No abstract

The aim of this paper is to study the human Heart Rate (HR) response during walking, cycling and rowing exercises using linear time varying (LTV) models. We used the frequency of exercise locomotion as the input to the model. This frequency characterizes the stride rate, cadence rate and strokes rate of the walking, cycling and rowing exercises respectively. The time varying parameters in the LTV models were estimated by the Kalman Filter (KF). The results in this study demonstrate that HR responses to these exercises exhibit some degree of time varying nature.

A system identification of a two-wheeled robot (TWR) using a data-driven approach from its fundamental nonlinear kinematics is investigated. The fundamental model of the TWR is implemented in a Simulink environment and tested at various input/output operating conditions. The testing outcome of TWR’s fundamental dynamics generated 12 datasets. These datasets are used for system identification using simple autoregressive exogenous (ARX) and non-linear auto-regressive exogenous (NLARX) models. Initially the ARX structure is heuristically selected and estimated through a single operating condition. We conclude that the single ARX model does not satisfy TWR dynamics for all datasets in term of fitness. However, NLARX fitted the 12 estimated datasets and 2 validation datasets using sigmoid nonlinearity. The obtained results are compared with TWR’s fundamental dynamics and predicted outputs of the NLARX showed more than 98% accuracy at various operating conditions.

The aim of the study is to regulate the human heart rate (HR) response to a pre-defined reference profile during aerobic activities of unknown type. A novel feature of the designed control system is obtained to generate the desired rhythmic movements, which is required to achieve the target HR profile during aerobic activities of unknown type. These rhythmic movements or frequency of locomotion is known as the exercise rate (ER) and is quantified as a fundamental measure of exercise intensity. The relationship between ER and HR is modelled by using a Linear Time Varying (LTV) system. The parameters of the model are estimated using a Kalman Filter. Based on this model, a robust adaptive H ∞ controller is designed. The H ∞ controller generates target ER (ER T) corresponding to target HR (HR T). This ER T is communicated to the exercising subject by using a human actuating System (HAS). The role of HAS is to achieve (ER T). To validate the performance of the system, it is tested on 6 healthy subjects during rowing and cycling exercises. The results demonstrate that the designed control system can regulate HR at a given profile with an average root mean square error (RM SE) of 3.1857 bpm and 2.9396 bpm for rowing and cycling, respectively. The developed system can be used for designing an optimal exercising protocol for individuals.

With the increase in energy demand, renewable energy has become a need of almost every country. Solar Energy is an important constituent of it and contributes a large portion in it. Forecasting the output power of a Photovoltaic (PV) system has always been a challenging problem in the power sector from the last few decades. The output power of a PV system depends upon several environmental factors such as irradiance (G), temperature (T), humidity (H), wind speed (W), provided the tilt angle is kept constant, among which the vital role is played by irradiance. Researchers have utilized several techniques to accurately predict the output power of PV module but every method has various pros and cons. In this paper, an experimental measurement dataset of 28296 samples with all the environmental parameters mentioned above are taken as the inputs and power as its output, of a Poly-Silicon (Poly-Si) PV module, is trained through Artificial Neural Network (ANN), to predict the output power accurately. The proposed ANN contains a layer size of 15 and training algorithm used is Levenberg-Marquardt. A detailed analysis and preprocessing of the data is carried out through Pearson's correlation method prior to training. The hyperparameters of Neural Network tuning are selected through heuristic method. The data division is done randomly with 70 % dataset used for training, 15 % dataset used for each validation and testing. The statistical results show that ANN accurately predicted the power output of PV module. The regression analysis values acquired are 98 % and the MSE of all the three phases is 0.0604.INDEX TERMS Artificial Neural Network (ANN), Environmental, Photovoltaic (PV) system, Renewable Energy (RE)

The aim of this paper is to develop the self biofeedback (SBF) control of oxygen consumption (Vo2) during cycling exercise. The developed system uses an estimator that can predict Vo2 in real time by using the measurements of heart rate (HR), respiratory rate (RespR) and frequency of exercising activity, this terms is known as Exercise Rate (ER). The biofeedback command is given to the exercising subject in terms of the desired action required by the subject to achieve the targeted Vo2 (Vo2target) profile. The desired action is determined by the SBF system based on the current estimates of Vo2 and is communicated to the exercising subject by flashing an indicator on the computer screen. The results obtained in this study demonstrate that the estimator developed for cycling exercise is capable of estimating Vo2 in real time. The developed system is tested on six healthy male subjects. The obtained results show that the SBF system performs well with the average steady state error in terms of Root Mean Square Error (RMSE) of 1 ml/min/Kg during low intensity exercise and with RMSE of 1.6426 ml/min/Kg during high intensity exercise.

Physical exercise has significant benefits for humans in improving the health and quality of their lives, by improving the functional performance of their cardiovascular and respiratory systems. However, it is very important to control the workload, e.g. the frequency of body movements, within the capability of the individual to maximise the efficiency of the exercise. The workload is generally represented in terms of heart rate (HR) and oxygen consumption (VO 2 ). We focus particularly on the control of HR and VO 2 using the workload of an individual body movement, also known as the exercise rate (ER), in this research.The first part of this report deals with the modelling and control of HR during an unknown type of rhythmic exercise. A novel feature of the developed system is to control HR via manipulating ER as a control input. The relation between ER and HR is modelled using a simple autoregressive model with unknown parameters. The parameters of the model are estimated using a Kalman filter and an indirect adaptive H ∞ controller is designed. The performance of the system is tested and validated on six subjects during rowing and cycling exercise. The results demonstrate that the designed control system can regulate HR to a predefined profile.The second part of this report deals with the problem of estimating VO 2 during rhythmic exercise, as the direct measurement of VO 2 is not realisable in these environments. Therefore, easy-to-use sensors are used to non-invasively measure HR, RespR, and ER to estimate VO 2 . The developed approach for cycling and rowing exercise predicts the percentage change in maximum VO 2 from the resting to the exercising phases, using a Hammerstein model. These VO 2 estimators were validated on six subjects by comparing the measured and estimated values of VO 2 for quality of fit. Results show that the average quality of fit in both exercises is improved as the intensity of exercise is increased. This shows that the relation between ER, RespR, HR and VO 2 is highly correlated during high-intensity exercise. Consequently, a selfbiofeedback (SBF) control of VO 2 is implemented in real time and the experimental results show the effectiveness of the proposed approach. Moreover, the efficiency of the SBF system is also analysed to show that it is more efficient in controlling VO 2 iii during low-intensity exercise. This research can facilitate the efficacy of rhythmic exercise for gaited and cardiovascular patients.

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.