Physical activity (PA) quantification by estimating energy expenditure (EE) is essential to health. Reference methods for EE estimation often involve expensive and cumbersome systems to wear. To address these problems, light-weighted and cost-effective portable devices are developed. Respiratory magnetometer plethysmography (RMP) is among such devices, based on the measurements of thoraco-abdominal distances. The aim of this study was to conduct a comparative study on EE estimation with low to high PA intensity with portable devices including the RMP. Fifteen healthy subjects aged 23.84±4.36 years were equipped with an accelerometer, a heart rate (HR) monitor, a RMP device and a gas exchange system, while performing 9 sedentary and physical activities: sitting, standing, lying, walking at 4 and 6 km/h, running at 9 and 12 km/h, biking at 90 and 110 W. An artificial neural network (ANN) as well as a support vector regression algorithm were developed using features derived from each sensor separately and jointly. We compared also three validation approaches for the ANN model: leave one out subject, 10 fold cross-validation, and subject-specific. Results showed that 1. for portable devices the RMP provided better EE estimation compared to accelerometer and HR monitor alone; 2. combining the RMP and HR data further improved the EE estimation performances; and 3. the RMP device was also reliable in EE estimation for various PA intensities.