Current recognition system have some problems

such as divulging privacy

binding human body and low recognition precision

which make it difficult to achieve clinical application.In order to improve the practicability of sleeping posture recognition

a method based on support vector machine（SVM）is proposed to classify six sleeping posture images which collected by flexible pressure sensor without restriction.The genetic algorithm（GA）is applied to optimize the critical parameters of SVM.The experimental results show that the method can accurately recognize the sleeping postures with an average recognition accuracy of 93.3 %

which means it has a good application prospect in the field of clinical nursing.