• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.91-98
• /
• 2023

Recently, according to development of artificial intelligence, a wide range of industry being automatic and optimized. Also we can find out some research of using supervised learning for deteceting defect of railway in domestic rail industry. However, there are structures other than rails on the track, and the fastener is a device that binds the rail to other structures, and periodic inspections are required to prevent safety accidents. In this paper, we present a method of reducing cost for labeling using semi-supervised and transfer model trained on rail fastener data. We use Resnet50 as the backbone network pretrained on ImageNet. At first we randomly take training data from unlabeled data and then labeled that data to train model. After predict unlabeled data by trained model, we adopted a method of adding the data with the highest probability for each class to the training data by a predetermined size. Futhermore, we also conducted some experiments to investigate the influence of the number of initially labeled data. As a result of the experiment, model reaches 92% accuracy which has a performance difference of around 5% compared to supervised learning. This is expected to improve the performance of the classifier by using relatively few labels without additional labeling processes through the proposed method.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.119-125
• /
• 2023

Through the Ukraine-Russia war, the military importance of drones is being reassessed, and North Korea has completed actual verification through a drone provocation towards South Korea at 2022. Furthermore, North Korea is actively integrating artificial intelligence (AI) technology into drones, highlighting the increasing threat posed by drones. In response, the Republic of Korea military has established Drone Operations Command(DOC) and implemented various drone defense systems. However, there is a concern that the efforts to enhance capabilities are disproportionately focused on striking systems, making it challenging to effectively counter swarm drone attacks. Particularly, Air Force bases located adjacent to urban areas face significant limitations in the use of traditional air defense weapons due to concerns about civilian casualties. Therefore, this study proposes a new passive air defense method that aims at disrupting the object detection capabilities of AI models to enhance the survivability of friendly aircraft against the threat posed by AI based swarm drones. Using laser-based adversarial examples, the study seeks to degrade the recognition accuracy of object recognition AI installed on enemy drones. Experimental results using synthetic images and precision-reduced models confirmed that the proposed method decreased the recognition accuracy of object recognition AI, which was initially approximately 95%, to around 0-15% after the application of the proposed method, thereby validating the effectiveness of the proposed method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.5
• /
• pp.889-898
• /
• 2021

Currently, due to the demographic cliff phenomenon in Republic of Korea, A serious defense vacuum could occur due to the lack of South Korean military's personal strength. As a result, The South Korean military has a possibility to implement the polices the prepare for military provocations and preemptive strikes by the North Korean military while resolving the South Korean defense vacuum caused by the shrinking population. It seems like that the only way for the South Korean military to solve the shortage of personal strength due to the population decline is to reduce the number of Mechanized Units(MU) other than, infantry and automate, and autonomous driving the weapons system of the Mechanized Units(MU). In this paper, we propose the use of the virtual autonomous driving of the self propelled artillery K-9's in self selection of the position and occupation of position and self positioning in the position. At the same time in this paper, the self propelled artillery K-9 model robot is used to simulate and the explain about the operation method, necessity and feasibility in the self propelled artillery K-9. In addition, this paper predicted the problems that would arise if the South Korean military deployed autonomous driving self propelled K-9, in real combat.

• Journal of the Korea Society for Simulation
• /
• v.31 no.3
• /
• pp.55-61
• /
• 2022

Currently police and fire departments use a Network/Wifi/GPS based emergency location positioning system established by mobile carriers to directly link with the device of the people who request the rescue to accurately position the expected location in the call area. However in the case of mountain rescue it is difficult to rescue the victim in golden time because the location of the search area cannot be limited when the victim is located in a radio shadow area of the mountain or the device power is off and this situation become worse if victim fail to report 911 by himself due to the injury. In this paper, we are expected to solve the previous problem by propose the mobile telecommunication forensic simulator consist of time series of cell information, human mobility model which include some general and specific features (age, gender, behavioral characteristics of victim, etc.) and intelligent infer system. The results of analysis appear in heatmap of polygons on the map based on the probability of the expected location information of the victim. With this technology we are expected to contribute to rapid and accurate lifesaving by reducing the search area of rescue team.

• Journal of Korean Philosophical Society
• /
• v.147
• /
• pp.239-260
• /
• 2018

Is an artificial intelligence robot, a non-human beings newly emerging in the age of technology, a threat to human beings, or a mutual cooperation or ensemble with human beings? The desire to control nature through the use of the power of science and technology is manifested in the fear that humans can annihilate themselves. This study attempts to identify the problems of Cartesian epistemology underlying these questions and fears and to answer these questions based on Merleau - Ponty 's ontological ontology using the Ontology and Latour' s ontology and technological philosophy. The cogito derived from the Cartesian philosophy became the basis of the structure of dichotomous epistemology of 'subjectivity and objectivity' based on human - reason. In the human-centered world, all non-human beings were tools or controls for humans. The problem of the modern people is not only to get help from the natural scientific methods to control the nature including man, but also to think that scientific method is the only way to understand the world. In criticizing this, Merleau-Ponty shows that the body mediates between human beings and non-human beings, and provides a possible ontological basis for the ontology. Merleau - Ponty 's phenomenological methodology and ontology are newly developed by Simondon under the influence of phenomenological philosopher and phenomenology. The relationship between human beings and nonhuman beings by Simondon appears as an ensemble of human and technical objects or a mutual co - operation of human and technical objects. In particular, Latour goes a step further in Simondon and defines all the bodies living in the world as actor-network theory, denying the core concept of modernity. Merleau - Ponty 's phenomenological view can be a new possible basis for the philosophical discussion of the technological age. We will see that the problem itself can be solved by shifting modern fear to a phenomenological attitude.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.53-59
• /
• 2021

In this paper, we propose a BERGPT-chatbot, a domestic AI chatbot that can alleviate negative emotions based on text input such as 'Replika'. We made BERGPT-chatbot into a chatbot capable of mitigating negative emotions by pipelined two models, KR-BERT and KoGPT2-chatbot. We applied a creative method of giving emotions to unrefined everyday datasets through KR-BERT, and learning additional datasets through KoGPT2-chatbot. The development background of BERGPT-chatbot is as follows. Currently, the number of people with depression is increasing all over the world. This phenomenon is emerging as a more serious problem due to COVID-19, which causes people to increase long-term indoor living or limit interpersonal relationships. Overseas artificial intelligence chatbots aimed at relieving negative emotions or taking care of mental health care, have increased in use due to the pandemic. In Korea, Psychological diagnosis chatbots similar to those of overseas cases are being operated. However, as the domestic chatbot is a system that outputs a button-based answer rather than a text input-based answer, when compared to overseas chatbots, domestic chatbots remain at a low level of diagnosing human psychology. Therefore, we proposed a chatbot that helps mitigating negative emotions through BERGPT-chatbot. Finally, we compared BERGPT-chatbot and KoGPT2-chatbot through 'Perplexity', an internal evaluation metric for evaluating language models, and showed the superity of BERGPT-chatbot.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.155-170
• /
• 2018

Predicting a company's financial bankruptcy is traditionally one of the most crucial forecasting problems in business analytics. In previous studies, prediction models have been proposed by applying or combining statistical and machine learning-based techniques. In this paper, we propose a novel intelligent prediction model based on the simulated annealing which is one of the well-known optimization techniques. The simulated annealing is known to have comparable optimization performance to the genetic algorithms. Nevertheless, since there has been little research on the prediction and classification of business decision-making problems using the simulated annealing, it is meaningful to confirm the usefulness of the proposed model in business analytics. In this study, we use the combined model of simulated annealing and machine learning to select the input features of the bankruptcy prediction model. Typical types of combining optimization and machine learning techniques are feature selection, feature weighting, and instance selection. This study proposes a combining model for feature selection, which has been studied the most. In order to confirm the superiority of the proposed model in this study, we apply the real-world financial data of the Korean companies and analyze the results. The results show that the predictive accuracy of the proposed model is better than that of the naïve model. Notably, the performance is significantly improved as compared with the traditional decision tree, random forests, artificial neural network, SVM, and logistic regression analysis.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.50 no.6
• /
• pp.42-57
• /
• 2022

This study aims to create a basic model for classifying the activity photos that urban park users shared on social media using Deep Learning through Artificial Intelligence. Regarding the social media data, photos related to urban parks were collected through a Naver search, were collected, and used for the classification model. Based on the indicators of Naturalness, Potential Attraction, and Activity, which can be used to evaluate the characteristics of urban parks, 21 classification categories were created. Urban park photos shared on Naver were collected by category, and annotated datasets were created. A custom CNN model and a transfer learning model utilizing a CNN pre-trained on the collected photo datasets were designed and subsequently analyzed. As a result of the study, the Xception transfer learning model, which demonstrated the best performance, was selected as the urban park user activity image classification model and evaluated through several evaluation indicators. This study is meaningful in that it has built AI as an index that can evaluate the characteristics of urban parks by using user-shared photos on social media. The classification model using Deep Learning mitigates the limitations of manual classification, and it can efficiently classify large amounts of urban park photos. So, it can be said to be a useful method that can be used for the monitoring and management of city parks in the future.

• Journal of the Korea Convergence Society
• /
• v.10 no.3
• /
• pp.49-57
• /
• 2019

The core technology development of the Fourth Industrial Revolution is linked to the development of other core technologies, which will change the industrial structure in the future and create a new smart business model. In this paper, tried to analyze the technology maturity level and analyze the technology maturity. To do this, used technology trend information to investigate and integrate the market, policy, etc. Of core technology of the 4th Industrial Revolution to achieve a comprehensive maturity level. Because technology maturity measures are scored by technology developers, prejudices may be acted upon according to a person's tendency, which may be a subjective evaluation. It is also a measure of the maturity of individual technologies, and thus is not suitable for evaluating the overall system integration perspective. However, it is possible to evaluate the maturity before integrating the core element technologies constituting the whole system and to use it as a means to compare the effect of the whole system and its feasibility and play an important role in the planning of technology development.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.293-301
• /
• 2023

Unstandardized medical data collection and management are still being conducted manually, and studies are being conducted to classify CT data using deep learning to solve this problem. However, most studies are developing models based only on the axial plane, which is a basic CT slice. Because CT images depict only human structures unlike general images, reconstructing CT scans alone can provide richer physical features. This study seeks to find ways to achieve higher performance through various methods of converting CT scan to 2D as well as axial planes. The training used 1042 CT scans from five body parts and collected 179 test sets and 448 with external datasets for model evaluation. To develop a deep learning model, we used InceptionResNetV2 pre-trained with ImageNet as a backbone and re-trained the entire layer of the model. As a result of the experiment, the reconstruction data model achieved 99.33% in body part classification, 1.12% higher than the axial model, and the axial model was higher only in brain and neck in contrast classification. In conclusion, it was possible to achieve more accurate performance when learning with data that shows better anatomical features than when trained with axial slice alone.