Translation of electroencephalographic (EEG) recordings into control signals for brain-computer interface (BCI) systems needs to be based on a robust classification of the various types of information. EEG-based BCI features are often noisy and likely to contain outliers. This contribution describes the application of a fuzzy support vector machine (FSVM) with a radial basis function kernel for classifying motor imagery tasks, while the statistical features over the set of the wavelet coefficients were extracted to characterize the time-frequency distribution of EEG signals. In the proposed FSVM classifier, a low fraction of support vectors was used as a criterion for choosing the kernel parameter and the trade-off parameter, together with the membership parameter based solely on training data. FSVM and support vector machine (SVM) classifiers outperformed the winner of the BCI Competition 2003 and other similar studies on the same Graz dataset, in terms of the competition criterion of the mutual information (MI), while the FSVM classifier yielded a better performance than the SVM approach. FSVM and SVM classifiers perform much better than the winner of the BCI Competition 2005 on the same Graz dataset for the subject O3 according to the competition criterion of the maximal MI steepness, while the FSVM classifier outperforms the SVM method. The proposed FSVM model has potential in reducing the effects of noise or outliers in the online classification of EEG signals in BCIs.

Due to its ability to learn the relationship among nodes from graph data, the graph convolution network (GCN) has received extensive attention. In the machine fault diagnosis field, it needs to construct input graphs reflecting features and relationships of the monitoring signals. Thus, the quality of the input graph affects the diagnostic performance. But it still has two limitations: 1) the constructed input graph usually has redundant edges, consuming excessive computational costs; 2) the constructed input graph cannot reflect the relationship between the noisy signals well. In order to overcome them, a dynamic graph-based feature learning with few edges considering noisy samples is proposed for rotating machinery fault diagnosis in this article. Noisy vibration signals are converted into one spectrum feature-based static graph, where redundant edges are simplified by the distance metric function. Edge connections of the input static graph are updated according to the relationship among high-level features extracted by the GCN. Based on this, dynamic input graphs are reconstructed as new graph representations for noisy samples. To verify the effectiveness of the proposed method, validation experiments were conducted on practical platforms, and results show that the dynamic input graph with few edges can effectively improve the diagnostic performance under different SNRs.

Estimation of on-off timing of human skeletal muscles during movement is an ongoing issue in surface electromyography (sEMG) signal processing for relevant clinical applications. Widely used single threshold methods still rely on the experience of the operator to manually establish a threshold level. In this paper, a novel approach to address this issue is presented. Based on the generalized likelihood ratio test, the maximum likelihood (ML) method is improved with an adaptive threshold technique based on the signal-to-noise ratio (SNR) estimate in the initial time before accurate sEMG analyses. The dependence of optimal threshold on SNR is determined by minimizing the onset/offset estimate error on a large set of simulated signals with well-known signal parameters. Accuracy and precision of the algorithm were assessed by using a set of simulated signals and real sEMG signals recorded from two healthy subjects during elbow flexion-extension movements with and without workload. Comparison with traditional algorithms shows that with a moderate increase in the computational effort the ML algorithm performs well even for low levels of EMG activity, while the proposed adaptive method is most robust with respect to variations in SNRs. Also, we discuss the results of analyzing the sEMG recordings from the selected proximal muscles of the upper limb in two hemiparetic subjects. The detection algorithm is automatic and user-independent, managing the detection of both onset and offset activation, and is applicable in presence of noise allowing use by skilled and unskilled operators alike.

Graph data-driven machine fault diagnosis methods make success using sufficient data recently. However, in the actual industry, there are rare failure data in historical data, leading to insufficient graph representation ability and reducing diagnosis performance. In this article, a generalized graph contrastive learning (GCL) framework for few-shot machine fault diagnosis is proposed. First, spectrum features of vibration data-based samples are used to calculate Euclidean distance matrix for constructing K-nearest neighborhood graph (KNNG), where K adjacent neighbors of each sample are connected. Avoiding excess calculation cost for graph construction, positive and negative KNNGs are constructed by changing parameter K . To make full use of few-shot samples, an unsupervised GCL subtask is set for pretraining graph deep learning model. Further, the unsupervised pretrained model is semisupervised trained using original KNNGs for outputting unlabeled nodes’ labels. The proposed method achieves 99.83%, 99.56% in bearing and gearbox dataset, respectively, and the proposed GCL framework works for different graph neural networks.

A large circular transmitter (power pad) is often utilized for inductively wireless charging so that the power receiver can position itself freely within the power pad. However, the uneven magnetic field distribution leads to the impedance mismatch and the variable transferred power due to the misalignment between a receiving coil and a relatively large transmitter coil. In this paper, the effects of the turn numbers, trace spacing, and coil size on the uniformity of magnetic field distribution over a planar spiral coil (PSC) are investigated based on an analytical model. Then the genetic algorithm is used to optimize the trace width and spacing of a ten-turn PSC with the fixed outer and inner diameters, whereas the magnetic field is numerically calculated by HFSS software. The geometrically optimal PSC is obtained with the trace width approximately equal to trace spacing for each turn by minimizing the coefficient of variation (COV) of magnetic field within an effective charging area over the coil. The results showed that the simulated and measured COVs of magnetic field were 0.130 and 0.121, respectively, which are obviously less than that of the uniformly-spaced regular coil and show a little less than that of the optimally spaced coil with fixed trace width. Therefore, the trace spacing is a major consideration to achieve the uniform magnetic field, whereas the trace width variation is applied to refine the evenness of field. It is also expected that the proposed GA-based optimization is well applied to design other Txs with conformable shape in inductively WPT systems for stable power delivery regardless of the receiver positions.

It is well known that many chronic diseases are associated with unhealthy diet. Although improving diet is critical, adopting a healthy diet is difficult despite its benefits being well understood. Technology is needed to allow an assessment of dietary intake accurately and easily in real-world settings so that effective intervention to manage being overweight, obesity, and related chronic diseases can be developed. In recent years, new wearable imaging and computational technologies have emerged. These technologies are capable of performing objective and passive dietary assessments with a much simplified procedure than traditional questionnaires. However, a critical task is required to estimate the portion size (in this case, the food volume) from a digital image. Currently, this task is very challenging because the volumetric information in the two-dimensional images is incomplete, and the estimation involves a great deal of imagination, beyond the capacity of the traditional image processing algorithms. In this work, we present a novel Artificial Intelligent (AI) system to mimic the thinking of dietitians who use a set of common objects as gauges (e.g., a teaspoon, a golf ball, a cup, and so on) to estimate the portion size. Specifically, our human-mimetic system “mentally” gauges the volume of food using a set of internal reference volumes that have been learned previously. At the output, our system produces a vector of probabilities of the food with respect to the internal reference volumes. The estimation is then completed by an “intelligent guess”, implemented by an inner product between the probability vector and the reference volume vector. Our experiments using both virtual and real food datasets have shown accurate volume estimation results.