• Journal of Korea Port Economic Association
• /
• v.36 no.3
• /
• pp.39-54
• /
• 2020

In the presidential political system, the word of the president has great influence on the formation of national policy and the decision-making process. Policy priorities are determined according to the president's ideology and core values, and various policies are established and executed according to the priorities. Therefore, this paper analyzes the contents of the president's speech. Since the president's speech is a semantic datum, in order to analyze unstructured text, big data analysis is conducted through the methods of machine learning and deep learning. In this study, the president's speech at the "National Sea Day" commemoration was obtained 1996 onwards and analyzed using topic modeling. As a result of the analysis, all the presidents' speeches were delivered with a view of the ocean that was consistent with the direction of their administration. It was confirmed that the ocean-industry-resource topics, which are the intrinsic values of the ocean, were not damaged and consistently emphasized by all presidents.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.632-637
• /
• 2020

The non-intrusive load monitoring (NILM) is an important way to cost-effective real-time monitoring the energy consumption and time of use for each appliance in a home or business using aggregated energy from a single recording meter. In this paper, we collect from the smart farm's power consumption data acquisition system to the server via an LTE modem, converted the total power consumption, and the power of individual electric devices into HDF5 format and performed NILM analysis. We perform NILM analysis using open source denoising autoencoder (DAE), long short-term memory (LSTM), gated recurrent unit (GRU), and sequence-to-point (seq2point) learning methods.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.447-453
• /
• 2020

In this paper, we propose a system to extract effective speaker representations from a speech signal using a deep learning method. Based on the fact that speech signal contains identity unrelated information such as text content, emotion, background noise, and so on, we perform a training such that the extracted features only represent speaker-related information but do not represent speaker-unrelated information. Specifically, we propose an auto-encoder based disentanglement method that outputs both speaker-related and speaker-unrelated embeddings using effective loss functions. To further improve the reconstruction performance in the decoding process, we also introduce a discriminator popularly used in Generative Adversarial Network (GAN) structure. Since improving the decoding capability is helpful for preserving speaker information and disentanglement, it results in the improvement of speaker verification performance. Experimental results demonstrate the effectiveness of our proposed method by improving Equal Error Rate (EER) on benchmark dataset, Voxceleb1.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.6
• /
• pp.1383-1392
• /
• 2019

Adversarial attack, which geneartes adversarial data to make target model misclassify the input data, is able to confuse real life applications of classification models and cause severe damage to the classification system. An Black-box adversarial attack learns a substitute model, which have similar decision boundary to the target model, and then generates adversarial data with the substitute model. Jacobian-based data augmentation is used to synthesize the training data to learn substitutes, but has a drawback that the data synthesized by the augmentation get distorted more and more as the training loop proceeds. We suggest data augmentation with 'decay factor' to alleviate this problem. The result shows that attack success rate of our method is higher(around 8.5%) than the existing method.

• Journal of Convergence for Information Technology
• /
• v.11 no.5
• /
• pp.94-103
• /
• 2021

This study aims to propose technical trading rules for Bitcoin futures and empirically analyze investment performance. Investment strategies include standard trading rules such as VMA, TRB, FR, MACD, RSI, BB, using Bitcoin futures daily data from December 18, 2017 to March 31, 2021. The trend-following rules showed higher investment performance than the comparative strategy B&H. Compared to KOSPI200 index futures, Bitcoin futures investment performance was higher. In particular, the investment performance has increased significantly in Sortino Ratio, which reflects downside risk. This study can find academic significance in that it is the first attempt to systematically analyze the investment performance of standard technical trading rules of Bitcoin futures. In future research, it is necessary to improve investment performance through the use of deep learning models or machine learning models to predict the price of Bitcoin futures.

• Journal of Ocean Engineering and Technology
• /
• v.33 no.5
• /
• pp.427-434
• /
• 2019

Artificial intelligence (AI)-aided research currently enjoys active use in a wide array of fields thanks to the rapid development of computing capability and the use of Big Data. Until now, forecasting methods were primarily based on physics models and statistical studies. Today, AI is utilized in disaster prevention forecasts by studying the relationships between physical factors and their characteristics. Current studies also involve combining AI and physics models to supplement the strengths and weaknesses of each aspect. However, prior to these studies, an optimization algorithm for the AI model should be developed and its applicability should be studied. This study aimed to improve the forecast performance by constructing a model for neural network optimization. An artificial neural network (ANN) followed the ever-changing path of a typhoon to produce similar typhoon predictions, while the optimization achieved by the neural network algorithm was examined by evaluating the activation function, hidden layer composition, and dropouts. A learning and test dataset was constructed from the available digital data of one typhoon that affected Korea throughout the record period (1951-2018). As a result of neural network optimization, assessments showed a higher degree of forecast accuracy.

• Informatization Policy
• /
• v.27 no.4
• /
• pp.47-66
• /
• 2020

The rapid development of artificial intelligence technologies such as machine learning and deep learning is expanding its impact in the public administrative and public policy sphere. This paper is an exploratory study on policy decision-making in the age of artificial intelligence to design automated configuration and operation through data analysis and algorithm development. The theoretical framework was composed of the types of policy problems according to the degree of problem structuring, and the success and failure cases were classified and analyzed to derive implications. In other words, when the problem structuring is more difficult than others, the greater the possibility of failure or side effects of decision-making using artificial intelligence. Also, concerns about the neutrality of the algorithm were presented. As a policy suggestion, a subcommittee was proposed in which experts in technical and social aspects play a professional role in establishing the AI promotion system in Korea. Although the subcommittee works independently, it suggests that it is necessary to establish governance in which the results of activities can be synthesized and integrated.

• Journal of the Korea Convergence Society
• /
• v.12 no.2
• /
• pp.21-28
• /
• 2021

In this study, we propose a deep learning-based NILM technique using actual measured power data for 5 kinds of home appliances and verify its effectiveness. For about 3 weeks, the active power of the central power measuring device and five kinds of home appliances (refrigerator, induction, TV, washing machine, air cleaner) was individually measured. The preprocessing method of the measured data was introduced, and characteristics of each household appliance were analyzed through spectogram analysis. The characteristics of each household appliance are organized into a learning data set. All the power data measured by the central power measuring device and 5 kinds of home appliances were time-series mapping, and training was performed using a LSTM neural network, which is excellent for time series data prediction. An algorithm that can disaggregate five types of energies using only the power data of the main central power measuring device is proposed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.933-943
• /
• 2022

As the Internet develops and the utilization rate of computers increases, the threats posed by malware keep increasing. This leads to the demand for a system to automatically analyzes a large amount of malware. In this paper, an automatic malware analysis technique using a deep learning algorithm is introduced. Our proposed method uses CNN (Convolutional Neural Network) to analyze the malicious features represented as images. To reflect semantic information of malware for detection, our method uses the opcode frequency data of binary for image generation, rather than using bytes of binary. As a result of the experiments using the datasets consisting of 20,000 samples, it was found that the proposed method can detect malicious codes with 91% accuracy.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.465-468
• /
• 2022

The incidence of traffic accidents is increasing every year, and Korea is among the top OECD countries. In order to improve this, various road traffic laws are being implemented, and various traffic control methods using equipment such as unmanned speed cameras and traffic control cameras are being applied. However, as drivers avoid crackdowns by detecting the location of traffic control cameras in advance through navigation, a mobile crackdown system that can be cracked down is needed, and research is needed to increase the recognition rate of vehicle license plates on the side of the road for accurate crackdown. This paper proposes a method to improve the vehicle number recognition rate on the road side by applying a gradient correction algorithm using image processing. In addition, custom data learning was conducted using a CNN-based YOLO algorithm to improve character recognition accuracy. It is expected that the algorithm can be used for mobile traffic control cameras without restrictions on the installation location.