to demonstrate the specificity of RP11-267A15.1 in prostate cancer tissues. Thus, the results of this study can provide a new theoretic insight into the identification of prostate cancer specific genes.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.38-48
• /
• 1996

We implemented and evaluated the preformance of a task level pipelined multicomputer "RV860-PIPE(Realtime Vision i860 system using PIPEline)" for computer vision applications. RV860-PIPE is a message-passing MIMD computer having ring interconnection network which is appropriate for vision processing. We designed the node computer of RV860-PIPE using a 64-bit microprocessor to have generality and high processing power for various vision algorithms. Furthermore, to reduce the communication overhead between node computers and between node computer and a frame grabber, we designed dedicated high speed communication channels between them. We showed the practical applicability of the implemented system by evaluting performances of various computer vision applications like edge detection, real-time moving object tracking, and real-time face recognition.

• The Journal of the Korea Contents Association
• /
• v.16 no.12
• /
• pp.373-382
• /
• 2016

Carbon dioxide Capture and Storage/Sequestration (CCS) technology has attracted attention as an ideal method for most carbon dioxide reduction needs. When the collected carbon dioxide is transported to storage via pipelines, the direct transport is made if the storage is close, otherwise it can also be transported via an intermediate storage hub. Determining the number and the location of the intermediate storage hubs is an important problem. A decision-making algorithm using a mathematical model for solving the problem requires considerably more variables and constraints to describe the multi-objective decision, but the computational complexity of the problem increases and it also does not guarantee the optimality. This research proposes an algorithm to determine the location and the number of the intermediate storage hub and develop a simulator for the connection network of the carbon dioxide emission site. The simulator also provides the course of transportation of the carbon dioxide. As a case study, this model is applied to Korea.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.662-667
• /
• 2022

Semantic role labeling task(SRL) is to extract predicate and arguments such as agent, patient, place, time. In the previously SRL task studies, a pipeline method extracting linguistic features of sentence has been proposed, but in this method, errors of each extraction work in the pipeline affect semantic role labeling performance. Therefore, methods using End-to-End neural network model have recently been proposed. In this paper, we propose a neural network model using the Biaffine Average Attention model for SRL task. The proposed model consists of a structure that can focus on the entire sentence information regardless of the distance between the predicate in the sentence and the arguments, instead of LSTM model that uses the surrounding information for prediction of a specific token proposed in the previous studies. For evaluation, we used F1 scores to compare two models based BERT model that proposed in existing studies using F1 scores, and found that 76.21% performance was higher than comparison models.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.53.4-54
• /
• 2021

Although the era of very large telescopes has come, small telescopes still have advantages for fast follow-up and long-term monitoring observation. Intensive monitoring survey of nearby galaxies (IMSNG) aims to understand the nature of the supernovae (SNe) by catching the early light curve from them with the network of small telescopes from 0.4-m to 1.0-m all around the world. To achieve the scientific goals with heterogeneous facilities, three factors are important. First, automatic processes as soon as data is uploaded will increase efficiency and shorten the time. Second, searching for transients is necessary to deal with newly emerged transients for fast follow-up observation. Finally, the Integrated process for different telescopes gives a homogeneous output, which will eventually make connections with the database easy. Here, we introduce the integrated pipeline, 'gppy' based on Python, for more than 10 facilities having various configurations and its performance. Processes consist of image pre-process, photometry, image align, image combine, photometry, and transient search. In the connected database, homogeneous output is summarized and analyzed additionally to filter transient candidates with light curves. This talk will suggest the future work to improve the performance and usability on the other projects, gravitational wave electromagnetic wave counterpart in Korea Observatory (GECKO), and small telescope network of Korea (SOMANGNET).