Redirigiendo al acceso original de articulo en 16 segundos...
Inicio  /  Applied Sciences  /  Vol: 10 Par: 20 (2020)  /  Artículo
ARTÍCULO
TITULO

Illegal Logging Detection Based on Acoustic Surveillance of Forest

Iosif Mporas    
Isidoros Perikos    
Vasilios Kelefouras and Michael Paraskevas    

Resumen

In this article, we present a framework for automatic detection of logging activity in forests using audio recordings. The framework was evaluated in terms of logging detection classification performance and various widely used classification methods and algorithms were tested. Experimental setups, using different ratios of sound-to-noise values, were followed and the best classification accuracy was reported by the support vector machine algorithm. In addition, a postprocessing scheme on decision level was applied that provided an improvement in the performance of more than 1%, mainly in cases of low ratios of sound-to-noise. Finally, we evaluated a late-stage fusion method, combining the postprocessed recognition results of the three top-performing classifiers, and the experimental results showed a further improvement of approximately 2%, in terms of absolute improvement, with logging sound recognition accuracy reaching 94.42% when the ratio of sound-to-noise was equal to 20 dB.

 Artículos similares

       
 
Ye Yu, Linghui Cai, Changmin Zhang, Li Wang, Rui Zhu, Yanran Huang and Taotao Cao    
Using 2D/3D seismic data and a large number of drilling and logging data and applying sequence stratigraphy, seismic sedimentology, and petroleum geology concepts, the characteristics of the sedimentary sequence of the forced regression have been analyse... ver más

 
Musbah Joma Aqel,Omar Naqshbandi,Munsif Yousef Sokiyna,Pertsevoi Valentyn     Pág. pp. 107 - 127
Now, people all over the world use messengers to communicate with their families and employees at work, schedule meetings, congratulate on holidays, and conduct banking operations using bots built into messengers. However, it is challenging to improve su... ver más

 
Lieve Macken, Daniel Prou and Arda Tezcan    
This paper studies the impact of machine translation (MT) on the translation workflow at the Directorate-General for Translation (DGT), focusing on two language pairs and two MT paradigms: English-into-French with statistical MT and English-into-Finnish ... ver más
Revista: Informatics

 
Mohammad Ashari Dwiputra, Rahmat Kurnia, Etty Riani     Pág. 1 - 8
Scientific information  mangrove ecosystem at Kulisusu bay was limited. This study aims to identify mangrove ecosystems area change at Kulisusu bay within 20 years periods (1995-2015) using satellite imagery Landsat 5 TM (1995), Landsat 7 ETM (2005)... ver más

 
Frederick Stumm, Michael D. Como     Pág. 1 - 17
Groundwater with chloride concentrations up to 15,000 mg/L has intruded the freshwater aquifer underlying southern Manhattan Island, New York. Historical (1940?1950) chloride concentration data of glacial aquifer wells in the study area indicate the pres... ver más
Revista: Water