Application of Wavelets and Kernel Methods to Detection and Extraction of Behaviours of Freshwater Mussels

Przymus, Piotr; Rykaczewski, K. P.; Wi, Ryszard; niewski,

doi:10.1007/978-3-642-27142-7_7

Cited by 7 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The methods that are used include DWT (Discrete Wavelet Transform) and k-NN classifiers (k-Nearest Neighbours), SRDA (Spectral Regression Discriminant Analysis) and FDA (Fisher Discriminant Analysis). This approach was first successfully applied by the team of R. Wiśniewski, P. Przymus and K. Rykaczewski [9] [10].…”

Section: Commercialisation Of Test Resultsmentioning

confidence: 99%

Biomonitoring of Inland and Inshore Waters with Use of Dreissena Polymorpha Mussels

Matuszak¹,

Grodzicki²,

Jankowski

et al. 2015

Polish Hyperbaric Research

View full text Add to dashboard Cite

The pollution of water that is used for consumption and in agricultural holdings contributes to an increased mortality rate, inhibition of growth and physiological functions, changes in the DNA (genotoxicity), changes within tissues (cytotoxicity) and organs of individuals who are exposed to chemical components. One of the most dangerous toxin classes which have effect on animals and humans who come into contact with contaminated water is the class of cyanobacterial toxins released by dying cyanobacteria. They contribute to very serious health conditions and also to fatalities. Toxins of this type are relatively difficult to detect on account of their seasonal changeability in blooming. One of the most effective methods of detecting water contamination automatically and continuously is biomonitoring with the use of Dreissena polymorpha mussels.

show abstract

Section: Commercialisation Of Test Resultsmentioning

confidence: 99%

Biomonitoring of Inland and Inshore Waters with Use of Dreissena Polymorpha Mussels

Matuszak¹,

Grodzicki²,

Jankowski

et al. 2015

Polish Hyperbaric Research

View full text Add to dashboard Cite

show abstract

“…Even on low-end computer, features extraction and classification of 16 min 40 s of observation from one sensor (i.e. fragment) does not exceeds 1 s. For details on used hardware and features algorithm performance see [20,Section 5]. We have used mlpy [30] as machine learning framework (see documentation for details of implementation and performance).…”

Section: Algorithm Performancementioning

confidence: 99%

“…With an algorithm constructed in such a way, we find the optimal parameter values (e.g. for threshold and decomposition level) using 30% of the data and event markers (see [20]). For comparing the correlation between researchers and the algorithm, we use the Tversky index defined as follows:…”

Section: Automatic Extraction Of Elementary Eventsmentioning

confidence: 99%

Zebra mussels’ behaviour detection, extraction and classification using wavelets and kernel methods

Przymus

Rykaczewski

Winiewski

2014

Future Generation Computer Systems

Self Cite

View full text Add to dashboard Cite

“…Wavelet transform has the advantage of processing information from nonstationary signals and could extract multiresolution spatial-temporal features. Wavelet transform is adopted to analyze the individual movement trajectories [ 31 ]. A discrete wavelet transform is presented to select optimal features from behavioral data [ 32 ].…”

Section: Toxic Analysismentioning

confidence: 99%

Aquatic Toxic Analysis by Monitoring Fish Behavior Using Computer Vision: A Recent Progress

Xia

Zuo-yi

et al. 2018

Journal of Toxicology

View full text Add to dashboard Cite

Video tracking based biological early warning system achieved a great progress with advanced computer vision and machine learning methods. Ability of video tracking of multiple biological organisms has been largely improved in recent years. Video based behavioral monitoring has become a common tool for acquiring quantified behavioral data for aquatic risk assessment. Investigation of behavioral responses under chemical and environmental stress has been boosted by rapidly developed machine learning and artificial intelligence. In this paper, we introduce the fundamental of video tracking and present the pioneer works in precise tracking of a group of individuals in 2D and 3D space. Technical and practical issues suffered in video tracking are explained. Subsequently, the toxic analysis based on fish behavioral data is summarized. Frequently used computational methods and machine learning are explained with their applications in aquatic toxicity detection and abnormal pattern analysis. Finally, advantages of recent developed deep learning approach in toxic prediction are presented.

show abstract

Application of Wavelets and Kernel Methods to Detection and Extraction of Behaviours of Freshwater Mussels

Cited by 7 publications

References 14 publications

Biomonitoring of Inland and Inshore Waters with Use of Dreissena Polymorpha Mussels

Biomonitoring of Inland and Inshore Waters with Use of Dreissena Polymorpha Mussels

Zebra mussels’ behaviour detection, extraction and classification using wavelets and kernel methods

Aquatic Toxic Analysis by Monitoring Fish Behavior Using Computer Vision: A Recent Progress

Contact Info

Product

Resources

About