Binary Relevance Model for Activity Recognition in Home Environment using Ambient Sensors

Jethanandani, Manan; Perumal, Thinagaran; Liaw, Yuh-Ching; Chang, Jieh-Ren; Sharma, Abhishek; Bao, Yipeng

doi:10.1109/icce-tw46550.2019.8991837

Cited by 6 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Decision trees were used as the base classifier and label combination was employed for the problem transformation. Binary relevance has been proposed in the literature for multilabel HAR [ 33 ]. The results were competitive with approaches transforming the problem into a classic classification problem.…”

Section: Related Workmentioning

confidence: 99%

Multilabel Classification Methods for Human Activity Recognition: A Comparison of Algorithms

Lentzas

Dalagdi

Vrakas

2022

Sensors

View full text Add to dashboard Cite

As the world’s population is aging, and since access to ambient sensors has become easier over the past years, activity recognition in smart home installations has gained increased scientific interest. The majority of published papers in the literature focus on single-resident activity recognition. While this is an important area, especially when focusing on elderly people living alone, multi-resident activity recognition has potentially more applications in smart homes. Activity recognition for multiple residents acting concurrently can be treated as a multilabel classification problem (MLC). In this study, an experimental comparison between different MLC algorithms is attempted. Three different techniques were implemented: RAkELd, classifier chains, and binary relevance. These methods are evaluated using the ARAS and CASAS public datasets. Results obtained from experiments have shown that using MLC can recognize activities performed by multiple people with high accuracy. While RAkELd had the best performance, the rest of the methods had on-par results.

show abstract

Section: Related Workmentioning

confidence: 99%

Multilabel Classification Methods for Human Activity Recognition: A Comparison of Algorithms

Lentzas

Dalagdi

Vrakas

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…These features are: mean value, standard deviation, minimum value, standard error of the mean (sem), the first central moment (deviation from mean), interquartile range (IQR), Median Absolute Deviation (MAD), median, maximum value, variance, skewness, the energy of the signal, kurtosis, and vector norm. Additionally, the first discrete difference of each time series for the fourteen features is calculated by (1).…”

Section: F Pre-processingmentioning

confidence: 99%

“…Human Activity Recognition (HAR) in smart homes is receiving increasing attention due to a wide range of potential applications, including physical activity recognition and intelligent assistance for elderly people and people with cognitive disorders [1]. In smart homes, data from various sensors may be fused to create models that recognise the activities of residents.…”

Section: Introductionmentioning

confidence: 99%

Classifying Imbalanced Multi-modal Sensor Data for Human Activity Recognition in a Smart Home using Deep Learning

Alani

Cosma

Taherkhani

2020

2020 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

In smart homes, data generated from real-time sensors for human activity recognition is complex, noisy and imbalanced. It is a significant challenge to create machine learning models that can classify activities which are not as commonly occurring as other activities. Machine learning models designed to classify imbalanced data are biased towards learning the more commonly occurring classes. Such learning bias occurs naturally, since the models better learn classes which contain more records. This paper examines whether fusing real-world imbalanced multi-modal sensor data improves classification results as opposed to using unimodal data; and compares deep learning approaches to dealing with imbalanced multi-modal sensor data when using various resampling methods and deep learning models. Experiments were carried out using a large multi-modal sensor dataset generated from the Sensor Platform for HEalthcare in a Residential Environment (SPHERE). The data comprises 16104 samples, where each sample comprises 5608 features and belongs to one of 20 activities (classes). Experimental results using SPHERE demonstrate the challenges of dealing with imbalanced multi-modal data and highlight the importance of having a suitable number of samples within each class for sufficiently training and testing deep learning models. Furthermore, the results revealed that when fusing the data and using the Synthetic Minority Oversampling Technique (SMOTE) to correct class imbalance, CNN-LSTM achieved the highest classification accuracy of 93.67% followed by CNN, 93.55%, and LSTM, i.e. 92.98%.

show abstract

Internet of Things (IoT) Based Activity Recognition Strategies in Smart Homes: A Review

et al. 2022

View full text Add to dashboard Cite

Binary Relevance Model for Activity Recognition in Home Environment using Ambient Sensors

Cited by 6 publications

References 4 publications

Multilabel Classification Methods for Human Activity Recognition: A Comparison of Algorithms

Multilabel Classification Methods for Human Activity Recognition: A Comparison of Algorithms

Classifying Imbalanced Multi-modal Sensor Data for Human Activity Recognition in a Smart Home using Deep Learning

Internet of Things (IoT) Based Activity Recognition Strategies in Smart Homes: A Review

Contact Info

Product

Resources

About