• Electronics and Telecommunications Trends
• /
• v.28 no.3
• /
• pp.57-66
• /
• 2013

무선랜이 폭발적으로 증가함에 따라, 기술 발전에 힘입은 네트워크 품질은 많이 향상되었지만, 보안 품질은 아직도 요원한 상황이다. 본고에서는 무선랜상에서 아이디 보안 취약성을 이용한 공격들과 이를 탐지하고 방어할 수 있는 디바이스 식별 기술에 대한 동향을 파악한다. 무선랜상에서 아이디 보안 취약성을 이용하는 MAC 속임 공격은 공격자의 존재를 속일 수 있을 뿐만 아니라, 네트워크 및 시스템 권한을 획득할 수 있기 때문에 네트워크 보안에 큰 위협이 되고 있다. 무선디바이스 식별 기술로서는 인증 방식, 프로토콜 분석 방식, 위치확인 방식, RF 지문 방식 등 많은 기법들이 있다. 본고에서는 이러한 기술들 중에서 현재 가장 활발하게 연구되고 있는 RF 지문 기술을 시스템 구조, 디바이스 식별 방법, 보안 취약성, 그리고 보안 응용 관점에서 자세히 분석한다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.151-154
• /
• 2002

본 논문에서는 음성 데이터에서 동일한 화자의 음성 구간을 찾아내는 화자 인덱싱(Speaker Indexing) 기술 중 사전 화자 모델링 과정을 통한 인덱싱 방법을 제안하고 실험하였다. 제안한 인덱싱 방법은 문장 독립(Text Independent) 화자 식별(Speaker Identification)에 사용할 수 있는 모음(Vowel)에 대해 특징 파라미터를 추출하고, 이를 바탕으로 화자별 모델을 구성하였다. 인덱싱은 음성 구간에서 모음의 위치를 검출하고, 구성한 화자 모델과의 거리 계산을 통하여 가장 가까운 모델을 식별된 결과로 한다. 그리고 식별된 결과는 화자 구간 변화와 음성 데이터의 특성을 바탕으로 필터링 과정을 거쳐 최종적인 인덱싱 결과를 얻는다. 화자 인덱싱 실험 대상으로 방송 뉴스를 녹음하여 10명의 화자 모델을 구성하였고, 인덱싱 실험을 수행한 결과 $91.8\%$의 화자 인덱싱 성능을 얻었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.408-410
• /
• 2022

최근 데이터 획득 위치에 가장 근접하고, 저 수준의 계산력을 제공하는 엣지 기기를 중심으로 직접 딥러닝 추론을 수행하고자 하는 요구가 증가하고 있다. 본 논문에서는 드론에서 촬영한 교통 영상 데이터를 기반으로, 다수의 차량 종류 및 보행자를 식별하는 모델을 Jetson Nano 에 탑재하여 기본 성능을 측정한다. 더불어, 자원제약형 기기 환경에서 TensorRT 와 Deepstream 을 활용하여 객체 식별 모델의 연산 경량화 및 추론 가속화 성능을 극대화하기 위한 구현 및 실험을 수행하여 Anchor-based 및 Anchor-free 객체 식별 모델의 정확도와 실시간 대응력을 평가하고 논의한다.

• Journal of Advanced Navigation Technology
• /
• v.25 no.5
• /
• pp.397-402
• /
• 2021

The real-name electric fishing gear system is one of the important policy capable to build 'abundant fishing ground' and to protect marine environment. And, fishing gear automatic-identification system is one of IoT services that can implement above-mentioned policy by using communication such as low power wide area (LPWA) and multi-sensing techniques. Fishing gear automatic -identification system can gather the location data and lost/hold data from electric buoy floated in sea and can provide them to fishermen and monitoring center in land. We have developed the communication modules and electric buoy consisted of fishing gear automatic-identification system. In this paper, we report the test results of communication distance between electric buoy and wireless node installed in fish boat and location error of electric buoy. It is confirmed that line of sight (LOS) distance between electric buoy and wireless node is obtained to be 62 km, which is two times of the desired value, and location error is obtained to be CEP 1 m, which is smaller than the desired value of CEP 5 m. Therefore, it is expected that service area and accuracy of the developed fishing gear automatic-identification system is more extended.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.333-340
• /
• 2022

The COVID-19 has made everyone anxious and people need to keep their distance. It is necessary to conduct collective assessment and screening of college students' mental health in the opening season of every year. This study uses and trains a multi-layer perceptron neural network model for deep learning to identify facial emotions. After the training, real pictures and videos were input for face detection. After detecting the positions of faces in the samples, emotions were classified, and the predicted emotional results of the samples were sent back and displayed on the pictures. The results show that the accuracy is 93.2% in the test set and 95.57% in practice. The recognition rate of Anger is 95%, Disgust is 97%, Happiness is 96%, Fear is 96%, Sadness is 97%, Surprise is 95%, Neutral is 93%, such efficient emotion recognition can provide objective data support for capturing negative. Deep learning emotion recognition system can cooperate with traditional psychological activities to provide more dimensions of psychological indicators for health.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.3
• /
• pp.331-338
• /
• 2016

In this paper, we propose a GRNN(: Generalized Regression Neural Network) algorithms for new eyes and face recognition identification system to solve the points that need corrective action in accordance with the existing problems of facial movements gaze upon it difficult to identify the user and. Using a Kalman filter structural information elements of a face feature to determine the authenticity of the face was estimated future location using the location information of the current head and the treatment time is relatively fast horizontal and vertical elements of the face using a histogram analysis the detected. And the light obtained by configuring the infrared illuminator pupil effects in real-time detection of the pupil, the pupil tracking was - to extract the text print vector.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.10
• /
• pp.2316-2322
• /
• 2013

Due to the development of ICT, with using hardwares such as WiFi, 3G and GPS and so on, smartphone could have provided a lot of applications with novel functions rapidly. Through such applications, lots of personal information such as personal location, personal images, and list of phone calls is created, saved and widely used. Because there is lots of leakage of the stored personal information due to loss of phone and application, privacy violation have been important issue nowadays. Smartphone with GPS and Internet provides location information. To protect the information, the technologies that only the authorized user can access it while inquiring the location information have been proposed. In this paper, to minimize the identification information for location information subject and information user and anonymize the identifiable information such as phone number, we proposed a model that can reduce the leakage of information and avoid the wrong usage of the stored information in the server. This technique will be used for protecting privacy when developing the application that provides routing service through location history information.

• Journal of Intelligence and Information Systems
• /
• v.9 no.3
• /
• pp.65-79
• /
• 2003

In general, the extraction and recognition of identifier is very hard work, because the scale or location of identifier is not fixed-form. And, because the provided image is contained by camera, it has some noises. In this paper, we propose methods for automatic detecting edge using canny edge mask. After detecting edges, we extract regions of identifier by detected edge information's. In regions of identifier, we extract each identifier using contour tracking algorithm. The self-generation supervised learning algorithm is proposed for recognizing them, which has the algorithm of combining the enhanced ART1 and the supervised teaming method. The proposed method has applied to the container images. The extraction rate of identifier obtained by using contour tracking algorithm showed better results than that from the histogram method. Furthermore, the recognition rate of the self-generation supervised teaming method based on enhanced ART1 was improved much more than that of the self-generation supervised learning method based conventional ART1.

• Journal of KIISE:Information Networking
• /
• v.37 no.5
• /
• pp.396-402
• /
• 2010

The tracking of current location of residents is an essential requirement for context-aware service of smart houses. This paper presents a wireless sensor network system which could detect location transition such as entrance and exit to a room and also identify the user who passed the room, without duty of wearing any sort of tag. We designed new sensor node to solve the problem of short operation lifetime of previous work[1] which has two pyroelectric infrared (PIR) sensors and an ultrasonic sensor, as well as a 2.4 GHz radio frequency wireless transceiver. The proposed user identification method is to discriminate a person based on his/her height by using an ultrasonic sensor. The detection idea of entering/exiting behavior is based on order of triggering of two PIR sensors. The topology of the developed wireless sensor network system is simple star structure in which each sensor node is connected to one sink node directly. We evaluated the proposed sensing system with a set of experiments for three subjects in a model house. The experimental result shows that the averaged recognition rate of user identification is 81.3% for three persons. and perfect entering/exiting behavior detection performance.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.12
• /
• pp.937-946
• /
• 2017

Recently, urban structures including buildings are becoming increasingly large and super high-rise in order to make human life more convenient. As the number of super high-rise buildings increases, however, the risk of fire and other disasters is increasing. Especially, it is expected that deaths and injuries will be tremendous than imagined if the evacuation guidance is not provided promptly and precisely for the occupants in case of a fire in super high-rise buildings. Therefore, rapid rescue should be done for those who are in need of residence or rescue in the building. To do this, identification of the size and location of people inside the building should be preceded. To do this, first, we conduct a preliminary study on existing location tracking technologies to identify occupants. Based on this, in this paper, we will study how to improve evacuation time in case of a fire in super high-rise buildings. For this purpose, we utilize the location tracking technology to identify the number of people in real time and improve the density when a disaster such as a fire occurs.