TY - JOUR
AU - Acharjee, Tapodhir
AB - Nowadays due to the advancement of the smart parking solutions, the drivers are eager to know that how much vacancy will be there in a particular parking place in specific day or in a particular hour of a day. An intelligent decision support system can help to provide advance information to the drivers about the occupancy percentage of a parking area. This information should be available to any type of vehicle in an indoor parking area. In this way, parking spaces could be found more quickly during traffic searches. Parking occupancy percentage forecasting is an optimum problem. Even though many researchers have tried to solve these problems previously using various methods of deep learning, there are still some shortcomings when it comes to estimating parking space occupancy levels. As such, in this paper, parking occupancy percentage is forecasted for an indoor parking system for any type of vehicle using a modified long short-term memory model (LSTM) as a CNN-LSTM hybrid model, from which parking occupancy percentage can be predicted using the prior parking information during specific dates and hours. With the use of the Internet of Things network, cloud server, and sensors used in various smart parking places, we generate real-time information to estimate the hybrid CNN-LSTM model and the results have been discussed in detail. Comparative analysis has been done with the existing time series a model including other LSTM models, and it is found that our proposed CNN-LSTM-based models provide better results in terms of different performance measurement parameters.
TI - Parking slot occupancy prediction using LSTM
JF - Innovations in Systems and Software Engineering
DO - 10.1007/s11334-022-00481-3
DA - 2025-03-01
UR - https://www.deepdyve.com/lp/springer-journals/parking-slot-occupancy-prediction-using-lstm-B3N6CTHLrw
SP - 65
EP - 77
VL - 21
IS - 1
DP - DeepDyve
ER -