A Framework of Combining Short-Term Spatial/Frequency Feature Extraction and Long-Term IndRNN for Activity Recognition †

  title={A Framework of Combining Short-Term Spatial/Frequency Feature Extraction and Long-Term IndRNN for Activity Recognition †},
  author={Beidi Zhao and Shuai Li and Yanbo Gao and Chuankun Li and Wanqing Li},
  journal={Sensors (Basel, Switzerland)},
Smartphone-sensors-based human activity recognition is attracting increasing interest due to the popularization of smartphones. It is a difficult long-range temporal recognition problem, especially with large intraclass distances such as carrying smartphones at different locations and small interclass distances such as taking a train or subway. To address this problem, we propose a new framework of combining short-term spatial/frequency feature extraction and a long-term independently recurrent… 

Variable Rate Independently Recurrent Neural Network (IndRNN) for Action Recognition

Experiments on skeleton-based action recognition show that the proposed variable rate IndRNN network can significantly improve the performance over the RNN models under the conventional training strategies.

A Deep Attention Model for Action Recognition from Skeleton Data

This paper presents a new IndRNN-based deep attention model, termed DA-IndRNN, for skeleton-based action recognition to effectively model the fact that different joints are usually of different

Modeling Accurate Human Activity Recognition for Embedded Devices Using Multi-level Distillation

A plug-and-play HAR modeling pipeline with multi-level distillation to build deep convolutional HAR models with native support of embedded devices and can compress the models with minor performance loss in an equal compression rate than other state-of-the-art knowledge distillation methods on seven public datasets.

Human Action Recognition: A Paradigm of Best Deep Learning Features Selection and Serial Based Extended Fusion

A DL-based design is proposed for human action recognition which achieved accuracies of 99.3%, 97.4%, 99.8%, and 99.9%, respectively, and the feature selection step performed better in terms of computational time compared with the state-of-the-art.

A systematic review of smartphone-based human activity recognition methods for health research

It is concluded that smartphones are well-suited for HAR research in the health sciences and future studies should focus on improving the quality of collected data, address missing data, incorporate more diverse participants and activities, relax requirements about phone placement, and share the source code of the implemented methods and algorithms.

Analysis of Art Classroom Teaching Behavior Based on Intelligent Image Recognition

This study attempts to identify and analyze the class behavior and validate the effectiveness of the collaborative classifiers proposed in this paper to build an intellectual classroom.

Dense CNN and IndRNN for the Sussex-Huawei Locomotion-Transportation Recognition Challenge

A framework of deep learning including one-dimensional (1D) Dense CNN and Dense IndRNN networks to explore short and long-term spatial temporal information is proposed and the decision fusion is utilized to improve performance.

Design of Artistic Creation Style ExtractionModel Based on Color Feature Data

According to the equilibrium configuration results, the fuzzy clustering method is used to extract the color style of works of art to improve the style extraction and extraction identification ability of work of art.



IndRNN based long-term temporal recognition in the spatial and frequency domain

This paper targets the SHL recognition challenge, which focuses on the location-independent and user-independent activity recognition using smartphone sensors, and proposes a new approach, an Independently Recurrent Neural Network (IndRNN) based long-term temporal activity recognition with spatial and frequency domain features.

Application of IndRNN for human activity recognition: the Sussex-Huawei locomotion-transportation challenge

A human activity recognition method using Independently Recurrent Neural Network (IndRNN) on the spectrum for the Sussex-Huawei Locomotion-Transportation (SHL) recognition challenge 2019 and achieved 82.6% accuracy of validation in hand position.

Smartphone-sensors Based Activity Recognition Using IndRNN

The recently proposed Independently Recurrent Neural Network is used to process data of different lengths in order to capture the temporal patterns at different granularities and has been applied and submitted to SHL recognition challenge as "UOW_AMRL".

Convolutional Neural Networks for human activity recognition using mobile sensors

An approach to automatically extract discriminative features for activity recognition based on Convolutional Neural Networks, which can capture local dependency and scale invariance of a signal as it has been shown in speech recognition and image recognition domains is proposed.

Human activity recognition with smartphone sensors using deep learning neural networks

Deep Dilation on Multimodality Time Series for Human Activity Recognition

A novel recurrent model to learn the temporal dependencies at different time scales is presented, inspired by the idea of dilation operation, and achieves a higher classification performance than the state-of-the-art methods.

Tackling the SHL recognition challenge with phone position detection and nearest neighbour smoothing

The solution consists of detecting the phone wearing position, selecting training data to create a user and position-specific classification model, and "smoothing" the predictions by identifying groups of similar data frames in the test set, which probably belong to the same class.

Enabling Reproducible Research in Sensor-Based Transportation Mode Recognition With the Sussex-Huawei Dataset

A systematic study of the relevance of statistical and frequency features based on the information theoretical criteria to inform recognition systems and systematically reports the reference performance obtained on all the identified recognition scenarios using a machine-learning recognition pipeline.

Combining LSTM and CNN for mode of transportation classification from smartphone sensors

A deep-learning-based algorithm is presented that combines long-short-term-memory (LSTM) layer and convolutional layer to classify eight different modes of transportation on the Sussex-Huawei Locomotion-Transportation (SHL) dataset.