The original EEG data collected are the 1D sequence, which ignores spatial topology information; Feature Pyramid Networks (FPN) is better at small dimension target detection and insufficient feature extraction in the scale transformation than CNN. We propose a method of FPN and Long Short-Term Memory (FPN-LSTM) for EEG feature map-based emotion recognition. According to the spatial arrangement of brain electrodes, the Azimuth Equidistant Projection (AEP) is employed to generate the 2D EEG map, which preserves the spatial topology information; then, the average power, variance power, and standard deviation power of three frequency bands ($\alpha$, $\beta$, and $\gamma$) are extracted as the feature data for the EEG feature map. BiCubic interpolation is employed to interpolate the blank pixel among the electrodes; the three frequency bands EEG feature maps are used as the G, R, and B channels to generate EEG feature maps. Then, we put forward the idea of distributing the weight proportion for channels, assign large weight to strong emotion correlation channels (AF3, F3, F7, FC5, and T7), and assign small weight to the others; the proposed FPN-LSTM is used on EEG feature maps for emotion recognition. The experiment results show that the proposed method can achieve Value and Arousal recognition rates of 90.05% and 90.84%, respectively.

Artificial ears with intelligence, which can sensitively detect sound—a variant of pressure—and generate consciousness and logical decision‐making abilities, hold great promise to transform life. However, despite the emerging flexible sensors for sound detection, most success is limited to very simple phonemes, such as a couple of letters or words, probably due to the lack of device sensitivity and capability. Herein, the construction of ultrasensitive artificial eardrums enabling intelligent song recognition is reported. This strategy employs novel geometric engineering of sensing units in the soft microstructure array (to significantly reduce effective modulus) along with complex song recognition exploration leveraging machine learning algorithms. Unprecedented pressure sensitivity (6.9 × 10³ kPa⁻¹) is demonstrated in a sensor with a hollow pyramid architecture with porous slants. The integrated device exhibits unparalleled (exceeding by 1–2 orders of magnitude compared with reported benchmark samples) sound detection sensitivity, and can accurately identify 100% (for training set) and 97.7% (for test set) of a database of the segments from 77 songs varying in language, style, and singer. Overall, the results highlight the outstanding performance of the hollow‐microstructure‐based sensor, indicating its potential applications in human–machine interaction and wearable acoustical technologies.

At present, most methods to improve the accuracy of emotion recognition based on electroencephalogram (EEG) are achieved by means of increasing the number of channels and feature types. This is to use the big data to train the classification model but it also increases the code complexity and consumes a large amount of computer time. We propose a method of Ant Colony Optimization with Convolutional Neural Networks and Long Short-Term Memory (ACO–CNN–LSTM) which can attain the dynamic optimal channels for lightweight data. First, transform the time-domain EEG signal to the frequency domain by Fast Fourier Transform (FFT), and the Differential Entropy (DE) of the three frequency bands ($\alpha$, $\beta$ and $\gamma$) are extracted as the feature data; Then, based on the DE feature dataset, ACO is employed to plan the path where the electrodes are located in the brain map. The classification accuracy of CNN-LSTM is used as the objective function for path determination, and the electrodes on the optimal path are used as the optimal channels; Next, the initial learning rate and batchsize parameters are exactly matched the data characteristics, which can obtain the best initial learning rate and batchsize; Finally, the SJTU Emotion EEG Dataset (SEED) dataset is used for emotion recognition based on the ACO–CNN–LSTM. From the experimental results, it can be seen that: the average accuracy of three-classification (positive, neutral, negative) can achieve 96.59 %, which is based on the lightweight data by means of ACO–CNN–LSTM proposed in the paper. Meanwhile, the computer time consumed is reduced. The computational efficiency is increased by 15.85 % compared with the traditional CNN-LSTM method. The accuracy can achieve more than 90 % when the data volume is reduced to 50 %. In summary, the proposed method of ACO–CNN–LSTM in the paper can get higher efficiency and accuracy.

A semi-supervised vector machine is a relatively new learning method using both labeled and unlabeled data in classification. Since the objective function of the model for an unstrained semi-supervised vector machine is not smooth, many fast optimization algorithms cannot be applied to solve the model. In order to overcome the difficulty of dealing with non-smooth objective functions, new methods that can solve the semi-supervised vector machine with desired classification accuracy are in great demand. A quintic spline function with three-times differentiability at the origin is constructed by a general three-moment method, which can be used to approximate the symmetric hinge loss function. The approximate accuracy of the quintic spline function is estimated. Moreover, a quintic spline smooth semi-support vector machine is obtained and the convergence accuracy of the smooth model to the non-smooth one is analyzed. Three experiments are performed to test the efficiency of the model. The experimental results show that the new model outperforms other smooth models, in terms of classification performance. Furthermore, the new model is not sensitive to the increasing number of the labeled samples, which means that the new model is more efficient.