| Popis: |
As a social being, humans must do a variety of activities ranging from waking up in the morning to going back to sleep at night. Of the many activities, this research wants to find out how many activities humans do, for example how many times people walk, lie down, and so on in a day. To find out the number of these activities, this study uses Learning Vector Quantization (LVQ) method for recognizing human activities. This study uses 561 features from 1000 data to be used for the training process and 500 data to be used in the testing process. Data with a large number of features can affect the length of the calculation process. Because LVQ uses features as input data, we need a method that can reduce the number of features. One method that can be used is the Particle Swarm Optimization (PSO) method. The training process is carried out using the PSO selection feature with the parameters of the number of particles 30, maximum iterations 30, the value of ω 0.3, Φp of 0.3 and Φg of 0.8. From the training process, gBest and LVQ parameters are obtained with a value of α 0.1, a reduction of α (dec α) 0.5, minimum α 0,0000001 and a maximum of epoch or iteration 5 with a final accuracy of 17%. |
