Complex Activity Representation and Recognition by Extended Stochastic Grammar

2006 ◽  
pp. 150-159 ◽  
Author(s):  
Zhang Zhang ◽  
Kaiqi Huang ◽  
Tieniu Tan
Keyword(s):  
Complex Activity ◽  
Stochastic Grammar ◽  
Activity Representation

Hierarchical Complex Activity Representation and Recognition Using Topic Model and Classifier Level Fusion

2017 ◽  
Vol 64 (6) ◽  
pp. 1369-1379 ◽  
Author(s):  
Liangying Peng ◽  
Ling Chen ◽  
Xiaojie Wu ◽  
Haodong Guo ◽  
Gencai Chen
Keyword(s):  
Topic Model ◽  
Complex Activity ◽  
Activity Representation ◽  
Level Fusion

A Novel Model for Human Activity Representation and Classification Based on Trajectory

2014 ◽  
Vol 1044-1045 ◽  
pp. 1007-1010
Author(s):  
Wei Xing Zhu ◽  
Wei Guang Xu ◽  
Guo Lin Hou ◽  
Jun You
Keyword(s):  
Human Activity ◽  
Kernel Function ◽  
Svm Classifier ◽  
Motion Trajectories ◽  
Euclidian Distance ◽  
Stochastic Grammar ◽  
Activity Representation ◽  
Novel Model

In this paper, a novel model, HDP-HMM-SCFG is proposed for representing and classifying activities based on motion trajectories. In the model, activities are represented by stochastic grammar using trajectory, where trajectory segments are considered as observations emitted by the grammar terminals attached with HMMs. Then, by replacing the Euclidian distance in the kernel function of Gaussian radial radix with EMD-DTW, which is proposed to measure the distance between two trajectories by integrating the pros. of both EMD and DTW, multi-class SVM classifier is constructed. Experiments on ASL dataset are carried on to validate our approach.

Effect of autumn feeding on dynamics of rectal congestion with excrement in carpathian breed honey bees

2020 ◽  
pp. 26-28
Author(s):  
Olesya V Strelbitskaya ◽  
◽  
Vladimir I. Kravchenko ◽  
Keyword(s):  
Point Of View ◽  
Theory And Practice ◽  
Complex Activity ◽  
Important Indicator ◽  
Apple Cider ◽  
Sugar Syrup ◽  
Main Indicator ◽  
Biological Laws ◽  
Honey Solution ◽  
Bee Colonies

Basic biological laws that govern the life of the bee family, as well as considering it as a whole organism, are necessary instruments for implementing effective methods of beekeeping and increasing the productivity of the industry. The study of the exterior features of bees must be carried out from different points of view for the concept of the complex activity of the bee family and in order to recommend methods for improving the preparation of bees for winter. Study of the mass of working bees and their rectum began to be used as the main indicator that affects the nature of the preparation of bee individuals for wintering. From the point of view of both theory and practice, filling the rectum with excrement in the autumn period will be an important indicator of an effective wintering in terms of preserving and further developing bee colonies. Effect of two kinds of liquid top feeding acidified with apple cider vinegar on the rectum congestion with excrement in working bees in the autumn, and the safety of bee colonies after winter was discussed in the article. The results of the indicators of the mass of working bees and intestinal mass when feeding two types of top dressing in the form of sugar syrup and honey solution with the addition of apple cider vinegar for the purpose of acidification are presented. The dynamics of rectal congestion in this group of bees is less compared to the group of bees receiving food in the form of sugar syrup. After wintering, during the spring audit, it was found that the safety of bees fed the autumn top dressing in the form of a honey solution with the addition of apple cider vinegar was 95% compared to bee families that received sugar syrup, the safety was 80.5%, with the detection of liquid excrement on the walls of hives and honeycombs

The interrelation of neurophysiological, psychological, and biochemical indicators in patients with occupational chronic mercury intoxication suffering from insomnia

2020 ◽  
Vol 60 (12) ◽  
pp. 904-910
Author(s):  
Elena V. Katamanova ◽  
Elena N. Korchuganova ◽  
Natalia V. Slivnitsyna ◽  
Irina V. Kudaeva ◽  
Oleg L. Lakhman
Keyword(s):  
Cerebral Cortex ◽  
Work Experience ◽  
Sleep Time ◽  
Serotonin Level ◽  
Complex Activity ◽  
Equivalent Dipole ◽  
Mercury Intoxication ◽  
Psychological Examination ◽  
Reticular System ◽  
Chronic Mercury Intoxication

Introduction. Despite the apparent connection of the existing neurological disorders and changes in the psycho-emotional sphere with sleep disorders in patients with chronic mercury intoxication (CRI), these relationships remain the least studied in the clinic neurointoxications. The study aimed to establish a connection between neurophysiological, biochemical, and psychopathological indicators in patients with occupational chronic mercury intoxication and insomnia. Materials and methods. Thirty-six patients took part in the examination in the remote period of CRI. The average age of patients in this group was 50.7±1.05 years, with an average work experience of 14.7±1.05. The authors carried out a psychological examination to determine the levels of depression, anxiety, asthenic state, computed electroencephalography (EEG), cognitive evoked potentials (CEP), polysomnography, the level of neurotransmitters. Results. The study showed that asthenization, when exposed to mercury, occurs due to a decrease in the limbic-hypothalamo-reticular complex activity (the presence of equivalent dipole sources of pathological activity in the area of diencephalic formations (thalamus, hypothalamus) in 56.2±5.6% of cases. The study showed a decrease in activity cerebral cortex, confirmed by weakening the coherent connections of the α-range in the occipital, central and frontal leads according to the data of coherent EEG analysis and changes on the part of the CEP. There was a direct correlation between the level of total sleep time and the serotonin level (rs=0.45), an inverse relationship between the level of depression and histamine level (rs=-0.56). Conclusion. The studies carried out to make it possible to establish the mechanisms of insomnia disorders in chronic mercury intoxication, which cause a weakening of the tone of the cerebral cortex and changes in neurotransmitter metabolism, as well as disorders of the reticular system with limbic structures. The study showed a close direct relationship between neurophysiological, psychological, and biochemical parameters in implementing insomnia in patients with chronic mercury intoxication.

El debriefing, aprendizaje reflexivo en la simulación interprofesional

2019 ◽  
Vol 62 (0) ◽  
pp. 45-53
Author(s):  
Hugo E. Olvera ◽  
Argimira Vianey Barona Nuñez ◽  
Laura S. Hernández Gutiérrez ◽  
Erick López León
Keyword(s):  
Clinical Practice ◽  
Communication Skills ◽  
Learning Objectives ◽  
Complex Activity ◽  
Learning Space ◽  
Daily Lives ◽  
Reaction Phase ◽  
Analysis Phase ◽  
Simulation Scenario ◽  
Basic Standards

In the field of interprofessional simulation, an important element for achieving the stated objectives of the simulation scenario is the debriefing. The debriefing is a complex activity that requires certain skills, experience and knowledge from the facilitator or facilitators, who are known as debriefer/s. Their function is to make the participants reflect on the reasons for their actions, their decisions, and how they acted as a team or individually. Its purpose is the acquisition of a significant learning (achieving the learning objectives) that can subsequently be applied in their daily lives. The interprofessional debriefing styles are varied, but basically its structure integrates: a reaction phase, an analysis phase and an application phase; keeping in mind that the basic standards must be maintained when carrying out a debriefing: time, the construction of a safe learning space, identification, and the closure of knowledge gaps. The advantages of performing an interprofessional debriefing goes beyond the objectives of the simulation, since it favors the acquisition of effective communication skills, teamwork, leadership, the notion of error, etc., which can later be applied in the daily clinical practice.

scholarly journals Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1685
Author(s):  
Sakorn Mekruksavanich ◽  
Anuchit Jitpattanakul
Keyword(s):  
Neural Networks ◽  
Activity Recognition ◽  
Human Activities ◽  
Recognition Performance ◽  
Confusion Matrix ◽  
Experimental Studies ◽  
Industrial Applications ◽  
Sensor Data ◽  
Complex Activity ◽  
Activity Data

Sensor-based human activity recognition (S-HAR) has become an important and high-impact topic of research within human-centered computing. In the last decade, successful applications of S-HAR have been presented through fruitful academic research and industrial applications, including for healthcare monitoring, smart home controlling, and daily sport tracking. However, the growing requirements of many current applications for recognizing complex human activities (CHA) have begun to attract the attention of the HAR research field when compared with simple human activities (SHA). S-HAR has shown that deep learning (DL), a type of machine learning based on complicated artificial neural networks, has a significant degree of recognition efficiency. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are two different types of DL methods that have been successfully applied to the S-HAR challenge in recent years. In this paper, we focused on four RNN-based DL models (LSTMs, BiLSTMs, GRUs, and BiGRUs) that performed complex activity recognition tasks. The efficiency of four hybrid DL models that combine convolutional layers with the efficient RNN-based models was also studied. Experimental studies on the UTwente dataset demonstrated that the suggested hybrid RNN-based models achieved a high level of recognition performance along with a variety of performance indicators, including accuracy, F1-score, and confusion matrix. The experimental results show that the hybrid DL model called CNN-BiGRU outperformed the other DL models with a high accuracy of 98.89% when using only complex activity data. Moreover, the CNN-BiGRU model also achieved the highest recognition performance in other scenarios (99.44% by using only simple activity data and 98.78% with a combination of simple and complex activities).

Sign in / Sign up

Export Citation Format

Share Document