The feature extraction and classification is an important stage in human activity recognition (HAR). In this paper, we discuss human activity classification using wearable multimodal wireless sensors in healthcare, especially in individuals with cardiovascular disease (CVD). We use majorly principle component analysis (PCA) on data collected using accelerometers and gyroscope data from subjects for 15 Local Muscular Endurance (LME) exercises. Well-known time domain and frequency-domain signal characteristic features are extracted and classification of best features is carried out with PCA. Supervised learning algorithms based with support vector machines (SVM) are used further for recognition of movement patterns.