• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권2호
• /
• pp.800-816
• /
• 2018

In recent years, video surveillance research has been able to recognize various behaviors of pedestrians and analyze the overall situation of objects by combining image analysis technology and deep learning method. Human Activity Recognition (HAR), which is important issue in video surveillance research, is a field to detect abnormal behavior of pedestrians in CCTV environment. In order to recognize human behavior, it is necessary to detect the human in the image and to estimate the pose from the detected human. In this paper, we propose a novel approach for 2D Human Pose Estimation based on object detection using RGB-D information. By adding depth information to the RGB information that has some limitation in detecting object due to lack of topological information, we can improve the detecting accuracy. Subsequently, the rescaled region of the detected object is applied to ConVol.utional Pose Machines (CPM) which is a sequential prediction structure based on ConVol.utional Neural Network. We utilize CPM to generate belief maps to predict the positions of keypoint representing human body parts and to estimate human pose by detecting 14 key body points. From the experimental results, we can prove that the proposed method detects target objects robustly in occlusion. It is also possible to perform 2D human pose estimation by providing an accurately detected region as an input of the CPM. As for the future work, we will estimate the 3D human pose by mapping the 2D coordinate information on the body part onto the 3D space. Consequently, we can provide useful human behavior information in the research of HAR.

• 한국컴퓨터정보학회논문지
• /
• 제14권5호
• /
• pp.157-165
• /
• 2009

본 논문에서는 일상 공간에서 발생할 수 있는 인간의 일상생활 행위(ADL: Activities of Daily Living)들을 인지하는 분산 모델을 제시한다. 사용자의 환경, 위치 및 행위 정보를 간단한 센서들이 부착된 가정용 기기 혹은 식기들을 통해 무선 센서 네트워크로 수집하며 분석하고, 이 정보를 기반으로 사용자의 생환패턴, 건강상태 등을 파악하여 이에 요구되는 라이프케어 서비스를 제공한다. 하지만 서비스의 제공을 위해서는 높은 수준의 행위인지 데이터가 요구되나 충분히 분석되어지지 않은 센싱 데이터들은 고차원 상창 추론을 위한 일상생활 행위 인지 모델의 구축을 어렵게 한다. 그러나 수집 데이터의 순서를 통해 행위를 인지할 수 있다는 것에 착안하여 센서 데이터들의 순서를 특정 행위 패턴을 분석하는 데 활용하고, 이를 기반으로 한 분산 선형 시간추론 알고리즘을 제안한다. 이 알고리즘은 가정, 사무실 및 병원과 같은 소규모 환경에서 행위를 인지하는 데 적절하다. 제안한 알고리즘의 성능평가를 위해서 MIT Media Lab에서 제공하는 공개 데이터를 사용하였으며, 75% 이상의 평균 행위 인지 정확도를 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권5호
• /
• pp.2327-2347
• /
• 2018

Human actions can be recognized from depth sequences. In the proposed algorithm, we initially construct depth, motion maps (DMM) by projecting each depth frame onto three orthogonal Cartesian planes and add the motion energy for each view. The body part of the action (BPoA) is calculated by using bounding box with an optimal window size based on maximum spatial and temporal changes for each DMM. Furthermore, feature vector is constructed by using BPoA for each human action view. In this paper, we employed an ensemble based learning approach called Rotation Forest to recognize different actions Experimental results show that proposed method has significantly outperforms the state-of-the-art methods on Microsoft Research (MSR) Action 3D and MSR DailyActivity3D dataset.

• 대한인간공학회지
• /
• 제31권2호
• /
• pp.271-279
• /
• 2012

Objective: This study classified three different emotional states(boredom, pain, and surprise) using physiological signals. Background: Emotion recognition studies have tried to recognize human emotion by using physiological signals. It is important for emotion recognition to apply on human-computer interaction system for emotion detection. Method: 122 college students participated in this experiment. Three different emotional stimuli were presented to participants and physiological signals, i.e., EDA(Electrodermal Activity), SKT(Skin Temperature), PPG(Photoplethysmogram), and ECG (Electrocardiogram) were measured for 1 minute as baseline and for 1~1.5 minutes during emotional state. The obtained signals were analyzed for 30 seconds from the baseline and the emotional state and 27 features were extracted from these signals. Statistical analysis for emotion classification were done by DFA(discriminant function analysis) (SPSS 15.0) by using the difference values subtracting baseline values from the emotional state. Results: The result showed that physiological responses during emotional states were significantly differed as compared to during baseline. Also, an accuracy rate of emotion classification was 84.7%. Conclusion: Our study have identified that emotions were classified by various physiological signals. However, future study is needed to obtain additional signals from other modalities such as facial expression, face temperature, or voice to improve classification rate and to examine the stability and reliability of this result compare with accuracy of emotion classification using other algorithms. Application: This could help emotion recognition studies lead to better chance to recognize various human emotions by using physiological signals as well as is able to be applied on human-computer interaction system for emotion recognition. Also, it can be useful in developing an emotion theory, or profiling emotion-specific physiological responses as well as establishing the basis for emotion recognition system in human-computer interaction.

• 한국멀티미디어학회논문지
• /
• 제25권6호
• /
• pp.807-818
• /
• 2022

In order to further improve the accuracy and time efficiency of behavior recognition in intelligent monitoring scenarios, a human behavior recognition algorithm based on YOLO combined with LSTM and CNN is proposed. Using the real-time nature of YOLO target detection, firstly, the specific behavior in the surveillance video is detected in real time, and the depth feature extraction is performed after obtaining the target size, location and other information; Then, remove noise data from irrelevant areas in the image; Finally, combined with LSTM modeling and processing time series, the final behavior discrimination is made for the behavior action sequence in the surveillance video. Experiments in the MSR and KTH datasets show that the average recognition rate of each behavior reaches 98.42% and 96.6%, and the average recognition speed reaches 210ms and 220ms. The method in this paper has a good effect on the intelligence behavior recognition.

• 대한임베디드공학회논문지
• /
• 제18권6호
• /
• pp.319-325
• /
• 2023

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.

• Archives of Pharmacal Research
• /
• 제25권4호
• /
• pp.421-427
• /
• 2002

For probing the importance of planarity of imidazolidinone motif of 4-phenyl-1-(N-acylindoline-5-sulfonyl)imidazolidinones 1 for their cytotoxicity, 4-phenyl-1-(N-acylindoline-5-sulfonyl)[1,2,5]thiadiazolidine-1,1-dioxides 2 were prepared and their cytotoxicity were measured against human lung carcinoma (A549), human colon carcinoma (COLO205), human ovarian cancer (SK-OV-3), human leukemic cancer (K562), and murine colon adenocarcinoma (Colon26) cell lines in vitro. Although only carbonyl moiety of imidazolidinone ring was replaced with sulfonyl group, compounds 2 do not show any activity against all five cancer cell lines unlike 1. Therefore the planarity of imidazolidinone ring of 1 should be an important factor for their cytotoxic activity.

• 인터넷정보학회논문지
• /
• 제13권2호
• /
• pp.87-98
• /
• 2012

에이전트의 의도를 인식하는 것은 사물지능형 컴퓨팅에서 인간컴퓨터 상호작용의 주요 부분이다. 컴퓨팅 시스템에서 인식 대상의 의도를 정확하게 유추하면 다수의 에이전트간의 협력 상황 이해와 특정 행동이 취해질 때의 상황 파악이 쉽기 때문이다. 본 연구는 다른 이의 행동을 해석하고 행동의 근거가 되는 의도와 목적을 추론하는 인간의 기제를 바탕으로, 컴퓨팅 시스템이 행동을 인식하여 습득한 사전 경험 데이터를 이용, 대상의 의도를 빠르게 인식하는 방법을 제안한다. 의도 인식을 수행하기 위해 제안 방법은 에이전트의 목적에 따른 행동 변화를 검출하고 시스템이 사전에 학습한 행동 정보를 모델링하기 위해 특정 형태의 행동 은닉마코프 형식을 이용한다. 에이전트의 의도를 추론하는 데 관점을 다양하게 취함으로써 시스템이 에이전트의 행동이 끝나기 전에 미리 의도를 추론하도록 한다. 의도 인식의 정확도, 조기 검출률과 정확 지속률에 대한 실험으로 여러 가지 행동을 취하는 에이전트의 의도 검출 결과를 정량적으로 제시함으로써 제안 연구가 효과적인 의도 인식 시스템 구현에 기여함을 보여준다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.542-544
• /
• 2019

Changes in a person's health affect one's lifestyle and work activities. According to the World Health Organization (WHO), abnormal activity is growing faster in people aged 60 or more than any other age group in almost every country. This trend steadily continues and expected to increase further in the near future. Abnormal activity put these people at high risk of expected incidents since most of these people live alone. Human abnormal activity analysis is a challenging, useful and interesting problem among the researchers and its particularly crucial task in life and health care areas. In this paper, we discuss the problem of abnormal activities of old people lives alone at home. We propose Convolutional Neural Network (CNN) based model to detect the abnormal behaviors of elderlies by utilizing six simulated action data from daily life actions.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제15권1호
• /
• pp.72-76
• /
• 2009

최근 유비쿼터스 컴퓨팅에 대한 관심이 높아지면서 유비쿼터스 환경에서의 서비스를 위한 인간과 컴퓨터의 상호 작용, 특히 인간의 행동을 인식하는 연구가 활발히 진행되고 있다. 기존의 영상기반 연구와는 달리 모바일 환경에 적합하도록 가속도 센서, 생리신호 센서 등 다양한 센서들을 활용하여 사용자의 행동을 인식하는 기법이 연구되고 있다. 본 논문에서는 멀티모달 센서들을 통합하고 동적 베이지안 네트워크를 계층적으로 구성하여 사용자의 행동을 인식하는 방법을 제안한다. 연산량이 비교적 적은 베이지안 네트워크로 전반적인 사용자 행동을 추론하고 획득된 각 행동의 확률순으로 동적 베이지안 네트워크를 구성한다. 동적 베이지안 네트워크는 OVR(One-Versus-Rest) 전략으로 학습되며, 확률순으로 행동이 검증되어 임계치를 넘는 경우 선택된 행동보다 낮은 확률의 행동에 대한 동적 베이지안 네트워크를 검증하지 않아 추론 연산량을 줄인다. 본 논문에서는 가속도 센서와 생리적 신호 센서를 기반으로 총 8가지의 행동을 인식하는 문제에 제안하는 방법을 적용하여 평균적으로 97.4%의 분류 정확률을 얻었다.