• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.10
• /
• pp.239-246
• /
• 2020

In the medical field where artificial intelligence technology is introduced, research related to clinical decision support system(CDSS) in relation to diagnosis and prediction is actively being conducted. In particular, medical imaging-based disease diagnosis area applied AI technologies at various products. However, medical imaging data consists of inconsistent data, and it is a reality that it takes considerable time to prepare and use it for research. This paper describes a one-stop AI learning platform for converting to medical image standard R_CDM(Radiology Common Data Model) and supporting AI algorithm development research based on the dataset. To this, the focus is on linking with the existing CDM(common data model) and model the system, including the schema of the medical imaging standard model and report information for multi-center research based on DICOM(Digital Imaging and Communications in Medicine) tag information. And also, we show the execution results based on generated datasets through the AI learning platform. As a proposed platform, it is expected to be used for various image-based artificial intelligence researches.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.241-251
• /
• 2022

Diagnosis and management of customer's skin condition is an important essential function in the cosmetics and beauty industry. As the social media environment spreads and generalizes to all fields of society, the interaction of questions and answers to various and delicate concerns and requirements regarding the diagnosis and management of skin conditions is being actively dealt with in the social media community. However, since social media information is very diverse and atypical big data, an intelligent skin condition diagnosis system that combines appropriate skin condition information analysis and artificial intelligence technology is necessary. In this paper, we developed the skin condition diagnosis system SCDIS to intelligently diagnose and manage the skin condition of customers by processing the text analysis information of social media into learning data. In SCDIS, an artificial neural network model, AnnTFIDF, that automatically diagnoses skin condition types using artificial neural network technology, a deep learning machine learning method, was built up and used. The performance of the artificial neural network model AnnTFIDF was analyzed using test sample data, and the accuracy of the skin condition type diagnosis prediction value showed a high performance of about 95%. Through the experimental and performance analysis results of this paper, SCDIS can be evaluated as an intelligent tool that can be used efficiently in the skin condition analysis and diagnosis management process in the cosmetic and beauty industry. And this study can be used as a basic research to solve the new technology trend, customized cosmetics manufacturing and consumer-oriented beauty industry technology demand.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.383-400
• /
• 2023

Air pollution-related diseases are escalating worldwide, with the World Health Organization (WHO) estimating approximately 7 million annual deaths in 2022. The rapid expansion of industrial facilities, increased emissions from various sources, and uncontrolled release of odorous substances have brought air pollution to the forefront of societal concerns. In South Korea, odor is categorized as an independent environmental pollutant, alongside air and water pollution, directly impacting the health of local residents by causing discomfort and aversion. However, the current odor management system in Korea remains inadequate, necessitating improvements. This study aims to enhance the odor management system by analyzing 1,010,749 data points collected from odor sensors located in Osong, Chungcheongbuk-do, using an Ensemble-Based Multi-Region Integrated Odor Concentration Prediction Model. The research results demonstrate that the model based on the XGBoost algorithm exhibited superior performance, with an RMSE of 0.0096, significantly outperforming the single-region model (0.0146) with a 51.9% reduction in mean error size. This underscores the potential for increasing data volume, improving accuracy, and enabling odor prediction in diverse regions using a unified model through the standardization of odor concentration data collected from various regions.

• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.33-41
• /
• 2023

As carbon-free has been getting interest, renewable energy sources have been increasing. However, renewable energy is intermittent and variable so it is difficult to predict the produced electrical energy from a renewable energy source. In this study, digital-twin concept is applied to solve difficulties in predicting electrical energy from a renewable energy source. Considering that rotation of wind turbine has high correlation with produced electrical energy, a model which simulates rotation in the drivetrain of a wind turbine is developed. The base of a drivetrain simulation model is set with well-known state equation in mechanical engineering, which simulates the rotating system. Simulation based machine learning is conducted to get unknown parameters which are not provided by manufacturer. The simulation is repeated and parameters in simulation model are corrected after each simulation by optimization algorithm. The trained simulation model is validated with 27 real wind turbine operation data set. The simulation model shows 4.41% error in average compared to real wind turbine operation data set. Finally, it is assessed that the drivetrain simulation model represents the real wind turbine drivetrain system well. It is expected that wind-energy-prediction accuracy would be improved as wind turbine digital twin including the developed drivetrain simulation model is applied.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1181-1189
• /
• 2022

Clouds are composed of tiny water droplets, ice crystals, or mixtures suspended in the atmosphere and cover about two-thirds of the Earth's surface. Cloud detection in satellite images is a very difficult task to separate clouds and non-cloud areas because of similar reflectance characteristics to some other ground objects or the ground surface. In contrast to thick clouds, which have distinct characteristics, thin transparent clouds have weak contrast between clouds and background in satellite images and appear mixed with the ground surface. In order to overcome the limitations of transparent clouds in cloud detection, this study conducted cloud detection focusing on transparent clouds using machine learning techniques (Random Forest [RF], Convolutional Neural Networks [CNN]). As reference data, Cloud Mask and Cirrus Mask were used in MOD35 data provided by MOderate Resolution Imaging Spectroradiometer (MODIS), and the pixel ratio of training data was configured to be about 1:1:1 for clouds, transparent clouds, and clear sky for model training considering transparent cloud pixels. As a result of the qualitative comparison of the study, bothRF and CNN successfully detected various types of clouds, including transparent clouds, and in the case of RF+CNN, which mixed the results of the RF model and the CNN model, the cloud detection was well performed, and was confirmed that the limitations of the model were improved. As a quantitative result of the study, the overall accuracy (OA) value of RF was 92%, CNN showed 94.11%, and RF+CNN showed 94.29% accuracy.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.925-938
• /
• 2022

Agricultural reservoirs are an important water resource nationwide and vulnerable to abnormal climate effects such as drought caused by climate change. Therefore, it is required enhanced management for appropriate operation. Although water-level tracking is necessary through continuous monitoring, it is challenging to measure and observe on-site due to practical problems. This study presents an objective comparison between multiple AI models for water-body extraction using radar images that have the advantages of wide coverage, and frequent revisit time. The proposed methods in this study used Sentinel-1 Synthetic Aperture Radar (SAR) images, and unlike common methods of water extraction based on optical images, they are suitable for long-term monitoring because they are less affected by the weather conditions. We built four AI models such as Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), and Automated Machine Learning (AutoML) using drone images, sentinel-1 SAR and DSM data. There are total of 22 reservoirs of less than 1 million tons for the study, including small and medium-sized reservoirs with an effective storage capacity of less than 300,000 tons. 45 images from 22 reservoirs were used for model training and verification, and the results show that the AutoML model was 0.01 to 0.03 better in the water Intersection over Union (IoU) than the other three models, with Accuracy=0.92 and mIoU=0.81 in a test. As the result, AutoML performed as well as the classical machine learning methods and it is expected that the applicability of the water-body extraction technique by AutoML to monitor reservoirs automatically.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.127-148
• /
• 2020

The data center is a physical environment facility for accommodating computer systems and related components, and is an essential foundation technology for next-generation core industries such as big data, smart factories, wearables, and smart homes. In particular, with the growth of cloud computing, the proportional expansion of the data center infrastructure is inevitable. Monitoring the health of these data center facilities is a way to maintain and manage the system and prevent failure. If a failure occurs in some elements of the facility, it may affect not only the relevant equipment but also other connected equipment, and may cause enormous damage. In particular, IT facilities are irregular due to interdependence and it is difficult to know the cause. In the previous study predicting failure in data center, failure was predicted by looking at a single server as a single state without assuming that the devices were mixed. Therefore, in this study, data center failures were classified into failures occurring inside the server (Outage A) and failures occurring outside the server (Outage B), and focused on analyzing complex failures occurring within the server. Server external failures include power, cooling, user errors, etc. Since such failures can be prevented in the early stages of data center facility construction, various solutions are being developed. On the other hand, the cause of the failure occurring in the server is difficult to determine, and adequate prevention has not yet been achieved. In particular, this is the reason why server failures do not occur singularly, cause other server failures, or receive something that causes failures from other servers. In other words, while the existing studies assumed that it was a single server that did not affect the servers and analyzed the failure, in this study, the failure occurred on the assumption that it had an effect between servers. In order to define the complex failure situation in the data center, failure history data for each equipment existing in the data center was used. There are four major failures considered in this study: Network Node Down, Server Down, Windows Activation Services Down, and Database Management System Service Down. The failures that occur for each device are sorted in chronological order, and when a failure occurs in a specific equipment, if a failure occurs in a specific equipment within 5 minutes from the time of occurrence, it is defined that the failure occurs simultaneously. After configuring the sequence for the devices that have failed at the same time, 5 devices that frequently occur simultaneously within the configured sequence were selected, and the case where the selected devices failed at the same time was confirmed through visualization. Since the server resource information collected for failure analysis is in units of time series and has flow, we used Long Short-term Memory (LSTM), a deep learning algorithm that can predict the next state through the previous state. In addition, unlike a single server, the Hierarchical Attention Network deep learning model structure was used in consideration of the fact that the level of multiple failures for each server is different. This algorithm is a method of increasing the prediction accuracy by giving weight to the server as the impact on the failure increases. The study began with defining the type of failure and selecting the analysis target. In the first experiment, the same collected data was assumed as a single server state and a multiple server state, and compared and analyzed. The second experiment improved the prediction accuracy in the case of a complex server by optimizing each server threshold. In the first experiment, which assumed each of a single server and multiple servers, in the case of a single server, it was predicted that three of the five servers did not have a failure even though the actual failure occurred. However, assuming multiple servers, all five servers were predicted to have failed. As a result of the experiment, the hypothesis that there is an effect between servers is proven. As a result of this study, it was confirmed that the prediction performance was superior when the multiple servers were assumed than when the single server was assumed. In particular, applying the Hierarchical Attention Network algorithm, assuming that the effects of each server will be different, played a role in improving the analysis effect. In addition, by applying a different threshold for each server, the prediction accuracy could be improved. This study showed that failures that are difficult to determine the cause can be predicted through historical data, and a model that can predict failures occurring in servers in data centers is presented. It is expected that the occurrence of disability can be prevented in advance using the results of this study.

• 대한공업교육학회지
• /
• v.34 no.2
• /
• pp.267-285
• /
• 2009

The collaborative learning has been considered as an efficient teaching model and under the recent basic learning environment, even face-to-face classroom circumstance rapidly increases the courses of blended learning which utilize the merits of e-learning environment. Nonetheless, the study on the strategy for systematic blended learning is quite scarce. In this study, the survey was done for developing the blended learning strategy, based on the collaborative learning model at the face-to-face environment and judging the satisfaction on the courses which the model was applied to. The survey consists of demographic questions, satisfaction in the whole courses, satisfaction in the collaborative learning under the blended learning environment and satisfaction in the blended learning strategy and support tools applied to each step of the learning. The result of this study is as follows. First, in response to the question that the blended learning can complement the face-to-face classroom courses, the respondents represented average 4.09 at 5-point Likert scale. And to the question whether the collaborative learning is more efficient under the blended learning environment than the face-to-face classroom, the response corresponds to 4.06 scale on the average. Second, as for the satisfaction in the blended learning strategy and support tools applied to the each step of the blended learning, the satisfaction degree is analyzed as high as over 4.0 on the average toward all the questions. Third, regarding the support tools used for the blended learning strategy, the learners consider the tools as most helpful in order of chatting, team community, mail & note and archive. Lastly, I would like to suggest that the study result should be highly reflected in constructing the collaborative learning module of learning control system in the future.