A multi-scale attention residual-based U-Net network for stroke electrical impedance tomography.

Electrical impedance tomography (EIT), a non-invasive, radiation-free, and convenient imaging technique, has been widely used in the diagnosis of stroke. However, due to soft-field nonlinearity and the ill-posed inverse problem, EIT images always suffer from low spatial resolution. Therefore, a multi-scale convolutional attention residual-based U-Net (MARU-Net) network is proposed for stroke reconstruction. Based on the U-Net network, a residual module and a multi-scale convolutional attention module are added to the concatenation layer. The multi-scale module extracts feature information of different sizes, the attention module strengthens the useful information, and the residual module improves the performance of the network. Based on the above advantages, the network is used in the EIT system for stroke imaging. Compared with convolutional neural networks and one-dimensional convolutional neural networks, the MARU-Net network has fewer artifacts, and the reconstructed image is clear. At the same time, the reduction of noisy artifacts in the MARU-Net network is verified. The results show that the image correlation coefficient of the reconstructed image with noise is greater than 0.87. Finally, the practicability of the network is verified by a model physics experiment.

Detection of driver drowsiness level using a hybrid learning model based on ECG signals.

OBJECTIVES: Fatigue has a considerable impact on the driver's vehicle and even the driver's own operating ability. METHODS: An intelligent algorithm is proposed for the problem that it is difficult to classify the degree of drowsiness generated by the driver during the driving process. By studying the driver's electrocardiogram (ECG) during driving, two models were established to jointly classify the ECG signals as awake, stress, and fatigue or drowsiness states for drowsiness levels. Firstly, the deep learning method was used to establish the model_1 to predict the drowsiness of the original ECG, and model_2 was developed using the combination of principal component analysis (PCA) and weighted K-nearest neighbor (WKNN) algorithm to classify the heart rate variability characteristics. Then, the drowsiness prediction results of the two models were weighted according to certain rules, and the hybrid learning model combining dilated convolution and bidirectional long short-term memory network with PCA and WKNN algorithm was established, and the mixed model was denoted as DiCNN-BiLSTM and PCA-WKNN (DBPW). Finally, the validity of the DBPW model was verified by simulation of the public database. RESULTS: The experimental results show that the average accuracy, sensitivity and F1 score of the test model in the dataset containing multiple drivers are 98.79, 98.81, and 98.79 % respectively, and the recognition accuracy for drowsiness or drowsiness state is 99.33 %. CONCLUSIONS: Using the proposed algorithm, it is possible to identify driver anomalies and provide new ideas for the development of intelligent vehicles.

A cascaded convolutional neural networks for stroke detection imaging.

In recent years, electrical impedance tomography has widely been used in stroke detection. To improve the prediction accuracy and anti-noise ability of the system, the inverse problem of electrical impedance tomography needs to be solved, for which cascade convolutional neural networks are used. The proposed network is divided into two parts so that the advantages can be compounded when parts of a network are cascaded together. To get high-resolution imaging, an optimized network based on encoding and decoding is designed in the first part. The second part is composed of a residual module, which is used to extract the characteristics of voltage information and ensure that no information is lost. The anti-noise performance of the network is better than other networks. In physical experiments, it is also proved that the algorithm can roughly restore the location of the object in the field.

A three-dimensional adaptive rational interpolation algorithm for removing TMS-EEG pulse artifacts.

Objective.Transcranial magnetic stimulation in combination with electroencephalography (TMS-EEG) has been widely used to study the reactivity and connectivity of brain regions. In order to efficiently and fast solve the pulse artifacts problem caused by TMS electromagnetic pulses, a three-dimensional adaptive rational quadratic Hermite interpolation algorithm is proposed.Approach.Firstly, a three-dimensional signal matrix is obtained by a signal recombination algorithm, where the removed window is automatically obtained by a derivative threshold. Secondly, the adaptive rational quartic Hermite interpolation algorithm is used to interpolate the removed window. Finally, the performance of the algorithm is verified using simulated and public database data.Main results.The simulation results show that the proposed algorithm improves the SNR by 23.88%-47.60%, reduces the RMSE by 46.52%-81.11%, reduces the average MAE by 47.83%-58.33%, and reduces the time consumption of the proposed algorithm by 45.90% compared with the piecewise cubic Hermite interpolation algorithm.Significance.Therefore, TMS-EEG pulse artifacts can be removed effectively and quickly with the proposed algorithm.

Compact and ordered swarms of unmanned aerial vehicles in cluttered environments.

The globally coordinated motion produced by the classical swarm model is typically generated by simple local interactions at the individual level. Despite the success of these models in interpretation, they cannot guarantee compact and ordered collective motion when applied to the cooperation of unmanned aerial vehicle (UAV) swarms in cluttered environments. Inspired by the behavioral characteristics of biological swarms, a distributed self-organized Reynolds (SOR) swarm model of UAVs is proposed. In this model, a social term is designed to keep the swarm in a collision-free, compact, and ordered collective motion, an obstacle avoidance term is introduced to make the UAV avoid obstacles with a smooth trajectory, and a migration term is added to make the UAV fly in a desired direction. All the behavioral rules for agent interactions are designed with as simple a potential function as possible. And the genetic algorithm is used to optimize the parameters of the model. To evaluate the collective performance, we introduce different metrics such as (a) order, (b) safety, (c) inter-agent distance error, (d) speed range. Through the comparative simulation with the current advanced bio-inspired compact and Vasarhelyi swarm models, the proposed approach can guide the UAV swarm to pass through the dense obstacle environment in a safe and ordered manner as a compact group, and has adaptability to different obstacle densities.

Review of microwave imaging algorithms for stroke detection.

Microwave imaging is one of the rapidly developing frontier disciplines in the field of modern medical imaging. The development of microwave imaging algorithms for reconstructing stroke images is discussed in this paper. Compared with traditional stroke detection and diagnosis techniques, microwave imaging has the advantages of low price and no ionizing radiation hazards. The research hotspots of microwave imaging algorithms in the field of stroke are mainly reflected in the design and improvement of microwave tomography, radar imaging, and deep learning imaging. However, the current research lacks the analysis and combing of microwave imaging algorithms. In this paper, the development of common microwave imaging algorithms is reviewed. The concept, research status, current research hotspots and difficulties, and future development trends of microwave imaging algorithms are systematically expounded. The microwave antenna is used to collect scattered signals, and a series of microwave imaging algorithms are used to reconstruct the stroke image. The classification diagram and flow chart of the algorithms are shown in this Figure. (The classification diagram and flow chart are based on the microwave imaging algorithms.).

A new current injection and voltage measurement strategy of 3D electrical impedance tomography based on scanning electrode.

Electrical impedance tomography (EIT) technology is an important imaging approach to show the conductivity distribution of the area noninvasively. Recently, 3D EIT has been extensively studied for its more comprehensive display of electrical properties. Nonetheless, most 3D EIT electrode models are based on multilayer ring electrodes and only suitable for specific scenarios. In order to overcome its limitations and alleviate the ill-condition of 3D EIT, we propose a new current injection and voltage measurement strategy based on scanning row electrodes (SRE) called the back electrode excitation (BEEM) strategy and select the optimal number of excitation electrodes according to different imaging effects. A 3D electrical impedance imaging system based on SRE is designed. Then, the traditional excitation measurement strategy is introduced, and the two strategies are compared through simulation and actual experiments. The results show that the BEEM strategy with SRE can not only obtain rich potential information in the finite field but also significantly improve the imaging detection depth, accuracy, and noise immunity compared with the flat electrode array.

A fast and efficient algorithm for multi-channel transcranial magnetic stimulation (TMS) signal denoising.

TMS signal denoising is crucial for 264-channel TMS high-performance magnetic field detection system application, which can be considered as a problem of obtaining an optimal solution to the desired clean signal. In order to efficiently suppress the noise, an improved generalized morphological filtering (IGMF) algorithm based on adaptive framing is proposed. Firstly, the framing points are calculated by the adaptive framing algorithm, and multiple signal segments are obtained by the framing points. Then, the IGMF algorithm is used to filter the signal segments. Finally, the filtered signal segments are merged into TMS signals. The performance of our algorithm is evaluated using the SNR, RMSE, and MAE. Experiments show that the results of the proposed algorithm on three evaluation indicators are superior to others. And the running time of the algorithm is only 2.88 ~ 37.87% of others. Therefore, the proposed algorithm can efficiently denoise TMS signals and has advantages in fast processing of multi-channel signals. The improved generalized morphological filtering(IGMF) algorithm based on adaptive framing algorithm is used to process 264-channel signals, which achieves signal denoising through a series of operations. The flowchart and result of this algorithm are shown in Fig. 1.

[Research on the detection algorithm of electrocardiogram characteristic wave based on energy segmentation and stationary wavelet transform].

The detection of electrocardiogram (ECG) characteristic wave is the basis of cardiovascular disease analysis and heart rate variability analysis. In order to solve the problems of low detection accuracy and poor real-time performance of ECG signal in the state of motion, this paper proposes a detection algorithm based on segmentation energy and stationary wavelet transform (SWT). Firstly, the energy of ECG signal is calculated by segmenting, and the energy candidate peak is obtained after moving average to detect QRS complex. Secondly, the QRS amplitude is set to zero and the fifth component of SWT is used to locate P wave and T wave. The experimental results show that compared with other algorithms, the algorithm in this paper has high accuracy in detecting QRS complex in different motion states. It only takes 0.22 s to detect QSR complex of a 30-minute ECG record, and the real-time performance is improved obviously. On the basis of QRS complex detection, the accuracy of P wave and T wave detection is higher than 95%. The results show that this method can improve the efficiency of ECG signal detection, and provide a new method for real-time ECG signal classification and cardiovascular disease diagnosis.

Multi-class motor imagery EEG classification method with high accuracy and low individual differences based on hybrid neural network.

Objective.Most current methods of classifying different patterns for motor imagery EEG signals require complex pre-processing and feature extraction steps, which consume time and lack adaptability, ignoring individual differences in EEG signals. It is essential to improve algorithm performance with the increased classes and diversity of subjects.Approach.This study introduces deep learning method for end-to-end learning to complete the classification of four-class MI tasks, aiming to improve the recognition rate and balance the classification accuracy among different subjects. A new one-dimensional input data representation method is proposed. This representation method can increase the number of samples and ignore the influence of channel correlation. In addition, a cascade network of convolutional neural network and gated recurrent unit is designed to learn time-frequency information from EEG data without extracting features manually, this model can capture the hidden representations related to different MI mode of each people.Main results. Experiments on BCI Competition 2a dataset and actual collected dataset achieve high accuracy near 99.40% and 92.56%, and the standard deviation is 0.34 and 1.35 respectively. Results demonstrate that the proposed method outperforms the advanced methods and baseline models.Significance.Experimental results show that the proposed method improves the accuracy of multi-classification and overcomes the impact of individual differences on classification by training neural network subject-dependent, which promotes the development of actual brain-computer interface systems.

An improved multi-swarm particle swarm optimizer for optimizing the electric field distribution of multichannel transcranial magnetic stimulation.

Multichannel transcranial magnetic stimulation (mTMS) is a therapeutic method to improve psychiatric diseases, which has a flexible working pattern used to different applications. In order to make the electric field distribution in the brain meet the treatment expectations, we have developed a novel multi-swam particle swarm optimizer (NMSPSO) to optimize the current configuration of double layer coil array. To balance the exploration and exploitation abilities, three novel improved strategies are used in NMSPSO based on multi-swarm particle swarm optimizer. Firstly, a novel information exchange strategy is achieved by individual exchanges between sub-swarms. Secondly, a novel leaning strategy is used to control knowledge dissemination in the population, which not only increases the diversity of the particles but also guarantees the convergence. Finally, a novel mutation strategy is introduced, which can help the population jump out of the local optimum for better exploration ability. The method is examined on a set of well-known benchmark functions and the results show that NMSPSO has better performance than many particle swarm optimization variants. And the superior electric field distribution in mTMS can be obtained by NMSPSO to optimize the current configuration of the double layer coil array.

A multi-channel parameters adjustable magnetic field generator.

In order to increase the security and flexibility of the magnetic field generator, a multi-channel parameters adjustable (MCPA) magnetic field generator is designed and implemented in this paper. The circuit topology of the MCPA magnetic field generator is presented. The working principle of MCPA is analyzed. The pulse current is measured and verified by experiments. The results show that the pulsed current amplitude is adjustable under 1000 A, the adjustment range of the effective pulse width is 0-160 µs, and the adjustment range of the frequency is 1-10 Hz. The magnetic field intensity at 2.5 cm below the scalp of the brain was measured when the three channels were working at the same time. It can be seen that the intensity of the magnetic field in the central area is apparently higher than that in the surrounding. The channels of MCPA can also be chosen flexibly as needed. Therefore, it has a very high application and research value in the field of biological magnetism therapy.

A multi-module energy-saving pulsed magnetic field generator.

In order to generate the unipolar and bipolar pulsed magnetic fields and improve the energy efficiency of the magnetic field generator, a multi-module energy-saving (MMES) pulsed magnetic field generator is designed. The circuit topology of the MMES pulsed magnetic field generator is presented and the experimental data are measured by experiments. The results show that the peak current values of unipolar and bipolar pulsed magnetic fields are 156 A and 154 A by discharging two capacitors, and the intensities are 87.6 mT and 86.5 mT, respectively. The energy-saving rates of unipolar and bipolar pulsed magnetic fields can be up to 17.64% and 19.36%, respectively. Therefore, it has very high application and research value in the field of biological magnetism therapy.

A multi-channel high-speed magnetic field detection system based on FPGA for transcranial magnetic stimulation.

Transcranial magnetic stimulation (TMS), a popular technology, acts on the brain by using a pulse magnetic field to cause a series of physiological and biochemical reactions. In order to detect the magnetic field generated by the TMS coil with high-speed and multi-channel performance, a novel magnetic field detection system based on a field programmable gate array (FPGA) is designed and implemented. The detection system includes an induction coil array, a data acquisition (DAQ) card, and upper computer monitor software. The DAQ card contains analog signal processing circuits, a multiplexer, an analog-to-digital converter, and a FPGA with a high-speed, parallel, and switching idea. The system can sample at a rate of 500 ksps, with 14-bit resolution and 12 channels. The three dimensional (3D) magnetic field can be monitored on the screen with a waveform display and 3D magnetic field vector display. The DAQ card has a good signal noise and distortion and cross talk of 88.35 dB and -79.69 dB, respectively. Compared with the NI DAQ card, the proposed system has a relative error smaller than 1.81% and a mean square error smaller than 2.89 × 10-6, which verifies that the proposed detection system has a good performance. The multi-channel high-speed magnetic field detection system provides an important platform for the study of TMS in medical, engineering, and other fields.

A multifunctional energy-saving magnetic field generator.

To improve the energy utilization of magnetic field generators for biological applications, a multifunctional energy-saving magnetic field generator (ESMFG) is presented. It is capable of producing both an alternating magnetic field (AMF) and a bipolar pulse magnetic field (BPMF) with high energy-saving and energy-reuse rates. Based on a theoretical analysis of an RLC second-order circuit, the energy-saving and energy-reuse rates of both types of magnetic fields can be calculated and are found to have acceptable values. The results of an experimental study using the proposed generator show that for the BPMF, the peak current reaches 130 A and the intensity reaches 70.3 mT. For the AMF, the intensity is 11.0 mT and the RMS current is 20 A. The energy-saving and energy-reuse rates for the AMF generator are 61.3% and 63.5%, respectively, while for the BPMF generator, the energy-saving rate is 33.6%. Thus, the proposed ESMFG has excellent potential for use in biomedical applications.

Evaluation of measurement and stimulation patterns in open electrical impedance tomography with scanning electrode.

The reconstruction quality in electrical impedance tomography is limited by the current injection amplitude, the injection and measurement patterns, and the measurement accuracy as well as the number and placement of electrodes. This paper dedicates to increase the number of independent voltage measurements by scanning electrode (SE), and design an optimal measurement and stimulation pattern for open electrical impedance tomography (OEIT). Firstly, several measurement patterns are, performed in OEIT, aiming to evaluate the right number of the measurement points for the imaged target in a certain depth. The results indicate that the image quality gets higher with the number of measurement point increased to some extent. Thus, it can guide the optimum design for the electrode system in OEIT. Secondly, through the numerical calculation and salt water tank experiment, in contrast to adjacent current injection pattern, cross-current-injection pattern achieves better reconstruction with higher imaging quality and penetration depth, and is more robust against data noise in deep domain. Lastly, the experiments also indicate that the electrode contact area affects the reconstruction quality and investigation depth. Therefore, OEIT with SE can improve the application in clinic, such as the detection and monitoring of vascular, breast, and pulmonary diseases.

The differential Howland current source with high signal to noise ratio for bioimpedance measurement system.

The stability and signal to noise ratio (SNR) of the current source circuit are the important factors contributing to enhance the accuracy and sensitivity in bioimpedance measurement system. In this paper we propose a new differential Howland topology current source and evaluate its output characters by simulation and actual measurement. The results include (1) the output current and impedance in high frequencies are stabilized after compensation methods. And the stability of output current in the differential current source circuit (DCSC) is 0.2%. (2) The output impedance of two current circuits below the frequency of 200 KHz is above 1 MΩ, and below 1 MHz the output impedance can arrive to 200 KΩ. Then in total the output impedance of the DCSC is higher than that of the Howland current source circuit (HCSC). (3) The SNR of the DCSC are 85.64 dB and 65 dB in the simulation and actual measurement with 10 KHz, which illustrates that the DCSC effectively eliminates the common mode interference. (4) The maximum load in the DCSC is twice as much as that of the HCSC. Lastly a two-dimensional phantom electrical impedance tomography is well reconstructed with the proposed HCSC. Therefore, the measured performance shows that the DCSC can significantly improve the output impedance, the stability, the maximum load, and the SNR of the measurement system.

A novel combined regularization algorithm of total variation and Tikhonov regularization for open electrical impedance tomography.

A Tikhonov regularization method in the inverse problem of electrical impedance tomography (EIT) often results in a smooth distribution reconstruction, with which we can barely make a clear separation between the inclusions and background. The recently popular total variation (TV)regularization method including the lagged diffusivity (LD) method can sharpen the edges, and is robust to noise in a small convergence region. Therefore, in this paper, we propose a novel regularization method combining the Tikhonov and LD regularization methods. Firstly, we clarify the implementation details of the Tikhonov, LD and combined methods in two-dimensional open EIT by performing the current injection and voltage measurement on one boundary of the imaging object. Next, we introduce a weighted parameter to the Tikhonov regularization method aiming to explore the effect of the weighted parameter on the resolution and quality of reconstruction images with the inclusion at different depths. Then, we analyze the performance of these algorithms with noisy data. Finally, we evaluate the effect of the current injection pattern on reconstruction quality and propose a modified current injection pattern.The results indicate that the combined regularization algorithm with stable convergence is able to improve the reconstruction quality with sharp contrast and more robust to noise in comparison to the Tikhonov and LD regularization methods solely. In addition, the results show that the current injection pattern with a bigger driver angle leads to a better reconstruction quality.