• Journal of Korea Multimedia Society
• /
• v.22 no.5
• /
• pp.558-572
• /
• 2019

Anthropomorphism is the attribution of human traits, emotions, or intentions to non-human entities. Anthropomorphic animal face masking is the process by which human characteristics are plotted on the animal kind. In this research, we are proposing a compact system which finds the resemblance between a human face and animal face using Deep Convolutional Neural Network (DCNN) and later applies morphism between them. The whole process is done by firstly finding which animal most resembles the particular human face through a DCNN based animal face classification. And secondly, doing triangulation based morphing between the particular human face and the most resembled animal face. Compared to the conventional manual Control Point Selection system using an animator, we are proposing a Viola-Jones algorithm based Control Point selection process which detects facial features for the human face and takes the Control Points automatically. To initiate our approach, we built our own dataset containing ten thousand animal faces and a fourteen layer DCNN. The simulation results firstly demonstrate that the accuracy of our proposed DCNN architecture outperforms the related methods for the animal face classification. Secondly, the proposed morphing method manages to complete the morphing process with less deformation and without any human assistance.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.235-241
• /
• 2019

In this paper, we propose a new algorithm to detect rear-approaching vehicle using the frame similarity of ROI(Region of Interest) based on deep learning algorithm for use in agricultural machinery systems. Since the vehicle detection system for agricultural machinery needs to detect only a vehicle approaching from the rear. we use Faster R-CNN model that shows excellent accuracy rate in deep learning for vehicle detection. And we proposed an algorithm that uses the frame similarity for ROI using constrained conditions. Experimental results show that the proposed method has a detection rate of 99.9% and reduced the false positive values.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.240-243
• /
• 2021

Recently, there have been research results of applying Big data and AI technologies to the evaluation and individual learning for education. It is information technology innovations that collect dynamic and complex data, including student personal records, physiological data, learning logs and activities, learning outcomes and outcomes from social media, MOOCs, intelligent tutoring systems, LMSs, sensors, and mobile devices. In addition, e-learning was generated a large amount of learning data in the COVID-19 environment. It is expected that learning analysis and AI technology will be applied to extract meaningful patterns and discover knowledge from this data. On the learner's perspective, it is necessary to identify student learning and emotional behavior patterns and profiles, improve evaluation and evaluation methods, predict individual student learning outcomes or dropout, and research on adaptive systems for personalized support. This study aims to contribute to research in the field of education by researching and classifying machine learning technologies used in anomaly detection and recommendation systems for educational data.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.69-80
• /
• 2021

Neural machine translation using deep neural network has emerged as a mainstream research, and an abundance of investment and studies on model structure and parallel language pair have been actively undertaken for the best performance. However, most recent neural machine translation studies pass along decoding strategy to future work, and have insufficient a variety of experiments and specific analysis on it for generating language to maximize quality in the decoding process. In machine translation, decoding strategies optimize navigation paths in the process of generating translation sentences and performance improvement is possible without model modifications or data expansion. This paper compares and analyzes the significant effects of the decoding strategy from classical greedy decoding to the latest Dynamic Beam Allocation (DBA) in neural machine translation using a sequence to sequence model.

• Journal of Digital Convergence
• /
• v.16 no.6
• /
• pp.151-161
• /
• 2018

Income is a vital aspect of economic life. Knowing what their income will help people create budgets that allow them to pay for their living expenses. Income data is used by banks, stores, and service companies for marketing purposes and for retaining loyal customers; it is a crucial demographic element used at a wide variety of customer touch points. Therefore, it is essential to be able to make income predictions for existing and potential customers. This paper aims to predict employment earnings or income based on history, and uses machine learning techniques such as SVMs (Support Vector Machines), Gaussian, decision tree and DCNNs (Deep Convolutional Neural Networks) for predicting employment earnings. The results show that the DCNN method provides optimum results with 88% compared to other machine learning techniques used in this paper. Improvement of the data length such PCA has the potential to provide more optimum result.

• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.748-756
• /
• 2022

Thanks to the competition of AlphaGo and Sedol Lee, machine learning has received world-wide attention and huge investments. The performance improvement of computing devices greatly contributed to big data processing and the development of neural networks. Artificial intelligence not only imitates human beings in many fields, but also seems to be better than human capabilities. Although humans' creation is still considered to be better and higher, several artificial intelligences continue to challenge human creativity. The quality of some creative outcomes by AI is as good as the real ones produced by human beings. Sometimes they are not distinguishable, because the neural network has the competence to learn the common features contained in big data and copy them. In order to confirm whether artificial intelligence can express the inherent characteristics of different arts, this paper proposes a new neural network model called Humming. It is an experimental model that combines vgg16, which extracts image features, and DeepJ's architecture, which excels in creating various genres of music. A dataset produced by our experiment shows meaningful and valid results. Different results, however, are produced when the amount of data is increased. The neural network produced a similar pattern of music even though it was a different classification of images, which was not what we were aiming for. However, these new attempts may have explicit significance as a starting point for feature transfer that will be further studied.

• Journal of the Microelectronics and Packaging Society
• /
• v.31 no.3
• /
• pp.50-57
• /
• 2024

Recently, applying a machine learning to surrogate modeling for rapid optimization of complex designs have been widely researched. Once trained, the machine learning surrogate model can predict similar outputs to Finite Element Analysis (FEA) simulations but require significantly less computing resources. In addition, combined with optimization methodologies, it can identify optimal design variable with less time requirement compared to iterative simulation. This study proposes a Deep Neural Network (DNN) model with Bayesian Optimization (BO) approach for efficiently searching the optimal design variables to minimize the warpage of electronic package. The DNN model was trained by using design variable-warpage dataset from FEA simulation, and the Bayesian optimization was applied to find the optimal design variables which minimizing the warpage. The suggested DNN + BO model shows over 99% consistency compared to actual simulation results, while only require 15 second to identify optimal design variable, which reducing the optimization time by more than 57% compared to FEA simulation.

• Convergence Security Journal
• /
• v.21 no.3
• /
• pp.57-66
• /
• 2021

As the detection performance using deep learning and machine learning of the intrusion detection field has been verified, the cases of using it are increasing day by day. However, it is difficult to collect the data required for learning, and it is difficult to apply the machine learning performance to reality due to the imbalance of the collected data. Therefore, in this paper, A mixed sampling technique using t-SNE visualization for imbalanced data processing is proposed as a solution to this problem. To do this, separate fields according to characteristics for intrusion detection events, including payload. Extracts TF-IDF-based features for separated fields. After applying the mixed sampling technique based on the extracted features, a data set optimized for intrusion detection with imbalanced data is obtained through data visualization using t-SNE. Nine sampling techniques were applied through the open intrusion detection dataset CSIC2012, and it was verified that the proposed sampling technique improves detection performance through F-score and G-mean evaluation indicators.

• The Journal of Engineering Geology
• /
• v.33 no.4
• /
• pp.639-655
• /
• 2023

Recently, there has been a growing demand for underground space, leading to the utilization of earth retaining walls for deep excavations. Earth retaining walls are structures that are susceptible to displacement, and their measurement and management are carried out in accordance with the standards established by the Ministry of Land, Infrastructure, and Transport. However, managing displacement through measurement can be considered similar to post-processing. Therefore, in this study, we not only predicted the horizontal displacement of a retaining wall with ground anchors installed using machine learning, but also analyzed the impact of the prediction model based on data scaling and data splitting methods while learning measurement data using machine learning. Custom splitting was the most suitable method for learning and outputting measurement data. Data scaling demonstrated excellent performance, with an error within 1 and an R-squared value of 0.77 when the anchor tensile force and water pressure were standardized. Additionally, it predicted a negative displacement compared to a model that without scaling.

• Soft Computing and Machine Intelligence
• /
• v.1 no.1
• /
• pp.31-35
• /
• 2021

In recent years, due to COVID-19, the process of shopping has become more restricted and difficult for customers. Based on this aspect, customers are more interested in online shopping to keep the Untact rules and stay safe, similarly ordering their product based on their need and interest with most straightforward and fastest ways. In this paper, the reinforcement learning technique is applied in the product recommendation system to improve the recommendation system quality for better and more related suggestions based on click patterns and users' profile information. The dataset used in this system was taken from an online shopping mall in Jeju island, South Korea. We have compared the proposed method with the recent state-of-the-art and research results, which show that reinforcement learning effectiveness is higher than other approaches.