Long Short-Term Memory (LSTM)-Based Dog Activity Detection Using Accelerometer and Gyroscope

Abstract

Dog owners are extremely driven to comprehend the activity and health of their dogs and to keep tabs on their well-being. Dogs’ health and well-being, whether as household pets or service animals, are critical issues that are addressed seriously for moral, psychological, and economical reasons. Evaluations of a dog’s welfare depend on quantitative assessments of the frequency and variability of certain behavioral features, which are sometimes challenging to make in a dog’s normal environment. While it is challenging to obtain dogs’ behavioral patterns, it is nearly impossible to directly identify one distinct behavior when they are roaming around at will. Applications for automatic pet monitoring include real-time surveillance and monitoring systems that accurately identify pets using the most recent methods for the classification of pet activities. The suggested method makes use of a long short-term memory (LSTM)-based method to detect and classify the activities of dogs based on sensor data (i.e., accelerometer and gyroscope). The goal of this study is to use wearable sensor data and examine the activities of dogs using recurrent neural network (RNN) technology. We considered 10 pet behaviors, which include walking, sitting, down, staying, feeding, sideways, leaping, running, shaking, and nose work. As dog activity has a wider diversity, experimental work is performed on the multi-layer LSTM framework to have a positive influence on performance. In this study, data were collected from 10 dogs of various ages, sexes, breeds, and sizes in a safe setting. Data preprocessing and data synchronization were performed after the collection of data. The LSTM model was trained using the preprocessed data and the model’s performance was evaluated by the test dataset. The model showed good accuracy and high performance for the detection of 10 activities of dogs. This model will be helpful for the real-time monitoring of dogs’ activity, thus improving the well-being of dogs.

Unsupervised Domain Adaptation for Mitigating Sensor Variability and Interspecies Heterogeneity in Animal Activity Recognition

“…Moreover, these sensors can be attached to various body parts depending on the purpose of the measurement, environmental conditions, and animal characteristics. Neck sensors are widely used in AAR due to their ease of attachment to animals [4][5][6][7][8][9][10][13][14][15][16][17]. However, neck sensors have shown a lower classification performance due to orientation shifts caused by the tightness of sensors [13,14,48].…”

“…In the feature extractor, we implemented a residual block which set up the kernel size {(1, 7), (1,5), (1, 3)}, and applied batch normalization and Leaky ReLU as the activation functions. We stacked three residual blocks with the number of kernels {64, 128, 128}.…”

“…Behavior recognition of animals has emerged as a promising method for estimating their health status and monitoring abnormal behaviors. The widely-used types of sensors in identifying animal behavior include cameras [1][2][3] and wearable devices [4][5][6]. Wearable devices, comprising accelerometers, gyroscopes, magnetometers, pressure sensors, and global navigation satellite systems (GNSSs), have garnered increasing popularity in animal monitoring applications.…”

“…The scarcity of annotation is an additional constraint in AAR. In most studies and public datasets, animal activities are annotated via the visual inspection of animal behaviors in video recordings, often requiring substantial human resources and potentially raising privacy concerns [5,17,21,22]. Federated learning, as proposed by Mao et al (2022), provides a mechanism to update a global server model by aggregating only local parameters, eliminating the need to collect the raw data from local devices [17].…”

Current Research in Future Information and Communication Engineering 2022

“…In terms of validating the data accuracy of the STM-LSTM-based fall detection system, optimal values of the parameters in the LSTM and normalization method were found as follows: best accuracy of 98.21% at no-normalization, no-sampling, 128 hidden layer nodes, and a regularization rate of 0.015. In the fourth paper, authored by Husain et al [15], automatic pet monitoring applications include real-time monitoring and monitoring systems that accurately identify pets using the latest methods for classifying pet activities. An LSTM-based method to detect and classify dog activity based on sensor data (i.e., accelerometers and gyroscopes) was proposed.…”