The aim of this paper is to develop estimator that can predict oxygen consumption (V(O2)) during cycling and rowing exercises, by using non-invasive and easily measurable quantities such as heart rate (HR), respiratory rate (RespR) and frequency of exercising activity. The frequency of exercise is quantified as a universal measure of exercise intensity and is known as Exercise Rate (ER). This ER is responsible for deviation in V(O2) (ΔV(O2)), HR (ΔHR), and RespR (ΔRespR) from their respective baseline measurements during exercise. Therefore, ΔV(O2) can be estimated from Δ, ΔRespR and ER. The resting measured of V(O2) is referred as V(O(2rest)); this is computed from the physical fitness of an individual. The Hammerstein model is adopted for the estimation of ΔV(O2). Results in this study demonstrate that the developed estimators for each type of exercise are capable of estimating V(O2) by adding up V(O(2rest)) and ΔV(O2) at various intensities during cycling and rowing.