• Journal of Information Processing Systems
• /
• v.1 no.1 s.1
• /
• pp.14-21
• /
• 2005

Even though mainly statistical methods have been used in anomaly network intrusion detection, to detect various attack types, machine learning based anomaly detection was introduced. Machine learning based anomaly detection started from research applying traditional learning algorithms of artificial intelligence to intrusion detection. However, detection rates of these methods are not satisfactory. Especially, high false positive and repeated alarms about the same attack are problems. The main reason for this is that one packet is used as a basic learning unit. Most attacks consist of more than one packet. In addition, an attack does not lead to a consecutive packet stream. Therefore, with grouping of related packets, a new approach of group-based learning and detection is needed. This type of approach is similar to that of multiple-instance problems in the artificial intelligence community, which cannot clearly classify one instance, but classification of a group is possible. We suggest group generation algorithm grouping related packets, and a learning algorithm based on a unit of such group. To verify the usefulness of the suggested algorithm, 1998 DARPA data was used and the results show that our approach is quite useful.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.52-60
• /
• 2022

Few-shot learning is a sub-area of machine learning problems, which aims to classify target images that only contain a few labeled samples for training. As a representative few-shot learning method, the Prototypical network has been received much attention due to its simplicity and promising results. However, the Prototypical network uses the sample mean of samples from the same class as the prototypes of that class, which easily results in learning uncharacteristic features in the low-data scenery. In this study, we propose to use local descriptors (i.e., patches along the channel within feature maps) from the same class to explicitly obtain more representative prototypes for Prototypical Network so that significant intra-class feature information can be maintained and thus improving the classification performance on few-shot learning tasks. Experimental results on various benchmark datasets including mini-ImageNet, CUB-200-2011, and tiered-ImageNet show that the proposed method can learn more discriminative intra-class features by the local descriptors and obtain more generic prototype representations under the few-shot setting.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.751-762
• /
• 2016

This paper presents an overview of the emerging field of quantum machine learning which promises an innovative expedited performance of current classical machine learning algorithms by applying quantum theory. The approaches and technical details of recently developed quantum machine learning algorithms that have been able to substantially accelerate existing classical machine learning algorithms are presented. In addition, the quantum annealing algorithm behind the first commercial quantum computer is also discussed.

• Journal of the Korea Institute of Building Construction
• /
• v.22 no.3
• /
• pp.317-326
• /
• 2022

With the development of various technologies in the area of artificial intelligence, a number of studies to application of artificial intelligence technology in the construction field are underway. Diverse technologies have been applied to the task of predicting construction costs, and construction cost prediction technologies applying artificial intelligence technologies have recently been developed. However, it is difficult to secure the vast amount of construction cost data required for machine learning, which has not yet been practically used. In this study, to predict the construction cost, the latest artificial neural network(ANN) method is used to propose a method to improve the construction cost prediction performance. In particular, to improve predictive performance, a log conversion method of target variables and a feature scaling method to eliminate the difference in the relative influence of each column data are applied, and their performance in predicting construction cost is compared and analyzed.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.673-681
• /
• 2021

This study is a case study of artificial intelligence education subjects in the graduate school of education. The main educational contents consisted of understanding and practice of machine learning, data analysis, actual artificial intelligence using Entries, artificial intelligence and physical computing. As a result of the survey on the educational effect after the application of the curriculum, it was found that the students preferred the use of the Entry AI block and the use of the Blacksmith board as a physical computing tool as the priority applied to the elementary education field. In addition, the data analysis area is effective in linking math data and graph education. As a physical computing tool, Husky Lens is useful for scalability by using image processing functions for self-driving car maker education. Suggestions for desirable AI education include training courses by level and reinforcement of data collection and analysis education.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.401-409
• /
• 2021

This study is a case study of artificial intelligence education subjects in the graduate school of education. The main educational contents consisted of understanding and practice of machine learning, data analysis, actual artificial intelligence using Entries, artificial intelligence and physical computing. As a result of the survey on the educational effect after the application of the curriculum, it was found that the students preferred the use of the Entry AI block and the use of the Blacksmith board as a physical computing tool as the priority applied to the elementary education field. In addition, the data analysis area is effective in linking math data and graph education. As a physical computing tool, Husky Lens is useful for scalability by using image processing functions for self-driving car maker education. Suggestions for desirable AI education include training courses by level and reinforcement of data collection and analysis education.

• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.212-220
• /
• 2024

When a typhoon or natural disaster occurs, a significant number of orchard fruits fall. This has a great impact on the income of farmers. In this paper, we introduce an AI-based method to enhance low-quality raw images. Specifically, we focus on apple images, which are being used as AI training data. In this paper, we utilize both a basic program and an artificial intelligence model to conduct a general image process that determines the number of apples in an apple tree image. Our objective is to evaluate high and low performance based on the close proximity of the result to the actual number. The artificial intelligence models utilized in this study include the Convolutional Neural Network (CNN), VGG16, and RandomForest models, as well as a model utilizing traditional image processing techniques. The study found that 49 red apple fruits out of a total of 87 were identified in the apple tree image, resulting in a 62% hit rate after the general image process. The VGG16 model identified 61, corresponding to 88%, while the RandomForest model identified 32, corresponding to 83%. The CNN model identified 54, resulting in a 95% confirmation rate. Therefore, we aim to select an artificial intelligence model with outstanding performance and use a real-time object separation method employing artificial function and image processing techniques to identify orchard fruits. This application can notably enhance the income and convenience of orchard farmers.

• Journal of The Korean Association of Information Education
• /
• v.25 no.2
• /
• pp.367-375
• /
• 2021

This study developed and applied an artificial intelligence education program as an educational method for increasing computational thinking of elementary school students and verified its effectiveness. The educational program was designed based on the results of a demand analysis conducted using Google survey of 100 elementary school teachers in advance according to the ADDIE(Analysis-Design-Development-Implementation-Evaluation) model. Among Machine Learning for Kids, we use scratch for block-based programming and develop and apply textbooks to improve computational thinking in the programming process of learning the principles of artificial intelligence and solving problems directly by utilizing numerical data. The degree of change in computational thinking was analyzed through pre- and post-test results using beaver challenge, and the analysis showed that this study had a positive impact on improving computational thinking of elementary school students.

• Design & Manufacturing
• /
• v.17 no.1
• /
• pp.27-32
• /
• 2023

In this paper, we intend to predict the mass of the spiral using CAE and machine learning. First, We generated 125 data for the experiment through a complete factor design of 3 factors and 5 levels. Next, the data were derived by performing a molding analysis through CAE, and the machine learning process was performed using a machine learning tool. To select the optimal model among the models learned using the learning data, accuracy was evaluated using RMSE. The evaluation results confirmed that the Support Vector Machine had a good predictive performance. To evaluate the predictive performance of the predictive model, We randomly generated 10 non-overlapping data within the existing injection molding condition level. We compared the CAE and support vector machine results by applying random data. As a result, good performance was confirmed with a MAPE value of 0.48%.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.2
• /
• pp.1-7
• /
• 2024

In this paper, we compare three models (logistic regression, Random Forest, and XGBoost) for predicting stroke occurrence using data from the Korea National Health and Nutrition Examination Survey (KNHANES). We evaluated these models using various metrics, focusing mainly on recall and F1 score to assess their performance. Initially, the logistic regression model showed a satisfactory recall score among the three models; however, it was excluded from further consideration because it did not meet the F1 score threshold, which was set at a minimum of 0.5. The F1 score is crucial as it considers both precision and recall, providing a balanced measure of a model's accuracy. Among the models that met the criteria, XGBoost showed the highest recall rate and showed excellent performance in stroke prediction. In particular, XGBoost shows strong performance not only in recall, but also in F1 score and AUC, so it should be considered the optimal algorithm for predicting stroke occurrence. This study determines that the performance of XGBoost is optimal in the field of stroke prediction.