DAUNet: Detail-Aware U-Shaped Network for 2D Human Pose Estimation

Human pose estimation is a critical research area in the field of computer vision,playing a significant role in applications such as human-computer interaction,behavior analysis,and action recognition.In this paper,we propose a U-shaped keypoint detection network(DAUNet)based on an improved ResNet subsampling structure and spatial grouping mechanism.This network addresses key challenges in traditional methods,such as information loss,large network redundancy,and insufficient sensitivity to low-resolution features.DAUNet is composed of three main components.First,we introduce an improved BottleNeck block that employs partial convolution and strip pooling to reduce computational load and mitigate feature loss.Second,after upsampling,the network eliminates redundant features,improving the overall efficiency.Finally,a lightweight spatial grouping attention mechanism is applied to enhance low-resolution semantic features within the feature map,allowing for better restoration of the original image size and higher accuracy.Experimental results demonstrate that DAUNet achieves superior accuracy compared to most existing keypoint detection models,with a mean PCKh@0.5 score of 91.6%on the MPII dataset and an AP of 76.1%on the COCO dataset.Moreover,real-world experiments further validate the robustness and generalizability of DAUNet for detecting human bodies in unknown environments,highlighting its potential for broader applications.

A U-Shaped Network-Based Grid Tagging Model for Chinese Named Entity Recognition

Chinese named entity recognition(CNER)has received widespread attention as an important task of Chinese information extraction.Most previous research has focused on individually studying flat CNER,overlapped CNER,or discontinuous CNER.However,a unified CNER is often needed in real-world scenarios.Recent studies have shown that grid tagging-based methods based on character-pair relationship classification hold great potential for achieving unified NER.Nevertheless,how to enrich Chinese character-pair grid representations and capture deeper dependencies between character pairs to improve entity recognition performance remains an unresolved challenge.In this study,we enhance the character-pair grid representation by incorporating both local and global information.Significantly,we introduce a new approach by considering the character-pair grid representation matrix as a specialized image,converting the classification of character-pair relationships into a pixel-level semantic segmentation task.We devise a U-shaped network to extract multi-scale and deeper semantic information from the grid image,allowing for a more comprehensive understanding of associative features between character pairs.This approach leads to improved accuracy in predicting their relationships,ultimately enhancing entity recognition performance.We conducted experiments on two public CNER datasets in the biomedical domain,namely CMeEE-V2 and Diakg.The results demonstrate the effectiveness of our approach,which achieves F1-score improvements of 7.29 percentage points and 1.64 percentage points compared to the current state-of-the-art(SOTA)models,respectively.

Effect of mold and core preheating temperature on corrosion resistance of casting Al-12Si alloy U-shaped cooling channel

Temperature has an important impact on the corrosion resistance of mold with cooling channels prepared by casting method.The effect of preheating temperature of the mold and the carbon fiber core on the roughness and corrosion resistance of U-shaped cooling channels made of Al-12Si alloy was examined in depth.The experimental results suggest that as the preheating temperature increased from 273 K to 573 K,the roughness of the inner wall of the cooling channel reduced from 96.6μm to 77.0μm.When the preheating temperature continued to increase to 723 K,the roughness increased to 85.3μm.The wetting between the Al melt and the carbon fiber will reduce micro bubbles and waves on the channel wall as the preheating temperature rises,thereby reducing the roughness.However,with the further increase of preheating temperature,it will increase the solidification time of the Al melt.At this time,the carbon fiber and Al melt will take more time to react,which increases the roughness of the channel wall to a certain extent.The results of exfoliation corrosion show that the larger roughness will aggravate exfoliation corrosion.The prolongation of high temperature reaction time between the carbon fiber and the Al melt will lead to the segregation of Si,which is easy to cause intergranular corrosion.Therefore,reasonable preheating temperature has an important impact on the roughness and corrosion resistance of U-shaped cooling channels.

Relationship between Kawasaki disease and abdominal pain

This editorial presents an analysis of an article recently published in the World Journal of Clinical Cases.Kawasaki disease(KD)is a well-known pediatric vasculitis characterized by fever,rash,conjunctivitis,oral mucosal changes,and swelling of the extremities.This editorial aims to delve into the intricate relationship between KD and abdominal pain,drawing insights from recent research findings to provide a comprehensive understanding and potential avenues for future investigation.

Quantifying source-sink relationships in leaf-color modified rice genotypes during grain filling

Leaf-color modification can affect canopy photosynthesis,with potential effects on rice yield and yield components.Modulating source-sink relationships through crop management is often used to improve crop productivity.This study investigated whether and how modifying leaf color alters source-sink relationships and whether current crop cultivation practices remain applicable for leaf-color modified genotypes.Periodically collected data of total biomass and nitrogen(N)accumulation in rice genotypes of four genetic backgrounds and their leaf-color modified variants(greener or yellower)were analyzed,using a recently established modelling method to quantify the source-sink(im)balance during grain filling.Among all leaf-color variants,only one yellower-leaf variant showed a higher source capacity than its normal genotype.This was associated with greater post-flowering N-uptake that prolonged the functional leaf-N duration,and this greater post-flowering N-uptake was possible because of reduced pre-flowering N-uptake.A density experiment showed that current management practices(insufficient planting density accompanied by abundant N application)are unsuitable for the yellower-leaf genotype,ultimately limiting its yield potential.Leaf-color modification affects source-sink relationships by regulating the N trade-off between pre-and post-flowering uptake,as well as N translocation between source and sink organs.To best exploit leaf-color modification for improving crop productivity,adjustments of crop management practices are required.

What diameter?What height?Influence of measures of average tree size on area-based allometric volume relationships

Volume is an important attribute used in many forest management decisions.Data from 83 fixed-area plots located in central New Brunswick,Canada,are used to examine how different measures of stand-level diameter and height influence volume prediction using a stand-level variant of Honer's(1967)volume equation.When density was included in the models(Volume=f(Diameter,Height,Density))choice of diameter measure was more important than choice of height measure.When density was not included(Volume=f(Diameter,Height)),the opposite was true.For models with density included,moment-based estimators of stand diameter and height performed better than all other measures.For models without density,largest tree estimators of stand diameter and height performed better than other measures.The overall best equation used quadratic mean diameter,Lorey's height,and density(root mean square error=5.26 m^3·ha^(-1);1.9%relative error).The best equation without density used mean diameter of the largest trees needed to calculate a stand density index of 400 and the mean height of the tallest 400 trees per ha(root mean square error=32.08 m^(3)·ha^(-1);11.8%relative error).The results of this study have some important implications for height subsampling and LiDAR-derived forest inventory analyses.

Three anti-inflammatory polysaccharides from Lonicera japonica Thunb.:insights into the structure-function relationships

This study demonstrates the feasibility of producing three polysaccharides(neutral LJP-1,acidic LJP-2 and acidic LJP-3)with significant in vitro and in vivo anti-inflammatory activities from the flowers of Lonicera japonica.The three polysaccharides differed in chemical composition,molecular weight(Mw)distribution,glycosidic linkage pattern,functional groups and morphology.They exhibited excellent protective effects(in a dose-dependent manner)in lipopolysaccharide-injured RAW264.7 macrophages and Cu SO4-damaged zebrafish via reducing NO production and inhibiting the overexpressions of inflammation-related transcription factors,inflammatory proteins and cytokines in the NF-κB/MAPK signaling pathways.Their antiinflammatory effects varied owing to their different molecular characteristics and chemical compositions.Overall,LJP-2 at 400μg/m L was the most effective.LJP-2 consisted mainly of→5)-α-L-Araf(1→,→4)-α-LGalp A(1→and→2)-α-L-Rhap(1→residues with terminal T-β-D-Glcp.Thus,honeysuckle flowers are good sources of anti-inflammatory polysaccharides,and precise fractionation enables the production of potent antiinflammatory agents for the development of functional foods and healthcare products.

Bidirectional relationship between diabetes mellitus and depression:Mechanisms and epidemiology

Diabetes mellitus and depression exhibit a complex bidirectional relationship that profoundly impacts patient health and quality of life.This review explores the physiological mechanisms,including inflammation,oxidative stress,and neu-roendocrine dysregulation,that link these conditions.Psychosocial factors such as social support and lifestyle choices also contribute significantly.Epidemiological insights reveal a higher prevalence of depression among diabetics and an in-creased risk of diabetes in depressed individuals,influenced by demographic variables.Integrated management strategies combining mental health asse-ssments and personalized treatments are essential.Future research should focus on longitudinal and multi-omics studies to deepen understanding and improve therapeutic outcomes.

Characterizing permeability-porosity relationships of porous rocks using a stress sensitivity model in consideration of elastic-structural deformation and tortuosity sensitivity

Clarifying the relationship between stress sensitivities of permeability and porosity is of great significance in guiding underground resource mining.More and more studies focus on how to construct stress sensitivity models to describe the relationship and obtain a comprehensive stress sensitivity of porous rock.However,the limitations of elastic deformation calculation and incompleteness of considered tortuosity sensitivity lead to the fact that the existing stress sensitivity models are still unsatisfactory in terms of accuracy and generalization.Therefore,a more accurate and generic stress sensitivity model considering elastic-structural deformation of capillary cross-section and tortuosity sensitivity is proposed in this paper.The elastic deformation is derived from the fractal scaling model and Hooke's law.Considering the effects of elastic-structural deformation on tortuosity sensitivity,an empirical formula is proposed,and the conditions for its applicability are clarified.The predictive performance of the proposed model for the permeability-porosity relationships is validated in several sets of publicly available experimental data.These experimental data are from different rocks under different pressure cycles.The mean and standard deviation of relative errors of predicted stress sensitivity with respect to experimental data are 2.63%and 1.91%.Compared with other models,the proposed model has higher accuracy and better predictive generalization performance.It is also found that the porosity sensitivity exponent a,which can describe permeability-porosity relationships,is 2 when only elastic deformation is considered.a decreases from 2 when structural deformation is also considered.In addition,a may be greater than 3 due to the increase in tortuosity sensitivity when tortuosity sensitivity is considered even if the rock is not fractured.

Monitor and Acceptance among Couples in Romantic Relationships:Actor-Partner Interdependence Models Based on the Monitor and Acceptance Theory

Communication could be an essential part of couples in their daily life.Based on Monitor and Acceptance Theory(MAT),the present study explored the mediating role of communication in the relationship between mindfulness and relationship quality among college-student couples.The research examined the dynamic relationship of monitoring and acceptance to relationship satisfaction in the Actor-Partner Interdependence Model(APIM),and the mediating effect of positive or negative communications in these relationships.A total of 96 pairs of couples in the universities in Nanjing,China participated in the research.Momentary measurements were used to measure the momentary levels of their monitor,acceptance,positive/negative communication,and relationship satisfaction.A Hierarchical Linear Model(HLM)was used to deal with the APIM.Results showed that the women’s monitor facet of state mindfulness negatively predicted men’s relationship satisfaction through women’s negative communication,and the women’s acceptance facet of state mindfulness positively predicted women’s relationship satisfaction through women’s positive and negative communication at the within-person level.The study highlights the importance of cooperation in monitoring and acceptance for couples to own and hold high levels of relationship satisfaction.

Elucidating the structure-activity relationship of Cu-Ag bimetallic catalysts for electrochemical CO_(2) reduction

Developing bimetallic catalysts is an effective strategy for enhancing the activity and selectivity of electrochemical CO_(2) reduction reactions,where understanding the structure-activity relationship is essential for catalyst design.Herein,we prepared two Cu-Ag bimetallic catalysts with Ag nanoparticles attached to the top or the bottom of Cu nanowires.When tested in a flow cell,the Cu-Ag catalyst with Ag nanoparticles on the bottom achieved a faradaic efficiency of 54%for ethylene production,much higher than the catalyst with Ag nanoparticles on the top.The catalysts were further studied in the H-cell and zero-gap MEA cell.It was found that placing the two metals in the intensified reaction zone is crucial to triggering the tandem reaction of bimetallic catalysts.Our work elucidates the structure-activity relationship of bimetallic catalysts for CO_(2) reduction and demonstrates the importance of considering both catalyst structures and cell characteristics to achieve high activity and selectivity.

The Relationship between Father-Love Absence and Loneliness:Based on the Perspective of the Social Functionalist Theory and the Social Needs Theory

Fathers play an important role in adolescents’development,which is significant for their development and influences their mental health,including feeling of loneliness.However,the effects and mechanisms of father-love absence on individual loneliness are not clear.Based on the social functionalist theory and the social needs theory,this study examines the influence of individual fatherlove absence on loneliness and its underlying mechanisms.A questionnaire survey was administered to 319 junior high school students and 1,476 high school students.The results showed that adolescents with father-love absence had higher levels of loneliness,and that father-love absence affected loneliness levels through mediating pathways of individual gratitude,peer relationships,and gratitude to peer relationships.This study not only confirms the negative effects of father-love absence on adolescents’loneliness,but also explains the mediate roles of individual gratitude and peer relationships.It enriches the theoretical system related to family education and has important theoretical and practical implications for further interventions on adolescents’mental health from the perspective of fatherless parenting.

Floristic composition and edaphic relationships in ferruginous campo rupestre reference ecosystems

Land use change and occupation have led to modifications in the environment causing loss of biodiversity and ecosystem services throughout the planet.Some environments with high economic relevance,such as the ferruginous campo rupestre(rupestrian grassland known as Canga in Brazil),are even more susceptible to severe impacts due to their extreme habitat conditions and low resilience.The determination of reference ecosystems based on the intrinsic characteristics of the ecosystem is essential for conservation as well as to the implementation of ecological restoration.We proposed the reference ecosystem of the three main types of habitats of the ferruginous campo rupestre based on their floristic composition.We described the floristic composition of each habitat and evaluated the physicochemical properties of the soils and the relationship between plants and soils.All three habitats showed high diversity of plant species and many endemic species,such as Chamaecrista choriophylla,Cuphea pseudovaccinium,Lychnophora pinaster,and Vellozia subalata.The distribution of vegetation was strongly related with the edaphic characteristics,with a set of species more adapted to high concentration of base saturation,fine sand,organic carbon,and iron,while another set of species succeeded in more acidic soils with higher S and silt concentration.We provide support for the contention that the ferruginous campo rupestre is a mosaic of different habitats shaped by intrinsic local conditions.Failure to recognize the floristic composition of each particular habitat can lead to inappropriate restoration,increased habitat homogenization and increased loss of biodiversity and ecosystem services.This study also advances the knowledge base for building the reference ecosystem for the different types of ferruginous campo rupestre habitats,as well as a key database for highlighting those species contribute most to community assembly in this diverse and threatened tropical mountain ecosystem.

PCB CT Image Element Segmentation Model Optimizing the Semantic Perception of Connectivity Relationship

Computed Tomography(CT)is a commonly used technology in Printed Circuit Boards(PCB)non-destructive testing,and element segmentation of CT images is a key subsequent step.With the development of deep learning,researchers began to exploit the“pre-training and fine-tuning”training process for multi-element segmentation,reducing the time spent on manual annotation.However,the existing element segmentation model only focuses on the overall accuracy at the pixel level,ignoring whether the element connectivity relationship can be correctly identified.To this end,this paper proposes a PCB CT image element segmentation model optimizing the semantic perception of connectivity relationship(OSPC-seg).The overall training process adopts a“pre-training and fine-tuning”training process.A loss function that optimizes the semantic perception of circuit connectivity relationship(OSPC Loss)is designed from the aspect of alleviating the class imbalance problem and improving the correct connectivity rate.Also,the correct connectivity rate index(CCR)is proposed to evaluate the model’s connectivity relationship recognition capabilities.Experiments show that mIoU and CCR of OSPC-seg on our datasets are 90.1%and 97.0%,improved by 1.5%and 1.6%respectively compared with the baseline model.From visualization results,it can be seen that the segmentation performance of connection positions is significantly improved,which also demonstrates the effectiveness of OSPC-seg.

Different mechanisms underlie similar species-area relationships in two tropical archipelagoes

Despite much research in the field of island biogeography,mechanisms regulating insular diversity remain elusive.Here,we aim to explore mechanisms underlying plant species-area relationships in two tropical archipelagoes in the South China Sea.We found positive plant species-area relationships for both coral and continental archipelagoes.However,our results showed that different mechanisms contributed to similar plant species-area relationships between the two archipelagoes.For coral islands,soil nutrients and spatial distance among communities played major roles in shaping plant community structure and species diversity.By contrast,the direct effect of island area,and to a lesser extent,soil nutrients determined plant species richness on continental islands.Intriguingly,increasing soil nutrients availability(N,P,K)had opposite effects on plant diversity between the two archipelagoes.In summary,the habitat quality effect and dispersal limitation are important for regulating plant diversity on coral islands,whereas the passive sampling effect,and to a lesser extent,the habitat quality effect are important for regulating plant diversity on continental islands.More generally,our findings indicate that island plant species-area relationships are outcomes of the interplay of both niche and neutral processes,but the driving mechanisms behind these relationships depends on the type of islands.

Modern pollen-vegetation relationships along altitudinal vegetation belts in the Leigong Mountain of southwestern China

Understanding the distribution,dispersal,and correlation of modern pollen with vegetation in mountainous regions is essential for establishing accurate modern analogs for fossil pollen records.This study,conducted in Leigong Mountain on the YunnanGuizhou Plateau of southwestern China,involved the collection of 35 surface soil samples from diverse vegetation communities along an elevational gradient ranging from 1210 to 1875 meters.The results reveal a close correspondence between modern pollen assemblages and vegetation zones.Principal Component Analysis(PCA)results indicate that pollen assemblages can effectively distinguish between subtropical montane evergreen broad-leaved forest(SEBF)and subtropical montane deciduous broadleaved forest(SDBF).However,both SEBF and SDBF show significant overlap with subtropical montane evergreen-deciduous broad-leaved mixed forest(SEMF).Detrended Correspondence Analysis(DCA)results clearly distinguish the three vegetation zones,and the first axis of DCA shows a significant positive correlation with elevation(p<0.01,R=0.48).Discriminant Analysis(DA)successfully assigns 94.4%of the modern pollen samples to their respective vegetation zones.Pollen taxa such as Impatiens,Astertype,and Rosaceae exhibit significant indicative capabilities for the SEBF zone,effectively distinguishing this vegetation zone from others.Pinus and Alnus display overrepresentation in the Leigong Mountain region,while Quercus(D,deciduous-type)and Poaceae exhibit high representation in the SEBF zone.In the SEBF zone,both pollen diversity and richness are the lowest.Our study reveals the complex relationship between the richness and diversity of pollen and vegetation.The diversity and richness of tree and shrub pollen are found to be lower than those of the corresponding plants.The pollen-vegetation relationship elucidated in this study serves as a critical reference for reconstructing ancient environments from fossil pollen retrieved in this region.

Relationship between Inter Canine Width and Inter Alar Width, Inter Commissural Width, and Inter Canthal Distance: A Pilot Study

The aim of this study was to determine the relationship between inter canine width (ICW) and inter alar width (IAW), inter commissural width (ICoW), and inter canthal distance (ICaD) in Bantu population. Materials and Methods: It was a pilot study included all participants who were aged at least 18 years, without a history of orthodontics treatment from Prosthodontics Department, Faculty of Dental Medicine, University of Kinshasa. The Ethics committee of the National Center of Research for Dental Sciences in DR Congo approved the study protocol (CNRSB 1504.218). The participants medical records were obtained from the interview and dental examination. Nature of the study was explained with participant information sheet, and an informed consent of all participants was obtained. The inclusion criteria were no missing maxillary and mandibular teeth, no diastema, and no anterior restorations, 18 years old before enrollment in the study. The exclusion criteria were inability to meet the above requirements, pregnancy, and refusal to participate in the study. The inter-canine width (ICW), inter alar width (IAW), inter canthal distance (ICaD) and inter-commissural width (ICoW) of each participant were measured with a digital Vernier caliper (Mitutoyo, UK Ltd.,) (0.01 mm) three times and the average value was recorded. The inter canthal distance (ICaD) was measured without applying pressure by bringing the recording parts of the caliper just in contact with the medial angle. The inter alar width (IAW) was marked with a fine marked pencil on the widest outer surface of the alae of the nose on either side or width. Those two points were measured without applying pressure by bringing the recording parts of the caliper just in contact with the outer surface. The participant was told to stop breathing shortly to avoid any change in shape of the nose. The inter-commissural width (ICoW) was determined by measuring the maxillary lip vermilion from commissure to commissure without the application of pressure on the tissue in the relaxed state. The inter-canine width (ICW) was measured indirectly using a dental floss. A dental floss was marked on one end prior to placement in the mouth. Using that point as reference, the dental floss was circumference along the curvature of the anterior dentition such that it passed along the contact point of all the teeth. The distal end of the canine teeth on both sides was then marked on the floss while it was stretched in the patients mouth. Floss was marked on both sides with the marker pencil. The distance between the two proximal contact points was measured and recorded. Data, analysis and validation were performed by the SPSS software (version 22.0, IBM SPSS Statistics, Chicago, IL, USA). Unpaired t-test was used, of Kolmogorov-Smirnov test. Analysis of variance (ANOVA) test was used to test for comparability between socio-demographic characteristics dental measurements. Pearsons correlation coefficients test was calculated to determine the relationship between facial and dental parameters. Significance was set at P 0.01. Results: Of 314 participants enrolled, 202 were included. The age ranged from 18 to 68 years, with a mean age of 40.62 12.99 years. Although the Pearsons correlation coefficients were negative. Ninety-three participants (46%) were men and one hundred and nine (54%) were women. The overall mean age was 40.62 12.99 years. Facial and dental measurements were greater in women than men with significant differences for ICW (p = 0.04). However, no significant difference was seen between men and women for IAW, ICaD and ICoW (p = 0.44, p = 0.23, p = 0.31 respectively). The correlation including Pearsons correlation coefficient and P-values for all participants is not demonstrated. Conclusion: Within the limitations of this study, the results suggest that IAW, ICaD and ICoW cannot be used as a preliminary method for determining the width of the maxillary for anterior teeth for edentulous patients.

Predicting Users’ Latent Suicidal Risk in Social Media: An Ensemble Model Based on Social Network Relationships

Suicide has become a critical concern,necessitating the development of effective preventative strategies.Social media platforms offer a valuable resource for identifying signs of suicidal ideation.Despite progress in detecting suicidal ideation on social media,accurately identifying individuals who express suicidal thoughts less openly or infrequently poses a significant challenge.To tackle this,we have developed a dataset focused on Chinese suicide narratives from Weibo’s Tree Hole feature and introduced an ensemble model named Text Convolutional Neural Network based on Social Network relationships(TCNN-SN).This model enhances predictive performance by leveraging social network relationship features and applying correction factors within a weighted linear fusion framework.It is specifically designed to identify key individuals who can help uncover hidden suicidal users and clusters.Our model,assessed using the bespoke dataset and benchmarked against alternative classification approaches,demonstrates superior accuracy,F1-score and AUC metrics,achieving 88.57%,88.75%and 94.25%,respectively,outperforming traditional TextCNN models by 12.18%,10.84%and 10.85%.We assert that our methodology offers a significant advancement in the predictive identification of individuals at risk,thereby contributing to the prevention and reduction of suicide incidences.

A Large-Scale Group Decision Making Model Based on Trust Relationship and Social Network Updating

With the development of big data and social computing,large-scale group decisionmaking(LGDM)is nowmerging with social networks.Using social network analysis(SNA),this study proposes an LGDM consensus model that considers the trust relationship among decisionmakers(DMs).In the process of consensusmeasurement:the social network is constructed according to the social relationship among DMs,and the Louvain method is introduced to classify social networks to form subgroups.In this study,the weights of each decision maker and each subgroup are computed by comprehensive network weights and trust weights.In the process of consensus improvement:A feedback mechanism with four identification and two direction rules is designed to guide the consensus of the improvement process.Based on the trust relationship among DMs,the preferences are modified,and the corresponding social network is updated to accelerate the consensus.Compared with the previous research,the proposedmodel not only allows the subgroups to be reconstructed and updated during the adjustment process,but also improves the accuracy of the adjustment by the feedbackmechanism.Finally,an example analysis is conducted to verify the effectiveness and flexibility of the proposed method.Moreover,compared with previous studies,the superiority of the proposed method in solving the LGDM problem is highlighted.

The Risk Role of Defeat on the Mental Health of College Students:A Moderated Mediation Effect of Academic Stress and Interpersonal Relationships

Background:College students face significant academic and physiological changes,making them more susceptible to psychological issues such as depression,self-injury,and suicidal ideation.Feelings of defeat can exacerbate these risks by increasing academic stress.However,interpersonal relationships can moderate the impact of academic stress on students’mental health.Utilizing the presage–process–product model,this study aims to empirically investigate how feelings of defeat influence depression,self-injury,and suicidal ideation among college students.Additionally,it explores the mediating role of academic stress and the moderating role of various types of interpersonal relationships.Methods:A total of 1612 college students(750 females,862 males,mean age=19.64±0.62 years)were recruited through cluster sampling.Data were collected via offline questionnaires administered by a trained psychology teacher and a postgraduate student,ensuring high reliability with two examiners per class.Latent profile analysis(LPA)was used to examine the impact of defeat on mental health outcomes,while mediation analysis was conducted to assess the roles of academic stress and interpersonal relationships.Results:1.Defeat is identified as a significant risk factor for mental health issues among college students;2.Four distinct patterns of interpersonal relationships were identified:the interpersonal-relationship risk group,the father–child-relationship high-risk group,the general interpersonal-relationship group,and the superior interpersonal-relationship group;3.Academic stress partially mediates the relationship between defeat and mental health issues such as depression,self-injury,and suicidal ideation;4.Different interpersonal relationship models moderate the impact of academic stress on depression and suicidal ideation.Conclusion:Defeat is a significant risk factor for mental health problems in college students.Academic stress partially mediates the negative impact of defeat on mental health,while patterns of interpersonal relationships moderate this impact.Effective early prevention and intervention should focus on monitoring students’stress levels and fostering warm,positive parent–child relationships.