Klasifikace vzorů pomocí fuzzy neuronových sítí

| Kategorie: Diplomové, bakalářské práce  | Tento dokument chci!

Práce popisuje základy principu funkčnosti neuronů a vytvoření umělých neuronových sítí. Je zde důkladně popsána struktura a funkce neuronů a ukázán nejpoužívanější algoritmus pro učení neuronů. Základy fuzzy logiky, včetně jejich výhod a nevýhod, jsou rovněž prezentovány. Detailněji je popsán algoritmus zpětného šíření chyb a adaptivní neuro-fuzzy inferenční systém. Tyto techniky poskytují efektivní způsoby učení neuronových sítí.

Vydal: FCC Public s. r. o. Autor: Tamás Ollé

Strana 38 z 67

Vámi hledaný text obsahuje tato stránku dokumentu který není autorem určen k veřejnému šíření.

Jak získat tento dokument?






Poznámky redaktora
1.1) where length the frame sn nth sample the frame Finally, the signal suppressed the edges frames that any given time the most important will the central part. Otherwise, frequency components that not exist the original signal would be added the speech signal and distort it. In practise, however, need limit the input signal with band-pass filter or sample with higher sampling frequency and then apply digital antialiasing filter. first frame from 25 ms, second frame from and on). Since the component present only due quantization error offset it has effect speech recognition, but may have negative impact the used algorithms which assume signal with zero components. For the purpose speech recognition the division ms where every frame covers the previous one (i.e. component is subtracted from each frame according the formula:     1 0 ' N i inn s N ss (6.1 Signal preparation Before processing with neural network, the signal has processed to contain only information relevant for recognition. The most often used sampling rate according the sampling theorem kHz for speech signal processing (carrying only human speech), since for most phonemes, almost all the energy contained the 100 kHz range.1 Division into frames and preprocessing The basis any speech processing record the signal.29 6. Signal processing performed only once for each time frame and, moreover, is largely accomplished the hardware. Furthermore, the signal divided into short frames time which are processed separately. This process of reducing the amount information the speech signal called parameterization. Therefore additional transformation is applied the final framework which helps the further work with the samples: averaging and weighting with Hamming window. 6. Furthermore, useful adjust the signal into an appropriate format that the recognizer will able work well with. also avoids potential signal distortion the edges the frame where signal was cut off. For this purpose . This means that inappropriate or useless content has removed. This section includes sampling and quantization audio input which mostly provided by specialized hardware where the user’s task only setting the sampling frequency