• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.367-374
• /
• 2021

Stock price prediction is a subject of research in various fields such as economy, statistics, computer engineering, etc. In recent years, researches on predicting the movement of stock prices by learning artificial intelligence models from various indicators such as basic indicators and technical indicators have become active. This study proposes a deep learning model that predicts the ups and downs of KOSPI from overseas indices such as S&P500, past KOSPI indices, and trading trends by KOSPI investors. The proposed model extracts a latent variable using a stacked auto-encoder to predict stock price fluctuations, and predicts the fluctuation of the closing price compared to the market price of the day by learning an LSTM suitable for learning time series data from the extracted latent variable to decide to buy or sell based on the value. As a result of comparing the returns and prediction accuracy of the proposed model and the comparative models, the proposed model showed better performance than the comparative models.

• Journal of the Korea Convergence Society
• /
• v.10 no.8
• /
• pp.59-65
• /
• 2019

There are various subtypes of cells in cancer tissues, but it is hard to confirm their composition experimentally. Here, we estimated the cell composition of each sample from gene expression data by using statistical machine learning approaches, two different regression models and investigated whether the cell composition was different between cancer and normal tissue. As a result, we found that CD8 T cell and Neutrophil were increased in oral cancer tissues compared to normal tissues. In addition, we applied t-SNE, which is one of the unsupervised learning, to verify whether normal tissue and oral cancer tissue can be clustered by the derived cell composition. Moreover, we showed that it is possible to predict oral cancer and normal tissue by several supervised classification algorithms. The study would help to improve the understanding of the immune cell infiltration at oral cancer.

• Journal of the Korea Society for Simulation
• /
• v.29 no.1
• /
• pp.47-55
• /
• 2020

This paper presents a real-time autonomous computation of shot numbers and aiming points against multiple soft targets on grounds by applying an unsupervised learning, k-mean clustering and Monte carlo simulation. For this computation, a 100 × 200 square meters size of virtual battlefield is created where an augmented enemy infantry platoon unit attacks, defences, and is scatted, and a virtual weapon with a lethal range of 15m is modeled. In order to determine damage types of the enemy unit: no damage, light wound, heavy wound and death, Monte carlo simulation is performed to apply the Carlton damage function for the damage effect of the soft targets. In addition, in order to achieve the damage effectiveness of the enemy units in line with the commander's intention, the optimal shot numbers and aiming point locations are calculated in less than 0.4 seconds by applying the k-mean clustering and repetitive Monte carlo simulation. It is hoped that this study will help to develop a system that reduces the decision time for 'detection-decision-shoot' process in battalion-scaled combat units operating Dronebot combat system.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.741-750
• /
• 2021

School violence has long been recognized as a social problem, and various efforts have been made to prevent it. In this study, we propose a system that can prevent school violence by analyzing data on the frequency of conversations between students, friendship and preference to be in the same group. This data was quantified using a Likert scale questionnaire, and also grouped into the appropriate number of clusters using the K-means algorithm. Additionally, the homeroom teacher observed the frequency and nature of conversations between students, and targeted specific individuals or groups for counseling and intervention, with the aim of reducing school violence. Data analysis revealed that the teachers' qualitative observations were consistent with the quantified data based on student questionnaires, and therefore applicable as quantitative data towards the identification and understanding of student relationships within the classroom. The study has potential limitations. The data used is subjective and based on peer evaluations which can be inconsistent as the students may use different criteria to evaluate one another. It is expected that this study will help homeroom teachers in their efforts to prevent school violence by understanding the relationships between students within the classroom.

• The Korean Journal of Applied Statistics
• /
• v.34 no.6
• /
• pp.905-922
• /
• 2021

Cluster analysis is one of unsupervised learning techniques used for discovering clusters when there is no prior knowledge of group membership. K-means, one of the commonly used cluster analysis techniques, may fail when the number of variables becomes large. In such high-dimensional cases, it is common to perform tandem analysis, K-means cluster analysis after reducing the number of variables using dimension reduction methods. However, there is no guarantee that the reduced dimension reveals the cluster structure properly. Principal component analysis may mask the structure of clusters, especially when there are large variances for variables that are not related to cluster structure. To overcome this, techniques that perform dimension reduction and cluster analysis simultaneously have been suggested. This study proposes probabilistic reduced K-means, the transition of reduced K-means (De Soete and Caroll, 1994) into a probabilistic framework. Simulation shows that the proposed method performs better than tandem clustering or clustering without any dimension reduction. When the number of the variables is larger than the number of samples in each cluster, probabilistic reduced K-means show better formation of clusters than non-probabilistic reduced K-means. In the application to a real data set, it revealed similar or better cluster structure compared to other methods.

• The Journal of the Korea Contents Association
• /
• v.21 no.10
• /
• pp.59-66
• /
• 2021

In this paper, an improved integrated security control procedure is newly proposed by applying artificial intelligence technology to integrated security control and unifying the existing security control and AI security control response procedures. Current cyber security control is highly dependent on the level of human ability. In other words, it is practically unreasonable to analyze various logs generated by people from different types of equipment and analyze and process all of the security events that are rapidly increasing. And, the signature-based security equipment that detects by matching a string and a pattern has insufficient functions to accurately detect advanced and advanced cyberattacks such as APT (Advanced Persistent Threat). As one way to solve these pending problems, the artificial intelligence technology of supervised and unsupervised learning is applied to the detection and analysis of cyber attacks, and through this, the analysis of logs and events that occur innumerable times is automated and intelligent through this. The level of response has been raised in the overall aspect by making it possible to predict and block the continuous occurrence of cyberattacks. And after applying AI security control technology, an improved integrated security control service model was newly proposed by integrating and solving the problem of overlapping detection of AI and SIEM into a unified breach response process(procedure).

• Database Research
• /
• v.34 no.3
• /
• pp.137-147
• /
• 2018

A key to a well-performing human activity recognition (HAR) system through machine learning technique is the availability of a substantial amount of labeled data. Collecting sufficient labeled data is an expensive and time-consuming task. To build a HAR system in a new environment (i.e., the target domain) with very limited labeled data, it is unfavorable to naively exploit the data or trained classifier model from the existing environment (i.e., the source domain) as it is due to the domain difference. While traditional machine learning approaches are unable to address such distribution mismatch, transfer learning approach leverages the utilization of knowledge from existing well-established source domains that help to build an accurate classifier in the target domain. In this work, we propose a transfer learning approach to create an accurate HAR classifier with very limited data through the multitask neural network. The classifier loss function minimization for source and target domain are treated as two different tasks. The knowledge transfer is performed by simultaneously minimizing the loss function of both tasks using a single neural network model. Furthermore, we utilize the unlabeled data in an unsupervised manner to help the model training. The experiment result shows that the proposed work consistently outperforms existing approaches.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.3
• /
• pp.171-179
• /
• 2020

Recently, studies have shown that convolution neural networks are achieving the best performance in image classification, object detection, and image generation. Vision based defect inspection which is more economical than other defect inspection, is a very important for a factory automation. Although supervised anomaly detection algorithm has far exceeded the performance of traditional machine learning based method, it is inefficient for real industrial field due to its tedious annotation work, In this paper, we propose ADGAN, a unsupervised anomaly detection architecture using the variational autoencoder and the generative adversarial network which give great results in image generation task, and demonstrate whether the proposed network architecture identifies anomalous images well on MNIST benchmark dataset as well as our own welding defect dataset.

• Journal of Korea Foundry Society
• /
• v.42 no.6
• /
• pp.369-376
• /
• 2022

The die-casting process is an important process for various industries, but there are limitations in the profitability and productivity of related companies due to the high defect rate. In order to overcome this, this study has developed die-casting fault detection modules based on industrial AI technologies. The developed module is constructed from three-stage models depending on the characteristics of the dataset. The first-stage model conducts fault detection based on supervised learning from the dataset without labels. The second-stage model realizes one-class classification based on semi-supervised learning, where the dataset only has production success labels. The third-stage model corresponds to fault detection based on supervised learning, where the dataset includes a small amount of production failure cases. The developed fault detection module exhibited outstanding performance with roughly 96% accuracy for actual process data.

• Journal of Advanced Navigation Technology
• /
• v.12 no.5
• /
• pp.502-508
• /
• 2008

With the increased use of the internet and the tremendous amount of data it transfers, it is more necessary to summarize documents. We propose a new method using the Non-negative Semantic Variable Matrix (NSVM) and the generic important of semantic features obtained by Non-negative Matrix Factorization (NMF) to extract the sentences for automatic generic summarization. The proposed method use non-negative constraints which is more similar to the human's cognition process. As a result, the proposed method selects more meaningful sentences for summarization than the unsupervised method used the Latent Semantic Analysis (LSA) or clustering methods. The experimental results show that the proposed method archives better performance than other methods.