20.500.12556/RUL-91112 RAZPOZNAVANJE VRSTNO-SPECIFIČNIH VIBRACIJSKIH SIGNALOV ŠKRŽATKOV SAMCEV VRSTE A. BICINCTA »DRAGONJA« IN REPRODUKCIJA ODGOVOROV SAMICE V REALNEM ČASU RECOGNIZING SPECIES-SPECIFIC VIBRATIONAL SIGNALS OF A. BICINCTA »DRAGONJA« MALES AND REPRODUCING FEMALE REPLIES IN REAL TIME Škržatki spadajo v skupino najpomembnejših prenašalcev bolezni rastlin. Razpoznavanje in lokalizacija potencialnih partnerjev poteka izključno z vrstno in spolno-specifičnimi vibracijskimi signali, ki se izmenjujejo v natančno koordiniranih duetih. V pričujočem delu je predstavljen avtonomni sistem AS1 za razpoznavanje pozivov samcev Aphrodes bicincta “Dragonja” in reprodukcijo odgovorov samice v realnem času. Navedena vrsta škržatkov je bila izbrana zaradi kompleksne strukture dueta, kjer se morajo odgovori samice zgoditi v kratkih (47–175 ms) intervalih med ponavljajočimi se elementi napeva samca, da jih ta začne iskati. Ker se pozivi samca prenašajo prek rastline, se med iskanjem spreminjajo registrirani frekvenčni parametri njegovih pozivov. Zasnovani in izdelani sta bili strojna oprema na osnovi digitalnega signalnega kontrolerja in ustrezna programska oprema AS. Algoritem AS je osnovan na metodah za razpoznavanje človeškega govora in je v grobem sestavljen iz luščenja in razvrščanja značilk. Uporabljene značilke so bili kepstralni koeficienti linearnega napovedovanja, izvedena je bila tudi primerjava računskega časa z linearnimi kepstralnimi koeficienti. Na osnovi simulacij natančnosti razpoznavanja in meritev računskih časov različnih razvrščevalnikov, specifičnega modela mešanih Gaussovih porazdelitev, metode podpornih vektorjev ter večplastnega perceptrona je bila za vedenjski poskus izbrana zadnja metoda. Zasnovan je bil tudi algoritem za pripravo učne množice za nadzorovano učenje razvrščevalnikov. Za preprečevanje vnosa iz šuma izračunanih značilk v razvrščevalnik je bil uporabljen detektor na Autonomous System osnovi sledenja vrha pasovno omejenega spektra linearnega napovedovanja. Za hitrejšo analizo avdio posnetkov, pridobljenih med vedenjskim poskusom, je bil zasnovan algoritem, ki avtomatsko izlušči relevantne karakteristične parametre. Navedeni algoritem bi bilo možno uporabiti tudi na ostalih vrstah z podobno frekvenčno-časovno strukturo vibracijskih signalov. Uspešnost delovanja AS je bila preverjena z vedenjskimi poskusi z živimi samci. Algoritem AS je uspešno razpoznal vibracijske signale A. bicincta “Dragonja” iz šuma okolice. Hitra identifikacija v realnem času je omogočila sinhronizirano predvajanje odgovorov samic. Statistične razlike v deležu samcev, ki so vzpostavili duet med AS, in živo samico ni bilo. Prav tako ni bilo razlike med uspešnostjo razpoznavanja pozivnih napevov samcev med živo samico in AS. AS je z oponašanjem dueta samice uspelo privabiti samce do vira odgovorov samice. Na osnovi rezultatov vedenjskih poskusov so bile narejene simulacije spektralnega odštevanja in meritve računske zahtevnosti te metode. Navedena metoda je izboljšala razmerje posnetkov signal-šum s pozivi samcev za 26 dB. Primerna je tudi za obdelavo signalov v realnem času na AS. Raziskane so bile tudi metode za zmanjševanje vpliva rastline na predvajani signal, ki temeljijo na inverznem filtriranju predvajanega signala. Na osnovi rezultatov simulacij metode adaptivnega filtriranja LMS2 in metode linearnega napovedovanja je bila izbrana slednja za preliminarne teste AS na rastlini. Metoda linearnega napovedovanja je uspešno zmanjšala vpliv rastline na frekvenčne parametre predvajanega signala v točki merjenja. Primarno je AS orodje za študijo vibracijske komunikacije. Na osnovi rezultatov nadaljnjih študij bi lahko za nadzor škodljivcev razvili sisteme, ki namesto pesticidov uporabljajo vibracijsko komunikacijo. Kljub trenutnim omejitvam glede zajemanja in reprodukcije vibracijskih signalov predstavlja AS izhodišče za izdelavo vibracijske pasti, ki bi privabljala in ujela samce ter prekinila razmnoževalni cikel škodljivcev. Leafhoppers are among the chief transmitters of plant disease. In the species, the recognition and discovery of potential partners takes place exclusively through species- and sex-specific vibrational signals taking place in precisely coordinated duets. This work describes an autonomous system AS, capable of recognizing the male call of the leafhopper Aphrodes bicincta “Dragonja” and generating female replies in real time. The species in question was selected as it has a complex duet structure, with the female replies having to appear in short (4–175ms) intervals between continuously repeated elements in the male call, triggering the male searching behaviour. As the male call is transmitted via the plant, a variation in the frequency parameters of the registered call can be observed during the search. Designed on the basis of a digital signal controller was special hardware, with corresponding software for the AS. The AS algorithm is based on human speech recognition methods comprising of feature extraction and classification. The features used were linear prediction cepstral coefficients, chosen after a computational time comparison with the linear frequency cepstral coefficients. The latter method was selected as the basis of the behavioural experiment based on a simulation of three different classifiers: the Gaussian mixture model, support vector machines and multilayer perceptron. An algorithm for preparing the training set for supervised classifier learning was devised. A bandwidth-limited linear prediction call activity detector based on spectrum peak tracking was used to prevent feeding the noise-based feature vectors into the classifier. For faster analysis of the audio recordings from the behavioural experiment, an algorithm was devised to automatically extract the relevant characteristic parameters. The described algorithm can also be used on other species with a similar frequency - temporal vibrational signal structure. We tested the efficiency of the AS in behavioural experiments with live males. The AS method successfully classified vibrational calls of a male A. bicincta “Dragonja” from the background noise. There was no statistical difference in percentage of males that established a duet between the AS and the live female. The mimicking of a duetting female by the AS also attracted the males to the source of the female reply. Simulations of the spectral subtraction method and the computational time measurements on the AS were based on the behavioural experiment results. The described method improved the signal-to-noise ratio of the male call recordings by 26 dB and was deemed appropriate for real-time signal recognition on the AS. Also researched were plant equalization methods based on the inverse playback signal filtering. By comparing the simulations of the LMS adaptive filtering method and the linear prediction method, the latter was chosen for tests on the plant. The linear prediction method successfully reduced the influence of the plant on the frequency parameters of the playback signal at the point of measurement. The primary purpose of the AS is to further study vibrational communication. Based on the study results, different pest control systems could be developed which would use vibrational communication instead of pesticides. Despite current limitations of the vibrational signal measurement and reproduction, the AS represents a starting point in the development of a vibrational trap which would attract and capture males and disrupt the reproduction cycle of pests. škržatki vibracijska komunikacija avtonomni sistem strojno učenje Leafhoppers vibrational communication autonomous system machine learning true false false Slovenski jezik Angleški jezik Doktorsko delo/naloga 2017-03-20 13:30:01 2017-03-20 13:30:05 2023-06-16 09:04:04 0000-00-00 00:00:00 2017 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 1970-01-01 38363 11730516 Korinsek_Gasper_-_RAZPOZNAVANJE_VRSTNO-SPECIFICNIH_VIBRACIJSKIH_SIGNALOV_SKRZATKOV_SAMCEV_VRSTE_.pdf Korinsek_Gasper_-_RAZPOZNAVANJE_VRSTNO-SPECIFICNIH_VIBRACIJSKIH_SIGNALOV_SKRZATKOV_SAMCEV_VRSTE_.pdf 1 4A9EE97C1D884395A7FFE228DC7113B9 7b8e16b4adea354b983ff0800240c68474328d71edc8c04ba49528807f7193c7 deef37cf-a1b1-11eb-a523-00155dcfd717 20.500.12556/rul/61e79683-63ee-4087-8785-5b624c63597d https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=94724 Fakulteta za elektrotehniko 0 0 0