基于4D-Label-free技术慢性弥漫性轴索损伤大鼠海马组织的蛋白质组学分析

目的筛选慢性弥漫性轴索损伤(DAI)大鼠海马组织差异表达蛋白(DEPs),为探索慢性DAI潜在发病机制以及临床诊断、筛选药物治疗靶点、评估预后等提供实验依据。方法实验动物分为模型组(DAI组,n=20)和对照组(CON组,n=20),采用改良的Marmarou法建立SD大鼠DAI模型,模型建立3周后利用4D-Label-free技术检测慢性DAI组脑海马组织中的蛋白图谱变化,以DAI组/CON组表达量变化倍数(FC)>1.2或<0.83且P<0.05筛选DEPs,运用基因本体(GO)功能注释和京都基因与基因百科全书(KEGG)通路富集分析方法对筛选的DEPs进行生物信息学分析。结果共筛选出92个DEPs,上调52个,下调40个。GO分析结果显示,DEPs主要涉及去磷酸化,ATP合成耦合电子传递,过氧化氢介导的细胞程序性死亡的正向调节及神经递质受体内化等生物过程功能。KEGG通路分析结果提示,DEPs主要参与代谢途径、活性氧、神经变性途径-多种疾病、逆行内源性大麻素信号传导、谷胱甘肽代谢等信号通路。结论通过4D-Label-free技术筛选出了慢性DAI组大鼠海马组织中的DEPs。所筛选出的DEPs及其所富集的生物过程和信号通路为慢性DAI的深入研究提供依据。

基于label-free定量蛋白质组学方法筛选沉默CHAF1B基因后心肌细胞差异表达蛋白及调控网络分析

目的分析沉默染色质装配因子1亚基B(chromatin assembly factor 1 subunit B,CHAF1B)基因后心肌细胞中差异表达蛋白,预测CHAF1B基因调控网络,为寻找促进心肌细胞修复的潜在治疗靶点提供参考。方法采用转染和蛋白质印迹法筛选沉默CHAF1B基因的有效小干扰RNA(small interfering RNA,siRNA)。应用有效siRNA沉默人源心肌AC16细胞CHAF1B基因后,采用细胞活力检测方法检测细胞活力;提取总蛋白质进行定量、还原、烷基化和胰蛋白酶裂解成肽段,利用高效液相串联质谱法鉴定肽段;搜索UniProt蛋白库筛选差异表达的蛋白质进行基因本体(Gene Ontology,GO)富集分析、京都基因与基因组百科全书(Kyoto Encyclopedia of Genes and Genomes,KEGG)通路富集和蛋白质互作网络(protein-protein interaction networks,PPI)分析。结果siRNA有效沉默CHAF1B基因后,心肌细胞存活明显受到抑制;label-free定量蛋白质组学方法鉴定结果显示,共有69个差异表达蛋白质,其中50个表达显著上调(差异倍数≥2,P<0.05),19个表达显著下调(差异倍数≤0.5,P<0.05)。GO分析显示,差异表达蛋白质主要参与大分子复合亚基体、细胞组分生物合成和组装等生物学过程,分布在细胞质和囊泡等区域,发挥蛋白质结合等分子功能。KEGG通路富集和PPI分析显示,差异表达蛋白质参与的信号通路包括蛋白酶体、氨酰tRNA生物合成、胞吞、嘧啶代谢和氨基酸生物合成等10条信号途径;表达显著上调的蛋白质如蛋白酶体亚单位A2和B7、26 S蛋白酶体调节亚单位6B和10B参与蛋白酶体途径,丝氨酸、甘氨酸、谷氨酰胺和赖氨酸tRNA合成酶介导氨酰tRNA生物合成;表达显著下调的蛋白质包括骨架相关蛋白2/3复合体亚单位3和热休克70蛋白1样参与胞吞作用,核糖核苷-二磷酸还原酶大亚基介导嘧啶代谢等通路。实时荧光定量聚合酶链式反应结果证实,转染CHAF1B siRNA后心肌细胞中合成骨架相关蛋白2/3复合体亚单位3的基因ARPC3和氨酰tRNA生物合成关键基因QARS1的mRNA水平均显著降低。结论CHAF1B为心肌细胞存活的关键蛋白质,参与调控心肌细胞的胞吞和氨基酸生物合成等多种生物学过程,参考其调控网络可帮助寻找促进心肌细胞修复的干预环节。

近红外无创血糖浓度的Label Sensitivity算法和支持向量机回归

近红外光谱分析技术在生物医学工程领域具有广阔应用前景。无创且持续性地测量能实时监控人体血糖水平,给糖尿病患者带来极大便利性、提高生存质量、降低糖尿病并发症发生率具有很大的社会效益。无创血糖监测的想法提出较早,但仍然存在预测精度低、预测值与标签值相关性不高等难点,至今没有达到临床要求。近年来,光谱检测技术发展迅猛且机器学习技术在智能信息处理方面具有明显优势,两者结合可以有效提高人体无创血糖医学监测模型的精度和普适性。提出了一种标签敏感度算法(LS),并结合支持向量机方法建立了人体血糖含量预测模型。使用近红外光谱仪采集了4名志愿者食指处动态血液光谱数据(每名志愿者28组数据),并使用多元散射矫正(MSC)方法消除了部分光散射的影响。考虑血糖对不同波长光的吸收有差异,提出了基于血糖浓度标签差的特征波长挑选方法,并构建了标签敏感度支持向量机(LSSVR)预测模型。设计实验,对比该模型与偏最小二乘回归(PLSR)和区分度支持向量机(FSSVR)算法。结果表明,LS算法的最佳特征波长数为32,经特征波长选择后的LSSVR表现最佳,其均方误差降低至0.02 mmol·L^(-1),明显优于全谱段PLSR模型,血糖浓度的预测值与标签值的相关系数提升至99.8%,预测值全部位于可容许误差的克拉克网格A区内。LSSVR模型的优异表现为早日实现血糖的无创监测提供了新思路。

基于Label-free技术的非小细胞肺癌蛋白质差异研究

目的 基于非小细胞肺癌(non-small-cell lung cancer,NSCLC)及与其配对的非癌性邻近组织(non-cancerous adjacent tissues,NATs)的蛋白质组学分析,寻找NSCLC诊断相关蛋白标志物。方法 应用非标记定量蛋白组学(LFP)技术,以NSCLC患者配对的NATs为对照,对5例NSCLC患者进行癌组织蛋白质组学分析。以差异倍数>1.5(上调)或<0.67(下调)且P<0.05为标准筛选差异蛋白。应用String网站和R语言对差异蛋白进行基因本体论(gene ontology,GO)分析、京都基因和基因组百科全书(Kyoto Encyclopedia of Genes and Genomes,KEGG)分析,为进一步研究提供良好基础。结果 本研究发现差异蛋白共644个,其中339个蛋白表达上调,305个蛋白表达下调。PCA结果显示,差异蛋白可明显区分NSCLC与NATs。GO分析结果表明,差异蛋白大多以细胞外泌体的形式存在且主要富集于调节胞外分泌、胞外分泌、骨髓细胞激活参与免疫反应等的生物学过程以及钙粘着蛋白绑定、细胞外基质绑定等的分子功能。KEGG分析结果显示,差异蛋白主要富集在抗坏血酸和醛酸代谢、组氨酸代谢、蛋白质消化吸收、丙酮酸代谢等通路(P<0.05)。结论 NSCLC与NATs存在明显差异,可为发现NSCLC新型标志物提供线索。

基于Label-free技术的高州油茶铝胁迫蛋白质组学研究

【目的】南方地区拥有大面积的酸性红壤,导致土壤中铝元素多以离子的形式溶出,严重抑制油茶的生长及高产。研究采用Label-free技术探究高州油茶在铝胁迫下的蛋白质组学响应,为揭示高州油茶应答铝胁迫的分子响应机制奠定了理论基础。【方法】以高州油茶两年生实生苗为试验材料,测定不同浓度铝处理条件下高州油茶叶片部分代谢指标及抗氧化生理相关指标,同时比较对照组(CK)和4 mmol/L铝处理组(GZ4)差异蛋白质的表达。【结果】生理试验结果表明,不同浓度铝胁迫下油茶幼苗都会发生氧化胁迫导致细胞活性氧(ROS)积累,2 mmol/L铝浓度下油茶叶片通过增加渗透调节物质含量和增强多种抗氧化酶活性以清除细胞活性氧,使细胞免受氧化胁迫的损害;而4 mmol/L铝浓度下叶片丙二醛(MDA)含量和脯氨酸(PRO)含量明显升高,积累的活性氧超出了自身所能清除的范围,叶片可溶性糖含量和可溶性蛋白含量显著减少,抗氧化酶活性均有不同程度减弱,油茶正常的生理功能受到抑制。蛋白质组学数据表明,CK组和GZ4组共鉴定到4282个蛋白质,与CK组相比,GZ4处理组有207个蛋白质的表达丰度显著增加,129个蛋白质的表达丰度显著降低。差异表达蛋白质的通路富集和蛋白质互作网络分析结果表明,4 mmol/L铝胁迫下高州油茶主要通过提高谷胱甘肽代谢,增强细胞清除活性氧和自由基负离子的能力缓解铝胁迫造成的氧化损伤;4 mmol/L铝浓度下高州油茶蛋白质合成和光合作用受到明显抑制,抗氧化酶活性减弱可能与细胞供能能力不足有关。【结论】铝胁迫下高州油茶主要通过能量及碳水化合物代谢、氨基酸合成及代谢、生物碱合成、蛋白质加工、卟啉和叶绿素代谢等代谢途径抵抗铝毒。

Constraints on Characteristics and Distribution of Gas Hydrate and Free Gas Using Broad-Band Processing of Three-Dimensional Seismic Data

Gas hydrate drilling expeditions in the Pearl River Mouth Basin,South China Sea,have identified concentrated gas hydrates with variable thickness.Moreover,free gas and the coexistence of gas hydrate and free gas have been confirmed by logging,coring,and production tests in the foraminifera-rich silty sediments with complex bottom-simulating reflectors(BSRs).The broad-band processing is conducted on conventional three-dimensional(3D)seismic data to improve the image and detection accuracy of gas hydratebearing layers and delineate the saturation and thickness of gas hydrate-and free gas-bearing sediments.Several geophysical attributes extracted along the base of the gas hydrate stability zone are used to demonstrate the variable distribution and the controlling factors for the differential enrichment of gas hydrate.The inverted gas hydrate saturation at the production zone is over 40% with a thickness of 90 m,showing the interbedded distribution with different boundaries between gas hydrate-and free gas-bearing layers.However,the gas hydrate saturation value at the adjacent canyon is 70%,with 30-m-thick patches and linear features.The lithological and fault controls on gas hydrate and free gas distributions are demonstrated by tracing each gas hydrate-bearing layer.Moreover,the BSR depths based on broad-band reprocessed 3D seismic data not only exhibit variations due to small-scale topographic changes caused by seafloor sedimentation and erosion but also show the upward shift of BSR and the blocky distribution of the coexistence of gas hydrate and free gas in the Pearl River Mouth Basin.

Label Recovery and Trajectory Designable Network for Transfer Fault Diagnosis of Machines With Incorrect Annotation

The success of deep transfer learning in fault diagnosis is attributed to the collection of high-quality labeled data from the source domain.However,in engineering scenarios,achieving such high-quality label annotation is difficult and expensive.The incorrect label annotation produces two negative effects:1)the complex decision boundary of diagnosis models lowers the generalization performance on the target domain,and2)the distribution of target domain samples becomes misaligned with the false-labeled samples.To overcome these negative effects,this article proposes a solution called the label recovery and trajectory designable network(LRTDN).LRTDN consists of three parts.First,a residual network with dual classifiers is to learn features from cross-domain samples.Second,an annotation check module is constructed to generate a label anomaly indicator that could modify the abnormal labels of false-labeled samples in the source domain.With the training of relabeled samples,the complexity of diagnosis model is reduced via semi-supervised learning.Third,the adaptation trajectories are designed for sample distributions across domains.This ensures that the target domain samples are only adapted with the pure-labeled samples.The LRTDN is verified by two case studies,in which the diagnosis knowledge of bearings is transferred across different working conditions as well as different yet related machines.The results show that LRTDN offers a high diagnosis accuracy even in the presence of incorrect annotation.

GLOBAL SOLUTIONS TO 1D COMPRESSIBLE NAVIER-STOKES/ALLEN-CAHN SYSTEM WITH DENSITY-DEPENDENT VISCOSITY AND FREE-BOUNDARY

This paper is concerned with the Navier-Stokes/Allen-Cahn system,which is used to model the dynamics of immiscible two-phase flows.We consider a 1D free boundary problem and assume that the viscosity coefficient depends on the density in the form ofη(ρ)=ρ^(α).The existence of unique global H^(2m)-solutions(m∈N)to the free boundary problem is proven for when 0<α<1/4.Furthermore,we obtain the global C^(∞)-solutions if the initial data is smooth.

母体产前血清AFP、Freeβ-HCG、uE3检测对筛查胎儿染色体异常的临床价值

目的探讨产前母体血清甲胎蛋白(AFP)、游离β绒毛膜促性腺激素(Free-β-HCG)、雌三醇(uE3)检测对筛查胎儿染色体异常的临床价值。方法选取我院2021年9月—2023年3月100例高风险孕妇进行无创DNA检测,根据染色体状态分为阳性组、阴性组。对比2组孕12周时血清AFP、Freeβ-HCG、uE3及NT值水平,Logistic回归分析血清各指标对胎儿染色体异常的影响因素;ROC分析孕12周时血清各指标联合检测对胎儿染色体异常的预测价值。结果阳性组孕12周时血清AFP、uE3均低于阴性组、血清Freeβ-HCG及NT值均高于阴性组(P<0.05);分析认为孕12周时血清AFP、uE3为胎儿染色体异常的保护因素、Freeβ-HCG及NT值为胎儿染色体异常的危险因素(P<0.05);ROC分析孕12周时检测母体血清AFP、Freeβ-HCG、uE3水平对预测胎儿染色体异常的AUC分别为0.654、0.673、0.664,其联合检测对预测胎儿染色体异常的AUC为0.717。结论产前母体血清AFP、Freeβ-HCG、uE3联合检测在胎儿染色体异常的筛查中均具有较高的预测价值,3者联合检测的预测效能更高,可广泛应用于早期临床筛查中。

Free radicals trigger the closure of open pores in lignin-derived hard carbons toward improved sodium-storage capacity

The chemical activation of various precursors is effective for creating additional closed pores in hard carbons for sodium storage.However,the formation mechanism of closed pores under the influence of pore-forming agents is not well understood.Herein,an effective chemical activation followed by a high-temperature self-healing strategy is employed to generate interconnected closed pores in lignin-derived hard carbon(HCs).By systematic experimental design combined with electron paramagnetic res-onance spectroscopy,it can be found that the content of free radicals in the carbon matrix influences the closure of open pores at high temperatures.Excessively high activation temperature(>700 C)leads to a low free radical concentration,making it difficult to achieve self-healing of open pores at high tempera-tures.By activation at 700°C,a balance between pore making and self-healing is achieved in the final hard carbon.A large number of free radicals triggers rapid growth and aggregation of carbon microcrys-tals,blocking pre-formed open micropores and creating additional interconnected closed pores in as-obtained hard carbons.As a result,the optimized carbon anode(LK-700-1300)delivers a high reversible capacity of 330.8 mA h g^(-1) at 0.03 A g^(-1),which is an increase of 86 mA h g^(-1) compared to the pristine lignin-derived carbon anode(L-700-1300),and exhibits a good rate performance(202.1 mA h g^(-1) at 1 A g^(-1)).This work provides a universal and effective guidance for tuning closed pores of hard carbons from otherprecursors.

Metagenomic analysis revealing the metabolic role of microbial communities in the free amino acid biosynthesis of Monascus rice vinegar during fermentation

Free amino acid(FAA)is the important component of vinegar that infl uences quality perception and consumer acceptance.FAA is one of the major metabolites produced by microorganisms;however,the microbial metabolic network on FAA biosynthesis remains unclear.Through metagenomic analysis,this work aimed to elucidate the roles of microbes in FAA biosynthesis during Monascus rice vinegar fermentation.Taxonomic profiles from functional analyses showed 14 dominant genera with high contributions to the metabolism pathways.The metabolic network for FAA biosynthesis was then constructed,and the microbial distribution in different metabolic pathways was illuminated.The results revealed that 5 functional genera were closely involved in FAA biosynthesis.This study illuminated the metabolic roles of microorganisms in FAA biosynthesis and provided crucial insights into the functional attributes of microbiota in vinegar fermentation.

Learning about good nutrition with the 5-color front-of-package label"Nutri-Score":an experimental study

The Nutri-Score is a 5-color front-of-pack nutrition label designed to provide consumers with an easily understandable guideline to the healthiness of food products.The impact that the Nutri-Score may have on consumers'choices is unclear since different experimental paradigms have found vastly different effect sizes.In the present study,we have investigated how student participants change a hypothetical personal 1-daydietary plan after a learning phase during which they learn about the Nutri-Scores of the available food items.Participants were instructed to compose a healthy diet plan in order that the question of whether the NutriScore would improve their ability to compose a healthy dietary plan could be investigated,independent of the question of whether they would apply this knowledge in their ordinary lives.We found a substantial(Cohen's d=0.86)positive impact on nutritional quality(as measured by the Nutrient Profiling System score of the Food Standards Agency)and a medium-sized(Cohen's d=0.43)reduction of energy content.Energy content reduction was larger for participants who had initially composed plans with higher energy content.The results suggest that the Nutri-Score has the potential to guide consumers to healthier food choices.It remains unclear,however,whether this potential will be reflected in real-life dietary choices.

Local saliency consistency-based label inference for weakly supervised salient object detection using scribble annotations

Recently,weak supervision has received growing attention in the field of salient object detection due to the convenience of labelling.However,there is a large performance gap between weakly supervised and fully supervised salient object detectors because the scribble annotation can only provide very limited foreground/background information.Therefore,an intuitive idea is to infer annotations that cover more complete object and background regions for training.To this end,a label inference strategy is proposed based on the assumption that pixels with similar colours and close positions should have consistent labels.Specifically,k-means clustering algorithm was first performed on both colours and coordinates of original annotations,and then assigned the same labels to points having similar colours with colour cluster centres and near coordinate cluster centres.Next,the same annotations for pixels with similar colours within each kernel neighbourhood was set further.Extensive experiments on six benchmarks demonstrate that our method can significantly improve the performance and achieve the state-of-the-art results.

Molecular Mechanisms of Intracellular Delivery of Nanoparticles Monitored by an Enzyme‑Induced Proximity Labeling

Achieving increasingly finely targeted drug delivery to organs,tissues,cells,and even to intracellular biomacromolecules is one of the core goals of nanomedicines.As the delivery destination is refined to cellular and subcellular targets,it is essential to explore the delivery of nanomedicines at the molecular level.However,due to the lack of technical methods,the molecular mechanism of the intracellular delivery of nanomedicines remains unclear to date.Here,we develop an enzyme-induced proximity labeling technology in nanoparticles(nano-EPL)for the real-time monitoring of proteins that interact with intracellular nanomedicines.Poly(lactic-co-glycolic acid)nanoparticles coupled with horseradish peroxidase(HRP)were fabricated as a model(HRP(+)-PNPs)to evaluate the molecular mechanism of nano delivery in macrophages.By adding the labeling probe biotin-phenol and the catalytic substrate H_(2)O_(2)at different time points in cellular delivery,nano-EPL technology was validated for the real-time in situ labeling of proteins interacting with nanoparticles.Nano-EPL achieves the dynamic molecular profiling of 740 proteins to map the intracellular delivery of HRP(+)-PNPs in macrophages over time.Based on dynamic clustering analysis of these proteins,we further discovered that different organelles,including endosomes,lysosomes,the endoplasmic reticulum,and the Golgi apparatus,are involved in delivery with distinct participation timelines.More importantly,the engagement of these organelles differentially affects the drug delivery efficiency,reflecting the spatial–temporal heterogeneity of nano delivery in cells.In summary,these findings highlight a significant methodological advance toward understanding the molecular mechanisms involved in the intracellular delivery of nanomedicines.

Performance evaluation of seven multi-label classification methods on real-world patent and publication datasets

Purpose:Many science,technology and innovation(STI)resources are attached with several different labels.To assign automatically the resulting labels to an interested instance,many approaches with good performance on the benchmark datasets have been proposed for multi-label classification task in the literature.Furthermore,several open-source tools implementing these approaches have also been developed.However,the characteristics of real-world multi-label patent and publication datasets are not completely in line with those of benchmark ones.Therefore,the main purpose of this paper is to evaluate comprehensively seven multi-label classification methods on real-world datasets.Research limitations:Three real-world datasets differ in the following aspects:statement,data quality,and purposes.Additionally,open-source tools designed for multi-label classification also have intrinsic differences in their approaches for data processing and feature selection,which in turn impacts the performance of a multi-label classification approach.In the near future,we will enhance experimental precision and reinforce the validity of conclusions by employing more rigorous control over variables through introducing expanded parameter settings.Practical implications:The observed Macro F1 and Micro F1 scores on real-world datasets typically fall short of those achieved on benchmark datasets,underscoring the complexity of real-world multi-label classification tasks.Approaches leveraging deep learning techniques offer promising solutions by accommodating the hierarchical relationships and interdependencies among labels.With ongoing enhancements in deep learning algorithms and large-scale models,it is expected that the efficacy of multi-label classification tasks will be significantly improved,reaching a level of practical utility in the foreseeable future.Originality/value:(1)Seven multi-label classification methods are comprehensively compared on three real-world datasets.(2)The TextCNN and TextRCNN models perform better on small-scale datasets with more complex hierarchical structure of labels and more balanced document-label distribution.(3)The MLkNN method works better on the larger-scale dataset with more unbalanced document-label distribution.

CONVEXITY OF THE FREE BOUNDARY FOR AN AXISYMMETRIC INCOMPRESSIBLE IMPINGING JET

This paper is devoted to the study of the shape of the free boundary for a threedimensional axisymmetric incompressible impinging jet.To be more precise,we will show that the free boundary is convex to the fluid,provided that the uneven ground is concave to the fluid.

Convergence analysis for complementary-label learning with kernel ridge regression

Complementary-label learning(CLL)aims at finding a classifier via samples with complementary labels.Such data is considered to contain less information than ordinary-label samples.The transition matrix between the true label and the complementary label,and some loss functions have been developed to handle this problem.In this paper,we show that CLL can be transformed into ordinary classification under some mild conditions,which indicates that the complementary labels can supply enough information in most cases.As an example,an extensive misclassification error analysis was performed for the Kernel Ridge Regression(KRR)method applied to multiple complementary-label learning(MCLL),which demonstrates its superior performance compared to existing approaches.

A hierarchical enhanced data-driven battery pack capacity estimation framework for real-world operating conditions with fewer labeled data

Battery pack capacity estimation under real-world operating conditions is important for battery performance optimization and health management,contributing to the reliability and longevity of batterypowered systems.However,complex operating conditions,coupling cell-to-cell inconsistency,and limited labeled data pose great challenges to accurate and robust battery pack capacity estimation.To address these issues,this paper proposes a hierarchical data-driven framework aimed at enhancing the training of machine learning models with fewer labeled data.Unlike traditional data-driven methods that lack interpretability,the hierarchical data-driven framework unveils the“mechanism”of the black box inside the data-driven framework by splitting the final estimation target into cell-level and pack-level intermediate targets.A generalized feature matrix is devised without requiring all cell voltages,significantly reducing the computational cost and memory resources.The generated intermediate target labels and the corresponding features are hierarchically employed to enhance the training of two machine learning models,effectively alleviating the difficulty of learning the relationship from all features due to fewer labeled data and addressing the dilemma of requiring extensive labeled data for accurate estimation.Using only 10%of degradation data,the proposed framework outperforms the state-of-the-art battery pack capacity estimation methods,achieving mean absolute percentage errors of 0.608%,0.601%,and 1.128%for three battery packs whose degradation load profiles represent real-world operating conditions.Its high accuracy,adaptability,and robustness indicate the potential in different application scenarios,which is promising for reducing laborious and expensive aging experiments at the pack level and facilitating the development of battery technology.

Multi-Label Feature Selection Based on Improved Ant Colony Optimization Algorithm with Dynamic Redundancy and Label Dependence

The world produces vast quantities of high-dimensional multi-semantic data.However,extracting valuable information from such a large amount of high-dimensional and multi-label data is undoubtedly arduous and challenging.Feature selection aims to mitigate the adverse impacts of high dimensionality in multi-label data by eliminating redundant and irrelevant features.The ant colony optimization algorithm has demonstrated encouraging outcomes in multi-label feature selection,because of its simplicity,efficiency,and similarity to reinforcement learning.Nevertheless,existing methods do not consider crucial correlation information,such as dynamic redundancy and label correlation.To tackle these concerns,the paper proposes a multi-label feature selection technique based on ant colony optimization algorithm(MFACO),focusing on dynamic redundancy and label correlation.Initially,the dynamic redundancy is assessed between the selected feature subset and potential features.Meanwhile,the ant colony optimization algorithm extracts label correlation from the label set,which is then combined into the heuristic factor as label weights.Experimental results demonstrate that our proposed strategies can effectively enhance the optimal search ability of ant colony,outperforming the other algorithms involved in the paper.

A Robust Framework for Multimodal Sentiment Analysis with Noisy Labels Generated from Distributed Data Annotation

Multimodal sentiment analysis utilizes multimodal data such as text,facial expressions and voice to detect people’s attitudes.With the advent of distributed data collection and annotation,we can easily obtain and share such multimodal data.However,due to professional discrepancies among annotators and lax quality control,noisy labels might be introduced.Recent research suggests that deep neural networks(DNNs)will overfit noisy labels,leading to the poor performance of the DNNs.To address this challenging problem,we present a Multimodal Robust Meta Learning framework(MRML)for multimodal sentiment analysis to resist noisy labels and correlate distinct modalities simultaneously.Specifically,we propose a two-layer fusion net to deeply fuse different modalities and improve the quality of the multimodal data features for label correction and network training.Besides,a multiple meta-learner(label corrector)strategy is proposed to enhance the label correction approach and prevent models from overfitting to noisy labels.We conducted experiments on three popular multimodal datasets to verify the superiority of ourmethod by comparing it with four baselines.