[Research on Parkinson's disease recognition algorithm based on sample enhancement].

Parkinson's disease patients have early vocal cord damage, and their voiceprint characteristics differ significantly from those of healthy individuals, which can be used to identify Parkinson's disease. However, the samples of the voiceprint dataset of Parkinson's disease patients are insufficient, so this paper proposes a double self-attention deep convolutional generative adversarial network model for sample enhancement to generate high-resolution spectrograms, based on which deep learning is used to recognize Parkinson's disease. This model improves the texture clarity of samples by increasing network depth and combining gradient penalty and spectral normalization techniques, and a family of pure convolutional neural networks (ConvNeXt) classification network based on Transfer learning is constructed to extract voiceprint features and classify them, which improves the accuracy of Parkinson's disease recognition. The validation experiments of the effectiveness of this paper's algorithm are carried out on the Parkinson's disease speech dataset. Compared with the pre-sample enhancement, the clarity of the samples generated by the proposed model in this paper as well as the Fréchet inception distance (FID) are improved, and the network model in this paper is able to achieve an accuracy of 98.8%. The results of this paper show that the Parkinson's disease recognition algorithm based on double self-attention deep convolutional generative adversarial network sample enhancement can accurately distinguish between healthy individuals and Parkinson's disease patients, which helps to solve the problem of insufficient samples for early recognition of voiceprint data in Parkinson's disease. In summary, the method effectively improves the classification accuracy of small-sample Parkinson's disease speech dataset and provides an effective solution idea for early Parkinson's disease speech diagnosis.

[Research on fault diagnosis of patient monitor based on text mining].

The conventional fault diagnosis of patient monitors heavily relies on manual experience, resulting in low diagnostic efficiency and ineffective utilization of fault maintenance text data. To address these issues, this paper proposes an intelligent fault diagnosis method for patient monitors based on multi-feature text representation, improved bidirectional gate recurrent unit (BiGRU) and attention mechanism. Firstly, the fault text data was preprocessed, and the word vectors containing multiple linguistic features was generated by linguistically-motivated bidirectional encoder representation from Transformer. Then, the bidirectional fault features were extracted and weighted by the improved BiGRU and attention mechanism respectively. Finally, the weighted loss function is used to reduce the impact of class imbalance on the model. To validate the effectiveness of the proposed method, this paper uses the patient monitor fault dataset for verification, and the macro F1 value has achieved 91.11%. The results show that the model built in this study can realize the automatic classification of fault text, and may provide assistant decision support for the intelligent fault diagnosis of the patient monitor in the future.

Micro SleepNet: efficient deep learning model for mobile terminal real-time sleep staging.

The real-time sleep staging algorithm that can perform inference on mobile devices without burden is a prerequisite for closed-loop sleep modulation. However, current deep learning sleep staging models have poor real-time efficiency and redundant parameters. We propose a lightweight and high-performance sleep staging model named Micro SleepNet, which takes a 30-s electroencephalography (EEG) epoch as input, without relying on contextual signals. The model features a one-dimensional group convolution with a kernel size of 1 × 3 and an Efficient Channel and Spatial Attention (ECSA) module for feature extraction and adaptive recalibration. Moreover, the model efficiently performs feature fusion using dilated convolution module and replaces the conventional fully connected layer with Global Average Pooling (GAP). These design choices significantly reduce the total number of model parameters to 48,226, with only approximately 48.95 Million Floating-point Operations per Second (MFLOPs) computation. The proposed model is conducted subject-independent cross-validation on three publicly available datasets, achieving an overall accuracy of up to 83.3%, and the Cohen Kappa is 0.77. Additionally, we introduce Class Activation Mapping (CAM) to visualize the model's attention to EEG waveforms, which demonstrate the model's ability to accurately capture feature waveforms of EEG at different sleep stages. This provides a strong interpretability foundation for practical applications. Furthermore, the Micro SleepNet model occupies approximately 100 KB of memory on the Android smartphone and takes only 2.8 ms to infer one EEG epoch, meeting the real-time requirements of sleep staging tasks on mobile devices. Consequently, our proposed model has the potential to serve as a foundation for accurate closed-loop sleep modulation.

A screening method based on analytic hierarchy process for closed-loop DBS strategies of Parkinson's disease.

BACKGROUND: Closed-loop deep brain stimulation (DBS) is a research hotspot in the treatment of Parkinson's disease. However, a variety of stimulation strategies will increase the selection time and cost in animal experiments and clinical studies. Moreover, the stimulation effect is little difference between similar strategies, so the selection process will be redundant. OBJECTIVE: The objective was to propose a comprehensive evaluation model based on analytic hierarchy process (AHP) to select the best one among similar strategies. METHODS: Two similar strategies, namely, threshold stimulation (CDBS) and threshold stimulus after EMD feature extraction (EDBS), were used for analysis and screening. The values of Similar to Unified Parkinson's Disease Rating Scale estimates (SUE), ß power and energy consumption were calculated and analysed. The stimulation threshold with the best improvement effect was selected. The weights of the indices were allocated by AHP. Finally, the weights and index values were combined, and the comprehensive scores of the two strategies were calculated using the evaluation model. RESULTS: The optimal stimulation threshold for CDBS was 52% and for EDBS was 62%. The weights of the indices were 0.45, 0.45 and 0.1, respectively. According to comprehensive scores, different from the situation where either EDBS or CDBS can be called optimal stimulation strategies. But under the same threshold stimulation, the EDBS was better than the CDBS under the optimal level. CONCLUSION: The evaluation model based on AHP under the optimal stimulation conditions satisfied the screening conditions between the two strategies.

An improved YOLO Nano model for dorsal hand vein detection system.

To date, venipuncture, the most necessary and fundamental medical means, still remains a challenging task for medical stuff due to significant individual differences in vein condition. Thanks to mature development in near-infrared (NIR) imaging technology, a series of venepuncture auxiliary equipment has been devised and put into use. Yet, previous researches concentrated more on vein pattern segmentation, failing to materialize the identification of veins suitable to puncture in an embedded system. Given the above, we propose an approach to detect and locate the optimal veins fully utilizing the state-of-the-art deep learning and image processing technologies in order to provide a more practical reference. Firstly, a dedicated NIR-based puncturable vein positioning system is designed, realizing collection of dorsal hand vein images as well as the rapid and accurate location of veins suitable to puncture. Secondly, considering the limitations of embedded devices on computation ability and memory, an improved network based on YOLO Nano, named YOLO Nano-Vein, is presented with architecture trimmed, output scales reduced, and an atrous spatial pyramid pooling (ASPP) added. Finally, average precision (AP) is increased from 91.68 to 93.23%, and the detection time and parameters of network are reduced by 22% and 17.5%, respectively, which validates the proposed network achieves higher accuracy with less detection time in comparison with YOLO Nano and YOLOv3, indicating stronger applicability for detection tasks on embedded devices.

A deep learning algorithm based on 1D CNN-LSTM for automatic sleep staging.

BACKGROUND: Sleep staging is an important part of sleep research. Traditional automatic sleep staging based on machine learning requires extensive feature extraction and selection. OBJECTIVE: This paper proposed a deep learning algorithm without feature extraction based on one-dimensional convolutional neural network and long short-term memory. METHODS: The algorithm can automatically divide sleep into 5 phases including awake period, non-rapid eye movement sleep period (N1 ∼ N3) and rapid eye movement using the electroencephalogram signals. The raw signal was processed by the wavelet transform. Then, the processed signal was directly input into the deep learning algorithm to obtain the staging result. RESULTS: The accuracy of staging is 93.47% using the Fpz-Cz electroencephalogram signal. When using the Fpz-Cz and electroencephalogram signal, the algorithm can obtain the highest accuracy of 94.15%. CONCLUSION: These results show that this algorithm is suitable for different physiological signals and can realize end-to-end automatic sleep staging without any manual feature extraction.

Synchrosqueezing with short-time fourier transform method for trinary frequency shift keying encoded SSVEP.

BACKGROUND: The frequencies that can evoke strong steady state visual evoked potentials (SSVEP) are limited, which leads to brain-computer interface (BCI) instruction limitation in the current SSVEP-BCI. To solve this problem, the visual stimulus signal modulated by trinary frequency shift keying was introduced. OBJECTIVE: The main purpose of this paper is to find a more reliable recognition algorithm for SSVEP-BCI based on trinary frequency shift keying modulated stimuli. METHODS: First, the signal modulated by trinary frequency shift keying is simulated by MATLAB. At different noise levels, the empirical mode decomposition, singular value decomposition, and synchrosqueezing with the short-time Fourier transform are used to extract the characteristic frequency and reconstruct the signal. Then, the coherent method is used to demodulate the reconstructed signal. Second, in the paradigm of BCI using trinary frequency shift keying modulated stimuli, the three methods mentioned above are used to reconstruct EEG signals, and canonical correlation analysis and coherent demodulation are used to recognize the BCI instructions. RESULTS: For simulated signals, it is found that synchrosqueezing with short-time Fourier transform has a better effect on extracting the characteristic frequencies. For the EEG signal, it is found that the method combining synchrosqueezing with short-time Fourier transform and coherent demodulation has a higher accuracy and information translate rate than other methods. CONCLUSION: The method combining synchrosqueezing with short-time Fourier transform and coherent demodulation proposed in this paper can be applied in the SSVEP system based on trinary frequency shift keying modulated stimuli.

Synthesis of Surfactant-Assisted C/Fe-FeVO4 Nanostructure: Characterization and Photocatalytic Degradation of Ciprofloxacin.

The novel C/Fe-FeVO4 composite photocatalyst were synthesized by using a two-step hydrothermal synthesis method. Through a detailed exploration on the chemical and phisical properties by some spectroscopic and analytical techniques, the as-prepared C/Fe-FeVO4 exhibted a nanosheet and meso porosity structure. Accordingly, we further utilized this C/Fe-FeVO4 composite as a photocatalist for degradating the notorious ciprofloxacin (CIP) under simulated solar light (SSL) irradiation. Due to its outstanding catalytic properties, the C/Fe-FeVO4 exhibited superior photocatalytic activity. The possible photocatalytic mechanism has been discussed.

Comparative analysis of different characteristics of automatic sleep stages.

BACKGROUND AND OBJECTIVE: With the acceleration of social rhythm and the increase of pressure, there are various sleep problems among people. Sleep staging is an important basis for the diagnosis of sleep disorders and other related diseases. The process of automatic staging of sleep is mainly divided into three core steps: data preprocessing, feature extraction, and classification. Accurate analysis of the features of sleep electroencephalogram (EEG) signals is not only helpful to improve the accuracy of sleep staging, but also help people to understand their sleep status. METHODS: This paper focuses on the analysis of EEG features during sleep staging, and reviews many feature extraction methods and classification methods for sleep staging and sums up these algorithms used in literatures and its staging results. Besides, this paper lists a total of 22 features based on time domain, time-frequency, and nonlinear analysis methods, including kurtosis, skewness, Hjorth parameters, and standard deviations, wavelets energy; sample entropy (SampEn), fuzzy entropy, Tsallis entropy, fractal dimension (FD), complexity. The data set comes from EDF database. Wavelet transform (WT) and support vector machine (SVM) are used to achieve the sleep staging based on single-channel EEG signal. And the characteristic feature data was analyzed by ANOVA. RESULTS: By comparison, the SampEn, fuzzy entropy, FD and complexity can achieve ideal sleep staging. The highest accuracy of sleep staging is 85.93%. The FD and complexity are simpler than the entropy value, but their accuracies are lower. Furthermore, the distribution of these methods in different sleep period is more significant than others, which is content with the results of sleep staging. CONCLUSION: In a word, due to the non-stationary and non-linear characteristics of EEG signals, time domain and time-frequency analysis methods all have some limitations. Nonlinear analysis was more effective and practical for the analysis of sleep EEG.

Ensemble learning algorithm based on multi-parameters for sleep staging.

The aim of this study is to propose a high-accuracy and high-efficiency sleep staging algorithm using single-channel electroencephalograms (EEGs). The process consists four parts: signal preprocessing, feature extraction, feature selection, and classification algorithms. In the preconditioning of EEG, wavelet function and IIR filter are used for noise reduction. In feature selection, 15 feature algorithms in time domain, time-frequency domain, and nonlinearity are selected to obtain 30 feature parameters. Feature selection is very important for eliminating irrelevant and redundant features. Feature selection algorithms as Fisher score, Sequential Forward Selection (SFS), Sequential Floating Forward Selection (SFFS), and Fast Correlation-Based Filter Solution (FCBF) were used. The paper establishes a new ensemble learning algorithm based on stacking model. The basic layers are k-Nearest Neighbor (KNN), Random Forest (RF), Extremely Randomized Trees (ERT), Multi-layer Perceptron (MLP), and Extreme Gradient Boosting (XGBoost) and the second layer is a Logistic regression. Comparing classification of RF, Gradient Boosting Decision Tree (GBDT), and XGBoost, the accuracies and kappa coefficients are 96.67% and 0.96 using the proposed method. It is higher than other classification algorithms.The results show that the proposed method can accurately sleep staging using single-channel EEG and has a high ability to predict sleep staging. Graphical abstract.

A feature extraction method for adaptive DBS using an improved EMD.

OBJECTIVE: Local field potential (LFP) of a patient with Parkinson's disease often shows abnormal oscillation phenomenon. Extracting and studying this phenomenon and designing adaptive deep brain stimulation (DBS) control library have great significance in the treatment of disease. MATERIALS AND METHODS: This paper has designed a feature extraction method based on modified empirical mode decomposition (EMD) which extracts the abnormal oscillation signal in the time domain to increase the overall performance. The intrinsic mode function (IMF) component which contains abnormal oscillation is extracted by using EMD before an intrinsic characteristic of the oscillation signal is obtained. Abnormal oscillation signal is acquired using signal normalization, peak counting, and envelope method with a threshold which in turn keeps the integrity and accuracy as well as the efficiency. RESULTS: Comparative study of eight patients (six patients with DBS closed and drugs stopped; two patients with stimulation) has verified the feasibility of using modified EMD in extracting abnormal oscillation signal. The results showed that patients who take DBS suffer less abnormal oscillation than those who take no treatment. These results match the energy rise in the band of 3-30 Hz on local field potential spectrum of the patient with Parkinson's disease. CONCLUSIONS: Unlike previous oscillation extraction algorithm, improved EMD feature extraction method directly isolates abnormal oscillation signal from LFP. Significant improvement has been made in feature extraction algorithm in adaptability, real-time performance, and accuracy.

A SSVEP Stimuli Encoding Method Using Trinary Frequency-Shift Keying Encoded SSVEP (TFSK-SSVEP).

SSVEP is a kind of BCI technology with advantage of high information transfer rate. However, due to its nature, frequencies could be used as stimuli are scarce. To solve such problem, a stimuli encoding method which encodes SSVEP signal using Frequency Shift-Keying (FSK) method is developed. In this method, each stimulus is controlled by a FSK signal which contains three different frequencies that represent "Bit 0," "Bit 1" and "Bit 2" respectively. Different to common BFSK in digital communication, "Bit 0" and "Bit 1" composited the unique identifier of stimuli in binary bit stream form, while "Bit 2" indicates the ending of a stimuli encoding. EEG signal is acquired on channel Oz, O1, O2, Pz, P3, and P4, using ADS1299 at the sample rate of 250 SPS. Before original EEG signal is quadrature demodulated, it is detrended and then band-pass filtered using FFT-based FIR filtering to remove interference. Valid peak of the processed signal is acquired by calculating its derivative and converted into bit stream using window method. Theoretically, this coding method could implement at least 2 n-1 (n is the length of bit command) stimulus while keeping the ITR the same. This method is suitable to implement stimuli on a monitor and where the frequency and phase could be used to code stimuli is limited as well as implementing portable BCI devices which is not capable of performing complex calculations.

Combining canonical correlation analysis and infinite reference for frequency recognition of steady-state visual evoked potential recordings: a comparison with periodogram method.

Steady-state visual evoked potentials (SSVEP) are the visual system responses to a repetitive visual stimulus flickering with the constant frequency and of great importance in the study of brain activity using scalp electroencephalography (EEG) recordings. However, the reference influence for the investigation of SSVEP is generally not considered in previous work. In this study a new approach that combined the canonical correlation analysis with infinite reference (ICCA) was proposed to enhance the accuracy of frequency recognition of SSVEP recordings. Compared with the widely used periodogram method (PM), ICCA is able to achieve higher recognition accuracy when extracts frequency within a short span. Further, the recognition results suggested that ICCA is a very robust tool to study the brain computer interface (BCI) based on SSVEP.

[Review of the active locomotion system for capsule endoscope].

This review summarized the progress of researches on the active locomotion system for capsule endoscope, analyzed the moving and controlling principles in different locomotion systems, and compared their merits and shortcomings. Owing to the complexity of human intestines and the limits to the size and consumption of locomotion system from the capsule endoscope, there is not yet one kind of active locomotion system currently used in clinical practice. The locomotive system driven by an outer rotational magnetic field could improve the commercial endoscope capsule, while its magnetic field controlling moving is complex. Active locomotion system driven by shape memory alloys will be the orientated development and the point of research in the future.

[Development of a video image system for wireless capsule endoscopes based on DSP].

A video image recorder to record video picture for wireless capsule endoscopes was designed. TMS320C6211 DSP of Texas Instruments Inc. is the core processor of this system. Images are periodically acquired from Composite Video Broadcast Signal (CVBS) source and scaled by video decoder (SAA7114H). Video data is transported from high speed buffer First-in First-out (FIFO) to Digital Signal Processor (DSP) under the control of Complex Programmable Logic Device (CPLD). This paper adopts JPEG algorithm for image coding, and the compressed data in DSP was stored to Compact Flash (CF) card. TMS320C6211 DSP is mainly used for image compression and data transporting. Fast Discrete Cosine Transform (DCT) algorithm and fast coefficient quantization algorithm are used to accelerate operation speed of DSP and decrease the executing code. At the same time, proper address is assigned for each memory, which has different speed;the memory structure is also optimized. In addition, this system uses plenty of Extended Direct Memory Access (EDMA) to transport and process image data, which results in stable and high performance.

[An image acquisition & processing system of the wireless endoscope based on DSP].

This paper covers an image acquisition & processing system of the capsule-style endoscope. Images sent by the endoscope are compressed and encoded with the digital signal processor (DSP) saving data in HD into PC for analyzing and processing in the image browser workstation.