Existing Labeling Methods Research Articles

Labeling methods for partially ordered paths

The landscape of applications and subroutines relying on shortest path computations continues to grow steadily. This growth is driven by the undeniable success of shortest path algorithms in theory and practice. It also introduces new challenges as the models and assessing the optimality of paths become more complicated. Hence, multiple recent publications in the field adapt existing labeling methods in an ad hoc fashion to their specific problem variant without considering the underlying general structure: they always deal with multi-criteria scenarios, and those criteria define different partial orders on the paths. In this paper, we introduce the partial order shortest path problem (POSP), a generalization of the multi-objective shortest path problem (MOSP) and in turn also of the classical shortest path problem. POSP captures the particular structure of many shortest path applications as special cases. In this generality, we study optimality conditions or the lack of them, depending on the objective functions’ properties. Our final contribution is a big lookup table summarizing our findings and providing the reader with an easy way to choose among the most recent multi-criteria shortest path algorithms depending on their problems’ weight structure. Examples range from time-dependent shortest path bottleneck path problems to the electric vehicle shortest path problem with recharging and complex financial weight functions studied in the public transportation community. Our results hold for general digraphs and, therefore, surpass previous generalizations that were limited to acyclic graphs.

감정 어휘 사전을 이용한 문학 감정분류

Recently, emotion analysis technology has been developed to classify emotions felt in texts such as sentences and documents, and it is being used in a variety of research, including literature. Because emotions are an important foundation for understanding literature, it is important to apply emotion analysis technology in literary research, and efforts are needed to improve problems that arise during the emotion analysis process for the development of technology. This study explains the problems that arise from existing labeling methods when constructing learning data, and introduces ‘emotion lexicon-based emotion labeling’ to improve these problems. To prove the effectiveness of emotion lexicon-based labeling, we constructed two learning data with different emotion labeling methods, entered them into a emotion analysis model, and compared the results. As a result, the accuracy of the model using emotion lexicon-based labeling was 91.95%, showing approximately 20% higher performance than the model using existing labeling. In addition, as a result of going beyond quantitative evaluation and directly checking the analysis results by inputting literary passages from the CSAT into the model, the model using emotion lexicon-based labeling showed better predictive power.

Integration of harvester trajectory and satellite imagery for large-scale winter wheat mapping using deep positive and unlabeled learning

Limited accurate ground truth labels are the primary constraint for data-driven modeling analysis of large-scale crop mapping. Existing labeling methods largely rely on field surveys, visual interpretation, and historical ground information. These labor-intensive approaches are often limited by spatiotemporal heterogeneity of crop distribution and encounter the challenge of gathering extensive crop labels. The massive operating trajectories of agricultural machinery contain precise location information of the crop fields, providing a new source for accurate crop labels at a large spatial scale. This study develops a large-scale crop mapping workflow through widespread harvester trajectory and 10 m Sentinel-2 imagery. The trajectory-based automatic labeling method is developed to generate 287,533 winter wheat labels by jointly using harvester coordinates and satellite images. These generated one-class ground labels are further used to develop positive and unlabeled learning based deep learning models for winter wheat mapping. The Positive and Unlabeled Learning-based Convolutional Neural Network (PUL-CNN) outperforms the other four one-class based classifiers with an F1 score of 94.4 % at 12 study sites. The estimated county-level winter wheat acreage agrees well with census data with R2 of 0.86 in the overall study region. The interpretation analysis based on the Shapley Additive Explanation method shows the heading and greening stages are the critical periods for wheat mapping, aligning well with the separability in Normalized Difference Vegetation Index (NDVI) curves. The results of winter wheat mapping demonstrate the integration of harvester trajectory and remote sensing data facilitates large-scale winter wheat mapping. To the best of our knowledge, this is the first study that fuses operating trajectories of agricultural machinery and satellite images for large-scale crop mapping based on the deep positive and unlabeled learning approach. This study could be possibly applied for better understanding the land cover and land use changes.

Assembly Characterization of Human Equilibrium Nucleoside Transporter 1 (hENT1) by Inhibitor Probe-Based dSTORM Imaging.

Nucleoside transporters (NTs) play an important role in the metabolism of nucleoside substances and the efficacy of nucleoside drugs. Its spatial information related to biofunctions at the single-molecule level remains unclear, owing to the limitation of the existing labeling methods and traditional imaging methods. Therefore, we synthesize the inhibitor-based fluorescent probe SAENTA-Cy5 and apply direct stochastic optical reconstruction microscopy (dSTORM) to conduct refined observation of human equilibrative nucleoside transporter 1 (hENT1), the most important and famous member of NTs. We first demonstrate the labeling specificity and superiority of SAENTA-Cy5 to the antibody probe. Then, we found different assembly patterns of hENT1 on the apical and basal membranes, which are further investigated to be caused by varying associations of membrane carbohydrates, membrane classical functional domains (lipid rafts), and associated membrane proteins (EpCAM). Our work provides an efficient method for labeling hENT1, which contributes to realize fine observation of NTs. The findings on the assembly features and potential assembly mechanism of hENT1 promote a better understanding of its biofunction, which facilitates further investigations on how NTs work in the metabolism of nucleoside and nucleoside analogues.

A Labeling Method for Financial Time Series Prediction Based on Trends.

Time series prediction has been widely applied to the finance industry in applications such as stock market price and commodity price forecasting. Machine learning methods have been widely used in financial time series prediction in recent years. How to label financial time series data to determine the prediction accuracy of machine learning models and subsequently determine final investment returns is a hot topic. Existing labeling methods of financial time series mainly label data by comparing the current data with those of a short time period in the future. However, financial time series data are typically non-linear with obvious short-term randomness. Therefore, these labeling methods have not captured the continuous trend features of financial time series data, leading to a difference between their labeling results and real market trends. In this paper, a new labeling method called “continuous trend labeling” is proposed to address the above problem. In the feature preprocessing stage, this paper proposed a new method that can avoid the problem of look-ahead bias in traditional data standardization or normalization processes. Then, a detailed logical explanation was given, the definition of continuous trend labeling was proposed and also an automatic labeling algorithm was given to extract the continuous trend features of financial time series data. Experiments on the Shanghai Composite Index and Shenzhen Component Index and some stocks of China showed that our labeling method is a much better state-of-the-art labeling method in terms of classification accuracy and some other classification evaluation metrics. The results of the paper also proved that deep learning models such as LSTM and GRU are more suitable for dealing with the prediction of financial time series data.

Designer cell-self-implemented labeling of microvesicles in situ with the intracellular-synthesized quantum dots

Cell-derived microvesicles (MVs) are secreted from almost all kinds of mammalian cells into the extracellular space, and play crucial roles in intercellular communication and transporting biomolecules between cells. However, there is a great challenge for visualizing and monitoring of MVs’ bio-behaviors due to the limitations of existing labeling methods. Herein, we report the first paradigm of designer cell-self-implemented labeling of MVs secreted from living mammalian MCF-7 cells in situ using the intracellular-synthesized fluorescent quantum dots (QDs) during the formation of MVs. By elaborately coupling intracellular biochemical reactions and metabolism pathways, the MCF-7 cells can be illuminated brightly by intracellular-biosynthesized fluorescent CdSe QDs. Simultaneously, intracellular-synthesized QDs can be in situ encapsulated by the secreted MVs budding from the plasma membrane of the fluorescing cells to label the MVs with an efficiency of up to 89.9%. The whole labeling process skillfully combines designer precise cell-tuned intricate synthesis of CdSe QDs with mild in-situ labeling via cell-self-implementation just after feeding the cell with suitable chemicals, which is structure- or function-nondestructive and much more straightforward and milder than those by chemical conjugation or indirect encapsulation with conventional fluorogenic labels.

Progressive multi-atlas label fusion by dictionary evolution.

Accurate segmentation of anatomical structures in medical images is important in recent imaging based studies. In the past years, multi-atlas patch-based label fusion methods have achieved a great success in medical image segmentation. In these methods, the appearance of each input image patch is first represented by an atlas patch dictionary (in the image domain), and then the latent label of the input image patch is predicted by applying the estimated representation coefficients to the corresponding anatomical labels of the atlas patches in the atlas label dictionary (in the label domain). However, due to the generally large gap between the patch appearance in the image domain and the patch structure in the label domain, the estimated (patch) representation coefficients from the image domain may not be optimal for the final label fusion, thus reducing the labeling accuracy. To address this issue, we propose a novel label fusion framework to seek for the suitable label fusion weights by progressively constructing a dynamic dictionary in a layer-by-layer manner, where the intermediate dictionaries act as a sequence of guidance to steer the transition of (patch) representation coefficients from the image domain to the label domain. Our proposed multi-layer label fusion framework is flexible enough to be applied to the existing labeling methods for improving their label fusion performance, i.e., by extending their single-layer static dictionary to the multi-layer dynamic dictionary. The experimental results show that our proposed progressive label fusion method achieves more accurate hippocampal segmentation results for the ADNI dataset, compared to the counterpart methods using only the single-layer static dictionary.

Dual-Layer Groupwise Registration for Consistent Labeling of Longitudinal Brain Images.

The growing collection of longitudinal images for brain disease diagnosis necessitates the development of advanced longitudinal registration and anatomical labeling methods that can respect temporal consistency between images. However, the characteristics of such longitudinal images and how they lodge into the image manifold are often neglected in existing labeling methods. Indeed, most of them independently align atlases to each target time-point image for propagating the pre-defined atlas labels to the subject domain. In this paper, we present a dual-layer groupwise registration method to consistently label anatomical regions of interest in brain images across different time-points using a multi-atlases-based labeling framework. Our framework can best enhance the labeling of longitudinal images through: (1) using the group mean of the longitudinal images of each subject (i.e., subject-mean) as a bridge between atlases and the longitudinal subject scans to align atlases to all time-point images jointly; and (2) using inter-atlas relationship in their nesting manifold to better register each atlas image to the subject-mean. These steps yield to a more consistent (from the joint alignment of atlases with all time-point images) and more accurate (from the manifold-guided registration between each atlases and the subject-mean image) registration, thereby eventually improving the consistency and accuracy for the subsequent labeling step. We have tested our dual-layer groupwise registration method to label two challenging longitudinal brain datasets (i.e., healthy infants and Alzheimer's disease subjects). Our experimental results have showed that our method achieves higher labeling accuracy while keeping the labeling consistency over time, when compared to the traditional registration scheme (without our proposed contributions). Moreover, the proposed framework can flexibly integrate with the existing label fusion methods, such as sparse-patch based methods, to improve the labeling accuracy of longitudinal datasets.

The Lewis GFP Transgenic Rat Strain is a Useful Cell Donor for Neural Transplantation

Stem cell transplantation is a promising therapeutic approach in neurodegenerative diseases. Studying graft survival and development has important implications for the further development of experimental and clinical transplantation protocols. Cellular elements in neural transplants are sometimes difficult to identify. The existing labeling methods cannot reliably provide stably labeled cells that can be detected in long-term experiments. Transgenic (tg) Lewis rats ubiquitously expressing green fluorescent protein (GFP) provide an ideal donor source. The aim of this project was to investigate the potential of GFP-tg Lewis rats to serve as donor tissue for neural stem cell transplantation. Ventral mesencephalon (VM) GFP-tg E14.5-derived cells were compared to wild-type (wt) in vitro and in vivo. Firstly, cells from GFP and non-GFP VM tissue were compared with regard to their proliferation and response towards 6-OHDA-toxicity in culture. Secondly, 6-OHDA-lesioned hemiparkinsonian Sprague-Dawley/Crl:CD(SD) rats received intrastriatal grafts derived from VM of E14.5 GFP-tg rats. Due to the fact that donor and recipient belong to two different rat strains, we focused on graft survival in correlation with immunosuppression and graft GFP and tyrosine hydroxylase (TH) expression. In summary, in vitro tg cells exhibited 98% GFP expression and did not differ from wt cells in any of the measured parameters. In vivo, all experimental groups showed a significant compensation in rotation behavior after transplantation. Furthermore, there was no difference on rotation behavior or graft morphology and survival pattern as well as GFP expression between immunosuppressed and nonimmunosuppressed animals. The GFP-positive population of the graft was composed of 13.3% GFAP-positive, 56.1% NeuN-positive, and 1.9% TH-positive cells. Analysis of graft subpopulations manifested that 70.6% of GFAP-positive, 86.9% of NeuN-positive, and 80.1% of TH-positive cells coexpressed GFP. In conclusion, our data show that the Lewis GFP-tg rats serve as an excellent cell source for studying primary neural precursor cells in the transplantation paradigm.

Model based labeling for mixture models

Label switching is one of the fundamental problems for Bayesian mixture model analysis. Due to the permutation invariance of the mixture posterior, we can consider that the posterior of a m-component mixture model is a mixture distribution with m! symmetric components and therefore the object of labeling is to recover one of the components. In order to do labeling, we propose to first fit a symmetric m!-component mixture model to the Markov chain Monte Carlo (MCMC) samples and then choose the label for each sample by maximizing the corresponding classification probabilities, which are the probabilities of all possible labels for each sample. Both parametric and semi-parametric ways are proposed to fit the symmetric mixture model for the posterior. Compared to the existing labeling methods, our proposed method aims to approximate the posterior directly and provides the labeling probabilities for all possible labels and thus has a model explanation and theoretical support. In addition, we introduce a situation in which the ideally labeled samples are available and thus can be used to compare different labeling methods. We demonstrate the success of our new method in dealing with the label switching problem using two examples.

A rapid and inexpensive labeling method for microarray gene expression analysis

BackgroundGlobal gene expression profiling by DNA microarrays is an invaluable tool in biological research. However, existing labeling methods are time consuming and costly and therefore often limit the scale of microarray experiments and sample throughput. Here we introduce a new, fast, inexpensive method for direct random-primed fluorescent labeling of eukaryotic cDNA for gene expression analysis and compare the results obtained on the NimbleGen microarray platform with two other widely-used labeling methods, namely the NimbleGen-recommended double-stranded cDNA protocol and the indirect (aminoallyl) method.ResultsTwo total RNA samples were labeled with each method and hybridized to NimbleGen expression arrays. Although all methods tested here provided similar global results and biological conclusions, the new direct random-primed cDNA labeling method provided slightly better correlation between replicates compared to the other methods and thus increased ability to find statistically significant differentially expressed genes.ConclusionThe new direct random-primed cDNA labeling method introduced here is suitable for gene expression microarrays and provides a rapid, inexpensive alternative to existing methods. Using NimbleGen microarrays, the method produced excellent results comparable to those obtained with other methods. However, the simplicity and cost-effectiveness of the new method allows for increased sample throughput in microarray experiments and makes the process amenable to automation with a relatively simple liquid handling system.

Theoretical Proof and Empirical Confirmation of a Continuous Labeling Method Using Naturally 13C‐Depleted Carbon Dioxide

AbstractContinuous isotope labeling and tracing is often needed to study the transformation, movement, and allocation of carbon in plant‐soil systems. However, existing labeling methods have numerous limitations. The present study introduces a new continuous labeling method using naturally 13C‐depleted CO2. We theoretically proved that a stable level of 13C‐CO2 abundance in a labeling chamber can be maintained by controlling the rate of CO2‐free air injection and the rate of ambient airflow with coupling of automatic control of CO2 concentration using a CO2 analyzer. The theoretical results were tested and confirmed in a 54 day experiment in a plant growth chamber. This new continuous labeling method avoids the use of radioactive 14C or expensive 13C‐enriched CO2 required by existing methods and therefore eliminates issues of radiation safety or unaffordable isotope cost, as well as creating new opportunities for short‐ or long‐term labeling experiments under a controlled environment.