Computer-Based Neural Network in TensorBoard
Living conditions data fed into a machine learning model has been proposed as a way to predict happiness. The hierarchical machine learning model has a two-layer structure for happiness prediction. In the first layer, the parameters of base estimators are tuned using the grid search technique. In the second layer, the weights of the based estimators are optimized using particle swarm optimization (PSO).
The 6 question survey is based on the following living conditions:
- Availability of information about city services
- Cost of housing
- Quality of public schools
- Trust in local police
- Maintenance of streets and sidewalks
- Availability of social community events
They concluded that, “our hierarchical structure and optimization strategies are effective for improving the performance of happiness prediction and could be a useful tool for decision makers to know people’s happiness status based on certain living conditions. It is worth noting that our proposed model could be extended for other prediction problems, such as depression prediction.”
We look forward to their next paper extending the model to predict depression.
https://doi.org/10.1007/s10489-022-03811-x
