• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.253-261
• /
• 2024

The role of the library is as a public institution that provides academic information to a variety of people, including students, the general public, and researchers. These days, as the importance of lifelong education is emphasized, libraries are evolving beyond simply storing and lending materials to complex cultural spaces that share knowledge and information through various educational programs and cultural events. One of the problems library user's faces is locating books to borrow. This problem occurs because of errors in the location of borrowed books due to delays in updating library databases related to borrowed books, incorrect labeling, and books temporarily located in different locations. The biggest problem is that it takes a long time for users to search for the books they want to borrow. In this paper, we propose a system that visually displays the location of books in real time using an AI vision sensor and LED. The AI vision sensor-based book location guidance system generates a QR code containing the call number of the borrowed book. When the AI vision sensor recognizes this QR code, the exact location of the book is visually displayed through LED to guide users to find it easily. We believe that the AI vision sensor-based book location guidance system dramatically improves book search and management efficiency, and this technology is expected to have great potential for use not only in libraries and bookstores but also in a variety of other fields.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.9
• /
• pp.445-456
• /
• 2017

In this paper, we propose a method to detect spam tweets containing unhealthy information by using an n-gram dictionary under limited labeling. Spam tweets that contain unhealthy information have a tendency to use similar words and sentences. Based on this characteristic, we show that spam tweets can be effectively detected by applying a Naive Bayesian classifier using n-gram dictionaries which are constructed from spam tweets and normal tweets. On the other hand, constructing an initial training set requires very high cost because a large amount of data flows in real time in a twitter. Therefore, there is a need for a spam detection method that can be applied in an environment where the initial training set is very small or non exist. To solve the problem, we propose a method to generate pseudo-labels by utilizing twitter's retweet function and use them for the configuration of the initial training set and the n-gram dictionary update. The results from various experiments using 1.3 million korean tweets collected from December 1, 2016 to December 7, 2016 prove that the proposed method has superior performance than the compared spam detection methods.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.3
• /
• pp.23-29
• /
• 2019

Conventional crack detection methods have a problem of consuming a lot of labor, time and cost. To solve these problems, an automatic detection system is needed to detect cracks in images obtained by using vehicles or UAVs(unmanned aerial vehicles). In this paper, we have studied road crack detection with unmanned aerial photographs. Aerial images are generated through preprocessing and labeling to generate morphological information data sets of cracks. The generated data set was applied to the mask R-CNN model to obtain a new model in which various crack information was learned. Experimental results show that the cracks in the proposed aerial image were detected with an accuracy of 73.5% and some of them were predicted in a certain type of crack region.

• Convergence Security Journal
• /
• v.23 no.2
• /
• pp.55-66
• /
• 2023

Recently, there is an increasing movement to increase the value of AI learning data and to secure high-quality data based on previous research on AI learning data in all areas of society. Therefore, quality management is very important in construction projects to secure high-quality data. In this paper, quality management to secure high-quality data when building AI learning data and improvement plans for each construction process are presented. In particular, more than 80% of the data quality of unstructured data built for AI learning is determined during the construction process. In this paper, we performed quality inspection of image/video data. In addition, we identified inspection procedures and problem elements that occurred in the construction phases of acquisition, data cleaning, labeling, and models, and suggested ways to secure high-quality data by solving them. Through this, it is expected that it will be an alternative to overcome the quality deviation of data for research groups and operators participating in the construction of AI learning data.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.159-162
• /
• 2017

Long Short-Term Memory Recurrent Neural Network(LSTM RNN)는 순차 데이터 모델링에 적합한 딥러닝 모델이다. Bidirectional LSTM RNN(BiLSTM RNN)은 RNN의 그래디언트 소멸 문제(vanishing gradient problem)를 해결한 LSTM RNN을 입력 데이터의 양 방향에 적용시킨 것으로 입력 열의 모든 정보를 볼 수 있는 장점이 있어 자연어처리를 비롯한 다양한 분야에서 많이 사용되고 있다. Highway Network는 비선형 변환을 거치지 않은 입력 정보를 히든레이어에서 직접 사용할 수 있게 LSTM 유닛에 게이트를 추가한 딥러닝 모델이다. 본 논문에서는 Highway Network를 한국어 의미역 결정에 적용하여 기존 연구 보다 더 높은 성능을 얻을 수 있음을 보인다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.3
• /
• pp.69-78
• /
• 1996

This paper presetns an iterative relaxation method for stereo matching using matching probability and compatibility coefficients between disparities. Stereo matching can be considered as the labeling problem of assigning unique matches to feature points of image an relaxation labelin gis an iterative procedure which reduces local ambiguities and achieves global consistency. the relation between disparities is determined from highly reliable matches in initial matching and quantitatively expressed in temrs of compatibility coefficient. The matching results of neighbor pixels support center pixel through compatibility coefficients and update its matching probability. The proposed adaptive method reduces the degradtons on the discontinuities of disparity areas and obtains fast convergence.

• 한국경영정보학회:학술대회논문집
• /
• 2007.06a
• /
• pp.951-958
• /
• 2007

Radio Frequency Identification (RFID) is a technology for automated identification of objects and people. RFID may be viewed as a means of explicitly labeling objects to facilitate their "perception" by computing devices. RFlD systems have been gaining more popularity in areas especially in supply chain management and automated identification systems. However, there are many existing and potential problems in the RFlD systems which could threat the technology s future. To successfully adopt RFID technology in various applications. we need to develop the solutions to protect the RFID system s data information. This study investigates important issues related to privacy and security of RF1D based on the recent literature and suggests solutions to cope with the problem.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.159-162
• /
• 2017

Long Short-Term Memory Recurrent Neural Network(LSTM RNN)는 순차 데이터 모델링에 적합한 딥러닝 모델이다. Bidirectional LSTM RNN(BiLSTM RNN)은 RNN의 그래디언트 소멸 문제(vanishing gradient problem)를 해결한 LSTM RNN을 입력 데이터의 양 방향에 적용시킨 것으로 입력 열의 모든 정보를 볼 수 있는 장점이 있어 자연어처리를 비롯한 다양한 분야에서 많이 사용되고 있다. Highway Network는 비선형 변환을 거치지 않은 입력 정보를 히든레이어에서 직접 사용할 수 있게 LSTM 유닛에 게이트를 추가한 딥러닝 모델이다. 본 논문에서는 Highway Network를 한국어 의미역 결정에 적용하여 기존 연구 보다 더 높은 성능을 얻을 수 있음을 보인다.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.55-60
• /
• 2018

기계학습 기반인 관계추출 모델을 설계할 때 다량의 학습데이터를 빠르게 얻기 위해 원격지도학습 방식으로 데이터를 수집한다. 이러한 데이터는 잘못 분류되어 학습데이터로 사용되기 때문에 모델의 성능에 부정적인 영향을 끼칠 수 있다. 본 논문에서는 이러한 문제를 강화학습 접근법을 사용해 해결하고자 한다. 본 논문에서 제안하는 모델은 오 분류된 데이터로부터 좋은 품질의 데이터를 찾는 문장선택기와 선택된 문장들을 가지고 학습이 되어 관계를 추출하는 관계추출기로 구성된다. 문장선택기는 지도학습데이터 없이 관계추출기로부터 피드백을 받아 학습이 진행된다. 이러한 방식은 기존의 관계추출 모델보다 좋은 성능을 보여주었고 결과적으로 원격지도학습데이터의 단점을 해결한 방법임을 보였다.

• Journal of the Semiconductor & Display Technology
• /
• v.7 no.3
• /
• pp.59-63
• /
• 2008

Geo-coding refers to the process of associating data with location information, and the system deals with geographic identifiers expressed as latitude and longitude or street addresses. Although many services have been launched, there still remains a problem for users to create geo-coded photo with manually labeling GPS(Global Positioning System) coordinate or synchronizing with separate devices. In this paper, we design and implement a geo-coding system which utilizes the time and location information embedded in digital photographs in order to automatically categorize a personal photo collection. An included GPS receiver labels a photograph with its corresponding GPS coordinates, and the position of the camera is automatically recorded into the photo image header at the moment of capture. The place and time where the photo was taken allows us to provide context metadata on the management and retrieval of information.