• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.159-168
• /
• 2021

Detecting cyber-attacks using machine learning or deep learning is being studied and applied widely in network intrusion detection systems. We noticed that the application of deep learning algorithms yielded many good results. However, because each deep learning model has different architecture and characteristics with certain advantages and disadvantages, so those deep learning models are only suitable for specific datasets or features. In this paper, in order to optimize the process of detecting cyber-attacks, we propose the idea of building a new deep learning network model based on the association and combination of individual deep learning models. In particular, based on the architecture of 2 deep learning models: Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM), we combine them into a combined deep learning network for detecting cyber-attacks based on network traffic. The experimental results in Section IV.D have demonstrated that our proposal using the CNN-LSTM deep learning model for detecting cyber-attacks based on network traffic is completely correct because the results of this model are much better than some individual deep learning models on all measures.

• Journal of Korea Multimedia Society
• /
• v.22 no.4
• /
• pp.515-526
• /
• 2019

DOOH(Digital Out Of Home) advertising targets for reaching consumers through outdoor digital display medias. Traditionally, scheduling of advertisement contents over DOOH medias is usually done by operator's strategy, but an efficient ad scheduling strategy is not easy to find under various advertising contexts. In this paper, we present a context-aware factorization machine-based recommendation model for the scheduling under various advertising contexts, and provide analysis for understanding of the contexts' effects on advertising based on the recommendation model. Through simulation results on the dataset adapted from a real dataset of RecSys challenge 2015, it is shown that the proposed model and analysis based on the model will be effective for better scheduling of ad contents under advertising contexts over DOOH networks.

• International journal of advanced smart convergence
• /
• v.9 no.4
• /
• pp.115-119
• /
• 2020

Recently, CCTV installations are rapidly increasing in the public and private sectors to prevent various crimes. In accordance with the increasing number of CCTVs, video-based abnormal behavior detection in control systems is one of the key technologies for safety. This is because it is difficult for the surveillance personnel who control multiple CCTVs to manually monitor all abnormal behaviors in the video. In order to solve this problem, research to recognize abnormal behavior using deep learning is being actively conducted. In this paper, we propose a model for detecting abnormal behavior based on the deep learning model that is currently widely used. Based on the abnormal behavior video data provided by AI Hub, we performed a comparative experiment to detect anomalous behavior through violence learning and fainting in videos using 2D CNN-LSTM, 3D CNN, and I3D models. We hope that the experimental results of this abnormal behavior learning model will be helpful in developing intelligent CCTV.

• International journal of advanced smart convergence
• /
• v.10 no.2
• /
• pp.201-208
• /
• 2021

Recently, artificial intelligence(AI) has been used throughout society, and social interest in it is increasing. Accordingly, the necessity of AI education is becoming a big topic in the education field. As a response to this trend, the Korean education authorities have also announced plans for AI education, and various studies have been performed in academic field to revitalize AI education in the future. However, the curriculum research on what differentiates AI education from existing SW education and what and how to train AI is still in its infancy. In this paper, Therefore, we focused on the experiences of elementary school students in solving problems in their own lives, and developed a teaching-learning model based on design-based research so that students can design a problem-solving process and experience the process of feedback. We applied the developed teaching-learning model to the problem-solving process and confirmed that it increased students' understanding and satisfaction with AI education.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.1-12
• /
• 2022

The current progression in the Internet of Things (IoT) and Machine Learning (ML) based technologies converted the traditional healthcare system into a smart healthcare system. The incorporation of IoT and ML has changed the way of treating patients and offers lots of opportunities in the healthcare domain. In this view, this research article presents a new IoT and ML-based disease diagnosis model for the diagnosis of different diseases. In the proposed model, vital signs are collected via IoT-based smart medical devices, and the analysis is done by using different data mining techniques for detecting the possibility of risk in people's health status. Recommendations are made based on the results generated by different data mining techniques, for high-risk patients, an emergency alert will be generated to healthcare service providers and family members. Implementation of this model is done on Anaconda Jupyter notebook by using different Python libraries in it. The result states that among all data mining techniques, SVM achieved the highest accuracy of 0.897 on the same dataset for classification of Parkinson's disease.

• International conference on construction engineering and project management
• /
• 2005.10a
• /
• pp.503-508
• /
• 2005

In the modern, distributed and dynamic construction environment it is important to exchange information from different sources and in different data formats in order to improve the processes supported by these systems. Previous research has demonstrated that (i) a significant percentage of construction data is stored in semi-structured or unstructured data formats (ii) locating and identifying such data that are needed for the important decision making processes is a very hard and time-consuming task. In this paper, an automated methodology for the classification and retrieval of construction images in AEC/FM model based systems will be presented. Specifically, a combination of techniques from the areas of image processing, computer vision, and content-based image retrieval have been deployed to develop a method that can retrieve related construction site image data from components of a project model.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• Journal of Electrical Engineering and Technology
• /
• v.1 no.2
• /
• pp.161-169
• /
• 2006

Load representation has a significant impact on power system analysis and control results. In this paper, composite load models are developed based on on-line measurement data from a practical power system. Three types of static-dynamic load models are derived: general ZIP-induction motor model, Exponential-induction motor model and Z-induction motor model. For the dynamic induction motor model, two different third-order induction motor models are studied. The performances in modeling real and reactive power behaviors by composite load models are compared with other dynamic load models in terms of relative mismatch error. In addition, numerical consideration of ill-conditioned parameters is addressed based on trajectory sensitivity. Numerical studies indicate that the developed composite load models can accurately capture the dynamic behaviors of loads during disturbance.

• Korean Journal of Computational Design and Engineering
• /
• v.15 no.3
• /
• pp.243-252
• /
• 2010

This paper describes a new practical simplification method for feature-based solid models. In this approach, a solid model created using feature modeling operations is first simplified by the suppression of detailed features, and then, if necessary, the model is converted to a surface model to facilitate its modification. Finally, the simplified surface model is delivered to analysis packages. The algorithm was implemented based on CATIA V.5 and applied to mid-surface generation of plastic parts for structural analysis to prove the validity and usefulness.

• Korean Journal of Computational Design and Engineering
• /
• v.13 no.3
• /
• pp.217-226
• /
• 2008

Web Services for CAD (WSC) aims at interoperation with CAD systems based on Web Services. This paper introduces one part of WSC which enables remote users to retrieve assembly model data using Web Services. However, retrieving assembly model data takes long time. To resolve this problem, this paper proposes using parallel Web Services. As assembly models comprise a set of part models, it is easy to separate the problem domain into smaller problems. In addition, Web Services inherently supports distributed computing. This characteristic makes the parallel processing of Web Services easy. Firstly, the implementation of WSC which retrieves assembly model data based parallel Web Services is shown. And then, for the comparison, the experiments on the retrieval of assembly model data based on single Web Services and parallel Web Services are shown.