Redirigiendo al acceso original de articulo en 22 segundos...
Inicio  /  Drones  /  Vol: 7 Par: 1 (2023)  /  Artículo
ARTÍCULO
TITULO

Practical Study of Recurrent Neural Networks for Efficient Real-Time Drone Sound Detection: A Review

Dana Utebayeva    
Lyazzat Ilipbayeva and Eric T. Matson    

Resumen

The detection and classification of engine-based moving objects in restricted scenes from acoustic signals allow better Unmanned Aerial System (UAS)-specific intelligent systems and audio-based surveillance systems. Recurrent Neural Networks (RNNs) provide wide coverage in the field of acoustic analysis due to their effectiveness in widespread practical applications. In this work, we propose to study SimpleRNN, LSTM, BiLSTM, and GRU recurrent network models for real-time UAV sound recognition systems based on Mel-spectrogram using Kapre layers. The main goal of the work is to study the types of RNN networks in a practical sense for a reliable drone sound recognition system. According to the results of an experimental study, the GRU (Gated Recurrent Units) network model demonstrated a higher prediction ability than other RNN architectures for detecting differences and the state of objects from acoustic signals. That is, RNNs gave higher recognition than CNNs for loaded and unloaded audio states of various UAV models, while the GRU model showed about 98% accuracy for determining the UAV load states and 99% accuracy for background noise, which consisted of more other data.

 Artículos similares

       
 
Dunqing Li, Feng Liao, Lixin Wang, Jianfu Lin and Junfang Wang    
As urbanization accelerates, deep excavation projects have become increasingly vital in the construction of high-rise buildings and underground facilities. However, the potential risks to the surrounding environment and the inherent complexities involved... ver más
Revista: Buildings

 
Mo Fan, Massoomeh Hedayati Marzbali, Aldrin Abdullah and Mohammad Javad Maghsoodi Tilaki    
Contemporary urban development places a critical emphasis on pedestrian environments, especially in historic cities like George Town, which is a UNESCO World Heritage Site in Malaysia. Although survey questionnaires effectively captured public perception... ver más
Revista: Urban Science

 
Yuchen Wang, Adeela Gulzari and Victor Prybutok    
This study investigates the understudied area of motivational factors influencing the rental intention of electric vehicles (EVs) within the context of their integration into urban transportation to combat air pollution and reduce carbon footprints and e... ver más

 
Jian Xu, Yujia Qian, Bingyue He, Huixuan Xiang, Ran Ling and Genyu Xu    
To effectively combat environmental challenges, it is necessary to evaluate urban residential building carbon emissions and implement energy-efficient, emission-reducing strategies. The lack of a specialized carbon emission monitoring system complicates ... ver más
Revista: Buildings

 
Josephine Vaughan, Rebecca Evans and Willy Sher    
Accounting for the embodied carbon in construction materials and calculating the carbon footprint of entire construction projects in life-cycle assessments is a rapidly developing area in the construction industry. Carbon emission accounting relies on in... ver más
Revista: Buildings