• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.61-68
• /
• 2022

In this paper, we propose a system to predict the GPS trajectory of a pedestrian based on a deep learning model. Pedestrian trajectory prediction is a study that can prevent pedestrian danger and collision situations through notifications, and has an impact on business such as various marketing. In addition, it can be used not only for pedestrians but also for path prediction of unmanned transportation, which is receiving a lot of spotlight. Among various trajectory prediction methods, this paper is a study of trajectory prediction using GPS data. It is a deep learning model-based study that predicts the next route by learning the GPS trajectory of pedestrians, which is time series data. In this paper, we presented a data set construction method that allows the deep learning model to learn the GPS route of pedestrians, and proposes a trajectory prediction deep learning model that does not have large restrictions on the prediction range. The parameters suitable for the trajectory prediction deep learning model of this study are presented, and the model's test performance are presented.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.334-337
• /
• 2019

In this study, we built the data collection system to learn user's habit data by deep learning and to create an indoor environment according to the situation. The system consists of a data collection server and several sensor nodes, which creates the environment according to the data collected. We used Google Inception v3 network to analyze the photographs and hand-designed second DNN (Deep Neural Network) to infer behaviors. As a result of the DNN learning, we gained 98.4% of Testing Accuracy. Through this results, we were be able to prove that DNN is capable of extrapolating the situation.

• ETRI Journal
• /
• v.43 no.2
• /
• pp.299-312
• /
• 2021

It is necessary to achieve high performance in the task of zero anaphora resolution (ZAR) for completely understanding the texts in Korean, Japanese, Chinese, and various other languages. Deep-learning-based models are being employed for building ZAR systems, owing to the success of deep learning in the recent years. However, the objective of building a high-quality ZAR system is far from being achieved even using these models. To enhance the current ZAR techniques, we fine-tuned a pretrained bidirectional encoder representations from transformers (BERT). Notably, BERT is a general language representation model that enables systems to utilize deep bidirectional contextual information in a natural language text. It extensively exploits the attention mechanism based upon the sequence-transduction model Transformer. In our model, classification is simultaneously performed for all the words in the input word sequence to decide whether each word can be an antecedent. We seek end-to-end learning by disallowing any use of hand-crafted or dependency-parsing features. Experimental results show that compared with other models, our approach can significantly improve the performance of ZAR.

• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.295-301
• /
• 2021

Digital media technology is gradually developing with the development of convergence quaternary industrial technology and mobile devices. The combination of deep learning and augmented reality can provide more convenient and lively services through the interaction of 3D virtual images with the real world. We combine deep learning-based pose prediction with augmented reality technology. We predict the eight vertices of the bounding box of the object in the image. Using the predicted eight vertices(x,y), eight vertices(x,y,z) of 3D mesh, and the intrinsic parameter of the smartphone camera, we compute the external parameters of the camera through the PnP algorithm. We calculate the distance to the object and the degree of rotation of the object using the external parameter and apply to AR content. Our method provides services in a web environment, making it highly accessible to users and easy to maintain the system. As we provide augmented reality services using consumers' smartphone cameras, we can apply them to various business fields.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.305-318
• /
• 2022

Abusive behaviors have become a common issue in many online social media platforms. Profanity is common form of abusive behavior in online. Social media platforms operate the filtering system using popular profanity words lists, but this method has drawbacks that it can be bypassed using an altered form and it can detect normal sentences as profanity. Especially in Korean language, the syllable is composed of graphemes and words are composed of multiple syllables, it can be decomposed into graphemes without impairing the transmission of meaning, and the form of a profane word can be seen as a different meaning in a sentence. This work focuses on the problem of filtering system mis-detecting normal phrases with profane phrases. For that, we proposed the deep learning-based framework including grapheme and syllable separation-based word embedding and appropriate CNN structure. The proposed model was evaluated on the chatting contents from the one of the famous online games in South Korea and generated 90.4% accuracy.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.183-183
• /
• 2021

Deep learning methods and their application have become an essential part of prediction and modeling in water-related research areas, including hydrological processes, climate change, etc. It is known that application of deep learning leads to high availability of data sources in hydrology, which shows its usefulness in analysis of precipitation, runoff, groundwater level, evapotranspiration, and so on. However, there is still a limitation on microclimate analysis and prediction with deep learning methods because of deficiency of gauge-based data and shortcomings of existing technologies. In this study, a real-time rainfall prediction model was developed from a sky image data set with convolutional neural networks (CNNs). These daily image data were collected at Chung-Ang University and Korea University. For high accuracy of the proposed model, it considers data classification, image processing, ratio adjustment of no-rain data. Rainfall prediction data were compared with minutely rainfall data at rain gauge stations close to image sensors. It indicates that the proposed model could offer an interpolation of current rainfall observation system and have large potential to fill an observation gap. Information from small-scaled areas leads to advance in accurate weather forecasting and hydrological modeling at a micro scale.

• Journal of Internet Computing and Services
• /
• v.20 no.1
• /
• pp.25-37
• /
• 2019

Inspired by the rapid development of deep learning and online biometrics-based authentication, we propose a handwritten one-time password authentication system which employs deep learning-based handwriting recognition and writer verification techniques. We design a convolutional neural network to recognize handwritten digits and a Siamese network to compute the similarity between the input handwriting and the genuine user's handwriting. We propose the first application of the second edition of NIST Special Database 19 for a writer verification task. Our system achieves 98.58% accuracy in the handwriting recognition task, and about 93% accuracy in the writer verification task based on four input images. We believe the proposed handwriting-based biometric technique has potential for use in a variety of online authentication services under the FIDO framework.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.275-284
• /
• 2023

Land monitoring involves systematically understanding changes in land use, leveraging spatial information such as satellite imagery and aerial photographs. Recently, the integration of deep learning technologies, notably object detection and semantic segmentation, into land monitoring has spurred active research. This study developed a web service to facilitate such integrations, allowing users to analyze aerial and drone images using CNN models. The web service architecture comprises AI, WEB/WAS, and DB servers and employs three primary deep learning models: DeepLab V3, YOLO, and Rotated Mask R-CNN. Specifically, YOLO offers rapid detection capabilities, Rotated Mask R-CNN excels in detecting rotated objects, while DeepLab V3 provides pixel-wise image classification. The performance of these models fluctuates depending on the quantity and quality of the training data. Anticipated to be integrated into the LX Corporation's operational network and the Land-XI system, this service is expected to enhance the accuracy and efficiency of land monitoring.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.89-96
• /
• 2020

Deep learning using an artificial neural network has been recently researched and developed in various fields such as image recognition, big data and data analysis. However, federated learning has emerged to solve issues of data privacy invasion and problems that increase the cost and time required to learn. Federated learning presented learning techniques that would bring the benefits of distributed processing system while solving the problems of existing deep learning, but there were still problems with server-client system and motivations for providing learning data. So, we replaced the role of the server with a blockchain system in federated learning, and conducted research to solve the privacy and security problems that are associated with federated learning. In addition, we have implemented a blockchain-based system that motivates users by paying compensation for data provided by users, and requires less maintenance costs while maintaining the same accuracy as existing learning. In this paper, we present the experimental results to show the validity of the blockchain-based system, and compare the results of the existing federated learning with the blockchain-based federated learning. In addition, as a future study, we ended the thesis by presenting solutions to security problems and applicable business fields.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.5
• /
• pp.685-690
• /
• 2021

In this paper, we propose a deep learning-based transmit power control scheme to maximize the sum-rates while satisfying the minimum data-rate in downlink non-orthogonal multiple access (NOMA) systems. In downlink NOMA, we consider the co-channel interference that occurs from a base station other than the cell where the user is located, and the user feeds back the signal-to-interference plus noise power ratio (SINR) information instead of channel state information to reduce system feedback overhead. Therefore, the base station controls transmit power using only SINR information. The use of implicit SINR information has the advantage of decreasing the information dimension, but has disadvantage of reducing the data-rate. In this paper, we resolve this problem with deep learning-based training methods and show that the performance of training can be improved if the dimension of deep learning inputs is effectively reduced. Through simulation, we verify that the proposed deep learning-based power control scheme improves the sum-rate while satisfying the minimum data-rate.