• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.1043-1044
• /
• 2024

교통사고분석 시스템(TAAS, 도로교통공단) 통계에 따르면 PM(Personal Mobility) 관련 교통사고는 2023년 2389건으로, 2019년 447건 대비 5배 이상 증가하였다. 증가하는 교통사고를 예방하기 위해 본 논문에서는 AI 기술을 이용한 스마트 전동 킥보드 안전 시스템을 제시한다. AI 딥러닝 기반 모델을 적용해 무면허, 헬멧 미착용, 2인 이상 탑승, 횡단보도 주행, 교통안전에 위배되는 무단 주차를 제한한다. 본 시스템을 통해 전동 킥보드 이용자들의 도로교통법 준수와 공공의 안전 강화를 기대한다.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.11-20
• /
• 2019

In this study, a novel virtual reality (VR) experience environment is proposed for enabling walking adaptation of visually impaired people. The core of proposed VR environment is based on immersive walking interactions and deep learning based braille blocks recognition. To provide a realistic walking experience from the perspective of visually impaired people, a tracker-based walking process is designed for determining the walking state by detecting marching in place, and a controller-based VR white cane is developed that serves as the walking assistance tool for visually impaired people. Additionally, a learning model is developed for conducting comprehensive decision-making by recognizing and responding to braille blocks situated on roads that are followed during the course of directions provided by the VR white cane. Based on the same, a VR application comprising an outdoor urban environment is designed for analyzing the VR walking environment experience. An experimental survey and performance analysis were also conducted for the participants. Obtained results corroborate that the proposed VR walking environment provides a presence of high-level walking experience from the perspective of visually impaired people. Furthermore, the results verify that the proposed learning algorithm and process can recognize braille blocks situated on sidewalks and roadways with high accuracy.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.33-43
• /
• 2024

This research assessed the applicability of the You Only Look Once (YOLO)v8 and DeepLabv3+ models for the effective detection of compost heaps, identified as a significant source of non-point source pollution. Utilizing high-resolution imagery acquired through Unmanned Aerial Vehicles(UAVs), the study conducted a comprehensive comparison and analysis of the quantitative and qualitative performances. In the quantitative evaluation, the YOLOv8 model demonstrated superior performance across various metrics, particularly in its ability to accurately distinguish the presence or absence of covers on compost heaps. These outcomes imply that the YOLOv8 model is highly effective in the precise detection and classification of compost heaps, thereby providing a novel approach for assessing the management grades of compost heaps and contributing to non-point source pollution management. This study suggests that utilizing UAVs and deep learning technologies for detecting and managing compost heaps can address the constraints linked to traditional field survey methods, thereby facilitating the establishment of accurate and effective non-point source pollution management strategies, and contributing to the safeguarding of aquatic environments.

• Journal of KIISE
• /
• v.45 no.2
• /
• pp.157-164
• /
• 2018

Due to the revolutionary advances in deep learning, performance of pattern recognition has increased significantly in many applications like speech recognition and image recognition, and some systems outperform human-level intelligence in specific domains. Unlike pattern recognition, in this paper, we focus on generating Korean sentences based on a few Korean sentences. We apply variational recurrent auto-encoder (VRAE) and modify the model considering some characteristics of Korean sentences. To reduce the number of words in the model, we apply a word spacing model. Also, there are many Korean sentences which have the same meaning but different word order, even without subjects or objects; therefore we change the unidirectional encoder of VRAE into a bidirectional encoder. In addition, we apply an interpolation method on the encoded vectors from the given sentences, so that we can generate new sentences which are similar to the given sentences. In experiments, we confirm that our proposed method generates better sentences which are semantically more similar to the given sentences.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1293-1304
• /
• 2022

The personalization recommendation system means analyzing each individual's interests or preferences and recommending information or products accordingly. These personalized recommendations can reduce the time consumers spend searching for information by accessing the products they need more quickly, and companies can increase corporate profits by recommending appropriate products that meet their needs. In this study, products are recommended to consumers using collaborative filtering, matrix factorization, and deep learning, which are representative personalization recommendation techniques. To this end, the data set after purchasing shopping mall products, which is raw data, is pre-processed in the form of transmitting the data set to the input of the recommended system, and the pre-processed data set is analyzed from various angles. In addition, each model performs verification and performance comparison on the recommended results, and explores the model with optimal performance, suggesting which model should be used when building the recommendation system at the mall.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1935-1941
• /
• 2021

In order to develop an algorithm using deep learning, which has been recently applied to various fields, it is necessary to have rich, high-quality learning data. In this paper, we propose an acquisition system for biological signals that simultaneously collects bio-signal data such as optical videos, thermal videos, and voices, which are mainly used in developing deep learning algorithms and useful in derivation of information, and transmit them to the server. To increase the portability of the collector, it was made based on Raspberry Pi, and the collected data is transmitted to the server through the wireless Internet. To enable simultaneous data collection from multiple collectors, an ID for login was assigned to each subject, and this was reflected in the database to facilitate data management. By presenting an example of biological data collection for fatigue measurement, we prove the application of the proposed acquisition system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.4
• /
• pp.25-34
• /
• 2024

This paper presents the development of a mobile application that detects and identifies canine skin diseases by training a deep learning-based U-Net model to infer the presence and location of skin lesions from images. U-Net, primarily used in medical imaging for image segmentation, is effective in distinguishing specific regions of an image in a polygonal form, making it suitable for identifying lesion areas in dogs. In this study, six major canine skin diseases were defined as classes, and the U-Net model was trained to differentiate among them. The model was then implemented in a mobile app, allowing users to perform lesion analysis and prediction through simple camera shots, with the results provided directly to the user. This enables pet owners to monitor the health of their pets and obtain information that aids in early diagnosis. By providing a quick and accurate diagnostic tool for pet health management through deep learning, this study emphasizes the significance of developing an easily accessible service for home use.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.12
• /
• pp.321-332
• /
• 2020

Decentralized approaches are extensively researched by academia and industry in order to cover up the flaws of existing systems in terms of data privacy. Blockchain and decentralized learning are prominent representatives of a deconcentrated approach. Blockchain is secure by design since the data record is irrevocable, tamper-resistant, consensus-based decision making, and inexpensive of overall transactions. On the other hand, decentralized learning empowers a number of devices collectively in improving a deep learning model without exposing the dataset publicly. To motivate participants to use their resources in building models, a decent and proportional incentive system is a necessity. A centralized incentive mechanism is likely inconvenient to be adopted in decentralized learning since it relies on the middleman that still suffers from bottleneck issues. Therefore, we design an incentive model for decentralized learning applications by leveraging the Ethereum smart contract. The simulation results satisfy the design goals. We also outline the concerns in implementing the presented scheme for sensitive data regarding privacy and data leakage.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.58-65
• /
• 2019

Automatic text summarization is a process of shortening a text document by either extraction or abstraction. The abstraction approach inspired by deep learning methods scaling to a large amount of document is applied in recent work. Abstractive text summarization involves utilizing pre-generated word embedding information. Low-frequent but salient words such as terminologies are seldom included to dictionaries, that are so called, out-of-vocabulary(OOV) problems. OOV deteriorates the performance of Encoder-Decoder model in neural network. In order to address OOV words in abstractive text summarization, we propose a copy mechanism to facilitate copying new words in the target document and generating summary sentences. Different from the previous studies, the proposed approach combines accurate pointing information and selective copy mechanism based on bidirectional RNN and bidirectional LSTM. In addition, neural network gate model to estimate the generation probability and the loss function to optimize the entire abstraction model has been applied. The dataset has been constructed from the collection of abstractions and titles of journal articles. Experimental results demonstrate that both ROUGE-1 (based on word recall) and ROUGE-L (employed longest common subsequence) of the proposed Encoding-Decoding model have been improved to 47.01 and 29.55, respectively.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.367-378
• /
• 2021

Field compost is a representative non-point pollution source for livestock. If the field compost flows into the water system due to rainfall, nutrients such as phosphorus and nitrogen contained in the field compost can adversely affect the water quality of the river. In this paper, we propose a method for detecting field compost using unmanned aerial vehicle images and deep learning-based semantic segmentation. Based on 39 ortho images acquired in the study area, about 30,000 data were obtained through data augmentation. Then, the accuracy was evaluated by applying the semantic segmentation algorithm developed based on U-net and the filtering technique of Open CV. As a result of the accuracy evaluation, the pixel accuracy was 99.97%, the precision was 83.80%, the recall rate was 60.95%, and the F1-Score was 70.57%. The low recall compared to precision is due to the underestimation of compost pixels when there is a small proportion of compost pixels at the edges of the image. After, It seems that accuracy can be improved by combining additional data sets with additional bands other than the RGB band.