An Enhanced Deep Learning Approach for Smartphone-Based Human Activity Recognition in IoHT

Soni, Vaibhav; Jaiswal, Shashank; Semwal, Vijay Bhaskar; Roy, Bholanath; Choubey, Dilip Kumar; Mallick, Dheeresh K.

doi:10.1007/978-981-19-5868-7_37

Cited by 2 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most common deep learning approaches are Recurrent Neural Networks (RNN) [26], Deep belief Networks (DBN) [27], convolutional neural networks (CNNs) [28], and deep forward neural networks. A DL architecture consists of bidirectional gated recurrent unit (BiGRU) and 2 convolutional layers was proposed for HAR in internet of healthcare things environment by using smartphone's sensors [29].…”

Section: Introductionmentioning

confidence: 99%

Multi-head CNN-based activity recognition and its application on chest-mounted sensor-belt

Verma,

Tyagi,

Aneja

2024

Eng. Res. Express

View full text Add to dashboard Cite

In recent years, a great deal of research has been done on the identification, monitoring, and classification of human activities. Human activity recognition (HAR) is a term commonly used to describe the automatic identification of physical activities. For activity recognition, there are primarily vision-based and sensor-based methods available. The computer vision-based method is generally effective in lab settings, but because of clutter, fluctuating light levels, and contrast, it may not perform well in real-world scenarios. Continuous monitoring and analysis of physiological signals obtained from heterogeneous sensors attached to an individual's body is required to realise sensor-based HAR systems. Most of the previous research in human activity recognition (HAR) is biased along with feature engineering and pre-processing which requires a good amount of domain knowledge. Application-specific modelling and time-taking methods are involved in these approaches. In this work, the multi-head convolutional neural network-based human activity recognition framework is proposed where automatic feature extraction and classification are involved in the form of an end-to-end classification approach. Experiments of this approach are performed by taking raw wearable sensor data with few pre-processing steps and without the involvement of a handcrafted feature extraction technique. 99.23% and 93.55% accuracy are obtained on the WISDM and UCI-HAR datasets which denoted the much improvement in the assessment of HAR over other similar approaches. The model is also tested on locally collected data from a chest mounted belt with fabric sensors and an accuracy of 87.14% has been achieved on that data. 

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-head CNN-based activity recognition and its application on chest-mounted sensor-belt

Verma,

Tyagi,

Aneja

2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

Activity Recognition and IoT-Based Analysis Using Time Series and CNN

Beemkumar

Gupta²,

Bhardwaj

et al. 2023

Advances in Systems Analysis, Software Engineering, and High Performance Computing

View full text Add to dashboard Cite

Using time series data obtained from accelerometer and gyroscope sensors on an iPhone 6s, the authors address the topic of human activity and attribute detection. The collection contains time series data from 24 subjects who completed six activities in 15 trials. The aim is to appropriately identify the six activities using machine learning techniques. The usage of a convolutional neural network (CNN) for the categorization of human activity and attribute identification data obtained from accelerometer and gyroscope sensors on an iPhone 6s is proposed in this research. The collection contains time series data from 24 subjects who completed six activities in 15 trials. The study begins by pre-processing the data by transforming the folders into class labels and plotting the time series data. The time-series data is made up of multivariate data from both the accelerometer and gyroscope sensors, totaling 12 characteristics. The accelerometer sums up two acceleration vectors, gravity, and user acceleration, which may be distinguished using core motion tracking technology.

show abstract

An Enhanced Deep Learning Approach for Smartphone-Based Human Activity Recognition in IoHT

Cited by 2 publications

References 27 publications

Multi-head CNN-based activity recognition and its application on chest-mounted sensor-belt

Multi-head CNN-based activity recognition and its application on chest-mounted sensor-belt

Activity Recognition and IoT-Based Analysis Using Time Series and CNN

Contact Info

Product

Resources

About