2018
DOI: 10.1007/978-3-030-05348-2_32
|View full text |Cite
|
Sign up to set email alerts
|

Evolutionary Deep Learning for Car Park Occupancy Prediction in Smart Cities

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
60
0

Year Published

2018
2018
2020
2020

Publication Types

Select...
6
3

Relationship

2
7

Authors

Journals

citations
Cited by 78 publications
(60 citation statements)
references
References 25 publications
0
60
0
Order By: Relevance
“…Regarding the algorithms for the generation of predictions, here we have studied some techniques for time-series prediction based on regression. However, recently the recurring neural network technique has emerged as a good method for the generation of time-series predictions (LeCun et al, 2015, Camero et al, 2018. We plan to improve the fill-level predictions by using an algorithm based on recurring neural networks.…”
Section: Discussionmentioning
confidence: 99%
“…Regarding the algorithms for the generation of predictions, here we have studied some techniques for time-series prediction based on regression. However, recently the recurring neural network technique has emerged as a good method for the generation of time-series predictions (LeCun et al, 2015, Camero et al, 2018. We plan to improve the fill-level predictions by using an algorithm based on recurring neural networks.…”
Section: Discussionmentioning
confidence: 99%
“…In terms of predicting the parking occupancy rate, Zheng et al found that the Regression Tree method outperforms the other two algorithms they evaluated. Camero et al [13] presented a Recurrent Neural Network (RNN)-based approach to predict the number of free parking spaces. Their main aim was to improve the performance of the RNN.…”
Section: Related Workmentioning
confidence: 99%
“…In contrast, the use of the sensors has recently increased in various fields, such as anomaly detection, whose principles can be applied to DSD [4,34,35]. In the following sections, we discuss three deep learning algorithms used in sensing systems for anomaly detection [36][37][38].…”
Section: Deep Learning-based Sensorsmentioning
confidence: 99%
“…This residual error can be used to detect points of frequent anomalies. Experiments with actual IoT sensor data have indicated that abnormality detection using LSTM mainly detects the sudden change of a value efficiently [38].…”
Section: Long Short-term Memory (Lstm) Modelmentioning
confidence: 99%