Method to operate multiple sensors for multiple instances of interconnected human activity recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in performing Human Activity Recognition (HAR) across multiple locations in a factory setting due to bandwidth constraints and network congestion when using multiple sensors, and lack the ability to handle interconnected worker activities effectively.
Innovation Solution
A system that utilizes domain knowledge of historical task sequences to estimate the probability of future tasks and selectively activates sensors for data transmission based on task probabilities, optimizing data allocation and reducing unnecessary data transfer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple sensors transmit all their monitoring data over wireless network to gateway for HAR processing, then HAR can be performed at multiple locations, but network congestion occurs due to high data volume
Solution Approach 1:
The system performs preliminary action by predicting future worker actions and pre-determining which sensors need to transmit data. Historical data of task sequences is analyzed to forecast worker movements before they occur, allowing the system to schedule sensor data transmission in advance, avoiding network congestion while ensuring HAR data availability.
Solution Approach 2:
The invention extracts only the necessary sensor data for HAR purposes rather than transmitting all sensor data. By identifying and extracting only the monitoring data related to predicted worker actions and critical work areas, the system reduces data volume transmitted over the network while maintaining HAR effectiveness.
2Measurement precision
If all sensors transmit data simultaneously for comprehensive HAR monitoring, then measurement coverage is improved, but data transmission bandwidth is exhausted
Solution Approach 1:
The system applies local quality by differentiating between critical and non-critical work areas. Sensors in areas with high predicted worker activity and critical tasks are scheduled for data transmission, while sensors in areas with low predicted activity remain inactive. This localized approach ensures high-quality HAR data is collected where needed without exhausting overall bandwidth.
Solution Approach 2:
The system performs preliminary analysis of historical task sequence data to predict future worker actions and pre-schedules sensor data transmission. This preliminary action allows the system to transmit data only when and where it is most likely to be needed, optimizing the balance between measurement quality and data volume.
3Measurement precision
If sensors operate continuously for complete activity monitoring, then HAR accuracy is maintained, but energy consumption and operational costs increase
Solution Approach 1:
Instead of continuous operation, the system implements periodic action by scheduling sensor data transmission based on predicted worker actions. Sensors are activated periodically at specific time intervals when worker presence is anticipated, rather than continuously, reducing energy consumption while maintaining HAR accuracy through strategic sampling.
Solution Approach 2:
The system uses preliminary prediction of worker actions to schedule sensor operation in advance. By analyzing historical data patterns, the system determines optimal activation times for sensors before workers actually arrive, ensuring accurate HAR monitoring occurs only when needed, thereby reducing overall energy consumption.
Data Source
AI summary
Example implementations described herein involve systems and methods that involve recognizing, from sensor data, an area from the plurality of areas and a candidate task from the one or more candidate tasks associated with the area; estimating a probability of each of the plurality of candidate tasks for the each of the plurality of areas for a specific future period of time, based on referencing historical data of task sequences previously executed; accepting the ones of the plurality of candidate tasks for the each of the plurality of areas having the probability being higher than a threshold; and scheduling one or more sensors to activate and transmit in the specific future period of time in associated areas for the plurality of areas associated with other ones of the plurality of candidate tasks for the each of the plurality of areas not having the probability being higher than the threshold.