In order to early diagnosis and treatment of knee abnormalities, in this study an automated diagnosis system using wearable EMG and goniometer sensors is proposed. Eight different classification techniques are investigated with a set of time-domain features. The experiments are conducted with 22 subjects' data and the best accuracy of 97.17% is achieved based on the Bagged Decision Trees classifier. We have also evaluated the classifications quality with Fixed-size Overlapping Sliding Window (FOSW) segmentation technique where SVM and Bagged Decision Trees classifiers could obtain the accuracy of 100% in distinguishing healthy subjects from people with knee abnormality.