Tracking the information about your manuscript
Communicate with the editorial office
Query manuscript payment status Edit officeCollecting, editing, reviewing and other affairs offices
Managing manuscripts
Managing author information and external review Expert Information Expert officeOnline Review
Online Communication with the Editorial Department
Visited
Page visits today: 40
About the Journal
Governed by: Jiangsu Education Department
Sponsored by: Nantong University
Published by: Editorial Office of Journal of Nantong University (Natural Science Edition)
Issues per year: 4
ISSN: 1673-2340
CN: 32-1755/N
Construction of clinical event prediction models for stroke patients based on multimodal fusion
Wang Muyu;Yang Yang;Chen Hui;Predicting clinical events in patients with stroke is important for reducing healthcare burden and improving patient outcomes. However, existing prediction models are typically developed using single-modality data, such as medical images, whereas multimodal medical data that may provide complementary information have not been fully exploited. To address this issue, this study proposed and compared methods for constructing stroke clinical event prediction models by integrating magnetic resonance imaging(MRI), radiology reports, and laboratory test data. First, a three-dimensional convolutional neural network, a pretrained Chinese language model, and a multilayer perceptron were used to extract features from MRI images, radiology reports, and tabular data, respectively. Concatenation-based and averaging-based multimodal fusion strategies were then designed and compared. Subsequently, prediction models based on unimodal, bimodal, and trimodal data were evaluated for two tasks: predicting whether the length of hospital stay would exceed 7 or 14 days. The results showed that, for the two prediction tasks, the multimodal model integrating imaging, textual, and tabular data achieved area under the receiver operating characteristic curve(AUROC) values of 0.746 and 0.813, respectively, and area under the precision-recall curve(AUPRC) values of 0.580 and 0.542, respectively, outperforming all unimodal and bimodal models. Among the evaluated multimodal fusion strategies, attention-weighted averaging achieved the best performance, with an AUROC of 0.813 and an AUPRC of 0.542. These results demonstrate that multimodal data fusion can effectively improve the performance of clinical event prediction models for patients with stroke.
A population-regulated attention network for assisted diagnosis of autism spectrum disorder
Zhang Xiongtao;Ma Yuan;Wang Feng;Yan Qiqi;Shen Qing;Graph neural networks(GNNs) based on multimodal magnetic resonance imaging(MRI) have shown considerable potential in medical image analysis because of their ability to effectively model the non-Euclidean structure of brain networks. However, most existing studies overlook substantial inter-individual variability in clinical symptoms and incorporate demographic information only through simple feature concatenation, which limits classification performance. In addition, heterogeneity across imaging sites can impair model generalizability in cross-site validation. To address these limitations, this study proposed a demographic-regulated multimodal graph attention network framework(DM-GAT). First, a demographic-aware dynamic graph structure learning(D-GSL) module was developed to reconstruct latent brain network topology using demographic information, thereby alleviating the effects of noise and interindividual variability in static functional connectivity. Second, a multi-view demographic interaction attention(M-DIA)mechanism was introduced, in which demographic features were used as gating signals to dynamically modulate attention weights for nodes and edges, thereby enhancing subject-specific representation learning. Experiments on the cross-site ABIDE and ADHD-200 datasets demonstrated that DM-GAT achieved a classification accuracy(ACC) of 74.51% on ABIDE, which comprised 943 subjects from 17 sites, compared with 73.27% achieved by MHNet. Ablation studies further confirmed the effectiveness of the D-GSL and M-DIA modules, with the D-GSL module improving ACC by approximately 4 percentage points.
Alzheimer′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.
A 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.
Application 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.
Power-Efficiency Co-optimization of Class E Inverter Circuits Based on the NSGA-II Algorithm
Shang Xiuzhang;Tan Shuxin;To address the challenges of parameter optimization and the difficulty in attaining globally optimal parameter sets in the design of Class E inverter circuits， this paper proposes an optimization methodology that integrates the NSGA-II algorithm with circuit simulation. Output power and conversion efficiency are taken as dual optimization objectives， equivalent circuit models of commercial components—incorporating parasitic parameters—are embedded into the simulation environment， An initial population of 10 000 parameter combinations is generated by uniform random sampling within ±10% of the theoretically calculated values， and evaluated through transient simulations to obtain the corresponding performance metrics. Elite parent individuals are selected through non-dominance sorting and crowding distance calculations， which are subsequently re-evaluated via simulation. The parent and offspring populations are merged， and a new generation is formed by non-dominance sorting and crowding distance calculations. This iterative process continues until the improvement in the maximum efficiency saturates， yielding a Pareto-optimal set of passive component parameters for the Class E inverter circuit.For a 4 MHz Class E inverter operating at 20 V input， the conventionally designed circuit based on theoretical parameters delivers an output power of 40.6 W with a conversion efficiency of 90.7%. In contrast， the highest efficiency point on the optimized Pareto front achieves an efficiency of 96.2% at an output power of 48.2 W， while the maximum power point reaches 81.0 W while still maintaining an efficiency of 91.0%. This method successfully achieves a synergistic optimization of conversion efficiency and output power in Class E inverter circuits ， offering a systematic and reproducible design pathway for the parameter optimization of high-frequency Class E circuits.
[Downloads: 23 ] [Citations: 0 ] [Reads: 19 ] HTML PDF Cite this article
Carbon Emission Prediction for Asphalt Pavement Maintenance Construction Based on Meta-Learner Parameter Optimization
LIAO Huanwang;JIN Jiayu;XIAO Qing;WU Yang;To address the problems of limited sample size， strong variable coupling， and difficulty in adaptive ensemble weight allocation in carbon emission prediction for asphalt pavement maintenance construction， an ensemble prediction method based on Gaussian mixture model (GMM) data augmentation and improved non-dominated sorting genetic algorithm II (NSGA-II) weight optimization is proposed. Using 17 actual maintenance projects as samples， a seven-variable energy-consumption feature system is constructed. GMM augmentation is applied only to the training set， expanding the number of training samples from 12 to 70， and support vector machine (SVM)， least absolute shrinkage and selection operator (LASSO)， and gradient boosting decision tree (GBDT) are selected as base learners. The results show that the augmented samples are mainly distributed within the neighborhood of the original training samples. Under the current test-set conditions， the mean absolute error (MAE)， root mean square error (RMSE)， mean absolute percentage error (MAPE)， and coefficient of determination (R2) of the proposed model are 4.673， 6.291， 9.009%， and 0.934， respectively. In the Bootstrap resampling analysis based on the fixed test set， the proposed method exhibited lower overall errors than the averaging and empirical weighting methods. The proposed method can provide a reference for carbon emission prediction and low-carbon scheme comparison in similar asphalt pavement maintenance projects.
[Downloads: 12 ] [Citations: 0 ] [Reads: 11 ] HTML PDF Cite this article
Research progress on the co-infection and interaction mechanisms of Xanthomonas in plant disease complexes
Chen Lei;Wang Jing;Chen Xian;Pedro Laborda;Wang Suyan;Xanthomonas is one of the most widespread and destructive plant bacterial pathogens， posing a significant threat to global food security by infecting a wide range of major crops， including rice， cabbage， soybean， and cassava. The pathovars (pathovar， pv.) of Xanthomonas exhibit high host specificity and environmental adaptability， with each specific pathovar typically infecting only one or a few plant species. During the infection process， Xanthomonas can act independently or interact with other pathogens to form coinfections， leading to complex plant disease complexes. This review systematically summarizes recent advances in the study of Xanthomonas co-infections with other bacteria. It focuses on three typical interaction patterns—antagonism， synergism， and coexistence—and elaborates on the potential mechanisms underlying these interactions within plant disease complexes. This review aims to deepen the understanding of Xanthomonas co-infection phenomena and provide a theoretical reference for the study of other plant disease complexes.
[Downloads: 27 ] [Citations: 0 ] [Reads: 14 ] HTML PDF Cite this article
Advances in the Application of Artificial Intelligence in Acute Respiratory Distress Syndrome
SUN Xiangyu;LIU Xiaozhu;Acute respiratory distress syndrome (ARDS) remains a pivotal unsolved challenge in critical care medicine. Its high mortality rate and marked interindividual heterogeneity in patients render it difficult to further enhance the clinical efficacy of conventional supportive therapies. This systematic review comprehensively collates the research progress of artificial intelligence (AI) and machine learning (ML) technologies in the clinical management of ARDS， and focuses on analyzing their transformative value in innovating the diagnosis and treatment pathway of ARDS and improving clinical outcomes. The multimodal application scenarios of AI/ML technologies are systematically explored: early prediction and accurate diagnosis of ARDS are achieved based on multimodal data such as electronic health records (EHRs) and imaging examinations; prognostic assessment models superior to traditional scoring systems are constructed to implement accurate patient risk stratification; different ARDS subtypes are precisely identified to provide scientific guidance for formulating individualized treatment regimens. In addition， the specific roles of AI technologies in the optimization of clinical treatment are elaborated in detail， and their application potential in the field of ARDS-related drug research and development is also covered. Finally， the major current bottlenecks in the application of AI technologies for ARDS are analyzed， including inconsistent data quality， insufficient model generalization ability， poor interpretability， and difficulties in clinical translation and integration. Meanwhile， it is pointed out that AI-driven diagnosis and treatment strategies provide an unprecedented opportunity for the implementation of precision medicine for ARDS， the optimization of real-time clinical decision-making， and the ultimate improvement of patient prognosis， thus offering a comprehensive reference basis for subsequent relevant research and clinical translational applications.
[Downloads: 72 ] [Citations: 0 ] [Reads: 63 ] HTML PDF Cite this article
Impulsive Sampled-Data Control of Nonlinear Flexible Spacecraft under Cyberattacks
DENG Yingwei;YAN Hao;DING Kui;WANG Zipeng;This paper investigates the secure tracking control problem for nonlinear flexible spacecraft subject to false data injection (FDI) attacks. An impulsive sampled-data control method based on the Takagi-Sugeno (T-S) fuzzy model is proposed to guarantee stable trajectory tracking in a networked environment. First， the nonlinear attitude dynamics of the flexible spacecraft are represented by a T-S fuzzy model to describe the strong nonlinearity and rigid-flexible coupling. A fuzzy reference system with the same structure is then introduced， and the tracking control problem is transformed into the stability analysis of an error system. Second， since FDI attacks on sampled data may cause abrupt state jumps， a T-S fuzzy impulsive error system is established. Accordingly， a fuzzy impulsive state-feedback controller is designed. Furthermore， by constructing a piecewise time-varying Lyapunov function and using linear matrix inequality techniques， sufficient conditions are derived to ensure the asymptotic stability and prescribed H∞ performance of the closed-loop system. A feasible procedure is also provided for computing the controller gains. Finally， a numerical example of a typical flexible spacecraft is presented. The results show that， under bounded periodic FDI attacks on the sampled error information channel， the proposed controller effectively suppresses the tracking errors induced by attack signals and rigid-flexible coupling. The attitude angular velocities and quaternion vector components converge to the reference trajectory. Compared with the case without control input， the closed-loop tracking errors are significantly reduced， the control inputs remain within a reasonable range， and the H∞ steady-state attenuation rate satisfies the prescribed performance index. These results demonstrate the effectiveness and rationality of the proposed T-S fuzzy impulsive sampled-data control method.
[Downloads: 20 ] [Citations: 0 ] [Reads: 66 ] HTML PDF Cite this article
Application of Increasing PID Controlling Method in Temperature Controlling System
YAN Xiao-zhao,ZHANG Xing-guo(School of Mechanical Engineering,Nantong University,Nantong 226007,China)Temperature control is widely applied in scientific experiments and industrial processes.However,the temperature control system has characteristics of being nonlinear,time-varying and has hysteretic complicated large inertial system,and the effect of control is closely related to the algorithms adopted.In this paper,an experimental temperature control system is developed to meet the requirement of innovative ability training for mechatronic undergraduates.An increasing PID control algorithm is designed.The experimental results prove that the effect of the designed algorithm is better than the traditional PID algorithm.
Research and Development in Techniques of Dyeing Wastewater Treatment
JING Xiao-hui 1,YOUKe-fei 2,DING Xin-yu 2,CAI Zai-sheng 1(1.School of Chemistry and Chemical Engineering,Donghua University,Shanghai200051,China; 2.School of Chemistry and Chemical Engineering,Nantong University,Nantong226007,China)Reviewof the progress on treating methods of dyeing wastewater is presented,especially the advanced techniques are introduced,suchas membrane extraction,ultrasonic processes,high-energyphysical processes,advanced electrocatalytic oxidaˉtion processes and advanced photocatalytic oxidation processes.The treating trend for the dyeing wastewater is discussed.
The Application and the Development Foreground of Chitin and Chitosan
ZHANG Wei,LIN Hong,CHEN Yu-yue (School of Material Engineering,Soochow University,Suzhou 215021,China)The structure and the performance of chitin and chitosan are introduced and the application of chitin and chitosan in various fields is analyzed in this paper.The existing problems and the development foreground of chitin and chitosan are summarized in this paper.
Overview of SERS
LAN Yan-na,ZHOULing (Nantong Institute of Technology,Nantong226007,China)The principle of Raman spectrumis expounded first.Then the characteristics of SERS effect in experiment is summaˉrized and the mechanism of SERS is described.It's an accepted viewthat the mechanism of electromagnetic enhancement and the mechanismof chemical enhancement are both in existence.But which one is more important in different experiment depends on specific condition.
Application of ANSYS to Reinforced Concrete Beam
WANG Ya-ping 1,CHEN Jian-ping 2 ,CHEN Wu-zhou 3(1.Nantong Institute of Technology,Nantong226007,China;2.Nantong Architectural Design Institute of Industry,Nantong226001,China;3.Nantong Water Conservancy Construction Company,Nantong226005,China)In this article,taking features of reinforced concrete into account ,FEM software of ANSYS was used to calculate the beam' s deformation and the stress and strain of the normal section.At last,the answers to ANSYS(crack length,stress of reinforc-ing bar and concrete)and theoretical answers were compared in search of reasons and ways or measures that can amend it.
The Application and the Development Foreground of Chitin and Chitosan
ZHANG Wei,LIN Hong,CHEN Yu-yue (School of Material Engineering,Soochow University,Suzhou 215021,China)The structure and the performance of chitin and chitosan are introduced and the application of chitin and chitosan in various fields is analyzed in this paper.The existing problems and the development foreground of chitin and chitosan are summarized in this paper.
Application of Increasing PID Controlling Method in Temperature Controlling System
YAN Xiao-zhao,ZHANG Xing-guo(School of Mechanical Engineering,Nantong University,Nantong 226007,China)Temperature control is widely applied in scientific experiments and industrial processes.However,the temperature control system has characteristics of being nonlinear,time-varying and has hysteretic complicated large inertial system,and the effect of control is closely related to the algorithms adopted.In this paper,an experimental temperature control system is developed to meet the requirement of innovative ability training for mechatronic undergraduates.An increasing PID control algorithm is designed.The experimental results prove that the effect of the designed algorithm is better than the traditional PID algorithm.
Preparation of functionalized carbon nanomaterials and their energy storage applications
LI Qi;QIN Tian;GE Cunwang;Over the past decades, functional carbon nanomaterials(FCMs) have attracted much attention from the materials science community owning to their outstanding physical and chemical properties, such as high electronic conductivity/rapid mass transfer, plentiful active sites, good chemical stability, and robust mechanical stiffness. In view of the anisotropic and synergistic effects stemming from the functionalization as well as small size effect at the nanoscale,these multifunctional FCMs exhibit high potential especially in lithium-ion batteries, sodium-ion batteries, potassiumion batteries, lithium-sulfur batteries, organic solar cells, and supercapacitors. In this review, the functionalization strategies of carbon nanomaterials that have been developed over the last five years are comprehensively summarized and then application of FCMs in energy storage and conversion is introduced exhaustively. Finally, the pressing challenges and research directions are discussed according to the development trend.
Preparation of biochar and its application in environmental pollution management
WANG Jiayue;LING Qian;ZHANG Yunhao;WANG Xinyu;LIN Jiaqi;ZHANG Weitao;LIU Zhixin;WANG Xiangke;Biochar is a kind of environmentally friendly porous material which can be easily synthesized at low cost and in large scale. It has a wide range of applications in environmental pollution control and pollutants′ remediation and immobilization due to its large specific surface area and abundant surface functional groups. In this review, we mainly summarized the preparation of biochar, discussed the effect of preparation conditions on the properties of prepared biochar. The application of biochar in the removal of various pollutants from wastewater and soil improvement,the immobilization and elimination of different pollutants in soils, were reviewed in detail and the interaction mechanism was discussed. The removal of heavy metal ions was mainly attributed to the sorption of metal ions through the formation of surface complexes and part of metal ions could be reduced from high valence to low valence and then immobilized on biochar through adsorption-reduction-solidification strategy. The removal of organic pollutants from solution to biochar was mainly attributed to surface complexation, H bonding and π-π interaction on biochar surfaces.The organic pollutants could also be photocatalytic degraded by biochar or biochar-based materials under visible light irradiation. In conclusion, further research and discussion on the interaction mechanism of pollutant molecular with biochar at molecular level are helpful for the application of biochar in wastewater treatment and soil remediation. This review is of scientific significance for reducing the migration and transformation of pollutants in the environment and reducing the risk of environmental pollutants in the natural environment.
Modeling and simulation of proton exchange membrane electrolyzer system
WANG Huidong;YAO Haiyan;GUO Qiang;XIA Hongjun;Proton exchange membrane(PEM) electrolyzer converts electrical energy into chemical and heat energy,which is a green hydrogen production method, featuring fast response, high current density, compact structure, and other advantages. In the modeling of proton exchange membrane electrolysis water hydrogen production system,existing literature lacks a lumped parameter model that comprehensively describes the voltage and current changes of the electrolysis cell, as well as the temperature dynamics of each component of the system. This study establishes a steady-state voltage model of PEM electrolyzer and the thermal dynamic model of the system based on the basic principles of electrochemistry and the laws of thermodynamics. The simulation analysis was carried out based on MATLAB/Simulink software, and the simulation results were compared with the experimental data. The results showed that the voltage error is less than 0.02 V, and the temperature error is less than 1.6 K, which verifies the validity of the model. The established model can describe and predict the behavior of system parameters and provide support for system design and control. According to the efficiency model of PEM electrolyzer and the simulation results, the influence of different temperature and pressure on the performance of the electrolyzer was analyzed. It is concluded that increasing the temperature and decreasing the pressure can improve the efficiency of the electrolyzer, with temperature being the main factor. Using the simulation model, a feedforward PID controller was employed for temperature control, achieving an overshoot of less than 0.6 K and a settling time within 400 seconds. Comparison with a traditional PID controller demonstrates that the feedforward PID controller has advantages in terms of reduced overshoot and faster response.