Active Learning Strategies for Textual Dataset-Automatic Labelling

The Internet revolution has resulted in abundant data from various sources,including social media,traditional media,etcetera.Although the availability of data is no longer an issue,data labelling for exploiting it in supervised machine learning is still an expensive process and involves tedious human efforts.The overall purpose of this study is to propose a strategy to automatically label the unlabeled textual data with the support of active learning in combination with deep learning.More specifically,this study assesses the performance of different active learning strategies in automatic labelling of the textual dataset at sentence and document levels.To achieve this objective,different experiments have been performed on the publicly available dataset.In first set of experiments,we randomly choose a subset of instances from training dataset and train a deep neural network to assess performance on test set.In the second set of experiments,we replace the random selection with different active learning strategies to choose a subset of the training dataset to train the same model and reassess its performance on test set.The experimental results suggest that different active learning strategies yield performance improvement of 7% on document level datasets and 3%on sentence level datasets for auto labelling.

基于Yolov5的交通信号灯智能识别程序开发

交通信号检测是智能汽车识别交通环境的一项重要辅助技术,现有的算法能够解决单一交叉口环境下的信号检测问题,但需要在十字路口的复杂交通环境中提高算法的精度和干扰可靠性。文章以one-stage目标检测算法Yolov5的应用为研究基础,实现多场景下的交通信号灯自动检测与识别,使用Labeling进行图片标注,通过镜像、裁剪、反转、等运行增强数据集,不断地调参实验与迭代模型训练,目标检测精度达到80%。

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。

Fe-N-C core-shell catalysts with single low-spin Fe(Ⅱ)-N_(4)species for oxygen reduction reaction and high-performance proton exchange membrane fuel cells

Fe-N-doped carbon materials(Fe-N-C)are promising candidates for oxygen reduction reaction(ORR)relative to Pt-based catalysts in proton exchange membrane fuel cells(PEMFCs).However,the intrinsic contributions of Fe-N_(4)moiety with different chemical/spin states(e.g.D1,D2,D3)to ORR are unclear since various states coexist inevitably.In the present work,Fe-N-C core-shell nanocatalyst with single lowspin Fe(Ⅱ)-N_(4)species(D1)is synthesized and identified with ex-situ ultralow temperature Mossbauer spectroscopy(T=1.6 K)that could essentially differentiate various Fe-N_(4)states and invisible Fe-O species.By quantifying with CO-pulse chemisorption,site density and turnover frequency of Fe-N-C catalysts reach 2.4×10^(-9)site g^(-1)and 23 e site~(-1)s^(-1)during the ORR,respectively.Half-wave potential(0.915V_(RHE))of the Fe-N-C catalyst is more positive(approximately 54 mV)than that of Pt/C.Moreover,we observe that the performance of PEMFCs on Fe-N-C almost achieves the 2025 target of the US Department of Energy by demonstrating a current density of 1.037 A cm^(-2)combined with the peak power density of 0,685 W cm^(-2),suggesting the critical role of Fe(Ⅱ)-N_(4)site(D1).After 500 h of running,PEMFCs still deliver a power density of 1.26 W cm^(-2)at 1.0 bar H_(2)-O_(2),An unexpected rate-determining step is figured out by isotopic labelling experiment and theoretical calculation.This work not only offers valuable insights regarding the intrinsic contribution of Fe-N_(4)with a single spin state to alkaline/acidic ORR,but also provides great opportunities for developing high-performance stable PEMFCs.

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.

Erratum to:Regulation of different light conditions for efficient biomass production and protein accumulation of Spirulina platensis

In this article,the legend for Fig.3 f&g was inadvertently mislabeled.The figure below shows the wrong one.The figure should have appeared as shown below.

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.

Does Green Food Certification promote agri-food export quality?Evidence from China

The construction of a food certification system plays a vital role in upgrading export quality, which previous studies have largely overlooked. We match China's industry-level data of Green Food Certification with its HS6-digit export data of agri-food products to quantify the impact of Green Food Certification on export quality. We identify the significant and positive effect of Green Food Certification on export quality. The 2SLS estimation based on instrumental variables and a range of robustness checks confirm the validity and robustness of the benchmark conclusions. Further analysis discloses that Green Food Certification improves export quality by raising agricultural production efficiency and brand premiums. Heterogeneity analysis shows that the effect of Green Food Certification varies across regions, notably improving the quality of agri-food products exported to developed regions and regions with high levels of import supervision. Furthermore, among various product types, Green Food Certification significantly improves the export quality of primary products and products vulnerable to non-tariff measures. The above findings could guide the future development of agri-food quality certification systems, potentially leading to a transformation and promotion of the agri-food trade.

In situ visualization of the cellular uptake and sub-cellular distribution of mussel oligosaccharides

Unlike chemosynthetic drugs designed for specific molecular and disease targets,active small-molecule natural products typically have a wide range of bioactivities and multiple targets,necessitating extensive screening and development.To address this issue,we propose a strategy for the direct in situ microdynamic examination of potential drug candidates to rapidly identify their effects and mechanisms of action.As a proof-of-concept,we investigated the behavior of mussel oligosaccharide(MOS-1)by tracking the subcellular dynamics of fluorescently labeled MOS-1 in cultured cells.We recorded the entire dynamic process of the localization of fluorescein isothiocyanate(FITC)-MOS-1 to the lysosomes and visualized the distribution of the drug within the cell.Remarkably,lysosomes containing FITC-MOS-1 actively recruited lipid droplets,leading to fusion events and increased cellular lipid consumption.These drug behaviors confirmed MOS-1 is a candidate for the treatment of lipid-related diseases.Furthermore,in a high-fat HepG2 cell model and in high-fat diet-fed apolipoprotein E(ApoE)^(-/-)mice,MOS-1 significantly promoted triglyceride degradation,reduced lipid droplet accumulation,lowered serum triglyceride levels,and mitigated liver damage and steatosis.Overall,our work supports the prioritization of in situ visual monitoring of drug location and distribution in subcellular compartments during the drug development phase,as this methodology contributes to the rapid identification of drug indications.Collectively,this methodology is significant for the screening and development of selective small-molecule drugs,and is expected to expedite the identification of candidate molecules with medicinal effects.

Improved training framework in a neural network model for disruption prediction and its application on EXL-50

A neural network model with a classical annotation method has been used on the EXL-50tokamak to predict impending disruption.However,the results revealed issues of overfitting and overconfidence in predictions caused by inaccurate labeling.To mitigate these issues,an improved training framework has been proposed.In this approach,soft labels from previous training serve as teachers to supervise the further learning process;this has lead to a significant improvement in predictive model performance.Notably,this enhancement is primarily attributed to the coupling effect of the soft labels and correction mechanism.This improved training framework introduces an instance-specific label smoothing method,which reflects a more nuanced model assessment on the likelihood of a disruption.It presents a possible solution to effectively address the challenges associated with accurate labeling across different machines.

5-Bromo-2'-deoxyuridine labeling:historical perspectives,factors infiuencing the detection,toxicity,and its implications in the neurogenesis

The halopyrimidine 5-bromo-2′-deoxyuridine(BrdU)is an exogenous marker of DNA synthesis.Since the introduction of monoclonal antibodies against BrdU,an increasing number of methodologies have been used for the immunodetection of this synthesized bromine-tagged base analogue into replicating DNA.BrdU labeling is widely used for identifying neuron precursors and following their fate during the embryonic,perinatal,and adult neurogenesis in a variety of vertebrate species including birds,reptiles,and mammals.Due to BrdU toxicity,its incorporation into replicating DNA presents adverse consequences on the generation,survival,and settled patterns of cells.This may lead to false results and misinterpretation in the identification of proliferative neuroblasts.In this review,I will indicate the detrimental effects of this nucleoside during the development of the central nervous system,as well as the reliability of BrdU labeling to detect proliferating neuroblasts.Moreover,it will show factors influencing BrdU immunodetection and the contribution of this nucleoside to the study of prenatal,perinatal,and adult neurogenesis.Human adult neurogenesis will also be discussed.It is my hope that this review serves as a reference for those researchers who focused on detecting cells that are in the synthetic phase of the cell cycle.

Comparison of biliary protein spectrum in gallstone patients with obesity and those with normal body weight

Background: Obesity is a common public health issue and is currently deemed a disease. Research has shown that the risk of gallstones in individuals with obesity is elevated. This study aimed to explore the bile proteomics differences between cholelithiasis patients with obesity and normal body weight. Methods: Bile samples from 20 patients(10 with obesity and 10 with normal body weight) who underwent laparoscopic cholecystectomy at our center were subjected to tandem mass tag labeling(TMT) and liquid chromatography-tandem mass spectrometry(LC-MS/MS), followed by further bioinformatic analysis. Results: Among the differentially expressed proteins, 23 were upregulated and 67 were downregulated. Bioinformatic analysis indicated that these differentially expressed proteins were mainly involved in cell development, inflammatory responses, glycerolipid metabolic processes, and protein activation cascades. In addition, the activity of the peroxisome proliferator-activated receptor(PPAR, a subfamily of nuclear receptors) signaling pathway was decreased in the Kyoto Encyclopedia of Genes and Genomes(KEGG) enrichment analysis. Two downregulated proteins in the PPAR signaling pathway, APO A-Ⅰ and APO A-Ⅱ, were confirmed using enzyme-linked immunosorbent assay. Conclusions: The PPAR signaling pathway may play a crucial role in the development of cholelithiasis among patients with obesity. Furthermore, biliary proteomics profiling of gallstones patients with obesity is revealed, providing a reference for future research.

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.

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.

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.

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.

Carbon allocation in Picea jezoensis:Adaptation strategies of a non-treeline species at its upper elevation limit

Understanding the physiological adaptations of non-treeline trees to environmental stress is important to understand future shifts in species composition and distribution of current treeline ecotone.The aim of the present study was to elucidate the mechanisms of the formation of the upper elevation limit of non-treeline tree species,Picea jezoensis,and the carbon allocation strategies of the species on Changbai Mountain.We employed the^(13)C in situ pulse labeling technique to trace the distribution of photosynthetically assimilated carbon in Picea jezoensis at different elevational positions(tree species at its upper elevation limit(TSAUE,1,700 m a.s.l.)under treeline ecotone;tree species at a lower elevation position(TSALE,1,400 m a.s.l.).We analyzed^(13)C and the non-structural carbohydrate(NSC)concentrations in various tissues following labeling.Our findings revealed a significant shift in carbon allocation in TSAUE compared to TSALE.There was a pronounced increase inδ^(13)C allocation to belowground components(roots,soil,soil respiration)in TSAUE compared to TSALE.Furthermore,the C flow rate within the plant-soil-atmosphere system was faster,and the C residence time in the plant was shorter in TSAUE.The trends indicate enhanced C sink activity in belowground tissues in TSAUE,with newly assimilated C being preferentially directed there,suggesting a more conservative C allocation strategy by P.jezoensis at higher elevations under harsher environments.Such a strategy,prioritizing C storage in roots,likely aids in withstanding winter cold stress at the expense of aboveground growth during the growing season,leading to reduced growth of TSAUE compared to TSALE.The results of the present study shed light on the adaptive mechanisms governing the upper elevation limits of non-treeline trees,and enhances our understanding of how non-treeline species might respond to ongoing climate change.

Impaired implicit emotion regulation in patients with panic disorder:An event-related potential study on affect labeling

BACKGROUND Panic disorder(PD)involves emotion dysregulation,but its underlying mechanisms remain poorly understood.Previous research suggests that implicit emotion regulation may play a central role in PD-related emotion dysregulation and symptom maintenance.However,there is a lack of studies exploring the neural mechanisms of implicit emotion regulation in PD using neurophysiological indicators.AIM To study the neural mechanisms of implicit emotion regulation in PD with eventrelated potentials(ERP).METHODS A total of 25 PD patients and 20 healthy controls(HC)underwent clinical evaluations.The study utilized a case-control design with random sampling,selecting participants for the case group from March to December 2018.Participants performed an affect labeling task,using affect labeling as the experimental condition and gender labeling as the control condition.ERP and behavioral data were recorded to compare the late positive potential(LPP)within and between the groups.RESULTS Both PD and HC groups showed longer reaction times and decreased accuracy under the affect labeling.In the HC group,late LPP amplitudes exhibited a dynamic pattern of initial increase followed by decrease.Importantly,a significant group×condition interaction effect was observed.Simple effect analysis revealed a reduction in the differences of late LPP amplitudes between the affect labeling and gender labeling conditions in the PD group compared to the HC group.Furthermore,among PD patients under the affect labeling,the late LPP was negatively correlated with disease severity,symptom frequency,and intensity.CONCLUSION PD patients demonstrate abnormalities in implicit emotion regulation,hampering their ability to mobilize cognitive resources for downregulating negative emotions.The late LPP amplitude in response to affect labeling may serve as a potentially valuable clinical indicator of PD severity.

Cosmetic or Dietary Vegetable Oils Sampled in the Cameroonian Market May Not Expose Consumers to Lipid Oxidation Products Generating Oxidative Stress and Inflammation

Vegetable oils are a source of energy, essential fatty acids, antioxidants and fat-soluble vitamins useful for human health care and development. These oils also contribute to organoleptic quality of their products’ derivatives. However, their chemical and physical properties can be modified by the mode of their extraction, storage and distribution. These modifications might negatively affect the nutritional quality of the oils. The goals of this study were to: sample different vegetable oils for cosmetic or dietary use marketed in Cameroon, and verify purity and oxidation states of each kind of oil through determination of its acidity, iodine, peroxide, saponification, refractive indexes and the conformity of the labeling. The carotene content, the level of polar components and specific absorbance were also determined. As the result, six oils namely palm, palm kernel, coconut, black cumin, peanut and shea butter were collected. Apart from labeling, chemicals and physicals parameters analyzed were generally in accordance with the Cameroonian and Codex Alimentarius standard. This study suggests that vegetable oils sampled in the Cameroonian market may not expose consumers to lipid oxidation products generating pathological oxidative stress and inflammation. However, efforts in application of existing standard need to be done as far as labeling are concerned.