A5017398875- Air Quality Monitoring and Forecasting
- Fire Detection and Safety Systems
- Artificial Intelligence in Healthcare
- Advanced Queuing Theory Analysis
- Mobile Ad Hoc Networks
- Machine Learning in Healthcare
- Wind and Air Flow Studies
- Traditional Chinese Medicine Studies
- Interconnection Networks and Systems
- Wireless Communication Networks Research
- Distributed systems and fault tolerance
- Advanced Chemical Sensor Technologies
- Advanced Wireless Network Optimization
- COVID-19 diagnosis using AI
- Energy Harvesting in Wireless Networks
- Real-Time Systems Scheduling
- Opportunistic and Delay-Tolerant Networks
- Risk and Safety Analysis
- Simulation and Modeling Applications
- Image Retrieval and Classification Techniques
- Advanced Optical Imaging Technologies
- Age of Information Optimization
- IoT Networks and Protocols
- Anomaly Detection Techniques and Applications
- Image and Signal Denoising Methods
Gachon University
2023-2024
Chungbuk National University
2008-2023
Semyung University
2023
Diabetes mellitus (DM) is a global health challenge that requires advanced strategies for its early detection and prevention. This study evaluates the South Korean population using Korea National Health Nutrition Examination Survey (KNHANES) dataset from 2015 to 2021, provided by Disease Control Prevention Agency (KDCA), focusing on improving diabetes prediction models. Outlier removal was implemented Mahalanobis distance (MAH), feature selection based multicollinearity (MC) reliability...
<abstract> <p>The incidence of hypertension has increased dramatically in both elderly and young populations. The also with the outbreak COVID-19 pandemic. To enhance detection accuracy, we proposed a multivariate outlier removal method based on deep autoencoder (DAE) technique. was applied to Korean National Health Nutrition Examination Survey (KNHANES) database. Several studies have identified various risk factors for chronic hypertension. Chronic diseases are often...
Natural gas is widely used for domestic and industrial purposes, whether it being leaked into the air cannot be directly known. The current problem that leakage not only economically harmful but also detrimental to health. Therefore, much research has been done on damage risks, predicting leakages just beginning. In this study, we propose a method based deep learning predict from environmental data. Our proposed successfully improved performance of machine classification algorithms by...
Natural gas (NG), typically methane, is released into the air, causing significant air pollution and environmental health problems. Nowadays, there a need to use machine-based methods predict losses widely. In this article, we proposed NG leakage levels through feature selection based on factorial analysis (FA) of USA’s urban natural open data. The paper has been divided three sections. First, select essential features using FA. Then, dataset labeled by k-means clustering with OrdinalEncoder...
Ground temperature (GT) or soil (ST) is simply the measurement of warmness soil. Even though GT plays a meaningful role in agricultural production, direct method measuring time-consuming, expensive, and requires human effort. The foremost objective this study to build machine learning (ML) models for hourly prediction at different depths (5, 10, 20, 30 cm) with optimum hyperparameter tuning less complexity. present utilizes statistical model (multiple linear regression (MLR)) four ML...
The natural gas (NG), mostly methane leaks into the air, it is a big problem for climate. detected NG under U.S. city streets and collected data. In this paper, we introduced Deep Neural Network (DNN) classification of prediction level NS leak. proposed method OrdinalEncoder(OE) based K-means clustering Multilayer Perceptron(MLP) predicting 15 features are input neurons using backpropagation. propose OE labeling target data k-means compared normalization methods performance leak prediction....
In this paper, we determine the performance of a packet data multiplexer with go-back-N ARQ protocol under Markovian interruption. It is assumed that input process into system Poisson process. The output channel divided series time slots and can be transmitted in slot time. modeled blocked by some interruption, whose state change between blocking non-blocking states given Markov process.The overall has been analyzed considering relationship, taking interruption account, about buffer behavior...
In this study, the relationship between natural gas (NG) data and gas-related environmental elements was performed using machine learning algorithms to predict level of leakage risk without directly measuring data. The study based on open provided by server IoT-based remote control Picarro sensor specification. naturel leaks into air, it is a big problem for air pollution, environment health. proposed method multivariate outlier removing Random Forest (RF) classification predicting NG leak....
Abstract Background In recent years, the incidence of hypertension has increased dramatically in both elderly and young populations. The also with outbreak COVID-19 pandemic. aims this study to improve prediction detection using a multivariate outlier removal method based on deep autoencoder (DAE) Korean national health data from Korea National Health Nutrition Examination Survey (KNHANES) database. Several studies have identified various risk factors for chronic hypertension. Chronic...
This paper discusses packet data multiplexing using stop‐and‐wait (SW) and go‐back‐N (GBN) automatic repeat request (ARQ) protocols under Markovian interruption. The Markov process shows the output channel by examining interruption inactive active states. We assume that whenever voice signal is link used will be blocked for packet, traffic input exponentially distributed in increments via Poisson process, with each transmitted within an individual time slot. Active periods of original are...