• Communications for Statistical Applications and Methods
• /
• 제30권6호
• /
• pp.551-560
• /
• 2023

Recently, there has been significant research into the recognition of human activities using three-dimensional sequential skeleton data captured by the Kinect depth sensor. Many of these studies employ deep learning models. This study introduces a novel feature selection method for this data and analyzes it using machine learning models. Due to the high-dimensional nature of the original Kinect data, effective feature extraction methods are required to address the classification challenge. In this research, we propose using the first four moments as predictors to represent the distribution of joint sequences and evaluate their effectiveness using two datasets: The exergame dataset, consisting of three activities, and the MSR daily activity dataset, composed of ten activities. The results show that the accuracy of our approach outperforms existing methods on average across different classifiers.

• Advances in robotics research
• /
• 제2권2호
• /
• pp.129-140
• /
• 2018

With the increasing demand for the development of human pose estimation, such as human-computer interaction and human activity recognition, there have been numerous approaches to detect the 2D poses of people in images more efficiently. Despite many years of human pose estimation research, the estimation of human poses with images remains difficult to produce satisfactory results. In this study, we propose a robust 2D human body pose estimation method using an RGB camera sensor. Our pose estimation method is efficient and cost-effective since the use of RGB camera sensor is economically beneficial compared to more commonly used high-priced sensors. For the estimation of upper-body joint positions, semantic segmentation with a fully convolutional network was exploited. From acquired RGB images, joint heatmaps accurately estimate the coordinates of the location of each joint. The network architecture was designed to learn and detect the locations of joints via the sequential prediction processing method. Our proposed method was tested and validated for efficient estimation of the human upper-body pose. The obtained results reveal the potential of a simple RGB camera sensor for human pose estimation applications.

• Industrial Engineering and Management Systems
• /
• 제9권2호
• /
• pp.131-140
• /
• 2010

Biclustering is a method of finding meaningful subsets of objects and attributes simultaneously, which may not be detected by traditional clustering methods. It is popularly used for the analysis of microarray data representing the expression levels of genes by conditions. Usually, biclustering algorithms do not consider a sequential relation between attributes. For time series data, however, bicluster solutions should keep the time sequence. This paper proposes a new biclustering algorithm for time series data by modifying the plaid model. The proposed algorithm introduces a parameter controlling an interval between two selected time points. Also, the pruning step preventing an over-fitting problem is modified so as to eliminate only starting or ending points. Results from artificial data sets show that the proposed method is more suitable for the extraction of biclusters from time series data sets. Moreover, by using the proposed method, we find some interesting observations from real-world time-course microarray data sets and apartment price data sets in metropolitan areas.

• 한국환경농학회지
• /
• 제24권2호
• /
• pp.106-116
• /
• 2005

This experiment was conducted to investigate available extraction capacity and potential mobility of heavy metal according to the distribution property and contamination level of heavy metals in soils and to suggest a reform measure of soil environment assessment methodology applied with soil quality and the official soil heavy metal test methods in domestic and foreign countries. The soils were collected from the natural forest paddy with long-term application of same type fertilizer, and paddies near metal mine and industrial complex. The post-treatment methods of soil were partial extraction, acid digestion and sequential extraction methods. For the heavy metal contents with different soil properties, it was shown that their natural forest and paddy soil were slightly low and similar to the general paddy soil, while their paddies near metal mine and industrial complex were higher than the standard level of Soil Environment Protection Act. Heavy metal concentrations in the soils with different soil properties had difference between $HNO_3\;and\;HNO_3+HCl$ extractant by US-EPA 3051a method. There were highly significant positive relationships in both two methods. It was appeared that the higher extractable concentration ratio with 0.1N-HCl to total heavy metal content with $HNO_3+HCl$ extractant the greater total heavy metal content. There were highly significant positive correlationship between total heavy metal content and extractable content with 0.1N-HCl. For extractable capacity of soil extractable solution compared to the total heavy metal content it was appeared that it extractable method with 0.1N-HCl was higher than those with EDTA and DTPA. In extractable ratio with 0.1N-HCl in the contaminated paddy soils near mine and industrial complex, it was shown that the lower soil pH, the higher total heavy metal content. The order of a potential mobility coefficient by distribution of heavy metal content with ie different typies in the soil was Cd>Ni>Zn>Cu>Pb. It could be known that contamination characteristics of heavy metals with different types of soils were affected by different heavy metal components, contamination degree and soil chemical properties, and heavy metal concentration with different extractable methods had great variations with adjacent environment. To be compared with assessment methodology of soil environment impact at domestic and foreign countries with our results, it might be considered that there was necessary to make a single analysis method based on total heavy metal content with environmental overloading concept because of various analysis methods for total heavy metal content and present analysis method with great variation according to soil environment. In spite of showing higher concentration of heavy metal with acidic digestion than the extractable method, it might be considered that there is need to be adjusted the national standard of soil heavy metal contamination.

• 대한전자공학회논문지SP
• /
• 제45권5호
• /
• pp.103-110
• /
• 2008

산업용 방사선영상으로부터 신뢰할만한 용접부위를 추출하는 것은 용접부의 결함을 검출하기 이전에 수행해야할 선행과제이다. 이 논문은 강판튜브 CR영상으로부터 용접특징 부위의 검출과 추출을 시도한다. 먼저 용접부위와 비용접부위로 구분된 샘플영상 160(개)를 통계 분석하여 두 부류 사이의 차이를 식별한다. 그 후 군집화 파라미터 결정을 위한 패턴분류 작업을 실시한다. 이 파라미터들은 간격, 함수부합정도 및 연속성이다. 관측된 용접영상을 선(線)별로 처리하되 각 선데이터군(群)에 가변 이동창을 적용하여 구역을 선점한다. 각 창을 구성하는 데이터의 직접 및 비용접부위 귀속여부는 국부확률선군집화 방식을 적용하여 분류한다. 순차적 과정을 거쳐 매 단계마다의 경계치 산출에 의해 두 영역 사이의 경계선을 추적하며 그 결과 용접 특징부위를 추출한다. 그리고 CR용접영상 실험을 통해 그 효과를 입증한다.

• 한국멀티미디어학회논문지
• /
• 제25권11호
• /
• pp.1547-1556
• /
• 2022

As mechanical facilities are interacting with each other, the failure of some equipment can affect the entire system, so it is necessary to quickly detect and diagnose the abnormality of mechanical equipment. This study proposes a deep learning model that can effectively diagnose abnormalities in rotating machinery and equipment. CNN is widely used for feature extraction and LSTMs are known to be effective in learning sequential information. In LSTM, the number of parameters and learning time increase as the length of input data increases. In this study, we propose a method of segmenting an input segment signal into shorter-length sub-segment signals, sequentially inputting them to CNN through a time-distributed method for extracting features, and inputting them into LSTM. A failure diagnosis test was performed using the vibration data collected from the motor for ventilation equipment installed at the urban railway station. The experiment showed an accuracy of 99.784% in fault diagnosis. It shows that the proposed method is effective in the fault diagnosis of rotating machinery and equipment.

• 한국지하수토양환경학회지:지하수토양환경
• /
• 제12권6호
• /
• pp.100-106
• /
• 2007

본 연구에서는 휴.폐광산 인근 납(Pb), 카드뮴(Cd), 비소(As)로 오염된 논토양에 대하여 $(NH_4)_2HPO_4$, $Na_2HPO_4{\cdot}12H_2O$, $Ca(H_2PO_4{\cdot}2H_2O$, $Ca(H_2PO_4)_2{\cdot}H_2O$, $H_3PO_4$를 안정화물질로 선정하여 $PO_4/Pb_{total}$의 몰비를 0.5, 1, 2, 4로 안정화 처리하였다. 안정화효율 평가를 위해 토양오염공정시험법과 TCLP(EPA Method 1311)를 수행한 결과, 납의 경우 $H_3PO_4$와 $Ca(H_2PO_4)_2{\cdot}H_2O$가 토양환경보전법상의 '가' 지역 기준을 만족하였으며, 특히 $H_3PO_4$의 경우 몰비가 증가할수록 안정화 효율이 급격히 증가하였다. 카드뮴은 납에 비하여 안정화효율이 매우 낮게 나타났으며, 비소의 경우 대부분의 안정화물질에서 안정화효율이 거의 나타나지 않거나 오히려 용출농도가 증가하였다. $H_3PO_4$가 다른 인산염 물질에 비해 납의 안정화에 높은 효율을 나타낸 것은 $H_3PO_4$에 의한 토양 pH의 저하로 인한 $Pb^{2+}$의 용출과 함께 $PO_4$가 반응하여 생성물인 hydroxypyromorphite(HP) 형성되었기 때문으로 판단된다. 연속추출법을 통한 안정화처리 전.후 토양내 중금속 결합형태의 변화는 $H_3PO_4$의 경우 5단계인 Residual fraction의 비율이 약 60% 정도 증가하였고 XRD 분석결과 $H_3PO_4$에서만 hydroxypyromorphite peak가 발견된 것과 일치하였다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2010년도 춘계 학술발표회
• /
• pp.984-999
• /
• 2010

A long-term field demonstration experiment of selected stabilization method to reduce the heavy metal mobility in farmland soil contaminated by heavy metals around abandoned mine site was conducted. Field demonstration experiments were established on the contaminated farmland with the wooden plate(thickness=1cm) which dimension were width=200cm, Length=200cm, height=80cm and filled with treated soil, which was mixed with lime stone and steel refining slag except on control plot. Soil samples in the plots were collected and analyzed during the experiment period(2008. 2~2008. 8) after the installation of the plots. Field demonstration experiments results showed that the application ratio of lime stone 5% was effective for immobilizing heavy metal components in contaminated farmland soil.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2009년도 춘계 학술발표회
• /
• pp.265-277
• /
• 2009

A long-term field demonstration experiment of selected stabilization method to reduce the heavy metal mobility in farmland soil contaminated by heavy metals around abandoned mine site was conducted. Field demonstration experiments were established on the contaminated farmland with the wooden plate(thickness=1cm) which dimension were width=200cm, Length=200cm, height=80cm and filled with treated soil, which was mixed with lime stone and steel refining slag except on control plot. Soil samples were collected and analyzed during the experiment period(2008. 2~2008. 8) after the installation of the plots. Field demonstration experiments results showed that the application ratio of lime stone 5% was effective for immobilizing heavy metal components in contaminated farmland soil.

• 대한전자공학회논문지SP
• /
• 제37권2호
• /
• pp.39-49
• /
• 2000

본 논문에서는 다중 클래스 데이터를 위한 특징 추출 방법을 최적화하는 기법을 제안한다 제안된 특징 추출 기법은 분류 오차에 기반한 방법으로 특징 공간(feature space)을 탐색하여 가우시안 최대우도 분류기 (Gaussian ML Classifier)의 분류오차(classification error)가 최소가 되도록 하는 특징벡터 집합을 구하는 방법이다 제안된 방법은 임의의 초기 특징벡터를 설정한 후 steepest descent 알고리즘을 적용하여 분류오차가 감소하는 방향으로 초기벡터를 갱신시킨다 본 논문에서는 순차탐색 및 전체탐색 두 가지의 방법을 제안하며 순차탐색은 추가로 특징벡터를 구하는 경우 이미 구해진 특징벡터를 포함하여 최소의 분류오차를 얻을 수 있는 특징벡터를 구한다 반면에 전체탐색 방법은 추가의 특징벡터를 구할 경우 새로운 초기 특징벡터 집합을 설정하여 이미 구해진 특징벡터를 포함하는 제약을 받지 않는다. 실험결과 제안된 두 가지 방법은 기존의 특징추출 방법보다 우수한 성능을 보여주고 있다.