Principal coefficient encoding for subject-independent human activity analysis

Abstract

Tracking human physical activity using smartphones is an emerging trend in healthcare monitoring and healthy lifestyle management. Neural networks are broadly used to analyze the inertial data of activity recognition. Inspired by the autoencoder neural networks, we propose a layer-wise network, namely principal coefficient encoder model (PCEM). Unlike the vanilla neural networks which apply random weight initialization andback-propagation for parameter updating, an optimized weight initialization is implemented in PCEM via principal coefficient learning. This principal coefficient encoding allows rapid data learning with no back-propagation intervention and no gigantic hyperparameter tuning. In PCEM, the most principal coefficients of the training data are determined to be the network weights. Two hidden layers with principal coefficient encoding are stacked in PCEM for the sake of deep architecture design. The performance of PCEM is evaluated based on a subject-independent protocol where training and testing samples are from different users, with no overlapping subjects in between the training and testing sets. This subject-independent protocol can better assess the generalization of the model to new data. Experimental results exhibit that PCEM outperforms certain state-of-the-art machine learning and deep learning models, including convolutional neural network, and deep belief network. PCEM can achieve ~97% accuracy in subject-independent human activity analysis.

Activity recognition based on spatio-temporal features with transfer learning

“…Han et al [21] introduced networks influenced by autoencoders. A principal coefficient encoder model (PCEM) was instrumental.…”

Chicken tracking for location mapping of lameness chickens using YOLOv8 and deep learning-based tracking algorithm

“…This allows for early detection of any disease-related symptoms in the chicken [21]. The object detection process based on deep learning has many benefits that can be used for many things, such as traffic light detection using faster-CNN [22], detection of switchgear removal errors using CNN-long short-term memory (LSTM) [23], you only look once, version 5 (YOLOv5) for image and video-based criminal detection [24], you only look once, version 3 (YOLOv3)-based distance detection in public spaces during COVID-19 [25], classifying yoga poses using CNN [26], analyzing human activity using CNN [27], designing a robot design for assisting the elderly using CNN [28], estimating the age of pedestrians using CNN [29], carrying out automatic surveillance at night using CNN [30], identifying human emotions for assistant robots using CNN [31], deep learning can also be used for sound event detection using CNN [32].…”

Human activity recognition method using joint deep learning and acceleration signal

“…The second module recognized the activities performed in each window using a CNN model. The calculations performed on the CNN parameters required 77.06 MB of memory [23]- [25].…”