Nonlinear elastic constitutive relations of residually stressed composites with stiff curved fibres

Mechanical models of residually stressed fibre-reinforced solids,which do not resist bending,have been developed in the literature.However,in some residually stressed fibre-reinforced elastic solids,resistance to fibre bending is significant,and the mechanical behavior of such solids should be investigated.Hence,in this paper,we model the mechanical aspect of residually stressed elastic solids with bending stiffness due to fibre curvature,which up to the authors’knowledge has not been mechanically modeled in the past.The proposed constitutive equation involves a nonsymmetric stress and a couple-stress tensor.Spectral invariants are used in the constitutive equation,where each spectral invariant has an intelligible physical meaning,and hence they are useful in experiment and analysis.A prototype strain energy function is proposed.Moreover,we use this prototype to give results for some cylindrical boundary value problems.

From waste to wealth:Coal tar residue derived carbon materials as low-cost anodes for potassium-ion batteries

Carbon materials are widely recognized as highly promising electrode materials for various energy storage system applications.Coal tar residues(CTR),as a type of carbon-rich solid waste with high value-added utilization,are crucially important for the development of a more sustainable world.In this study,we employed a straightforward direct carbonization method within the temperature range of 700-1000℃to convert the worthless solid waste CTR into economically valuable carbon materials as anodes for potassium-ion batteries(PIBs).The effect of carbonization temperature on the microstructure and the potassium ions storage properties of CTR-derived carbons(CTRCs)were systematically explored by structural and morphological characterization,alongside electrochemical performances assessment.Based on the co-regulation between the turbine layers,crystal structure,pore structure,functional groups,and electrical conductivity of CTR-derived carbon carbonized at 900℃(CTRC-900H),the electrode material with high reversible capacity of 265.6m Ah·g^(-1)at 50 m A·g^(-1),a desirable cycling stability with 93.8%capacity retention even after 100 cycles,and the remarkable rate performance for PIBs were obtained.Furthermore,cyclic voltammetry(CV)at different scan rates and galvanostatic intermittent titration technique(GITT)have been employed to explore the potassium ions storage mechanism and electrochemical kinetics of CTRCs.Results indicate that the electrode behavior is predominantly governed by surface-induced capacitive processes,particularly under high current densities,with the potassium storage mechanism characterized by an“adsorption-weak intercalation”mechanism.This work highlights the potential of CTR-based carbon as a promising electrode material category suitable for high-performance PIBs electrodes,while also provides valuable insights into the new avenues for the high value-added utilization of CTR.

A Lightweight Multiscale Feature Fusion Network for Solar Cell Defect Detection

Solar cell defect detection is crucial for quality inspection in photovoltaic power generation modules.In the production process,defect samples occur infrequently and exhibit random shapes and sizes,which makes it challenging to collect defective samples.Additionally,the complex surface background of polysilicon cell wafers complicates the accurate identification and localization of defective regions.This paper proposes a novel Lightweight Multiscale Feature Fusion network(LMFF)to address these challenges.The network comprises a feature extraction network,a multi-scale feature fusion module(MFF),and a segmentation network.Specifically,a feature extraction network is proposed to obtain multi-scale feature outputs,and a multi-scale feature fusion module(MFF)is used to fuse multi-scale feature information effectively.In order to capture finer-grained multi-scale information from the fusion features,we propose a multi-scale attention module(MSA)in the segmentation network to enhance the network’s ability for small target detection.Moreover,depthwise separable convolutions are introduced to construct depthwise separable residual blocks(DSR)to reduce the model’s parameter number.Finally,to validate the proposed method’s defect segmentation and localization performance,we constructed three solar cell defect detection datasets:SolarCells,SolarCells-S,and PVEL-S.SolarCells and SolarCells-S are monocrystalline silicon datasets,and PVEL-S is a polycrystalline silicon dataset.Experimental results show that the IOU of our method on these three datasets can reach 68.5%,51.0%,and 92.7%,respectively,and the F1-Score can reach 81.3%,67.5%,and 96.2%,respectively,which surpasses other commonly usedmethods and verifies the effectiveness of our LMFF network.

Structural and microwave absorption properties of CoFe_(2)O_(4)/residual carbon composites

Electromagnetic interference,which necessitates the rapid advancement of substances with exceptional capabilities for bsorbing electromagnetic waves,is of urgent concern in contemporary society.In this work,CoFe_(2)O_(4)/residual carbon from coal gasification fine slag(CFO/RC)composites were created using a novel hydrothermal method.Various mechanisms for microwave absorption,including conductive loss,natural resonance,interfacial dipole polarization,and magnetic flux loss,are involved in these composites.Consequently,compared with pure residual carbon materials,this composite offers superior capabilities in microwave absorption.At 7.76GHz,the CFO/RC-2 composite achieves an impressive minimum reflection loss(RL_(min))of-43.99 dB with a thickness of 2.44 mm.Moreover,CFO/RC-3 demonstrates an effective absorption bandwidth(EAB)of up to 4.16 GHz,accompanied by a thickness of 1.18mm.This study revealed the remarkable capability of the composite to diminish electromagnetic waves,providing a new generation method for microwave absorbing materials of superior quality.

Social function scores and influencing factors in patients with residual depressive symptoms

BACKGROUND At present,the influencing factors of social function in patients with residual depressive symptoms are still unclear.Residual depressive symptoms are highly harmful,leading to low mood in patients,affecting work and interpersonal communication,increasing the risk of recurrence,and adding to the burden on families.Studying the influencing factors of their social function is of great significance.AIM To explore the social function score and its influencing factors in patients with residual depressive symptoms.METHODS This observational study surveyed patients with residual depressive symptoms(case group)and healthy patients undergoing physical examinations(control group).Participants were admitted between January 2022 and December 2023.Social functioning was assessed using the Sheehan Disability Scale(SDS),and scores were compared between groups.Factors influencing SDS scores in patients with residual depressive symptoms were analyzed by applying multiple linear regression while using the receiver operating characteristic curve,and these RESULTS The SDS scores of the 158 patients with depressive symptoms were 11.48±3.26.Compared with the control group,the SDS scores and all items in the case group were higher.SDS scores were higher in patients with relapse,discon-tinuous medication,drug therapy alone,severe somatic symptoms,obvious residual symptoms,and anxiety scores≥8.Disease history,medication compliance,therapy method,and residual symptoms correlated positively with SDS scores(r=0.354,0.414,0.602,and 0.456,respectively).Independent influencing factors included disease history,medication compliance,therapy method,somatic symptoms,residual symptoms,and anxiety scores(P<0.05).The areas under the curve for predicting social functional impairment using these factors were 0.713,0.559,0.684,0.729,0.668,and 0.628,respectively,with sensitivities of 79.2%,61.8%,76.8%,81.7%,63.6%,and 65.5%and specificities of 83.3%,87.5%,82.6%,83.3%,86.7%,and 92.1%,respectively.CONCLUSION The social function scores of patients with residual symptoms of depression are high.They are affected by disease history,medication compliance,therapy method,degree of somatic symptoms,residual symptoms,and anxiety.

改进注意力机制嵌入PR-Net模型的水稻病害识别仿真

针对现有的CNN模型在水稻叶部病害的识别中准确率较低的问题,提出了一种结合并行结构和残差结构的混合卷积神经网络模型PRC-Net(parallel residual with coordinate attention network)。引入并行结构,提高卷积的感受野;结合残差结构,使特征信息完整的连续传递;在骨干模型PR-Net中嵌入改进的空间注意力机制,增强对不同尺度病斑特征信息的凝聚程度;为进一步提升病害识别的准确率,并减少模型的训练时间和推理时间,通过改变加权方式对模型结构进行优化。仿真结果表明:与InceptionResNetV2等分类模型相比,PRC-Net具有更少的训练参数、更短的训练时间和更高的识别精度,性能优于其他作物病害识别模型。

基于GRU-DRSN的双通道人体活动识别

人体活动识别(human activity recognizition, HAR)在医疗、军工、智能家居等领域有很大的应用空间。传统机器学习方法特征提取难度较大且精度不高。针对上述问题并结合传感器时序特性,提出了一种融合CBAM(convolutional block attention module)注意力机制的GRU-DRSN双通道并行模型,有效避免了传统串行模型因网络深度加深引起梯度爆炸和消失问题。同时并行结构使得两条支路具有相同的优先级,使用深度残差收缩网络(deep residual shrinkage network, DRSN)提取数据的深层空间特征,同时使用门控循环结构(gated recurrent unit, GRU)学习活动样本在时间序列上的特征,同时进行提取样本不同维度的特征,并通过CBAM模块进行特征的权重分配,最后通过Softmax层进行识别,实现了端对端的人体活动识别。使用公开数据集(wireless sensor data mining, WISDM)进行验证,模型平均精度达到了97.6%,与传统机器学习模型和前人所提神经网络模型相比,有更好的识别效果。

Structural properties of residual carbon in coal gasification fine slag and their influence on flotation separation and resource utilization:A review

Coal gasification fine slag(FS)is a typical solid waste generated in coal gasification.Its current disposal methods of stockpil-ing and landfilling have caused serious soil and ecological hazards.Separation recovery and the high-value utilization of residual carbon(RC)in FS are the keys to realizing the win-win situation of the coal chemical industry in terms of economic and environmental benefits.The structural properties,such as pore,surface functional group,and microcrystalline structures,of RC in FS(FS-RC)not only affect the flotation recovery efficiency of FS-RC but also form the basis for the high-value utilization of FS-RC.In this paper,the characteristics of FS-RC in terms of pore structure,surface functional groups,and microcrystalline structure are sorted out in accordance with gasification type and FS particle size.The reasons for the formation of the special structural properties of FS-RC are analyzed,and their influence on the flotation separation and high-value utilization of FS-RC is summarized.Separation methods based on the pore structural characterist-ics of FS-RC,such as ultrasonic pretreatment-pore-blocking flotation and pore breaking-flocculation flotation,are proposed to be the key development technologies for improving FS-RC recovery in the future.The design of low-cost,low-dose collectors containing polar bonds based on the surface and microcrystalline structures of FS-RC is proposed to be an important breakthrough point for strengthening the flotation efficiency of FS-RC in the future.The high-value utilization of FS should be based on the physicochemical structural proper-ties of FS-RC and should focus on the environmental impact of hazardous elements and the recyclability of chemical waste liquid to es-tablish an environmentally friendly utilization method.This review is of great theoretical importance for the comprehensive understand-ing of the unique structural properties of FS-RC,the breakthrough of the technological bottleneck in the efficient flotation separation of FS,and the expansion of the field of the high value-added utilization of FS-RC.

Disturbance failure mechanism of highly stressed rock in deep excavation:Current status and prospects

This article reviews the current status on the dynamic behavior of highly stressed rocks under disturbances.Firstly,the experimental apparatus,methods,and theories related to the disturbance dynamics of deep,high-stress rock are reviewed,followed by the introduction of scholars’research on deep rock deformation and failure from an energy perspective.Subsequently,with a backdrop of highstress phenomena in deep hard rock,such as rock bursts and core disking,we delve into the current state of research on rock microstructure analysis and residual stresses from the perspective of studying the energy storage mechanisms in rocks.Thereafter,the current state of research on the mechanical response and the energy dissipation of highly stressed rock formations is briefly retrospected.Finally,the insufficient aspects in the current research on the disturbance and failure mechanisms in deep,highly stressed rock formations are summarized,and prospects for future research are provided.This work provides new avenues for the research on the mechanical response and damage-fracture mechanisms of rocks under high-stress conditions.

A short overview of the lead iodide residue impact and regulation strategies in perovskite solar cells

Lead iodide(PbI2) is a vital raw material for preparing perovskite solar cells(PSCs),and it not only takes part in forming the light absorption layer but also remains in the grain boundary as a passivator.In other words,the PbI2 content in the precursor and as formed film will affect the efficiency and stability of the PSCs.With moderate residual PbI2,it passivates the bulk/surface defects of perovskite,reduces the interfacial recombination,promotes the perovskite stability,minimizes the device hysteresis,and so on.Deficient PbI2 residue will reduce the interfacial passivation effect and device performance.In addition to facilitating the non-radiative recombination,over PbI2 residue can also lead to electronic insulation in the grain boundary and deteriorate the device performance.However,the impact and regulation of PbI2 residue on the device performance and stability is still not fully understood.Herein,a comprehensive and detailed review is presented by discussing the PbI2 residue impact and its regulation strategies(i.e., elimination,facilitation and conversion of the residue PbI2) to manipulate the PbI2 content,distribution and forms.Finally,we also show future outlooks in this field,with an aim to help further the progression of high-efficiency and stable PSCs.

Identifying the best common factor model via exploratory eactor analysis

Currently,there is no solid criterion for judging the quality of the estimators in factor analysis.This paper presents a new evaluation method for exploratory factor analysis that pinpoints an appropriate number of factors along with the best method for factor extraction.The proposed technique consists of two steps:testing the normality of the residuals from the fitted model via the Shapiro-Wilk test and using an empirical quantified index to judge the quality of the factor model.Examples are presented to demonstrate how the method is implemented and to verify its effectiveness.

Constructing a stable interface on Ni-rich LiNi_(0.8)Co_(0.1)Mn_(0.1)O_(2) cathode via lactic acid-assisted engineering strategy

Ni-rich layered oxides are potential cathode materials for next-generation high energy density Li-ion batteries due to their high capacity and low cost.However,the inherently unstable surface properties,including high levels of residual Li compounds,dissolution of transition metal cations,and parasitic side reactions,have not been effectively addressed,leading to significant degradation in their electrochemical performance.In this study,we propose a simple and effective lactic acid-assisted interface engineering strategy to regulate the surface chemistry and properties of Ni-rich LiNi_(0.8)Co_(0.1)Mr_(0.1)O_(2) cathode.This novel surface treatment method successfully eliminates surface residual Li compounds,inhibits structural collapse,and mitigates cathode-electrolyte interface film growth.As a result,the lactic acidtreated LiNi_(0.8)Co_(0.1)Mn_(0.1)O_(2) achieved a remarkable capacity retention of 91.7% after 100 cycles at 0.5 C(25℃) and outstanding rate capability of 149.5 mA h g^(-1) at 10 C,significantly outperforming the pristine material.Furthermore,a pouch-type full cell incorporating the modified LiNi_(0.8)Co_(0.1)Mn_(0.1)O_(2) cathode demonstrates impressive long-term cycle life,retaining 81.5% of its capacity after 500 cycles at 1 C.More importantly,the thermal stability of the modified cathode is also dramatically improved.This study offers a valuable surface modification strategy for enhancing the overall performance of Ni-rich cathode materials.

Residual alkali-evoked cross-linked polymer layer for anti-air-sensitivity LiNi_(0.89)Co_(0.06)Mn_(0.05)O_(2)cathode

High-energy density lithium-ion batteries(LIBs)with layered high-nickel oxide cathodes(LiNi_(x)Co_(y)Mn_(1-x-y)O_(2),x≥0.8)show great promise in consumer electronics and vehicular applications.However,LiNi_(x)Co_(y)Mn_(1-x-y)O_(2)faces challenges related to capacity decay caused by residual alkalis owing to high sensitivity to air.To address this issue,we propose a hazardous substances upcycling method that fundamentally mitigates alkali content and concurrently induces the emergence of an anti-air-sensitive layer on the cathode surface.Through the neutralization of polyacrylic acid(PAA)with residual alkalis and then coupling it with 3-aminopropyl triethoxysilane(KH550),a stable and ion-conductive cross-linked polymer layer is in situ integrated into the LiNi_(0.89)Co_(0.06)Mn_(0.05)O_(2)(NCM)cathode.Our characterization and measurements demonstrate its effectiveness.The NCM material exhibits impressive cycling performance,retaining 88.4%of its capacity after 200 cycles at 5 C and achieving an extraordinary specific capacity of 170.0 mA h g^(-1) at 10 C.Importantly,this layer on the NCM efficiently suppresses unfavorable phase transitions,severe electrolyte degradation,and CO_(2)gas evolution,while maintaining commendable resistance to air exposure.This surface modification strategy shows widespread potential for creating air-stable LiNi_(x)Co_(y)Mn_(1-x-y)O_(2)cathodes,thereby advancing high-performance LIBs.

Evolution of microstructure and properties of a novel Ni-based superalloy during stress relief annealing

We discussed the decrease in residual stress,precipitation evolution,and mechanical properties of GH4151 alloy in different annealing temperatures,which were studied by the scanning electron microscope(SEM),high-resolution transmission electron microscopy(HRTEM),and electron backscatter diffraction(EBSD).The findings reveal that annealing processing has a significant impact on diminishing residual stresses.As the annealing temperature rose from 950 to 1150℃,the majority of the residual stresses were relieved from 60.1 MPa down to 10.9 MPa.Moreover,the stress relaxation mechanism transitioned from being mainly controlled by dislocation slip to a combination of dislocation slip and grain boundary migration.Meanwhile,the annealing treatment promotes the decomposition of the Laves,accompanied by the precipitation ofμ-(Mo_(6)Co_(7))starting at 950℃ and reaching a maximum value at 1050℃.The tensile strength and plasticity of the annealing alloy at 1150℃ reached the maximum(1394 MPa,56.1%)which was 131%,200%fold than those of the as-cast alloy(1060 MPa,26.6%),but the oxidation process in the alloy was accelerated at 1150℃.The enhancement in durability and flexibility is primarily due to the dissolution of the brittle phase,along with the shape and dispersal of theγ′phase.

Workout Action Recognition in Video Streams Using an Attention Driven Residual DC-GRU Network

Regular exercise is a crucial aspect of daily life, as it enables individuals to stay physically active, lowers thelikelihood of developing illnesses, and enhances life expectancy. The recognition of workout actions in videostreams holds significant importance in computer vision research, as it aims to enhance exercise adherence, enableinstant recognition, advance fitness tracking technologies, and optimize fitness routines. However, existing actiondatasets often lack diversity and specificity for workout actions, hindering the development of accurate recognitionmodels. To address this gap, the Workout Action Video dataset (WAVd) has been introduced as a significantcontribution. WAVd comprises a diverse collection of labeled workout action videos, meticulously curated toencompass various exercises performed by numerous individuals in different settings. This research proposes aninnovative framework based on the Attention driven Residual Deep Convolutional-Gated Recurrent Unit (ResDCGRU)network for workout action recognition in video streams. Unlike image-based action recognition, videoscontain spatio-temporal information, making the task more complex and challenging. While substantial progresshas been made in this area, challenges persist in detecting subtle and complex actions, handling occlusions,and managing the computational demands of deep learning approaches. The proposed ResDC-GRU Attentionmodel demonstrated exceptional classification performance with 95.81% accuracy in classifying workout actionvideos and also outperformed various state-of-the-art models. The method also yielded 81.6%, 97.2%, 95.6%, and93.2% accuracy on established benchmark datasets, namely HMDB51, Youtube Actions, UCF50, and UCF101,respectively, showcasing its superiority and robustness in action recognition. The findings suggest practicalimplications in real-world scenarios where precise video action recognition is paramount, addressing the persistingchallenges in the field. TheWAVd dataset serves as a catalyst for the development ofmore robust and effective fitnesstracking systems and ultimately promotes healthier lifestyles through improved exercise monitoring and analysis.

A New Encrypted Traffic Identification Model Based on VAE-LSTM-DRN

Encrypted traffic identification pertains to the precise acquisition and categorization of data from traffic datasets containing imbalanced and obscured content.The extraction of encrypted traffic attributes and their subsequent identification presents a formidable challenge.The existing models have predominantly relied on direct extraction of encrypted traffic data from imbalanced datasets,with the dataset’s imbalance significantly affecting the model’s performance.In the present study,a new model,referred to as UD-VLD(Unbalanced Dataset-VAE-LSTM-DRN),was proposed to address above problem.The proposed model is an encrypted traffic identification model for handling unbalanced datasets.The encoder of the variational autoencoder(VAE)is combined with the decoder and Long-short term Memory(LSTM)in UD-VLD model to realize the data enhancement processing of the original unbalanced datasets.The enhanced data is processed by transforming the deep residual network(DRN)to address neural network gradient-related issues.Subsequently,the data is classified and recognized.The UD-VLD model integrates the related techniques of deep learning into the encrypted traffic recognition technique,thereby solving the processing problem for unbalanced datasets.The UD-VLD model was tested using the publicly available Tor dataset and VPN dataset.The UD-VLD model is evaluated against other comparative models in terms of accuracy,loss rate,precision,recall,F1-score,total time,and ROC curve.The results reveal that the UD-VLD model exhibits better performance in both binary and multi classification,being higher than other encrypted traffic recognition models that exist for unbalanced datasets.Furthermore,the evaluation performance indicates that the UD-VLD model effectivelymitigates the impact of unbalanced data on traffic classification.and can serve as a novel solution for encrypted traffic identification.

Comprehensive reutilization of herbal waste:Coproduction of magnolol,honokiol,and β-amyrin from Magnolia officinalis residue

Herbal extraction residues(HERs)cause serious environmental pollution and resource waste.In this study,a novel green route was designed for the comprehensive reutilization of all components in HERs,taking Magnolia officinalis residues(MOR)as an example.The reluctant structure of MOR was first destroyed by alkali pretreatment to release the functional ingredients(magnolol and honokiol)originally remaining in MOR and to make MOR more accessible for hydrolysis.A metal–organic frame material MIL-101(Cr)with a maximum absorption capacity of 255.64 mg g^(-1)was synthesized to absorb the released honokiol and magnolol from the pretreated MOR solutions,and 40 g L^(-1)reducing sugars were obtained with 81.8%enzymatic hydrolysis rate at 10%MOR solid loading.Finally,382 mg L-1β-amyrin was produced from MOR hydrolysates by an engineered yeast strain.In total,1 kg honokiol,8 kg magnolol,and 7.64 kg β-amyrin could produce from 1 ton MOR by this cleaner process with a total economic output of 170,700 RMB.

Possibilities for the synthesis of superheavy element Z=121 in fusion reactions

Based on the dinuclear system model,the calculated evaporation residue cross sections matched well with the current experimental results.The synthesis of superheavy elements Z=121 was systematically studied through combinations of stable projectiles with Z=21-30 and targets with half-lives exceeding 50 d.The influence of mass asymmetry and isotopic dependence on the projectile and target nuclei was investigated in detail.The reactions^(254)Es(^(46)Ti,3n)^(297)121 and^(252)Es(^(46)Ti,3n)^(295)121 were found to be experimentally feasible for synthesizing superheavy element Z=121,with maximal evaporation residue cross sections of 6.619 and 4.123 fb at 219.9 and 223.9 MeV,respectively.

Antagonism effect of residual S triggers the dual-path mechanism for water oxidation

Transition metal chalcogenides(TMCs)are recognized as pre-catalysts,and their(oxy)hydroxides derived from electrochemical reconstruction are the active species in the water oxidation.However,understanding the role of the residual chalcogen in the reconstructed layer is lacking in detail,and the corresponding catalytic mechanism remains controversial.Here,taking Cu_(1-x)Co_(x)S as a platform,we explore the regulating effect and existence form of the residual S doped into the reconstructive layer for oxygen evolution reaction(OER),where a dual-path OER mechanism is proposed.First-principles calculations and operando~(18)O isotopic labeling experiments jointly reveal that the residual S in the reconstructive layer of Cu_(1-x)Co_(x)S can wisely balance the adsorbate evolution mechanism(AEM)and lattice oxygen oxidation mechanism(LOM)by activating lattice oxygen and optimizing the adsorption/desorption behaviors at metal active sites,rather than change the reaction mechanism from AEM to LOM.Following such a dual-path OER mechanism,Cu_(0.4)Co_(0.6)S-derived Cu_(0.4)Co_(0.6)OSH not only overcomes the restriction of linear scaling relationship in AEM,but also avoids the structural collapse caused by lattice oxygen migration in LOM,so as to greatly reduce the OER potential and improved stability.

Software Defect Prediction Method Based on Stable Learning

The purpose of software defect prediction is to identify defect-prone code modules to assist software quality assurance teams with the appropriate allocation of resources and labor.In previous software defect prediction studies,transfer learning was effective in solving the problem of inconsistent project data distribution.However,target projects often lack sufficient data,which affects the performance of the transfer learning model.In addition,the presence of uncorrelated features between projects can decrease the prediction accuracy of the transfer learning model.To address these problems,this article propose a software defect prediction method based on stable learning(SDP-SL)that combines code visualization techniques and residual networks.This method first transforms code files into code images using code visualization techniques and then constructs a defect prediction model based on these code images.During the model training process,target project data are not required as prior knowledge.Following the principles of stable learning,this paper dynamically adjusted the weights of source project samples to eliminate dependencies between features,thereby capturing the“invariance mechanism”within the data.This approach explores the genuine relationship between code defect features and labels,thereby enhancing defect prediction performance.To evaluate the performance of SDP-SL,this article conducted comparative experiments on 10 open-source projects in the PROMISE dataset.The experimental results demonstrated that in terms of the F-measure,the proposed SDP-SL method outperformed other within-project defect prediction methods by 2.11%-44.03%.In cross-project defect prediction,the SDP-SL method provided an improvement of 5.89%-25.46% in prediction performance compared to other cross-project defect prediction methods.Therefore,SDP-SL can effectively enhance within-and cross-project defect predictions.