In the process of lower limb rehabilitation training, fatigue estimation is of great significance to improve the accuracy of intention recognition and avoid secondary injury. However, most of the existing methods only consider surface electromyography (sEMG) features but ignore electrocardiogram (ECG) features when performing in fatigue estimation, which leads to the low and unstable recognition efficiency. Aiming at this problem, a method that uses the fusion features of ECG and sEMG signal to estimate the fatigue during lower limb rehabilitation was proposed, and an improved particle swarm optimization-support vector machine classifier (improved PSO-SVM) was proposed and used to identify the fusion feature vector. Finally, the accurate recognition of the three states of relax, transition and fatigue was achieved, and the recognition rates were 98.5%, 93.5%, and 95.5%, respectively. Comparative experiments showed that the average recognition rate of this method was 4.50% higher than that of sEMG features alone, and 13.66% higher than that of the combined features of ECG and sEMG without feature fusion. It is proved that the feature fusion of ECG and sEMG signals in the process of lower limb rehabilitation training can be used for recognizing fatigue more accurately.
The task of automatic generation of medical image reports faces various challenges, such as diverse types of diseases and a lack of professionalism and fluency in report descriptions. To address these issues, this paper proposes a multimodal medical imaging report based on memory drive method (mMIRmd). Firstly, a hierarchical vision transformer using shifted windows (Swin-Transformer) is utilized to extract multi-perspective visual features of patient medical images, and semantic features of textual medical history information are extracted using bidirectional encoder representations from transformers (BERT). Subsequently, the visual and semantic features are integrated to enhance the model's ability to recognize different disease types. Furthermore, a medical text pre-trained word vector dictionary is employed to encode labels of visual features, thereby enhancing the professionalism of the generated reports. Finally, a memory driven module is introduced in the decoder, addressing long-distance dependencies in medical image data. This study is validated on the chest X-ray dataset collected at Indiana University (IU X-Ray) and the medical information mart for intensive care chest x-ray (MIMIC-CXR) released by the Massachusetts Institute of Technology and Massachusetts General Hospital. Experimental results indicate that the proposed method can better focus on the affected areas, improve the accuracy and fluency of report generation, and assist radiologists in quickly completing medical image report writing.
Signal classification is a key of brain-computer interface (BCI). In this paper, we present a new method for classifying the electroencephalogram (EEG) signals of which the features are heterogeneous. This method is called wrapped elastic net feature selection and classification. Firstly, we used the joint application of time-domain statistic, power spectral density (PSD), common spatial pattern (CSP) and autoregressive (AR) model to extract high-dimensional fused features of the preprocessed EEG signals. Then we used the wrapped method for feature selection. We fitted the logistic regression model penalized with elastic net on the training data, and obtained the parameter estimation by coordinate descent method. Then we selected best feature subset by using 10-fold cross-validation. Finally, we classified the test sample using the trained model. Data used in the experiment were the EEG data from international BCI Competition Ⅳ. The results showed that the method proposed was suitable for fused feature selection with high-dimension. For identifying EEG signals, it is more effective and faster, and can single out a more relevant subset to obtain a relatively simple model. The average test accuracy reached 81.78%.
The PET/CT imaging technology combining positron emission tomography (PET) and computed tomography (CT) is the most advanced imaging examination method currently, and is mainly used for tumor screening, differential diagnosis of benign and malignant tumors, staging and grading. This paper proposes a method for breast cancer lesion segmentation based on PET/CT bimodal images, and designs a dual-path U-Net framework, which mainly includes three modules: encoder module, feature fusion module and decoder module. Among them, the encoder module uses traditional convolution for feature extraction of single mode image; The feature fusion module adopts collaborative learning feature fusion technology and uses Transformer to extract the global features of the fusion image; The decoder module mainly uses multi-layer perceptron to achieve lesion segmentation. This experiment uses actual clinical PET/CT data to evaluate the effectiveness of the algorithm. The experimental results show that the accuracy, recall and accuracy of breast cancer lesion segmentation are 95.67%, 97.58% and 96.16%, respectively, which are better than the baseline algorithm. Therefore, it proves the rationality of the single and bimodal feature extraction method combining convolution and Transformer in the experimental design of this article, and provides reference for feature extraction methods for tasks such as multimodal medical image segmentation or classification.
The recurrent neural network architecture improves the processing ability of time-series data. However, issues such as exploding gradients and poor feature extraction limit its application in the automatic diagnosis of mild cognitive impairment (MCI). This paper proposed a research approach for building an MCI diagnostic model using a Bayesian-optimized bidirectional long short-term memory network (BO-BiLSTM) to address this problem. The diagnostic model was based on a Bayesian algorithm and combined prior distribution and posterior probability results to optimize the BO-BiLSTM network hyperparameters. It also used multiple feature quantities that fully reflected the cognitive state of the MCI brain, such as power spectral density, fuzzy entropy, and multifractal spectrum, as the input of the diagnostic model to achieve automatic MCI diagnosis. The results showed that the feature-fused Bayesian-optimized BiLSTM network model achieved an MCI diagnostic accuracy of 98.64% and effectively completed the diagnostic assessment of MCI. In conclusion, based on this optimization, the long short-term neural network model has achieved automatic diagnostic assessment of MCI, providing a new diagnostic model for intelligent diagnosis of MCI.
As the most common active brain-computer interaction paradigm, motor imagery brain-computer interface (MI-BCI) suffers from the bottleneck problems of small instruction set and low accuracy, and its information transmission rate (ITR) and practical application are severely limited. In this study, we designed 6-class imagination actions, collected electroencephalogram (EEG) signals from 19 subjects, and studied the effect of collaborative brain-computer interface (cBCI) collaboration strategy on MI-BCI classification performance, the effects of changes in different group sizes and fusion strategies on group multi-classification performance are compared. The results showed that the most suitable group size was 4 people, and the best fusion strategy was decision fusion. In this condition, the classification accuracy of the group reached 77%, which was higher than that of the feature fusion strategy under the same group size (77.31% vs. 56.34%), and was significantly higher than that of the average single user (77.31% vs. 44.90%). The research in this paper proves that the cBCI collaboration strategy can effectively improve the MI-BCI classification performance, which lays the foundation for MI-cBCI research and its future application.
The effective classification of multi-task motor imagery electroencephalogram (EEG) is helpful to achieve accurate multi-dimensional human-computer interaction, and the high frequency domain specificity between subjects can improve the classification accuracy and robustness. Therefore, this paper proposed a multi-task EEG signal classification method based on adaptive time-frequency common spatial pattern (CSP) combined with convolutional neural network (CNN). The characteristics of subjects' personalized rhythm were extracted by adaptive spectrum awareness, and the spatial characteristics were calculated by using the one-versus-rest CSP, and then the composite time-domain characteristics were characterized to construct the spatial-temporal frequency multi-level fusion features. Finally, the CNN was used to perform high-precision and high-robust four-task classification. The algorithm in this paper was verified by the self-test dataset containing 10 subjects (33 ± 3 years old, inexperienced) and the dataset of the 4th 2018 Brain-Computer Interface Competition (BCI competition Ⅳ-2a). The average accuracy of the proposed algorithm for the four-task classification reached 93.96% and 84.04%, respectively. Compared with other advanced algorithms, the average classification accuracy of the proposed algorithm was significantly improved, and the accuracy range error between subjects was significantly reduced in the public dataset. The results show that the proposed algorithm has good performance in multi-task classification, and can effectively improve the classification accuracy and robustness.
In order to solve the current problems in medical equipment maintenance, this study proposed an intelligent fault diagnosis method for medical equipment based on long short term memory network(LSTM). Firstly, in the case of no circuit drawings and unknown circuit board signal direction, the symptom phenomenon and port electrical signal of 7 different fault categories were collected, and the feature coding, normalization, fusion and screening were preprocessed. Then, the intelligent fault diagnosis model was built based on LSTM, and the fused and screened multi-modal features were used to carry out the fault diagnosis classification and identification experiment. The results were compared with those using port electrical signal, symptom phenomenon and the fusion of the two types. In addition, the fault diagnosis algorithm was compared with BP neural network (BPNN), recurrent neural network (RNN) and convolution neural network (CNN). The results show that based on the fused and screened multi-modal features, the average classification accuracy of LSTM algorithm model reaches 0.970 9, which is higher than that of using port electrical signal alone, symptom phenomenon alone or the fusion of the two types. It also has higher accuracy than BPNN, RNN and CNN, which provides a relatively feasible new idea for intelligent fault diagnosis of similar equipment.
The result of the emotional state induced by music may provide theoretical support and help for assisted music therapy. The key to assessing the state of emotion is feature extraction of the emotional electroencephalogram (EEG). In this paper, we study the performance optimization of the feature extraction algorithm. A public multimodal database for emotion analysis using physiological signals (DEAP) proposed by Koelstra et al. was applied. Eight kinds of positive and negative emotions were extracted from the dataset, representing the data of fourteen channels from the different regions of brain. Based on wavelet transform, δ, θ, α and β rhythms were extracted. This paper analyzed and compared the performances of three kinds of EEG features for emotion classification, namely wavelet features (wavelet coefficients energy and wavelet entropy), approximate entropy and Hurst exponent. On this basis, an EEG feature fusion algorithm based on principal component analysis (PCA) was proposed. The principal component with a cumulative contribution rate more than 85% was retained, and the parameters which greatly varied in characteristic root were selected. The support vector machine was used to assess the state of emotion. The results showed that the average accuracy rates of emotional classification with wavelet features, approximate entropy and Hurst exponent were respectively 73.15%, 50.00% and 45.54%. By combining these three methods, the features fused with PCA possessed an accuracy of about 85%. The obtained classification accuracy by using the proposed fusion algorithm based on PCA was improved at least 12% than that by using single feature, providing assistance for emotional EEG feature extraction and music therapy.
Objective To propose a heart sound segmentation method based on multi-feature fusion network. Methods Data were obtained from the CinC/PhysioNet 2016 Challenge dataset (a total of 3 153 recordings from 764 patients, about 91.93% of whom were male, with an average age of 30.36 years). Firstly the features were extracted in time domain and time-frequency domain respectively, and reduced redundant features by feature dimensionality reduction. Then, we selected optimal features separately from the two feature spaces that performed best through feature selection. Next, the multi-feature fusion was completed through multi-scale dilated convolution, cooperative fusion, and channel attention mechanism. Finally, the fused features were fed into a bidirectional gated recurrent unit (BiGRU) network to heart sound segmentation results. Results The proposed method achieved precision, recall and F1 score of 96.70%, 96.99%, and 96.84% respectively. Conclusion The multi-feature fusion network proposed in this study has better heart sound segmentation performance, which can provide high-accuracy heart sound segmentation technology support for the design of automatic analysis of heart diseases based on heart sounds.