• Proceedings of the Korean Vacuum Society Conference
• /
• 2009.02a
• /
• pp.142.2-142.2
• /
• 2009

• Journal of the Optical Society of Korea
• /
• v.17 no.1
• /
• pp.109-109
• /
• 2013

• Journal of Biomedical Engineering Research
• /
• v.43 no.4
• /
• pp.259-270
• /
• 2022

Artificial intelligence (AI) has been studied in various fields of medical imaging. Currently, top-notch deep learning (DL) techniques have led to high diagnostic accuracy and fast computation. However, they are rarely used in real clinical practices because of a lack of reliability concerning their results. Most DL models can achieve high performance by extracting features from large volumes of data. However, increasing model complexity and nonlinearity turn such models into black boxes that are seldom accessible, interpretable, and transparent. As a result, scientific interest in the field of explainable artificial intelligence (XAI) is gradually emerging. This study aims to review diverse XAI approaches currently exploited in medical imaging. We identify the concepts of the methods, introduce studies applying them to imaging modalities such as computational tomography (CT), magnetic resonance imaging (MRI), and endoscopy, and lastly discuss limitations and challenges faced by XAI for future studies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1743-1758
• /
• 2023

Automatic modulation classification is a critical algorithm for non-cooperative communication systems. This paper addresses the challenging problem of closed-set and open-set signal modulation classification in complex channels. We propose a novel approach that incorporates a self-learning filter and center-loss in Deep Residual Shrinking Networks (DRSN) for closed-set modulation classification, and the Opendistance method for open-set modulation classification. Our approach achieves better performance than existing methods in both closed-set and open-set recognition. In closed-set recognition, the self-learning filter and center-loss combination improves recognition performance, with a maximum accuracy of over 92.18%. In open-set recognition, the use of a self-learning filter and center-loss provide an effective feature vector for open-set recognition, and the Opendistance method outperforms SoftMax and OpenMax in F1 scores and mean average accuracy under high openness. Overall, our proposed approach demonstrates promising results for automatic modulation classification, providing better performance in non-cooperative communication systems.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.153-154
• /
• 2007

In this paper, we propose context information communication system using RF module to prevent railway cross accident. Since the communication module transmits to the train with high bit rate, OFDM(Orthogonal frequency division multiplexing) modulation method that distributes high speed data and transmits multiple times is applied. And image information is transmitted to the train's transceiver device by using ISM band (2.4GHz frequency band) that is proper to mobile communication. By using this system, we can deal with urgent situations at the railway cross and prevent railway cross accidents in advance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.1077-1079
• /
• 2005

The development of marine life database is insufficient and information service through internet is short now. We collect and analysis data of marine life and develop the database and provide information about marine life through internet. Also internet shopping, news, leisure information are serviced.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.934-936
• /
• 2004

본문에서는 최근 들어 각광을 받고 있는 패턴인식 방법론인 Support Vector Machine을 이용하여 중국어 개체명을 식별하는 방법을 제안하고자 한다. SVM(support vector machine)은 입력 자질이 많을 경우에도 안정적인 성능을 나타내고 보편적으로 적용할 수 있는 모델을 개발할 수 있는 장점이 있다. 실험에서 어휘. 품사, 의미부류 등 많은 수의 자질을 이용하였다. 실험결과는 본문에서 제안한 방법이 튜닝을 거치지 않아도 좋은 성능을 나타낼 수 있고, 수행 속도도 만족스럽다는 것을 보여주었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.11a
• /
• pp.7-8
• /
• 2010

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.267-270
• /
• 2005

An RFID patch antenna for metallic object has been designed. The effects of variation of distance between the tag antenna and ground of the antenna have been studied. Various dielectric constants, thickness, permittivity, width of transmission line and length of transmission line have been used to design the better tag antenna for metallic object.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06a
• /
• pp.158-159
• /
• 2008