This research investigates the application of multisource data fusion using a Multi-Layer Perceptron (MLP) for Human Activity Recognition (HAR). The study integrates four distinct open-source datasets—WISDM, DaLiAc, MotionSense, and PAMAP2—to develop a generalized MLP model for classifying six human activities. Performance analysis of the fused model for each dataset reveals accuracy rates of 95.83 $\mathrm{\%}$ for WISDM, 97 $\mathrm{\%}$ for DaLiAc, 94.65 $\mathrm{\%}$ for MotionSense, and 98.54 $\mathrm{\%}$ for PAMAP2. A comparative evaluation was conducted between the fused MLP model and the individual dataset models, with the latter tested on separate validation sets. The results indicate that the MLP model, trained on the fused dataset, exhibits superior performance relative to the models trained on individual datasets. This finding suggests that multisource data fusion significantly enhances the generalization and accuracy of HAR systems. The improved performance underscores the potential of integrating diverse data sources to create more robust and comprehensive models for activity recognition.

A PANDA ring resonator circuit has been applied to the measurement of muscle actions, measuring signals created by facial muscle contractions. A system, which is called the Optical Muscle Sensing System, was developed which uses sensors to measure the mechanism of facial muscle contractions and the strength of contraction and degrees of perturbation of the facial muscles that are used directly for each facial gesture. The signal data was obtained from the simulation of the facial gestures and this data was applied in the classification of the facial gesture signals of each particular gesture. Facial gestures include blinking, smiling, grimacing and various other contortions of the face which may imply emotions and are part of normal human communication. Understanding of these mechanisms will be useful and applicable to facial rehabilitation services.