Adaptive Pet Wearable Sensing for Accurate Low-Power Data Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies for companion animals lack efficient methods to collect and process human de-identification information for artificial intelligence learning, particularly considering the varying sensory sensitivities and states of companion animals, leading to inefficiencies and high power consumption in wearable devices.
Innovation Solution
A human de-identification information collection device that includes microphones, inertial measurement devices, and gas sensors, adaptively setting sampling rates and operation modes based on animal breed, age, gender, and temperament, and using interpolation models to manage data from multiple sensors, including audible and inaudible frequency bands, while integrating noise filtering and calibration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the sampling rate for collecting audio data and inertial data is increased to improve measurement precision, then the data collection accuracy improves, but the power consumption increases
Solution Approach 1:
The patent applies dynamics by making the sampling rate adjustable rather than fixed. The processor dynamically determines the sampling rate based on real-time analysis of audio data and inertial data, selecting from multiple predetermined rates (e.g., 1 Hz, 5 Hz, 10 Hz, 20 Hz, 40 Hz). This allows the system to optimize between measurement precision and power consumption by using lower sampling rates when animal behavior is predictable and higher rates when sudden changes are detected.
Solution Approach 2:
The patent changes the parameter of sampling rate based on detected animal states. When the animal is in a sleeping state, the system uses lower sampling rates to reduce power consumption. When the animal is active or shows signs of distress, the system increases the sampling rate to improve measurement precision. This parameter adaptation resolves the contradiction by making the measurement rate flexible rather than static.
2Measurement precision
If the complexity of the interpolation model is increased to improve data processing accuracy, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent applies dynamics to the interpolation model complexity by making it adjustable. The processor determines the degree of the interpolation model from multiple predetermined degrees (e.g., 1st degree, 2nd degree, 3rd degree) based on the sampling rate and animal behavior characteristics. This allows the system to use simpler models when data patterns are regular and more complex models only when necessary, resolving the contradiction between processing accuracy and device complexity.
3Measurement precision
If multiple sensors are used to collect comprehensive animal information, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent applies universality by designing a processor that can handle multiple types of sensor data (audio data from microphones, inertial data from accelerometers/gyroscopes, and olfactory data from gas sensors) using unified processing techniques. The same interpolation and sampling rate determination methods are applied across different sensor types, reducing the effective complexity despite having multiple sensors. This multi-functional approach allows comprehensive animal monitoring while managing system complexity through standardized processing protocols.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The device efficiently collects and processes human de-identification information, adapting to animal states for low power consumption, thereby enhancing the practicality and effectiveness of wearable devices for AI learning.
Implementation Method 1
a first microphone for capturing sounds in an audible frequency band of the companion animal
Implementation Method 2
an inertial measurement device for generating inertial data about a change in acceleration and angular velocity according to movement of the companion animal
Data Source
AI summary
A human de-identification information collection device for artificial intelligence learning according to an embodiment may comprise: at least one microphone for capturing sounds generated around a companion animal and generating at least one audio data, an inertial measurement device for generating inertial data about a change in acceleration and angular velocity according to movement of the companion animal, and a processor for determining each sampling rate for collecting the at least one audio data, and the inertial data on the basis of at least one among a breed, an age, a gender, whether or not neutered, and a temperament type of the companion animal.