• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.19-27
• /
• 2022

In general, the performance of ML(Machine Learning) application is determined by various factors such as the type of ML model, the size of model (number of parameters), hyperparameters setting during the training, and training data. In particular, the recognition accuracy of ML may be deteriorated or experienced overfitting problem if the amount of dada used for training is insufficient. Existing studies focusing on image recognition have widely used open datasets for training and evaluating the proposed ML models. However, for specific applications where the sensor used, the target of recognition, and the recognition situation are different, it is necessary to build the dataset manually. In this case, the performance of ML largely depends on the quantity and quality of the data. In this paper, training data used for motion recognition application is augmented using the kernel density estimation algorithm which is a type of non-parametric estimation method. We then compare and analyze the recognition accuracy of a ML application by varying the number of original data, kernel types and augmentation rate used for data augmentation. Finally experimental results show that the recognition accuracy is improved by up to 14.31% when using the narrow bandwidth Tophat kernel.

• Journal of Convergence for Information Technology
• /
• v.12 no.5
• /
• pp.1-14
• /
• 2022

This study tried to suggest crisis management compliance to prevent personal information infringement accidents that may occur in the process because the data including personal information is being processed in the artificial intelligence (AI) service process. To this end, first, the AI service provision process is divided into 3 processes such as service planning/data design and collection process, data pre-processing and purification process, and algorithm development and utilization process. And 3 processes are subdivided into 9 stages following to personal information processing stages to infringe personal information. All processes were investigated with literature and experts' Delphi. Second, the investigated personal information infringement factors were selected through FGI, Delphi, etc. for experts. Third, a survey was conducted with experts on the severity and possibility of each personal information infringement factor, and the validity and adequacy of the 94 responses were verified. Fourth, to present appropriate risk management compliance for personal information infringement factors in AI services, a method for calculating the risk level of personal information infringement is prepared by utilizing the asset value of personal information, personal information infringement factors, and the possibility of infringement accidents. Through this, the countermeasures for personal information infringement incidents were suggested according to the scored risk level.

• Tunnel and Underground Space
• /
• v.32 no.5
• /
• pp.298-311
• /
• 2022

Some problems, such as aging workers, a decreased population due to a low birth rate, and shortage of skilled workers, are rising in construction sites. Therefore research for smart construction technology that can be improved for productivity, safety, and quality has been recently developed with government support by replacing traditional construction technology with advanced digital technology. In particular, the motor grader that mainly performs road surface flattening is a construction machine that requires the application of automation technology for repetitive construction. It is predicted that the construction period will be shortened if the construction automation technology such as trajectory tracking, automation work, and remote control technology is applied. In this study, we introduce the hardware and software architecture of the smart motor grader to apply unmanned and automation technology and then analyze the traditional earthwork method of the motor grader. We suggested the application plans for the path pattern and blade control method of the smart motor grader based on this. In addition, we verified the performance of waypoint-based path-following depending on scenarios and the blade control's performance through tests.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.315-324
• /
• 2022

In this paper, we propose KoEPT, a Transformer-based generative model for automatic math word problems solving. A math word problem written in human language which describes everyday situations in a mathematical form. Math word problem solving requires an artificial intelligence model to understand the implied logic within the problem. Therefore, it is being studied variously across the world to improve the language understanding ability of artificial intelligence. In the case of the Korean language, studies so far have mainly attempted to solve problems by classifying them into templates, but there is a limitation in that these techniques are difficult to apply to datasets with high classification difficulty. To solve this problem, this paper used the KoEPT model which uses 'expression' tokens and pointer networks. To measure the performance of this model, the classification difficulty scores of IL, CC, and ALG514, which are existing Korean mathematical sentence problem datasets, were measured, and then the performance of KoEPT was evaluated using 5-fold cross-validation. For the Korean datasets used for evaluation, KoEPT obtained the state-of-the-art(SOTA) performance with 99.1% in CC, which is comparable to the existing SOTA performance, and 89.3% and 80.5% in IL and ALG514, respectively. In addition, as a result of evaluation, KoEPT showed a relatively improved performance for datasets with high classification difficulty. Through an ablation study, we uncovered that the use of the 'expression' tokens and pointer networks contributed to KoEPT's state of being less affected by classification difficulty while obtaining good performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.77-82
• /
• 2023

The Ministry of Agriculture, Food and Rural Affairs established the FarmMap, an digital map of agricultural land. In this study, using deep learning, we suggest the application of farm map reading to farmland such as paddy fields, fields, ginseng, fruit trees, facilities, and uncultivated land. The farm map is used as spatial information for planting status and drone operation by digitizing agricultural land in the real world using aerial and satellite images. A reading manual has been prepared and updated every year by demarcating the boundaries of agricultural land and reading the attributes. Human reading of agricultural land differs depending on reading ability and experience, and reading errors are difficult to verify in reality because of budget limitations. The farmmap has location information and class information of the corresponding object in the image of 5 types of farmland properties, so the suitable AI technique was tested with ResNet50, an instance segmentation model. The results of attribute reading of agricultural land using deep learning and attribute reading by humans were compared. If technology is developed by focusing on attribute reading that shows different results in the future, it is expected that it will play a big role in reducing attribute errors and improving the accuracy of digital map of agricultural land.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.8
• /
• pp.253-262
• /
• 2023

E-voting is a concept that includes actions such as kiosk voting at a designated place and internet voting at an unspecified place, and has emerged to alleviate the problem of consuming a lot of resources and costs when conducting offline voting. Using E-voting has many advantages over existing voting systems, such as increased efficiency in voting and ballot counting, reduced costs, increased voting rate, and reduced errors. However, centralized E-voting has not received attention in public elections and voting on corporate agendas because the results of voting cannot be trusted due to concerns about data forgery and modulation and hacking by others. In order to solve this problem, recently, by designing an E-voting system using blockchain, research has been actively conducted to supplement concepts lacking in existing E-voting, such as increasing the reliability of voting information and securing transparency. In this paper, we proposed an electronic voting system that introduced hybrid blockchain that uses public and private blockchains in convergence. A hybrid blockchain can solve the problem of slow transaction processing speed, expensive fee by using a private blockchain, and can supplement for the lack of transparency and data integrity of transactions through a public blockchain. In addition, the proposed system is implemented as BaaS to ensure the ease of type conversion and scalability of blockchain and to provide powerful computing power. BaaS is an abbreviation of Blockchain as a Service, which is one of the cloud computing technologies and means a service that provides a blockchain platform ans software through the internet. In this paper, in order to evaluate the feasibility, the proposed system and domestic and foreign electronic voting-related studies are compared and analyzed in terms of blockchain type, anonymity, verification process, smart contract, performance, and scalability.

• Journal of the Korea Society for Simulation
• /
• v.19 no.4
• /
• pp.291-299
• /
• 2010

As recent advances in science, technology and performance requirements of the weapons system are getting highly diversified and complex, the performance requirements also get stringent and strict. Moreover, the weapons system should be intimately connected with other systems such as watchdog system, command and control system, C4I system, etc. However, a tremendous amount of time, cost and risk being spent to acquire new weapons system, and not being diminished compared to the rapid pace of its development speed. Defense Modeling and Simulation(M&S) comes into the spotlight as an alternative to overcoming these difficulties as well as constraints. In this paper, we propose the development process of virtual test framework based on the synthetic environment as a tool to analyze the effectiveness of the weapons system of underwater engagement model. To prove the proposed concept, we develop the test-bed of virtual test using Delta3D simulation engine, which is open source S/W. We also design the High Level Architecture and Real-time Infrastructure(HLA/RTI) based Federation for the interoperation with heterogeneous simulators. The significance of the study entails (1)the rapid and easy development of simulation tools that are customized for the Korean Theater of War; (2)the federation of environmental entities and the moving equations of the combat entities to manifest a realistic simulation.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.314-328
• /
• 2023

In this paper, we propose a texture map compression method based on the hierarchical coding method of SHVC to support the scalability function of dynamic mesh compression. The proposed method effectively eliminates the redundancy of multiple-resolution texture maps by downsampling a high-resolution texture map to generate multiple-resolution texture maps and encoding them with SHVC. The dynamic mesh decoder supports the scalability of mesh data by decoding a texture map having an appropriate resolution according to receiver performance and network environment. To evaluate the performance of the proposed method, the proposed method is applied to V-DMC (Video-based Dynamic Mesh Coding) reference software, TMMv1.0, and the performance of the scalable encoder/decoder proposed in this paper and TMMv1.0-based simulcast method is compared. As a result of experiments, the proposed method effectively improves in performance the average of -7.7% and -5.7% in terms of point cloud-based BD-rate (Luma PSNR) in AI and LD conditions compared to the simulcast method, confirming that it is possible to effectively support the texture map scalability of dynamic mesh data through the proposed method.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.173-178
• /
• 2023

As Korean literature spreads around the world, its position in the overseas publishing market has become important. As demand in the overseas publishing market continues to grow, it is essential to predict future book sales and analyze the characteristics of books that have been highly favored by overseas readers in the past. In this study, we proposed ensemble learning based prediction model and analyzed characteristics of the cumulative sales of more than 5,000 copies classified as good sellers published overseas over the past 5 years. We applied the five ensemble learning models, i.e., XGBoost, Gradient Boosting, Adaboost, LightGBM, and Random Forest, and compared them with other machine learning algorithms, i.e., Support Vector Machine, Logistic Regression, and Deep Learning. Our experimental results showed that the ensemble algorithm outperforms other approaches in troubleshooting imbalanced data. In particular, the LightGBM model obtained an AUC value of 99.86% which is the best prediction performance. Among the features used for prediction, the most important feature is the author's number of overseas publications, and the second important feature is publication in countries with the largest publication market size. The number of evaluation participants is also an important feature. In addition, text mining was performed on the four book reviews that sold the most among good-selling books. Many reviews were interested in stories, characters, and writers and it seems that support for translation is needed as many of the keywords of "translation" appear in low-rated reviews.

• Journal of The Korean Association of Information Education
• /
• v.26 no.5
• /
• pp.341-352
• /
• 2022

The wave of a knowledge and information society led by AI, Big Data, and so on is having an all-round impact on our way of life. Therefore the Ministry of Education is in a hurry to strengthen Digital Literacy, including AI and SW Education, by improving the curriculum that can cultivate basic knowledge and capabilities to respond to changes in the future society. It can be seen that establishing a foundation for cultivating Digital Literacy through all subjects and improving basic and in-depth learning in new technology fields such as AI linked to the information curriculum is an essential part for future society. However, research on each content for cultivating Digital and AI literacy is relatively active, while research on teaching and learning strategies is insufficient. Therefore in this study, a CT-based Digital and AI teaching and learning strategy that can foster that was developed and Delphi expert verification was conducted, and the final teaching and learning strategy was completed after evaluating instructor usability and analyzing learner effectiveness.