• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.43-53
• /
• 2023

In this detailed and comprehensive study, our primary focus has been placed on accurately gauging the number of visitors and their real-time locations in commercial spaces. Particularly, in a real cafe, using security cameras, we have developed a system that can offer live updates on available seating and predict future congestion levels. By employing YOLO, a real-time object detection and tracking algorithm, the number of visitors and their respective locations in real-time are also monitored. This information is then used to update a cafe's indoor map, thereby enabling users to easily identify available seating. Moreover, we developed a model that predicts the congestion of a cafe in real time. The sophisticated model, designed to learn visitor count and movement patterns over diverse time intervals, is based on Long Short Term Memory (LSTM) to address the vanishing gradient problem and Sequence-to-Sequence (Seq2Seq) for processing data with temporal relationships. This innovative system has the potential to significantly improve cafe management efficiency and customer satisfaction by delivering reliable predictions of cafe congestion to all users. Our groundbreaking research not only demonstrates the effectiveness and utility of indoor location tracking technology implemented through security cameras but also proposes potential applications in other commercial spaces.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.173-178
• /
• 2023

As Korean literature spreads around the world, its position in the overseas publishing market has become important. As demand in the overseas publishing market continues to grow, it is essential to predict future book sales and analyze the characteristics of books that have been highly favored by overseas readers in the past. In this study, we proposed ensemble learning based prediction model and analyzed characteristics of the cumulative sales of more than 5,000 copies classified as good sellers published overseas over the past 5 years. We applied the five ensemble learning models, i.e., XGBoost, Gradient Boosting, Adaboost, LightGBM, and Random Forest, and compared them with other machine learning algorithms, i.e., Support Vector Machine, Logistic Regression, and Deep Learning. Our experimental results showed that the ensemble algorithm outperforms other approaches in troubleshooting imbalanced data. In particular, the LightGBM model obtained an AUC value of 99.86% which is the best prediction performance. Among the features used for prediction, the most important feature is the author's number of overseas publications, and the second important feature is publication in countries with the largest publication market size. The number of evaluation participants is also an important feature. In addition, text mining was performed on the four book reviews that sold the most among good-selling books. Many reviews were interested in stories, characters, and writers and it seems that support for translation is needed as many of the keywords of "translation" appear in low-rated reviews.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2023

Research using AI and big data is also being actively conducted in the health and medical fields such as disease diagnosis and treatment. Most of the existing research data used cohort data from research institutes or some patient data. In this paper, the difference in the prediction rate of survival and the factors affecting survival between breast cancer patients in their 40~50s and other age groups was revealed using health insurance review claim data held by the HIRA. As a result, the accuracy of predicting patients' survival was 0.93 on average in their 40~50s, higher than 0.86 in their 60~80s. In terms of that factor, the number of treatments was high for those in their 40~50s, and age was high for those in their 60~80s. Performance comparison with previous studies, the average precision was 0.90, which was higher than 0.81 of the existing paper. As a result of performance comparison by applied algorithm, the overall average precision of Decision Tree, Random Forest, and Gradient Boosting was 0.90, and the recall was 1.0, and the precision of multi-layer perceptrons was 0.89, and the recall was 1.0. I hope that more research will be conducted using machine learning automation(Auto ML) tools for non-professionals to enhance the use of the value for health insurance review claim data held by the HIRA.

• Journal of Intelligence and Information Systems
• /
• v.10 no.1
• /
• pp.109-123
• /
• 2004

Corporate financial distress and bankruptcy prediction is one of the major application areas of artificial neural networks (ANNs) in finance and management. ANNs have showed high prediction performance in this area, but sometimes are confronted with inconsistent and unpredictable performance for noisy data. In addition, it may not be possible to train ANN or the training task cannot be effectively carried out without data reduction when the amount of data is so large because training the large data set needs much processing time and additional costs of collecting data. Instance selection is one of popular methods for dimensionality reduction and is directly related to data reduction. Although some researchers have addressed the need for instance selection in instance-based learning algorithms, there is little research on instance selection for ANN. This study proposes a genetic algorithm (GA) approach to instance selection in ANN for bankruptcy prediction. In this study, we use ANN supported by the GA to optimize the connection weights between layers and select relevant instances. It is expected that the globally evolved weights mitigate the well-known limitations of gradient descent algorithm of backpropagation algorithm. In addition, genetically selected instances will shorten the learning time and enhance prediction performance. This study will compare the proposed model with other major data mining techniques. Experimental results show that the GA approach is a promising method for instance selection in ANN.

• Journal of Korea Multimedia Society
• /
• v.8 no.11
• /
• pp.1496-1509
• /
• 2005

In this paper, an adaptive license plate recognition system which detects and recognizes license plate at real-time by using projected plane convolution and Decision Tree Classifier is proposed. And it was tested in circumstances which presence of complex background. Generally, in expressway tollgate or gateway of parking lots, it is very difficult to detect and segment license plate because of size, entry angle and noisy problem of vehicles due to CCD camera and road environment. In the proposed algorithm, we suggested to extract license plate candidate region after going through image acquisition process with inputted real-time image, and then to compensate license size as well as gradient of vehicle with change of vehicle entry position. The proposed algorithm can exactly detect license plate using accumulated edge, projected convolution and chain code labeling method. And it also segments letter of license plate using adaptive binary method. And then, it recognizes license plate letter by applying hybrid pattern vector method. Experimental results show that the proposed algorithm can recognize the front and rear direction license plate at real-time in the presence of complex background environments. Accordingly license plate detection rate displayed $98.8\%$ and $96.5\%$ successive rate respectively. And also, from the segmented letters, it shows $97.3\%$ and $96\%$ successive recognition rate respectively.

• Journal of Biomedical Engineering Research
• /
• v.21 no.3 s.61
• /
• pp.239-246
• /
• 2000

In this paper. we propose a semi-automatic segmentation algorithm to extract organ in 3D medical data by using a manually segmentation result in a sing1e slice. Generally region glowing based tracking method consists of 3 steps object projection. seed extraction and boundary decision by region growing. But because the boundary between organs in medical data is vague, improper seeds make the boundary dig into the organ or extend to the false region. In the proposed algorithm seeds are carefully extracted to find suitable boundaries between organs after region growing. And the jagged boundary at low gradient region after region growing is corrected by post-processing using Fourier descriptor. Also two-path tracking make it possible to catch up newly appeared areas. The proposed algorithm provides satisfactory results in segmenting 1 mm distance kidneys from X-rav CT body image set of 82 slices.

• Journal of KIISE:Software and Applications
• /
• v.32 no.2
• /
• pp.128-139
• /
• 2005

Moving object boundary is very important for moving object segmentation. But the moving object boundary shows broken boundary We invent a novel space-oriented boundary linking algorithm to link the broken boundary The boundary linking algorithm forms a quadrant around the terminating pixel in the broken boundary and searches forward other terminating pixel to link within a radius. The boundary linking algorithm guarantees shortest distance linking. We also register the background from image sequence. We construct two object masks, one from the result of boundary linking and the other from the registered background, and use these two complementary object masks together for moving object segmentation. We also suppress the moving cast shadow using Roberts gradient operator. The major advantages of the proposed algorithms are more accurate moving object segmentation and the segmentation of the object which has holes in its region using these two object masks. We experiment the algorithms using the standard MPEG-4 test sequences and real video sequence. The proposed algorithms are very efficient and can process QCIF image more than 48 fps and CIF image more than 19 fps using a 2.0GHz Pentium-4 computer.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.1
• /
• pp.17-28
• /
• 2019

In the financial investment management strategy, the distributed investment selecting and combining various financial assets is called portfolio management theory. In recent years, the blockchain based financial assets, such as cryptocurrencies, have been traded on several well-known exchanges, and an efficient portfolio management approach is required in order for investors to steadily raise their return on investment in cryptocurrencies. On the other hand, deep learning has shown remarkable results in various fields, and research on application of deep reinforcement learning algorithm to portfolio management has begun. In this paper, we propose an efficient financial portfolio investment management method based on Asynchronous Advantage Actor-Critic (A3C), which is a representative asynchronous reinforcement learning algorithm. In addition, since the conventional cross-entropy function can not be applied to portfolio management, we propose a proper method where the existing cross-entropy is modified to fit the portfolio investment method. Finally, we compare the proposed A3C model with the existing reinforcement learning based cryptography portfolio investment algorithm, and prove that the performance of the proposed A3C model is better than the existing one.

• Korean Journal of Optics and Photonics
• /
• v.31 no.6
• /
• pp.247-258
• /
• 2020

In this paper, based on a stochastic parallel gradient descent (SPGD) algorithm we study phase control of a coherent-beam-combining system under turbulent atmospheric conditions. Based on the statistical theory of atmospheric turbulence, we carry out the analysis of the phase and wavefront distortion of a laser beam propagating through a turbulent atmospheric medium. We also conduct numerical simulations of a coherent-beam-combining system with 7- and 19-channel laser beams distorted by atmospheric turbulence. Through numerical simulations, we characterize the phase-control characteristics and efficiency of the coherent-beam-combining system under various degrees of atmospheric turbulence. It is verified that the SPGD algorithm is capable of realizing 7-channel coherent beam combining with a beam-combining efficiency of more than 90%, even under the turbulent atmospheric conditions up to cn2 of 10-13 m-2/3. In the case of 19-channel coherent beam combining, it is shown that the same turbulent atmospheric conditions result in a drastic reduction of the beam-combining efficiency down to 60%, due to the elevated impact of the corresponding refractive-index inhomogeneity. In addition, by putting together the number of iterations of the SPGD algorithm required for phase locking under atmospheric turbulence and the time intervals of atmospheric phenomena, which typically are of the order of ㎲, it is estimated that hundreds of MHz to a few GHz of computing bandwidth of SPGD-based phase control may be required for a coherent-beam-combining system to confront such turbulent atmospheric conditions. We expect the results of this paper to be useful for quantitatively analyzing and predicting the effects of atmospheric turbulence on the SPGD-based phase-control performance of a coherent-beam-combining system.

• Journal of Korean Society of Forest Science
• /
• v.111 no.4
• /
• pp.603-612
• /
• 2022

The study aims were to evaluate a machine-learning, algorithm-based, forest biomass-estimation model to estimate subnational forest biomass and to comparatively analyze REDD+ forest reference emission levels. Time-series Landsat satellite imagery and ESA Biomass Climate Change Initiative information were used to build a machine-learning-based biomass estimation model. The k-nearest neighbors algorithm (kNN), which is a non-parametric learning model, and the tree-based random forest (RF) model were applied to the machine-learning algorithm, and the estimated biomasses were compared with the forest reference emission levels (FREL) data, which was provided by the Paraguayan government. The root mean square error (RMSE), which was the optimum parameter of the kNN model, was 35.9, and the RMSE of the RF model was lower at 34.41, showing that the RF model was superior. As a result of separately using the FREL, kNN, and RF methods to set the reference emission levels, the gradient was set to approximately -33,000 tons, -253,000 tons, and -92,000 tons, respectively. These results showed that the machine learning-based estimation model was more suitable than the existing methods for setting reference emission levels.