Deep convolutional neural network-based enhanced crowd density monitoring for intelligent urban planning on smart cities DOI Creative Commons
Wahida Mansouri, Manal Abdullah Alohali, Hamed Alqahtani

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 17, 2025

The concept of a smart city has spread as solution ensuring wider availability data and services to citizens, apart from means lower the environmental footprint cities. Crowd density monitoring is cutting-edge technology that enables cities monitor effectively manage crowd movements in real time. By utilizing advanced artificial intelligence video analytics, valuable insights are accumulated behaviour, assisting improving operational efficiency, public safety, urban planning. This also significantly contributes resource allocation emergency response, contributing smarter, safer environments. classification using deep learning (DL) employs NN models interpret analyze information sensors such IoT devices CCTV cameras. technique trains DL on large datasets accurately count people region, traffic management, recurrent neural networks (RNNs) for time-series convolutional (CNNs) image processing, model adapts varying scenarios, lighting, angles. manuscript presents Deep Convolutional Neural Network-based Density Monitoring Intelligent Urban Planning (DCNNCDM-IUP) proposed DCNNCDM-IUP utilizes methods detect densities, which can assist planning Initially, performs preprocessing Gaussian filtering (GF). SE-DenseNet approach, effectually learns complex feature patterns extraction. Moreover, hyperparameter selection approach accomplished by red fox optimization (RFO) methodology. Finally, long short-term memory (ConvLSTM) methodology recognizes varied densities. A comprehensive simulation analysis conducted demonstrate improved performance technique. experimental validation portrayed superior accuracy value 98.40% compared existing models.

Язык: Английский

Deep convolutional neural network-based enhanced crowd density monitoring for intelligent urban planning on smart cities DOI Creative Commons
Wahida Mansouri, Manal Abdullah Alohali, Hamed Alqahtani

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 17, 2025

The concept of a smart city has spread as solution ensuring wider availability data and services to citizens, apart from means lower the environmental footprint cities. Crowd density monitoring is cutting-edge technology that enables cities monitor effectively manage crowd movements in real time. By utilizing advanced artificial intelligence video analytics, valuable insights are accumulated behaviour, assisting improving operational efficiency, public safety, urban planning. This also significantly contributes resource allocation emergency response, contributing smarter, safer environments. classification using deep learning (DL) employs NN models interpret analyze information sensors such IoT devices CCTV cameras. technique trains DL on large datasets accurately count people region, traffic management, recurrent neural networks (RNNs) for time-series convolutional (CNNs) image processing, model adapts varying scenarios, lighting, angles. manuscript presents Deep Convolutional Neural Network-based Density Monitoring Intelligent Urban Planning (DCNNCDM-IUP) proposed DCNNCDM-IUP utilizes methods detect densities, which can assist planning Initially, performs preprocessing Gaussian filtering (GF). SE-DenseNet approach, effectually learns complex feature patterns extraction. Moreover, hyperparameter selection approach accomplished by red fox optimization (RFO) methodology. Finally, long short-term memory (ConvLSTM) methodology recognizes varied densities. A comprehensive simulation analysis conducted demonstrate improved performance technique. experimental validation portrayed superior accuracy value 98.40% compared existing models.

Язык: Английский

Процитировано

0