Occupancy Model Sensor Noise Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Parking occupancy detection systems face inaccuracies due to sensor failures, as they do not equally miss measurements for full and empty spaces, leading to unreliable predictions of available parking spaces, especially during peak times when accurate evaluation is crucial.
Innovation Solution
A probabilistic sensor noise model is combined with a demand model to predict occupancy status, learning parameters from training data to account for various failure scenarios, such as random or condition-dependent sensor failures, enabling accurate prediction even with incomplete data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If sensor failure is assumed to be random and independent of occupancy state, then the prediction model is simpler to implement, but the prediction accuracy deteriorates because full and empty spaces do not have missing measurements with equal probability
Solution Approach 1:
The patent changes the parameter of sensor failure probability from being constant (random failure assumption) to being occupancy-dependent. The model learns different failure probabilities for occupied versus unoccupied spaces, allowing the sensor noise model to adapt to the actual conditional failure rates observed in the data, thereby improving prediction accuracy without excessive complexity
Solution Approach 2:
The model uses feedback from observed occupancy data to learn and refine the sensor noise parameters. By continuously learning from the data, the model adjusts its understanding of sensor failure patterns, improving its ability to distinguish between true occupancy states and sensor failures
2Productivity
If the system assumes equal probability of missing measurements for full and empty spaces, then the data processing is simpler, but the occupancy status prediction becomes unreliable during peak times when accurate evaluation is crucial
Solution Approach 1:
The patent changes the fundamental parameter of missing measurement probability from uniform to non-uniform distribution. The sensor noise model explicitly parameters the dependency between occupancy state and measurement completeness, allowing the system to handle peak time conditions where accuracy is most critical
Solution Approach 2:
The system performs preliminary learning of sensor noise characteristics during normal operation, building up the occupancy-dependent failure probability models before peak times occur. This preliminary action allows the system to be ready with accurate prediction capabilities when demand is highest
Data Source
AI summary
A system and method for generating an occupancy model are disclosed. The model is learned using occupancy data for zones, each zone including cells, which are occupied or not at a given time, each with a sensor, which may be reporting or not. The data provides an observed occupancy corresponding to a number of cells in the respective zone which have reporting sensors, and the number of those sensors which are reporting that the respective cell is occupied. The occupancy model is based on a demand model and a sensor noise model which accounts for behavior of the non-reporting sensors. The noise model assumes that the probability of a sensor being in the reporting state is dependent on whether the respective cell is occupied or not. The model can fit the occupancy data better than one which assumes that non-reporting cells are occupied with the same frequency as reporting ones.