• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.970-977
• /
• 2018

The autonomous vehicle is based on an advanced driver assistance system (ADAS) consisting of a sensor that collects information about the surrounding environment and a control module that determines the measured data. As interest in autonomous navigation technology grows recently, an easy development framework for ADAS beginners and learners is needed. However, existing development and verification methods are based on high performance vehicle simulator, which has drawbacks such as complexity of verification method and high cost. Also, most of the schemes do not provide the sensing data required by the ADAS directly from the simulator, which limits verification reliability. In this paper, we present an interactive ADAS development and verification framework using a 3D vehicle simulator that overcomes the problems of existing methods. ADAS with image recognition based artificial intelligence was implemented as a virtual sensor in a 3D car simulator, and autonomous driving verification was performed in real scenarios.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.405-408
• /
• 2016

Games like Go, Chess, Janggi have helped to brain development of the people. These games are developed by computer program. And many algorithms have been developed to allow myself to play. The person winning chess program was developed in the 1990s. But game of go is too large number of cases. So it was considered impossible to win professional go player. However, with the use of MCTS(Monte Carlo Tree Search) and CNN(Convolutional Neural Network), the performance of the go algorithm is greatly improved. In this paper, using CNN and MCTS were proceeding development of go algorithm. Using the manual of go learning CNN look for the best position, MCTS calculates the win probability in the game to proceed with simulation. In addition, extract pattern information of go using existing manual of go, plans to improve speed and performance by using it. This method is showed a better performance than general go algorithm. Also if it is receiving sufficient computing power, it seems to be even more improved performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.331-337
• /
• 2014

Paradigm shift to cloud computing has increased the importance of security. Even though public cloud computing providers such as Amazon, already provides security related service like firewall and identity management services, it is not suitable to protect data in cloud environments. Because in public cloud computing environments do not allow to use client's own security solution nor equipments. In this environments, user are supposed to do something to enhance security by their hands, so the needs of visualized security management arises. To implement visualized security management, developing near realtime data handling & packet classification mechanisms are crucial. The key technical challenges in packet classification is how to classify packet in the manner of unsupervised way without human interactions. To achieve the goal, this paper presents automated packet classification mechanism based on naive-bayesian and packet Chunking techniques, which can identify signature and does machine learning by itself without human intervention.

• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.883-892
• /
• 2019

This study is the method which is adapted to control ankle joint movement for resolving the problem of gait imbalance in intervals where gait environments are changed and slope walking, as applying terrain-adaptive technique to intelligent above-knee prosthesis. In this development of above-knee prosthesis, to classify the gait modes is essential. For distinguishing the stance phases and the swing phase depending on roads, a machine learning which combines decision tree and random forest from knee angle data and inertial sensor data, is proposed and adapted. By using this method, the ankle movement state of the prosthesis is controlled. This study verifies whether the problem is resolved through butterfly diagram.

• The Journal of Society for e-Business Studies
• /
• v.24 no.3
• /
• pp.99-110
• /
• 2019

As the 4th industrial revolution progressing, manufacturers are trying to apply intelligent information technologies such as IoT(internet of things) and machine learning. In the semiconductor/LCD/tire manufacturing process, schedule plan that minimizes setup change and due date violation is very important in order to ensure efficient production. Therefore, in this paper, we suggest the deep learning based scheduling generation model minimizes setup change and due date violation in parallel machines. The proposed model learns patterns of minimizing setup change and due date violation depending on considered order using the amount of historical data. Therefore, the experiment results using three dataset depending on levels of the order list, the proposed model outperforms compared to priority rules.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.2
• /
• pp.67-78
• /
• 2019

Accurate electric load forecasting is very important in the efficient operation of the smart grid. Recently, due to the development of IT technology, many works for constructing accurate forecasting models have been developed based on big data processing using artificial intelligence techniques. These forecasting models usually utilize external factors such as temperature, humidity and historical electric load as independent variables. However, due to diverse internal and external factors, historical electrical load contains many missing data, which makes it very difficult to construct an accurate forecasting model. To solve this problem, in this paper, we propose a random forest-based missing data recovery scheme and construct an electric load forecasting model based on multilayer perceptron using the estimated values of missing data and external factors. We demonstrate the performance of our proposed scheme via various experiments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.79-82
• /
• 2019

This study aims to design and implement automated SEO tools that has applied the artificial intelligence techniques for search engine optimization (SEO; Search Engine Optimization). Traditional Search Engine Optimization (SEO) on-page optimization show limitations that rely only on knowledge of webpage administrators. Thereby, this paper proposes the metadata generation system. It introduces three approaches for recommending metadata; i) Downloading the metadata which is the top of webpage ii) Generating terms which is high relevance by using bi-directional Long Short Term Memory (LSTM) based on attention; iii) Learning through the Generative Adversarial Network (GAN) to enhance overall performance. It is expected to be useful as an optimizing tool that can be evaluated and improve the online marketing processes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.4
• /
• pp.381-387
• /
• 2019

The limitations of applying a variety of artificial intelligence to the medical community are, first, subjective views, extensive interpreters and physical fatigue in interpreting the image of an interpreter's illness. And there are questions about how long it takes to collect annotated data sets for each illness and whether to get sufficient training data without compromising the performance of the developed deep learning algorithm. In this paper, when collecting basic images based on acne data sets, the selection criteria and collection procedures are described, and a model is proposed to classify data into small loss rates (5.46%) and high accuracy (96.26%) in the sequential structure. The performance of the proposed model is compared and verified through a comparative experiment with the model provided by Keras. Similar phenomena are expected to be applied to the field of medical and skin care by applying them to the acne classification model proposed in this paper in the future.

• Phonetics and Speech Sciences
• /
• v.13 no.3
• /
• pp.71-78
• /
• 2021

Most neural-network-based speech synthesis models utilize neural vocoders to convert mel-scaled spectrograms into high-quality, human-like voices. However, neural vocoders combined with mel-scaled spectrogram prediction models demand considerable computer memory and time during the training phase and are subject to slow inference speeds in an environment where GPU is not used. This problem does not arise in linear spectrogram prediction models, as they do not use neural vocoders, but these models suffer from low voice quality. As a solution, this paper proposes a Tacotron 2 and Transformer-based linear spectrogram prediction model that produces high-quality speech and does not use neural vocoders. Experiments suggest that this model can serve as the foundation of a high-quality text-to-speech model with fast inference speed.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.1
• /
• pp.175-182
• /
• 2021

The purpose of this paper is to develop a machine learning-based marine drone to prevent the farming from harmful birds such as ducks. Existing drones have been developed as marine drones to solve the problem of being lost if they collide with birds in the air or are in the sea. We designed a CNN-based learning algorithm to judge harmful birds that appear on the sea by maritime drones operating by autonomous driving. It is designed to transmit video to the control PC by connecting the Raspberry Pi to the camera for location recognition and tracking of harmful birds. After creating a map linked with the location GPS coordinates in advance at the mobile-based control center, the GPS location value for the location of the harmful bird is received and provided, so that a marine drone is dispatched to combat the harmful bird. A bird fighting drone system was designed and implemented.