检索结果-南通市图书馆

同方期刊数据库

MDCFS: few-shot object detection with multilevel decoupled classifiers

在线全文

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： LI Chuanhui ZHOU Mian FENG Zhikun SUI Zezhou gao Zhan School of Computer Science and Engineering， Tianjin University of Technology

Few-shot object detection poses unique challenges as it requires effectively learning novel classes with limited labeled data. Current approaches often suffer from biases towards base classes during fine-tuning， leading to suboptimal performance on detecting novel classes. Additionally， in complex scenes， the confusion between foreground and background objects further affects the accuracy and robustness of the model. To address these issues， we propose the Multilevel Decoupling Classification Few-Shot Algorithm (MDCFS). we decouple the standard classifier into a parallel foreground classifier and a background classifier in the Few-Shot Object Detection (FSOD) setting. This decoupling enables the independent separation of positive samples from noisy negative samples， alleviating the foreground-background confusion problem commonly encountered in few-shot detectors. For Generalized Few-Shot Object Detection (G-FSOD)， where the few-shot dataset contains base classes， we further decouple the foreground classification head into a base class classification head and a novel class classification head. To ensure balance， we assign more weight to the novel class classification head， effectively addressing the bias towards base classes. Furthermore， we optimize the initial weights of the few-shot fine-tuning stage， significantly reducing training time and mitigating catastrophic forgetting in G-FSOD. Additionally， we incorporate metric learning into our model with minimal cost. Experimental results demonstrate the effectiveness of our approach. Compared to state-of-the-art few-shot object detection methods based on fine-tuning， MDCFS achieves performance improvements of up to 6.3% on the PASCAL VOC dataset and 1.5% on the COCO dataset.

关键词：

Catalytic atroposelective synthesis of indolyl quinazolinones bearing N-N/C-C diaxes

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China Chemistry 2025年

作者： Ning-Yi Wang Shuo gao Zhu-Di Shu Bei-Bei Cheng Chun Ma Yu-Chen Zhang Feng Shi Research Center of Chiral Functional Heterocycles School of Chemistry and Materials Science Jiangsu Normal University School of Petrochemical Engineering Changzhou University School of Chemistry and Chemical Engineering Henan Normal University

The first catalytic atroposelective synthesis of indole derivatives bearing N-N/C-C diaxes has been established by the strategy of de novo ring formation. By this strategy, various indolyl quinazolinones bearing vicinal N-N/C-C diaxes were synthesized in high yields with overall good diastereoselectivities and excellent enantioselectivities via chiral phosphoric acid-catalyzed onepot asymmetric formal (5+1) cycloaddition/oxidation reaction. Moreover, such indolyl quinazolinones bearing vicinal N-N/CC diaxes have good configurational stability and could be converted into new chiral ligands with applications in asymmetric catalysis. Therefore, this work not only offered a new member for the family of diaxial atropisomers, but also provided a powerful strategy for catalytic asymmetric synthesis of atropisomers bearing N-N/C-C diaxes.

关键词：

An efficient and balanced feature pyramid network: shared-FPN

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： Tian Sulong Qin Longfei Pang Wenchao gao Ying Zhao Dexin School of Computer Science and Engineering， Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology， Tianjin University of Technology

In the field of object detection， it is challenging to achieve a balance between neck complexity and accuracy. To address this issue， we propose an efficient and decoupled neck module called Shared-FPN(Shared Feature Pyramid Network). Our design aims to effectively address the trade-off between these two factors. Neck modules are crucial for effectively fusing multi-scale information in neural network models. However， traditional neck designs， with their single structure， have struggled to significantly improve detection performance. In recent years， the incorporation of neural architecture search techniques in neck design has led to an increase in model complexity. This trade-off between model complexity and detection performance highlights the need for more efficient neck design approaches. Not only does Shared-FPN not increase the number of model parameters and FLOPs， but it also can be easily ported to any of the detection models. It improves on PAFPN by using transposed convolution with a large convolution kernel as the upsampling module， designing spatial pyramidal pooling-fast downsampling(SPPFD) based on shared pooling， and designing shared convolution as the right part module. To evaluate the performance of Shared-FPN in object detection tasks， we conducted experiments on object detection datasets. The results show that Shared-FPN achieved excellent performance across all sizes. In particular， on the VOC 2012 dataset， which contains mostly large objects， Shared-FPN's mAP was improved by 11.2% compared to FPN with YOLOX-s as the detector. On the COCO dataset， which contains mostly small objects， Shared-FPN's mAP was improved by 7.8% compared to FPN and 7.1% compared to PAFPN with Faster RCNN as the detector. Shared-FPN can be easily inserted into any of the detectors for better performance in various scenarios， such as small， medium or large objects.

关键词：

Voxel event graph neural network for event-based human gait recognition

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： MA Guangyuan GONG Xiaolin XU Jiangtao gao Jiandong GUO Zhaoxuan School of Microelectronics， Tianjin University

To improve the accuracy of event-based gait recognition， a method called voxel event graph neural network (VEGNN) is proposed. This method voxelizes the event stream and selects representative voxels as vertices of the graph. Then the edges are constructed based on spatio-temporal distance and temporal order constraints so that the event stream is constructed as a graph structure. Finally， a lightweight feature extraction network based on graph neural networks (GNNs) is used to efficiently capture spatio-temporal information and motion cues from the event graph. To evaluate our method， an event-based gait recognition dataset called Celex-Gait is created. Experimental results show that VEGNN achieves a gait recognition accuracy of 95.8% (best among all methods) and 93.9% (second best among all methods) on the Celex-Gait dataset and the DVS128-Gait-Day dataset， respectively. Furthermore， compared to the state-of-the-art methods， VEGNN reduces the number of model parameters by 30%. This indicates that VEGNN achieves higher recognition accuracy with lower model complexity.

关键词：

Composite-mask GAN based on refined optical flow and disparity map for SLAM visual odometry

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： JI Yuehui JIANG Jingwei LIU Junjie SONG Yu gao Qiang School of Electrical Engineering and Automation， Tianjin University of Technology Tianjin Key Laboratory of Control Theory and Application for Complex Systems

Although deep learning methods have been widely applied in slam visual odometry over the past decade with impressive improvements， the accuracy remains limited in complex dynamic environments. In this paper， a composite mask-based generative adversarial network is introduced to predict camera motion and binocular depth maps. Specifically， a perceptual generator is constructed to obtain the corresponding parallax map and optical flow from between two neighboring frames. Then， an iterative pose improvement strategy is proposed to improve the accuracy of pose estimation. Finally， a composite mask is embedded in the discriminator to sense structural deformation in the synthesized virtual image， thereby increasing the overall structural constraints of the network model， improving the accuracy of camera pose estimation， and reducing drift issues in the Visual Odometer. Detailed quantitative and qualitative evaluations on the KITTI dataset show that the proposed framework outperforms existing conventional， supervised learning and unsupervised depth VO methods， providing better results in both pose estimation and depth estimation.

关键词：

Pulsed dynamic electrolysis enhanced PEMWE hydrogen production:Revealing the effects of pulsed electric fields on protons mass transport and hydrogen bubble escape

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2025年第1期100卷 201-214页

作者： Xuewei Zhang Wei Zhou Yuming Huang Liang Xie Tonghui Li Huimin Kang Lijie Wang Yang Yu Yani Ding Junfeng Li Jiaxiang Chen Miaoting Sun Shuo Cheng Xiaoxiao Meng Jihui gao Guangbo Zhao School of Energy Science and Engineering Harbin Institute of Technology China Datang Technology Innovation Co. Ltd

The transition of hydrogen sourcing from carbon-intensive to water-based methodologies is underway,with renewable energy-powered proton exchange membrane water electrolysis （PEMWE） emerging as the preeminent pathway for hydrogen *** remarkable advancements in this field,confronting the sluggish electrochemical kinetics and inherent high-energy consumption arising from deteriorated mass transport within PEMWE systems remains a formidable *** impediment stems primarily from the hindered protons mass transfer and the untimely hydrogen bubbles *** address these challenges,we harness the inherent variability of electrical energy and introduce an innovative pulsed dynamic water electrolysis *** to constant voltage electrolysis (hydrogen production rate:51.6 m L h-1,energy consumption:5.37 kwh Nm-3H2),this strategy (hydrogen production rate:66 m L h-1,energy consumption:3.83 kwh Nm-3H2) increases the hydrogen production rate by approximately 27%and reduces the energy consumption by about 28%.Furthermore,we demonstrate the practicality of this system by integrating it with an off-grid photovoltaic （PV） system designed for outdoor operation,successfully driving a hydrogen production current of up to 500 mA under an average voltage of approximately 2 *** combined results of in-situ characterization and finite element analysis reveal the performance enhancement mechanism:pulsed dynamic electrolysis （PDE） dramatically accelerates the enrichment of protons at the electrode/solution interface and facilitates the release of bubbles on the electrode *** such,PDE-enhanced PEMWE represents a synergistic advancement,concurrently enhancing both the hydrogen generation reaction and associated transport *** promising technology not only redefines the landscape of electrolysis-based hydrogen production but also holds immense potential for broadening its application across a diverse spectrum of electrocatalytic endeavors.

关键词： Electrolysis

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

数字化赋能乡村公共文化空间的机理与路径

西北农林科技大学学报（社会科学版） 2025年第1期25卷 17-27页

作者：高春凤北京建筑大学人文与社会科学学院北京100044

数字化是破解乡村公共文化空间发展困境的重要抓手,对于推进城乡公共文化服务均等化具有重要作用。数字化有助于打破“空间即建筑,形态即实体”的观念,推动乡村公共文化空间从线下向线上、实体向虚拟、传统业态向新兴业态转变,促进文化... 详细信息

数字化是破解乡村公共文化空间发展困境的重要抓手,对于推进城乡公共文化服务均等化具有重要作用。数字化有助于打破“空间即建筑,形态即实体”的观念,推动乡村公共文化空间从线下向线上、实体向虚拟、传统业态向新兴业态转变,促进文化基础设施升级、服务机构互联和文化资源整合。鉴于实践中存在的数字化设施不足、文化资源互联共享不足、网络文化治理滞后等问题,乡村公共文化空间的建设和发展要以数字化赋能为主线,按照理论赋能推动思想理念转变、技术赋能提升乡村公共文化空间建设品质、服务赋能增强乡村公共文化空间发展活力、治理赋能提高乡村公共文化空间管理效度的逻辑机理,依据“新空间、新基建、新机制、新场景”路径,以“数字化+”“互联网+”“人工智能+”为驱动,打造多元场景融合、线下线上协同、供给需求匹配、数量质量并重、标准特色兼容的新型乡村公共文化空间。

关键词：数字化赋能乡村公共文化空间逻辑机理空间重塑

Short-term Photovoltaic Power Prediction Based on Feature Optimization and Hybrid Improved Grey Wolf Algorithm-optimized BiLSTM Network

维普期刊数据库

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Dianwang Jishu/Power System Technology 2025年第1期49卷 209-222页

作者： Zhao, Ruyi Wang, Xiaohui Zheng, Bihuang Li, Daoxing gao, Yi Guo, Pengtian China Electric Power Research Institute Haidian District Beijing 100192 China Economic and Technological Research Institute State Grid Tianjin Electric Power Company Hedong District Tianjin 300171 China

To address the challenges posed by strong noise interference in photovoltaic (PV) sequences and the issues of low accuracy and poor generalization of a single model in PV power prediction, we propose a short-term PV power prediction method. This method uses feature optimization and a hybrid improved Grey Wolf algorithm to optimize the BiLSTM network. Firstly, the mutual information algorithm is employed for variable selection in input data to eliminate redundant variables. Subsequently, the Complementary Ensemble Empirical Mode Decomposition and an improved wavelet threshold algorithm are applied to the selected data for feature reconstruction to reduce noise interference in the data and optimize input variable features. Finally, the standard Grey Wolf Optimizer algorithm underwent hybrid optimization by integrating improved Tent chaotic mapping, nonlinear decreasing factors, dynamic weight strategies, and the differential evolution algorithm. This process aimed to ascertain the optimal hyperparameter combination for the BiLSTM network. The attention mechanism was also employed to extract key temporal information from the data, developing a novel short-term photovoltaic power prediction model. Simulation experiments demonstrate that, compared to the least squares support vector machine, long short-term memory network, and bidirectional long short-term memory neural network, the proposed model achieves an average reduction of 12.45%, 7.95%, and 5.37% in root mean square error under various weather conditions such as sunny, cloudy, overcast, and rainy, showcasing excellent predictive performance, good generalization ability, and promising engineering application value. © 2025 Power System Technology Press. All rights reserved.

关键词： Mean square error

融合BiLSTM与CNN的推特黑灰产分类模型

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

计算机工程与应用 2025年第1期61卷 186-195页

作者：朱恩德王威高见中国人民公安大学信息网络安全学院北京100038

当前推特等国外社交平台,已成为从事网络黑灰产犯罪不可或缺的工具,对推特上黑灰产账号进行发现、检测和分类对于打击网络犯罪、维护社会稳定具有重大意义。现有的推文分类模型双向长短时记忆网络(bi-directional long short-term memor... 详细信息

当前推特等国外社交平台,已成为从事网络黑灰产犯罪不可或缺的工具,对推特上黑灰产账号进行发现、检测和分类对于打击网络犯罪、维护社会稳定具有重大意义。现有的推文分类模型双向长短时记忆网络(bi-directional long short-term memory,BiLSTM)可以学习推文的上下文信息,却无法学习局部关键信息,卷积神经网络(convolution neural network,CNN)模型可以学习推文的局部关键信息,却无法学习推文的上下文信息。结合BiLSTM与CNN两种模型的优势,提出了BiLSTM-CNN推文分类模型,该模型将推文进行向量化后,输入BiLSTM模型学习推文的上下文信息,再在BiLSTM模型后引入CNN层,进行局部特征的提取,最后使用全连接层将经过池化的特征连接在一起,并应用softmax函数进行四分类。模型在自主构建的中文推特黑灰产推文数据集上进行实验,并使用TextCNN、TextRNN、TextRCNN三种分类模型作为对比实验,实验结果显示,所提的BiLSTM-CNN推文分类模型在对四类推文进行分类的宏准确率为98.32%,明显高于TextCNN、TextRNN和TextRCNN三种模型的准确率。

关键词：文本分类双向长短期记忆网络(BiLSTM) 卷积神经网络(CNN) 黑灰产推特

维普期刊数据库