System for recognizing hand gestures based on microcontroller board data and neural network

U ovom radu pokriven je čitav proces izrade sustava koji koristi neuronske mreže. Mikrokontrolerska pločica, Arduino Nano, sa senzorom MPU-6050, korištena je kao izvor podatka. Pomoću nje prikupljeni su podaci o gestama. Za to je bila izrađena aplikacija u programskom jeziku Processing, koja tražili podatke od mikrokontrolera te dodaje odgovarajuću oznaku geste na te podatke. Podaci su zatim zapisani u .csv datoteku. Neuronska mreža koja je implementirana je unaprijedna neuronska mreža, a algoritam za učenje je algoritam propagacije pogreške unatrag. Nakon što smo istrenirali mrežu i dobili model koji prepoznaje geste, a taj model je ugrađen u aplikaciju za prepoznavanje u stvarnom vremenu.This paper covers the entire process of making system using neural networks. The Arduino Nano, microcontroller board, with the MPU-6050 sensor, was used as a source of data. Using it gestures data was collected. For this, an application was developed in the Programming language Processing, that asked for data from the microcontroller and added the corresponding gesture label to data. The data was then written to a .csv file. The neural network that was implemented is a feedforward neural network, and the algorithm for learning is the backpropagation. After we've trained the network and got a model for recognizing gestures, this model was embedded in the real-time recognition app