scholarly journals Daily Human Activities Recognition Using Heterogeneous Sensors from Smartphones

2017 ◽  
Vol 111 ◽  
pp. 323-328 ◽  
Author(s):  
Minh-Son Dao ◽  
Tuan-Anh Nguyen-Gia ◽  
Van-Cuong Mai
Keyword(s):  
Human Activities ◽  
Heterogeneous Sensors ◽  
Human Activities Recognition

scholarly journals A Deep Learning Approach for Human Activities Recognition From Multimodal Sensing Devices

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 179028-179038
Author(s):  
Isibor Kennedy Ihianle ◽  
Augustine O. Nwajana ◽  
Solomon Henry Ebenuwa ◽  
Richard I. Otuka ◽  
Kayode Owa ◽  
...  
Keyword(s):  
Deep Learning ◽  
Human Activities ◽  
Learning Approach ◽  
Multimodal Sensing ◽  
Human Activities Recognition

Critical Behavior Monitoring for Children with Special Needs in Preventing Physical Injury Using Kinect

2015 ◽  
pp. 211-249
Author(s):  
Ong Chin Ann ◽  
Lau Bee Theng ◽  
Henry Lee Seldon ◽  
Fernando Anddie Putra
Keyword(s):  
Special Needs ◽  
Critical Behavior ◽  
Human Activities ◽  
Autism Spectrum ◽  
Physical Injury ◽  
Children With Special Needs ◽  
Kinect Sensor ◽  
Monitoring Model ◽  
Behavior Monitoring ◽  
Human Activities Recognition

This research studies ways to prevent physical injury for children with special needs, or specifically children with Autism Spectrum Disorder (ASD). The prevention is achievable by monitoring child behavior in the classroom from time to time. A Critical Behavior Monitoring model was developed for this purpose. The model is integrated with a Kinect sensor (by Microsoft) to process the signal acquired for human activities recognition. Currently, the model manages to identify 17 different human activities and notify parents or teachers via SMS and/or email if any unusual or critical activities are detected (i.e. falling down or asking for help). This will ensure immediate action is taken to prevent injuries or the situation from getting worse.

scholarly journals Extract the Relational Information of Static Features and Motion Features for Human Activities Recognition in Videos

2016 ◽  
Vol 2016 ◽  
pp. 1-7 ◽  
Author(s):  
Li Yao
Keyword(s):  
Bipartite Graph ◽  
Human Activities ◽  
Recognition Task ◽  
Small Dimension ◽  
Relational Information ◽  
Kl Divergence ◽  
Motion Features ◽  
Projective Function ◽  
Human Activities Recognition ◽  
The Relationship

Both static features and motion features have shown promising performance in human activities recognition task. However, the information included in these features is insufficient for complex human activities. In this paper, we propose extracting relational information of static features and motion features for human activities recognition. The videos are represented by a classical Bag-of-Word (BoW) model which is useful in many works. To get a compact and discriminative codebook with small dimension, we employ the divisive algorithm based on KL-divergence to reconstruct the codebook. After that, to further capture strong relational information, we construct a bipartite graph to model the relationship between words of different feature set. Then we use ak-way partition to create a new codebook in which similar words are getting together. With this new codebook, videos can be represented by a new BoW vector with strong relational information. Moreover, we propose a method to compute new clusters from the divisive algorithm’s projective function. We test our work on the several datasets and obtain very promising results.

Sign in / Sign up

Export Citation Format

Share Document