Wearing transfemoral prosthesis is the only way to complete daily physical activity for amputees. Motion pattern recognition is important for the control of prosthesis, especially in the recognizing swing phase and stance phase. In this paper, it is reported that surface electromyography (sEMG) signal is used in swing and stance phase recognition. sEMG signal of related muscles was sampled by Infiniti of a Canadian company. The sEMG signal was then filtered by weighted filtering window and analyzed by height permitted window. The starting time of stance phase and swing phase is determined through analyzing special muscles. The sEMG signal of rectus femoris was used in stance phase recognition and sEMG signal of tibialis anterior is used in swing phase recognition. In a certain tolerating range, the double windows theory, including weighted filtering window and height permitted window, can reach a high accuracy rate. Through experiments, the real walking consciousness of the people was reflected by sEMG signal of related muscles. Using related muscles to recognize swing and stance phase is reachable. The theory used in this paper is useful for analyzing sEMG signal and actual prosthesis control.
In order to improve the speech quality and auditory perceptiveness of electronic cochlear implant under strong noise background, a speech enhancement system used for electronic cochlear implant front-end was constructed. Taking digital signal processing (DSP) as the core, the system combines its multi-channel buffered serial port (McBSP) data transmission channel with extended audio interface chip TLV320AIC10, so speech signal acquisition and output with high speed are realized. Meanwhile, due to the traditional speech enhancement method which has the problems as bad adaptability, slow convergence speed and big steady-state error, versiera function and de-correlation principle were used to improve the existing adaptive filtering algorithm, which effectively enhanced the quality of voice communications. Test results verified the stability of the system and the de-noising performance of the algorithm, and it also proved that they could provide clearer speech signals for the deaf or tinnitus patients.
On account of the mechanical disturbance of external chest pressing to electrocardiogram (ECG) signal, the ECG rhythm cannot be identified reliably during the cardio-pulmonary resuscitation period. Whereas the possibility of successful resuscitation will be lowered due to interrupted external chest pressing, a new filtering algorithm, enhanced leastmean-square (eLMS) algorithm, was proposed and developed in our laboratory. The algorithm can filter the disturbance of external chest pressing without the support of hardware reference signal and correctly identify ventricular fibrillation (VF) rhythm and normal sinus rhythm in case of uninterrupted external chest pressing. Without other reference signals, this algorithm realizes filtering only through the interrupted electrocardiograma (cECG) signal. It was verified with ECG signal and disturbance signal under different signal to noise ratios and contrasted with other mature algorithms. The verification results showed that the identification effect of eLMS was superior to those of others under different signal to noise ratios. Furthermore, ECG rhythm can be correctly identified only through cECG signal. This algorithm not only reduces the research and development(R & D)costs of automated external defibrillator but also raises the identification accuracy of ECG rhythm and the possibility of successful resuscitation.
The paper introduces a training system for foot ulcer patients based on three axis accelerometer, which uses three axis accelerometer and Apple mobile phone platform to guide foot ulcer patients to carry out a variety of lower limb muscle tissues training. The acceleration values of three directions for the foot training is obtained by analog-to-digital conversion and transmitted to the Apple mobile phone via its Bluetooth low energy. The Apple mobile phone accomplishes acceleration data preprocessing, numerical filtering and adaptive dual-threshold processing by our developed application program, so as to achieve the purpose of foot gesture recognition. The experimental result shows that the design can effectively present the training situation and effect of patients, encourage patients to adhere to the training, and provide some reference data for doctors and patients.
Electrocardiogram (ECG) signals are easily disturbed by internal and external noise, and its morphological characteristics show significant variations for different patients. Even for the same patient, its characteristics are variable under different temporal and physical conditions. Therefore, ECG signal detection and recognition for the heart disease real-time monitoring and diagnosis are still difficult. Based on this, a wavelet self-adaptive threshold denoising combined with deep residual convolutional neural network algorithm was proposed for multiclass arrhythmias recognition. ECG signal filtering was implemented using wavelet adaptive threshold technology. A 20-layer convolutional neural network (CNN) containing multiple residual blocks, namely deep residual convolutional neural network (DR-CNN), was designed for recognition of five types of arrhythmia signals. The DR-CNN constructed by residual block local neural network units alleviated the difficulty of deep network convergence, the difficulty in tuning and so on. It also overcame the degradation problem of the traditional CNN when the network depth was increasing. Furthermore, the batch normalization of each convolution layer improved its convergence. Following the recommendations of the Association for the Advancements of Medical Instrumentation (AAMI), experimental results based on 94 091 2-lead heart beats from the MIT-BIH arrhythmia benchmark database demonstrated that our proposed method achieved the average detection accuracy of 99.034 9%, 99.498 0% and 99.334 7% for multiclass classification, ventricular ectopic beat (Veb) and supra-Veb (Sveb) recognition, respectively. Using the same platform and database, experimental results showed that under the comparable network complexity, our proposed method significantly improved the recognition accuracy, sensitivity and specificity compared to the traditional deep learning networks, such as deep Multilayer Perceptron (MLP), CNN, etc. The DR-CNN algorithm improves the accuracy of the arrhythmia intelligent diagnosis. If it is combined with wearable equipment, internet of things and wireless communication technology, the prevention, monitoring and diagnosis of heart disease can be extended to out-of-hospital scenarios, such as families and nursing homes. Therefore, it will improve the cure rate, and effectively save the medical resources.
In order to eliminate the influence of motion artifacts, high-frequency noise and baseline drift on photoplethysmographic (PPG), and to obtain the accurate value of heart rate in motion state, this paper proposed a de-noising method of PPG signal based on normalized least mean square (NLMS) adaptive filtering combining ensemble empirical mode decomposition(EEMD). Firstly, the PPG signal containing noise is passed through an adaptive filter with a 3-axis acceleration sensor as a reference signal to filter out motion artifacts. Secondly, the PPG signal is decomposed by EEMD to obtain a series of intrinsic modal function (IMF) according to the frequency from high to low. The threshold range of the signal is judged by the permutation entropy (PE) criterion, thereby filtering out the high frequency noise and the baseline drift. The experimental results show that the Pearson correlation coefficient between the calculated heart rate of PPG signal and the standard heart rate based on electrocardiogram (ECG) signal is 0.731 and the average absolute error percentage is 6.10% under different motion states, which indicates that the method can accurately calculate the heart rate in moving state and is beneficial to the physiological monitoring under the state of human motion.
Image registration is of great clinical importance in computer aided diagnosis and surgical planning of liver diseases. Deep learning-based registration methods endow liver computed tomography (CT) image registration with characteristics of real-time and high accuracy. However, existing methods in registering images with large displacement and deformation are faced with the challenge of the texture information variation of the registered image, resulting in subsequent erroneous image processing and clinical diagnosis. To this end, a novel unsupervised registration method based on the texture filtering is proposed in this paper to realize liver CT image registration. Firstly, the texture filtering algorithm based on L0 gradient minimization eliminates the texture information of liver surface in CT images, so that the registration process can only refer to the spatial structure information of two images for registration, thus solving the problem of texture variation. Then, we adopt the cascaded network to register images with large displacement and large deformation, and progressively align the fixed image with the moving one in the spatial structure. In addition, a new registration metric, the histogram correlation coefficient, is proposed to measure the degree of texture variation after registration. Experimental results show that our proposed method achieves high registration accuracy, effectively solves the problem of texture variation in the cascaded network, and improves the registration performance in terms of spatial structure correspondence and anti-folding capability. Therefore, our method helps to improve the performance of medical image registration, and make the registration safely and reliably applied in the computer-aided diagnosis and surgical planning of liver diseases.
Traditional methods of non-contact human respiratory rate measurement usually require complex devices or algorithms. Aiming at this problem, a non-contact respiratory rate measurement method based on only the RGB video information was proposed in this paper. The method consisted of four steps. Firstly, spatial filtering was applied to each frame of the input video. Secondly, a gray compensation algorithm was used to compensate for the gray level change caused by the environmental light. Thirdly, the gray levels of each pixel over time were filtered separately by a low-pass filter. Finally, the region of interest was determined based on the filtering results, and the respiration rate of the human is measured. The physical measurement experiments were designed, and the measurement accuracy was compared with that of the biological radar. The error of the proposed method was between − 5.5% and 3% in different detection directions. The results show that the non-contact respiration rate measurement method can effectively measure the human respiration rate.