Labeling Data Research Articles

A dynamic collaborative adversarial domain adaptation network for unsupervised rotating machinery fault diagnosis

Acquiring sufficient fault data labels for new tasks in rotating machinery fault diagnosis is tricky. Accurately identifying faults in unlabeled scenarios is a critical and urgent practical need. Unsupervised domain adaptation (UDA) is a mainstream method to address this issue. However, most existing UDA models are static and struggle to dynamically adjust according to changes in the target task, resulting in limited diagnostic performance. To address this limitation, a dynamic collaborative adversarial domain adaptation network (DCADAN) is proposed for unsupervised rotating machinery fault diagnosis. Firstly, a multi-objective dynamic collaborative generator is designed to endow with dynamic characteristics for adjusting its own architecture, enhancing the capture capability of key domain adaptation features. Secondly, a dual-system dynamic collaborative adversarial mode is established to dynamically adjust the network training architecture, forming task-oriented refined diagnostic decision edges to steadily improve domain adaptation diagnostic capability. Finally, a multi-source domain dynamic collaborative loss is developed to match the force of multiple source domains, forming an efficient collaborative diagnostic pattern with dynamic adjustment across multi-source domains. Two case studies indicate that DCADAN demonstrates superior diagnostic performance when executing cross-domain diagnosis tasks without target labels.

Host plants of the weevil genus Heilipus Germar, 1824 (Coleoptera, Curculionidae, Molytinae, Molytini, Hylobiina)

Heilipus Germar, 1824 (Coleoptera, Curculionidae, Molytinae, Molytini, Hylobiina) is a largely understudied tropical lineage of weevils with 90 described species distributed from the southern United States to northern Argentina. Several of its species cause damage to avocado (Persea americana Mill.; Lauraceae Juss.) crops in the Americas. Apart from the species of economic importance, there is a paucity of information regarding the host plants of species of Heilipus. This study presents a comprehensive overview of the current knowledge on the habits and host plants of this group of weevils, based on a literature review and the examination of label data associated with entomological material in museums and scientific collections. The larval stages of 24 Heilipus species are borers of either seeds or trunks of 38 plant species belonging to 13 genera: 33 species (12 genera) from the family Lauraceae and five species (one genus) from the family Annonaceae Juss. Four new host plant records and the first identification of habits and host plants for H. albovenosus (Champion), H. empiricus (Pascoe), H. fassli (Voss) and H. mirus (Pascoe) are provided. The biology and host plants of the seed and trunk borers are discussed, as well as the oligophagous feeding behaviour exhibited by these two feeding guilds. Seed-boring Heilipus species constitute one of the primary groups of pre-dispersal seed predators of the family Lauraceae in the Americas. Furthermore, the high diversity of Heilipus and its host plants in the Brazilian Atlantic Forest suggests that this area may be a possible centre of origin for these weevils.

Large Language Model and Digital Twins Empowered Asynchronous Federated Learning for Secure Data Sharing in Intelligent Labeling

With the advancement of the large language model (LLM), the demand for data labeling services has increased dramatically. Big models are inseparable from high-quality, specialized scene data, from training to deploying application iterations to landing generation. However, how to achieve intelligent labeling consistency and accuracy and improve labeling efficiency in distributed data middleware scenarios is the main difficulty in enhancing the quality of labeled data at present. In this paper, we proposed an asynchronous federated learning optimization method based on the combination of LLM and digital twin technology. By analysising and comparing and with other existing asynchronous federated learning algorithms, the experimental results show that our proposed method outperforms other algorithms in terms of performance, such as model accuracy and running time. The experimental validation results show that our proposed method has good performance compared with other algorithms in the process of intelligent labeling both in terms of accuracy and running solves the consistency and accuracy problems of intelligent labeling in a distributed data center.

Spatially integrated cortico-subcortical tracing data for analyses of rodent brain topographical organization

The cerebral cortex extends axonal projections to several subcortical brain regions, including the striatum, thalamus, superior colliculus, and pontine nuclei. Experimental tract-tracing studies have shown that these subcortical projections are topographically organized, reflecting the spatial organization of sensory surfaces and body parts. Several public collections of mouse- and rat- brain tract-tracing data are available, with the Allen mouse brain connectivity atlas being most prominent. There, a large body of image data can be inspected, but it is difficult to combine data from different experiments and compare spatial distribution patterns. To enable co-visualization and comparison of topographical organization in mouse brain cortico-subcortical projections across experiments, we represent axonal labelling data as point data in a common 3D brain atlas space. We here present a collection of point-cloud data representing spatial distribution of corticostriatal, corticothalamic, corticotectal, and corticopontine projections in mice and exemplify how these spatially integrated point data can be used as references for experimental investigations of topographic organization in transgenic mice, and for cross-species comparison with corticopontine projections in rats.

Pseudo-Labeling and Time-Series Data Analysis Model for Device Status Diagnostics in Smart Agriculture

This study proposes an automated data-labeling model that combines a pseudo-labeling algorithm with waveform segmentation based on Long Short-Term Memory (LSTM) to effectively label time-series data in smart agriculture. This model aims to address the inefficiency of manual labeling for large-scale data generated by agricultural systems, enhancing the performance and scalability of predictive models. Our proposed method leverages key features of time-series data to automatically generate labels for new data, thereby improving model accuracy and streamlining data processing. By automating the labeling process, we reduce dependence on manual labeling, which is often labor-intensive and prone to errors in large datasets. This approach enables the efficient preparation of labeled data for applications such as anomaly detection, pattern recognition, and predictive modeling in smart agriculture. Experimental results demonstrate that the automated labeling model achieves 89% accuracy in agricultural environments and reduces data processing time by 30%. Future research will focus on extending the model’s applicability to diverse agricultural settings, enhancing generalization performance, and improving real-time processing capabilities, thereby advancing intelligent and sustainable smart agriculture systems.

Constructing a Classification Scheme - and its Consequences: A Field Study of Learning to Label Data for Computer Vision in a Hospital Intensive Care Unit

Research on data annotation for artificial intelligence (AI) has demonstrated that biases, power, and culture impact the ways that annotators apply labels to data and subsequently affect downstream AI systems. However, annotators can only apply labels that are available to them in the annotation classification scheme. Drawing on a 3-year ethnographic study of an R&D collaboration between medical and AI researchers, we argue that the construction of the classification schema itself -- decisions about what kinds of data can and cannot be collected, what activities can and cannot be detected in the data, what the possible annotation classes ought to be, and the rules by which an item ought to be classified into each class -- dramatically shape the annotation process, and through it, the AI. We draw on Bowker and Star's [9] classification theory to detail how the creation of a training data codebook for a computer vision algorithm in hospital intensive care units (ICUs) evolved from its original, clinically-driven goal of classifying complex clinical activities into a narrower goal of identifying physical objects and simpler activities in the ICU. This work reinforces how trade-offs and decisions made long before annotators begin labeling data are highly consequential to the resulting AI system.

The influence of alterations in the composition of intestinal microbiota on neurovascular coupling and cognitive dysfunction in individuals afflicted with CSVD

IntroductionAn expanding body of research has explored the crucial role of gut microbiota in cerebral small vessel disease (CSVD). The objective of this study is to investigate alterations in the gut microbiota structure among CSVD patients, to explore the correlation between differential taxonomic levels and the neurovascular coupling index as well as cognitive function and to elucidate the imaging and biomarkers of mild cognitive impairment (MCI) in CSVD. MethodsWe enrolled 104 patients with CSVD and 40 healthy controls (HC). Based on cognitive test scores, CSVD patients were categorized into a cognitively normal group (CSVD-NCI, n=61) and a mild cognitive impairment group (CSVD-MCI, n=43). Performing magnetic resonance imaging (MRI) scans, gut microbiota analysis, as well as clinical and neuropsychological assessments for all participants. Based on arterial spin labeling (ASL) and blood oxygen level-dependent (BOLD) imaging data, cerebral blood flow (CBF) and neural activity indices are computed. The coupling indices of CBF/mReHo, CBF/mfALFF, CBF/mALFF, and CBF/mDC are calculated to assess the whole-brain neurovascular coupling changes in patients with CSVD. ResultsSpecies annotation revealed differences in the composition at the phylum and genus levels among the HC, CSVD-NCI, and CSVD-MCI groups. Additionally, differential analysis using the Kruskal-Wallis test demonstrated specific dominant microbial communities in all three groups. The relative abundance of certain dominant microbial communities in CSVD patients exhibited correlations with neurovascular coupling and cognitive function. The combined assessment of Bacteroides genus and CBF/mDC proved effective in distinguishing between CSVD-NCI and CSVD-MCI, providing a novel non-invasive approach for the diagnosis of MCI in CSVD.

Cerebral blood flow and arterial transit time responses to exercise training in older adults

Brain vascular health worsens with age, as is made evident by resting grey matter cerebral blood flow (CBFGM) reductions and lengthening arterial transit time (ATTGM). Exercise training can improve aspects of brain health in older adults, yet its effects on CBFGM and ATTGM remain unclear. This randomised controlled trial assessed responses of CBFGM and ATTGM to a 26 week exercise intervention in 65 healthy older adults (control: n = 33, exercise: n = 32, aged 60–81 years), including whether changes in CBFGM or ATTGM were associated with changes in cognitive functions. Multiple-delay pseudo-continuous arterial spin labelling data were used to estimate resting global and regional CBFGM and ATTGM. Results showed no between-group differences in CBFGM or ATTGM following the intervention. However, exercise participants with the greatest cardiorespiratory gains (n = 17; ∆V̇O2peak >2 mL/kg/min) experienced global CBFGM reductions (-4.0 [-7.3, -0.8] mL/100 g/min). Cognitive functions did not change in either group and changes were not associated with changes in CBFGM or ATTGM. Our findings indicate that exercise training in older adults may induce global CBFGM reductions when high cardiorespiratory fitness gains are induced, but this does not appear to affect cognitive functions.

Fault detection research on novel transfer learning-based method for cross-condition, cross-system and cross-operation in public building HVAC sensors

Transfer learning (TL) has the inspiring potential for artificial intelligence in heating, ventilation and air conditioning (HVAC) system with insufficient data labels. However, traditional TL-based methods are limited when applied across different conditions, systems, and operations.Unfortunately, public building HVAC systems encounter challenges related to data acquisition and richness, making it difficult to obtain data from similar HVAC systems conditions, scenarios and operations. It proposes a novel TL-based method that combines energy and mass balance constraint equation (EBCe) to diagnose the sensor faults in HVAC systems across different systems, conditions and operations.Firstly, it utilizes laboratory data as the source domain data and constructes EBCe based on the common physical laws of HVAC system to reduce the data differences between laboratory and public buildings. Then, an laplacian kernel domain-adaptive neural network (LkDaNN) is proposed to generalize more efficiently feature differences between the source domain data and target domain data. Finally, experiment analyzes the non-fault and four control-sensors fault under both cross-operation and non-cross operation conditions. The experimental results demonstrate that the EBCe-LkDaNN method achieves satisfactory fault detection and diagnosis (FDD) performance.The overall FDD accuracy of porposed method can reach 90.72 % and 88.64 % under different cross-operation, respectively. Practical application of the EBCe-LkDaNN strategy for HVAC sensor FDD are discussed at last.

Multi-class Object Detection in Urban Scenes Based on Deep Learning

Abstract. The rapid development of urbanization presents challenges and requirements for multi-class object detection in urban scenes. Accurately identifying buildings, vehicles, and trees in urban scenes can optimize urban planning, traffic management, monitoring environmental conditions, and promote the development of smart cities. Traditional target detection methods perform poorly in complex urban environments, while deep learning technology achieves accurate target recognition and positioning by automatically extracting high-level semantic features. In this study, we chose to use the YOLOv5s algorithm for multi-class target detection in urban scenes. YOLOv5s is a lightweight deep learning model with small storage space and efficient detection speed. In this paper, the Potsdam area data published by ISPRS is used to make the label data of buildings, vehicles and trees. The YOLOv5s algorithm is used to iteratively train the model. The results show that the mAP value detected by the YOLOv5s model can reach 82.83%. The experimental results show that the algorithm shows higher accuracy than SSD and Faster R-CNN in tree detection. Although it has a slight decline in building and vehicle detection, considering the factors such as detection accuracy, speed, and model size, the YOLOv5s algorithm has a better recognition and detection effect for the detection of multi-class targets in urban scenes.

Domain Adaptive Urban Garbage Detection Based on Attention and Confidence Fusion

To overcome the challenges posed by limited garbage datasets and the laborious nature of data labeling in urban garbage object detection, we propose an innovative unsupervised domain adaptation approach to detecting garbage objects in urban aerial images. The proposed method leverages a detector, initially trained on source domain images, to generate pseudo-labels for target domain images. By employing an attention and confidence fusion strategy, images from both source and target domains can be seamlessly integrated, thereby enabling the detector to incrementally adapt to target domain scenarios while preserving its detection efficacy in the source domain. This approach mitigates the performance degradation caused by domain discrepancies, significantly enhancing the model’s adaptability. The proposed method was validated on a self-constructed urban garbage dataset. Experimental results demonstrate its superior performance over baseline models. Furthermore, we extended the proposed mixing method to other typical scenarios and conducted comprehensive experiments on four well-known public datasets: Cityscapes, KITTI, Sim10k, and Foggy Cityscapes. The result shows that the proposed method exhibits remarkable effectiveness and adaptability across diverse datasets.

Bias in medical AI: Implications for clinical decision-making.

Biases in medical artificial intelligence (AI) arise and compound throughout the AI lifecycle. These biases can have significant clinical consequences, especially in applications that involve clinical decision-making. Left unaddressed, biased medical AI can lead to substandard clinical decisions and the perpetuation and exacerbation of longstanding healthcare disparities. We discuss potential biases that can arise at different stages in the AI development pipeline and how they can affect AI algorithms and clinical decision-making. Bias can occur in data features and labels, model development and evaluation, deployment, and publication. Insufficient sample sizes for certain patient groups can result in suboptimal performance, algorithm underestimation, and clinically unmeaningful predictions. Missing patient findings can also produce biased model behavior, including capturable but nonrandomly missing data, such as diagnosis codes, and data that is not usually or not easily captured, such as social determinants of health. Expertly annotated labels used to train supervised learning models may reflect implicit cognitive biases or substandard care practices. Overreliance on performance metrics during model development may obscure bias and diminish a model's clinical utility. When applied to data outside the training cohort, model performance can deteriorate from previous validation and can do so differentially across subgroups. How end users interact with deployed solutions can introduce bias. Finally, where models are developed and published, and by whom, impacts the trajectories and priorities of future medical AI development. Solutions to mitigate bias must be implemented with care, which include the collection of large and diverse data sets, statistical debiasing methods, thorough model evaluation, emphasis on model interpretability, and standardized bias reporting and transparency requirements. Prior to real-world implementation in clinical settings, rigorous validation through clinical trials is critical to demonstrate unbiased application. Addressing biases across model development stages is crucial for ensuring all patients benefit equitably from the future of medical AI.

A shared multi-scale lightweight convolution generative network for few-shot multivariate time series forecasting

Time series forecasting is an important time series data mining technique. Among them, multivariate time series (MTS) forecasting has received extensive attention in many fields. However, many existing MTS forecasting models usually rely on a large amount of labeled data for model training, and data collection and labeling are difficult in real systems. The insufficient amount of data makes it difficult for the model to fully learn the intrinsic patterns and features of the data, which not only increases the prediction error, but also makes it hard to obtain satisfactory prediction results. To address this challenge, we propose a shared multi-scale lightweight convolution generative (SMLCG) network for few-shot multivariate time series forecasting by using samples generation strategy. The overall goal is to design a shared multi-scale feature generation prediction framework that generates data highly similar to the original sample and enriches the training sample to improve prediction accuracy. Specifically, the MTS is divided into different scales, and the multi-scale feature fusion module is utilized to capture and fuse the MTS information in different spatial dimensions to eliminate the heterogeneity among the data. Then, the key information in the multi-scale features is captured by a lightweight convolution generative network, and the feature weights are dynamically assigned to explore the change information. In addition, a spatio-temporal memory module is designed based on the parameter sharing strategy to capture the spatio-temporal dynamic relationship of sequences by learning the common knowledge in multi-scale features, thus improving the robustness and generalization ability. Through comprehensive experiments on four publicly available datasets and comparisons with other reported models, it is demonstrated that the SMLCG model can efficiently generate approximate samples in the few-shot case and provide excellent prediction results. The architecture of SMLCG serves as a valuable reference for practical solutions to address the few-shot problem in multivariate time series.

Investigation into Safety Regulation of Entertainment Venues Based on Big Data Label Analysis

The recreational escape rooms have recently emerged as a rapidly growing and widely embraced form of consumer entertainment. However, the industry’s expansion has brought forth certain challenges, notably the lack of authoritative oversight, which has led to issues such as piracy and theme infringement. To address these concerns, this study explores the management complexities of immersive entertainment venues from the perspective of responsive regulation. The study begins by abstracting a dataset of online cultural products related to entertainment venues into a complex network using specific measurement standards. A method employing the K-means clustering algorithm is then proposed to partition the associative structure of this complex network. The K-means clustering algorithm is particularly suitable for this task due to its efficiency in handling large-scale data, strong scalability, and ability to quickly and effectively group network nodes based on a defined objective function. Additionally, the algorithm allows for flexible adjustment of the number of clusters according to specific needs. Furthermore, the study enhances and tests the Practical Byzantine Fault Tolerance (PBFT) algorithm to validate its effectiveness and practicality. The findings reveal that when the distance criterion value is set at a=2, the improved PBFT algorithm exhibits exceptional performance. This discovery significantly enhances the security and control measures in immersive entertainment venues, enriching the theoretical framework related to administrative regulation and providing crucial theoretical resources for future legislative efforts. Finally, the study presents policy recommendations to strengthen the regulation of immersive entertainment venues. This study offers effective technical support for optimizing consumer market management measures and contributes to the development of new entertainment venues.

Unsupervised Domain-Adaptive Object Detection via Localization Regression Alignment.

Unsupervised domain-adaptive object detection uses labeled source domain data and unlabeled target domain data to alleviate the domain shift and reduce the dependence on the target domain data labels. For object detection, the features responsible for classification and localization are different. However, the existing methods basically only consider classification alignment, which is not conducive to cross-domain localization. To address this issue, in this article, we focus on the alignment of localization regression in domain-adaptive object detection and propose a novel localization regression alignment (LRA) method. The idea is that the domain-adaptive localization regression problem can be transformed into a general domain-adaptive classification problem first, and then adversarial learning is applied to the converted classification problem. Specifically, LRA first discretizes the continuous regression space, and the discrete regression intervals are treated as bins. Then, a novel binwise alignment (BA) strategy is proposed through adversarial learning. BA can further contribute to the overall cross-domain feature alignment for object detection. Extensive experiments are conducted on different detectors in various scenarios, and the state-of-the-art performance is achieved; these results demonstrate the effectiveness of our method. The code will be available at: https://github.com/zqpiao/LRA.

Diversifying training data does not improve generalizability of neural network models for PV identification

Data about behind-the-meter photovoltaics (PV) installations may be difficult to obtain for researchers. A number of investigators have considered deep learning as an attractive solution to this challenge, capable of directly identifying PV installations from aerial or satellite images. Deep learning models are well known to experience challenges when working with data from sources that they have never been exposed to. This study investigated whether generalizability can be improved by diversifying training data across available labeled data sources. We assessed the performance of models trained on all possible combinations of six different labeled datasets of aerial PV imagery, with a fixed number of total training images. Unfortunately, our results indicate that no combination of model training data achieved generalized performance that approaches models trained on data from a target data source. This implies that generalized ResNet models cannot be developed simply by modifying the configuration of the training data. Consequently, researchers should expect that some degree of data labeling is likely to be necessary when adapting these models to new applications, but our results do indicate that significant performance improvements are possible with only small (∼20%) introductions of target data. Future work may investigate alternative architectures, expanded training datasets, or ways to reduce the amount of labeled data necessary to adapt a model for a given application.

A general adaptive unsupervised feature selection with auto-weighting

Feature selection (FS) is essential in machine learning and data mining as it makes handling high-dimensional data more efficient and reliable. More attention has been paid to unsupervised feature selection (UFS) due to the extra resources required to obtain labels for data in the real world. Most of the existing embedded UFS utilize a sparse projection matrix for FS. However, this may introduce additional regularization terms, and it is difficult to control the sparsity of the projection matrix well. Moreover, such methods may seriously destroy the original feature structure in the embedding space. Instead, avoiding projecting the original data into the low-dimensional embedding space and identifying features directly from the raw features that perform well in the process of making the data show a distinct cluster structure is a feasible solution. Inspired by this, this paper proposes a model called A General Adaptive Unsupervised Feature Selection with Auto-weighting (GAWFS), which utilizes two techniques, non-negative matrix factorization, and adaptive graph learning, to simulate the process of dividing data into clusters, and identifies the features that are most discriminative in the clustering process by a feature weighting matrix Θ. Since the weighting matrix is sparse, it also plays the role of FS or a filter. Finally, experiments comparing GAWFS with several state-of-the-art UFS methods on synthetic datasets and real-world datasets are conducted, and the results demonstrate the superiority of the GAWFS.

Optimal Subsampling for Data Streams with Measurement Constrained Categorical Responses

High-velocity, large-scale data streams have become pervasive. Frequently, the associated labels for such data prove costly to measure and are not always available upfront. Consequently, the analysis of such data poses a significant challenge. In this article, we develop a method that addresses this challenge by employing an online subsampling procedure and a multinomial logistic model for efficient analysis of high-velocity, large-scale data streams. Our algorithm is designed to sequentially update parameter estimation based on the A-optimality criterion. Moreover, it significantly increases computational efficiency while imposing minimal storage requirements. Theoretical properties are rigorously established to quantify the asymptotic behavior of the estimator. The method’s efficacy is further demonstrated through comprehensive numerical studies on both simulated and real-world datasets.

Efficient ensemble uncertainty estimation in Gaussian processes regression

Abstract Reliable uncertainty measures are required when using data-based machine learning interatomic potentials (MLIPs) for atomistic simulations. In this work, we propose for sparse Gaussian process regression (GPR) type MLIPs a stochastic uncertainty measure akin to the query-by-committee approach often used in conjunction with neural network based MLIPs. The uncertainty measure is coined ‘label noise’ ensemble uncertainty as it emerges from adding noise to the energy labels in the training data. We find that this method of calculating an ensemble uncertainty is as well calibrated as the one obtained from the closed-form expression for the posterior variance when the sparse GPR is treated as a projected process. Comparing the two methods, our proposed ensemble uncertainty is, however, faster to evaluate than the closed-form expression. Finally, we demonstrate that the proposed uncertainty measure acts better to support a Bayesian search for optimal structure of Au20 clusters.

A fly in the ointment: the re-discovered holotype of ‘Trypeta’ cylindrica Walker, 1853 belongs to the genus Coelopacidia Enderlein (Diptera: Tephritidae), not Chyliza Fallén (Psilidae)

The ‘type’ of the fly species ‘Trypeta’ cylindrica Walker, 1853, from the William Saunders Collection, was misidentified and subsequently placed in the genus Chyliza Fallén (Psilidae). A specimen from the same collection with identical label data but belonging to Coelopacidia Enderlein (Tephritidae) is hereby identified as the correct holotype and the species should therefore be referred to as Coelopacidia cylindrica (Walker, 1853). Chyliza pallidipes Lamb, 1917 stat. rev. is taken out of synonymy and regarded as the valid name for the species previously treated as ‘Chyliza cylindrica’.