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 consumer...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.展开更多
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 immuno...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.展开更多
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 annotatio...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.展开更多
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 sha...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.展开更多
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 superv...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.展开更多
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 emot...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.展开更多
Non-descriptive and convenient labels are uninformative and unfairly project blame onto patients.The language clinicians use in the Electronic Medical Record,research,and clinical settings shapes biases and subsequent...Non-descriptive and convenient labels are uninformative and unfairly project blame onto patients.The language clinicians use in the Electronic Medical Record,research,and clinical settings shapes biases and subsequent behaviors of all providers involved in the enterprise of transplantation.Terminology such as noncompliant and nonadherent serve as a reason for waitlist inactivation and limit access to life-saving transplantation.These labels fail to capture all the circum-stances surrounding a patient’s inability to follow their care regimen,trivialize social determinants of health variables,and bring unsubstantiated subjectivity into decisions regarding organ allocation.Furthermore,insufficient Medicare coverage has forced patients to ration or stop taking medication,leading to allograft failure and their subsequent diagnosis of noncompliant.We argue that perpetuating non-descriptive language adds little substantive information,in-creases subjectivity to the organ allocation process,and plays a major role in reduced access to transplantation.For patients with existing barriers to care,such as racial/ethnic minorities,these effects may be even more drastic.Transplant committees must ensure thorough documentation to correctly encapsulate the entirety of a patient’s position and give voice to an already vulnerable population.展开更多
In the field of medical images,pixel-level labels are time-consuming and expensive to acquire,while image-level labels are relatively easier to obtain.Therefore,it makes sense to learn more information(knowledge)from ...In the field of medical images,pixel-level labels are time-consuming and expensive to acquire,while image-level labels are relatively easier to obtain.Therefore,it makes sense to learn more information(knowledge)from a small number of hard-to-get pixel-level annotated images to apply to different tasks to maximize their usefulness and save time and training costs.In this paper,using Pixel-Level Labeled Images forMulti-Task Learning(PLDMLT),we focus on grading the severity of fundus images for Diabetic Retinopathy(DR).This is because,for the segmentation task,there is a finely labeled mask,while the severity grading task is without classification labels.To this end,we propose a two-stage multi-label learning weakly supervised algorithm,which generates initial classification pseudo labels in the first stage and visualizes heat maps at all levels of severity using Grad-Cam to further provide medical interpretability for the classification task.A multitask model framework with U-net as the baseline is proposed in the second stage.A label update network is designed to alleviate the gradient balance between the classification and segmentation tasks.Extensive experimental results show that our PLDMLTmethod significantly outperforms other stateof-the-art methods in DR segmentation on two public datasets,achieving up to 98.897%segmentation accuracy.In addition,our method achieves comparable competitiveness with single-task fully supervised learning in the DR severity grading task.展开更多
In the realm of Multi-Label Text Classification(MLTC),the dual challenges of extracting rich semantic features from text and discerning inter-label relationships have spurred innovative approaches.Many studies in sema...In the realm of Multi-Label Text Classification(MLTC),the dual challenges of extracting rich semantic features from text and discerning inter-label relationships have spurred innovative approaches.Many studies in semantic feature extraction have turned to external knowledge to augment the model’s grasp of textual content,often overlooking intrinsic textual cues such as label statistical features.In contrast,these endogenous insights naturally align with the classification task.In our paper,to complement this focus on intrinsic knowledge,we introduce a novel Gate-Attention mechanism.This mechanism adeptly integrates statistical features from the text itself into the semantic fabric,enhancing the model’s capacity to understand and represent the data.Additionally,to address the intricate task of mining label correlations,we propose a Dual-end enhancement mechanism.This mechanism effectively mitigates the challenges of information loss and erroneous transmission inherent in traditional long short term memory propagation.We conducted an extensive battery of experiments on the AAPD and RCV1-2 datasets.These experiments serve the dual purpose of confirming the efficacy of both the Gate-Attention mechanism and the Dual-end enhancement mechanism.Our final model unequivocally outperforms the baseline model,attesting to its robustness.These findings emphatically underscore the imperativeness of taking into account not just external knowledge but also the inherent intricacies of textual data when crafting potent MLTC models.展开更多
Background In this work,we focus on the label layout problem:specifying the positions of overlaid virtual annotations in Virtual/Augmented Reality scenarios.Methods Designing a layout of labels that does not violate d...Background In this work,we focus on the label layout problem:specifying the positions of overlaid virtual annotations in Virtual/Augmented Reality scenarios.Methods Designing a layout of labels that does not violate domain-specific design requirements,while at the same time satisfying aesthetic and functional principles of good design,can be a daunting task even for skilled visual designers.Presenting the annotations in 3D object space instead of projection space,allows for the preservation of spatial and depth cues.This results in stable layouts in dynamic environments,since the annotations are anchored in 3D space.Results In this paper we make two major contributions.First,we propose a technique for managing the layout and rendering of annotations in Virtual/Augmented Reality scenarios by manipulating the annotations directly in 3D space.For this,we make use of Artificial Potential Fields and use 3D geometric constraints to adapt them in 3D space.Second,we introduce PartLabeling:an open source platform in the form of a web application that acts as a much-needed generic framework allowing to easily add labeling algorithms and 3D models.This serves as a catalyst for researchers in this field to make their algorithms and implementations publicly available,as well as ensure research reproducibility.The PartLabeling framework relies on a dataset that we generate as a subset of the original PartNet dataset consisting of models suitable for the label management task.The dataset consists of 10003D models with part annotations.展开更多
Labeled data is widely used in various classification tasks.However,there is a huge challenge that labels are often added artificially.Wrong labels added by malicious users will affect the training effect of the model...Labeled data is widely used in various classification tasks.However,there is a huge challenge that labels are often added artificially.Wrong labels added by malicious users will affect the training effect of the model.The unreliability of labeled data has hindered the research.In order to solve the above problems,we propose a framework of Label Noise Filtering and Missing Label Supplement(LNFS).And we take location labels in Location-Based Social Networks(LBSN)as an example to implement our framework.For the problem of label noise filtering,we first use FastText to transform the restaurant's labels into vectors,and then based on the assumption that the label most similar to all other labels in the location is most representative.We use cosine similarity to judge and select the most representative label.For the problem of label missing,we use simple common word similarity to judge the similarity of users'comments,and then use the label of the similar restaurant to supplement the missing labels.To optimize the performance of the model,we introduce game theory into our model to simulate the game between the malicious users and the model to improve the reliability of the model.Finally,a case study is given to illustrate the effectiveness and reliability of LNFS.展开更多
Label assignment refers to determining positive/negative labels foreach sample to supervise the training process. Existing Siamese-based trackersprimarily use fixed label assignment strategies according to human prior...Label assignment refers to determining positive/negative labels foreach sample to supervise the training process. Existing Siamese-based trackersprimarily use fixed label assignment strategies according to human priorknowledge;thus, they can be sensitive to predefined hyperparameters and failto fit the spatial and scale variations of samples. In this study, we first developa novel dynamic label assignment (DLA) module to handle the diverse datadistributions and adaptively distinguish the foreground from the backgroundbased on the statistical characteristics of the target in visual object tracking.The core of DLA module is a two-step selection mechanism. The first stepselects candidate samples according to the Euclidean distance between trainingsamples and ground truth, and the second step selects positive/negativesamples based on the mean and standard deviation of candidate samples.The proposed approach is general-purpose and can be easily integrated intoanchor-based and anchor-free trackers for optimal sample-label matching.According to extensive experimental findings, Siamese-based trackers withDLA modules can refine target locations and outperformbaseline trackers onOTB100, VOT2019, UAV123 and LaSOT. Particularly, DLA-SiamRPN++improves SiamRPN++ by 1% AUC and DLA-SiamCAR improves Siam-CAR by 2.5% AUC on OTB100. Furthermore, hyper-parameters analysisexperiments show that DLA module hardly increases spatio-temporal complexity,the proposed approach maintains the same speed as the originaltracker without additional overhead.展开更多
Radio frequency fingerprinting(RFF)is a remarkable lightweight authentication scheme to support rapid and scalable identification in the internet of things(IoT)systems.Deep learning(DL)is a critical enabler of RFF ide...Radio frequency fingerprinting(RFF)is a remarkable lightweight authentication scheme to support rapid and scalable identification in the internet of things(IoT)systems.Deep learning(DL)is a critical enabler of RFF identification by leveraging the hardware-level features.However,traditional supervised learning methods require huge labeled training samples.Therefore,how to establish a highperformance supervised learning model with few labels under practical application is still challenging.To address this issue,we in this paper propose a novel RFF semi-supervised learning(RFFSSL)model which can obtain a better performance with few meta labels.Specifically,the proposed RFFSSL model is constituted by a teacher-student network,in which the student network learns from the pseudo label predicted by the teacher.Then,the output of the student model will be exploited to improve the performance of teacher among the labeled data.Furthermore,a comprehensive evaluation on the accuracy is conducted.We derive about 50 GB real long-term evolution(LTE)mobile phone’s raw signal datasets,which is used to evaluate various models.Experimental results demonstrate that the proposed RFFSSL scheme can achieve up to 97%experimental testing accuracy over a noisy environment only with 10%labeled samples when training samples equal to 2700.展开更多
Analyzing the structure and function of the brain's neural network is critical for identifying the working principles of the brain and the mechanisms of brain diseases.Recombinant rabies viral vectors allow for th...Analyzing the structure and function of the brain's neural network is critical for identifying the working principles of the brain and the mechanisms of brain diseases.Recombinant rabies viral vectors allow for the retrograde labeling of projection neurons and cell type-specific trans-monosynaptic tracing,making these vectors powerful candidates for the dissection of synaptic inputs.Although several attenuated rabies viral vectors have been developed,their application in studies of functional networks is hindered by the long preparation cycle and low yield of these vectors.To overcome these limitations,we developed an improved production system for the rapid rescue and preparation of a high-titer CVS-N2c-ΔG virus.Our results showed that the new CVS-N2c-ΔG-based toolkit performed remarkably:(1)N2cG-coated CVS-N2c-ΔG allowed for efficient retrograde access to projection neurons that were unaddressed by rAAV9-Retro,and the efficiency was six times higher than that of rAAV9-Retro;(2)the trans-monosynaptic efficiency of oG-mediated CVS-N2c-ΔG was 2–3 times higher than that of oG-mediated SAD-B19-ΔG;(3)CVS-N2c-ΔG could delivery modified genes for neural activity monitoring,and the time window during which this was maintained was 3 weeks;and(4)CVS-N2c-ΔG could express sufficient recombinases for efficient transgene recombination.These findings demonstrate that new CVS-N2c-ΔG-based toolkit may serve as a versatile tool for structural and functional studies of neural circuits.展开更多
File labeling techniques have a long history in analyzing the anthological trends in computational linguistics.The situation becomes worse in the case of files downloaded into systems from the Internet.Currently,most ...File labeling techniques have a long history in analyzing the anthological trends in computational linguistics.The situation becomes worse in the case of files downloaded into systems from the Internet.Currently,most users either have to change file names manually or leave a meaningless name of the files,which increases the time to search required files and results in redundancy and duplications of user files.Currently,no significant work is done on automated file labeling during the organization of heterogeneous user files.A few attempts have been made in topic modeling.However,one major drawback of current topic modeling approaches is better results.They rely on specific language types and domain similarity of the data.In this research,machine learning approaches have been employed to analyze and extract the information from heterogeneous corpus.A different file labeling technique has also been used to get the meaningful and`cohesive topic of the files.The results show that the proposed methodology can generate relevant and context-sensitive names for heterogeneous data files and provide additional insight into automated file labeling in operating systems.展开更多
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 ...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.展开更多
China has paid considerable attention to developing and implementing a carbon labeling system in response to increasing environmental issues such as global warming.This paper aims to provide a theoretical basis for fo...China has paid considerable attention to developing and implementing a carbon labeling system in response to increasing environmental issues such as global warming.This paper aims to provide a theoretical basis for formulating and implementing a carbon labeling system in China through a study of consumer acceptance behavior and its influencing factors.This paper constructed an extended model of consumers’acceptance behavior of carbon neutral labels based on the theories and methods of Unified Theory of Acceptance and Use of Technology(UTAUT)and analyzed the effects of five factors(carbon label cognition,performance expectancy,effort expectancy,social influence,and facilitating factors)on consumer carbon neutral label acceptance and adoption.The structural equation model analysis revealed that carbon label cognition,performance expectancy,social influence,and facilitating factors significantly,and positively impact consumers’acceptance of carbon neutral labels.Moreover,carbon label cognition,performance expectancy,and facilitating factors significantly,and positively affect consumers’carbon neutral label adoption behavior.Meanwhile,carbon label cognition,and effort expectancy have no significant impact on consumers’willingness to accept carbon neutral labels,which in turn significantly impacts consumers’carbon neutral label adoption behavior.According to the research findings,increasing the promotion of carbon labeling and improving the practical strategies and management recommendations for carbon label design are proposed.展开更多
Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks,which lies in the fact that examples closer to the decision boundaries are much more vulnerable t...Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks,which lies in the fact that examples closer to the decision boundaries are much more vulnerable to being attacked and should be given larger weights.The probability margin(PM)method is a promising approach to continuously and path-independently mea-suring such closeness between the example and decision boundary.However,the performance of PM is limited due to the fact that PM fails to effectively distinguish the examples having only one misclassified category and the ones with multiple misclassified categories,where the latter is closer to multi-classification decision boundaries and is supported to be more critical in our observation.To tackle this problem,this paper proposed an improved PM criterion,called confused-label-based PM(CL-PM),to measure the closeness mentioned above and reweight adversarial examples during training.Specifi-cally,a confused label(CL)is defined as the label whose prediction probability is greater than that of the ground truth label given a specific adversarial example.Instead of considering the discrepancy between the probability of the true label and the probability of the most misclassified label as the PM method does,we evaluate the closeness by accumulating the probability differences of all the CLs and ground truth label.CL-PM shares a negative correlation with data vulnerability:data with larger/smaller CL-PM is safer/riskier and should have a smaller/larger weight.Experiments demonstrated that CL-PM is more reliable in indicating the closeness regarding multiple misclassified categories,and reweighting adversarial training based on CL-PM outperformed state-of-the-art counterparts.展开更多
文摘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.
文摘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.
基金the National Key R&D Program of China(2022YFB3402100)the National Science Fund for Distinguished Young Scholars of China(52025056)+4 种基金the National Natural Science Foundation of China(52305129)the China Postdoctoral Science Foundation(2023M732789)the China Postdoctoral Innovative Talents Support Program(BX20230290)the Open Foundation of Hunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment(2022JXKF JJ01)the Fundamental Research Funds for Central Universities。
文摘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.
基金supported by STI 2030-Major Projects 2021ZD0200400National Natural Science Foundation of China(62276233 and 62072405)Key Research Project of Zhejiang Province(2023C01048).
文摘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.
文摘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.
基金Supported by The National Natural Science Foundation of China,No.81871080the Key R&D Program of Jining(Major Program),No.2023YXNS004+2 种基金the National Natural Science Foundation of China,No.81401486the Natural Science Foundation of Liaoning Province of China,No.20170540276the Medicine and Health Science Technology Development Program of Shandong Province,No.202003070713.
文摘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.
文摘Non-descriptive and convenient labels are uninformative and unfairly project blame onto patients.The language clinicians use in the Electronic Medical Record,research,and clinical settings shapes biases and subsequent behaviors of all providers involved in the enterprise of transplantation.Terminology such as noncompliant and nonadherent serve as a reason for waitlist inactivation and limit access to life-saving transplantation.These labels fail to capture all the circum-stances surrounding a patient’s inability to follow their care regimen,trivialize social determinants of health variables,and bring unsubstantiated subjectivity into decisions regarding organ allocation.Furthermore,insufficient Medicare coverage has forced patients to ration or stop taking medication,leading to allograft failure and their subsequent diagnosis of noncompliant.We argue that perpetuating non-descriptive language adds little substantive information,in-creases subjectivity to the organ allocation process,and plays a major role in reduced access to transplantation.For patients with existing barriers to care,such as racial/ethnic minorities,these effects may be even more drastic.Transplant committees must ensure thorough documentation to correctly encapsulate the entirety of a patient’s position and give voice to an already vulnerable population.
文摘In the field of medical images,pixel-level labels are time-consuming and expensive to acquire,while image-level labels are relatively easier to obtain.Therefore,it makes sense to learn more information(knowledge)from a small number of hard-to-get pixel-level annotated images to apply to different tasks to maximize their usefulness and save time and training costs.In this paper,using Pixel-Level Labeled Images forMulti-Task Learning(PLDMLT),we focus on grading the severity of fundus images for Diabetic Retinopathy(DR).This is because,for the segmentation task,there is a finely labeled mask,while the severity grading task is without classification labels.To this end,we propose a two-stage multi-label learning weakly supervised algorithm,which generates initial classification pseudo labels in the first stage and visualizes heat maps at all levels of severity using Grad-Cam to further provide medical interpretability for the classification task.A multitask model framework with U-net as the baseline is proposed in the second stage.A label update network is designed to alleviate the gradient balance between the classification and segmentation tasks.Extensive experimental results show that our PLDMLTmethod significantly outperforms other stateof-the-art methods in DR segmentation on two public datasets,achieving up to 98.897%segmentation accuracy.In addition,our method achieves comparable competitiveness with single-task fully supervised learning in the DR severity grading task.
基金supported by National Natural Science Foundation of China(NSFC)(Grant Nos.62162022,62162024)the Key Research and Development Program of Hainan Province(Grant Nos.ZDYF2020040,ZDYF2021GXJS003)+2 种基金the Major Science and Technology Project of Hainan Province(Grant No.ZDKJ2020012)Hainan Provincial Natural Science Foundation of China(Grant Nos.620MS021,621QN211)Science and Technology Development Center of the Ministry of Education Industry-University-Research Innovation Fund(2021JQR017).
文摘In the realm of Multi-Label Text Classification(MLTC),the dual challenges of extracting rich semantic features from text and discerning inter-label relationships have spurred innovative approaches.Many studies in semantic feature extraction have turned to external knowledge to augment the model’s grasp of textual content,often overlooking intrinsic textual cues such as label statistical features.In contrast,these endogenous insights naturally align with the classification task.In our paper,to complement this focus on intrinsic knowledge,we introduce a novel Gate-Attention mechanism.This mechanism adeptly integrates statistical features from the text itself into the semantic fabric,enhancing the model’s capacity to understand and represent the data.Additionally,to address the intricate task of mining label correlations,we propose a Dual-end enhancement mechanism.This mechanism effectively mitigates the challenges of information loss and erroneous transmission inherent in traditional long short term memory propagation.We conducted an extensive battery of experiments on the AAPD and RCV1-2 datasets.These experiments serve the dual purpose of confirming the efficacy of both the Gate-Attention mechanism and the Dual-end enhancement mechanism.Our final model unequivocally outperforms the baseline model,attesting to its robustness.These findings emphatically underscore the imperativeness of taking into account not just external knowledge but also the inherent intricacies of textual data when crafting potent MLTC models.
文摘Background In this work,we focus on the label layout problem:specifying the positions of overlaid virtual annotations in Virtual/Augmented Reality scenarios.Methods Designing a layout of labels that does not violate domain-specific design requirements,while at the same time satisfying aesthetic and functional principles of good design,can be a daunting task even for skilled visual designers.Presenting the annotations in 3D object space instead of projection space,allows for the preservation of spatial and depth cues.This results in stable layouts in dynamic environments,since the annotations are anchored in 3D space.Results In this paper we make two major contributions.First,we propose a technique for managing the layout and rendering of annotations in Virtual/Augmented Reality scenarios by manipulating the annotations directly in 3D space.For this,we make use of Artificial Potential Fields and use 3D geometric constraints to adapt them in 3D space.Second,we introduce PartLabeling:an open source platform in the form of a web application that acts as a much-needed generic framework allowing to easily add labeling algorithms and 3D models.This serves as a catalyst for researchers in this field to make their algorithms and implementations publicly available,as well as ensure research reproducibility.The PartLabeling framework relies on a dataset that we generate as a subset of the original PartNet dataset consisting of models suitable for the label management task.The dataset consists of 10003D models with part annotations.
基金National Natural Science Foundation of China(No.10671074 and No.60673048)Natural Science Foundation of Education Ministry of Anhui Province(No.KJ2007B124 and No.2006KJ256B)
基金supported by the National Natural Science Foundation of China(No.61872219)the Natural Science Foundation of Shandong Province(ZR2019MF001).
文摘Labeled data is widely used in various classification tasks.However,there is a huge challenge that labels are often added artificially.Wrong labels added by malicious users will affect the training effect of the model.The unreliability of labeled data has hindered the research.In order to solve the above problems,we propose a framework of Label Noise Filtering and Missing Label Supplement(LNFS).And we take location labels in Location-Based Social Networks(LBSN)as an example to implement our framework.For the problem of label noise filtering,we first use FastText to transform the restaurant's labels into vectors,and then based on the assumption that the label most similar to all other labels in the location is most representative.We use cosine similarity to judge and select the most representative label.For the problem of label missing,we use simple common word similarity to judge the similarity of users'comments,and then use the label of the similar restaurant to supplement the missing labels.To optimize the performance of the model,we introduce game theory into our model to simulate the game between the malicious users and the model to improve the reliability of the model.Finally,a case study is given to illustrate the effectiveness and reliability of LNFS.
基金support of the National Natural Science Foundation of China (Grant No.52127809,author Z.W,http://www.nsfc.gov.cn/No.51625501,author Z.W,http://www.nsfc.gov.cn/)is greatly appreciated.
文摘Label assignment refers to determining positive/negative labels foreach sample to supervise the training process. Existing Siamese-based trackersprimarily use fixed label assignment strategies according to human priorknowledge;thus, they can be sensitive to predefined hyperparameters and failto fit the spatial and scale variations of samples. In this study, we first developa novel dynamic label assignment (DLA) module to handle the diverse datadistributions and adaptively distinguish the foreground from the backgroundbased on the statistical characteristics of the target in visual object tracking.The core of DLA module is a two-step selection mechanism. The first stepselects candidate samples according to the Euclidean distance between trainingsamples and ground truth, and the second step selects positive/negativesamples based on the mean and standard deviation of candidate samples.The proposed approach is general-purpose and can be easily integrated intoanchor-based and anchor-free trackers for optimal sample-label matching.According to extensive experimental findings, Siamese-based trackers withDLA modules can refine target locations and outperformbaseline trackers onOTB100, VOT2019, UAV123 and LaSOT. Particularly, DLA-SiamRPN++improves SiamRPN++ by 1% AUC and DLA-SiamCAR improves Siam-CAR by 2.5% AUC on OTB100. Furthermore, hyper-parameters analysisexperiments show that DLA module hardly increases spatio-temporal complexity,the proposed approach maintains the same speed as the originaltracker without additional overhead.
基金supported by Innovation Talents Promotion Program of Shaanxi Province,China(No.2021TD08)。
文摘Radio frequency fingerprinting(RFF)is a remarkable lightweight authentication scheme to support rapid and scalable identification in the internet of things(IoT)systems.Deep learning(DL)is a critical enabler of RFF identification by leveraging the hardware-level features.However,traditional supervised learning methods require huge labeled training samples.Therefore,how to establish a highperformance supervised learning model with few labels under practical application is still challenging.To address this issue,we in this paper propose a novel RFF semi-supervised learning(RFFSSL)model which can obtain a better performance with few meta labels.Specifically,the proposed RFFSSL model is constituted by a teacher-student network,in which the student network learns from the pseudo label predicted by the teacher.Then,the output of the student model will be exploited to improve the performance of teacher among the labeled data.Furthermore,a comprehensive evaluation on the accuracy is conducted.We derive about 50 GB real long-term evolution(LTE)mobile phone’s raw signal datasets,which is used to evaluate various models.Experimental results demonstrate that the proposed RFFSSL scheme can achieve up to 97%experimental testing accuracy over a noisy environment only with 10%labeled samples when training samples equal to 2700.
基金supported by the National Natural Science Foundation of China,Nos.32100899(to KZL),31830035(to FQX),31771156(to FQX),21921004(to FQX)the National Science and Technology Innovation 2030,No.2021ZD0201003(to FQX)+2 种基金the Key-Area Research and Development Program of Guangdong Province,No.2018B030331001(to FQX)the Strategic Priority Research Program of the Chinese Academy of Sciences,No.XDB32030200(to FQX)the Shenzhen Key Laboratory of Viral Vectors for Biomedicine,No.ZDSYS20200811142401005(to FQX)。
文摘Analyzing the structure and function of the brain's neural network is critical for identifying the working principles of the brain and the mechanisms of brain diseases.Recombinant rabies viral vectors allow for the retrograde labeling of projection neurons and cell type-specific trans-monosynaptic tracing,making these vectors powerful candidates for the dissection of synaptic inputs.Although several attenuated rabies viral vectors have been developed,their application in studies of functional networks is hindered by the long preparation cycle and low yield of these vectors.To overcome these limitations,we developed an improved production system for the rapid rescue and preparation of a high-titer CVS-N2c-ΔG virus.Our results showed that the new CVS-N2c-ΔG-based toolkit performed remarkably:(1)N2cG-coated CVS-N2c-ΔG allowed for efficient retrograde access to projection neurons that were unaddressed by rAAV9-Retro,and the efficiency was six times higher than that of rAAV9-Retro;(2)the trans-monosynaptic efficiency of oG-mediated CVS-N2c-ΔG was 2–3 times higher than that of oG-mediated SAD-B19-ΔG;(3)CVS-N2c-ΔG could delivery modified genes for neural activity monitoring,and the time window during which this was maintained was 3 weeks;and(4)CVS-N2c-ΔG could express sufficient recombinases for efficient transgene recombination.These findings demonstrate that new CVS-N2c-ΔG-based toolkit may serve as a versatile tool for structural and functional studies of neural circuits.
文摘File labeling techniques have a long history in analyzing the anthological trends in computational linguistics.The situation becomes worse in the case of files downloaded into systems from the Internet.Currently,most users either have to change file names manually or leave a meaningless name of the files,which increases the time to search required files and results in redundancy and duplications of user files.Currently,no significant work is done on automated file labeling during the organization of heterogeneous user files.A few attempts have been made in topic modeling.However,one major drawback of current topic modeling approaches is better results.They rely on specific language types and domain similarity of the data.In this research,machine learning approaches have been employed to analyze and extract the information from heterogeneous corpus.A different file labeling technique has also been used to get the meaningful and`cohesive topic of the files.The results show that the proposed methodology can generate relevant and context-sensitive names for heterogeneous data files and provide additional insight into automated file labeling in operating systems.
基金the Deanship of Scientific Research at Shaqra University for supporting this work.
文摘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.
基金supported by the National Social Science Foundation of China[Grant number.17BXW104]the Innorative School Project in Higher Education of Guangdong,China[Grant number.2016WZDXM025].
文摘China has paid considerable attention to developing and implementing a carbon labeling system in response to increasing environmental issues such as global warming.This paper aims to provide a theoretical basis for formulating and implementing a carbon labeling system in China through a study of consumer acceptance behavior and its influencing factors.This paper constructed an extended model of consumers’acceptance behavior of carbon neutral labels based on the theories and methods of Unified Theory of Acceptance and Use of Technology(UTAUT)and analyzed the effects of five factors(carbon label cognition,performance expectancy,effort expectancy,social influence,and facilitating factors)on consumer carbon neutral label acceptance and adoption.The structural equation model analysis revealed that carbon label cognition,performance expectancy,social influence,and facilitating factors significantly,and positively impact consumers’acceptance of carbon neutral labels.Moreover,carbon label cognition,performance expectancy,and facilitating factors significantly,and positively affect consumers’carbon neutral label adoption behavior.Meanwhile,carbon label cognition,and effort expectancy have no significant impact on consumers’willingness to accept carbon neutral labels,which in turn significantly impacts consumers’carbon neutral label adoption behavior.According to the research findings,increasing the promotion of carbon labeling and improving the practical strategies and management recommendations for carbon label design are proposed.
基金supported by the National Natural Science Foundation of China (No.62072127,No.62002076,No.61906049)Natural Science Foundation of Guangdong Province (No.2023A1515011774,No.2020A1515010423)+3 种基金Project 6142111180404 supported by CNKLSTISS,Science and Technology Program of Guangzhou,China (No.202002030131)Guangdong basic and applied basic research fund joint fund Youth Fund (No.2019A1515110213)Open Fund Project of Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University) (No.MJUKF-IPIC202101)Scientific research project for Guangzhou University (No.RP2022003).
文摘Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks,which lies in the fact that examples closer to the decision boundaries are much more vulnerable to being attacked and should be given larger weights.The probability margin(PM)method is a promising approach to continuously and path-independently mea-suring such closeness between the example and decision boundary.However,the performance of PM is limited due to the fact that PM fails to effectively distinguish the examples having only one misclassified category and the ones with multiple misclassified categories,where the latter is closer to multi-classification decision boundaries and is supported to be more critical in our observation.To tackle this problem,this paper proposed an improved PM criterion,called confused-label-based PM(CL-PM),to measure the closeness mentioned above and reweight adversarial examples during training.Specifi-cally,a confused label(CL)is defined as the label whose prediction probability is greater than that of the ground truth label given a specific adversarial example.Instead of considering the discrepancy between the probability of the true label and the probability of the most misclassified label as the PM method does,we evaluate the closeness by accumulating the probability differences of all the CLs and ground truth label.CL-PM shares a negative correlation with data vulnerability:data with larger/smaller CL-PM is safer/riskier and should have a smaller/larger weight.Experiments demonstrated that CL-PM is more reliable in indicating the closeness regarding multiple misclassified categories,and reweighting adversarial training based on CL-PM outperformed state-of-the-art counterparts.
