• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.111-118
• /
• 2022

In recent years, the number of single-person elderly households has increased, but when an emergency situation occurs inside the house in the case of single-person households, it is difficult to inform the outside world. Various smart home solutions have been proposed to detect emergency situations in single-person households, but it is difficult to use video media such as home CCTV, which has problems in the privacy area. Furthermore, if only a single sensor is used to analyze the abnormal situation of the elderly in the house, accurate situational analysis is limited due to the constraint of data amount. In this paper, therefore, we propose an algorithm of abnormal situation detection fusion inside the house by fusing 2DLiDAR, dust, and voice sensors, which are closely related to everyday life while protecting privacy, based on their correlations. Moreover, this paper proves the algorithm's reliability through data collected in a real-world environment. Adnormal situations that are detectable and undetectable by the proposed algorithm are presented. This study focuses on the detection of adnormal situations in the house and will be helpful in the lives of single-household users.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.55-58
• /
• 2024

In this paper, we propose a design and implementation of big data-based fine dust anomaly detection machine learning system. The proposed is system that classifies the fine dust air quality index through meteorological information composed of fine dust and big data. This system classifies fine dust through the design of an anomaly detection algorithm according to the outliers for each air quality index classification categories based on machine learning. Depth data of the image collected from the camera collects images according to the level of fine dust, and then creates a fine dust visibility mask. And, with a learning-based fingerprinting technique through a mono depth estimation algorithm, the fine dust level is derived by inferring the visibility distance of fine dust collected from the monoscope camera. For experimentation and analysis of this method, after creating learning data by matching the fine dust level data and CCTV image data by region and time, a model is created and tested in a real environment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.964-966
• /
• 2020

전염성이 매우 강한 돼지 호흡기 질병을 빠른 시간 내에 정확하게 탐지하지 못한다면 해당 돈사는 물론 타지역으로 전파되어 심각한 경제적 손실이 발생한다. 본 논문은 이와 같은 돼지 호흡기 질병을 저가격의 임베디드 보드에서도 탐지가 가능한 시스템을 제안한다. 해당 시스템은 돈사에 설치한 소리센서로부터 돼지의 이상 소리를 자동으로 탐지한 후, 탐지한 소리 시그널을 스펙트로그램으로 변환한다. 마지막으로, 스펙트로그램은 딥러닝 알고리즘에 적용되어 돼지 호흡기 질병을 탐지 및 식별한다. 이 때, 일반 컴퓨터 환경에 비해 비용 부담이 적은 임베디드 환경에서 실행되기 위하여 경량 딥러닝 모델인 MnasNet 을 사용하였으며, 임베디드 보드인 NVIDIA TX-2 에서 해당 시스템의 호흡기 질병 식별 성능을 확인한 결과 높은 탐지 성능과 실시간 탐지가 가능함을 확인하였다.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.5
• /
• pp.883-890
• /
• 2010

Illegal waste dumping is one of the major problems that the government agency monitoring water quality has to face. One solution to this problem is to find an efficient way of managing and supervising the water quality under various kinds of conditions. In this article we establish WQMA (water quality monitoring algorithm) based on the time series intervention model. It turns out thatWQMA is quite successful in detecting illegal waste dumping.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.172-174
• /
• 2001

침입 탐지란 컴퓨터와 네트워크 지원에 대한 유해한 침입 행동을 식별하고 대응하는 과정이다. 점차적으로 시스템에 대한 침입 유형들이 복잡해지고 전문적으로 이루어지면서 빠르고 정확한 대응을 할 수 있는 시스템이 요구되고 있다. 이에 따라, 대용량의 데이터를 지능적으로 분석하여 의미있는 정보를 추출하는 데이터 마이닝 기법을 적용함으로써 지능적이고 자동화된 탐지를 수행할 수 있도록 한다. 본 논문에서는 학습 데이터를 각각 사례로 데이터베이스에 저장한 후, 실험 데이터가 입려되면 가장 가까운 거리에 있는 학습 데이터의 크래스로 분류하는 사례 기반 학습을 이용하여 빠르게 사용자의 이상 행위에 대해 판정한다. 그러나 많은 사례로 인해 기억 공간이 늘어날 경우 시스템의 성능이 저하되는 문제점을 고려하여, 빈발 에피소드 알고리즘을 수행하여 발견한 순차 패턴을 사례화하여 정상 행위 프로파이로 사용하는 순차패턴에 대한 사례 기반 학습을 제안한다. 이로써, 시스템 성능의 저하율을 낮추고 빠르며 정확하게 지능적인 침입 탐지를 수행할 수 있다.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.31-37
• /
• 2021

In this paper, we propose an outlier detection algorithm called C-SCGP to prevent the degradation of localization performance based on RSS (Received Signal Strength) and AOA (Angle of Arrival) in the presence of outliers in wireless sensor networks. Since the accuracy of target estimation can significantly deteriorate due to various cause of outliers such as malfunction of sensor, jamming, and severe noise, it is important to detect and filter out all outliers. The single cluster graph partitioning (SCGP) algorithm has been widely used to remove such outliers. The proposed continuous-SCGP (C-SCGP) algorithm overcomes the weakness of the SCGP that requires the threshold and computing probability of outliers, which are impratical in many applications. The results of numerical simulations show that the performance of C-SCGP without setting threshold and probability computation is the same performance of SCGP.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.2 s.302
• /
• pp.11-20
• /
• 2005

In previous video conference system, when the number of participants in video conference increases by n, the bandwidth and memory of n2 is required. And also, it brings about increase in traffic and problem of a say during a conference in aspect of transmission of voice data. In this paper, we propose an algorithm of remote video conference using silence detection algerian to resolve the questions such as buffering method of video data in server and heavy traffic detection algorithm to the increase in participants. Video data buffering algorithm is not a method of broadcasting to other client in the server, but this algorithm uses two other methods; the buffering method of receiving compressed video data from clients and the indexing method for acquiring the video data of other participants in clients according to clients' bandwidth and network transmission speed. We apply a voice transmission algerian and a channel management algorithm to the remote video conference system. The method used in the voice transmission algorithm is a silence detection algorithm which does not send silent participants' voice data to the server. The channel management algorithm is a method allocating a say to the participants who have priority. In consideration of average 20 frames and 30ms regardless of a number of participants, we can safely conclude that the transmission of video and voice data is stable.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10c
• /
• pp.619-621
• /
• 2002

네트워크 기반 컴퓨터 시스템은 현대사회에 있어서 매우 중요한 역할을 담당하고 있기 때문에 이들은 정보 범죄들로부터 안정적이면서 효율적인 환경을 제공하는 것은 매우 중요한 일이다. 현재의 침입탐지 시스템은 네트워크 상에서 지속적으로 처리되는 대량의 패킷에 대하여 탐지속도가 떨어지고, 새로운 침입유형에 대한 대응방법이나 인지능력에도 한계가 있기 때문이다. 따라서 다양한 트래픽 속에서 탐지율을 높이고 탐지속도를 개선하기 위한 방안이 필요하다. 본 논문에서는 침입탐지 능력을 개선하기 위해 먼저, 광범위한 침입항목들에 대한 탐지 적용기술을 학습하고, 데이터 마이닝 기법을 이용하여 침입패턴 인식능력 및 새로운 패턴을 생성하는 적용기술을 제안하고자 한다. 침입 패턴생성을 위해 각 네트워크에 돌아다니는 관련된 패킷 정보와 호스트 세션에 기록되어진 자료를 필터링하고, 각종 로그 화일을 추출하는 프로그램들을 활용하여 침입과 일반적인 행동들을 분류하여 규칙들을 생성하였다. 마이닝 기법으로는 학습된 항목들에 대한 연관 규칙을 찾기 위한 연역적 알고리즘을 이용하였다. 또한, 추출 분석된 자료는 리눅스기반의 환경 하에서 다양하게 모아진 네트워크 로그파일들을 본 논문에서 제안한 방법에 따라 적용한 결과이다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.153-162
• /
• 2009

This paper suggests the novel light-weight signal processing algorithm for wireless sensor network applications which needs low computing complexity and power consumption. Exponential average method (EA) is utilized by real time, to process the magnetometer signal which is analyzed to understand the own physical characteristic in time domain. EA provides the robustness about noise, magnetic drift by temperature and interference, furthermore, causes low memory consumption and computing complexity for embedded processor. Hence, optimal parameter of proposal algorithm is extracted by statistical analysis. Using general and precision magnetometer, detection probability over 90% is obtained which restricted by 5% false alarm rate in simulation and using own developed magnetometer H/W, detection probability over 60~70% is obtained under 1~5% false alarm rate in simulation and experiment.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.2
• /
• pp.321-330
• /
• 2019

Prevention of corporate confidentiality leakage by insiders in enterprises is an essential task for the survival of enterprises. In order to prevent information leakage by insiders, companies have adopted security solutions, but there is a limit to effectively detect abnormal behavior of insiders with access privileges. In this study, we use the Unsupervised Learning algorithm of the machine learning technique to effectively and efficiently cluster the normal and abnormal access logs of the worker's work screen in the manufacturing information system, which includes the company's product manufacturing history and quality information. We propose an optimal feature selection model for anomaly detection by studying clustering methods.