Human activity recognition using LZW-Coded Probabilistic Finite State Automata

Abstract

Human activity recognition has become an increasingly important field of research with many practical applications related to health care and leisure activities. The accessibility of inexpensive portable sensors, such as accelerometers, allows for a widespread use of this technology for both commercial and personal activity recognition. This paper develops a novel feature extraction approach to human activity recognition through the development of the Lempel-Ziv-Welch Coded Probabilistic Finite State Automata (LZW-Coded PFSA) to classify activities such as walking, jumping, running, waist rotations, and shoulder rotations. The PFSA reveal the underlying architecture of a given activity and classify it without making any a priori assumptions by inferring patterns from the sensor measurements. LZW-Coded PFSA select the optimal variable length state from the time-series data and compress it into class-separable state transition matrices π. This algorithm is robust to subject biases and is shown to be effective with a correct classification rate of 95.63%.

Improving Resilience of Behaviometric Based Continuous Authentication with Multiple Accelerometers

“…We will use data where the activity is known beforehand. This is reasonable because of high accuracies achieved for activity recognition in other work [24]. Based on our previous research in the field of activity recognition [18], our hypothesis is that we can obtain even higher accuracies for our use case and setting, because our solution does not rely on a fine-grained distinction between activities, as discussed in section 4.4.…”

“…(2) explicitly exploit gait cycles to extract features: their first step is always to discover the gait cycle and extract it from the data sample. While the first assumption is reasonable for completely different activities (Wilson et al [24] achieved an activity classification accuracy of 95%), this is not valid for the latter. It is useless to extract gait cycles for sitting, and not straightforward to find patterns similar to gait cycles for activities like rowing, going to the gym or cycling.…”

Deep Learning for Sensor-Based Rehabilitation Exercise Recognition and Evaluation

“…Conventionally, features can be represented by the transition probabilities between states using the probabilistic finite state automata (PFSA) [ 32 ]. However, the computational complexity of calculating the transition probabilities is high.…”

“…The Lempel–Ziv–Welch (LZW)-coded PFSA [ 32 ] uses the LZW coding to symbolize sensor data and the PFSA to compute the state transition probabilities between hidden states. It consists of three steps: quantization, LZW coding, and PFSA construction.…”

“…The flowchart is shown in Figure 1 . We built an S-CNN to model the transition probabilities in the LZW-coded PFSA [ 32 ] to extract discriminative features. We explain the LZW-coded PFSA method first and then how to combine the state transition probabilities into the CNN model as an S-CNN.…”