Identification Vehicle Movement Detection in Forest Area using MFCC and KNN

Chaudhary, Mitika; Prakash, Vinay; Kumari, Neeraj

doi:10.1109/sysmart.2018.8746936

Cited by 11 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previously, ML-based classification was focused on supervised machine learning approach, consisting of two stages: extracting 'hand-crafted' features from audio signals, followed by classifying the features using a classifier algorithm. Commonly used features include Mel Frequency Cepstral Coefficients (MFCC) [11], [12], other less studied features includes harmonics components [13], [14], and spectral based features such as zero-crossing rate [15], pitch frequency [16] while k-nearest neighbour (k-NN) [11] support vector machine (SVM) [17], and artificial neural-network (ANN) [18] are the commonly used classifier algorithms. However, this approach can be problematic due to the potential bias and uncertainty of the expert creating the features, as well as the difficulty of acquiring prior knowledge of optimal features from large datasets.…”

Section: Related Workmentioning

confidence: 99%

Acoustic Vehicle Classification Using Mel-Frequency Features with Long Short-Term Memory Neural Networks

Yassin,

Mohd Shariff,

Kechik

et al. 2023

TEM Journal

View full text Add to dashboard Cite

Monitoring vehicle traffic at a large scale is a challenging task for authorities, particularly considering the high cost of traffic sensors such as vision cameras. To meet the growing demand for more accurate traffic monitoring, the use of traffic sounds has become a popular approach, as it provides insight into the types of traffic present. This paper reports on an approach to vehicle classification based on acoustic signals, using the Mel-Frequency Cepstral Coefficients (MFCC) and the Long Short-Term Memory (LSTM) networks. This study exhibited classification accuracy scores of 82-86.2% across four vehicle categories: motorcycle, car, truck, and no traffic. The results demonstrated that large-scale, low-cost acoustic processing can be effectively used for vehicle monitoring.

show abstract

Section: Related Workmentioning

confidence: 99%

Acoustic Vehicle Classification Using Mel-Frequency Features with Long Short-Term Memory Neural Networks

Yassin,

Mohd Shariff,

Kechik

et al. 2023

TEM Journal

View full text Add to dashboard Cite

show abstract

“…kNN outperforms FLD in the first implementation of the detector but underperforms it in the second one. More recently, kNN was the preferred algorithm in Reference [ 13 ] when detecting several audio events in a forest area.…”

Section: Related Workmentioning

confidence: 99%

“…Detecting sounds in outdoor environments has also several applications ranging from traffic noise mapping in a city [ 11 ] to soundscapes modeling [ 12 ] or open air surveillance [ 13 ]. The DYNAMAP project [ 14 ], for instance, distributed a low-cost WASN in Rome and Milan in order to monitor a very specific environmental noise, i.e., Road Traffic Noise (RTN), and evaluate its impact in urban and suburban areas.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Survey of Feature Extraction and Machine Learning Methods in Diverse Acoustic Environments

Bonet-Solà¹,

Alsina-Pagès²

2021

Sensors

View full text Add to dashboard Cite

Acoustic event detection and analysis has been widely developed in the last few years for its valuable application in monitoring elderly or dependant people, for surveillance issues, for multimedia retrieval, or even for biodiversity metrics in natural environments. For this purpose, sound source identification is a key issue to give a smart technological answer to all the aforementioned applications. Diverse types of sounds and variate environments, together with a number of challenges in terms of application, widen the choice of artificial intelligence algorithm proposal. This paper presents a comparative study on combining several feature extraction algorithms (Mel Frequency Cepstrum Coefficients (MFCC), Gammatone Cepstrum Coefficients (GTCC), and Narrow Band (NB)) with a group of machine learning algorithms (k-Nearest Neighbor (kNN), Neural Networks (NN), and Gaussian Mixture Model (GMM)), tested over five different acoustic environments. This work has the goal of detailing a best practice method and evaluate the reliability of this general-purpose algorithm for all the classes. Preliminary results show that most of the combinations of feature extraction and machine learning present acceptable results in most of the described corpora. Nevertheless, there is a combination that outperforms the others: the use of GTCC together with kNN, and its results are further analyzed for all the corpora.

show abstract

“…They consist of intentionally placed border crossings and imagined bounded areas, the so-called buffer zones around them, which together form the porous border area [5] (p. 5). In the context of the 2015 European migration crisis, an example of such a border is the concept of the green-grey border [6], which exists between Bosnia and Herzegovina and Croatia.…”

Section: Introductionmentioning

confidence: 99%

Multi-Purpose Accessibility of Mountain Area Forests for the Purpose of Forest Management and Protection of the State Border

Krivić-Tomić,

Papa,

Kožić

2023

Sustainability

View full text Add to dashboard Cite

The planning and implementation of surveillance of state territory in forested border areas, especially mountainous areas, is considered to be highly complex. This is illustrated by the example of the difficulties the European Union faced in controlling the 2015 European migration crisis. Thereby, Croatia has the difficult task of protecting the borders of the Union because a particular problem on the Western Balkan Route is the so-called bottleneck to Slovenia in the area of the Municipality of Donji Lapac, which consists of the green border with Bosnia and Herzegovina. Consequently, by using the example of planning multi-purpose forest roads, the aim of this paper is to propose the inclusion of the road network of border management units of mountain areas in the control system of the state’s green border, which, in this paper, includes its surveillance and protection by land for the purpose of national security. The research was conducted on the example of the Visočica–Lisac border management unit in the Municipality of Donji Lapac. The results of the research indicate a possible solution to the control of the border management unit by establishing a two-level surveillance system. The higher level consists of strategically defined surveillance points and corresponding multi-purpose forest roads designed on a tactical level. At this level, the priority is protection or, more precisely, defense of the state border. The lower level consists of tactically determined surveillance points with corresponding multi-purpose forest roads designed on the operational level. In addition to protecting the state border, this level would also have the task of protecting the forest, that is, monitoring the area of the management unit.

show abstract

Identification Vehicle Movement Detection in Forest Area using MFCC and KNN

Cited by 11 publications

References 29 publications

Acoustic Vehicle Classification Using Mel-Frequency Features with Long Short-Term Memory Neural Networks

Acoustic Vehicle Classification Using Mel-Frequency Features with Long Short-Term Memory Neural Networks

A Comparative Survey of Feature Extraction and Machine Learning Methods in Diverse Acoustic Environments

Multi-Purpose Accessibility of Mountain Area Forests for the Purpose of Forest Management and Protection of the State Border

Contact Info

Product

Resources

About