Using neural network to optimize operational parameter of vehicle while achieving favorable emotional state of rider
A system for transportation includes a vehicle, a rider occupying the vehicle, and a hybrid neural network. The hybrid neural network includes a first neural network to process a sensor input corresponding to the rider to determine an emotional state of the rider, and a second neural network to optimize at least one operating parameter of the vehicle to improve the emotional state of the rider.
1. A system for transportation, comprising:
a vehicle interface to interface with a vehicle occupied by a rider; and
a hybrid neural network, including:
a first neural network to process a sensor input corresponding to the rider to determine an emotional state of the rider;
a second neural network to classify social media data sourced from a plurality of social media sources and as being indicative of an effect on the system for transportation, wherein the social media data indicates at least one of an interest of the rider or a transportation objective of the rider, and
a third neural network to analyze the classified social media data and optimize at least one operating parameter of the vehicle to improve the emotional state of the rider, wherein the analysis of the classified social media data by the third neural network includes determining a value for the at least one operating parameter that is likely to improve the emotional state of the rider based on at least one of a model or a rule, wherein the at least one of the model or the rule includes a weighting for the at least one operating parameter, and wherein the optimization of the at least one operating parameter includes using the vehicle interface for at least one of:
adjustment of a routing plan of the vehicle to include passing a point of interest to the rider, or
selecting entertainment content from entertainment options including at least one of: movies, games, or advertising content,
wherein the third neural network is configured to optimize the at least one operating parameter of the vehicle in part by varying the at least one operating parameter to vary a cortisol level of the rider based on a time of day.
2. The system for transportation of claim 1 wherein the at least one operating parameter of the vehicle that is optimized by the third neural network affects: a speed of the vehicle, an acceleration of the vehicle, a deceleration of the vehicle, and a proximity to other vehicles along a route.
3. The system for transportation of claim 1 wherein a sensor that produces the sensor input corresponding to the rider is to gather physiological sensed data indicative of a hormone level of the rider, wherein the physiological sensed data includes galvanic skin response that is indicative of the cortisol level of the rider.
4. The system for transportation of claim 3 wherein the first neural network is to determine the emotional state of the rider through analysis of the physiological sensed data.
5. The system for transportation of claim 3 wherein the sensor is deployed in the vehicle.
6. The system for transportation of claim 3 wherein the sensor is a wearable sensor.
7. The system for transportation of claim 1 wherein the third neural network is to optimize the at least one operating parameter of the vehicle based on a correlation between a vehicle operating state and the emotional state of the rider.
8. The system for transportation of claim 1 wherein the emotional state of the rider that is improved includes at least one aspect of rider satisfaction.
9. The system for transportation of claim 8 wherein the at least one aspect of rider satisfaction is one of; an operating state of the vehicle, an in-vehicle state, a rider state, a routing state, or a user experience state.
10. The system for transportation of claim 1 wherein at least one of the neural networks in the hybrid neural network is a convolutional neural network.
11. The system for transportation of claim 1 wherein the social media data includes at least one of:
social media posts, social media feeds, like or dislike activity detected in the social media, indications of relationships, user behavior, discussion threads, or chats.
12. The system for transportation of claim 1 wherein the social media data includes at least one of: presence of a rare phenomenon at a location, entertainment choices, risk-related conditions, or modes of transportation used with an event.
13. A method, comprising:
processing, using a first neural network of a hybrid neural network, a sensor input corresponding to a rider in a vehicle to determine an emotional state of the rider;
classifying, using a second neural network of the hybrid neural network, social media data sourced from a plurality of social media sources and as being indicative of an effect on a system for transportation that includes the vehicle having the rider therein and the hybrid neural network, wherein the social media data indicates at least one of an interest of the rider or a transportation objective of the rider, and
analyzing, using a third neural network of the hybrid neural network, the classified social media data and optimizing at least one operating parameter of the vehicle to improve the emotional state of the rider, wherein analyzing the classified social media data includes determining a value for the at least one operating parameter that is likely to improve the emotional state of the rider based on at least one of a model or a rule, wherein the at least one of the model or the rule includes a weighting for the at least one operating parameter, and wherein the optimizing of the at least one operating parameter includes at least one of:
adjusting a routing plan of the vehicle to include passing a point of interest to the rider, or
selecting entertainment content from entertainment options, wherein the entertainment options include at least one of movies, games, or advertising content,
and wherein the third neural network is used to optimize the at least one operating parameter of the vehicle in part by varying the at least one operating parameter to vary a cortisol level of the rider based on a time of day.
14. The method of claim 13 wherein the at least one operating parameter of the vehicle that is optimized by the third neural network affects: a speed of the vehicle, an acceleration of the vehicle, a deceleration of the vehicle, and a proximity to other vehicles along a route.
15. The method of claim 13 wherein a sensor that produces the sensor input corresponding to the rider is to gather physiological sensed data indicative of a hormone level of the rider, wherein the physiological sensed data includes galvanic skin response indicative of the cortisol level of the rider.