• 인터넷정보학회논문지
• /
• 제24권4호
• /
• pp.57-64
• /
• 2023

현재 진행되는 고령화 및 인구절벽으로 대표되는 인구구조적 문제는 한국군 경계임무에 심각한 도전이 되고 있다. 본 연구의 목적은 AI모델을 적용해 군 경계체계를 지능화하는 것이다. 본 연구를 통해 제4차 산업혁명과 그 핵심이 되는 인공지능 알고리즘의 의의가 경계근무 상황실 내에서의 단순작업을 기계화하여 작업효율을 극대화하는 것임을 실증한다. 하나의 완성된 시스템으로서 군경계체계를 개발하기 위해, 지능화·자동화된 군(軍) 경계체계라는 목표로부터 필요한 인공지능 기술인 다중 객체 추적(multi-object tracking, MOT) 기술을 선택한다. 또한 체계 사용자의 접근성 및 체계 이용의 효율성을 담보하기 위해서는 데이터 시각화(data visualization)와 사용자 인터페이스(user interface)를 꼽았다. 이 추가 요소를 결합하여 하나의 유기적인 소프트웨어 애플리케이션을 구성한다. CCTV 영상 데이터 수집한 장소는 00부대 제1정문 및 제2정문에 설치된 CCTV 카메라이며, 지통실의 협조 아래 영상 수집을 진행하였다. 실험결과를 통해 경계체계를 지능화·자동화시켜 더 많은 정보를 경계체계 운용인원에게 전달할 수 있음을 보였다. 그러 나 여전히 개발된 소프트웨어 경계체계 역시 한계점이 존재한다. 이를 설명하여 군 경계체계 개발의 향후 방향성을 제시한다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권4호
• /
• pp.189-198
• /
• 2023

길거리에서 묻지마 범죄가 자주 발생함에 따라 CCTV의 보급이 증가하고 있다. 그러나 수동적으로 작동되는 CCTV의 단점 때문에 지능형 CCTV의 필요성이 주목 받고 있다. 이러한 지능형 CCTV의 무거운 시스템 때문에, 높은 성능의 기기들이 필요해 일반 CCTV를 대체하는데 비용적 측면에서 부담이 발생한다. 이 문제를 해결하기 위해 낮은 품질의 영상도 인식하며 높지 않은 성능의 기기에서도 시스템이 구동되는 지능형 CCTV 시스템이 필요하다. 따라서 본 논문은 AWS 기반 플랫폼을 활용하여 시스템을 경량화하고 영상을 텍스트화하여 실시간으로 위협을 감지할 수 있는 Saying CCTV 시스템을 제안한다. 이는 YOLO v4와 OpenPose를 사용해 추출한 데이터를 바탕으로 위험 객체와 위협 행동 그리고 위협 상황을 판단하며, 위험도를 머신러닝으로 계산하도록 구현하였다. 이를 통해, 언제 어디서나 네트워크만 연결되면 시스템을 동작시킬 수 있으며, 영상 촬영과 이미지 업로드가 최소한의 성능의 기기에서도 시스템 사용이 가능하다. 나아가 영상을 분석하여 텍스트로 저장되는 데이터들로 하여금 범죄의 유의미한 통계를 자동화하여 신속한 범죄 예방이 가능하다.

• 대한기계학회논문집A
• /
• 제32권4호
• /
• pp.340-346
• /
• 2008

An unmanned surveillance robot consists of a machine gun, a laser receiver, a thermal imager, a color CCD camera, and a laser illuminator. It has two axis control systems for elevation and azimuth. Because the current robot system is mounded at a fixed post to take care of surveillance tasks, it is necessary to modify such a surveillance robot to be installed on an UGV (Unmanned Ground Vehicle) system in order to watch blind areas. Thus, it is required to have a stabilization system to compensate the disturbance from the UGV. In this paper, a simulation based design scheme has been adopted to develop a mobile surveillance robot. The 3D CAD geometry model has first been produced by using Pro-Engineer. The required pan and tilt motor capacities have been analyzed using ADAMS inverse dynamics analysis. A target tracking and stabilization control algorithm of the mobile surveillance robot has been developed in order to compensate the motion of the vehicle which will experience the rough terrain. To test the performance of the stabilization control system of the robot, ADAMS/simulink co-simulations has been carried out.

• 한국주거학회논문집
• /
• 제18권3호
• /
• pp.115-123
• /
• 2007

The purpose of this study was to examine how housing facilities have been progressed, how housing life has been technicalized and which factors contributed to the modernization of Korean housing in the economic development era. Review of advertising material for apartment sales in the newspaper from 1970s' to the 1990s' are mainly utilized to follow up the changes of kitchen equipment and furnitures, bathroom equipments, heating and cooking facilities and their fuel system, information and telecommunication system as well as security and intelligent system. However, high technology in apartment was a symbol of modem housing in each time. The improvement of housing facilities brought about the improvement of efficiency in household works. In other words, housing space plays as "Living Machine". And appearance of new technology systems leaded to a pluralistic activities in the home. As well as improvement on the material environments accelerated the individualization phenomena in housing space.

• Journal of the Optical Society of Korea
• /
• 제17권2호
• /
• pp.188-199
• /
• 2013

This paper presents a novel algorithm for nighttime detection of the lane markers painted on a road at night. First of all, the proposed algorithm uses neighborhood average filtering, 8-directional Sobel operator and thresholding segmentation based on OTSU's to handle raw lane images taken from a digital CCD camera. Secondly, combining intensity map and gradient map, we analyze the distribution features of pixels on boundaries of lanes in the nighttime and construct 4 feature sets for these points, which are helpful to supply with sufficient data related to lane boundaries to detect lane markers much more robustly. Then, the searching method in multiple directions- horizontal, vertical and diagonal directions, is conducted to eliminate the noise points on lane boundaries. Adapted Hough transformation is utilized to obtain the feature parameters related to the lane edge. The proposed algorithm can not only significantly improve detection performance for the lane marker, but it requires less computational power. Finally, the algorithm is proved to be reliable and robust in lane detection in a nighttime scenario.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2006년도 학술대회 1부
• /
• pp.1387-1392
• /
• 2006

본 논문에서는 SVM (Support Vector Machine)을 기반으로 하여 인체의 뇌 하부구조인 해마에 대한 지능적 형상분석 방법을 제공한다. 일반적으로 의료 영상으로부터 해마의 형상 분석을 하기 위해서는 충분한 임상 데이터를 필요로 한다. 하지만 현실적으로 많은 양의 표본들을 얻는 것이 쉽지 않기 때문에 전문가의 지식을 기반으로 한 작업이 수반되어야 한다. 결국 이러한 요소들이 분석 작업을 어렵게 한다. 의학 기술이 복잡해 지면서 최근의 형상 분석 연구는 점차 통계적 모델을 기반으로 진행되고 있다. 본 연구에서는 해마로부터 고해상도의 매개변수형 모델을 만들어 형상 표현으로 이용하고, 집단간 분류 작업에 SVM 알고리즘을 적용하는 지능적 분석 방법을 구현한다. 우선 메쉬 데이터로부터 물리변형모델 기반의 매개변수 모델을 구축하고, PDM (point distribution model) 방법을 적용하여 두 집단을 대표하는 평균 모델을 생성한다. 마지막으로 SVM 기반의 이진 분류기를 구축하여 집단간 분류 작업을 수행한다. 구현한 모델링 방법과 분류기의 성능을 평가하기 위하여 본 연구에서는 네 가지 커널 함수 (linear, radial basis function, polynomial, sigmoid)들을 적용한다. 본 논문에서 제시한 매개변수형 모델은 다양한 형태의 의료 데이터로부터 보편적인 3차원 모델을 생성하고, 또한 모델의 전역적, 국부적인 특징들을 복합적으로 표현할 수 있기 때문에 통계적 형상분석에 적합하다. 그리고 SVM 기반의 분류기는 적은 수의 학습 데이터로부터 정상인 해마 집단과 간질 환자 집단간의 정확한 분류를 가능하게 한다.

• ETRI Journal
• /
• 제42권1호
• /
• pp.78-89
• /
• 2020

Human activity recognition (HAR) has become effective as a computer vision tool for video surveillance systems. In this paper, a novel biometric system that can detect human activities in 3D space is proposed. In order to implement HAR, joint angles obtained using an RGB-depth sensor are used as features. Because HAR is operated in the time domain, angle information is stored using the sliding kernel method. Haar-wavelet transform (HWT) is applied to preserve the information of the features before reducing the data dimension. Dimension reduction using an averaging algorithm is also applied to decrease the computational cost, which provides faster performance while maintaining high accuracy. Before the classification, a proposed thresholding method with inverse HWT is conducted to extract the final feature set. Finally, the K-nearest neighbor (k-NN) algorithm is used to recognize the activity with respect to the given data. The method compares favorably with the results using other machine learning algorithms.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.552-557
• /
• 2004

This paper presents a disturbance observer based on an $H_{\infty}$ controller synthesis for the trajectory control of a hydraulic excavator. Compared to conventional robot manipulators driven by electrical motors, the hydraulic excavator has more nonlinear and coupled dynamics. In particular, the interactions between an excavation tool and the materials being excavated are unstructured and complex. In addition, its operating modes depend on working conditions, which make it difficult to not only derive the exact mathematical model but also design a controller systematically. In this study, the approximated linear model obtained through off-line system identification is used as nominal plant model for a disturbance observer. A disturbance observer based tracking controller which considers the effect of disturbance and model uncertainty is synthesized in $H_{\infty}$ frameworks. Simulation results are used to demonstrate the applicability of the proposed control scheme.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.907-923
• /
• 2020

For the severe haze situation in the Beijing-Tianjin-Hebei region, conventional fine particulate matter (PM2.5) concentration prediction methods based on pollutant data face problems such as incomplete data, which may lead to poor prediction performance. Therefore, this paper proposes a method of predicting the PM2.5 concentration based on image analysis technology that combines image data, which can reflect the original weather conditions, with currently popular machine learning methods. First, based on local parameter estimation, autoregressive (AR) model analysis and local estimation of the increase in image blur, we extract features from the weather images using an approach inspired by free energy and a no-reference robust metric model. Next, we compare the coefficient energy and contrast difference of each pixel in the AR model and then use the percentages to calculate the image sharpness to derive the overall mass fraction. Furthermore, the results are compared. The relationship between residual value and PM2.5 concentration is fitted by generalized Gauss distribution (GGD) model. Finally, nonlinear mapping is performed via the wavelet neural network (WNN) method to obtain the PM2.5 concentration. Experimental results obtained on real data show that the proposed method offers an improved prediction accuracy and lower root mean square error (RMSE).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권10호
• /
• pp.5132-5148
• /
• 2017

Cyber attacks are evolving commensurate with recent developments in information security technology. Intrusion detection systems collect various types of data from computers and networks to detect security threats and analyze the attack information. The large amount of data examined make the large number of computations and low detection rates problematic. Feature selection is expected to improve the classification performance and provide faster and more cost-effective results. Despite the various feature selection studies conducted for intrusion detection systems, it is difficult to automate feature selection because it is based on the knowledge of security experts. This paper proposes a feature selection technique to overcome the performance problems of intrusion detection systems. Focusing on feature selection, the first phase of the proposed system aims at constructing a feature subset using a sequential forward floating search (SFFS) to downsize the dimension of the variables. The second phase constructs a classification model with the selected feature subset using a random forest classifier (RFC) and evaluates the classification accuracy. Experiments were conducted with the NSL-KDD dataset using SFFS-RF, and the results indicated that feature selection techniques are a necessary preprocessing step to improve the overall system performance in systems that handle large datasets. They also verified that SFFS-RF could be used for data classification. In conclusion, SFFS-RF could be the key to improving the classification model performance in machine learning.