• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    Journal of Nantong University(Natural Science Edition)

    Journal of Nantong University(Natural Science Edition)

    JournalISSN 1673-2340

    年发文量

    研究主题

    论文(1627)

    排序
    1Simulation Experiment on the Relationship Between Zero-Orientation Singularity and Motion Accuracy of Parallel Robots
    You Jingjing, Xu Jiameng, Lu Yimeng, Li Sa, Zhang Yi

    To address the unclear relationship between singularity and motion/force transmission performance in spatial mechanisms, a six-degree-of-freedom(6-DOF) spatial parallel robot is considered to investigate the influence of zeroorientation singularity on output motion accuracy in configuration space and velocity space. First, the actuation displacements of the prismatic joints are obtained through inverse kinematics simulations. Second, after adding 0.01%random noise to the actuation displacements of the prismatic joints, forward kinematics simulations are performed, and the output configuration errors and output velocity errors of the moving platform are calculated. Then, the reciprocal of the condition number of the rotational Jacobian matrix is used as an index to quantify how close the mechanism configuration is to the zero-orientation singular configuration. The results show that, when the parallel robot is reconfigured into the ″ 2-2-2″ and ″ 3-2-1″ topological configurations, the performance index for zero-orientation singularity should be greater than 0.16 and 0.28, respectively. Finally, the output motion characteristics of the two configurations are compared and analyzed. The results indicate that the former exhibits better motion transmission performance than the latter.

    2026
    引用
    AI阅读
    加入学术空间
    2Application of Artificial Intelligence in Radiotherapy Dose Prediction
    Zhang Zhenxi, Li Hui, Xiong Tianyu, Chen Zhi, Sun Hongfei, Ren Ge

    Radiotherapy dose distribution directly affects target coverage and the protection of organs at risk(OARs)and is an important basis for evaluating treatment plan quality. Conventional dose planning relies heavily on manual expertise and is associated with long planning times, variations in plan quality, and insufficient consistency across institutions. In recent years, artificial intelligence(AI), particularly deep learning, has been widely applied to patientspecific radiotherapy dose prediction. This review searched PubMed, Scopus, and the Web of Science Core Collection and included 211 original studies published from January 1, 2016, to September 30, 2025. Relevant advances were summarized from two perspectives: technical evolution and clinical translation. At the technical level, the development of convolutional neural networks, generative adversarial networks, Transformers, Mamba, diffusion models, and largemodel-assisted methods for dose prediction was reviewed, and their characteristics were compared in terms of model architecture, input information, prediction targets, public benchmarks, and evaluation frameworks. At the clinical translation level, numerical dose prediction was distinguished from physically deliverable treatment plans, and the relationships between prediction results and plan reoptimization, machine constraints, dose recalculation, quality assurance, and clinical validation were analyzed. Existing studies indicate that AI-based dose prediction has application potential for improving prediction accuracy, assisting treatment plan generation, and enhancing plan consistency. However, challenges remain, including insufficient cross-center generalizability, limited validation of physical deliverability, inadequate clinical interpretability, and insufficient adaptation to emerging radiotherapy techniques. Future studies should strengthen multicenter external validation, the integration of physical constraints, and the development of clinically oriented evaluation frameworks to promote the transition of AI-based dose prediction from algorithmic validation to reliable clinical application.

    2026
    引用
    AI阅读
    加入学术空间
    3A SHAP-integrated Multimodal Model for Three-Class Risk Prediction of Acute Radiation Esophagitis in Non-Small Cell Lung Cancer
    Cheng Xiuyan, Zheng Xiaoli, Mao Ronghu, Guo Wei, Wang Yongqiang, Lou Zhaoyang, Ge Hong, Li Bing

    Conventional normal tissue complication probability(NTCP) models often fail to adequately account for biological heterogeneity and provide individualized toxicity risk assessment in radiotherapy. To address these limitations,this study proposed a multimodal machine learning framework integrating clinical, computed tomography(CT)-based radiomic, and three-dimensional dosiomic features for three-class risk stratification of acute radiation esophagitis(ARE) after radiotherapy. A multimodal dataset was constructed from a cohort of 161 patients with locally advanced non-small cell lung cancer, comprising 56 patients with grade 0 ARE, 68 with grade 1 ARE, and 37 with grade ≥2 ARE. First, high-throughput features were extracted from planning CT images and three-dimensional dose distributions using PyRadiomics. A multi-stage feature selection strategy was then applied: unstable features were removed based on the intraclass correlation coefficient(ICC), followed by dimensionality reduction using Spearman correlation analysis and least absolute shrinkage and selection operator(LASSO) regression. This process yielded 28 key features,including 2 clinical, 19 radiomic, and 7 dosiomic features. The selected features were subsequently used to construct an XGBoost-based multimodal fusion classifier, with hyperparameters optimized by ten-fold cross-validation and grid search. SHapley Additive exPlanations(SHAP) were further employed to interpret the model at both global and local levels. On the test set, the multimodal fusion model achieved an area under the receiver operating characteristic curve(AUROC) of 0.770 and an F1-score of 0.611. Ablation experiments showed that the fusion model achieved an AUROC of 0.770, compared with 0.758 for the radiomics model, while obtaining better overall performance in terms of F1-score, recall, and specificity. The fusion model also outperformed the clinical model and the dosiomics model(AUROC = 0.580). SHAP analysis identified CT-based radiomic features, including InverseVariance and GrayLevelVariance, as well as several dosiomic texture features, as important contributors to model predictions. These results suggest that the proposed multimodal feature fusion framework can improve the graded prediction of complex radiation toxicities and may provide a useful computational decision-support approach for intelligent and individualized radiotherapy planning.

    2026
    引用
    AI阅读
    加入学术空间
    4Alzheimer′s Disease Electroencephalography Classification Based on Phase-Aware and Fourier Decomposition
    Ge Jiachang, Jiang Yizhang, Huang Lijun, Xia Kaijian

    To address the challenges that pathological features are easily obscured by background rhythms and that attention heads are prone to mode collapse in electroencephalography(EEG)-based Alzheimer′s disease(AD) classification, this study proposed PACformer, a phase-aware periodic Transformer classification framework. First, an adaptive phase projector consisting of a large-receptive-field one-dimensional convolution and a multilayer perceptron was used to estimate the initial phase of each EEG segment. The embedded features were then dynamically modulated through phase-aware gating to achieve phase alignment and feature enhancement. Second, a learnable Fourier series was introduced into the encoder to explicitly model periodic background trends, and a ″subtract-attend-add″ residual decomposition strategy was employed to emphasize local pathological perturbations. Finally, a multi-head spectral diversity loss was designed to encourage different attention heads to capture complementary frequency bands while suppressing spectral representation collapse. Experiments on the APAVA dataset showed that PACformer achieved an accuracy of 77.75%, an area under the receiver operating characteristic curve(AUROC) of 86.56%, and an area under the precision-recall curve(AUPRC) of 87.02%, outperforming all 11 comparison models. These results demonstrate that explicit phase alignment and frequency-domain decomposition can enhance the discriminative modeling of nonstationary physiological signals, providing a more robust approach for EEG-based auxiliary screening of AD.

    2026
    引用
    AI阅读
    加入学术空间
    5Advances in the Application of Fluoropolymers for Triboelectric Energy Harvesting
    Duan Yiyang, Wang Ping, Zhang Yan

    Against the background of growing global energy demand and increasing emphasis on sustainable development, triboelectric nanogenerators(TENGs) have attracted considerable attention because of their low cost, simple structure, and high efficiency in harvesting low-frequency mechanical energy. Among them, fluoropolymers have become key materials for fabricating high-performance triboelectric layers owing to their high electronegativity, low surface energy, chemical inertness, and stable dielectric properties. This review systematically summarizes recent research progress in fluoropolymer-based TENGs. First, various fabrication methods for triboelectric layers, including electrospinning, melt injection molding, surface spraying, and 3D printing, are introduced, and their respective advantages and limitations are comparatively analyzed. Subsequently, research advances in improving output performance through surface treatment, structural modification, functional filler incorporation, and material compositing are discussed, and the unique roles of fluoropolymers in enhancing charge density, energy conversion efficiency, and long-term stability are elucidated. On this basis, the major challenges faced by current research, including difficulties in large-scale fabrication, insufficient environmental adaptability, and limitations in device durability and integrability, are summarized. Future development directions are also discussed, including the design of novel fluorinated materials, multifunctional integrated structures, and applications in wearable energy systems. This review aims to provide a reference for the material optimization and expanded applications of fluoropolymer-based TENGs and to offer new perspectives for advancing green and sustainable energy technologies.

    2026
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 1627 篇论文

    高被引作者

    作者引用发文
    Zhi-Zhong Tan14316
    Daya Krishan Lobiyal1291
    Juan Chen1029
    XingGuo Zhang10210
    Yu Ren997
    Hui Xu945
    YuFeng Chen9010
    Yu Zhang8911
    Yang Jingxin8812
    XiaoYan Lu807

    高产作者

    作者引用发文
    Zhi-Zhong Tan14316
    Guoan Zhang3114
    Hongjun Ni6613
    Quan Shi5213
    Yang Jingxin8812
    Shibing Zhang2812
    Yu Zhang8911
    Jian Shi5011
    RuiPing Zhang4011
    Yueping Zhu5111

    相关期刊

    Chinese Journal of Liquid Crystals and Displays
    Journal of Guilin University of Electronic Technology
    Transducer and Microsystem Technologies
    Semiconductor Optoelectronics
    Journal of Changchun University of Technology
    Journal of China University of Metrology
    Journal of Natural Science of Heilongjiang University
    Infrared Technology
    齐齐哈尔大学学报(自然科学版)
    武汉大学学报(理学版)