A Laguerre-Volterra network model based on ant colony optimization applied to evaluate EMG-force relationship in the muscle fatigue state.

With the accuracy and convenience improvement of electromyographic (EMG) acquired by wearable devices, EMG is gradually used to evaluate muscle force signal, a non-invasive evaluation method. However, the relationship between EMG and force is a complex nonlinear relationship, even which will change with different movements and different muscle states. Therefore, it is difficult to evaluate this nonlinear EMG-force relationship, especially when the muscle state gradually transits from non-fatigue to deep fatigue. For more accurate values of force in human fatigue state, this paper proposes a dual-input Laguerre-Volterra network (LVN) model based on ant colony optimization. First, the changes in 19 EMG features are discussed with increasing fatigue. We also consider two non-Gaussian features: kurtosis and negentropy in the 19 features. Later, 11 EMG fatigue features are picked out according to the fatigue test. Then, the preprocessed EMG and a composite signal of the 11 fatigue features are simultaneously input into the LVN model. Subsequently, the ant colony optimization algorithm is selected to train the model parameters. At the same time, a penalty term that we defined is introduced into the model cost function to adjust the weight of each feature adaptively. Finally, some experiments prove that the LVN model could quick fit the accurate force signal in five fatigue stages, such as non-fatigue, slight fatigue, mild fatigue, severe fatigue, and extreme fatigue. This LVN model can quickly transform EMG into strength signal in real time, which is suitable for people to observe muscle strength by a wearable device and makes it easy to detect the muscle current state. This model has good stability and can remain effective for a long time with training once, which provides convenience for the users of wearable devices.

A new particle filter algorithm filtering motion artifact noise for clean electrocardiogram signals in wearable health monitoring system.

With the evolution of wearable systems, more and more people tend to wear wearable devices for health monitoring during sports. However, a large amount of motion artifact noise is introduced at this time, which is difficult to filter out due to its stochasticity. The amplitude and characteristics of motion artifact noise vary with changes in motion intensity. In order to filter out the motion artifact noise, the paperproposes a new particle algorithm, which can detect the intensity of the motion artifact for adaptive filtering, especiallysuitable for wearable health monitoring systems. In this algorithm, variational mode decomposition was first introduced to analyze the noisy electrocardiogram (ECG) signal in order to find the clean components. Then, the Laguerre estimation technique was applied to obtain an accurate ECG polar model. Taking this model as the state equation, a particle filter algorithm was defined to filter out the motion artifact noise. In the particle filter algorithm, we defined a parameter γ whose values were obtained from the six-axis data of motion sensor MPU6050 in our wearable device. This parameter γ could reflect the current noise levels and adaptively update the particle weights. Finally, some exercise experiments proved that the parameter γ could map the motion artifacts in real time and also demonstrated the superiority of the algorithm in terms of signal-to-noise ratio improvement and error reduction compared to other algorithms. The new particle filter algorithm proposed in this paper combines the six-axis data (three-axis accelerometer and three-axis gyroscope) with the ECG signal to effectively eliminate a large amount of motion artifact noise, thus solving the problem of excess noise from wearable devices when people are exercising, allowing them to accurately obtain real-time ECG health information.

A strong anti-noise segmentation algorithm based on variational mode decomposition and multi-wavelet for wearable heart sound acquisition system.

Wearable devices have now been widely used in the acquisition and measurement of heart sound signals with good effect. However, the wearable heart sound acquisition system (WHSAS) will face more noise compared with the traditional system, such as Gaussian white noise, powerline interference, colored noise, motion artifact noise, and lung sound noise, because users often wear these devices for running, walking, jumping or various strong noise occasions. In a strong noisy environment, WHSAS needs a high-precision segmentation algorithm. This paper proposes a segmentation algorithm based on Variational Mode Decomposition (VMD) and multi-wavelet. In the algorithm, various noises are layered and filtered out using VMD. The cleaner signal is fed into multi-wavelet to construct a time-frequency matrix. Then, the principal component analysis method is applied to reduce the dimension of the matrix. After extracting the high order Shannon envelope and Teager energy envelope of the heart sound, we accurately segment the signals. In this paper, the algorithm is verified through our developing WHSAS. The results demonstrate that the proposed algorithm can achieve high-precision segmentation of the heart sound under a mixed noise condition.