Query：
学者姓名：孔祥增
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
The combination of electroencephalography (EEG) signals with peripheral physiological signals (PPS) for emotion recognition has garnered increasing attention due to their objectivity and rich information content. However, the heterogeneity and correlations of multimodal physiological signals remain significant challenges in multimodal emotion recognition. In addition, effectively extracting spatiotemporal features from these physiological signals is crucial for accurate emotion recognition. To address these issues, we propose a multimodal emotion recognition framework based on intra-and inter-modal supervised contrastive learning (IAECL), using EEG and PPS signals as inputs. Specifically, IAECL employs modality-specific encoders to mitigate heterogeneity. In addition, a dual-level supervised contrastive learning strategy is introduced: intra-modal contrastive learning enhances the feature compactness within each modality, and inter-modal contrastive learning strengthens cross-modal correlations. To better extract complex spatiotemporal features from EEG, we further a novel EEG encoder that integrates graph-based modeling, spatial-temporal convolution, and multi-head attention. This design effectively captures inter-channel dependencies and enhances local-global feature interactions to improve EEG feature representation. Extensive experiments on the publicly available DEAP and DREAMER datasets demonstrated the superior performance of IAECL, which achieved state-of-the-art results in both within-subject and mixed-subject emotion classification tasks. Visualization analyses further revealed that IAECL effectively aligns multimodal features to enhance inter-modal correlations, offering a novel solution to the challenges of multi-modal emotion recognition. We also analyzed the optimal combination of other physiological signals (e.g., electromyography or temperature recording signals) with EEG for multimodal emotion recognition.
Keyword ：
EEG EEG Emotion recognition Emotion recognition Multimodal physiological signal Multimodal physiological signal Spatiotemporal features Spatiotemporal features Supervised contrastive learning Supervised contrastive learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhao, Rongyue , Ma, Tianyuan , Li, Wangsen et al. EEG-based multimodal emotion recognition framework with supervised contrastive learning and spatial-temporal convolutional attention network [J]. | DIGITAL SIGNAL PROCESSING , 2026 , 168 . |
| MLA | Zhao, Rongyue et al. "EEG-based multimodal emotion recognition framework with supervised contrastive learning and spatial-temporal convolutional attention network" . | DIGITAL SIGNAL PROCESSING 168 (2026) . |
| APA | Zhao, Rongyue , Ma, Tianyuan , Li, Wangsen , Li, Yihua , Li, Jinghu , Huang, Dong et al. EEG-based multimodal emotion recognition framework with supervised contrastive learning and spatial-temporal convolutional attention network . | DIGITAL SIGNAL PROCESSING , 2026 , 168 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Background: The residual fluoroquinolone antibiotics (FQs) in the environment and food has raised public concerns over their potential impact on human health. Terahertz metamaterial sensors (TMSs) have garnered significant attention due to their capability to enhance the interaction between terahertz waves and antibiotic molecules, enabling the detection of trace antibiotics. However, conventional quantitative and qualitative methods based on TMSs suffer from low accuracy and cumbersome processes, respectively. Herein, this work proposed a novel approach that reconstructed optimal terahertz response features of different TMSs with machine learning algorithms, which allowed for analysis of three similar trace FQs with enhanced accuracy. Results: The prepared three patterned TMSs exhibited different resonance responses, which varied with changes in FQs types and concentrations. The resonance peak features of the three TMSs were fused to construct the resonance peak feature matrix (W0) and combined with the K-Nearest Neighbor (KNN) algorithm to build the W0-KNN classification model. The interval feature matrix was constructed by optimizing and expanding the resonance peak feature width. The optimal resonance peak interval feature matrix (Wt) was combined with Gaussian process regression (GPR) algorithms with different kernel functions to build the Wt-GPR quantitative model. The results showed that W0-KNN achieved 100 % classification accuracy for the three FQs. Wt-GPR exhibited high quantitative accuracy for all three FQs with the determination coefficient (R2) of 0.94-0.98, and root mean square error (RMSE) of 6.4085-10.6540. The results of Wt-GPR with different kernel functions had small fluctuations, demonstrating high stability in predictive performance. Significance: Reconstructing features from multi-TMSs in combination with machine learning algorithms enables rapid, precise, and reliable qualitative and quantitative analysis of trace FQs. Our research introduces innovative concepts and methodologies to detect trace FQs using TMS-based sensors, paving the way for future applications of TMS in the biomolecular sensing and detection.
Keyword ：
Biomolecular sensing Biomolecular sensing Fluoroquinolone antibiotics Fluoroquinolone antibiotics Machine learning Machine learning Terahertz metamaterials sensor Terahertz metamaterials sensor Trace detection Trace detection
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Lintong , Kong, Xiangzeng , Wang, Shuhui et al. Resonance features integration of multiple terahertz metamaterials sensors for qualification and quantification of trace fluoroquinolone antibiotics [J]. | ANALYTICA CHIMICA ACTA , 2025 , 1345 . |
| MLA | Zhang, Lintong et al. "Resonance features integration of multiple terahertz metamaterials sensors for qualification and quantification of trace fluoroquinolone antibiotics" . | ANALYTICA CHIMICA ACTA 1345 (2025) . |
| APA | Zhang, Lintong , Kong, Xiangzeng , Wang, Shuhui , Zhang, Wenqing , Wu, Libin , Liu, Xinze et al. Resonance features integration of multiple terahertz metamaterials sensors for qualification and quantification of trace fluoroquinolone antibiotics . | ANALYTICA CHIMICA ACTA , 2025 , 1345 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Near-infrared (NIR) spectroscopy, with its advantages of non-destructive analysis, simple operation, and fast detection speed, has been widely applied in various fields. However, the effectiveness of current spectral analysis techniques still relies on complex preprocessing and feature selection of spectral data. While data-driven deep learning can automatically extract features from raw spectral data, it typically requires large amounts of labeled data for training, limiting its application in spectral analysis. To address this issue, we propose a self-supervised learning (SSL) framework based on convolutional neural networks (CNN) to enhance spectral analysis performance with small sample sizes. The method comprises two learning stages: pre-training and fine-tuning. In the pre-training stage, a large amount of pseudo-labeled data is used to learn intrinsic spectral features, followed by fine-tuning with a smaller set of labeled data to complete the final model training. Applied to our own collected dataset of three tea varieties, the proposed model achieved a classification accuracy of 99.12%. Additionally, experiments on three public datasets demonstrated that the SSL model significantly outperforms traditional machine learning methods, achieving accuracies of 97.83%, 98.14%, and 99.89%, respectively. Comparative experiments further confirmed the effectiveness of the pre-training stage, with the highest accuracy improvement, reaching 10.41%. These results highlight the potential of the proposed method for handling small sample spectral data, providing a viable solution for improved spectral analysis.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhao, Rongyue , Li, Wangsen , Xu, Jinchai et al. A CNN-based self-supervised learning framework for small-sample near-infrared spectroscopy classification [J]. | ANALYTICAL METHODS , 2025 , 17 (5) : 1090-1100 . |
| MLA | Zhao, Rongyue et al. "A CNN-based self-supervised learning framework for small-sample near-infrared spectroscopy classification" . | ANALYTICAL METHODS 17 . 5 (2025) : 1090-1100 . |
| APA | Zhao, Rongyue , Li, Wangsen , Xu, Jinchai , Chen, Linjie , Wei, Xuan , Kong, Xiangzeng . A CNN-based self-supervised learning framework for small-sample near-infrared spectroscopy classification . | ANALYTICAL METHODS , 2025 , 17 (5) , 1090-1100 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
本发明涉及图像识别技术领域，尤其涉及一种基于TransNeXt的水下鱼类识别方法，包括：1)在MMSegmentation框架中对水下鱼群图像数据集进行预处理，划分为训练集和测试集；2)将基于Ade20K数据集上预训练好的改进TransNeXt模型及其参数迁移到MMSegmentation框架中；3)利用训练集和测试集对改进TransNeXt模型进行迭代训练；4)将待检测水下鱼类图像输入到已经训练好的改进TransNeXt模型中，输出识别的结果。本发明可以提高复杂水下环境中鱼类识别的精度，实现水下鱼类的准确识别，适宜进一步推广应用。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张洲铭 , 王璨 , 孔祥增 . 一种基于TransNeXt的水下鱼类识别方法 : CN202411617981.4[P]. | 2024-11-13 . |
| MLA | 张洲铭 et al. "一种基于TransNeXt的水下鱼类识别方法" : CN202411617981.4. | 2024-11-13 . |
| APA | 张洲铭 , 王璨 , 孔祥增 . 一种基于TransNeXt的水下鱼类识别方法 : CN202411617981.4. | 2024-11-13 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Especially with the continuous maturity of the autonomous driving technology, the construction of safety evaluation model that can effectively solve accurate obstacle detection and control while ensuring real-time performance has become an urgent problem in the field of intelligent transportation. Based on the existing multi-task convolutional neural network combined with a reinforcement learning model, this paper presents a more complex and strongly integrated edge computing-driven intelligent perception and control framework. Iniyially, advanced ResNet network is employed to extract the features of multi-source sensor input, and the dynamic attention mechanism is adopted at this stage to filter out important information of obstacles. Then, through the combination of a hierarchical policy gradient-based reinforcement learning algorithm, the adaptive adjustment of vehicle speed and steering was completed, and the interactive iteration between the local decision-making layer and the global scheduling layer was carried out. Another is the collaborative detection part, where distributed data preprocessing and model inference modules are deployed on the edge side at the same time, and high-dimensional images and lidar point clouds are fused in real time in this area through lightweight parallel computing strategy. Experimental results indicate that the model realizes high-precision obstacle detection and stable vehicle control in complex road scenarios, and the overall performance exceeds that of existing mainstream methods. © 2025 IEEE.
Keyword ：
Automobile drivers Automobile drivers Autonomous vehicles Autonomous vehicles Complex networks Complex networks Decision making Decision making Edge computing Edge computing Edge detection Edge detection Intelligent robots Intelligent robots Intelligent systems Intelligent systems Intelligent vehicle highway systems Intelligent vehicle highway systems Learning algorithms Learning algorithms Neural networks Neural networks Obstacle detectors Obstacle detectors Reinforcement learning Reinforcement learning Vehicle detection Vehicle detection
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Weiya , Kong, Xiangzeng . Enhancing Obstacle Detection and Control in Autonomous Robotic Vehicles Through Edge Computing Integration [C] . 2025 : 1863-1866 . |
| MLA | Li, Weiya et al. "Enhancing Obstacle Detection and Control in Autonomous Robotic Vehicles Through Edge Computing Integration" . (2025) : 1863-1866 . |
| APA | Li, Weiya , Kong, Xiangzeng . Enhancing Obstacle Detection and Control in Autonomous Robotic Vehicles Through Edge Computing Integration . (2025) : 1863-1866 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The development of efficient and accurate methods for detecting contamination in agri-foods is critical for ensuring food safety. Terahertz time-domain spectroscopy (THz-TDS), distinguished by its unique spectral characteristics and nondestructive detection capabilities, emerges as a powerful tool for analyzing agri-food safety. This review systematically examines the integration of THz-TDS with frontier technologies (machine learning [ML], metamaterials [MM], microfluidics [MF], and functional nanomaterials [FN]) to enhance detection capabilities. The article delves into the advancements achieved in detecting physical, chemical, and microbial contaminants in agri-food over the past five years (2020-2024) through the integration of THz-TDS with these frontier technologies. Based on the current state of research, this article summarizes the challenges and prospects of THz-TDS with interdisciplinary integration technologies in applications. To advance THz-TDS for agri-food safety monitoring, multidisciplinary integration is required. ML is critical for deciphering complex THz spectral datasets, while MM play a pivotal role in amplifying analyte-specific spectral signatures. FN leverage their potential high-throughput specific adsorption and plasmonic resonance properties to enhance detection sensitivity and specificity. The MF systems can reduce absorption induced by water. This review aims to provide new insights into the multidisciplinary convergence to propel THz-TDS toward transformative agri-food safety applications.
Keyword ：
Agri-food safety Agri-food safety interdisciplinary integration technologies interdisciplinary integration technologies nondestructive detection nondestructive detection terahertz spectroscopy terahertz spectroscopy
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Lintong , Wang, Shuhui , Yang, Wangjincheng et al. A Comprehensive Review of Terahertz Time-Domain Spectroscopy for Agri-Food Safety Detection: Enhanced Sensing Performance Through Multidisciplinary Technology Integration [J]. | CRITICAL REVIEWS IN ANALYTICAL CHEMISTRY , 2025 . |
| MLA | Zhang, Lintong et al. "A Comprehensive Review of Terahertz Time-Domain Spectroscopy for Agri-Food Safety Detection: Enhanced Sensing Performance Through Multidisciplinary Technology Integration" . | CRITICAL REVIEWS IN ANALYTICAL CHEMISTRY (2025) . |
| APA | Zhang, Lintong , Wang, Shuhui , Yang, Wangjincheng , Liu, Xinze , Wei, Zenghui , Abdalla, Alwaseela et al. A Comprehensive Review of Terahertz Time-Domain Spectroscopy for Agri-Food Safety Detection: Enhanced Sensing Performance Through Multidisciplinary Technology Integration . | CRITICAL REVIEWS IN ANALYTICAL CHEMISTRY , 2025 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
本发明公开了一种基于喉部振动与脑电电刺激的语音信号测试方法与系统，涉及语音信息分类领域，包括：根据基础脑电信号判断是否在语音准备阶段对用户施加脑电电刺激；获取语音执行阶段同步采集到用户的喉部振动信号和脑电信号并分别进行数据预处理，得到预处理后的喉部振动信号和脑电信号；对预处理后的脑电信号采用PageRank算法进行通道选择，得到通道选择后的脑电信号；分别对预处理后的喉部振动信号和通道选择后的脑电信号进行特征提取和降维处理，得到降维后的喉部振动特征和降维后的脑电特征并输入到施加L1正则化的双模态SPCA，得到稀疏特征并输入到经训练的语音信号分类模型，得到语音分类识别结果。本发明解决聋哑人发音同音不同义的问题。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 胡启昌 , 温旺逍 , 孔祥增 et al. 基于喉部振动与脑电电刺激的语音信号测试方法与系统 : CN202510480149.2[P]. | 2025-04-17 . |
| MLA | 胡启昌 et al. "基于喉部振动与脑电电刺激的语音信号测试方法与系统" : CN202510480149.2. | 2025-04-17 . |
| APA | 胡启昌 , 温旺逍 , 孔祥增 , 张婷婷 , 黄栋 . 基于喉部振动与脑电电刺激的语音信号测试方法与系统 : CN202510480149.2. | 2025-04-17 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
本发明公开了一种基于铝钇氮薄膜的日盲紫外光电人工视觉突触器件及其制备方法，本方案涉及新型微纳电子材料及功能器件领域；该突触器件包括：衬底、底电极、日盲紫外光响应阻变层与顶电极；所述底电极设置于衬底上，用于引入日盲紫外光信号；日盲紫外光响应阻变层设置于底电极与顶电极之间，用于模拟突触可塑性。其中，日盲紫外光响应阻变层由具有光电导效应的铝钇氮薄膜制成，对波长为200‑280nm的日盲紫外光具有光响应；底电极为透明导电电极；电信号通过顶电极、底电极输入，日盲紫外光信号则通过透明导电底电极输入；本发明提供突触器件可在电信号以及日盲紫外光信号激励下，实现多种光电突触可塑性，在此基础上实现人工视觉功能的模拟。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 胡启昌 , 孔祥增 , 杨小龙 et al. 一种基于铝钇氮薄膜的日盲紫外光电人工视觉突触器件及其制备方法 : CN202411715585.5[P]. | 2024-11-27 . |
| MLA | 胡启昌 et al. "一种基于铝钇氮薄膜的日盲紫外光电人工视觉突触器件及其制备方法" : CN202411715585.5. | 2024-11-27 . |
| APA | 胡启昌 , 孔祥增 , 杨小龙 , 叶霖峰 , 林珺 . 一种基于铝钇氮薄膜的日盲紫外光电人工视觉突触器件及其制备方法 : CN202411715585.5. | 2024-11-27 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Memristors, with their intrinsic low power consumption, high speed operation, and unified memory-computing architecture, present a compelling alternative to overcome the limitations of traditional von Neumann systems. However, the instability of single-dielectric-layer memristors, primarily due to the unpredictable formation of conductive filaments, remains a significant challenge. This study presents the design and fabrication of an Ag/Sm2O3(O-D)/Sm2O3(O-R)/Pt/Ti photoelectric memristor with a dual-dielectric layer structure to address these stability concerns. The device exhibits extremely low operation voltages (V-SET: 0.13 V, V-RESET: -0.73 V), a switch window of up to 10(3), and stable performance across 100 consecutive cycles. Leveraging solar-blind UV writing and electrical erasing, this device performs '' OR '' logic operations with nonvolatile and reconfigurable characteristics, using UV and voltage as input signals and resistance states (RS) as output. The results demonstrate that the conduction mechanism is dominated by the conductive filament mechanism, and the dual-dielectric layer significantly improves the stability of the samarium oxide (Sm2O3) memristor. This study provides a potential approach to addressing the stability and longevity challenges in traditional memristors and holds promise for next-generation nonvolatile logic computing devices.
Keyword ：
conductive filament conductive filament dual-dielectric layer dual-dielectric layer optoelectronic memristor optoelectronic memristor Sm2O3 Sm2O3 solar-blind ultraviolet solar-blind ultraviolet
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Yuzhu , Ye, Linfeng , Yang, Xiaolong et al. Dual-Dielectric Layers Sm2O3-Based Photoelectric Memristor for Enhanced Stability [J]. | ACS APPLIED ELECTRONIC MATERIALS , 2025 , 7 (14) : 6672-6679 . |
| MLA | Wang, Yuzhu et al. "Dual-Dielectric Layers Sm2O3-Based Photoelectric Memristor for Enhanced Stability" . | ACS APPLIED ELECTRONIC MATERIALS 7 . 14 (2025) : 6672-6679 . |
| APA | Wang, Yuzhu , Ye, Linfeng , Yang, Xiaolong , Lin, Jun , Chen, Xiong , Kong, Xiangzeng et al. Dual-Dielectric Layers Sm2O3-Based Photoelectric Memristor for Enhanced Stability . | ACS APPLIED ELECTRONIC MATERIALS , 2025 , 7 (14) , 6672-6679 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Epilepsy is a prevalent neurological disorder marked by sudden, brief episodes of excessive neuronal activity caused by abnormal electrical discharges, which may lead to some mental disorders. Most existing deep learning methods for epilepsy detection rely solely on unimodal EEG signals, neglecting the potential benefits of multimodal information. To address this, we propose a novel multimodal model, DistilCLIP-EEG, based on the CLIP framework, which integrates both EEG signals and text descriptions to capture comprehensive features of epileptic seizures. The model involves an EEG encoder based on the Conformer architecture as a text encoder, the proposed Learnable BERT (BERT-LP) as prompt learning within the encoders. Both operate in a shared latent space for effective cross-modal representation learning. To enhance efficiency and adaptability, we introduce a knowledge distillation method where the trained DistilCLIP-EEG serves as a teacher to guide a more compact student model to reduce training complexity and time. On the TUSZ, AUBMC, and CHB-MIT datasets, both the teacher and student models achieved accuracy rates exceeding 97%. Across all datasets, the F1-scores were consistently above 0.94, demonstrating the robustness and reliability of the proposed framework. Moreover, the student model's parameter count and model size are approximately 58.1% of those of the teacher model, significantly reducing model complexity and storage requirements while maintaining high performance. These results highlight the potential of our proposed model for EEG-based epilepsy detection and establish a solid foundation for deploying lightweight models in resource-constrained settings. © 2025 IEEE.
Keyword ：
Biomedical signal processing Biomedical signal processing Deep learning Deep learning Distillation Distillation Electrophysiology Electrophysiology Learning systems Learning systems Neurodegenerative diseases Neurodegenerative diseases Neurons Neurons Personnel training Personnel training Signal encoding Signal encoding Students Students Teaching Teaching
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Zexin , Shi, Lin , Wu, Haoyu et al. DistilCLIP-EEG: Enhancing Epileptic Seizure Detection Through Multi-modal Learning and Knowledge Distillation [J]. | IEEE Journal of Biomedical and Health Informatics , 2025 . |
| MLA | Wang, Zexin et al. "DistilCLIP-EEG: Enhancing Epileptic Seizure Detection Through Multi-modal Learning and Knowledge Distillation" . | IEEE Journal of Biomedical and Health Informatics (2025) . |
| APA | Wang, Zexin , Shi, Lin , Wu, Haoyu , Luo, Junru , Kong, Xiangzeng , Qi, Jun . DistilCLIP-EEG: Enhancing Epileptic Seizure Detection Through Multi-modal Learning and Knowledge Distillation . | IEEE Journal of Biomedical and Health Informatics , 2025 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
