Recognition Experiments Research Articles

Multi-Session Electrocardiogram–Electromyogram Database for User Recognition

Current advancements in biosignal-based user recognition technology are paving the way for a next-generation solution that addresses the limitations of face- and fingerprint-based user recognition methods. However, existing biosignal benchmark databases (DBs) for user recognition often suffer from limitations, such as data collection from a small number of subjects in a single session, hindering comprehensive analysis of biosignal variability. This study introduces CSU_MBDB1 and CSU_MBDB2, databases containing electrocardiogram (ECG) and electromyogram (EMG) signals from diverse experimental subjects recorded across multiple sessions. These in-house DBs comprise ECG and EMG data recorded in multiple sessions from 36 and 58 subjects, respectively, with a time interval of more than one day between sessions. During the experiments, subjects performed a total of six gestures while comfortably seated at a desk. CSU_MBDB1 and CSU_MBDB2 consist of three identical gestures, providing expandable data for various applications. When the two DBs are expanded, ECGs and EMGs from 94 subjects can be used, which is the largest number among the multi-biosignal benchmark DBs built by multi-sessions. To assess the usability of the constructed DBs, a user recognition experiment was conducted, resulting in an accuracy of 66.39% for ten subjects. It is important to emphasize that we focused on demonstrating the applicability of the constructed DBs using a basic neural network without signal denoising capabilities. While this approach results in a sacrifice in accuracy, it concurrently provides substantial opportunities for performance enhancement through the implementation of optimized algorithms. Adapting signal denoising processes to the constructed DBs and designing a more sophisticated neural network would undoubtedly contribute to improving the recognition accuracy. Consequently, these constructed DBs hold promise in user recognition, offering valuable research for future investigations. Additionally, DBs can be used in research to analyze the nonlinearity characteristics of ECG and EMG.

False memories through auditory distraction: When irrelevant speech produces memory intrusions in the absence of semantic interference.

Task-irrelevant speech is known to cause disruption of short-term memory, either through specific interference with encoding processes (e.g., seriation, semantic processing) or by diverting attention from the focal task. Previous studies found that semantically related background speech can induce memory intrusions of words that were not part of the to-be-remembered list. While these findings suggest false memories due to semantic interference, the present study aims to test whether the presence of task-irrelevant speech affects the susceptibility to memory intrusions also in the absence of semantic interference. Therefore, incomprehensible to-be-ignored speech was presented during encoding of semantically related words. It was found across three experiments that incomprehensible changing-state speech increased the rate of false memories of non-presented but semantically related words in a subsequent recognition (Experiments 1 and 2) or recall test (Experiment 3), compared with white noise or steady-state speech. The findings indicate that speech interfered with serial-order processing of the to-be-remembered items, thus urging participants to rely on semantic information to encode and retrieve the presented words. While a focus on semantic information enabled participants to correctly recollect the majority of presented words, it most likely also increased the proportion of false memories of words with semantic associations to the presented words both in recall and recognition tests. In all three experiments, the presence of an auditory deviant in background speech did not increase the rate of false memories, suggesting that attentional capture alone does not necessarily induce source monitoring errors. However, Experiment 3 revealed that an increase in visual task-encoding load attenuated the changing-state effect on the production of false memories. This indicates that the semantic organisation processes initiated as a result of the loss of order information in case of changing-state speech may be sensitive to attentional control.

Research on the electromyography-based pattern recognition for inter-limb coordination in human crawling motion.

Aiming to provide a feasible crawling motion analysis method for clinical application, this study introduced electromyography (EMG)-based motion intention recognition technology into the pattern recognition of inter-limb coordination during human crawling for the first time. Eight inter-limb coordination modes (ILCMs) were defined. Ten adult participants were recruited, and each participant performed hands-knees crawling at low, medium, and fast speeds in self-selected ILCMs and the eight predefined ILCMs, respectively. EMG signals for pattern recognition were collected from 30 limbs and trunk muscles, and pressure signals for crawling cycle segmentation were collected from the left palm. The pattern recognition experiments were conducted in participant-specific, multi-participant, and participant-independent ways, respectively, adopting three different classifiers, including bidirectional long short-term memory (BiLSTM) network, support vector machine (SVM), and k-nearest neighbor (KNN). The experimental results show that EMG-based pattern recognition schemes could classify the eight ILCMs with high recognition rates, thereby confirming the feasibility of providing an EMG-based crawling motion analysis method for clinical doctors. Furthermore, based on the classification results of self-selected ILCMs at different speeds and the statistical results of stance duration, swing duration, and the duty factors of stance phase, the possible reasons why humans chose various ILCMs at different crawling speeds were discussed. The research results have potential application value for evaluating crawling function, understanding abnormal crawling control mechanisms, and designing rehabilitation robots.

Acanthopanax senticosus improves cognitive impairment in Alzheimer's disease by promoting the phosphorylation of the MAPK signaling pathway.

Acanthopanax senticosus (AS) can improve sleep, enhance memory, and reduce fatigue and is considered as an effective drug for Alzheimer's disease (AD). The therapeutic effect and mechanism need to be further investigated. To confirm the AS play efficacy in alleviating memory impairment in mice, 5×FAD transgenic mice were subjected to an open-field experiment and a novelty recognition experiment. Network pharmacology technique was used to analyze the information of key compounds and potential key targets of AS for the treatment of AD, molecular docking technique was applied to predict the binding ability of targets and compounds, and Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were also performed on the targets to derive the possible metabolic processes and pathway mechanisms of AS in treating AD. Quantitative real-time PCR (qRT-PCR) and western blot technique were carried out to validate the candidate genes and pathways. In the open-field experiment, compared with the wild-type (WT) group, the number of times the mice in the AD group crossed the central zone was significantly reduced (P< 0.01). Compared with the AD group, the number of times the mice in the AS group crossed the central zone was significantly increased (P< 0.001). In the new object recognition experiment, compared with the WT group, the percentage of times the AD group explored new objects was significantly reduced (P< 0.05). Compared with the AD group, the AS group had an increase in the percentage of time spent exploring new things and the number of times it was explored (P< 0.05). At the same time, the donepezil group had a significantly higher percentage of times exploring new things (P< 0.01). By using network pharmacology technology, 395 common targets of AS and AD were retrieved. The Cytoscape software was used to construct the protein-protein interaction (PPI) network of common targets. Using the algorithm, nine key targets were retrieved: APP, NTRK1, ESR1, CFTR, CSNK2A1, EGFR, ESR2, GSK3B, and PAK1. The results of molecular docking indicate that 11 pairs of compounds and their corresponding targets have a significant binding ability, as the molecular binding energies were less than -7.0. In comparison to the AD group, the mRNA expression of the key target genes was significantly decreased in the AS treatment group (P< 0.001). The KEGG analysis showed that the MAPK signaling pathway was significantly enriched, and Western blot confirmed that the TRAF6 protein decreased significantly (P< 0.0001). Meanwhile, the levels of MAP3K7 and P38 phosphorylation increased, and there was also an increase in the expression of HSP27 proteins. Our study indicates that the multi-component and multi-target properties of AS play an important role in the alleviation of anxiety and memory impairment caused by AD, and the mechanism is involved in the phosphorylation and activation of the MAPK signaling pathway. The results of this study could provide a novel perspective for the clinical treatment of AD.

The orthographic representation of a word’s morphological structure: beneficial and detrimental effect for spellers

In this paper we present a review of the literature on the role of a word’s morphological structure in written language processing, with an emphasis on spelling. First, we describe that many orthographies have opted for a representation of a word’s morphological structure. Second, we discuss experiments that have demonstrated the importance of a word’s morphological structure in reading, both in isolated word recognition experiments (so-called blind morphological decomposition) and in reading for meaning. Third, we discuss experimental findings that the written representation of a word’s morphological structure can have beneficial effects in spelling, already in young children with a good morphological awareness. However, several experiments have also shown that, in some circumstances, the speller’s task of representing morphology in written words creates considerable challenges and causes spelling errors rather than providing assistance. Closer inspection of this dissociation between beneficial and harmful effects reveals that two factors play a crucial role in determining the error risk: (a) the distinction between stems and affixes (i.e., morphological accessibility based on semantic transparency) and (b) the frequency with which a morpheme type in a language (stem, affix) must be retrieved in writing texts (accessibility based on type and token frequency). The review offers a theoretical framework against which the other papers in this special issue can be situated.

A Review of Research on The Neural Mechanisms of Lexical Tone Acquisition

The phenomenon of bilingualism is becoming more and more important as international communication becomes closer and closer. In the past, linguists' studies on second language acquisition by bilinguals seldom dealt with the language processing mechanism of the human brain itself, but the further development of science and technology has made it possible to quantify the laws of language learning at the neural level. In this paper, the author reviews the literature on the brain-neural mechanisms of tone perception in the primary stage of bilinguals from the perspectives of native language and bilingual tone perception in light of the previous research results. At present, the main research methods adopted in the study of tone acquisition are phonological experimental research and listening and dialectic research. However, the research on tone perception mostly focuses on differentiation and recognition experiments, the use of neuroscience technology is still insufficient, and the combination between disciplines is not close enough.

Discovery and learning of feature geometry in underwater acoustic sensing: Case studies and challenges in active sonar applications

Interpretable artificial intelligence (AI) and related machine learning (ML) techniques are gaining popularity for underwater acoustic sensing applications. However, interpretability of machine learnt features poses a fundamental challenge to successful application of these powerful data science techniques to underwater acoustics. Autonomous sonar target recognition is especially interesting from the data science perspective as beyond target-specific features, a sonar ping response typically includes significant interference from the environment, e.g., clutter, multipath scattering, etc. Such environmental interference, resulting from complex, dynamic, unpredictable, and often unknown factors, manifest as identifiable structures in acoustic color or alternate multi-dimensional feature representations that can lead to machine learning and classification errors. In this talk, we will discuss these challenges commonly encountered in underwater acoustics using case studies from field experiments in active sonar target recognition. Some results will also include physics-driven simulations in this domain to provide robust ground truths. In particular, we will posit how braided feature geometry and its representation, as well geometry of overlap between features can render a sonar target feature informative, explainable, and discoverable. [Work funded by the ONR Grant Nos. N000142112420 and N000142312503 and DoD Navy (NEEC) Grant No. N001742010016.]

FoPro-KD: Fourier Prompted Effective Knowledge Distillation for Long-Tailed Medical Image Recognition.

Representational transfer from publicly available models is a promising technique for improving medical image classification, especially in long-tailed datasets with rare diseases. However, existing methods often overlook the frequency-dependent behavior of these models, thereby limiting their effectiveness in transferring representations and generalizations to rare diseases. In this paper, we propose FoPro-KD, a novel framework that leverages the power of frequency patterns learned from frozen pre-trained models to enhance their transferability and compression, presenting a few unique insights: 1) We demonstrate that leveraging representations from publicly available pre-trained models can substantially improve performance, specifically for rare classes, even when utilizing representations from a smaller pre-trained model. 2) We observe that pre-trained models exhibit frequency preferences, which we explore using our proposed Fourier Prompt Generator (FPG), allowing us to manipulate specific frequencies in the input image, enhancing the discriminative representational transfer. 3) By amplifying or diminishing these frequencies in the input image, we enable Effective Knowledge Distillation (EKD). EKD facilitates the transfer of knowledge from pre-trained models to smaller models. Through extensive experiments in long-tailed gastrointestinal image recognition and skin lesion classification, where rare diseases are prevalent, our FoPro-KD framework outperforms existing methods, enabling more accessible medical models for rare disease classification. Code is available at https://github.com/xmed-lab/FoPro-KD.

Real-time continuous gesture recognition system based on PSO-PNN

In the field of natural human–machine interaction, wearable gesture interaction technologies have received considerable attention, particularly continuous gesture (CG) recognition. However, CG faces several challenges, including the impact of motion characteristics on gesture recognition and performance that is not sufficiently robust. Traditional algorithms are highly dependent on samples, thus meeting the requirements of low sample volume and high accuracy simultaneously is challenging. To address these challenges, we propose a real-time CG recognition system based on particle swarm optimization (PSO) and probabilistic neural network (PNN). This system employs principal component analysis for signal dimensionality reduction to alleviate computational burden and uses K-means clustering and Pearson correlation coefficient to extract optimal features for gesture classification. In offline gesture recognition experiments involving six CGs, the algorithm achieved an accuracy rate of 97% with a training set of 300 samples and a runtime of just 31.25 ms. Compared to other five algorithms, the proposed algorithm improved accuracy by at least 9% and reduced the runtime by 40.475 ms. Moreover, gesture recognition experiments were conducted using different datasets, with the PSO-PNN algorithm achieving an average recognition rate of 90.17%, at least 9.84% higher than other algorithms. Finally, in experiments on online CG control for robots in complex environments, the PSO-PNN demonstrated real-time performance of 28.56 ms and a task completion rate of 90.67%, validating the feasibility of PSO-PNN. This research provides a substantial theoretical and technical foundation for the ongoing enhancement and application of CG recognition technology.

Facial Expression Realization of Humanoid Robot Head and Strain-Based Anthropomorphic Evaluation of Robot Facial Expressions.

The facial expressions of humanoid robots play a crucial role in human-computer information interactions. However, there is a lack of quantitative evaluation methods for the anthropomorphism of robot facial expressions. In this study, we designed and manufactured a humanoid robot head that was capable of successfully realizing six basic facial expressions. The driving force behind the mechanism was efficiently transmitted to the silicone skin through a rigid linkage drive and snap button connection, which improves both the driving efficiency and the lifespan of the silicone skin. We used human facial expressions as a basis for simulating and acquiring the movement parameters. Subsequently, we designed a control system for the humanoid robot head in order to achieve these facial expressions. Moreover, we used a flexible vertical graphene sensor to measure strain on both the human face and the silicone skin of the humanoid robot head. We then proposed a method to evaluate the anthropomorphic degree of the robot's facial expressions by using the difference rate of strain. The feasibility of this method was confirmed through experiments in facial expression recognition. The evaluation results indicated a high degree of anthropomorphism for the six basic facial expressions which were achieved by the humanoid robot head. Moreover, this study also investigates factors affecting the reproduction of expressions. Finally, the impulse was calculated based on the strain curves of the energy consumption of the humanoid robot head to complete different facial expressions. This offers a reference for fellow researchers when designing humanoid robot heads, based on energy consumption ratios. To conclude, this paper offers data references for optimizing the mechanisms and selecting the drive components of the humanoid robot head. This was realized by considering the anthropomorphic degree and energy consumption of each part. Additionally, a new method for evaluating robot facial expressions is proposed.

EEG-FRM: a neural network based familiar and unfamiliar face EEG recognition method.

Recognizing familiar faces holds great value in various fields such as medicine, criminal investigation, and lie detection. In this paper, we designed a Complex Trial Protocol-based familiar and unfamiliar face recognition experiment that using self-face information, and collected EEG data from 147 subjects. A novel neural network-based method, the EEG-based Face Recognition Model (EEG-FRM), is proposed in this paper for cross-subject familiar/unfamiliar face recognition, which combines a multi-scale convolutional classification network with the maximum probability mechanism to realize individual face recognition. The multi-scale convolutional neural network extracts temporal information and spatial features from the EEG data, the attention module and supervised contrastive learning module are employed to promote the classification performance. Experimental results on the dataset reveal that familiar face stimuli could evoke significant P300 responses, mainly concentrated in the parietal lobe and nearby regions. Our proposed model achieved impressive results, with a balanced accuracy of 85.64%, a true positive rate of 73.23%, and a false positive rate of 1.96% on the collected dataset, outperforming other compared methods. The experimental results demonstrate the effectiveness and superiority of our proposed model.

Optical Microfiber Intelligent Sensor: Wearable Cardiorespiratory and Behavior Monitoring with a Flexible Wave-Shaped Polymer Optical Microfiber.

With the advantages of high flexibility, strong real-time monitoring capabilities, and convenience, wearable devices have shown increasingly powerful application potential in medical rehabilitation, health monitoring, the Internet of Things, and human-computer interaction. In this paper, we propose a novel and wearable optical microfiber intelligent sensor based on a wavy-shaped polymer optical microfiber (WPOMF) for cardiorespiratory and behavioral monitoring of humans. The optical fibers based on polymer materials are prepared into optical microfibers, fully using the advantages of the polymer material and optical microfibers. The prepared polymer optical microfiber is designed into a flexible wave-shaped structure, which enables the WPOMF sensor to have higher tensile properties and detection sensitivity. Cardiorespiratory and behavioral detection experiments based on the WPOMF sensor are successfully performed, which demonstrates the high sensitivity and stability potential of the WPOMF sensor when performing wearable tasks. Further, the success of the AI-assisted medical keyword pronunciation recognition experiment fully demonstrates the feasibility of integrating AI technology with the WPOMF sensor, which can effectively improve the intelligence of the sensor as a wearable device. As an optical microfiber intelligent sensor, the WPOMF sensor offers broad application prospects in disease monitoring, rehabilitation medicine, the Internet of Things, and other fields.

Bayesian Nonparametric Multivariate Mixture of Autoregressive Processes with Application to Brain Signals

One of neuroscience’s goals is to study the interactions between different brain regions during rest and while performing specific cognitive tasks. Multivariate Bayesian autoregressive decomposition (MBMARD) is proposed as an intuitive and novel Bayesian non-parametric model to represent high-dimensional signals as a low-dimensional mixture of univariate uncorrelated latent oscillations. Each latent oscillation captures a specific underlying oscillatory activity and, hence, is modeled as a unique second-order autoregressive process due to a compelling property, namely, that its spectral density’s shape is characterized by a unique frequency peak and bandwidth, parameterized by a location and a scale parameter. The posterior distributions of the latent oscillation parameters are computed using a Metropolis-within-Gibbs algorithm. One of the advantages of the MBMARD model is its higher robustness against misspecification, compared with standard models. The main scientific questions addressed by the MBMARD model relate to the effects of long-term alcohol abuse on memory. These effects were examined by analyzing the electroencephalogram records of alcoholic and non-alcoholic subjects performing a visual recognition experiment. The MBMARD model yielded novel and interesting findings, including the identification of subject-specific clusters of low- and high-frequency oscillations in different brain regions.

Auditory Ensemble Perception (Summary Statistics) for Music Scale Tones by Listeners with and without Absolute Pitch

ABSTRACT Ensemble perception refers to our ability to summarize complex information across individual items in a group. Ensemble perception of pitch in the auditory domain can be achieved remarkably well: listeners can accurately judge whether the pitch corresponding to the mean frequency of a set of six music scale tones is higher or lower than the pitch of a test tone presented after the set. Ensemble perception for music scale tones was performed by absolute pitch (AP) possessors (n = 16) and musically experienced non-AP listeners (n = 14). They performed a set averaging experiment (Experiment 1), and a tone recognition experiment, in which they judged whether an individual tone had been part of the set or not (Experiment 2). AP listeners obtained a significantly higher percentage correct and a smaller just noticeable difference than non-AP listeners when comparing the (average) pitch of the set and the test. Remarkably, though, AP listeners did not significantly outperform non-AP listeners in individual tone recognition. These results suggest that a cognitive tone-labeling strategy, as predominantly used by AP listeners, enhances ensemble perception for music scale tones. Musically experienced non-AP listeners, however, can achieve recognition of individual tones without tone labeling at a very high level as well. Possible strategies used by the listeners in both groups were discussed.

A Low-Cost Inertial Measurement Unit Motion Capture System for Operation Posture Collection and Recognition.

In factories, human posture recognition facilitates human-machine collaboration, human risk management, and workflow improvement. Compared to optical sensors, inertial sensors have the advantages of portability and resistance to obstruction, making them suitable for factories. However, existing product-level inertial sensing solutions are generally expensive. This paper proposes a low-cost human motion capture system based on BMI 160, a type of six-axis inertial measurement unit (IMU). Based on WIFI communication, the collected data are processed to obtain the displacement of human joints' rotation angles around XYZ directions and the displacement in XYZ directions, then the human skeleton hierarchical relationship was combined to calculate the real-time human posture. Furthermore, the digital human model was been established on Unity3D to synchronously visualize and present human movements. We simulated assembly operations in a virtual reality environment for human posture data collection and posture recognition experiments. Six inertial sensors were placed on the chest, waist, knee joints, and ankle joints of both legs. There were 16,067 labeled samples obtained for posture recognition model training, and the accumulated displacement and the rotation angle of six joints in the three directions were used as input features. The bi-directional long short-term memory (BiLSTM) model was used to identify seven common operation postures: standing, slightly bending, deep bending, half-squatting, squatting, sitting, and supine, with an average accuracy of 98.24%. According to the experiment result, the proposed method could be used to develop a low-cost and effective solution to human posture recognition for factory operation.

Research on Coal and Rock Recognition in Coal Mining Based on Artificial Neural Network Models

In the process of coal mining, one of the main reasons for the high labor intensity of workers and the frequent occurrence of casualties is the low level of intelligence of coal mining equipment. As the core equipment in the process of coal mining, the intelligence level of shearers directly affects the safety production and mining efficiency of coal mines. Coal and rock recognition technology is the core technology used to realize the intelligentization of shearers, which is an urgent technical problem to be solved in the field of coal mining. In this paper, coal seam images, rock stratum images, and coal–rock mixed-layer images of a coal mining area are taken as the research object, and key technologies such as the construction of a sample image library, classification and recognition, and semantic segmentation are studied by using the relevant theoretical knowledge of artificial neural network models. Firstly, the BP neural network is used to classify and identify coal seam images, rock stratum images, and coal–rock mixed-layer images, so as to distinguish which of the current mining targets of a shearer is the coal seam, rock stratum, or coal–rock mixed layer. Because different mining objectives will lead to different working modes of a shearer, it is necessary to maintain normal power to cut coal when encountering a coal seam, to stop working when encountering rock stratum, and to cut coal along the boundary between a coal seam and rock stratum when encountering a coal–rock mixed stratum. Secondly, the DeepLabv3+ model is used to perform semantic segmentation experiments on the coal–rock mixed-layer images. The purpose is to find out the distribution of coal and rocks in the coal–rock mixed layer in the coal mining area, so as to provide technical support for the automatic adjustment height of the shearer. Finally, the research in this paper achieved a 97.16% recognition rate in the classification and recognition experiment of the coal seam images, rock stratum images, and coal–rock mixed-layer images and a 91.2% accuracy in the semantic segmentation experiment of the coal–rock mixed-layer images. The research results of the two experiments provide key technical support for improving the intelligence level of shearers.

L-Net: A lightweight convolutional neural network for devices with low computing power

Deep learning (DL) has demonstrated exceptional success across various domains, including computer vision, natural language processing, and speech recognition. However, the training and inference processes of DL models typically require substantial computational resources and storage space, presenting a significant challenge within the Internet of Things (IoT) domain. This study contributes theoretically to the field of lightweight DL by proposing L-Net, a lightweight convolutional neural network designed specifically for low-compute devices. The L-Net addresses challenges associated with channel interaction disparities and vanishing gradients. To further improve the network performance, we introduce the residual enhanced channel attention (or R-ECA) module, which combines a bypass mechanism derived from simplified residual learning with the attention mechanism's cross-channel interaction. Additionally, we replace the rectified linear unit function (or ReLU) with an exponential linear unit (or ELU) function to enhance the network's nonlinear expression capability and training speed. We conducted object recognition experiments and compared the accuracy and prediction stability of L-Net with well-known models, such as AlexNet, VGG11, SqueezeNet, ResNet, and MobileNet, to assess its efficacy. Using the CIFAR-10 dataset and our custom dataset of apple tree leaf diseases, our experimental results demonstrate that, with relatively smaller model parameters, L-Net performs exceptionally well in terms of mean Average Precision (mAP), achieving 0.906. Furthermore, when applied to our custom dataset, L-Net exhibits relatively consistent performance across various dataset splits under different ratios, outperforming the majority of models.

Multi-Region and Multi-Band Electroencephalogram Emotion Recognition Based on Self-Attention and Capsule Network

Research on emotion recognition based on electroencephalogram (EEG) signals is important for human emotion detection and improvements in mental health. However, the importance of EEG signals from different brain regions and frequency bands for emotion recognition is different. For this problem, this paper proposes the Capsule–Transformer method for multi-region and multi-band EEG emotion recognition. First, the EEG features are extracted from different brain regions and frequency bands and combined into feature vectors which are input into the fully connected network for feature dimension alignment. Then, the feature vectors are inputted into the Transformer for calculating the self-attention of EEG features among different brain regions and frequency bands to obtain contextual information. Finally, utilizing capsule networks captures the intrinsic relationship between local and global features. It merges features from different brain regions and frequency bands, adaptively computing weights for each brain region and frequency band. Based on the DEAP dataset, experiments show that the Capsule–Transformer method achieves average classification accuracies of 96.75%, 96.88%, and 96.25% on the valence, arousal, and dominance dimensions, respectively. Furthermore, in emotion recognition experiments conducted on individual brain regions or frequency bands, it was observed that the frontal lobe exhibits the highest average classification accuracy, followed by the parietal, temporal, and occipital lobes. Additionally, emotion recognition performance is superior for high-frequency band EEG signals compared to low-frequency band signals.

A bearing fault diagnosis method with improved symplectic geometry mode decomposition and feature selection

A rolling bearing fault diagnosis method based on improved symplectic geometry mode decomposition (SGMD) and feature selection was proposed to solve the problem of low fault identification due to the influence of noise on early bearing fault features. First, the SGMD SGMD is improved to enhance its robustness in decomposing signals with noise, then the time domain, frequency domain, and time-frequency features of each symplectic geometric component are extracted as feature vectors. Second, a comprehensive feature selection strategy is proposed to select the optimal subset of features that are conducive to fault classification. Finally, considering the problem of low classification accuracy of a single machine learning model, the AdaBoost-WSO-SVM model is constructed for fault classification using the AdaBoost algorithm of integrated learning. Experimental decomposition of complex signals with noise indicates that the improved SGMD is more effective compared to traditional SGMD. Subsequently, multiple experiments were conducted using the bearing datasets from Case Western Reserve University (CWRU) and Jiangnan University (JNU). The experimental results reveal that, after comprehensive feature selection and ensemble learning pattern recognition experiments on the CWRU dataset, the average accuracy of fault diagnosis can reach 99.67%. On the JNU dataset, the proposed fault diagnosis method achieves an average accuracy of 95.03%. This suggests that, compared to other feature selection methods and classification models, the proposed approach in this paper exhibits higher accuracy and generalization capabilities.

Recovery-Based Occluded Face Recognition by Identity-Guided Inpainting.

Occlusion in facial photos poses a significant challenge for machine detection and recognition. Consequently, occluded face recognition for camera-captured images has emerged as a prominent and widely discussed topic in computer vision. The present standard face recognition methods have achieved remarkable performance in unoccluded face recognition but performed poorly when directly applied to occluded face datasets. The main reason lies in the absence of identity cues caused by occlusions. Therefore, a direct idea of recovering the occluded areas through an inpainting model has been proposed. However, existing inpainting models based on an encoder-decoder structure are limited in preserving inherent identity information. To solve the problem, we propose ID-Inpainter, an identity-guided face inpainting model, which preserves the identity information to the greatest extent through a more accurate identity sampling strategy and a GAN-like fusing network. We conduct recognition experiments on the occluded face photographs from the LFW, CFP-FP, and AgeDB-30 datasets, and the results indicate that our method achieves state-of-the-art performance in identity-preserving inpainting, and dramatically improves the accuracy of normal recognizers in occluded face recognition.