Fusing wearable and remote sensing data streams by fast incremental learning with swarm decision table for human activity recognition

Li, Tengyue; Fong, Simon; Wong, Kelvin Kian Loong; Wu, Ying; Yang, Xin‐She; Li, Xuqi

doi:10.1016/j.inffus.2020.02.001

Cited by 44 publications

(17 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent studies have attempted to improve further recognition rate of DNNs in MVHAR by training the model with multiple modalities [21,34,36,[43][44][45], multi-task [24], and crossview [41] techniques. Multimodal approaches combine 2D-RGB images with higher-level inputs, such as optical flow [21,34], depth information [43], radar sensors [45], and skeleton features [36,44]; the model consisted multiple streams that proceeded with different type of modalities. Multi-task assumed the model could produce informative latent variables by PLOS ONE simultaneously learning different but related tasks: predicting human activities from multiview inputs and the inputs' view-index [24].…”

Section: Related Workmentioning

confidence: 99%

A deep neural network model for multi-view human activity recognition

2022

View full text Add to dashboard Cite

Multiple cameras are used to resolve occlusion problem that often occur in single-view human activity recognition. Based on the success of learning representation with deep neural networks (DNNs), recent works have proposed DNNs models to estimate human activity from multi-view inputs. However, currently available datasets are inadequate in training DNNs model to obtain high accuracy rate. Against such an issue, this study presents a DNNs model, trained by employing transfer learning and shared-weight techniques, to classify human activity from multiple cameras. The model comprised pre-trained convolutional neural networks (CNNs), attention layers, long short-term memory networks with residual learning (LSTMRes), and Softmax layers. The experimental results suggested that the proposed model could achieve a promising performance on challenging MVHAR datasets: IXMAS (97.27%) and i3DPost (96.87%). A competitive recognition rate was also observed in online classification.

show abstract

Section: Related Workmentioning

confidence: 99%

A deep neural network model for multi-view human activity recognition

2022

View full text Add to dashboard Cite

show abstract

“…Wearables approaches are proposed in [10,24,46,51,52,53,54,55,56,57,58,59] to obtain occupancy information as a product of tasks completed by other systems which can be used to track the occupancy location. ML model can obtain signal intensity from statically positioned beacons in a target space to obtain a fine-grained occupant location and achieve the location accuracy of five meters.…”

Section: Literature Reviewmentioning

confidence: 99%

Comparative Analysis of Machine Learning Methods for Non-Intrusive Indoor Occupancy Detection and Estimation

Aliero¹,

Pasha²,

Toosi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Occupancy-driven application research has been active research for a decade that focuses on improving or replacing new building infrastructure to improve building energy efficiency. Existing approaches for HVAC energy saving are putting more emphasis on occupancy detection, estimation, and localization to trade-off between energy consumption and thermal comfort satisfaction. In a non-intrusive approach, various sensors, actuators, and analytic data methods are commonly used to process data from occupant surroundings and trigger appropriate action to achieve the task. However, the performance of the non-intrusive approach reported in the literature is relatively poor due to the lack of quality of dataset used in model training and expropriate choice of machine learning model. This study proposed a non-intrusive approach that to improve the collection and quality of dataset using data pre-processing. The study collected a training dataset using various sensors installed in the building and developed a model using five machine learning models to determine occupant’s presence and estimate their number in the building. The proposed solution is tested in the living room with a prototype system integrated with various sensors designed to obtain occupant surrounding environmental datasets. The model’s prediction results obtained indicate that it is possible for the proposed solution to obtain data, process, and predict the occupant number with high accuracy (73.6 -99.7% using random forest).

show abstract

“…The test results have been shown that HAR accuracy was improved when a wearing sensor was utilized simultaneously. Fast incremental learning [14] enhances the classification performance by the empirical data feeds, and it improves the performance of the learning approach to around five times. However, it does not benchmark the performance using several machine learning, and various angles of the field of views from aerial are not included.…”

Section: Related Workmentioning

confidence: 99%

Automated Human Activity Recognition by Colliding Bodies Optimization-based Optimal Feature Selection with Recurrent Neural Network (RNN)

Khatiwada¹,

Subedi²,

Chatterjee³

et al. 2020

Preprint

View full text Add to dashboard Cite

— In a smart healthcare system," Human Activity Recognition (HAR)" is considered as an efficient approach in pervasive computing from activity sensor readings. The "Ambient Assisted Living (AAL)" in the home or community helps the people to provide independent care and enhanced living quality. However, many AAL models are restricted to multiple factors that include both the computational cost and system complexity. Moreover, the HAR concept has more relevance because of its applications, such as content-based video search, sports play analysis, crowd behavior prediction systems, patient monitoring systems, and surveillance systems. This paper attempts to implement the HAR system using a popular deep learning algorithm, namely "Recurrent Neural Network (RNN)" with the activity data collected from smart activity sensors over time, and it is publicly available in the "UC Irvine Machine Learning Repository (UCI)". The proposed model involves three processes: (1) data collection, (b) optimal feature learning, and (c) activity recognition. The data gathered from the benchmark repository was initially subjected to optimal feature selection that helped to select the most significant features. The proposed optimal feature selection method is based on a new meta-heuristic algorithm called "Colliding Bodies Optimization (CBO)". An objective function derived from the recognition accuracy has been used for accomplishing the optimal feature selection. The proposed model on the concerned benchmark dataset outperformed the conventional models with enhanced performance.

show abstract

Fusing wearable and remote sensing data streams by fast incremental learning with swarm decision table for human activity recognition

Cited by 44 publications

References 15 publications

A deep neural network model for multi-view human activity recognition

A deep neural network model for multi-view human activity recognition

Comparative Analysis of Machine Learning Methods for Non-Intrusive Indoor Occupancy Detection and Estimation

Automated Human Activity Recognition by Colliding Bodies Optimization-based Optimal Feature Selection with Recurrent Neural Network (RNN)

Contact Info

Product

Resources

About