• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.834-841
• /
• 2022

Recently, applying artificial intelligence technologies in various fields of production has drawn an upsurge of research interest due to the increase for smart factory and artificial intelligence technologies. A great deal of effort is being made to introduce artificial intelligence algorithms into the defect detection task. Particularly, detection of defects on the surface of metal has a higher level of research interest compared to other materials (wood, plastics, fibers, etc.). In this paper, we compare and analyze the speed and performance of defect classification by combining machine learning techniques (Support Vector Machine, Softmax Regression, Decision Tree) with dimensionality reduction algorithms (Principal Component Analysis, AutoEncoders) and two convolutional neural networks (proposed method, ResNet). To validate and compare the performance and speed of the algorithms, we have adopted two datasets ((i) public dataset, (ii) actual dataset), and on the basis of the results, the most efficient algorithm is determined.

• The Journal of Society for e-Business Studies
• /
• v.27 no.1
• /
• pp.63-79
• /
• 2022

Recently, various studies have been conducted on stock price prediction using machine learning and deep learning techniques. Among these studies, the latest studies have attempted to predict stock prices using limit order books, which contain buy and sell order information of stocks. However, most of the studies using limit order books consider only the trend of limit order books over the most recent period of a specified length, and few studies consider both the medium and short term trends of limit order books. Therefore, in this paper, we propose a deep learning-based prediction model that predicts stock price more accurately by considering both the medium and short term trends of limit order books. Moreover, the proposed model considers news headlines during the same period to reflect the qualitative status of the company in the stock price prediction. The proposed model extracts the features of changes in limit order books with CNNs and the features of news headlines using Word2vec, and combines these information to predict whether a particular company's stock will rise or fall the next day. We conducted experiments to predict the daily stock price fluctuations of five stocks (Amazon, Apple, Facebook, Google, Tesla) with the proposed model using the real NASDAQ limit order book data and news headline data, and the proposed model improved the accuracy by up to 17.66%p and the average by 14.47%p on average. In addition, we conducted a simulated investment with the proposed model and earned a minimum of $492.46 and a maximum of $2,840.93 depending on the stock for 21 business days.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.2
• /
• pp.63-70
• /
• 2022

Although 2D Object detection has been largely improved in the past years with the advance of deep learning methods and the use of large labeled image datasets, 3D object detection from 2D imagery is a challenging problem in a variety of applications such as robotics, due to the lack of data and diversity of appearances and shapes of objects within a category. Google has just announced the launch of Objectron that has a novel data pipeline using mobile augmented reality session data. However, it also is corresponding to 2D-driven 3D object detection technique. This study explores more mature 2D object detection method, and applies its 2D projection to Objectron 3D lifting system. Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a stochastic representation of object regions using Gaussian distributions. We also present a similarity measure for the Gaussian distributions based on the Hellinger Distance, which can be viewed as a stochastic Intersection-over-Union. Our experimental results show that the proposed Gaussian representations are closer to annotated segmentation masks in available datasets. Thus, less accuracy problem that is one of several limitations of Objectron can be relaxed.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1047-1056
• /
• 2022

Sea ice, frozen sea water, in the Artic is a primary indicator of global warming. Due to its importance to the climate system, shipping-route navigation, and fisheries, Arctic sea ice prediction has gained increased attention in various disciplines. Recent advances in artificial intelligence (AI), motivated by a desire to develop more autonomous and efficient future predictions, have led to the development of new sea ice prediction models as alternatives to conventional numerical and statistical prediction models. This study aims to evaluate the performance of the two-stream convolutional long-and short-term memory (TS-ConvLSTM) AI model, which is designed for learning both global and local characteristics of the Arctic sea ice changes, for the minimum September Arctic sea ice from 2001 to 2021, and to show the possibility for an operational prediction system. Although the TS-ConvLSTM model generally increased the prediction performance as training data increased, predictability for the marginal ice zone, 5-50% concentration, showed a negative trend due to increasing first-year sea ice and warming. Additionally, a comparison of sea ice extent predicted by the TS-ConvLSTM with the median Sea Ice Outlooks (SIOs) submitted to the Sea Ice Prediction Network has been carried out. Unlike the TS-ConvLSTM, the median SIOs did not show notable improvements as time passed (i.e., the amount of training data increased). Although the TS-ConvLSTM model has shown the potential for the operational sea ice prediction system, learning more spatio-temporal patterns in the difficult-to-predict natural environment for the robust prediction system should be considered in future work.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.2
• /
• pp.91-108
• /
• 2022

In most cases, optical images have been used as training data of DL (Deep Learning) models for object detection, recognition, identification, classification, semantic segmentation, and instance segmentation. However, properties of 3D objects in the real-world could not be fully explored with 2D images. One of the major sources of the 3D geospatial information is DSM (Digital Surface Model). In this matter, characteristic information derived from DSM would be effective to analyze 3D terrain features. Especially, man-made objects such as buildings having geometrically unique shape could be described by geometric elements that are obtained from 3D geospatial data. The background and motivation of this paper were drawn from concept of the intrinsic image that is involved in high-level visual information processing. This paper aims to extract buildings after classifying terrain features by training DL model with DSM-derived information including slope, aspect, and SRI (Shaded Relief Image). The experiments were carried out using DSM and label dataset provided by ISPRS (International Society for Photogrammetry and Remote Sensing) for CNN-based SegNet model. In particular, experiments focus on combining multi-source information to improve training performance and synergistic effect of the DL model. The results demonstrate that buildings were effectively classified and extracted by the proposed approach.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.27 no.2
• /
• pp.49-70
• /
• 2022

Sea Surface Temperature (SST), one of the ocean features, has a significant impact on climate, marine ecosystem and human activities. Therefore, SST prediction has been always an important issue. Recently, deep learning has drawn much attentions, since it can predict SST by training past SST patterns. Compared to the numerical simulations, deep learning model is highly efficient, since it can estimate nonlinear relationships between input data. With the recent development of Graphics Processing Unit (GPU) in computer, large amounts of data can be calculated repeatedly and rapidly. In this study, Short-term SST will be predicted through Convolutional Neural Network (CNN)-based U-Net that can handle spatiotemporal data concurrently and overcome the drawbacks of previously existing deep learning-based models. The SST prediction performance depends on the seasonal and interannual SST variabilities around the southern coast of Korea. The predicted SST has a wide range of variance during spring and summer, while it has small range of variance during fall and winter. A wide range of variance also has a significant correlation with the change of the Pacific Decadal Oscillation (PDO) index. These results are found to be affected by the intensity of the seasonal and PDO-related interannual SST fronts and their intensity variations along the southern Korean seas. This study implies that the SST prediction performance using the developed deep learning model can be significantly varied by seasonal and interannual variabilities in SST.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.367-380
• /
• 2022

In this study, the periodic and simplified update and production way of the ECVAM (Environmental Conservation Value Assessment Map) was presented through the classification of environmental values using KOMPSAT-3A satellite imagery and land cover map. ECVAM is a map that evaluates the environmental value of the country in five stages based on 62 legal evaluation items and 8 environmental and ecological evaluation items, and is provided on two scales: 1:25000 and 1:5000. However, the 1:5000 scale environmental assessment map is being produced and serviced with a slow renewal cycle of one year due to various constraints such as the absence of reference materials and different production years. Therefore, in this study, one of the deep learning techniques, KOMPSAT-3A satellite image, SI (Spectral Indices), and land cover map were used to conduct this study to confirm the possibility of establishing an environmental assessment map. As a result, the accuracy was calculated to be 87.25% and 85.88%, respectively. Through the results of the study, it was possible to confirm the possibility of constructing an environmental assessment map using satellite imagery, optical index, and land cover classification.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.461-469
• /
• 2022

This paper presents a novel training data extraction approach using semi-supervised learning (SSL)-based classification without the analyst intervention for time-series land-cover mapping. The SSL-based approach first performs initial classification using initial training data obtained from past images including land-cover characteristics similar to the image to be classified. Reliable training data from the initial classification result are then extracted from SSL-based iterative classification using classification uncertainty information and class labels of neighboring pixels as constraints. The potential of the SSL-based training data extraction approach was evaluated from a classification experiment using unmanned aerial vehicle images in croplands. The use of new training data automatically extracted by the proposed SSL approach could significantly alleviate the misclassification in the initial classification result. In particular, isolated pixels were substantially reduced by considering spatial contextual information from adjacent pixels. Consequently, the classification accuracy of the proposed approach was similar to that of classification using manually extracted training data. These results indicate that the SSL-based iterative classification presented in this study could be effectively applied to automatically extract reliable training data for time-series land-cover mapping.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.1100-1118
• /
• 2021

In a wide range of ML applications, the training data contains privacy-sensitive information that should be kept secure. Training the ML systems by privacy-sensitive data makes the ML model inherent to the data. As the structure of the model has been fine-tuned by training data, the model can be abused for accessing the data by the estimation in a reverse process called model inversion attack (MIA). Although, MIA has been applied to shallow neural network models of recognizers in literature and its threat in privacy violation has been approved, in the case of a deep learning (DL) model, its efficiency was under question. It was due to the complexity of a DL model structure, big number of DL model parameters, the huge size of training data, big number of registered users to a DL model and thereof big number of class labels. This research work first analyses the possibility of MIA on a deep learning model of a recognition system, namely a face recognizer. Second, despite the conventional MIA under the white box scenario of having partial access to the users' non-sensitive information in addition to the model structure, the MIA is implemented on a deep face recognition system by just having the model structure and parameters but not any user information. In this aspect, it is under a semi-white box scenario or in other words a gray-box scenario. The experimental results in targeting five registered users of a CNN-based face recognition system approve the possibility of regeneration of users' face images even for a deep model by MIA under a gray box scenario. Although, for some images the evaluation recognition score is low and the generated images are not easily recognizable, but for some other images the score is high and facial features of the targeted identities are observable. The objective and subjective evaluations demonstrate that privacy cyber-attack by MIA on a deep recognition system not only is feasible but also is a serious threat with increasing alert state in the future as there is considerable potential for integration more advanced ML techniques to MIA.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.936-939
• /
• 2022

As air combat system technologies developed in recent years, the development of air defense systems is required. In the operating concept of the anti-aircraft defense system, selecting an appropriate armament for the target is one of the system's capabilities in efficiently responding to threats using limited anti-aircraft power. Much of the flying threat identification relies on the operator's visual identification. However, there are many limitations in visually discriminating a flying object maneuvering high speed from a distance. In addition, as the demand for unmanned and intelligent weapon systems on the modern battlefield increases, it is essential to develop a technology that automatically identifies and classifies the aircraft instead of the operator's visual identification. Although some examples of weapon system identification with deep learning-based models by collecting video data for tanks and warships have been presented, aerial vehicle identification is still lacking. Therefore, in this paper, we present a model for classifying fighters, helicopters, and drones using a convolutional neural network model and analyze the performance of the presented model.