• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제4권1호
• /
• pp.57-64
• /
• 2015

사용자의 상황에 따라 유용한 정보를 제공할 수 있는 행위인식 기술은 최근 많은 주목을 받고 있다. 스마트폰이 보급되기 전 행위인식 연구에서는 독립된 센서를 사용하여 사용자의 행위를 추론해야 했지만, 현재는 IT산업의 발달로 스마트폰의 내부 센서를 사용해 사용자의 행위를 추론할 수 있게 되었다. 따라서 행위인식 분야의 연구가 더욱 활발히 진행되고 있다. 행위인식 기술을 응용하면 사용자의 선호도에 따라 애플리케이션을 추천하거나 경로 정보를 제공하는 서비스 등을 개발할 수 있다. 기존의 행위인식 시스템들은 GPS를 이용하기 때문에 전력을 많이 소모한다는 단점이 있다. 반면에 최근 Google에서 발표한 행위인식(Google Activity Recognition) 시스템은 Network Provider를 이용하기 때문에 GPS 방식에 비해 전력소모가 적어 휴대해야 하는 스마트폰 응용 시스템에 적합하다. 하지만 Google Activity Recognition의 성능을 테스트한 결과 불필요한 행위 항목과 일부 잘못된 상황인지로 인해 정확한 사용자 행위를 파악하기 어렵다는 것을 발견했다. 행위인식 기술을 기반으로 한 새로운 서비스 개발을 위해 더욱 정확한 상황인지가 필요하므로 본 논문에서는 GAR의 문제점을 기술하고 정확도를 높이는 개선 방법을 적용한 AGAR(Advanced Google Activity Recognition)을 제안한다. 또한 AGAR의 이용가치를 평가하기 위하여 다른 여러 행위인식 시스템과 성능과 전력소모량을 비교분석하고 AGAR을 검증하는 예시 프로그램을 개발하여 응용 가능성을 설명한다.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1421-1429
• /
• 2017

Human activity recognition has been studied using various sensors and algorithms. Human activity recognition can be divided into sensor based and vision based on the method. In this paper, we proposed an activity recognition system using acceleration sensor and gyroscope sensor in smartphone among sensor based methods. We used Deep Belief Network (DBN), which is one of the most popular deep learning methods, to improve an accuracy of human activity recognition. DBN uses the entire input set as a common input. However, because of the characteristics of different time window depending on the type of human activity, the RBMs, which is a component of DBN, are configured hierarchically by combining them from different time windows. As a result of applying to real data, The proposed human activity recognition system showed stable precision.

• 전자통신동향분석
• /
• 제33권3호
• /
• pp.89-99
• /
• 2018

Human activity recognition (HAR) is a technology that aims to offer an automatic recognition of what a person is doing with respect to their body motion and gestures. HAR is essential in many applications such as human-computer interaction, health care, rehabilitation engineering, video surveillance, and artificial intelligence. Smartphones are becoming the most popular platform for activity recognition owing to their convenience, portability, and ease of use. The noticeable change in smartphone-based activity recognition is the adoption of a deep learning algorithm leading to successful learning outcomes. In this article, we analyze the technology trend of activity recognition using smartphone sensors, challenging issues for future development, and a strategy change in terms of the generation of a activity recognition dataset.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제21권5호
• /
• pp.351-358
• /
• 2015

최근 다양한 센서를 내장한 스마트폰의 발달로 인해 웨어러블 기기를 사용한 동작 인식 연구가 늘어나는 추세이다. 기존의 동작 인식 연구는 사용자 개인의 동작 인식에만 국한되어 있다. 따라서 본 논문에서는 인간의 집단 개념동작을 인식하는 기법을 제안한다. 인식에 앞서 장소 별 집단 동작의 특징을 분석하여 데이터를 생성한다. 강의실 환경에서의 집단 개념동작을 중점적으로 수업하기, 발표하기, 회의하기로 세 가지 동작을 연구한다. 본 연구에서 제안한 알고리즘을 적용하여 96% 이상의 높은 인식률을 도출하였다. 실시간으로 활용한다면 자동적으로 강의실의 사용률 및 사용 목적을 쉽게 분석할 수 있다. 나아가 분석된 데이터를 통해 장소 활용도를 높일 수 있다. 향후 다른 장소에 대한 집단 동작 인식을 연구하여 집단 동작 인식 시스템을 개발할 것이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2767-2780
• /
• 2016

Video-based human-activity recognition has become increasingly popular due to the prominent corresponding applications in a variety of fields such as computer vision, image processing, smart-home healthcare, and human-computer interactions. The essential goals of a video-based activity-recognition system include the provision of behavior-based information to enable functionality that proactively assists a person with his/her tasks. The target of this work is the development of a novel approach for human-activity recognition, whereby human-body-joint features that are extracted from depth videos are used. From silhouette images taken at every depth, the direction and magnitude features are first obtained from each connected body-joint pair so that they can be augmented later with motion direction, as well as with the magnitude features of each joint in the next frame. A generalized discriminant analysis (GDA) is applied to make the spatiotemporal features more robust, followed by the feeding of the time-sequence features into a Hidden Markov Model (HMM) for the training of each activity. Lastly, all of the trained-activity HMMs are used for depth-video activity recognition.

• 한국컴퓨터정보학회논문지
• /
• 제27권2호
• /
• pp.25-32
• /
• 2022

본 논문에서는 활동 인식장치를 이용한 딥러닝 기반의 반려동물 모니터링 시스템을 제안한다.이 시스템은 반려동물의 활동 인식장치와 반려인의 스마트 기기, 서버로 구성된다. 아두이노 기반 활동 인식 장치로부터 가속도와 자이로 데이터를 수집하고, 이로부터 반려동물의 걸음 수를 연산하였다. 수집된 데이터는 전처리 과정을 거쳐 CNN과 LSTM을 하이브리드한 딥러닝 모델을 통해 5가지 형태(앉기, 서기, 눕기, 걷기, 뛰기)로 활동을 인식함으로써 활동량을 측정한다. 마지막으로, 반려인의 스마트 기기에 일일 및 주간 브리핑 차트 등 활동 변화에 대한 모니터링을 제공한다. 성능 평가 결과, 반려동물의 구체화된 활동 인식 및 활동량 측정이 가능함을 확인하였다. 향후 데이터 축적을 통해 반려동물의 이상행동 탐지 및 헬스 케어 서비스의 확장을 기대할 수 있다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권3호
• /
• pp.197-201
• /
• 2006

In the implementation of a smart home, activity recognition technology using simple sensors is very important. In this paper, we propose a new activity recognition method based on Bayesian network (BN). The structure of the BN is learned by K2 algorithm and is composed of sensor nodes, activity nodes and time node whose state is quantized with reasonable interval. In the proposed method, the BN has less complexity and provides better activity recognition rate than the previous method.

• 한국컴퓨터정보학회논문지
• /
• 제20권9호
• /
• pp.67-72
• /
• 2015

Recently, studies that interact with human and things through motion recognition are increasing due to the expansion of IoT(Internet of Things). This paper proposed the system that recognizes the user's logical activity in home environment by attaching some sensors to various objects. We employ Arduino sensors and appreciate the logical activity by using the physical activitymodel that we processed in the previous researches. In this System, we can cognize the activities such as watching TV, listening music, talking, eating, cooking, sleeping and using computer. After we produce experimental data through setting virtual scenario, then the average result of recognition rate was 95% but depending on experiment sensor situation and physical activity errors the consequence could be changed. To provide the recognized results to user, we visualized diverse graphs.

• Journal of Information Processing Systems
• /
• 제10권3호
• /
• pp.335-354
• /
• 2014

The accuracy of training-based activity recognition depends on the training procedure and the extent to which the training dataset comprehensively represents the activity and its varieties. Additionally, training incurs substantial cost and effort in the process of collecting training data. To address these limitations, we have developed a training-free activity recognition approach based on a fuzzy logic algorithm that utilizes a generic activity model and an associated activity semantic knowledge. The approach is validated through experimentation with real activity datasets. Results show that the fuzzy logic based algorithms exhibit comparable or better accuracy than other training-based approaches.

• The Journal of Korean Physical Therapy
• /
• 제33권6호
• /
• pp.307-313
• /
• 2021

Purpose: This study was to the investigate recognition of physical activity between physical therapy students (PTS) and non-physical therapy students (NPTS) by measuring the level of physical activity using International Physical Activity Questionnaires (IPAQ). Methods: A cross-sectional survey was completed by 191 university students. The IPAQ with an additional question (Is physical activity necessary for your future job?) was used to evaluate the recognition and the amount of physical activity. The collected data were calculated as MET-minutes scores and were classified as walking, moderate, and vigorous level of physical activity. The students were analyzed by dividing them into those who had a part-time employment (16 PTS and 12 NPTS) and those who did not have a part-time employment (80 PTS and 83 NPTS). Results: In students with a part-time employment, no significances were observed between the PTS and NPTS, in terms of MET, frequency and time of physical activity, and sitting time (p>0.05). In students without a part-time employment, the NPTS was significantly higher than the PTS for the MET and frequency of physical activity in a vigorous level (p<0.05), and there were no significant differences in other levels of physical activity (p>0.05). In the additional question, the PTS showed a slightly higher than the NPTS (p<0.05). Conclusion: The physical therapy students did not remarkable barrier to recognition of physical activity, but there was a difference in their recognition of the vigorous level of physical activity. Therefore, the understanding of physical activity for PTS would play an important role in the recognition of how physical activity can be promoted.