• International conference on construction engineering and project management
• /
• 2017.10a
• /
• pp.80-88
• /
• 2017

Although hazard identification is one of the most important steps of safety management process, numerous hazards remain unidentified in the construction workplace due to the dynamic environment of the construction site and the lack of available resource for visual inspection. To this end, our previous study proposed the collective sensing approach for safety hazard identification and showed the feasibility of identifying hazards by capturing collective abnormalities in workers' walking patterns. However, workers generally performed different activities during the construction task in the workplace. Thereby, an additional process that can identify the worker's walking activity is necessary to utilize the proposed hazard identification approach in real world settings. In this context, this study investigated the feasibility of identifying walking activities during construction task using Wearable Inertial Measurement Units (WIMU) attached to the worker's ankle. This study simulated the indoor masonry work for data collection and investigated the classification performance with three different machine learning algorithms (i.e., Decision Tree, Neural Network, and Support Vector Machine). The analysis results showed the feasibility of identifying worker's activities including walking activity using an ankle-attached WIMU. Moreover, the finding of this study will help to enhance the performance of activity recognition and hazard identification in construction.

• The Journal of the Korea Contents Association
• /
• v.13 no.4
• /
• pp.64-72
• /
• 2013

This paper proposes a dynamic gesture recognition algorithm using SVM(Support Vector Machine) which is suitable for multi-dimension classification. First of all, the proposed algorithm locates the beginning and end of the gestures on the video frames at the Kinect camera, spots meaningful gesture frames, and normalizes the number of frames. Then, for gesture recognition, the algorithm extracts gesture features using body parts' positions and relations among the parts based on the human model from the normalized frames. C-SVM for each dynamic gesture is trained using training data which consists of positive data and negative data. The final gesture is chosen with the largest value of C-SVM values. The proposed gesture recognition algorithm can be applied to the interactive storybook as gesture interface.

• Steel and Composite Structures
• /
• v.47 no.1
• /
• pp.91-102
• /
• 2023

To study the evaluation standard and control limit of mortar filling layer void length, in this paper, the train sub-model was developed by MATLAB and the track-bridge sub-model considering the mortar filling layer void was established by ANSYS. The two sub-models were assembled into a train-track-bridge coupling dynamic model through the wheel-rail contact relationship, and the validity was corroborated by the coupling dynamic model with the literature model. Considering the randomness of fastening stiffness, mortar elastic modulus, length of mortar filling layer void, and pier settlement, the test points were designed by the Box-Behnken method based on Design-Expert software. The coupled dynamic model was calculated, and the support vector regression (SVR) nonlinear mapping model of the wheel-rail system was established. The learning, prediction, and verification were carried out. Finally, the reliable probability of the amplification coefficient distribution of the response index of the train and structure in different ranges was obtained based on the SVR nonlinear mapping model and Latin hypercube sampling method. The limit of the length of the mortar filling layer void was, thus, obtained. The results show that the SVR nonlinear mapping model developed in this paper has a high fitting accuracy of 0.993, and the computational efficiency is significantly improved by 99.86%. It can be used to calculate the dynamic response of the wheel-rail system. The length of the mortar filling layer void significantly affects the wheel-rail vertical force, wheel weight load reduction ratio, rail vertical displacement, and track plate vertical displacement. The dynamic response of the track structure has a more significant effect on the limit value of the length of the mortar filling layer void than the dynamic response of the vehicle, and the rail vertical displacement is the most obvious. At 250 km/h - 350 km/h train running speed, the limit values of grade I, II, and III of the lengths of the mortar filling layer void are 3.932 m, 4.337 m, and 4.766 m, respectively. The results can provide some reference for the long-term service performance reliability of the ballastless track-bridge system of HRS.

• Information and Communications Magazine
• /
• v.33 no.9
• /
• pp.24-29
• /
• 2016

영상의 화질 개선과 높은 대비를 얻기 위한 방법으로 최근 HDR(High Dynamic Range)영상을 디스플레이 장치에 매핑시키기 위한 톤매핑 기술이 널리 이용되고 있다. 하지만 단일프레임이 아닌 다중프레임으로 구성되어 있는 비디오에 이러한 톤매핑기술을 적용할 경우, 프레임 간 명암도 차이로 인하여 시각적으로 깜빡이는 현상인 플리커(Flicker)가 발생할 수 있으며, 이로 인해 사용자의 눈에 피로도를 증가시키고, 영상의 품질이 감소할 수 있다. 본 논문에서는 플리커 판별을 위해 영상의 명암도 측정법을 제안하여, 프레임별 명암값을 학습하기 위한 다양한 특징벡터를 정의한다. 학습된 SVM(Support Vector Machine) 분류기를 이용하여 플리커 발생 프레임을 선별하고 플리커 제거를 위한 톤 안정화 방법을 제안한다. 실험에서 제안한 방법을 통해 86.7%의 플리커를 검출하였으며, 프레임 간 톤 안정화 알고리즘의 최적화를 통해 플리커 발생빈도를 69.8% 감소시켰다.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1895-1896
• /
• 2008

지능형 빌딩 환경 모니터링 시스템과 같이 실내에서 센서 네트워크를 이용하여 환경 데이터를 수집하는 네트워크가 점점 확산되고 있다. 이와 같은 건축물 내에서의 무선 센서 네트워크는 랜덤하게 센서 노드들이 뿌려지는 것이 아니라, 사람의 의지대로 배치가 된다. 따라서 위치정보를 모르는 상황의 무선 센서 네트워크들이 가지는 라우팅 방법을 사용하는 것이 아니라 더 간결하면서 강한 네트워크 유지 능력을 가지는 라우팅 방법이 사용되게 된다. 본 논문에서는 트리 라우팅을 이용한 건물 환경 모니터링 시스템에 에너지 효율을 높이기 위하여 네트워크의 상황을 고려한 SVM을 이용한 동적 라우터 선택기법을 포함한 동적 트리 라우팅 기법에 대한 연구와 이의 구현을 보이고 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.313-315
• /
• 2002

본 논문에서는 학습 중 모멘트를 동적으로 조절하여 수련속도와 학습 성능을 향상시키는 동적모멘트를 제안하고 회귀방법으로 동적모멘트의 성능을 재확인한다. 제안된 학습방법은 기존의 정적모멘트와는 달리 수렴 정도에 따라 현재의 학습에 과거의 학습률을 단리 반영하는 방법으로 다른 학습법에 비해 보다 유연한 초평면을 갖으며 수렴에 이르는 시간이 오래 걸리는 KR(Kernel Relaxation)에 적용하여 그 성능을 확인한다. 본 논문에서 사용한 회귀방법은 RMS 오류율을 사용하였으며 제안된 학습방법인 동적모멘트를 SVM(support vector machine)의 순차 학습방법 중 최근 발표된 KR에 적용하여 RMS 오류율을 확인하였다. 실험의 공정성을 위해 신경망 분류기 표준평가데이터인 SONAR 데이터를 사용하였으며 실험 결과 동적모멘트를 이용한 회귀율이 정적모멘트를 이용한 방법보다 향상되었음을 확인하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.883-885
• /
• 2005

지지 벡터 기계(Support Vector Machine: SVM)를 이용한 다중부류 분류기법이 최근 활발히 연구되고 있다. SVM은 이진분류기이기 때문에 다중부류 분류를 위해서 다수의 분류기를 구성하고 이들을 효과적으로 결합하는 방법이 필요하다. 본 논문에서는 기존의 정적인 다중분류기 결합 방법과는 달리 포섭구조의 분류모델을 확률에 따라 동적으로 구성하는 방법을 제안한다. 확률적 분류기인 나이브 베이즈 분류기(NB)를 이용하여 입력된 샘플의 각 클래스에 대한 확률을 계산하고, OVA (One-Vs-All) 전략으로 구축된 다중의 SVM을 획득된 확률에 따라 포섭구조로 구성한다. 제안하는 방법은 OVA SVM에서 발생하는 중의적인 상황을 효과적으로 처리하여 고성능의 분류를 수행한다. 본 논문에서는 지문분류 문제에서 대표적인 NIST-4 지문 데이터베이스를 대상으로 제안하는 방법을 적용하여 $1.8\%$의 거부율에서 $90.8\%$의 분류율을 획득하였으며, 기존의 결합 방법인 다수결 투표(Majority vote), 승자독식(Winner-takes-all), 행동지식공간 (Behavior knowledge space), 결정템플릿(Decision template) 등보다 높은 성능을 확인하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.12
• /
• pp.79-85
• /
• 2017

In this paper, we propose a CNN-based swimmer detection algorithm. Every year, water safety accidents have been occurred frequently, and accordingly, intelligent video surveillance systems are being developed to prevent accidents. Intelligent video surveillance system is a real-time system that detects objects which users want to do. It classifies or detects objects in real-time using algorithms such as GMM (Gaussian Mixture Model), HOG (Histogram of Oriented Gradients), and SVM (Support Vector Machine). However, HOG has a problem that it cannot accurately detect the swimmer in a complex and dynamic environment such as a beach. In other words, there are many false positives that detect swimmers as waves and false negatives that detect waves as swimmers. To solve this problem, in this paper, we propose a swimmer detection algorithm using CNN (Convolutional Neural Network), specialized for small object sizes, in order to detect dynamic objects and swimmers more accurately and efficiently in complex environment. The proposed CNN sets the size of the input image and the size of the filter used in the convolution operation according to the size of objects. In addition, the aspect ratio of the input is adjusted according to the ratio of detected objects. As a result, experimental results show that the proposed CNN-based swimmer detection method performs better than conventional techniques.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.3055-3073
• /
• 2019

In this paper, a new user identification method is presented using real environmental human-computer-interaction (HCI) behavior data to improve method usability. User behavior data in this paper are collected continuously without setting experimental scenes such as text length, action number, etc. To illustrate the characteristics of real environmental HCI data, probability density distribution and performance of keyboard and mouse data are analyzed through the random sampling method and Support Vector Machine(SVM) algorithm. Based on the analysis of HCI behavior data in a real environment, the Multiple Kernel Learning (MKL) method is first used for user HCI behavior identification due to the heterogeneity of keyboard and mouse data. All possible kernel methods are compared to determine the MKL algorithm's parameters to ensure the robustness of the algorithm. Data analysis results show that keyboard data have a narrower range of probability density distribution than mouse data. Keyboard data have better performance with a 1-min time window, while that of mouse data is achieved with a 10-min time window. Finally, experiments using the MKL algorithm with three global polynomial kernels and ten local Gaussian kernels achieve a user identification accuracy of 83.03% in a real environmental HCI dataset, which demonstrates that the proposed method achieves an encouraging performance.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.556-570
• /
• 2021

The existing video expression recognition methods mainly focus on the spatial feature extraction of video expression images, but tend to ignore the dynamic features of video sequences. To solve this problem, a multi-mode convolution neural network method is proposed to effectively improve the performance of facial expression recognition in video. Firstly, OpenFace 2.0 is used to detect face images in video, and two deep convolution neural networks are used to extract spatiotemporal expression features. Furthermore, spatial convolution neural network is used to extract the spatial information features of each static expression image, and the dynamic information feature is extracted from the optical flow information of multiple expression images based on temporal convolution neural network. Then, the spatiotemporal features learned by the two deep convolution neural networks are fused by multiplication. Finally, the fused features are input into support vector machine to realize the facial expression classification. Experimental results show that the recognition accuracy of the proposed method can reach 64.57% and 60.89%, respectively on RML and Baum-ls datasets. It is better than that of other contrast methods.