• Journal of Internet Computing and Services
• /
• v.8 no.6
• /
• pp.43-53
• /
• 2007

Intrusion detection system(IDS) has recently evolved while combining signature-based detection approach with anomaly detection approach. Although signature-based IDS tools have been commonly used by utilizing machine learning algorithms, they only detect network intrusions with already known patterns, Ideal IDS tools should always keep the signature database of your detection system up-to-date. The system needs to generate the signatures to detect new possible attacks while monitoring and analyzing incoming network data. In this paper, we propose a new outlier cluster detection algorithm with density (or influence) function, Our method assumes that an outlier is a kind of cluster with similar instances instead of a single object in the context of network intrusion, Through extensive experiments using KDD 1999 Cup Intrusion Detection dataset. we show that the proposed method outperform the conventional outlier detection method using Euclidean distance function, specially when attacks occurs frequently.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.12
• /
• pp.123-129
• /
• 2014

In accordance with the development of various convergence devices, cameras are being used in many types of the systems such as security system, driver assistance device and so on, and a lot of people are exposed to these system. Therefore the system should be able to recognize the human behavior and support some useful functions with the information that is obtained from detected human behavior. In this paper we use a machine learning approach based on 2D image and propose the human behavior pattern recognition methods. The proposed methods can provide valuable information to support some useful function to user based on the recognized human behavior. First proposed one is "phone call behavior" recognition. If a camera of the black box, which is focused on driver in a car, recognize phone call pose, it can give a warning to driver for safe driving. The second one is "looking ahead" recognition for driving safety where we propose the decision rule and method to decide whether the driver is looking ahead or not. This paper also shows usefulness of proposed recognition methods with some experiment results in real time.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.3
• /
• pp.74-99
• /
• 2022

Surface ozone is produced by photochemical reactions of nitrogen oxides(NOx) and volatile organic compounds(VOCs) emitted from vehicles and industrial sites, adversely affecting vegetation and the human body. In South Korea, ozone is monitored in real-time at stations(i.e., point measurements), but it is difficult to monitor and analyze its continuous spatial distribution. In this study, surface ozone concentrations were interpolated to have a spatial resolution of 1.5km every hour using the stacking ensemble technique, followed by a 5-fold cross-validation. Base models for the stacking ensemble were cokriging, multi-linear regression(MLR), random forest(RF), and support vector regression(SVR), while MLR was used as the meta model, having all base model results as additional input variables. The results showed that the stacking ensemble model yielded the better performance than the individual base models, resulting in an averaged R of 0.76 and RMSE of 0.0065ppm during the study period of 2020. The surface ozone concentration distribution generated by the stacking ensemble model had a wider range with a spatial pattern similar with terrain and urbanization variables, compared to those by the base models. Not only should the proposed model be capable of producing the hourly spatial distribution of ozone, but it should also be highly applicable for calculating the daily maximum 8-hour ozone concentrations.

• Journal of Bio-Environment Control
• /
• v.29 no.3
• /
• pp.277-284
• /
• 2020

To increase the utilization of the intelligent methodology of smart farm management, estimation modeling techniques are required to assess prior examination of crops and environment changes in realtime. A mandatory environmental factor such as CO₂ is challenging to establish a reliable estimation model in time domain accounted for indoor agricultural facilities where various correlated variables are highly coupled. Thus, this study was conducted to develop an artificial neural network for reducing time complexity by using environmental information distributed in adjacent areas from a time perspective as input and output variables as CO₂. The environmental factors in the smart farm were continuously measured using measuring devices that integrated sensors through experiments. Modeling 1 predicted by the mean data of the experiment period and modeling 2 predicted by the day-to-day data were constructed to predict the correlation of CO₂. Modeling 2 predicted by the previous day's data learning performed better than Modeling 1 predicted by the 60-day average value. Until 30 days, most of them showed a coefficient of determination between 0.70 and 0.88, and Model 2 was about 0.05 higher. However, after 30 days, the modeling coefficients of both models showed low values below 0.50. According to the modeling approach, comparing and analyzing the values of the determinants showed that data from adjacent time zones were relatively high performance at points requiring prediction rather than a fixed neural network model.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.85-92
• /
• 2019

A 3D virtual character playing a role in a digital story-telling has a unique style in its appearance and motion. Because the style reflects the unique personality of the character, it is very important to preserve the style and keep its consistency. However, when the character's motion is directly controlled by a user's motion who is wearing motion sensors, the unique style can be discarded. We present a novel character motion control method that uses only a small amount of animation data created only for the character to preserve the style of the character motion. Instead of machine learning approaches requiring a large amount of training data, we suggest a search-based method, which directly searches the most similar character pose from the animation data to the current user's pose. To show the usability of our method, we conducted our experiments with a character model and its animation data created by an expert designer for a virtual reality game. To prove that our method preserves well the original motion style of the character, we compared our result with the result obtained by using general human motion capture data. In addition, to show the scalability of our method, we presented experimental results with different numbers of motion sensors.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.36-42
• /
• 2021

With recent developments in the Fourth Industrial Revolution, the manufacturing industry has changed rapidly. Through key aspects of Fourth Industrial Revolution super-connections and super-intelligence, machine learning will be able to make fault predictions during the foam-making process. Polyol and isocyanate are components in polyurethane foam. There has been a lot of research that could affect the characteristics of the products, depending on the specific mixture ratio and temperature. Based on these characteristics, this study collects data from each factor during the foam-making process and applies them to machine learning in order to predict faults. The algorithms used in machine learning are the decision tree, kNN, and an ensemble algorithm, and these algorithms learn from 5,147 cases. Based on 1,000 pieces of data for validation, the learning results show up to 98.5% accuracy using the ensemble algorithm. Therefore, the results confirm the faults of currently produced parts by collecting real-time data from each factor during the foam-making process. Furthermore, control of each of the factors may improve the fault rate.

• Korean Journal of Cognitive Science
• /
• v.21 no.2
• /
• pp.309-338
• /
• 2010

In this paper, we studied the brain-computer interface (BCI). BCIs help severely disabled people to control external devices by analyzing their brain signals evoked from motor imageries. The findings in the field of neurophysiology revealed that the power of $\beta$(14-26 Hz) and $\mu$(8-12 Hz) rhythms decreases or increases in synchrony of the underlying neuronal populations in the sensorymotor cortex when people imagine the movement of their body parts. These are called Event-Related Desynchronization / Synchronization (ERD/ERS), respectively. We implemented a BCI-based mouse interface system which enabled subjects to control a computer mouse cursor into four different directions (e.g., up, down, left, and right) by analyzing brain signal patterns online. Tongue, foot, left-hand, and right-hand motor imageries were utilized to stimulate a human brain. We used a non-invasive EEG which records brain's spontaneous electrical activity over a short period of time by placing electrodes on the scalp. Because of the nature of the EEG signals, i.e., low amplitude and vulnerability to artifacts and noise, it is hard to analyze and classify brain signals measured by EEG directly. In order to overcome these obstacles, we applied statistical machine-learning techniques. We could achieve high performance in the classification of four motor imageries by employing Common Spatial Pattern (CSP) and Linear Discriminant Analysis (LDA) which transformed input EEG signals into a new coordinate system making the variances among different motor imagery signals maximized for easy classification. From the inspection of the topographies of the results, we could also confirm ERD/ERS appeared at different brain areas for different motor imageries showing the correspondence with the anatomical and neurophysiological knowledge.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1779-1790
• /
• 2023

Satellite-based fog detection algorithms are being developed to detect fog in real-time over a wide area, with a focus on the Korean Peninsula (KorPen). The GEO-KOMPSAT-2A/Advanced Meteorological Imager (GK2A/AMI, GK2A) satellite offers an excellent temporal resolution (10 min) and a spatial resolution (500 m), while GEO-KOMPSAT-2B/Geostationary Ocean Color Imager-II (GK2B/GOCI-II, GK2B) provides an excellent spatial resolution (250 m) but poor temporal resolution (1 h) with only visible channels. To enhance the fog detection level (10 min, 250 m), we developed a fused GK2AB fog detection algorithm (FDA) of GK2A and GK2B. The GK2AB FDA comprises three main steps. First, the Korea Meteorological Satellite Center's GK2A daytime fog detection algorithm is utilized to detect fog, considering various optical and physical characteristics. In the second step, GK2B data is extrapolated to 10-min intervals by matching GK2A pixels based on the closest time and location when GK2B observes the KorPen. For reflectance, GK2B normalized visible (NVIS) is corrected using GK2A NVIS of the same time, considering the difference in wavelength range and observation geometry. GK2B NVIS is extrapolated at 10-min intervals using the 10-min changes in GK2A NVIS. In the final step, the extrapolated GK2B NVIS, solar zenith angle, and outputs of GK2A FDA are utilized as input data for machine learning (decision tree) to develop the GK2AB FDA, which detects fog at a resolution of 250 m and a 10-min interval based on geographical locations. Six and four cases were used for the training and validation of GK2AB FDA, respectively. Quantitative verification of GK2AB FDA utilized ground observation data on visibility, wind speed, and relative humidity. Compared to GK2A FDA, GK2AB FDA exhibited a fourfold increase in spatial resolution, resulting in more detailed discrimination between fog and non-fog pixels. In general, irrespective of the validation method, the probability of detection (POD) and the Hanssen-Kuiper Skill score (KSS) are high or similar, indicating that it better detects previously undetected fog pixels. However, GK2AB FDA, compared to GK2A FDA, tends to over-detect fog with a higher false alarm ratio and bias.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.243-264
• /
• 2018

Although the worldwide battery market is recently spurring the development of lithium secondary battery, lead acid batteries (rechargeable batteries) which have good-performance and can be reused are consumed in a wide range of industry fields. However, lead-acid batteries have a serious problem in that deterioration of a battery makes progress quickly in the presence of that degradation of only one cell among several cells which is packed in a battery begins. To overcome this problem, previous researches have attempted to identify the mechanism of deterioration of a battery in many ways. However, most of previous researches have used data obtained in a laboratory to analyze the mechanism of deterioration of a battery but not used data obtained in a real world. The usage of real data can increase the feasibility and the applicability of the findings of a research. Therefore, this study aims to develop a model which predicts the battery deterioration using data obtained in real world. To this end, we collected data which presents change of battery state by attaching sensors enabling to monitor the battery condition in real time to dozens of golf carts operated in the real golf field. As a result, total 16,883 samples were obtained. And then, we developed a model which predicts a precursor phenomenon representing deterioration of a battery by analyzing the data collected from the sensors using machine learning techniques. As initial independent variables, we used 1) inbound time of a cart, 2) outbound time of a cart, 3) duration(from outbound time to charge time), 4) charge amount, 5) used amount, 6) charge efficiency, 7) lowest temperature of battery cell 1 to 6, 8) lowest voltage of battery cell 1 to 6, 9) highest voltage of battery cell 1 to 6, 10) voltage of battery cell 1 to 6 at the beginning of operation, 11) voltage of battery cell 1 to 6 at the end of charge, 12) used amount of battery cell 1 to 6 during operation, 13) used amount of battery during operation(Max-Min), 14) duration of battery use, and 15) highest current during operation. Since the values of the independent variables, lowest temperature of battery cell 1 to 6, lowest voltage of battery cell 1 to 6, highest voltage of battery cell 1 to 6, voltage of battery cell 1 to 6 at the beginning of operation, voltage of battery cell 1 to 6 at the end of charge, and used amount of battery cell 1 to 6 during operation are similar to that of each battery cell, we conducted principal component analysis using verimax orthogonal rotation in order to mitigate the multiple collinearity problem. According to the results, we made new variables by averaging the values of independent variables clustered together, and used them as final independent variables instead of origin variables, thereby reducing the dimension. We used decision tree, logistic regression, Bayesian network as algorithms for building prediction models. And also, we built prediction models using the bagging of each of them, the boosting of each of them, and RandomForest. Experimental results show that the prediction model using the bagging of decision tree yields the best accuracy of 89.3923%. This study has some limitations in that the additional variables which affect the deterioration of battery such as weather (temperature, humidity) and driving habits, did not considered, therefore, we would like to consider the them in the future research. However, the battery deterioration prediction model proposed in the present study is expected to enable effective and efficient management of battery used in the real filed by dramatically and to reduce the cost caused by not detecting battery deterioration accordingly.