Chronic lung disease, in which the airway gets obstructed, is known as Chronic Obstructive Pulmonary Disease (COPD). According to WHO, COPD kills more than 3 million people every year. Spirometry is used to diagnose COPD; has many limitations. There is a need for physiologically accurate and easy to perform diagnosis technology. Researchers confirmed the activity of sternomastoid muscle in COPD with research limitations of; sample size, few time-domain features, lack of onset detection and the non-stationary nature ofElectromyographical signals (EMG). In this, paper COPD diagnosis is made by analyzing Sternomastoid muscle of respiration in time, frequency and time-frequency domain. The slope-based onset detection algorithm andconduction velocity lead to an improvement in COPD detection accuracy to 98.61%. The feature selection algorithm is developed for the selection of the most significant features. A single frequency Continuous Wavelet Transform (CWT) analysis at 7, 8 and 10 Hz of frequency is used to extract features and to classify COPD in its grades, leading to the classification accuracy of 85.89%. Non-invasive, easy to use COPD diagnosis and classification technique is developed.