|
ai-generated content (aigc) |
7 |
|
generative ai |
7 |
|
generative design |
7 |
|
generative method |
7 |
|
generative urban design |
7 |
|
human-machine collaboration |
7 |
|
urban form generation |
7 |
|
gis |
5 |
|
3d visualization |
4 |
|
building layout |
4 |
|
deep learning |
4 |
|
design scenario |
4 |
|
generative adversarial network (gan) |
4 |
|
national scale |
4 |
|
xgboost |
4 |
|
air taxi |
3 |
|
attention mechanism |
3 |
|
automated site planning |
3 |
|
built environment |
3 |
|
deep generative models |
3 |
|
demand analysis |
3 |
|
electric vertical take-off and landing (evtol) |
3 |
|
generative adversarial networks (gan) |
3 |
|
generative artificial intelligence (generative ai) |
3 |
|
human perception |
3 |
|
land price estimation |
3 |
|
literature review |
3 |
|
machine learning |
3 |
|
planning guidance |
3 |
|
recursive feature elimination |
3 |
|
road safety |
3 |
|
street view images |
3 |
|
urban air mobility (uam) |
3 |
|
urban air mobility life cycle |
3 |
|
air pollution control |
2 |
|
air quality |
2 |
|
air quality index |
2 |
|
air quality prediction |
2 |
|
association rule analysis |
2 |
|
association rule mining |
2 |
|
bayesian optimization |
2 |
|
bi-directional estimation |
2 |
|
big data |
2 |
|
big data techniques |
2 |
|
biochemical oxygen demand |
2 |
|
bootstrap-resampling-data-balancing method |
2 |
|
building energy |
2 |
|
deep matrix factorization |
2 |
|
deep neural network |
2 |
|
electric power |
2 |
|
energy use intensity |
2 |
|
enhanced learning model |
2 |
|
ensemble method |
2 |
|
explainable ai |
2 |
|
feature analysis |
2 |
|
feature importance |
2 |
|
felony assault |
2 |
|
geographic information system |
2 |
|
geographic lstm |
2 |
|
gradient boost decision tree |
2 |
|
grid importance rank |
2 |
|
harbor water |
2 |
|
hourly prediction |
2 |
|
ignition process |
2 |
|
imbalanced dataset |
2 |
|
lag-flstm |
2 |
|
land values per square foot |
2 |
|
lightgbm |
2 |
|
long short-term memory (lstm) |
2 |
|
long-interval consecutive missing values |
2 |
|
macro factors |
2 |
|
missing data |
2 |
|
multivariate inputs |
2 |
|
neural network |
2 |
|
pedestrian volume |
2 |
|
place of interest |
2 |
|
pm2.5 |
2 |
|
powerline vegetation faults |
2 |
|
road-based analysis |
2 |
|
run-off-road accidents |
2 |
|
semi-supervised learning |
2 |
|
sparse matrix |
2 |
|
spatial analysis |
2 |
|
spatial extrapolation |
2 |
|
spatial proximity analysis |
2 |
|
spatiotemporal distribution |
2 |
|
the most influential areas |
2 |
|
traffic accident fatality |
2 |
|
traffic fatality rates |
2 |
|
transfer learning |
2 |
|
unlabeled samples |
2 |
|
urban building energy modeling |
2 |
|
urban buildings |
2 |
|
urban morphology |
2 |
|
variable importance |
2 |
|
wildfire |
2 |
|
accurate and efficient classification based on multiple class-association rules (cmar) |
1 |
|
association rule mining (arm) |
1 |
|
building façade |
1 |
|
building shading |
1 |
|
crash detection |
1 |
|
deep learning methods |
1 |
|
design project |
1 |
|
different temporal resolutions |
1 |
|
energy and comfort models |
1 |
|
explainable machine learning |
1 |
|
geographic information system (gis) |
1 |
|
heat transfer coefficient |
1 |
|
key factors |
1 |
|
long short-term memory networks |
1 |
|
motorcycle accidents |
1 |
|
multi-objective optimization |
1 |
|
new rural community |
1 |
|
performance-based design |
1 |
|
three-dimensional model |
1 |
|
threshold determination |
1 |
|
traffic condition |
1 |
|
tree vegetable |
1 |
|
urban building energy model |
1 |
|
urban microclimate |
1 |
|
virtual wall |
1 |
