• Journal of Advanced Navigation Technology
• /
• v.23 no.2
• /
• pp.186-193
• /
• 2019

This paper presents and implements a simple programmable PCM encoder structure uisng the commutation method. In the telemetry system, information is required to assign each data to the channel in order to generate a frame format the data acpuired from the sensor. In this case, when the number of state information is large or the data type is various, there is a necessity to input a large amount of information to each channel. However, the more the number of channels and data, the more probability the error will occur. Therefore, in this paper, the channel information is created using the program. And PCM encoder was implemented to store channel information in ROM. The proposed PCM encoder architecture reduces the likelihood of errors. And it can improve the development speed. The validity of proposed structure is proved by simulation.

• Journal of Korea Multimedia Society
• /
• v.22 no.1
• /
• pp.44-54
• /
• 2019

Recently, image-based object detection has made great progress with the introduction of Convolutional Neural Network (CNN). Many trials such as Region-based CNN, Fast R-CNN, and Faster R-CNN, have been proposed for achieving better performance in object detection. YOLO has showed the best performance under consideration of both accuracy and computational complexity. However, these data-driven detection methods including YOLO have the fundamental problem is that they can not guarantee the good performance without a large number of training database. In this paper, we propose a data sampling method using CycleGAN to solve this problem, which can convert styles while retaining the characteristics of a given input image. We will generate the insufficient data samples for training more robust object detection without efforts of collecting more database. We make extensive experimental results using the day-time and night-time road images and we validate the proposed method can improve the object detection accuracy of the night-time without training night-time object databases, because we converts the day-time training images into the synthesized night-time images and we train the detection model with the real day-time images and the synthesized night-time images.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.51.3-51.3
• /
• 2019

Solar magnetograms are important for studying solar activity and predicting space weather disturbances1. Farside magnetograms can be constructed from local helioseismology without any farside data2-4, but their quality is lower than that of typical frontside magnetograms. Here we generate farside solar magnetograms from STEREO/Extreme UltraViolet Imager (EUVI) $304-{\AA}$ images using a deep learning model based on conditional generative adversarial networks (cGANs). We train the model using pairs of Solar Dynamics Observatory (SDO)/Atmospheric Imaging Assembly (AIA) $304-{\AA}$ images and SDO/Helioseismic and Magnetic Imager (HMI) magnetograms taken from 2011 to 2017 except for September and October each year. We evaluate the model by comparing pairs of SDO/HMI magnetograms and cGAN-generated magnetograms in September and October. Our method successfully generates frontside solar magnetograms from SDO/AIA $304-{\AA}$ images and these are similar to those of the SDO/HMI, with Hale-patterned active regions being well replicated. Thus we can monitor the temporal evolution of magnetic fields from the farside to the frontside of the Sun using SDO/HMI and farside magnetograms generated by our model when farside extreme-ultraviolet data are available. This study presents an application of image-to-image translation based on cGANs to scientific data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1227-1236
• /
• 2021

Adversarial attack, one of the attacks on deep learning classification model, is attack that add indistinguishable perturbations to input data and cause deep learning classification model to misclassify the input data. There are various adversarial attack algorithms. Accordingly, many studies have been conducted to detect adversarial attack but few studies have been conducted to classify what adversarial attack algorithms to generate adversarial input. if adversarial attacks can be classified, more robust deep learning classification model can be established by analyzing differences between attacks. In this paper, we proposed a model that detects and classifies adversarial attacks by constructing a random forest classification model with input features extracted from a target deep learning model. In feature extraction, feature is extracted from a output value of hidden layer based on class predicted by the target deep learning model. Through Experiments the model proposed has shown 3.02% accuracy on clean data, 0.80% accuracy on adversarial data higher than the result of pre-existing studies and classify new adversarial attack that was not classified in pre-existing studies.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.869-876
• /
• 2021

In the field of music, various AI composition methods using machine learning have recently been attempted. However, most of this research has been centered on Western music, and little research has been done on Korean traditional music. Therefore, in this paper, we will create a data set of Korean traditional music, create a melody using three algorithms based on the data set, and compare the results. Three models were selected based on the similarity between language and music, LSTM, Music Transformer and Self Attention. Using each of the three models, a melody generator was modeled and trained to generate melodies. As a result of user evaluation, the Self Attention method showed higher preference than the other methods. Data set is very important in AI composition. For this, a Korean traditional music data set was created, and AI composition was attempted with various algorithms, and this is expected to be helpful in future research on AI composition for Korean traditional music.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.453-455
• /
• 2022

Metadata is data that explains attributes and features to the data as structured data. Among them, video metadata refers to data extracted from information constituting the video for accurate content-based search. Recently, as the number of users using video content increases, the number of OTT providers is also increasing, and the role of metadata is becoming more important for OTT providers to recommend a large amount of video content to individual users or to search appropriately. In this paper, a study was conducted on a method of automatically extracting metadata for mood attributes through sound effects of images. In order to classify the sound effect of the video and generate metadata about the attributes of the mood, I would like to propose a method of establishing a terminology dictionary for the mood and extracting information through supervised learning.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1147-1161
• /
• 2023

The Internet of Things (IoT) requires a new processing model that will allow scalability in cloud computing while reducing time delay caused by data transmission within a network. Such a model can be achieved by using resources that are closer to the user, i.e., by relying on edge computing (EC). The amount of IoT data also grows with an increase in the number of IoT devices. However, building such a flexible model within a heterogeneous environment is difficult in terms of resources. Moreover, the increasing demand for IoT services necessitates shortening time delay and response time by achieving effective load balancing. IoT devices are expected to generate huge amounts of data within a short amount of time. They will be dynamically deployed, and IoT services will be provided to EC devices or cloud servers to minimize resource costs while meeting the latency and quality of service (QoS) constraints of IoT applications when IoT devices are at the endpoint. EC is an emerging solution to the data processing problem in IoT. In this study, we improve the load balancing process and distribute resources fairly to tasks, which, in turn, will improve QoS in cloud and reduce processing time, and consequently, response time.

• Journal of Internet of Things and Convergence
• /
• v.9 no.3
• /
• pp.13-19
• /
• 2023

In this paper, we investigated the implementation of a hairstyle recommendation system based on big data and deepfake technology. The proposed hairstyle recommendation system recognizes the facial shapes based on the user's photo (image). Facial shapes are classified into oval, round, and square shapes, and hairstyles that suit each facial shape are synthesized using deepfake technology and provided as videos. Hairstyles are recommended based on big data by applying the latest trends and styles that suit the facial shape. With the image segmentation map and the Motion Supervised Co-Part Segmentation algorithm, it is possible to synthesize elements between images belonging to the same category (such as hair, face, etc.). Next, the synthesized image with the hairstyle and a pre-defined video are applied to the Motion Representations for Articulated Animation algorithm to generate a video animation. The proposed system is expected to be used in various aspects of the beauty industry, including virtual fitting and other related areas. In future research, we plan to study the development of a smart mirror that recommends hairstyles and incorporates features such as Internet of Things (IoT) functionality.

• Annual Conference of KIPS
• /
• 2021.05a
• /
• pp.411-414
• /
• 2021

One of the elements of technology that has become extremely critical within the field of education today is Deep learning. It has been especially used in the area of natural language processing, with some word-representation vectors playing a critical role. However, some of the low-resource languages, such as Swahili, which is spoken in East and Central Africa, do not fall into this category. Natural Language Processing is a field of artificial intelligence where systems and computational algorithms are built that can automatically understand, analyze, manipulate, and potentially generate human language. After coming to discover that some African languages fail to have a proper representation within language processing, even going so far as to describe them as lower resource languages because of inadequate data for NLP, we decided to study the Swahili language. As it stands currently, language modeling using neural networks requires adequate data to guarantee quality word representation, which is important for natural language processing (NLP) tasks. Most African languages have no data for such processing. The main aim of this project is to recognize and focus on the classification of words in English, Swahili, and Korean with a particular emphasis on the low-resource Swahili language. Finally, we are going to create our own dataset and reprocess the data using Python Script, formulate the syllabic alphabet, and finally develop an English, Swahili, and Korean word analogy dataset.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.115-127
• /
• 2023

Video stabilization is one of the camera technologies that the importance is gradually increasing as the personal media market has recently become huge. For deep learning-based video stabilization, existing methods collect pairs of video datas before and after stabilization, but it takes a lot of time and effort to create synchronized datas. Recently, to solve this problem, unsupervised learning method using only unstable video data has been proposed. In this paper, we propose a network structure that learns the stabilized trajectory only with the unstable video image without the pair of unstable and stable video pair using the Convolutional Auto Encoder structure, one of the unsupervised learning methods. Optical flow data is used as network input and output, and optical flow data was mapped into grid units to simplify the network and minimize noise. In addition, to generate a stabilized trajectory with an unsupervised learning method, we define the loss function that smoothing the input optical flow data. And through comparison of the results, we confirmed that the network is learned as intended by the loss function.