To solve the safety problems caused by the restriction of interaction space and the singular configuration of rehabilitation robot in terminal traction upper limb rehabilitation training, a trajectory planning and tracking control scheme for rehabilitation training is proposed. The human-robot safe interaction space was obtained based on kinematics modeling and rehabilitation theory, and the training trajectory was planned based on the occupational therapy in rehabilitation medicine. The singular configuration of the rehabilitation robot in the interaction space was avoided by exponential adaptive damped least square method. Then, a nonlinear controller for the upper limb rehabilitation robot was designed based on the backstepping control method. Radial basis function neural network was used to approximate the robot model information online to achieve model-free control. The stability of the controller was proved by Lyapunov stability theory. Experimental results demonstrate the effectiveness and superiority of the proposed singular avoidance control scheme.
Fatigue driving is one of the leading causes of traffic accidents, posing a significant threat to drivers and road safety. Most existing methods focus on studying whole-brain multi-channel electroencephalogram (EEG) signals, which involve a large number of channels, complex data processing, and cumbersome wearable devices. To address this issue, this paper proposes a fatigue detection method based on frontal EEG signals and constructs a fatigue driving detection model using an asymptotic hierarchical fusion network. The model employed a hierarchical fusion strategy, integrating an attention mechanism module into the multi-level convolutional module. By utilizing both cross-attention and self-attention mechanisms, it effectively fused the hierarchical semantic features of power spectral density (PSD) and differential entropy (DE), enhancing the learning of feature dependencies and interactions. Experimental validation was conducted on the public SEED-VIG dataset. The proposed model achieved an accuracy of 89.80% using only four frontal EEG channels. Comparative experiments with existing methods demonstrate that the proposed model achieves high accuracy and superior practicality, providing valuable technical support for fatigue driving monitoring and prevention.
Based on bioelectrical impedance theory and pattern recognition algorithm, we in this study measured varieties of people's bioelectrical impedance in hands and identified different people according to their bioelectrical impedance. We designed a bioelectrical impedance collection circuit with AD5933 chip to measure the impedance in different people's hands, and we obtained the bioelectrical impedance spectrum for each person under 1-100 kHz electrical stimulation. We calculated the segmentation slopes of bioelectrical impedance spectrum, and took the slopes as characteristic parameters. In order to promote the recognition rate and prevent the overfitting of the model, we divided the people into the training set and the test set, and designed a 3 layer back propagation neural network model to train and test the samples. The results showed that back propagation neural network model could identify the test set effectively. The recognition rate of the training sets was as high as 97.62%, recognition rate of validation sets was 88.79%, recognition rate of test sets was 86.34%, and the synthetical recognition rate was 94.22%. It gives a clue that the network can perfectly recognize people in the training network as well as strangers that comes from the outside of the tests. Our work can verify the feasibility and reliability of using bioelectrical impedance and pattern recognition algorithm for identification, and can provide a simple and supplementary way to identify people.
Sleep apnea (SA) detection method based on traditional machine learning needs a lot of efforts in feature engineering and classifier design. We constructed a one-dimensional convolutional neural network (CNN) model, which consists in four convolution layers, four pooling layers, two full connection layers and one classification layer. The automatic feature extraction and classification were realized by the structure of the proposed CNN model. The model was verified by the whole night single-channel sleep electrocardiogram (ECG) signals of 70 subjects from the Apnea-ECG dataset. Our results showed that the accuracy of per-segment SA detection was ranged from 80.1% to 88.0%, using the input signals of single-channel ECG signal, RR interval (RRI) sequence, R peak sequence and RRI sequence + R peak sequence respectively. These results indicated that the proposed CNN model was effective and can automatically extract and classify features from the original single-channel ECG signal or its derived signal RRI and R peak sequence. When the input signals were RRI sequence + R peak sequence, the CNN model achieved the best performance. The accuracy, sensitivity and specificity of per-segment SA detection were 88.0%, 85.1% and 89.9%, respectively. And the accuracy of per-recording SA diagnosis was 100%. These findings indicated that the proposed method can effectively improve the accuracy and robustness of SA detection and outperform the methods reported in recent years. The proposed CNN model can be applied to portable screening diagnosis equipment for SA with remote server.
Automatic classification of heart sounds plays an important role in the early diagnosis of congenital heart disease. A kind of heart sound classification algorithms based on sub-band envelope feature and convolution neural network was proposed in this paper, which did not need to segment the heart sounds according to cardiac cycle accurately. Firstly, the heart sound signal was divided into some frames. Then, the frame level heart sound signal was filtered with Gammatone filter bank to obtain the sub-band signals. Next, the sub-band envelope was extracted by Hilbert transform. After that, the sub-band envelope was stacked into a feature map. Finally, type Ⅰ and type Ⅱ convolution neural network were selected as classifier. The result shown that the sub-band envelope feature was better in type Ⅰ than type Ⅱ. The algorithm is tested with 1 000 heart sound samples. The test results show that the overall performance of the algorithm proposed in this paper is significantly improved compared with other similar algorithms, which provides a new method for automatic classification of congenital heart disease, and speeds up the process of automatic classification of heart sounds applied to the actual screening.
Objective To systematically evaluate the diagnostic value of artificial intelligence assisted narrow-band imaging endoscopy diagnostic system for colorectal adenomatous polyps. Methods Pubmed, Embase, Web of Science, Cochrane Library, SinoMed, China National Knowledge Infrastructure, Chongqing VIP and Wanfang databases were searched. The diagnostic trials of the artificial intelligence assisted narrow-band imaging endoscopy diagnostic system for colorectal adenomatous polyps were comprehensively searched. The search time limit was from January 1, 2000 to October 31, 2022. The included studies were evaluated according to the Quality Assessment of Diagnostic Accuracy Studies-2, and the data were meta-analysed with RevMan 5.3, Meta-Disc 1.4 and Stata 13.0 statistical softwares. Results Finally, 11 articles were included, including 2178 patients. Meta-analysis results of the artificial intelligence assisted narrow-band imaging endoscopy diagnostic system for colorectal adenomatous polyps showed that the pooled sensitivity was 0.91, the pooled specificity was 0.88, the pooled positive likelihood ratio was 7.41, the pooled negative likelihood ratio was 0.10, the pooled diagnostic odds ratio was 76.45, and the area under the summary receiver operating characteristic curve was 0.957. Among them, 5 articles reported the diagnosis of small adenomatous polyps (diameter <5 mm) by the artificial intelligence assisted narrow-band imaging endoscopy diagnostic system. The results showed that the pooled sensitivity and the pooled specificity were 0.93 and 0.91, respectively, and the area under the summary receiver operating characteristic curve was 0.971. Five articles reported the accuracy of endoscopic diagnosis for adenomatous polyps of those with insufficient experience. The results showed that the pooled sensitivity and the pooled specificity were 0.84 and 0.76, respectively. The area under the summary receiver operating characteristic curve was 0.848. Compared with the artificial intelligence assisted narrow-band imaging endoscopy diagnostic system, the difference was statistically significant (Z=1.979, P=0.048). Conclusion The artificial intelligence assisted narrow-band imaging endoscopy diagnostic system has a high diagnostic accuracy, which can significantly improve the diagnostic accuracy for colorectal adenomatous polyps of those with insufficient endoscopic experience, and can effectively compensate for the adverse impact of their lack of endoscopic experience.
The human brain deteriorates as we age, and the rate and the trajectories of these changes significantly vary among brain regions and among individuals. Because neuroimaging data are potentially important indicators of individual's brain health, they are commonly used in brain age prediction. In this review, we summarize brain age prediction model from neuroimaging-based studies in the last ten years. The studies are categorized based on their image modalities and feature types. The results indicate that the prediction frameworks based on neuroimaging holds promise toward individualized brain age prediction. Finally, we addressed the challenges in brain age prediction and suggested some future research directions.
Objective To analyze the risk factors of type 2 diabetes mellitus and establish BP neural network model for screening of type 2 diabetes mellitus based on particle swarm optimization (PSO) algorithm. Methods Inpatients with type 2 diabetes mellitus in the Department of Endocrinology of the Affiliated Hospital of Guangdong Medical University and the Second Affiliated Hospital of Guangdong Medical University between July 2021 and August 2022 were selected as the case group and healthy people in the Health Management Center of the Affiliated Hospital of Guangdong Medical University as the control group. Basic information and physical and laboratory examination indicators were collected for comparative analysis. PSO-BP neural network model, BP neural network model and logistic regression models were established using MATLAB R2021b software and the optimal screening model of type 2 diabetes mellitus was selected. Based on the optimal model, the mean impact value algorithm was used to screen the risk factors of type 2 diabetes mellitus. Results A total of 1 053 patients were included in the case group and 914 healthy peoples in the control group. Except for type of salt, family history of comorbidities, body mass index, total cholesterol, low density lipoprotein cholesterol and staple food intake (P>0.05), the other indexes showed significant differences between the two groups. The performance of the PSO-BP neural network model outperformed the BP neural network model and the logistic regression model. Based on PSO-BP neural network model, the mean impact value algorithm showed that the risk factors for type 2 diabetes mellitus were fasting blood glucose , heart rate, age , waist-arm ratio and marital status , and the protective factors for type 2 diabetes mellitus were high density lipoprotein cholestero, vegetable intake, residence, education level, fruit intake and meat intake. Conclusions There are many influencing factors of type 2 diabetes mellitus. Focus should be placed on high-risk groups and regular disease screening should be carried out to reduce the risk of type 2 diabetes. The screening model of PSO-BP neural network performs the best, and it can be extended to the early screening and diagnosis of other diseases in the future.
Fetal electrocardiogram (ECG) signals provide important clinical information for early diagnosis and intervention of fetal abnormalities. In this paper, we propose a new method for fetal ECG signal extraction and analysis. Firstly, an improved fast independent component analysis method and singular value decomposition algorithm are combined to extract high-quality fetal ECG signals and solve the waveform missing problem. Secondly, a novel convolutional neural network model is applied to identify the QRS complex waves of fetal ECG signals and effectively solve the waveform overlap problem. Finally, high quality extraction of fetal ECG signals and intelligent recognition of fetal QRS complex waves are achieved. The method proposed in this paper was validated with the data from the PhysioNet computing in cardiology challenge 2013 database of the Complex Physiological Signals Research Resource Network. The results show that the average sensitivity and positive prediction values of the extraction algorithm are 98.21% and 99.52%, respectively, and the average sensitivity and positive prediction values of the QRS complex waves recognition algorithm are 94.14% and 95.80%, respectively, which are better than those of other research results. In conclusion, the algorithm and model proposed in this paper have some practical significance and may provide a theoretical basis for clinical medical decision making in the future.
Atrial fibrillation (AF) is a common arrhythmia, which can lead to thrombosis and increase the risk of a stroke or even death. In order to meet the need for a low false-negative rate (FNR) of the screening test in clinical application, a convolutional neural network with a low false-negative rate (LFNR-CNN) was proposed. Regularization coefficients were added to the cross-entropy loss function which could make the cost of positive and negative samples different, and the penalty for false negatives could be increased during network training. The inter-patient clinical database of 21 077 patients (CD-21077) collected from the large general hospital was used to verify the effectiveness of the proposed method. For the convolutional neural network (CNN) with the same structure, the improved loss function could reduce the FNR from 2.22% to 0.97% compared with the traditional cross-entropy loss function. The selected regularization coefficient could increase the sensitivity (SE) from 97.78% to 98.35%, and the accuracy (ACC) was 96.62%, which was an increase from 96.49%. The proposed algorithm can reduce the FNR without losing ACC, and reduce the possibility of missed diagnosis to avoid missing the best treatment period. Meanwhile, it provides a universal loss function for the clinical auxiliary diagnosis of other diseases.