工程技术最新文献

{"title":"MBRSTCformer: a knowledge embedded local-global spatiotemporal transformer for emotion recognition.","authors":"Chenglin Lin, Huimin Lu, Chenyu Pan, Songzhe Ma, Zexing Zhang, Runhui Tian","doi":"10.1007/s11571-025-10277-3","DOIUrl":"10.1007/s11571-025-10277-3","url":null,"abstract":"<p><p>Emotion recognition is an essential prerequisite for realizing generalized BCI, which possesses an extensive range of applications in real life. EEG-based emotion recognition has become mainstream due to its real-time mapping of brain emotional activities, so a robust EEG-based emotion recognition model is of great interest. However, most existing deep learning emotion recognition methods treat the EEG signal as a whole feature extraction, which will destroy its local stimulation differences and fail to extract local features of the brain region well. Inspired by the cognitive mechanisms of the brain, we propose the multi-brain regions spatiotemporal collaboration transformer (MBRSTCfromer) framework for EEG-based emotion recognition. First, inspired by the prior knowledge, we propose the Multi-Brain Regions Collaboration Network. The EEG data are processed separately after being divided by brain regions, and stimulation scores are presented to quantify the stimulation produced by different brain regions and feedback on the stimulation degree to the MBRSTCfromer. Second, we propose a Cascade Pyramid Spatial Fusion Temporal Convolution Network for multi-brain regions EEG features fusion. Finally, we conduct comprehensive experiments on two mainstream emotion recognition datasets to validate the effectiveness of our proposed MBRSTCfromer framework. We achieved 98.63 <math><mo>%</mo></math> , 98.15 <math><mo>%</mo></math> , and 98.58 <math><mo>%</mo></math> accuracy on the three dimensions (arousal, valence, and dominance) on the DEAP dataset; and 97.66 <math><mo>%</mo></math> , 97.07 <math><mo>%</mo></math> , and 97.97 <math><mo>%</mo></math> on the DREAMER dataset.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"95"},"PeriodicalIF":3.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12174000/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144332588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EA-EEG: a novel model for efficient motor imagery EEG classification with whitening and multi-scale feature integration.","authors":"Yutao Miao, Kaijie Li, Wenhao Zhao, Yushi Zhang","doi":"10.1007/s11571-025-10278-2","DOIUrl":"10.1007/s11571-025-10278-2","url":null,"abstract":"<p><p>Electroencephalography (EEG) is a non-invasive technique widely used in neuroscience and brain-computer interfaces (BCI) due to its high temporal resolution. In motor imagery EEG (MI-EEG) tasks, EEG signals reflect movement-related brain activity, making them ideal for BCI control. However, the non-stationary nature of MI-EEG signals poses significant challenges for classification, as frequency characteristics vary across tasks and individuals. Traditional preprocessing methods, such as bandpass filtering and standardization, may struggle to adapt to these variations, potentially limiting classification performance. To address this issue, this study introduces EA-EEG, an improved MI-EEG classification model that incorporates whitening as a preprocessing step to reduce channel correlation and enhance the model feature extraction ability. EA-EEG further leverages a multi-scale pooling strategy, combining convolutional networks and root mean square pooling to extract key spatial and temporal features, and applies prototype-based classification to improve MI-EEG classification performance. Experiments on the BCI4-2A and BCI4-2B datasets demonstrate that EA-EEG achieves state-of-the-art performance, with 85.33% accuracy (Kappa = 0.804) on BCI4-2A and 88.05% accuracy (Kappa = 0.761) on BCI4-2B, surpassing existing approaches. These results confirm EA-EEG's effectiveness in handling non-stationary MI-EEG signals, demonstrating its potential for robust BCI applications, including rehabilitation, prosthetic control, and cognitive monitoring.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"94"},"PeriodicalIF":3.1,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12173996/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144332587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging low-frequency components for enhanced high-frequency steady-state visual evoked potential based brain computer interface in fast calibration scenario.","authors":"Yixin Chen, Ren Xu, Andrew Ty Lau, Xinjie He, Weijie Chen, Xingyu Wang, Andrzej Cichocki, Jing Jin","doi":"10.1007/s11571-025-10303-4","DOIUrl":"https://doi.org/10.1007/s11571-025-10303-4","url":null,"abstract":"<p><p>High-frequency steady-state visual evoked potential-based brain-computer interface (SSVEP-BCI) systems offer improved user comfort but suffer from reduced performance compared to their low-frequency counterparts, limiting their practical application. To address this issue, we propose a transfer learning-based method that leverages low-frequency SSVEP data to enhance high-frequency SSVEP performance. A filtering mechanism is designed to extract informative components from low-frequency signals, and the least squares algorithm is employed to generate high-quality synthetic high-frequency data. Experiments conducted on two public datasets using TDCA, eTRCA, and advanced TRCA-based algorithms demonstrate significant performance improvements. Our approach requires only two calibration trials, achieving 9.03% and 14.49% accuracy increases for eTRCA and TDCA in Dataset 1, and 13.91% and 14.53% improvements in Dataset 2, all within 1.5 s. Moreover, our approach effectively addresses the issue of single calibration data for high-frequency SSVEP-BCI systems. These results support the feasibility of fast calibration and improved performance in real-world high-frequency BCI applications.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"124"},"PeriodicalIF":3.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12317958/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144783585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DWT-OEFS: discrete wavelet transform based optimized ensemble feature selection for Parkinson's disease severity classification.","authors":"Sneha Agrawal, Satya Prakash Sahu","doi":"10.1007/s11571-025-10312-3","DOIUrl":"https://doi.org/10.1007/s11571-025-10312-3","url":null,"abstract":"<p><p>Parkinson's disease (PD) is a cognitive degenerative condition of central nervous system which highly impacts the motor function, resulting in gait dysfunction. Determining the severity of PD is essential for timely and efficient medical management. Doctors often utilize clinical manifestations to grade the severity of PD using Hoehn & Yahr scale where their evaluation is heavily reliant on skill and experience. We propose an optimized ensemble metaheuristic-based feature selection framework by utilizing the signal processing techniques to grade the severity of PD on publicly available Physionet gait Vertical Ground Reaction Force dataset obtained using wearable device. Due to scarcity of medical dataset, the sample size is increased by segmentation of signal. Discrete wavelet transform (DWT) decomposes the signal and a total of 13 features including statistical, frequency and entropy-base are extracted. For an optimum subset of features, three bio-inspired metaheuristic algorithms Binary Grey Wolf Optimization, Binary Whale Optimization and Binary Dragonfly algorithm are used for optimized ensemble feature selection (OEFS) to prevent dimensionality curse thereby improving the classification accuracy. Further, the class imbalance issue is addressed via SMOTETomek and the selected features are then subjected to four best performing classifiers and weighted voting-based classifier. The suggested model is assessed using variety of performance assessment techniques like accuracy, precision, recall, F1-score and Mathew's Correlation Coefficient. The ensemble model achieves the maximum classification accuracy of 98.56% for multiclass classification through weighted voting. Our proposed approach outperforms existing models and individual classifiers, demonstrating its ability to accurately forecast and classify PD severity.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"126"},"PeriodicalIF":3.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12334388/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144815999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neurodynamic evidence reveals identity top-down influences emotional contagion of race.","authors":"Chao Kong, Yanqiu Wei, Ping Hu","doi":"10.1007/s11571-025-10322-1","DOIUrl":"https://doi.org/10.1007/s11571-025-10322-1","url":null,"abstract":"<p><p>Faces contain important information about emotion, race, identity, and age. A large body of research has illustrated that emotional contagion is influenced by race. The Categorization-Individuation Model (CIM) suggests that situational cues (e.g., authority, subjectively important ingroup-outgroup) cause perceivers to shift their attention to identity-diagnostic facial characteristics, especially for other-race faces. The current study is designed to reveal whether identity can top-down influence emotional contagion across races, and the time course of this influence. We recruited 30 Chinese college students to participate in two experiments. Experiment 1 used dynamic emotional faces of Asians and Whites to assess emotional contagion in different races. Experiment 2, based on experiment 1, employed a minimal group paradigm assigning identity information to the racial faces. We used ERP analysis to predict the potential neural mechanism of the influence of identity on racial emotion contagion, and used representation similarity analysis (RSA) to explore the temporal dynamics of the representation of race, emotion, and identity. Our results showed that (1) in experiment 1, Whites produced stronger P1 amplitudes than Asians; in experiment 2, RSA results showed that the time course of representation of race was about 100 ms. (2) In experiments 1 and 2, Happy produced stronger P200 amplitude than Angry; Asians produced stronger P200 amplitude than Whites; The RSA results showed that the time course of representation of emotion and emotional contagion both began about 200 ms after face appearance. (3) In experiment 2, the P300 amplitudes showed a significant interaction of identity and race, and in different group conditions, the P300 amplitude in Asians was stronger than in Whites; however, in the same group conditions, the difference between the two races was insignificant. Results illustrate that identity information top-down influences the neural mechanisms of racial emotional contagion, and the effects are divided into at least three stages: (1) an early stage bottom-up perceptual categorization of other-race; (2) a middle stage emotional and individualization processing; and (3) a late stage top-down modulation by identity cues. Our study is the first to explain the neurodynamics of emotional contagion processing using the Categorization-Individuation Model.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"134"},"PeriodicalIF":3.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12373628/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144945497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Room-temperature one-step synthesis of amine-functionalized lignin with ultra-high nitrogen content for efficient adsorption of Hg(II) and Congo red from wastewater.","authors":"Jiaqi Chen, Mingzhi Li, Yanyao Cai, Yangzi Luo, Haodong Huang, Ruifeng Luo, Yuanyuan Ge, Zhili Li","doi":"10.1016/j.biortech.2025.133069","DOIUrl":"10.1016/j.biortech.2025.133069","url":null,"abstract":"<p><p>Lignin has attracted attention in water treatment due to its extensive sources, complex structure, environmental friendliness, and functionality. Mannich modification is an effective method for enhancing the lignin's active sites, but it typically requires high temperatures and long reaction times, which limits its scalability for practical application. This study presents a simple, one-step Mannich reaction at room temperature for synthesizing aminated lignin (NAL) with high yield and ultra-high nitrogen content (17.34 %), using triethylenetetramine (TETA) as a modifier. The method effectively leverages TETA's symmetrical polyamine properties and glutaraldehyde (GDA)'s dual crosslinking functionality. Density functional theory (DFT) revealed that the potential and the discrepancy of reactive groups' energy gap (E_gap) were the key factors influencing the synthesis. The as-designed NAL exhibited excellent adsorption capacities of 1088.71 mg/g and 909.09 mg/g at 318 K for Hg(II) and Congo red (CR), respectively, that were superior to most reported modified lignin-based adsorbents. NAL also demonstrated robust resistance to ion interference, good reusability, and practical applicability. Notably, the adsorption performance of CR in the Hg(II)-CR binary system was enhanced with an adsorption capacity ratio (R_q) reaching 2.09. XPS, Zeta potential, and DFT calculations revealed that NAL's superior adsorption properties result from multiple interactions, including coordination, π-π interactions, hydrogen bonding, and electrostatic forces. Overall, NAL represents a green and highly effective material for environmental remediation with significant research and practical application value.</p>","PeriodicalId":258,"journal":{"name":"Bioresource Technology","volume":" ","pages":"133069"},"PeriodicalIF":9.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144783125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Acetate metabolism during xylose fermentation enhances 3-hydroxypropionic acid production in engineered acid-tolerant Issatchenkia orientalis.","authors":"Deokyeol Jeong, Dahye Lee, Junli Liu, Soo Rin Kim, Yong-Su Jin, Jikai Zhao, Eun Joong Oh","doi":"10.1016/j.biortech.2025.133113","DOIUrl":"10.1016/j.biortech.2025.133113","url":null,"abstract":"<p><p>Efficient bioconversion of acetate-rich lignocellulosic biomass into value-added chemicals remains a major challenge due to the toxicity of acetic acid. In this study, we developed an acid-tolerant Issatchenkia orientalis strain (IoDY01H) capable of producing 3-hydroxypropionic acid (3-HP), a key bioplastic precursor, from glucose, xylose, and acetate. Using a Cas9-based genome editing system with a hygromycin B resistance marker, we introduced heterologous genes encoding xylose utilization and β-alanine-based 3-HP biosynthetic pathways into the I. orientalis genome. Metabolomic analysis revealed that acetate supplementation redirected metabolic flux toward amino acid and lipid metabolism while reducing tricarboxylic acid (TCA) cycle intermediates. Acetate enhanced 3-HP production; however, the accumulation of β-alanine suggests that the activity of β-alanine-pyruvate aminotransferase may have been limited under acidic conditions. Consistent with this, fermentation at pH 5.5 resulted in higher 3-HP titers than at pH 3.5. Using pretreated hemp stalk hydrolysate as a feedstock, the engineered strain achieved a 3-HP titer of 8.7 g/L via separate hydrolysis and fermentation (SHF), outperforming simultaneous saccharification and fermentation (SSF). These findings demonstrate the feasibility of producing 3-HP from acetate-rich biomass using engineered non-conventional yeast and highlight I. orientalis as a promising microbial chassis for industrial bioconversion.</p>","PeriodicalId":258,"journal":{"name":"Bioresource Technology","volume":" ","pages":"133113"},"PeriodicalIF":9.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144797681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of aquaculture wastewater treatment systems: based on the isolation of the strain Acinetobacter sp. LF10.","authors":"Chuanlong Li, Zhifei Li, Zhiyong Jiang, Yunchuan Cai, Yun Xia, Hongyan Li, Kai Zhang, Jingjing Tian, Wenping Xie, Quanfa Zhong, Guangjun Wang, Jun Xie, Wangbao Gong","doi":"10.1016/j.biortech.2025.133117","DOIUrl":"10.1016/j.biortech.2025.133117","url":null,"abstract":"<p><p>A highly efficient denitrifying bacterial strain (Acinetobacter sp. LF10) was isolated in this study, strain LF10 efficiently removed ammonium (98.02 ± 0.43 %), nitrate (90.35 ± 1.68 %), and nitrite (86.84 ± 2.41 %) from aquatic systems through coordinated assimilatory and dissimilatory nitrate reduction pathways coupled with ammonium assimilation. Compared with the traditional denitrification process, strain LF10 has the potential to reduce greenhouse gas (N₂O) emissions. Strain LF10 not only has strong temperature adaptability (15-35 ℃), but also has the advantage of maintaining a high ammonia nitrogen removal rate under low C/N conditions. Strain LF10 has demonstrated great potential in the treatment of aquaculture wastewater. LF10 can maintain strong competitiveness in biofilters and significantly enhance the nitrogen removal performance of biofilters under normal temperature (31.0 ± 2.4 ℃) and low temperature (15.0 ± 0.3 ℃) conditions. The average total nitrogen removal rates were 94.67 ± 0.64 % and 84.72 ± 17.03 %, respectively. These attributes position LF10 as a highly promising candidate for nitrogen removal in aquaculture wastewater treatment, offering considerable potential for the resource utilization of wastewater in sustainable aquaculture practices.</p>","PeriodicalId":258,"journal":{"name":"Bioresource Technology","volume":" ","pages":"133117"},"PeriodicalIF":9.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144797690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The effect of selected homogeneous and heterogeneous catalysts and feedstock properties on the formation of water soluble components during hydrothermal liquefaction (HTL) of sewage sludge.","authors":"Krzysztof Kapusta, Magdalena Pankiewicz-Sperka, Wioleta Basa, Aleksandra Strugała-Wilczek, Donghai Xu, Peigao Duan, Botian Hao, Yuanyuan Wang, Lijian Leng, Le Yang, Liangliang Fan","doi":"10.1016/j.biortech.2025.133067","DOIUrl":"10.1016/j.biortech.2025.133067","url":null,"abstract":"<p><p>This study investigates the composition of aqueous phase (AP) from 24 HTL trials of two different municipal sewage sludge (MSS) samples, using homogeneous (Na₂CO₃, Li₂CO₃, K₂CO₃, Ba(OH)₂) and heterogeneous (Fe₂O₃, CeO₂, NiO/MoO₃, MoS₂, Ni/NiO, SnO₂, FeS) catalysts. Principal Component Analysis (PCA) was applied to assess the influence of feedstock and catalyst on AP composition i.e. formation of water soluble components. MSS1-derived AP showed a higher proportion of oxygenated aliphatics (13.9-33.7 %), while MSS2 had elevated N-heterocyclic aromatics (19.6-43.3 %). Homogeneous catalysts increased concentration of phenols (up to 26.3 %) and carboxylic acids, with K₂CO₃ almost doubling the carboxylic acid derivatives. Heterogeneous catalysts affected nitrogen and total organic carbon contents. Whereas Fe₂O₃ increases the aliphatic N-heterocycles from 20.6 % to 30.2 % (MSS1) and from 12.7 % to 21.0 % (MSS2), FeS strongly decreases the aromatic hydrocarbons from 9.5 % to 1.1 % (MSS1). PCA analysis confirmed distinct clustering patterns based on the interactions of the feedstock and catalyst, highlighting their synergistic effects. Phenol and cresol were present in the highest concentrations for both sludge, ranged up to 15.6 % and 15.4 % for MSS1 and 12.6 % and 12.9 % for MSS2, respectively. Among the oxygenated aliphatics the most abundant were cyklopenten-1-one, ethanone and their derivatives. N-heterocyclics were represented by a broad mix of pyrazine, pyridine, pyridinole, pyrrolidine, piperidine and their derivatives. The study demonstrates that feedstock properties significantly affect the AP composition, additionally it highlights the role of catalysts applied. These findings provide key insights into optimizing HTL conditions for industrial-scale applications and supporting effective AP by-product management strategies.</p>","PeriodicalId":258,"journal":{"name":"Bioresource Technology","volume":" ","pages":"133067"},"PeriodicalIF":9.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144803068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Memristor-based RDBO-CNN circuit design and application of image multi-classification recognition.","authors":"Gaoyong Han, Guanxiang Cheng, Yanfeng Wang, Junwei Sun","doi":"10.1007/s11571-025-10323-0","DOIUrl":"10.1007/s11571-025-10323-0","url":null,"abstract":"<p><p>Traditional convolutional neural networks used for classification largely rely on hyperparameter tuning and do not have the conditions for hardware implementation. Therefore, a memristor crossbar architecture circuit is proposed to implement the reinforced dung beetle optimization (RDBO) algorithm and the convolutional neural network (CNN). The circuit is composed of feeding module, storage module, ball rolling module, dance module, subpopulation module and CNN module. Traditional DBO algorithm with its adaptability and parallelism for CNN parameter optimization, there are some shortcomings. To solve the problem of unbalanced exploration and exploitation, the tendency to fall into local optimal state, an enhanced dung beetle optimization algorithm based on giant dung beetle and spiral search is proposed. The RDBO circuit is composed of feeding module, storage module, ball rolling module, dance module and subpopulation module. The CNN module is composed of convolution layer, pooling layer and fully connected layer, which is used to recognize and classify the image. The feasibility and accuracy of RDBO-CNN circuit are verified on MNIST image set. In order to further verify the effectiveness of the proposed circuit, simulation and comparison experiments are carried out the satellite image recognition RSI-CB image set which also has good accuracy. This will further promote the development and application of neural network technology.</p>","PeriodicalId":10500,"journal":{"name":"Cognitive Neurodynamics","volume":"19 1","pages":"128"},"PeriodicalIF":3.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12361027/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144945489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}