Search

Document forgery is a significant issue in Korea, with around ten thousand cases reported every year. Analyzing paper plays a crucial role in examining questionable documents such as marketable securities and contracts, which can aid in solving criminal cases of document forgery. Paper analysis can also provide essential insights in other types of criminal cases, serving as an important clue for solving cases such as the source of a blackmail letter. The papermaking process generates distinct forming fabric marks and formations, which are critical features for paper classification. These characteristics are observable under transmitted light and are created by the forming fabric pattern and the distribution of pulp fibers, respectively. In this study, we propose a novel approach for paper identification based on hybrid features. This method combines texture features extracted from images converted using the gray‐level co‐occurrence matrix (GLCM) approach and a convolutional neural network (CNN), with another set of features extracted by the CNN using the same images as input. We applied the proposed method to classification tasks for seven major paper brands available in the Korean market, achieving an accuracy of 97.66%. The results confirm the applicability of this method for visually inspecting paper products and demonstrate its potential for assisting in solving criminal cases involving document forgery. [ABSTRACT FROM AUTHOR]

Influenced by cultural background, economic development, social system, education system, and other factors, there is still a big gap between Chinese institutions and developed countries in flute teaching, even with our neighbors, South Korea and Japan. Under the influence of cultural background, economic development, social system, and educational system, there is still a very big gap between Chinese colleges and universities and developed countries in flute teaching, even with our neighbors, South Korea and Japan. Because of its local perception and weight-sharing structure, the convolutional neural network is closer to the biological neural network in the real world. The weight-sharing structure reduces the complexity of the neural network, which can avoid the complexity of feature extraction and classification process in data reconstruction. This paper studies the analysis and optimization of flute playing and teaching system based on a convolutional neural network. By applying local perception field and parameter sharing in a convolutional neural network at the same time and adding multiple filters, it can not only effectively reduce the number of parameters but also extract features layer by layer. In the process of convolution, the parameters of the characteristic map obtained by each layer decrease layer by layer, but the number increases gradually. Based on the analysis of the problems faced by the flute performance teaching, this paper puts forward the corresponding solutions in order to promote the flute performance teaching in China to achieve better results. [ABSTRACT FROM AUTHOR]

Using traditional methods based on detection rules written by human security experts presents significant challenges for the accurate detection of network threats, which are becoming increasingly sophisticated. In order to deal with the limitations of traditional methods, network threat detection techniques utilizing artificial intelligence technologies such as machine learning are being extensively studied. Research has also been conducted on analyzing various string patterns in network packet payloads through natural language processing techniques to detect attack intent. However, due to the nature of packet payloads that contain binary and text data, a new approach is needed that goes beyond typical natural language processing techniques. In this paper, we study a token extraction method optimized for payloads using n-gram and byte-pair encoding techniques. Furthermore, we generate embedding vectors that can understand the context of the packet payload using algorithms such as Word2Vec and FastText. We also compute the embedding of various header data associated with packets such as IP addresses and ports. Given these features, we combine a text 1D CNN and a multi-head attention network in a novel fashion. We validated the effectiveness of our classification technique on the CICIDS2017 open dataset and over half a million data collected by The Education Cyber Security Center (ECSC), currently operating in South Korea. The proposed model showed remarkable performance compared to previous studies, achieving highly accurate classification with an F1-score of 0.998. Our model can also preprocess and classify 150,000 network threats per minute, helping security agents in the field maximize their time and analyze more complex attack patterns. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to study the recognition of ships and their structures to improve the safety of drone operations engaged in shore-to-ship drone delivery service. This study has developed a system that can distinguish between ships and their structures by using a convolutional neural network (CNN). First, the dataset of the Marine Traffic Management Net is described and CNN's object sensing based on the Detectron2 platform is discussed. There will also be a description of the experiment and performance. In addition, this study has been conducted based on actual drone delivery operations—the first air delivery service by drones in Korea. [ABSTRACT FROM AUTHOR]

Despite various economic crisis situations around the world, the courier and delivery service market continues to be revitalized. The parcel shipping volume in Korea is currently 3.37 billion parcels, achieving a growth rate of about 140% compared to 2012, and 70% of parcels are from metropolitan areas. Given the above statistics, this paper focused on the development of an underground logistics system (ULS), in order to conduct a study to handle the freight volume in a more eco-friendly manner in the center of metropolitan areas. In this paper we first analyzed the points at which parcel boxes were damaged, based on a ULS. After collecting image data of the parcel boxes, the damaged parcel boxes were detected and classified using computerized methods, in particular, a convolutional neural network (CNN), MobileNet. For image classification, Google Colaboratory notebook was used and 4882 images were collected for the experiment. Based on the collected dataset, when conducting the experiment, the accuracy, recall, and specificity of classification for the testing set were 84.6%, 82% and 88.54%, respectively,. To validate the usefulness of the MobileNet algorithm, additional experiments were performed under the same conditions using other algorithms, VGG16 and ResNet50. The results show that MobileNet is superior to other image classification models when comparing test time. Thus, in the future, MobileNet has the potential to be used for identifying damaged boxes, and could be used to ensure the reliability and safety of parcel boxes based on a ULS. [ABSTRACT FROM AUTHOR]

In determining wind loads when designing buildings—especially high-rise buildings—wind speed is a critical factor. With increased progression of city high-rise construction, accurate prediction has become ever more important. Many factors, such as local climates, roughness of surrounding conditions, and terrain, may affect wind speed. But among all factors considered, terrain has a very large influence. Difficulties in reflecting the influence of terrain on wind speed include (1) collecting topographic data information; (2) quantitatively evaluating terrain features; and (3) expressing specific area relationships with surrounding observation stations. This paper poses means to solve these limitations by (1) using satellite imagery to gather topographic information; (2) evaluating terrain quantitatively with convolutional neural network (CNN)–based encoders; and (3) employing a graph neural network (GNN) to estimate the wind speed relationship of an arbitrary place to that of observation stations. Herein, a machine learning model utilizing the aforementioned means was proposed. To support this model, an experiment was conducted using observed wind speed data in Korea. Throughout the experiment, previous studies were used to compare results with ratification of the posed model. Given the submitted findings, further research and investigation to establish correlation with other experimental case results are proposed. [ABSTRACT FROM AUTHOR]

Featured Application: The underwater target classification algorithm proposed in this paper can be applied to an active sonar system to detect long-range targets. Detection and classification of unidentified underwater targets maneuvering in complex underwater environments are critical for active sonar systems. In previous studies, many detection methods were applied to separate targets from the clutter using signals that exceed a preset threshold determined by the sonar console operator. This is because the high signal-to-noise ratio target has enough feature vector components to separate. However, in a real environment, the signal-to-noise ratio of the received target does not always exceed the threshold. Therefore, a target detection algorithm for various target signal-to-noise ratio environments is required; strong clutter energy can lead to false detection, while weak target signals reduce the probability of detection. It also uses long pulse repetition intervals for long-range detection and high ambient noise, requiring classification processing for each ping without accumulating pings. In this study, a target classification algorithm is proposed that can be applied to signals in real underwater environments above the noise level without a threshold set by the sonar console operator, and the classification performance of the algorithm is verified. The active sonar for long-range target detection has low-resolution data; thus, feature vector extraction algorithms are required. Feature vectors are extracted from the experimental data using Power-Normalized Cepstral Coefficients for target classification. Feature vectors are also extracted with Mel-Frequency Cepstral Coefficients and compared with the proposed algorithm. A convolutional neural network was employed as the classifier. In addition, the proposed algorithm is to be compared with the result of target classification using a spectrogram and convolutional neural network. Experimental data were obtained using a hull-mounted active sonar system operating on a Korean naval ship in the East Sea of South Korea and a real maneuvering underwater target. From the experimental data with 29 pings, we extracted 361 target and 3351 clutter data. It is difficult to collect real underwater target data from the real sea environment. Therefore, the number of target data was increased using the data augmentation technique. Eighty percent of the data was used for training and the rest was used for testing. Accuracy value curves and classification rate tables are presented for performance analysis and discussion. Results showed that the proposed algorithm has a higher classification rate than Mel-Frequency Cepstral Coefficients without affecting the target classification by the signal level. Additionally, the obtained results showed that target classification is possible within one ping data without any ping accumulation. [ABSTRACT FROM AUTHOR]

Summary: Cables are among the most important structural components of cable‐stayed bridges; however, their vibrations due to the wind and vehicles significantly affect the serviceability of bridges. To overcome the expensive and time‐ and effort‐intensive installation of sensors in measuring cable vibrations, computer‐vision‐based displacement methods have been introduced. Even with the improved accuracy and convenience of vision‐based displacement methods, there are two main issues in their application in measuring cable vibrations: the manual selection of the region of interest (ROI) and loss of feature points using traditional tracking algorithms. To address these, this paper proposes a new specialized method to measure the structural displacement of cables. The proposed method automatically selects the ROI using a convolutional neural network and tracks the feature points in the cable more robustly using a modified Kanade–Lucas–Tomasi (KLT) algorithm. The automatic cable ROI selection network (Cable‐ROI Net) predicted the cable with an intersection over union of 89.59%. Meanwhile, modified KLT (Uni‐KLT) successfully measured the cable displacement with a root mean square error of 1.077 pixels, the conventional KLT failed to track the feature points. The on‐site validation test at a cable‐stayed bridge in Korea demonstrated the ability of the proposed method to automatically select the ROI and successfully measure the cable vibration for the entire duration of 30 min, whereas the traditional method required manual ROI selection and lost all feature points four times throughout the test. Therefore, the proposed method is expected to improve the current methods for measuring cable vibrations. [ABSTRACT FROM AUTHOR]

This special issue of IEEE Micro captures three contributions from among the ten regular and nine invited presentations of Cool Chips 24. The three papers are focused on convolutional neural network (CNN) acceleration, mobile deep neural network (DNN) training, and a supercomputer; were written by authors from China, Korea, and Japan, respectively; and all of them were the emerging topics at Cool Chips 24. [ABSTRACT FROM AUTHOR]

As urbanization progresses, many studies about the analysis and prediction of land-use change and urban sprawl have been conducted recently. As the sprawl phenomenon progresses rapidly, the urban expansion phenomenon became uncontrolled and it has affected negatively on the city's environment and transportation finally. So, it is essential to identify lands likely to be urbanized in the future because it aids in establishing land use plans and policies pre-acting the negative impact of spatially urban expansion the sprawl by determining factors affecting the urban sprawl. Previous studies based on statistical models are limited to identifying determining factors, so the prediction performance is low compared to deep learning. On the other hand, existing studies using machine learning and deep learning overlook selecting specific region-focused variables. Therefore, this study aims to analyze and predict changes in the Seoul Metropolitan Area's sprawl in Korea using the Convolutional Long Short-Term Memory Network (ConvLSTM) with factors at the city scale and neighboring factors at the local scale in the Seoul Metropolitan Area (SMA). ConvLSTM is a type of combination model: combining Recurrent Neural Network(RNN) and Convolutional Neural Network(CNN). This study showed that ConvLSTM with factors at the city and neighboring factors at the local scale predicted the urbanized land. The determinants contain population and roads ratio at the city scale, and neighboring urban lands, distance to the nearest subway stations, slope, and elevation at the local scale. The results reveal that predicted urban lands in 2020 increase over the entire region. In particular, the expected urban lands in 2020 increase by reducing farmlands in the southern part of the SMA. It is consistent with the trend of urbanized lands from 1980 to 2010. In addition, urbanization occurs in areas adjacent to Seoul due to the well-established urban infrastructure. The results of this study can be used as evidence to establish sustainable land use plans and regulations in the future. [ABSTRACT FROM AUTHOR]

A data‐driven model for predicting the surface temperature using neural networks was proposed to alleviate the computational burden of numerical weather prediction (NWP). Our model, named TPTNet uses only 2 m temperature measured at the weather stations of the South Korean Peninsula as input to predict the local temperature at finite forecast hours. The turbulent fluctuation component of the temperature was extracted from the station measurements by separating the climatology component accounting for the yearly and daily variations. The effect of station altitude was then compensated by introducing a potential temperature. The resulting turbulent potential temperature (TPT) data at irregularly distributed stations were used as input for predicting the TPT at forecast hours through three trained networks based on convolutional neural network, Swin Transformer, and a graph neural network. By comparing the prediction performance of our network with that of persistence and NWP, we found that our model can make predictions comparable to NWP for up to 12 hr. Plain Language Summary: We developed a new model called TPTNet to predict local temperatures using only temperature measurements from weather stations in South Korea. This model aims to reduce the heavy computational demands of traditional numerical weather prediction (NWP) methods. By analyzing 20 years of data, we separated the regular temperature patterns that change yearly and daily from the more unpredictable fluctuations. We also adjusted the model for the altitude of each weather station. We trained three different types of neural networks for this purpose: a convolutional neural network, a Swin Transformer, and a graph neural network. When we tested our model with new data from 2020, it made reliable temperature predictions for up to 12 hr, performing as well as, or even better than, traditional NWP methods. This new approach could help improve weather forecasting by making it faster and less computationally intensive. Key Points: Only 2 m temperature data measured at the weather station is used as input for the prediction of temperature at finite forecast hoursTurbulent fluctuation temperature relative to the climatological yearly and daily periodic variations with the altitude adjustment using potential temperature is considered in data‐driven learningFor 12 hr of forecast hour, TPTNet produces forecasts comparable to those of the numerical weather prediction, with the less scattered errors over stations [ABSTRACT FROM AUTHOR]

The most important thing to operate a power system is that the power supply should be close to the power demand. In order to predict the amount of electric power transaction (EPT), it is important to choose and decide the variable and its starting date. In this paper, variables that could be acquired one the starting day of prediction were chosen. This paper designated date, temperature and special day as variables to predict the amount of EPT of the Korea Electric Power company. This paper also used temperature data from a year ago to predict the next year. To do this, we proposed single deep learning algorithms and hybrid deep learning algorithms. The former included multi-layer perceptron (MLP), convolution neural network (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), support vector machine regression (SVR), and adaptive network-based fuzzy inference system (ANFIS). The latter included LSTM + CNN and CNN + LSTM. We then confirmed the improvement of accuracy for prediction using pre-processed variables compared to original variables We also assigned two years of test data during 2017–2018 as variable data to measure high prediction accuracy. We then selected a high-accuracy algorithm after measuring root mean square error (RMSE) and mean absolute percent error (MAPE). Finally, we predicted the amount of EPT in 2018 and then measured the error for each proposed algorithm. With these acquired error data, we obtained a model for predicting the amount of EPT with a high accuracy. [ABSTRACT FROM AUTHOR]

The spread of American Bullfrog has a significant impact on the surrounding ecosystem. It is important to study the mechanisms of their spreading so that proper mitigation can be applied when needed. This study analyzes data from national surveys on bullfrog distribution. We divided the data into 25 regional clusters. To assess the spread within each cluster, we constructed temporal sequences of spatial distribution using the agglomerative clustering method. We employed Elementary Cellular Automata (ECA) to identify rules governing the changes in spatial patterns. Each cell in the ECA grid represents either the presence or absence of bullfrogs based on observations. For each cluster, we counted the number of presence location in the sequence to quantify spreading intensity. We used a Convolutional Neural Network (CNN) to learn the ECA rules and predict future spreading intensity by estimating the expected number of presence locations over 400 simulated generations. We incorporated environmental factors by obtaining habitat suitability maps using Maxent. We multiplied spreading intensity by habitat suitability to create an overall assessment of bullfrog invasion risk. We estimated the relative spreading assessment and classified it into four categories: rapidly spreading, slowly spreading, stable populations, and declining populations. [ABSTRACT FROM AUTHOR]

We propose a novel system leveraging deep learning-based methods to predict urban traffic accidents and estimate their severity. The major challenge is the data imbalance problem in traffic accident prediction. The problem is caused by numerous zero values in the dataset due to the rarity of traffic accidents. To address the issue, we propose a grid-clustered feature map with the ideas of grids and cells. To predict the occurrence of accidents in the grid, we introduce an accident detector that combines the power of a Convolutional Neural Network (CNN) with a Deep Neural Network (DNN). Then, hierarchical DNNs are supposed to be an accident risk classifier to estimate the risk of each cell in the accident-occurrence grid. The proposed system can effectively reduce instances with no traffic accidents. Furthermore, we introduce the concept of the Accident Risk Index (ARI) to better represent the severity of risk at each cell. Also, we consider all the explanatory variables, such as dangerous driving behaviors, traffic mobility, and safety facility information, that can be related to traffic accidents. To improve the prediction accuracy, we further take into consideration all the explanatory variables, such as dangerous driving behaviors, traffic mobility, and safety facility information, that can be related to traffic accidents. In the experiment, we highlight the benefits of our method for urban traffic accident management by significantly improving model performance compared to the baselines. The feasibility and applicability of the proposed system are validated in the data of Daejeon City, Republic of Korea. The proposed prediction system can dynamically advise and recommend commuters, traffic management systems, and city planners on alternatives, optimizations, and interventions. [ABSTRACT FROM AUTHOR]

Coronavirus 2019 (COVID-19) has posed a serious threat to the lives and health of the majority of people worldwide. Since the early days of the outbreak, South Korea's government and citizens have made persistent efforts to provide effective prevention against further spread of the disease. In particular, the participation of individual citizens in complying with the necessary code of conduct to prevent spread of the infection, through measures such as social distancing and mask wearing, is as instrumental as the geographical tracking of the trajectory of the infected. In this paper, we propose an activity recognition method based on a wristband equipped with an IR array and inertial measurement unit (IMU) to detect individual compliance with codes of personal hygiene management, such as mask wearing, which are recommended to prevent the spread of infectious diseases. The results of activity recognition were comparatively analyzed by applying conventional machine learning algorithms and convolutional neural networks (CNNs) to the IMU time series and IR array thermal images collected from 25 subjects. When CNN and 24 × 32 thermal images were used, 97.8% accuracy was achieved (best performance), and when 6 × 8 low-resolution thermal images were used, similar performance with 97.1% accuracy was obtained. In the case of using IMU, the performance of activity recognition was lower than that obtained with the IR array, but an accuracy of 93% was achieved even in the case of applying machine learning algorithms, indicating that it is more suitable for wearable devices with low computational capability. [ABSTRACT FROM AUTHOR]

Pine wilt is a devastating disease that typically kills affected pine trees within a few months. In this paper, we confront the problem of detecting pine wilt disease. In the image samples that have been used for pine wilt disease detection, there is high ambiguity due to poor image resolution and the presence of "disease-like" objects. We therefore created a new dataset using large-sized orthophotographs collected from 32 cities, 167 regions, and 6121 pine wilt disease hotspots in South Korea. In our system, pine wilt disease was detected in two stages: n the first stage, the disease and hard negative samples were collected using a convolutional neural network. Because the diseased areas varied in size and color, and as the disease manifests differently from the early stage to the late stage, hard negative samples were further categorized into six different classes to simplify the complexity of the dataset. Then, in the second stage, we used an object detection model to localize the disease and "disease-like" hard negative samples. We used several image augmentation methods to boost system performance and avoid overfitting. The test process was divided into two phases: a patch-based test and a real-world test. During the patch-based test, we used the test-time augmentation method to obtain the average prediction of our system across multiple augmented samples of data, and the prediction results showed a mean average precision of 89.44% in five-fold cross validation, thus representing an increase of around 5% over the alternative system. In the real-world test, we collected 10 orthophotographs in various resolutions and areas, and our system successfully detected 711 out of 730 potential disease spots. [ABSTRACT FROM AUTHOR]

The energy manufacturers are required to produce an accurate amount of energy by meeting the energy requirements at the end-user side. Consequently, energy prediction becomes an essential role in the electric industrial zone. In this paper, we propose the hybrid ensemble deep learning model, which combines multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM), and hybrid CNN-LSTM to improve the forecasting performance. These DL architectures are more popular and better than other machine learning (ML) models for time series electrical load prediction. Therefore, hourly-based energy data are collected from Jeju Island, South Korea, and applied for forecasting. We considered external features associated with meteorological conditions affecting energy. Two-year training and one-year testing data are preprocessed and arranged to reform the times series, which are then trained in each DL model. The forecasting results of the proposed ensemble model are evaluated by using mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Error metrics are compared with DL stand-alone models such as MLP, CNN, LSTM, and CNN-LSTM. Our ensemble model provides better performance than other forecasting models, providing minimum MAPE at 0.75%, and was proven to be inherently symmetric for forecasting time-series energy and demand data, which is of utmost concern to the power system sector. [ABSTRACT FROM AUTHOR]

This paper investigates the influence of incorporating spatiotemporal wind data on the performance of wind forecasting neural networks. While previous studies have shown that including spatial data enhances the accuracy of such models, limited research has explored the impact of different spatial and temporal scales of input wind data on the learnability of neural network models. In this study, convolutional neural networks (CNNs) are employed and trained using various scales of spatiotemporal wind data. The research demonstrates that using spatiotemporally correlated data from the surrounding area and past time steps for training a CNN favorably affects the predictive performance of the model. The study proposes correlation analyses, including autocorrelation and Pearson correlation analyses, to unveil the influence of spatiotemporal wind characteristics on the predictive performance of different CNN models. The spatiotemporal correlations and performances of CNN models are investigated in three regions: Korea, the USA, and the UK. The findings reveal that regions with smaller deviations of autocorrelation coefficients (ACC) are more favorable for CNNs to learn the regional and seasonal wind characteristics. Specifically, the regions of Korea, the USA, and the UK exhibit maximum standard deviations of ACCs of 0.100, 0.043, and 0.023, respectively. The CNNs wind prediction performances follow the reverse order of the regions: UK, USA, and Korea. This highlights the significant impact of regional and seasonal wind conditions on the performance of the prediction models. [Display omitted] • 3D CNN-based wind velocity prediction. • Estimation of CNN learnability through spatiotemporal wind correlation analysis. • Discovery of influence of local geometric and seasonal wind on CNN prediction. • The proposed correlation analysis can aid in selecting yaw-control wind farm sites. [ABSTRACT FROM AUTHOR]

Background: The Rey Complex Figure Test (RCFT) has been widely used to evaluate the neurocognitive functions in various clinical groups with a broad range of ages. However, despite its usefulness, the scoring method is as complex as the figure. Such a complicated scoring system can lead to the risk of reducing the extent of agreement among raters. Although several attempts have been made to use RCFT in clinical settings in a digitalized format, little attention has been given to develop direct automatic scoring that is comparable to experienced psychologists. Therefore, we aimed to develop an artificial intelligence (AI) scoring system for RCFT using a deep learning (DL) algorithm and confirmed its validity. Methods: A total of 6680 subjects were enrolled in the Gwangju Alzheimer's and Related Dementia cohort registry, Korea, from January 2015 to June 2021. We obtained 20,040 scanned images using three images per subject (copy, immediate recall, and delayed recall) and scores rated by 32 experienced psychologists. We trained the automated scoring system using the DenseNet architecture. To increase the model performance, we improved the quality of training data by re-examining some images with poor results (mean absolute error (MAE) ≥ 5 [points]) and re-trained our model. Finally, we conducted an external validation with 150 images scored by five experienced psychologists. Results: For fivefold cross-validation, our first model obtained MAE = 1.24 [points] and R-squared ( R 2 ) = 0.977. However, after evaluating and updating the model, the performance of the final model was improved (MAE = 0.95 [points], R 2 = 0.986). Predicted scores among cognitively normal, mild cognitive impairment, and dementia were significantly different. For the 150 independent test sets, the MAE and R 2 between AI and average scores by five human experts were 0.64 [points] and 0.994, respectively. Conclusion: We concluded that there was no fundamental difference between the rating scores of experienced psychologists and those of our AI scoring system. We expect that our AI psychologist will be able to contribute to screen the early stages of Alzheimer's disease pathology in medical checkup centers or large-scale community-based research institutes in a faster and cost-effective way. [ABSTRACT FROM AUTHOR]

Background: A considerable volume of possible applications of artificial intelligence (AI) in the field of rhinology exists, and research in the area is rapidly evolving. Objective: This scoping review aims to provide a brief overview of all current literature on AI in the field of rhinology. Further, it aims to highlight gaps in the literature for future rhinology researchers. Methods: OVID MEDLINE (1946-2022) and EMBASE (1974-2022) were searched from January 1, 2017 until May 14, 2022 to identify all relevant articles. The Preferred Reporting Items for Systematic Reviews and Meta-analyses Extension for Scoping Reviews checklist was used to guide the review. Results: A total of 2420 results were identified of which 62 met the eligibility criteria. A further 17 articles were included through bibliography searching, for a total of 79 articles on AI in rhinology. Each year resulted in an increase in the number of publications, from 3 articles published in 2017 to 31 articles published in 2021. Articles were produced by authors from 22 countries with a relative majority coming from the USA (19%), China (19%), and South Korea (13%). Articles were placed into 1 of 5 categories: phenotyping/endotyping (n = 12), radiological diagnostics (n = 42), prognostication (n = 10), non-radiological diagnostics (n = 7), surgical assessment/planning (n = 8). Diagnostic or prognostic utility of the AI algorithms were rated as excellent (n = 29), very good (n = 25), good (n = 7), sufficient (n = 1), bad (n = 2), or was not reported/not applicable (n = 15). Conclusions: AI is experiencing an increasingly significant role in rhinology research. Articles are showing high rates of diagnostic accuracy and are being published at an almost exponential rate around the world. Utilizing AI in radiological diagnosis was the most published topic of research, however, AI in rhinology is still in its infancy and there are several topics yet to be thoroughly explored. [ABSTRACT FROM AUTHOR]

The Fukushima nuclear disaster highlights the importance of accurate and fast predictions of tsunami hazard to critical coastal infrastructure to devise mitigation strategies in both long-term and real-time events. Recently, deep learning models allowed us to make accurate and rapid forecasts on high dimensional, non-linear, and non-stationary time series data such as that associated with tsunami waveforms. Thus, this study uses a one-dimensional convolutional neural network (CNN) model to predict waveforms at cooling water intakes of nuclear power plant at Uljin in South Korea. The site is particularly vulnerable to tsunamis originating from the west coast of Japan. Data for the CNN model are generated by numerical simulation of 1107 cases of tsunami propagation initiating from fault locations. The time series data for waveforms were predicted at 13 virtual gauges located in the nearshore region of the study area, 10 of which were classified as observation points and 3 gauges situated at the cooling water intakes were categorized as target locations. The performance assessment of the model's forecasts showed excellent results with rapid predictions. The study highlights two main points: (i) deep learning models can be based on sparse waveform in situ data (such as that recorded by deep-ocean assessment and reporting of tsunamis or any locally operating monitoring stations for ocean waves) or numerically simulated data at only a few points along the dominant wave propagation direction, and (ii) deep learning models are fully capable of accurate and fast predictions of complex geo-hazards that prompt rapid emergency response to coordinate mitigation efforts. [ABSTRACT FROM AUTHOR]

Crude oil plays an important role in the global economy, as it contributes one-third of the energy consumption worldwide. However, despite its importance in policymaking and economic development, forecasting its price is still challenging due to its complexity and irregular price trends. Although a significant amount of research has been conducted to improve forecasting using external factors as well as machine-learning and deep-learning models, only a few studies have used hybrid models to improve prediction accuracy. In this study, we propose a novel hybrid model that captures the finer details and interconnections between multivariate factors to improve the accuracy of petroleum oil price prediction. Our proposed hybrid model integrates a convolutional neural network and a recurrent neural network with skip connections and is trained using petroleum oil prices and external data directly accessible from the official website of South Korea's national oil corporation and the official Yahoo Finance site. We compare the performance of our univariate and multivariate models in terms of the Pearson correlation, mean absolute error, mean squared error, root mean squared error, and R squared ( R 2 ) evaluation metrics. Our proposed models exhibited significantly better performance than the existing models based on long short-term memory and gated recurrent units, showing correlations of 0.985 and 0.988, respectively, for 10-day price predictions and obtaining better results for longer prediction periods when compared with other deep-learning models. We validated that our proposed model with skip connections outperforms the benchmark models and showed that the convolutional neural network using gated recurrent units with skip connections is superior to the compared models. The findings suggest that, to some extent, relying on a single source of data is ineffective in predicting long-term changes in oil prices, and thus, to develop a better prediction model based on time-series based data, it is necessary to take a multivariate approach and develop an efficient computational model with skip connections. [ABSTRACT FROM AUTHOR]

Remote sensing image retrieval (RSIR) is the process of searching for identical areas by investigating the similarities between a query image and the database images. RSIR is a challenging task owing to the time difference, viewpoint, and coverage area depending on the shooting circumstance, resulting in variations in the image contents. In this paper, we propose a novel method based on a coarse-to-fine strategy, which makes a deep network more robust to the variations in remote sensing images. Moreover, we propose a new triangular loss function to consider the whole relation within the tuple. This loss function improves the retrieval performance and demonstrates better performance in terms of learning the detailed information in complex remote sensing images. To verify our methods, we experimented with the Google Earth South Korea dataset, which contains 40,000 images, using the evaluation metric Recall@n. In all experiments, we obtained better performance results than those of the existing retrieval training methods. Our source code and Google Earth South Korea dataset are available online. [ABSTRACT FROM AUTHOR]

Recently, IT technologies related to the Fourth Industrial Revolution (4IR), such as artificial intelligence (AI), Internet of things (IoT), cloud computing, and edge computing have been studied. Although there are many used clothing occurrences with 61 trillion worn of clothing consumption per year in Korea, it is not properly collected due to the efficiency of the used clothing collection system, and the collected used clothing is not properly recycled due to insufficient recycling system, lack of skilled labor force, and health problems of workers. To solve this problem, this study proposes a deep learning clothing classification system (DLCCS) using cloud and edge computing. The system proposed is to classify clothing image data input from camera terminals installed in various clothing classification sites in various regions into two classes, as well as nine classes, by deep learning using convolution neural network (CNN). And the classification results are stored in the cloud through edge computing. The edge computing enables the analysis of the data of the Internet of Things (IoT) device on the edge of the network before transmitting it to the cloud. The performance evaluation parameters that are considered for the proposed research study are transmission velocity and latency. Proposed system can efficiently improve the process and automation in the classification and processing of recycled clothing in various places. It is also expected that the waste of clothing resources and health problems of clothing classification workers will be improved. [ABSTRACT FROM AUTHOR]

In the food industry, many companies inspect the X-ray images of foods for foreign bodies. One promising approach for detecting food items with foreign bodies (i.e., abnormal food items) in an X-ray image is the use of image classification methods such as convolutional neural networks (CNNs), which can help automatically detect abnormal food items. One of the important issues in training a good CNN model is obtaining a large training dataset. However, it is often difficult to obtain such a dataset because it requires a manual labeling task that is time-consuming and involves a considerable amount of human effort. In addition, it is increasingly difficult to conduct a manual labeling when the food items overlap in an X-ray image. In this regard, we propose an automatic labeling method to train CNN models for detecting abnormal food items from their X-ray images. The proposed method prepares additional X-ray images that show only foreign bodies. Then, it overlaps an original X-ray image with an additional image and identifies the original X-ray image as abnormal if the overlapped area exceeds a predetermined threshold. To verify the performance of the proposed method, we conducted a case study at an X-ray inspection facility in Korea. We found that the proposed method is effective in detecting and classifying every food item in an X-ray image. [ABSTRACT FROM AUTHOR]

In this study, we developed a deep learning model to identify patients with tongue cancer based on a validated dataset comprising oral endoscopic images. We retrospectively constructed a dataset of 12,400 verified endoscopic images from five university hospitals in South Korea, collected between 2010 and 2020 with the participation of otolaryngologists. To calculate the probability of malignancy using various convolutional neural network (CNN) architectures, several deep learning models were developed. Of the 12,400 total images, 5576 images related to the tongue were extracted. The CNN models showed a mean area under the receiver operating characteristic curve (AUROC) of 0.845 and a mean area under the precision-recall curve (AUPRC) of 0.892. The results indicate that the best model was DenseNet169 (AUROC 0.895 and AUPRC 0.918). The deep learning model, general physicians, and oncology specialists had sensitivities of 81.1%, 77.3%, and 91.7%; specificities of 86.8%, 75.0%, and 90.9%; and accuracies of 84.7%, 75.9%, and 91.2%, respectively. Meanwhile, fair agreement between the oncologist and the developed model was shown for cancer diagnosis (kappa value = 0.685). The deep learning model developed based on the verified endoscopic image dataset showed acceptable performance in tongue cancer diagnosis. [ABSTRACT FROM AUTHOR]

Yoon, J.; Kim, S.; Kim, I., and Song, D., 2021. Detection of wave parameters using CCTV images-based on deep learning algorithm. In: Lee, J.L.; Suh, K.-S.; Lee, B.; Shin, S., Lee, J. (eds.), Crisis and Integrated Management for Coastal and Marine Safety. Journal of Coastal Research, Special Issue No. 114, pp. 281–284. Coconut Creek (Florida), ISSN 0749-0208. The closed-circuit television (CCTV) systems have been used for various applications in oceanic research fields. CCTV is an effective installation method for offshore monitoring that can conveniently and continuously observe the coastal region using the visible or infrared light in the electromagnetic spectrum. However, in the case of wave-observing CCTV images, there is a problem: it is difficult to extract the corresponding feature points between the video frames, which causes of inaccurate measurement of wave parameters. Recently, in the field of machine learning technology, deep learning-based video analysis that does not require the detection of feature points has been proposed. In this paper, we analyze wave-observing CCTV images with deep learning method in particular convolution neural network, and find the optimal method of observing waves through CCTV by three different datasets. For training, the CCTV data from the Samcheok Beach in the Republic of Korea were used. Wave observation data, which were used as input for machine learning, were collected by an acoustic wave and current profiler (AWAC). Moreover, to make up for insufficient observation data, the data to enhance the prediction model through deep learning were augmented. The results of this study confirm that the deep learning algorithm can be utilized to detect wave period and wave height. Consequently, continuous CCTV images can be combined with deep learning algorithm to clarify the complex characteristics of wave distribution and its temporal changes. [ABSTRACT FROM AUTHOR]

Introduction: This scoping review aims to provide an overview of the existing evidence on the use of artificial intelligence (AI) and machine learning (ML) in orthodontics, its translation into clinical practice, and what limitations do exist that have precluded their envisioned application. Methods: A scoping review of the literature was carried out following the PRISMA-ScR guidelines. PubMed was searched until July 2020. Results: Sixty-two articles fulfilled the inclusion criteria. A total of 43 out of the 62 studies (69.35%) were published this last decade. The majority of these studies were from the USA (11), followed by South Korea (9) and China (7). The number of studies published in non-orthodontic journals (36) was more extensive than in orthodontic journals (26). Artificial Neural Networks (ANNs) were found to be the most commonly utilized AI/ML algorithm (13 studies), followed by Convolutional Neural Networks (CNNs), Support Vector Machine (SVM) (9 studies each), and regression (8 studies). The most commonly studied domains were diagnosis and treatment planning—either broad-based or specific (33), automated anatomic landmark detection and/or analyses (19), assessment of growth and development (4), and evaluation of treatment outcomes (2). The different characteristics and distribution of these studies have been displayed and elucidated upon therein. Conclusion: This scoping review suggests that there has been an exponential increase in the number of studies involving various orthodontic applications of AI and ML. The most commonly studied domains were diagnosis and treatment planning, automated anatomic landmark detection and/or analyses, and growth and development assessment. [ABSTRACT FROM AUTHOR]

The aim of this study is to evaluate and compare the performances of 5 machine learning (ML) techniques for predicting the spatial probability of landslide at Atsuma, Japan, and Mt. Umyeon, Korea. 5 ML models used are Naïve Bayes (NB), ensemble learning (random forest (RF) and adaboost (AB)), and deep learning (multilayer perceptron (MLP) and convolutional neural network (CNN)) models. Real landslide events at the study areas are randomly separated to the training set for landslide mapping and the validation set for assessing performance. To assess the performance of the used models, the resulting models are validated using receiver operating characteristic (ROC) curve. The success rate curves show that the areas under the curve (AUC) for the NB, RF, AB, MLP, and CNN are 85.1, 88.8, 88.6, 87.5, and 95.0%, respectively, at Atsuma and 68.7, 85.6, 90.5, 81.6, and 92.0%, respectively, at Mt. Umyeon. Similarly, the validation results show that the areas under the curve for the NB, RF, AB, MLP, and CNN are 84.3, 87.1, 87.1, 86.7, and 89.7%, respectively, at Atsuma and 64.9, 85.5, 83.9, 84.7, and 90.5%, respectively, at Mt. Umyeon. In addition, statistical tests such as Chi-square test and difference of proportions test show that all classified landslide susceptibility maps have statistical significance and the significant difference in classified landslide susceptibility maps from different ML models. The comparison results among 5 ML models show that the CNN model had the best performance and NB model had the worst performance in both study areas. [ABSTRACT FROM AUTHOR]

In recent years, the application of a smart city in the healthcare sector via loT systems has continued to grow exponentially and various advanced network intrusions have emerged since these loT devices are being connected. Previous studies focused on security threat detection and blocking technologies that rely on testbed data obtained from a single medical IoT device or simulation using a well-known dataset, such as the NSL-KDD dataset. However, such approaches do not reflect the features that exist in real medical scenarios, leading to failure in potential threat detection. To address this problem, we proposed a novel intrusion classification architecture known as a Multi-class Classification based Intrusion Detection Model (M-IDM), which typically relies on data collected by real devices and the use of convolutional neural networks (i.e., it exhibits better performance compared with conventional machine learning algorithms, such as naïve Bayes, support vector machine (SVM)). Unlike existing studies, the proposed architecture employs the actual healthcare IoT environment of National Cancer Center in South Korea and actual network data from real medical devices, such as a patient's monitors (i.e., electrocardiogram and thermometers). The proposed architecture classifies the data into multiple classes: Critical, informal, major, and minor, for intrusion detection. Further, we experimentally evaluated and compared its performance with those of other conventional machine learning algorithms, including naïve Bayes, SVM, and logistic regression, using neural networks. [ABSTRACT FROM AUTHOR]

As the deep learning algorithm has become a popular data analysis technique, atmospheric scientists should have a balanced perception of its strengths and limitations so that they can provide a powerful analysis of complex data with well-established procedures. Despite the enormous success of the algorithm in numerous applications, certain issues related to its applications in air quality forecasting (AQF) require further analysis and discussion. This study addresses significant limitations of an advanced deep learning algorithm, the convolutional neural network (CNN), in two common applications: (i) a real-time AQF model and (ii) a post-processing tool in a dynamical AQF model, the Community Multi-scale Air Quality Model (CMAQ). In both cases, the CNN model shows promising accuracy for ozone prediction 24 h in advance in both the United States of America and South Korea (with an overall index of agreement exceeding 0.8). For the first case, we use the wavelet transform to determine the reasons behind the poor performance of CNN during the nighttime, cold months, and high-ozone episodes. We find that when fine wavelet modes (hourly and daily) are relatively weak or when coarse wavelet modes (weekly) are strong, the CNN model produces less accurate forecasts. For the second case, we use the dynamic time warping (DTW) distance analysis to compare post-processed results with their CMAQ counterparts (as a base model). For CMAQ results that show a consistent DTW distance from the observation, the post-processing approach properly addresses the modeling bias with predicted indexes of agreement exceeding 0.85. When the DTW distance of CMAQ versus observation is irregular, the post-processing approach is unlikely to perform satisfactorily. Awareness of the limitations in CNN models will enable scientists to develop more accurate regional or local air quality forecasting systems by identifying the affecting factors in high-concentration episodes. [ABSTRACT FROM AUTHOR]

Accurate electrocardiogram (ECG) interpretation is crucial in the clinical ECG workflow because it is most likely associated with a disease that can cause major problems in the body. In this study, we proposed an ECG-signal multi-classification model using deep learning. We used a squeeze-and-excitation residual network (SE-ResNet), which is a residual network(ResNet) with a squeeze-and-excitation block. Experiments were performed for seven different types of lead-II ECG data obtained from the Korea University Anam Hospital in South Korea. These seven types are normal sinus rhythm, atrial fibrillation, atrial flutter, sinus bradycardia, sinus tachycardia, premature ventricular contraction and first-degree atrioventricular block. We compared the SE-ResNet with a ResNet, as a baseline model, for various depths of layer (18/34/50/101/152). We confirmed that the SE-ResNet had better classification performance than the ResNet, for all layers. The SE-ResNet classifier with 152 layers achieved F1 scores of 97.05% for seven-class classifications. Our model surpassed the baseline model, ResNet, by +1.40% for the seven-class classifications. For ECG-signal multi-classification, considering the F1 scores, the SE-ResNet might be better than the ResNet baseline model. [ABSTRACT FROM AUTHOR]

Featured Application: Forecasting particulate matter of size less than 2.5 µm (PM 2.5 ) in big cities is a major challenge for scientific community. In addition to environmental impacts, these particulate matter cause various diseases, such as cardiopulmonary disease, stroke, lung cancer and even neurological disorders. Forecasting high PM 2.5 events helps to raise awareness among people to take precautionary measures, such as limit outdoor activities, use masks, etc. In the future, advanced Machine Learning (ML) based PM 2.5 forecasting will help to reduce the cost of sampling of PM 2.5 , such as sampler and equipment costs, which are needed to measure the concentration of particulate matter in air. Air pollution not only damages the environment but also leads to various illnesses such as respiratory tract and cardiovascular diseases. Nowadays, estimating air pollutants concentration is becoming very important so that people can prepare themselves for the hazardous impact of air pollution beforehand. Various deterministic models have been used to forecast air pollution. In this study, along with various pollutants and meteorological parameters, we also use the concentration of the pollutants predicted by the community multiscale air quality (CMAQ) model which are strongly related to PM 2.5 concentration. After combining these parameters, we implement various machine learning models to predict the hourly forecast of PM 2.5 concentration in two big cities of South Korea and compare their results. It has been shown that Long Short Term Memory network outperforms other well-known gradient tree boosting models, recurrent, and convolutional neural networks. [ABSTRACT FROM AUTHOR]

This study uses deep learning algorithms to predict the rotational speed of the turbine generator in an oscillating water column-type wave energy converter (OWC-WEC). The effective control and operation of OWC-WECs remain a challenge due to the variation in the input wave energy and the significantly high peak-to-average power ratio. Therefore, the rated power control of OWC-WECs is essential for increasing the operating time and power output. The existing rated power control method is based on the instantaneous rotational speed of the turbine generator. However, due to physical limitations, such as the valve operating time, a more refined rated power control method is required. Therefore, we propose a method that applies a deep learning algorithm. Our method predicts the instantaneous rotational speed of the turbine generator and the rated power control is performed based on the prediction. This enables precise control through the operation of the high-speed safety valve before the energy input exceeds the rated value. The prediction performances for various algorithms, such as a multi-layer perceptron (MLP), recurrent neural network (RNN), long short-term memory (LSTM), and convolutional neural network (CNN), are compared. In addition, the prediction performance of each algorithm as a function of the input datasets is investigated using various error evaluation methods. For the training datasets, the operation data from an OWC-WEC west of Jeju in South Korea is used. The analysis demonstrates that LSTM exhibits the most accurate prediction of the instantaneous rotational speed of a turbine generator and CNN has visible advantages when the data correlation is low. [ABSTRACT FROM AUTHOR]

Edge intelligence (EI) has received a lot of interest because it can reduce latency, increase efficiency, and preserve privacy. More significantly, as the Internet of Things (IoT) has proliferated, billions of portable and embedded devices have been interconnected, producing zillions of gigabytes on edge networks. Thus, there is an immediate need to push AI (artificial intelligence) breakthroughs within edge networks to achieve the full promise of edge data analytics. EI solutions have supported digital technology workloads and applications from the infrastructure level to edge networks; however, there are still many challenges with the heterogeneity of computational capabilities and the spread of information sources. We propose a novel event-driven deep-learning framework, called EDL-EI (event-driven deep learning for edge intelligence), via the design of a novel event model by defining events using correlation analysis with multiple sensors in real-world settings and incorporating multi-sensor fusion techniques, a transformation method for sensor streams into images, and lightweight 2-dimensional convolutional neural network (CNN) models. To demonstrate the feasibility of the EDL-EI framework, we presented an IoT-based prototype system that we developed with multiple sensors and edge devices. To verify the proposed framework, we have a case study of air-quality scenarios based on the benchmark data provided by the USA Environmental Protection Agency for the most polluted cities in South Korea and China. We have obtained outstanding predictive accuracy (97.65% and 97.19%) from two deep-learning models on the cities' air-quality patterns. Furthermore, the air-quality changes from 2019 to 2020 have been analyzed to check the effects of the COVID-19 pandemic lockdown. [ABSTRACT FROM AUTHOR]

Weather is affected by a complex interplay of factors, including topography, location, and time. For the prediction of temperature in Korea, it is necessary to use data from multiple regions. To this end, we investigate the use of deep neural-network-based temperature prediction model time-series weather data obtained from an automatic weather station and image data from a regional data assimilation and prediction system (RDAPS). To accommodate such different types of data into a single model, a bidirectional long short-term memory (BLSTM) model and a convolutional neural network (CNN) model are chosen to represent the features from the time-series observed data and the RDAPS image data. The two types of features are combined to produce temperature predictions for up to 14 days in the future. The performance of the proposed temperature prediction model is evaluated by objective measures, including the root mean squared error and mean bias error. The experiments demonstrated that the proposed model combining both the observed and RDAPS image data is better in all performance measures for all prediction periods compared with the BLSTM-based model using observed data and the CNN-BLSTM-based model using RDAPS image data alone. [ABSTRACT FROM AUTHOR]

River monitoring and predicting analysis for establishing pollutant loads management require numerous budgets and human resources. However, it is general that the number of government officials in charge of these tasks is few. Although the government has been commissioning a study related to river management to experts, it has been inevitable to avoid the consumption of a massive budget because the characteristics of pollutant loads present various patterns according to topographic of the watershed, such as topology like South Korea. To address this, previous studies have used conceptual and empirical models and have recently used artificial neural network models. The conceptual model has a shortcoming in which it required massive data and has vexatious that has to enforce the sensitivity and uncertain analysis. The empirical model and artificial neural network (ANN) need lower data than a conceptual model; however, these models have a flaw that could not reflect the topographical characteristic. To this end, this study has used a convolution neural network (CNN), one of the deep learning algorithms, to reflect the topographical characteristic and had estimated the pollutant loads of ungauged watersheds. The estimation results for the biochemical oxygen demand (BOD) and total phosphorus (TP) loads for three ungauged watersheds were all excellent. However, prediction results with low accuracy were obtained when the hydrological images of a watershed with a land cover status different from the ungauged watersheds were used as training data for the CNN model. [ABSTRACT FROM AUTHOR]

Recently, developing countries have steadily been pushing for the construction of stream-oriented smart cities, breaking away from the existing old-town-centered development in the past. Due to the accelerating effects of climate change along with such urbanization, it is imperative for urban rivers to establish a flood warning system that can predict the amount of high flow rates of accuracy in engineering, compared to using the existing Computational Fluid Dynamics (CFD) models for disaster prevention. In this study, in the case of streams where missing data existed or only small observations were obtained, the variation in flow rates could be predicted with only the appropriate deep learning models, using only limited time series flow data. In addition, the selected deep learning model allowed the minimum number of input learning data to be determined. In this study, the time series flow rates were predicted by applying the deep learning models to the Han River, which is a highly urbanized stream that flows through the capital of Korea, Seoul and has a large seasonal variation in the flow rate. The deep learning models used are Convolution Neural Network (CNN), Simple Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM) and Gated Recurrent Unit (GRU). Sequence lengths for time series runoff data were determined first to assess the accuracy and applicability of the deep learning models. By analyzing the forecast results of the outflow data of the Han River, sequence length for 14 days was appropriate in terms of the predicted accuracy of the model. In addition, the GRU model is effective for deep learning models that use time series data of the region with large fluctuations in flow rates, such as the Han River. Furthermore, through this study, it was possible to propose the minimum number of training data that could provide flood warning system with an effective flood forecasting system although the number of input data such as flow rates secured in new towns developed around rivers was insufficient. [ABSTRACT FROM AUTHOR]

Malware detection of non-executables has recently been drawing much attention because ordinary users are vulnerable to such malware. Hangul Word Processor (HWP) is software for editing non-executable text files and is widely used in South Korea. New malware for HWP files continues to appear because of the circumstances between South Korea and North Korea. There have been various studies to solve this problem, but most of them are limited because they require a large amount of effort to define features based on expert knowledge. In this study, we designed a convolutional neural network to detect malware within HWP files. Our proposed model takes a raw byte stream as input and predicts whether it contains malicious actions or not. To incorporate highly variable lengths of HWP byte streams, we propose a new padding method and a spatial pyramid average pooling layer. We experimentally demonstrate that our model is not only effective, but also efficient. [ABSTRACT FROM AUTHOR]

Particulate matter (PM) has become a problem worldwide, with many deleterious health effects such as worsened asthma, affected lungs, and various toxin-induced cancers. The International Agency for Research on Cancer (IARC) under the World Health Organization (WHO) has designated PM as a group 1 carcinogen. Although Korea Environment Corporation forecasts the status of outdoor PM four times a day, whichever is higher among PM10 and PM2.5. Korea Environment Corporation forecasts for the stages of PM. It remains difficult to predict the value of PM when going out. We correlate air quality and solar terms, address format, and weather data, and PM in the Korea. We analyzed the correlation between address format, air quality data, and weather data, and PM. We evaluated performance according to the sequence length and batch size and found the best outcome with a sequence length of 7 days, and a batch size of 96. We performed PM prediction using the Long Short-Term Recurrent Unit (LSTM), the Convolutional Neural Network (CNN), and the Gated Recurrent Unit (GRU) models. The CNN model suffered the limitation of only predicting from the training data, not from the test data. The LSTM and GRU models generated similar prediction results. We confirmed that the LSTM model has higher accuracy than the other two models. [ABSTRACT FROM AUTHOR]