• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.150-161
• /
• 2018

We propose a novel deep neural network model for detecting human activities in untrimmed videos. The process of human activity detection in a video involves two steps: a step to extract features that are effective in recognizing human activities in a long untrimmed video, followed by a step to detect human activities from those extracted features. To extract the rich features from video segments that could express unique patterns for each activity, we employ two different convolutional neural network models, C3D and I-ResNet. For detecting human activities from the sequence of extracted feature vectors, we use BLSTM, a bi-directional recurrent neural network model. By conducting experiments with ActivityNet 200, a large-scale benchmark dataset, we show the high performance of the proposed DeepAct model.

• Korean Journal of Acupuncture
• /
• 제38권3호
• /
• pp.162-174
• /
• 2021

Objectives : We aimed to identify the antidepressant effect of liver tonification acupuncture treatment (ACU (LT); KI10, LR8, LU8, LR4) and four gate acupuncture treatment (ACU (FG); LI4, LR3) and its brain neural activity in the normal and chronic restraint stress (CRS)-induced mouse model. Methods : Firstly, normal mice were given ACU (LT) or ACU (FG) and the c-Fos expressions in each brain region were analyzed to examine brain neural activity. Secondly, CRS was administered to mice for 4 weeks, then ACU (LT) or ACU (FG) was performed for 2 weeks. The depression-like behavior was evaluated using open field test (OFT) before and after acupuncture treatment. Then, the c-Fos expressions in each brain region were analyzed to examine brain neural activity. Results : In normal mice, ACU (FG) regulated brain neural activities in the hypothalamus, hippocampus, and periaqueductal gray. ACU (LT) changed more brain regions in the prefrontal cortex, insular cortex, striatum, and hippocampus, including those altered by ACU (FG). In CRS-induced model, ACU (LT) alleviated depression-like behavior more than ACU (FG). Also, brain neural activities in the motor cortex area 2 (M2), agranular ventral part and piriform of insular cortex (AIV and Pir), and cornu ammonis (CA) 1 and CA3 of hippocampus were changed by ACU (LT), and those of AIV and CA3 were also changed by ACU (FG). As in normal mice, ACU (LT) resulted in changes in more brain regions, including those altered by ACU (FG) in CRS model. M2, Pir, and CA1 were only changed by ACU (LT) in depression model, suggesting that these brain regions reflect the specific effect of ACU (LT). Conclusions : ACU (LT) relieved depression-like behavior more than ACU (FG), and this acupuncture effect was associated with modulation of brain neural activities in the motor cortex, insular cortex, and hippocampus.

• 전자공학회논문지S
• /
• 제35S권2호
• /
• pp.70-78
• /
• 1998

Spike detection in long-term EEG monitoring forepilepsy by wavelet transform(WT), artificial neural network(ANN) and the expert system is presented. First, a small set of wavelet coefficients is used to represent the characteristics of a singlechannel epileptic spikes and normal activities. In this stage, two parameters are also extracted from the relation between EEG activities before the spike event and EEG activities with the spike. then, three-layer feed-forward network employing the error back propagation algorithm is trained and tested using parameters obtained from the first stage. Spikes are identified in individual EEG channels by 16 identical neural networks. Finally, 16-channel expert system based on the context information of adjacent channels is introducedto yield more reliable results and reject artifacts. In this study, epileptic spikes and normal activities are selected from 32 patient's EEG in consensus among experts. The result showed that the WT reduced data input size and the preprocessed ANN had more accuracy than that of ANN with the same input size of raw data. Ina clinical test, our expert rule system was capable of rejecting artifacts commonly found in EEG recodings.

• 융합신호처리학회논문지
• /
• 제23권4호
• /
• pp.234-240
• /
• 2022

본 논문은 직종별 근무 환경에 따른 상대적 운동량을 고려한 맞춤형 AI 운동 추천 서비스 방법을 제안한다. 가속도 및 자이로 센서를 활용하여 수집된 데이터를 18가지 일상생활의 신체활동으로 분류한 WISDM 데이터베이스를 기반으로 전신, 하체, 상체의 3가지 활동으로 분류한 후 인식된 활동 지표를 통해 적절한 운동을 추천한다. 본 논문에서 신체활동 분류를 위해서 사용하는 1차원 합성곱 신경망(1D CNN; 1 Dimensional Convolutional Neural Network) 모델은 커널 크기가 다른 다수의 1D 컨볼루션(Convolution) 계층을 병렬적으로 연결한 컨볼루션 블록을 사용한다. 컨볼루션 블록은 하나의 입력 데이터에 다층 1D 컨볼루션을 적용함으로써 심층 신경망 모델로 추출할 수 있는 입력 패턴의 세부 지역 특징을 보다 얇은 계층으로도 효과적으로 추출 할 수 있다. 제안한 신경망 모델의 성능 평가를 위해서 기존 순환 신경망(RNN; Recurrent Neural Network) 모델과 비교 실험한 결과 98.4%의 현저한 정확도를 보였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2008년도 춘계종합학술대회 A
• /
• pp.229-232
• /
• 2008

A Neural network classification of human activity data is presented. The data acquisition system involves a tri-axial accelerometer in wireless sensor network environment. The wireless ad-hoc system has the advantage of small size, convenience for wearability and cost effectiveness. The system can further improve the range of user mobility with the inclusion of ad-hoc environment. The classification is based on the frequencies of the involved activities. The most significant Fast Fourier coefficients, of the acceleration of the body movement, are used for classification of the daily activities like, Rest walk and Run. A supervised learning approach is used. The work presents classification accuracy with the available fast batch training algorithms i.e. Levenberg-Marquardt and Resilient back propagation scheme is used for training and calculation of accuracy.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.744-751
• /
• 2022

Construction is among the most dangerous industries with numerous accidents occurring at job sites. Following an accident, an investigation report is issued, containing all of the specifics. Analyzing the text information in construction accident reports can help enhance our understanding of historical data and be utilized for accident prevention. However, the conventional method requires a significant amount of time and effort to read and identify crucial information. The previous studies primarily focused on analyzing related objects and causes of accidents rather than the construction activities. This study aims to extract construction activities taken by workers associated with accidents by presenting an automated framework that adopts a deep learning-based approach and natural language processing (NLP) techniques to automatically classify sentences obtained from previous construction accident reports into predefined categories, namely TRADE (i.e., a construction activity before an accident), EVENT (i.e., an accident), and CONSEQUENCE (i.e., the outcome of an accident). The classification model was developed using Convolutional Neural Network (CNN) showed a robust accuracy of 88.7%, indicating that the proposed model is capable of investigating the occurrence of accidents with minimal manual involvement and sophisticated engineering. Also, this study is expected to support safety assessments and build risk management systems.

• The Journal of Korean Physical Therapy
• /
• 제32권5호
• /
• pp.312-318
• /
• 2020

Purpose: This study aimed to investigate the evidence that therapeutic horseback riding can improve balance, muscle, ADL, equivalenc, GMFM, gait, emotion with developmental disabilities and neural patients. Methods: To conduct meta-analysis, the search focused on studies that employed therapeutic horseback riding for developmental disabilities and neural patients for which eight databases (KIS, RISS, DBpia, National Assembly Library, Pubmed, Embase, Google scholar and Cochrane Library) were used to extract literature published from 2002 to September 2019. The data were analyzed the RevMan 3.5.3 program. Results: As a result of meta-analysis, therapeutic horseback riding total effect size is 0.552 for children with developmental disabilities and neural patients. And effect size result of according to assessment type variable first, balance effect size is 0.594. Second, muscle activities effect size is 0.425. Third, ADL effect size is 0.430. Fourth, equivalance effect size is 0.640. Fifth, GMFM effect size is 0.482. Sixth, gait effect size is 0.400 and seventh emotion effect size is 0.876. Conclusion: These findings is horseback riding is effective The effect size by outcome was observed to be the effective for children with developmental disabilities and neural patients. and also the horseback riding provided the positive effects of balance, muscle activities, ADL, equivalance, GMFM, gait, emotion for children with developmental disabilities and neural patients. It is hoped that this study will contribute to the development of effective treatments for children with developmental disabilities and neural patients therapeutic horseback riding and the development of study.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2008년도 추계종합학술대회 B
• /
• pp.265-269
• /
• 2008

Home health care with compact wearable units sounds to be a convenient solution for the elderly people living independently. This paper presents a method to detect fall from the other activities of daily living and also to classify those activities. This kind of ambulatory monitoring enables them to get an emergency help in the case of the fatal fall event and can provide their general health status by observing the activities being performed in daily life. A tri-axial accelerometer sensor is used to get the acceleration anomalies associated with the user's movements. The three axis acceleration data are transferred to the base station sensor node via an IEEE 802.15.4 compliant zigbee module. The base station sensor node sends the data to base station PC for an offline processing. This work shows the feature set preparation using the principal component analysis (PCA) for the designing of neural network. The work includes the most common activities of daily living (ADL) like Rest, Walk and Run along with the detection of fall events from ADL. The angle from the vertical is found to be the most significant feature parameter for classification of fall while mean, standard deviation and FFT coefficients were used as the feature parameter for classifying the other activities under consideration. The accuracy for detection of fall events is 86%. The overall accuracy for ADL and fall is 94%.

• 인터넷정보학회논문지
• /
• 제22권3호
• /
• pp.9-16
• /
• 2021

This study aims to develop a human activity recognition (HAR) system as a Deep-Learning (DL) classification model, distinguishing various human activities. We solely rely on the signals from a wristband accelerometer worn by a person for the user's convenience. 3-axis sequential acceleration signal data are gathered within a predefined time-window-slice, and they are used as input to the classification system. We are particularly interested in developing a Deep-Learning model that can outperform conventional machine learning classification performance. A total of 13 activities based on the laboratory experiments' data are used for the initial performance comparison. We have improved classification performance using the Convolutional Neural Network (CNN) combined with an auto-encoder feature reduction and parameter tuning. With various publically available HAR datasets, we could also achieve significant improvement in HAR classification. Our CNN model is also compared against Recurrent-Neural-Network(RNN) with Long Short-Term Memory(LSTM) to demonstrate its superiority. Noticeably, our model could distinguish both general activities and near-identical activities such as sitting down on the chair and floor, with almost perfect classification accuracy.

• 한국안전학회지
• /
• 제38권1호
• /
• pp.1-8
• /
• 2023

It is extremely important to design safety-guaranteed industrial processes because such process determine the ultimate outcomes of industrial activities, including worker safety. Application of artificial intelligence (AI) in industrial safety involves modeling industrial safety systems by using vast amounts of safety-related data, accident prediction, and accident prevention based on predictions. As a preliminary step toward realizing AI-based industrial safety in Korea, this study discusses neural network-based modeling of industrial safety systems. The input variables that are the most discriminatory relative to the output variables of industrial safety processes are selected using two information-theoretic measures, namely entropy and cross entropy. Normalized frequency and severity of industrial accidents are selected as the output variables. Our simulation results confirm the effectiveness of the proposed neural network model and, therefore, the feasibility of extending the model to include more input and output variables.