Search

Aiming at the problem that existing emotion recognition methods fail to make full use of the information in the time, frequency, and spatial domains in the EEG signals, which leads to the low accuracy of EEG emotion classification, this paper proposes a multi-feature, multi-frequency band-based cross-scale attention convolutional model (CATM). The model is mainly composed of a cross-scale attention module, a frequency–space attention module, a feature transition module, a temporal feature extraction module, and a depth classification module. First, the cross-scale attentional convolution module extracts spatial features at different scales for the preprocessed EEG signals; then, the frequency–space attention module assigns higher weights to important channels and spatial locations; next, the temporal feature extraction module extracts temporal features of the EEG signals; and, finally, the depth classification module categorizes the EEG signals into emotions. We evaluated the proposed method on the DEAP dataset with accuracies of 99.70% and 99.74% in the valence and arousal binary classification experiments, respectively; the accuracy in the valence–arousal four-classification experiment was 97.27%. In addition, considering the application of fewer channels, we also conducted 5-channel experiments, and the binary classification accuracies of valence and arousal were 97.96% and 98.11%, respectively. The valence–arousal four-classification accuracy was 92.86%. The experimental results show that the method proposed in this paper exhibits better results compared to other recent methods, and also achieves better results in few-channel experiments. [ABSTRACT FROM AUTHOR]

The electroencephalogram (EEG) has recently emerged as a pivotal tool in brain imaging analysis, playing a crucial role in accurately interpreting brain functions and states. To address the problem that the presence of ocular artifacts in the EEG signals of patients with obstructive sleep apnea syndrome (OSAS) severely affects the accuracy of sleep staging recognition, we propose a method that integrates a support vector machine (SVM) with genetic algorithm (GA)-optimized variational mode decomposition (VMD) and second-order blind identification (SOBI) for the removal of ocular artifacts from single-channel EEG signals. The SVM is utilized to identify artifact-contaminated segments within preprocessed single-channel EEG signals. Subsequently, these signals are decomposed into variational modal components across different frequency bands using the GA-optimized VMD algorithm. These components undergo further decomposition via the SOBI algorithm, followed by the computation of their approximate entropy. An approximate entropy threshold is set to identify and remove components laden with ocular artifacts. Finally, the signal is reconstructed using the inverse SOBI and VMD algorithms. To validate the efficacy of our proposed method, we conducted experiments utilizing both simulated data and real OSAS sleep EEG data. The experimental results demonstrate that our algorithm not only effectively mitigates the presence of ocular artifacts but also minimizes EEG signal distortion, thereby enhancing the precision of sleep staging recognition based on the EEG signals of OSAS patients. [ABSTRACT FROM AUTHOR]

In recent years, artificial intelligence (AI) technology has promoted the development of electroencephalogram (EEG) emotion recognition. However, existing methods often overlook the computational cost of EEG emotion recognition, and there is still room for improvement in the accuracy of EEG emotion recognition. In this study, we propose a novel EEG emotion recognition algorithm called FCAN–XGBoost, which is a fusion of two algorithms, FCAN and XGBoost. The FCAN module is a feature attention network (FANet) that we have proposed for the first time, which processes the differential entropy (DE) and power spectral density (PSD) features extracted from the four frequency bands of the EEG signal and performs feature fusion and deep feature extraction. Finally, the deep features are fed into the eXtreme Gradient Boosting (XGBoost) algorithm to classify the four emotions. We evaluated the proposed method on the DEAP and DREAMER datasets and achieved a four-category emotion recognition accuracy of 95.26% and 94.05%, respectively. Additionally, our proposed method reduces the computational cost of EEG emotion recognition by at least 75.45% for computation time and 67.51% for memory occupation. The performance of FCAN–XGBoost outperforms the state-of-the-art four-category model and reduces computational costs without losing classification performance compared with other models. [ABSTRACT FROM AUTHOR]

In this paper, a fiber-based chromatic dispersion probe for simultaneous measurement of X-axis and Z-axis displacements with nanometric resolutions by using the full width at half maxima (FWHM) of the detected spectral signal has been proposed and demonstrated. For X-axis, FWHM is employed for indicating the X-axis displacement based on the fact that the FWHM remains almost constant with the varying Z-axis displacement of the fiber detector and shows a linear relationship with the X-axis displacement within a specific Z-axis displacement range. For the Z-axis, the linear relationship between the centroid wavelength λ of the detected spectral signal and the Z-axis displacement is employed for indicating the Z-axis displacement based on the fact that the sensitivity (slope of the λ-Z curve) is also linear with X-axis displacement within a certain X-axis displacement range. Theoretical and experimental investigations have verified the feasibility of the proposed chromatic dispersion probe, which yields X- and Z-axis measurement ranges of 2.3 μm and 15 μm and X- and Z-axis measurement resolutions of better than 25 nm and 50 nm, respectively. Experiments were further performed to evaluate the basic performance of the prototype probe and the maximum measurement errors were less than 10 nm and 60 nm for X- and Z-axis displacements, respectively. [ABSTRACT FROM AUTHOR]

This paper presents a fiber-based chromatic dispersion probe for the simultaneous measurement of dual-axis absolute and relative displacement with nanometric resolutions. The proposed chromatic dispersion probe is based on optical dispersion. In the probe, the employed light beam is split into two sub-beams, and then the two sub-beams are made to pass through two optical paths with different optical settings where two identical single-mode fiber detectors are located at different defocused positions of the respective dispersive lenses. In this way, two spectral signals can be obtained to indicate the absolute displacement of each of the dual-axes. A signal processing algorithm is proposed to generate a normalized output wavelength that indicates the relative displacement of the dual-axis. With the proposed chromatic dispersion probe, the absolute and relative displacement measurements of the dual-axis can be realized simultaneously. Theoretical and experimental investigations reveal that the developed chromatic dispersion probe realizes an absolute measurement range and a measurement resolution of approximately 180 μm and 50 nm, respectively, for each axis. Moreover, a relative displacement measurement range and a measurement resolution of about 240 μm and 100 nm, respectively, are achieved for the dual-axis. [ABSTRACT FROM AUTHOR]

A new method based on the interferometric pseudo-lateral-shearing method is proposed to evaluate the pitch variation of a large-scale planar variable-line-spacing (VLS) grating. In the method, wavefronts of the first-order diffracted beams from a planar VLS grating are measured by a commercial Fizeau form interferometer. By utilizing the differential wavefront of the first-order diffracted beam before and after the small lateral shift of the VLS grating, the pitch variation of the VLS grating can be evaluated. Meanwhile, additional positioning errors of the grating in the lateral shifting process could degrade the measurement accuracy of the pitch variation. To address the issue, the technique referred to as the reference plane technique is also introduced, where the least squares planes in the wavefronts of the first-order diffracted beams are employed to reduce the influences of the additional positioning errors of the VLS grating. The proposed method can also reduce the influence of the out-of-flatness of the reference flat in the Fizeau interferometer by taking the difference between the measured positive and negative diffracted wavefronts; namely, self-calibration can be accomplished. After the theoretical analysis and simulations, experiments are carried out with a large-scale VLS grating to verify the feasibility of the proposed methods. Furthermore, the evaluated VLS parameters are verified by comparing them with the readout signal of an absolute surface encoder employing the evaluated VLS grating as the scale for measurement. [ABSTRACT FROM AUTHOR]

An interferometric self-calibration method for the evaluation of the pitch deviation of scale grating has been extended to evaluate the pitch deviation of the long-range type linear scale by utilizing the stitching interferometry technique. Following the previous work, in which the interferometric self-calibration method was proposed to assess the pitch deviation of the scale grating by combing the first-order diffracted beams from the grating, a stitching calibration method is proposed to enlarge the measurement range. Theoretical analysis is performed to realize the X-directional pitch deviation calibration of the long-range linear scale while reducing the second-order accumulation effect by canceling the influence of the reference flat error in the sub-apertures' measurements. In this paper, the stitching interferometry theory is briefly reviewed, and theoretical equations of the X-directional pitch deviation stitching are derived for evaluation of the pitch deviation of the long-range linear scale. Followed by the simulation verification, some experiments with a linear scale of 105 mm length from a commercial interferential scanning-type optical encoder are conducted to verify the feasibility of the self-calibration stitching method for the calibration of the X-directional pitch deviation of the linear scale over its whole area. [ABSTRACT FROM AUTHOR]

Monitoring plant nitrogen (N) in a timely way and accurately is critical for precision fertilization. The imaging technology based on visible light is relatively inexpensive and ubiquitous, and open-source analysis tools have proliferated. In this study, texture- and geometry-related phenotyping combined with color properties were investigated for their potential use in evaluating N in pakchoi (Brassica campestris ssp. chinensis L.). Potted pakchoi treated with four levels of N were cultivated in a greenhouse. Their top-view images were acquired using a camera at six growth stages. The corresponding plant N concentration was determined destructively. The quantitative relationships between the nitrogen nutrition index (NNI) and the image-based phenotyping features were established using the following algorithms: random forest (RF), support vector regression (SVR), and neural network (NN). The results showed the full model based on the color, texture, and geometry-related features outperforms the model based on only the color-related feature in predicting the NNI. The RF full model exhibited the most robust performance in both the seedling and harvest stages, reaching prediction accuracies of 0.823 and 0.943, respectively. The high prediction accuracy of the model allows for a low-cost, non-destructive monitoring of N in the field of precision crop management. [ABSTRACT FROM AUTHOR]