An Energy-Efficient Method for Human Activity Recognition with Segment-Level Change Detection and Deep Learning

Abstract

Human activity recognition (HAR), which is important in context awareness services, needs to occur continuously in daily life, owing to which an energy-efficient method is needed. However, because human activities have a longer cycle than HAR methods, which have analysis cycles of a few seconds, continuous classification of human activities using these methods is computationally and energy inefficient. Therefore, we propose segment-level change detection to identify activity change with very low computational complexity. Additionally, a fully convolutional network (FCN) with a high recognition rate is used to classify the activity only when activity change occurs. We compared the accuracy and energy consumption of the proposed method with that of a method based on a convolutional neural network (CNN) by using a public dataset on different embedded platforms. The experimental results showed that, although the recognition rate of the proposed FCN model is similar to that of the CNN model, the former requires only 10% of the network parameters of the CNN model. In addition, our experiments to measure the energy consumption on the embedded platforms showed that the proposed method uses as much as 6.5 times less energy than the CNN-based method when only HAR energy consumption is compared.

Accelerometer-Based Human Activity Recognition for Patient Monitoring Using a Deep Neural Network

“…These are convolutional neural networks (CNNs), a type of recurrent neural networks called long short-term memory (LSTM) and a combination of both. CNNs have been applied to sensor data for HAR with outstanding performances [ 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 ]. Previous studies proposed augmenting the feature vector extracted by a CNN with several statistical features [ 33 , 34 ].…”

An Energy-Efficient Human Activity Recognition System Based on Smartphones

“…Given the size of our HAR tasks, we simplify AlexNet by cycling fine-tuning to form our DL-HAR model. The final net structure is given in Table 1 Refer to [41], we use a full-connected convolutional net (FCN) structure, which replace the full-connected layers with global average pooling (GAP) layers. The GAP contains less parameters that can lighten the net structure.…”

Sport-Related Human Activity Detection and Recognition Using a Smartwatch

“…This watch can record triaxial acceleration and triaxial angular velocity (as shown in the middle of the right part of Figure 2), which are used by our algorithm for HADR. The sampling frequency of the Pacewear watch is 50 Hz, which is the sampling rate often used in HAR studies [1,5].…”

“…The subsequent classifier is then used to classify these activities by using the information in these segments. Many researchers [2,3,4,5] have used this segmentation method to identify activities with strong periodicity and a single motion state because, after segmentation, each segment contains a meaningful motion state. However, many sports are characterized by complex motion states and non-periodicity.…”