http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Batchuluun, D. (검색결과 25 건)
- 무료
- 기관 내 무료
- 유료
-
Fuzzy system based human behavior recognition by combining behavior prediction and recognition
Batchuluun, G.,Kim, J.H.,Hong, H.G.,Kang, J.K.,Park, K.R. Pergamon 2017 Expert Systems with Applications Vol. No.
With the development of intelligent surveillance systems, human behavior recognition has been extensively researched. Most of the previous methods recognized human behavior based on spatial and temporal features from (current) input image sequences, without the behavior prediction from previously recognized behaviors. Considering an example of behavior prediction, ''punching'' is more probable in the current frame when the previous behavior is ''standing'' as compared to the previous behavior being ''lying down.'' Nevertheless, there has been little study regarding the combination of currently recognized behavior information with behavior prediction. Therefore, we propose a fuzzy system based behavior recognition technique by combining both behavior prediction and recognition. To perform behavior recognition during daytime and nighttime, a dual camera system of visible light and thermal (far infrared light) cameras is used to capture 12 datasets including 11 different human behaviors in various surveillance environments. Experimental results along with the collected datasets and open database showed that the proposed method achieved higher accuracy of behavior recognition when compared to conventional methods.
-
-
Hand Gesture Recognition Using an Infrared Proximity Sensor Array
Batchuluun, Ganbayar,Odgerel, Bayanmunkh,Lee, Chang Hoon Korean Institute of Intelligent Systems 2015 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.15 No.3
Hand gesture is the most common tool used to interact with and control various electronic devices. In this paper, we propose a novel hand gesture recognition method using fuzzy logic based classification with a new type of sensor array. In some cases, feature patterns of hand gesture signals cannot be uniquely distinguished and recognized when people perform the same gesture in different ways. Moreover, differences in the hand shape and skeletal articulation of the arm influence to the process. Manifold features were extracted, and efficient features, which make gestures distinguishable, were selected. However, there exist similar feature patterns across different hand gestures, and fuzzy logic is applied to classify them. Fuzzy rules are defined based on the many feature patterns of the input signal. An adaptive neural fuzzy inference system was used to generate fuzzy rules automatically for classifying hand gestures using low number of feature patterns as input. In addition, emotion expression was conducted after the hand gesture recognition for resultant human-robot interaction. Our proposed method was tested with many hand gesture datasets and validated with different evaluation metrics. Experimental results show that our method detects more hand gestures as compared to the other existing methods with robust hand gesture recognition and corresponding emotion expressions, in real time.
-
-
Batchuluun Iderbayar,Sodnom Oyungerel,김영민 한국지질과학협의회 2024 Geosciences Journal Vol.28 No.2
This study aims to determine the depositional setting and deposit type of the Ereen deposit in the Bayanjargalan soum of Dundgovi province and the Dartsagt deposit in the Dalanjargalan soum of Dornogovi province, Mongolia. Both deposits are hosted within the sediments of the Neoproterozoic Oortsog Formation. The ore-hosted Oortsog Formation consists of shale with muscovitesericite-magnetite-quartz and marbled limestone. The former is characterzid by gray to black shaly texture. Major, minor and trace elements composition of 16 ore samples of these two deposits were analyzed by XRF, ICP-MS and ICP-OES. The total iron (TFe) contents of the ore samples from the Ereen deposit range from 28.83 to 51.09 wt% with an average of 41.92 wt% whereas the TFe contents of the Dartsagt deposit from 37.61 to 49.78 wt% with an average of 43.15 wt%. In the Post-Archean Australian Shale (PAAS)-normalized REY diagram, the samples from the Ereen and the Dartsagt deposits show a weakly LREE depleted and HREE weakly enriched trend. Also, in the chondrite-normalized REY diagram, negative Eu anomaly Y-enriched trend are observed. The Eu/Eu*SN values of the Ereen deposit (0.93 to 1.25, average 1.08) and the Dartsagt deposit range from 0.93 to 1.25 (avg. 1.08) and from 1.05 to 1.61 (avg. 1.22), respectively. These trace elements characteristics indicate that these two deposits belong to the Superior-type BIF deposit formed on the passive continental margin and are not likely to be associated with volcanogenic rocks.
-
Body-movement-based human identification using convolutional neural network
Batchuluun, Ganbayar,Naqvi, Rizwan Ali,Kim, Wan,Park, Kang Ryoung Elsevier 2018 expert systems with applications Vol.101 No.-
<P><B>Abstract</B></P> <P>Biometric technology based on human gait identifies humans at a far distance even if the individual's face is covered, hidden, or not visible to cameras in dark environments. Previous studies based on human gait were conducted considering both bright and dark environments for human identification in surveillance systems. The studies conducted in low-illumination environments (dark environments) are based on side view images (horizontal walking) of subjects. However, there are cases in which people only show the front and back views of their bodies while they are walking in low-illumination corridors. In these views, it is difficult to identify humans by using conventional features such as cycle, cadence, stride length of walking, and distance between points (ankle, knee, and hip). Additionally, the cases of problems such as people carrying cellphones and/or small personal items (a purse, bag, clothes, etc.) have critical effects on the accuracy of human identification. To overcome these problems, we propose a new human identification technique, which is based on the front and back view images of a human, captured by using a thermal camera sensor. Our technique uses movements of the human body for identification, particularly movement of the head, shoulders, and legs. We have used a convolutional neural network for feature extraction and classification in this study. Five datasets were compiled by collecting data of 80 people including men and women in both bright and dark environments. The experimental results with our collected data and open database showed a higher performance by using our method compared to those of previous studies.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Our method is body movement-based human identification using front and back view. </LI> <LI> Our identification method is robust to the cases of people carrying items or with various poses. </LI> <LI> Deep learning method using thermal difference image-based three-channel inputs is used. </LI> <LI> Our collected database and trained CNN are public to other researchers. </LI> </UL> </P>
-
Batchuluun Tseveen,Enkhjargal Natsagdorj,Altangerel Balgan,Tsolmon Renchin,Bayanmunkh Norovsuren,Zaya Mart 한국산림과학회 2020 Forest Science And Technology Vol.16 No.3
Forests in Mongolia yield low productivity and are vulnerable to disturbances from drought, fire, pests, and illegal logging. Such forests can quickly lose their ecological balance. Logging activities in these areas are limited in monitoring and controls. This study assesses two different logging operations for their natural regeneration capacity by comparing the composition of the soil, soil organisms, physical and chemical properties, and forest cover change after the completion of logging operations. The logging operations were analyzed in two different regions, the Khartsai and Tariakhtai threshold in Selenge soum, Bulgan province. A skyline logging operation was undertaken on Khartsai threshold in 1983 and a tractor logging operation (clear-cutting) on Tariakhtai threshold in 1987. After the completion of the logging, the forests were naturally regenerated. In 2002, soil samples were collected and soil organisms and physical and chemical properties were examined. Satellites images were also used to evaluate forest cover changes after the end of the logging operations. Significant differences in the naturally regenerated tree species in the skyline logging, tractor logging, and natural forest areas were observed. Average tree ring growth was 0.9 mm in the skyline logging site, 0.6 mm in the tractor logging site, and 1.2 mm in the natural forest. Based on forest cover changes observed in satellite images, the density of naturally regenerated tree species in the natural forest area was higher than that in the skyline logging area. In contrast, the latter recorded a higher density than that in the tractor logging area. Therefore, processing of satellite images of forest cover changes with high-resolution data provides valuable information for the local forest community and helps decision-makers in their further actions.
-
-
Hand Gesture Recognition Using an Infrared Proximity Sensor Array
Ganbayar Batchuluun,Bayanmunkh Odgerel,Chang Hoon Lee 한국지능시스템학회 2015 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.15 No.3
Hand gesture is the most common tool used to interact with and control various electronic devices. In this paper, we propose a novel hand gesture recognition method using fuzzy logic based classification with a new type of sensor array. In some cases, feature patterns of hand gesture signals cannot be uniquely distinguished and recognized when people perform the same gesture in different ways. Moreover, differences in the hand shape and skeletal articulation of the arm influence to the process. Manifold features were extracted, and efficient features, which make gestures distinguishable, were selected. However, there exist similar feature patterns across different hand gestures, and fuzzy logic is applied to classify them. Fuzzy rules are defined based on the many feature patterns of the input signal. An adaptive neural fuzzy inference system was used to generate fuzzy rules automatically for classifying hand gestures using low number of feature patterns as input. In addition, emotion expression was conducted after the hand gesture recognition for resultant human-robot interaction. Our proposed method was tested with many hand gesture datasets and validated with different evaluation metrics. Experimental results show that our method detects more hand gestures as compared to the other existing methods with robust hand gesture recognition and corresponding emotion expressions, in real time.
-
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
