• The Journal of the Korea Contents Association
• /
• v.18 no.11
• /
• pp.123-134
• /
• 2018

Recently, due to the rising incidence of disasters in the nation, there has been a growing interest in the relevance and role of science and technology in solving disaster and safety related issues. In addition, the necessities of securing the human rights of all citizens in disaster risk reduction, identifying fields of technology development for effective disaster response, and improving the efficiency of R&D investment for disaster and safety are becoming more important as the different types of disasters and stages of disaster and safety management process have been considered. In this study, we analyzed bipartite or two-mode networks constructed from an expert survey dataset of technology development for disaster and safety management. The results reveal that earthquake and fire are the two disasters affecting an individual and society at large and demonstrate that AI and big data analytics are effective supports in managing disaster and safety. We believe that such a network analytic approach can be used to explore some important implications exist for the national science and technology effort and successful disaster and safety management practices in Korea.

• Tunnel and Underground Space
• /
• v.30 no.6
• /
• pp.540-550
• /
• 2020

Machine learning has been actively used in the field of automation due to the development and establishment of AI technology. The important thing in utilizing machine learning is that appropriate algorithms exist depending on data characteristics, and it is needed to analysis the datasets for applying machine learning techniques. In this study, advance rate is predicted using geotechnical and machine data of TBM tunnel section passing through the soil ground below the stream. Although there were no problems of application of statistical technology in the linear regression model, the coefficient of determination was 0.76. While, the ensemble model and support vector machine showed the predicted performance of 0.88 or higher. it is indicating that the model suitable for predicting advance rate of the EPB Shield TBM was the support vector machine in the analyzed dataset. As a result, it is judged that the suitability of the prediction model using data including mechanical data and ground information is high. In addition, research is needed to increase the diversity of ground conditions and the amount of data.

• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.1-9
• /
• 2021

Deep learning in computer vision has made accelerated improvement over a short period but large-scale learning data and computing power are still essential that required time-consuming trial and error tasks are involved to derive an optimal network model. In this study, we propose a similar image classification performance improvement method based on CR (Confusion Rate) that considers only the characteristics of the data itself regardless of network optimization or data reinforcement. The proposed method is a technique that improves the performance of the deep learning model by calculating the CRs for images in a dataset with similar characteristics and reflecting it in the weight of the Loss Function. Also, the CR-based recognition method is advantageous for image identification with high similarity because it enables image recognition in consideration of similarity between classes. As a result of applying the proposed method to the Resnet18 model, it showed a performance improvement of 0.22% in HanDB and 3.38% in Animal-10N. The proposed method is expected to be the basis for artificial intelligence research using noisy labeled data accompanying large-scale learning data.

• Journal of Internet of Things and Convergence
• /
• v.8 no.1
• /
• pp.37-43
• /
• 2022

The fundamental basis of AI technology is learningable data. Recently, the types and amounts of data collected and produced by the government or private companies are increasing exponentially, however, verified data that can be used for actual machine learning has not yet led to it. This study discusses the conditions that data actually can be used for machine learning should meet, and identifies factors that degrade data quality through case studies. To this end, two representative cases of developing a prediction model using public big data was selected, and data for actual problem solving was collected from the public data portal. Through this, there is a difference from the results of applying valid data screening criteria and post-processing. The ultimate purpose of this study is to argue the importance of data quality management that must be most fundamentally preceded before the development of machine learning technology, which is the core of artificial intelligence, and accumulating valid data.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.51-66
• /
• 2023

In this paper, we propose a new type of process discovery framework, which is named as control-path-driven process group discovery framework, to be used for process mining and process reengineering in supporting life-cycle management of business process models. In addition, we develop a process mining system based on the proposed framework and perform experimental verification through it. The process execution event logs applied to the experimental effectiveness and verification are specially defined as Process BIG-Logs, and we use it as the input datasets for the proposed discovery framework. As an eventual goal of this paper, we design and implement a control path-driven process group discovery algorithm and framework that is improved from the ρ-algorithm, and we try to verify the functional correctness of the proposed algorithm and framework by using the implemented system with a BIG-Log dataset. Note that all the process mining algorithm, framework, and system developed in this paper are based on the structural information control net process modeling methodology.

• Information Systems Review
• /
• v.24 no.4
• /
• pp.97-118
• /
• 2022

As generative adversarial network (GAN) based oversampling techniques have achieved impressive results in class imbalance of unstructured dataset such as image, many studies have begun to apply it to solving the problem of imbalance in structured dataset. However, these studies have failed to reflect the characteristics of structured data due to changing the data structure into an unstructured data format. In order to overcome the limitation, this study adapted CycleGAN to reflect the characteristics of structured data, and proposed hybridization of synthetic minority oversampling technique (SMOTE) and the adapted CycleGAN. In particular, this study tried to overcome the limitations of existing studies by using a one-dimensional convolutional neural network unlike previous studies that used two-dimensional convolutional neural network. Oversampling based on the method proposed have been experimented using various datasets and compared the performance of the method with existing oversampling methods such as SMOTE and adaptive synthetic sampling (ADASYN). The results indicated the proposed hybrid oversampling method showed superior performance compared to the existing methods when data have more dimensions or higher degree of imbalance. This study implied that the classification performance of oversampling structured data can be improved using the proposed hybrid oversampling method that considers the characteristic of structured data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3904-3922
• /
• 2022

As a research hotspot, pedestrian detection has a wide range of applications in the field of computer vision in recent years. However, current pedestrian detection methods have problems such as insufficient detection accuracy and large models that are not suitable for large-scale deployment. In view of these problems mentioned above, a lightweight pedestrian detection and early warning method using a new model called you only look once (Yolov5) is proposed in this paper, which utilizing advantages of Yolov5s model to achieve accurate and fast pedestrian recognition. In addition, this paper also optimizes the loss function of the batch normalization (BN) layer. After sparsification, pruning and fine-tuning, got a lot of optimization, the size of the model on the edge of the computing power is lower equipment can be deployed. Finally, from the experimental data presented in this paper, under the training of the road pedestrian dataset that we collected and processed independently, the Yolov5s model has certain advantages in terms of precision and other indicators compared with traditional single shot multiBox detector (SSD) model and fast region-convolutional neural network (Fast R-CNN) model. After pruning and lightweight, the size of training model is greatly reduced without a significant reduction in accuracy, and the final precision reaches 87%, while the model size is reduced to 7,723 KB.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.5
• /
• pp.273-283
• /
• 2022

Banking and finance is a broad term that incorporates a variety of smaller, more specialized subjects such as corporate finance, tax finance, and insurance finance. A virtual assistant that assists users in searching for information about banking and finance terms might be an extremely beneficial tool for users. In this study, we explored the process of searching for information, seeking opportunities, and developing a virtual assistant in the first stages of starting learning and understanding Vietnamese to increase effectiveness and save time, which is also an innovative business practice in Use-case Vietnam. We built the FIBA2020 dataset and proposed a pipeline that used Natural Language Processing (NLP) inclusive of Natural Language Understanding (NLU) algorithms to build chatbot applications. The open-source framework RASA is used to implement the system in our study. We aim to improve our model performance by replacing parts of RASA's default tokenizers with Vietnamese tokenizers and experimenting with various language models. The best accuracy we achieved is 86.48% and 70.04% in the ideal condition and worst condition, respectively. Finally, we put our findings into practice by creating an Android virtual assistant application using the model trained using Whitespace tokenizer and the pre-trained language m-BERT.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.12
• /
• pp.357-362
• /
• 2023

Bridges are important transportation infrastructure, but they are subject to damage and cracking due to various environmental factors and constant traffic loads, which accelerate their aging. With many bridges now older than their original construction, there is a need for systems to ensure safety and diagnose deterioration. Bridges are already utilizing structural health monitoring (SHM) technology to monitor the condition of bridges in real time or periodically. Along with this technology, the development of intelligent bridge monitoring technology utilizing artificial intelligence and Internet of Things technology is underway. In this paper, we study an edge system technique for predicting bridge safety using fast Fourier transform and dimensionality reduction algorithm for maintenance of aging bridges. In particular, unlike previous studies, we investigate whether it is possible to form a dataset using sensor data collected from actual bridges and check the safety of bridges.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.5
• /
• pp.1019-1026
• /
• 2019

Due to limitations of existing methods for detecting newly introduced malware, the importance of the development of artificial intelligence vaccines arises. Existing artificial intelligence vaccines have a disadvantage that the accuracy of the detection rate is low because those vaccines do not scan all parts of the file. In this paper, we suggest an enhanced method for detecting malware which is composed of unique OP Code features in the malware files. Specifically, we tested the method with text datasets trained on Random Forest algorithm and with image datasets trained on the Inception V3 model. As a result, the highest accuracy of the detection rate was about 80%.