• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.157-166
• /
• 2022

In the case of a die-casting process, defects that are difficult to confirm by visual inspection, such as shrinkage bubbles, may occur due to an error in maintaining a vacuum state. Since these casting defects are discovered during post-processing operations such as heat treatment or finishing work, they cannot be taken in advance at the casting time, which can cause a large number of defects. In this study, we propose an approach that can predict the occurrence of casting defects by defect type using machine learning technology based on casting parameter data collected from equipment in the die casting process in real time. Die-casting parameter data can basically be collected through the casting equipment controller. In order to perform classification analysis for predicting defects by defect type, labeling of casting parameters must be performed. In this study, first, the defective data set is separated by performing the primary clustering based on the total defect rate obtained during the post-processing. Second, the secondary cluster analysis is performed using the defect rate by type for the separated defect data set, and the labeling task is performed by defect type using the cluster analysis result. Finally, a classification learning model is created by collecting the entire labeled data set, and a real-time monitoring system for defect prediction using LabView and Python was implemented. When a defect is predicted, notification is performed so that the operator can cope with it, such as displaying on the monitoring screen and alarm notification.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.39-49
• /
• 2021

Recently, large and diverse weather data are being collected by sensors from various sources. Efforts to predict the concentration of fine dust through machine learning are being made everywhere, and this study intends to compare PM10 and PM2.5 prediction models using data from 840 outdoor air meters installed throughout the city. Information can be provided in real time by predicting the concentration of fine dust after 5 minutes, and can be the basis for model development after 10 minutes, 30 minutes, and 1 hour. Data preprocessing was performed, such as noise removal and missing value replacement, and a derived variable that considers temporal and spatial variables was created. The parameters of the model were selected through the response surface method. XGBoost, Random Forest, and Deep Learning (Multilayer Perceptron) are used as predictive models to check the difference between fine dust concentration and predicted values, and to compare the performance between models.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.13-20
• /
• 2023

In this paper, the actual data of VOC reduction facilities was analyzed through a model that detects and predicts data anomalies. Using the USAD model, which shows stable performance in the field of anomaly detection, anomalies in real-time data are detected and sensors that cause anomalies are searched. In addition, we propose a method of predicting and warning, when abnormalities that time will occur by predicting future outliers with an auto-regressive model. The experiment was conducted with the actual data of the VOC reduction facility, and the anomaly detection test results showed high detection rates with precision, recall, and F1-score of 98.54%, 89.08%, and 93.57%, respectively. As a result, averaging of the precision, recall, and F1-score for 8 sensors of detection rates were 99.64%, 99.37%, and 99.63%. In addition, the Hamming loss obtained to confirm the validity of the detection experiment for each sensor was 0.0058, showing stable performance. And the abnormal prediction test result showed stable performance with an average absolute error of 0.0902.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.12
• /
• pp.357-362
• /
• 2023

Bridges are important transportation infrastructure, but they are subject to damage and cracking due to various environmental factors and constant traffic loads, which accelerate their aging. With many bridges now older than their original construction, there is a need for systems to ensure safety and diagnose deterioration. Bridges are already utilizing structural health monitoring (SHM) technology to monitor the condition of bridges in real time or periodically. Along with this technology, the development of intelligent bridge monitoring technology utilizing artificial intelligence and Internet of Things technology is underway. In this paper, we study an edge system technique for predicting bridge safety using fast Fourier transform and dimensionality reduction algorithm for maintenance of aging bridges. In particular, unlike previous studies, we investigate whether it is possible to form a dataset using sensor data collected from actual bridges and check the safety of bridges.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.826-842
• /
• 2024

As 5G and AI continue to develop, there has been a significant surge in the healthcare industry. The COVID-19 pandemic has posed immense challenges to the global health system. This study proposes an FL-supported edge computing model based on federated learning (FL) for predicting clinical outcomes of COVID-19 patients during hospitalization. The model aims to address the challenges posed by the pandemic, such as the need for sophisticated predictive models, privacy concerns, and the non-IID nature of COVID-19 data. The model utilizes the FATE framework, known for its privacy-preserving technologies, to enhance predictive precision while ensuring data privacy and effectively managing data heterogeneity. The model's ability to generalize across diverse datasets and its adaptability in real-world clinical settings are highlighted by the use of SHAP values, which streamline the training process by identifying influential features, thus reducing computational overhead without compromising predictive precision. The study demonstrates that the proposed model achieves comparable precision to specific machine learning models when dataset sizes are identical and surpasses traditional models when larger training data volumes are employed. The model's performance is further improved when trained on datasets from diverse nodes, leading to superior generalization and overall performance, especially in scenarios with insufficient node features. The integration of FL with edge computing contributes significantly to the reliable prediction of COVID-19 patient outcomes with greater privacy. The research contributes to healthcare technology by providing a practical solution for early intervention and personalized treatment plans, leading to improved patient outcomes and efficient resource allocation during public health crises.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.5
• /
• pp.1035-1040
• /
• 2024

The main objective of inspecting structures is to ensure the safety of all entities that utilize these structures as cracks in structures if not attended to could lead to serious calamities. With that objective in mind, artificial intelligence (AI) based technologies to assist human inspectors are needed especially for retaining walls in structures. In this paper, we predict the crack displacement of retaining walls using an Polynomial Regressive (PR) analysis model, as well as Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) deep learning models, and compare their performance. For the performance comparison, we apply multi-variable feature inputs, by utilizing temperature and rainfall data that may affect the crack displacement of the retaining wall. The training and inference data were collected through measuring sensors such as inclinometers, thermometers, and rain gauges. The results show that the multi-variable feature model had a MAE of 0.00186, 0.00450 and 0.00842, which outperformed the single variable feature model at 0.00393, 0.00556 and 0.00929 for the polynomial regression model, LSTM model and the GRU model respectively from the evaluation performed.

• Journal of Internet of Things and Convergence
• /
• v.10 no.4
• /
• pp.27-33
• /
• 2024

As of 2023, the number of accident victims in the domestic construction industry is 26,829, ranking second only to other businesses (service industries). The accident types of casualties in all industries were falls (29,229 people), followed by falls (14,357 people). Based on the above data, this study attaches sensors to hard hats and insoles to predict fall accidents that frequently occur at construction sites, and proposes smart safety equipment that applies a random forest algorithm based on the data collected through this. The random forest model can determine fall accidents in real time with high accuracy by generating multiple decision trees and combining the predictions of each tree. This model classifies whether a worker has had a fall accident and the type of behavior through data collected from the MPU-6050 sensor attached to the hard hat. Fall accidents that are primarily determined from hard hats are secondarily predicted through sensors attached to the insole, thereby increasing prediction accuracy. It is expected that this will enable rapid response in the event of an accident, thereby reducing worker deaths and accidents.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.8
• /
• pp.667-675
• /
• 2013

This paper presents vision-based techniques for underwater landmark detection, map-based localization, and SLAM (Simultaneous Localization and Mapping) in structured underwater environments. A variety of underwater tasks require an underwater robot to be able to successfully perform autonomous navigation, but the available sensors for accurate localization are limited. A vision sensor among the available sensors is very useful for performing short range tasks, in spite of harsh underwater conditions including low visibility, noise, and large areas of featureless topography. To overcome these problems and to a utilize vision sensor for underwater localization, we propose a novel vision-based object detection technique to be applied to MCL (Monte Carlo Localization) and EKF (Extended Kalman Filter)-based SLAM algorithms. In the image processing step, a weighted correlation coefficient-based template matching and color-based image segmentation method are proposed to improve the conventional approach. In the localization step, in order to apply the landmark detection results to MCL and EKF-SLAM, dead-reckoning information and landmark detection results are used for prediction and update phases, respectively. The performance of the proposed technique is evaluated by experiments with an underwater robot platform in an indoor water tank and the results are discussed.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.20 no.1
• /
• pp.119-128
• /
• 2017

G-induced Loss of Consciousness(G-LOC) can be predicted by measuring Electromyogram(EMG) signals. Existing studies have mainly focused on specific body parts and lacked of consideration with quantitative EMG indices. The purpose of this study is to analyze the indices of EMG signals by human body parts for monitoring G-LOC condition. The data of seven EMG features such as Root Mean Square(RMS), Integrated Absolute Value(IAV), and Mean Absolute Value(MAV) for reflecting muscle contraction and Slope Sign Changes(SSC), Waveform Length (WL), Zero Crossing(ZC), and Median Frequency(MF) for representing muscle contraction and fatigue was retrieved from high G-training on a human centrifuge simulator. A total of 19 trainees out of 47 trainees of the Korean Air Force fell into G-LOC condition during the training in attaching EMG sensor to three body parts(neck, abdomen, calf). IAV, MAV, WL, and ZC under condition after G-LOC were decreased by 17 %, 17 %, 18 %, and 4 % comparing to those under condition before G-LOC respectively. Also, RMS, IAV, MAV, and WL in neck part under condition after G-LOC were higher than those under condition before G-LOC; while, those in abdomen and calf part lower. This study suggest that measurement of IAV and WL by attaching EMG sensor to calf part may be optimal for predicting G-LOC.

• Smart Structures and Systems
• /
• v.22 no.2
• /
• pp.133-137
• /
• 2018

Increasing interest in prognostics and health management has heightened the need for wireless sensor networks (WSN) with efficient power sources. Piezoelectric energy harvesters using Pb(Zr,Ti)O3 (PZT) are one of the candidate power sources for WSNs as they efficiently convert mechanical vibration energy into electrical energy. These types of devices are resonated at a specific frequency, which has a significant impact on the amount of energy harvested, by external vibration. Hence, precise prediction of mechanical deformation including modal analysis of piezoelectric devices is crucial for estimating the energy generated under specific conditions. In this study, an experimental vibrational system capable of controlling a wide range of frequencies and accelerations was designed to generate mechanical vibration for piezoelectric energy harvesters. In conjunction with MATLAB, the system automatically finds the resonance frequency of harvesters. A small accelerometer and non-contact laser displacement sensor are employed to investigate the mechanical deformation of harvesters. Mechanical deformation under various frequencies and accelerations were investigated and analyzed based on data from two types of sensors. The results verify that the proposed system can be employed to carry out vibration experiments for piezoelectric harvesters and measurement of their mechanical deformation.