Numerical Labels Research Articles

OCRClassifier: integrating statistical control chart into machine learning framework for better detecting open chromatin regions.

Open chromatin regions (OCRs) play a crucial role in transcriptional regulation and gene expression. In recent years, there has been a growing interest in using plasma cell-free DNA (cfDNA) sequencing data to detect OCRs. By analyzing the characteristics of cfDNA fragments and their sequencing coverage, researchers can differentiate OCRs from non-OCRs. However, the presence of noise and variability in cfDNA-seq data poses challenges for the training data used in the noise-tolerance learning-based OCR estimation approach, as it contains numerous noisy labels that may impact the accuracy of the results. For current methods of detecting OCRs, they rely on statistical features derived from typical open and closed chromatin regions to determine whether a region is OCR or non-OCR. However, there are some atypical regions that exhibit statistical features that fall between the two categories, making it difficult to classify them definitively as either open or closed chromatin regions (CCRs). These regions should be considered as partially open chromatin regions (pOCRs). In this paper, we present OCRClassifier, a novel framework that combines control charts and machine learning to address the impact of high-proportion noisy labels in the training set and classify the chromatin open states into three classes accurately. Our method comprises two control charts. We first design a robust Hotelling T2 control chart and create new run rules to accurately identify reliable OCRs and CCRs within the initial training set. Then, we exclusively utilize the pure training set consisting of OCRs and CCRs to create and train a sensitized T2 control chart. This sensitized T2 control chart is specifically designed to accurately differentiate between the three categories of chromatin states: open, partially open, and closed. Experimental results demonstrate that under this framework, the model exhibits not only excellent performance in terms of three-class classification, but also higher accuracy and sensitivity in binary classification compared to the state-of-the-art models currently available.

A text-based, generative deep learning model for soil reflectance spectrum simulation in the solar range (400–2499 nm)

Soil spectral reflectance is a necessary input for land surface and radiative transfer models, and can be used to infer soil properties. Numerous soil reflectance inversion models have been developed based on mechanistic approaches, each with their own limitations. Mechanistic models based on radiative transfer theory are usually based on only a few input soil properties, whereas data-driven approaches are limited by high non-uniformity of available published datasets that severely limits the amount of data usable for model calibration. To address these limitations, a fully data-driven soil optics generative model (SOGM) for simulation of soil reflectance spectra from soil property inputs was developed based on the denoising diffusion probabilistic model (DDPM). The model was trained on an extensive dataset comprising nearly 180,000 soil spectra-property set pairs from 17 published datasets. The model generates soil reflectance spectra from text-based inputs describing soil properties and their values rather than only numerical values and labels in binary vector format, which means the model can handle variable formats for property reporting. Because the model is generative, it can simulate reasonable output spectra based on an incomplete set of available input properties, which becomes more reliable as the input property set becomes more complete. Two additional sub-models were also built to complement the SOGM: a spectral padding model that can fill in the gaps for spectra shorter than the target solar range (400 to 2499 nm), and a wet soil spectra model that can estimate the effects of water content on soil reflectance spectra given the dry spectrum predicted by the SOGM. It can also be easily integrated with other soil–plant radiation models used for remote sensing research such as PROSAIL and Helios 3D plant modeling software. The testing results of the SOGM on new datasets not included in model training demonstrated that the model can generate reasonable soil reflectance spectra based on available property inputs. Results also show soil clay/sand/silt fraction, organic carbon content, nitrogen content, and iron content tended to be important properties for spectra simulation. Inclusion of some trace minerals like nickel as model inputs decreased model performance because of their low concentrations and large propensity for ground-truth measurement error.

A well-visualized effect: How nutritional content–equivalent labels influence healthfulness perceptions

Consumers are increasingly relying on nutrition labels to assess the healthfulness of food products. Previous research has mainly explored abstract numerical labels that explicitly quantify nutritional content (e.g., “vitamin content: 268 mg”). However, given that consumers tend to process images more efficiently than numbers, this study investigates whether visualized nutritional content–equivalent labels (e.g., “vitamin content ≈▪[orange icons]”) convey nutrient content more effectively than numerical labels, thereby enhancing consumers’ healthfulness perceptions. The results indicate that visualized nutritional content–equivalent labels lead to higher perceived healthfulness compared to numerical labels, primarily due to the activation of mental imagery. However, this effect is attenuated when informational (vs. transformational) advertising appeals are used on the packaging. The findings emphasis the effectiveness of visualized nutritional content–equivalent labels in communicating healthy nutrition information to consumers.

Dataset preparation for CROHME 2019 for training a neural network

Subject of research. This article examines the process of data preparation for training neural network models that address the task of recognizing complex handwritten mathematical expressions and converting them into typesetting systems like LaTeX or MathML. The dataset under study is CROHME 2019, which contains images of handwritten mathematical expressions and their corresponding LaTeX annotations. The objective of this research is to develop and describe a data preparation process that ensures correct model training and minimizes errors in numerical labels and transformations. The study focuses on the following key stages: loading and preprocessing images, parsing LaTeX annotations, linking images with their corresponding annotations, normalizing pixel values, creating and verifying the tokenizer vocabulary, and preparing the tokenizer itself. The methods include data analysis and processing using specialized tools for working with images and text annotations. The main outcome of this work is the creation of a dataset ready for use in training the neural network model. The prepared dataset ensures accurate alignment between images and annotations, as well as correct conversion of mathematical expressions into LaTeX code.

Enhancing power equipment defect identification through multi-label classification methods

Accurate identification and classification of equipment defects are essential for assessing the health of power equipment and making informed maintenance decisions. Traditional defect classification methods, which rely on subjective manual records and intricate defect descriptions, have proven to be inefficient. Existing approaches often evaluate equipment status solely based on defect grade. To enhance the precision of power equipment defect identification, we developed a multi-label classification dataset by compiling historical defect records. Furthermore, we assessed the performance of 11 established multi-label classification methods on this dataset, encompassing both traditional machine learning and deep learning methods. Experimental results reveal that methods considering label correlations exhibit significant performance advantages. By employing balanced loss functions, we effectively address the challenge of sample imbalance across various categories, thereby enhancing classification accuracy. Additionally, segmenting the power equipment defect classification task, which involves numerous labels, into label recall and ranking stages can substantially improve classification performance. The dataset we have created is available for further research by other scholars in the field.

A community sin vergüenza: Considerations when designing classroom spaces for bi/multilingual students to speak, listen, and be heard

ABSTRACT This article explores the parallels experienced when pre-service teachers and those teaching multilingual students in elementary school design classroom spaces around the Right of the Learner to speak, listen, and be heard. We share examples of democratic commitments and shifts in our own understandings of the role of the teacher and professor. We also discuss the importance of being willing to be with students as they shed the shame that may have kept them silent in other classroom settings. This article explores what it means for educators to make room for Latinx students to use their voices and embrace their ideas sin vergüenza, without shame.

Impact of Five Types of Front-of-Package Nutrition Labels on Consumer Behavior among Young Adults: A Systematic Review.

The World Health Organization (WHO) recommends that governments promote and implement front-of-package (FoP) nutrition labels to prevent noncommunicable diseases. Recently, additional research has focused on various views on FoP label creation. However, few review studies have examined how different FoP labels affect young consumer behavior. Therefore, this study thoroughly analyzed the evidence on how FoP labels in five categories affect young consumer purchasing intention and behavior. We searched for keywords in the Web of Science, Scopus, and EBSCO databases and screened study samples according to inclusion and exclusion criteria. Fourteen studies that matched the criteria were included in this review. We discovered that numerous studies support the efficacy of the "graded indicators" category labels, with the "color-coded" and "positive logos" categories trailing closely behind. The effectiveness of the "warning" FoP label category is mixed on consumers' healthy purchasing behavior and intention. The numerical FoP labels were most commonly used to indicate ineffectiveness. Future studies should investigate the effects of FoP labels on various subpopulations and conduct thorough evaluations of the design elements of FoP labels. Also, they should offer evidence-based recommendations, supported by both quantitative and qualitative data, for regions that have not yet implemented FoP labeling systems.

EU climate labeling policy: Analyzing consumer’s comprehension of CO2 footprint labels

In theory, climate labeling holds the potential to guide consumers towards making more climate-friendly food choices. However, for the efficacy such labeling the ease and accuracy of an information understanding is crucial. Over recent years, numerous new climate labeling schemes have emerged in the European market. In this study, we investigate perception and objective knowledge to gain a better understanding of consumer comprehension of various existing label types. These include climate-neutral, reduction, carbon footprint, best-in-class and multi-level traffic light labels. The results reveal that a traffic light label is markedly better understood by consumers than the other label types analyzed. For instance, while more than 50 % of respondents believed they understood the climate-neutral label, it caused frequent wrongful inferences, posing a risk of misinterpretation and greenwashing. In contrast, participants demonstrated a high level of both positive perception and objective knowledge regarding the traffic light label. Therefore, traffic light labeling has the greatest potential to encourage climate-friendly dietary choices and reduce consumer confusion in the food market.

Thinking fast, not slow: intuitive nutrition labels increase healthier food preferences under time pressure

PurposeFront-of-pack (FOP) nutrition labeling has attracted considerable attention in a wide range of communities. However, the limited effects of FOP nutrition labels on healthier food preferences have been reported. Drawing on the dual system theory, this study aimed to investigate which FOP nutrition labels increase healthier food preferences and when. Drawing on the dual-process theory, this study aimed to investigate the effects of Nutri-Scores on healthy food preferences under time pressure.Design/methodology/approachParticipants saw two food packages (healthier and less healthy) with either intuitive (nutrient score) or numeric FOP labels. They then had to choose one of their preferred products with or without time pressure.FindingsAcross two studies (including one pre-registered replication), the results consistently demonstrated that the Nutri-Score (vs numeric labels) increases healthier food preferences under time pressure. No significant difference in the likelihood of choosing healthier food was found between the labels under non-time pressure.Originality/valueTogether, our results suggest that intuitive FOP labeling (i.e. Nutri-Score) enhances healthier food preferences during Type 1 processing and provides practical implications for promoting healthy eating.

A surprising lack of consequences when constraining language

IntroductionLabels considered normatively appropriate for specific social identity groups change. Researchers have examined the effects of censorship and slur usage, but minimal research examines the psychological consequences of imposing new language constraints on people.MethodsAcross four samples of university students (Ntotal = 997), we sought participants' compliance in avoiding usage of numerous commonplace group labels while they wrote essays about obese people (Sample 1) or specific ethnic groups (Samples 2-4).ResultsWe observed consistently high compliance rates: participants either invented novel terminology to describe the group or avoided group labels entirely. We observed a substantial absence of task discomfort, attitudinal shifts regarding the group, or motivational shifts, according to Bayesian analyses. Nor did we detect negative effects of language constraint among people who saw themselves as opposed to censorship.DiscussionAlthough free speech and respectful language remain a multifaceted social debate, our findings show that university students are willing to follow even completely contrived language directives when describing social identity groups and to do so without substantial discomfort or backlash against those groups.

Any-Way Meta Learning

Although meta-learning seems promising performance in the realm of rapid adaptability, it is constrained by fixed cardinality. When faced with tasks of varying cardinalities that were unseen during training, the model lacks its ability. In this paper, we address and resolve this challenge by harnessing `label equivalence' emerged from stochastic numeric label assignments during episodic task sampling. Questioning what defines ``true" meta-learning, we introduce the ``any-way" learning paradigm, an innovative model training approach that liberates model from fixed cardinality constraints. Surprisingly, this model not only matches but often outperforms traditional fixed-way models in terms of performance, convergence speed, and stability. This disrupts established notions about domain generalization. Furthermore, we argue that the inherent label equivalence naturally lacks semantic information. To bridge this semantic information gap arising from label equivalence, we further propose a mechanism for infusing semantic class information into the model. This would enhance the model's comprehension and functionality. Experiments conducted on renowned architectures like MAML and ProtoNet affirm the effectiveness of our method.

Multi-label feature selection based on fuzzy rough sets with metric learning and label enhancement

Multi-label feature selection based on fuzzy rough sets, as a key step of multi-label data preprocessing, has been widely concerned by scholars in recent years. Most of the existing multi-label feature selection algorithms directly treat labels as logical labels and use a single distance metric to describe similarity. However, the variability of label descriptions and the limitations of a single distance measure should not be overlooked. In this paper, we propose a fuzzy rough set model with metric learning and label enhancement. Specifically, we use a kernel membership label enhancement algorithm based on JS divergence to convert logical labels into numerical labels, which not only reflects the importance of different labels, but also takes into account the differences in label distribution. In addition, a multi-metric learning algorithm is proposed for multi-label learning, in which the metric distance function under the label space and feature space can be learned autonomously. Then, based on the proposed model, we propose a novel multi-label feature selection algorithm based on metric learning and fuzzy rough sets. On this basis, a fast multi-label feature selection algorithm is further designed to improve the computational efficiency. In the experiments, compared with other nine algorithms on real-world datasets, the results show the superiority of the proposed algorithm.

SG-MIAN: Self-guided multiple information aggregation network for image-level weakly supervised skin lesion segmentation

Nowadays, skin disease is becoming one of the most malignant diseases that threaten people’s health. Computer aided diagnosis based on deep learning has become a widely used technology to assist medical professionals in diagnosis, and segmentation of lesion areas is one of the most important steps in it. However, traditional medical image segmentation methods rely on numerous pixel-level labels for fully supervised training, and such labeling process is time-consuming and requires professional competence. In order to reduce the costs of pixel-level labeling, we proposed a method only using image-level label to segment skin lesion areas. Due to the lack of lesion’s spatial and intensity information in image-level labels, and the wide distribution range of irregular shape and different texture on skin lesions, the algorithm must pay great attention to the automatic lesion localization and perception of lesion boundary. In this paper, we proposed a Self-Guided Multiple Information Aggregation Network (SG-MIAN). Our backbone network MIAN utilizes the Multiple Spatial Perceptron (MSP) solely using classification information as guidance to discriminate the key classification features of lesion areas, and thereby performing more accurate localization and activation of lesion areas. Additionally, adjunct to MSP, we also proposed an Auxiliary Activation Structure (AAS) and two auxiliary loss functions to further self-guided boundary correction, achieving the goal of accurate boundary activation. To verify the effectiveness of the proposed method, we conducted extensive experiments using the HAM10000 dataset and the PH2dataset, which demonstrated superior performance compared to most existing weakly supervised segmentation methods.

Group and Group Isomorphism in Pyraminx

Pyraminx is a twisty puzzle in the shape of a tetrahedron with 4 sides. Pyraminx is played with the bottom completely flat and the front side facing the person holding the Pyraminx. The goal of the Pyraminx game is to randomize the colors, then return the scrambled colors to their original color positions by rotating the sides. This research does not discuss the most effective way of solving Pyraminx but focuses more on proving that movements in Pyraminx form group and that there is a group isomorphism from the group of Pyraminx movements to the symmetry permutation subgroup in Pyraminx. First, it is proved that movements in Pyraminx form group using 2 methods, namely direct proof in Pyraminx (Pyaminx movement group) and performing permutations in set containing numeric labels in the form of numbers 1 to 36 on Pyraminx facets by following the movements of Pyraminx ( symmetry permutation subgroup). Furthermore, it is proved that there is a group isomorphism from the Pyraminx movement group to the symmetry permutation subgroup in Pyraminx.

Use of the Scales software complex in planning the surgical treatment of patients with lumbar degenerative spondylolisthesis

The aim of the study was to develop a virtual software package that, when it is based on personalized indicators, allows planning surgical tactics and performing differentiated treatment of patients with degenerative lumbar spondylolisthesis.The results of surgical treatment of retrospective group patients were the basis for creation of a virtual complex.A virtual software package has been developed. It is an expert system for making decisions about surgical tactics for patients with lumbar degenerative spondylolisthesis. The operation of the program is based on the automated analysis of a given list of input parameters. The core of the virtual complex is represented by two configurations, one of which contains an artificial neural network. As a result of virtual processing of the patient’s individual parameters, the program gives an answer in the form of two color scales with numerical labels: a scale of differentiated choice between isolated decompression and decompression supplemented with posterior fusion; scales for a differentiated choice between laminectomy supplemented with medial facetectomy and bilateral decompression of the spinal canal from a unilateral approach. Using the developed software package, surgical treatment of 26 patients with lumbar degenerative spondylolisthesis was performed.The Scales virtual complex, based on key general somatic and clinical and radiological parameters of a patient, creates an opportunity for a surgeon to make the most balanced and informed decision on the tactics of surgical treatment of lumbar degenerative spondylolisthesis. A personalized approach, accompanied by artificial intelligence technology, is aimed at reducing the likelihood of tactical errors and long-term complications of surgical interventions. The use of color scales with digital labels makes it possible to simplify the process of preoperative planning and to create conditions for achieving a balance between the decision of the program and the individual opinion of a specialist surgeon. The result of differentiated treatment of a group of patients using a virtual system was a significant and statistically significant ( p < 0.001) improvement in the life quality of operated patients in the long-term period.

Novel Multidimensional Pain Assessment Tool Is a Feasible, Valid, and Enjoyable Approach to Communication of Pain Symptoms in Pediatric Sickle Cell Disease

Background: Pain is the most common symptom of sickle cell disease (SCD) and is especially difficult to assess in the pediatric population. Children have varied developmental stages and cognitive abilities making the communication of this subjective experience hard to operationalize. Both the assessment of pain and validation of these assessments is challenging. No pediatric pain assessment tool has been deemed valid and reliable across all ages and types of pain. Commonly used pediatric tools include the Wong-Baker Faces scale, the numeric rating scale, and the visual analog scale (VAS), which combines the visuals of faces and numeric rating. These are unidimensional - only assessing the severity of pain, and in the case of faces, can cause confusion between pain severity and patient affect. In children with SCD, accurate pain assessment is crucial to current and lifelong management. “Painimation” is a technology-based pain assessment tool that incorporates conceptual animations, rather than numbers or words, to characterize pain. These animations are intended to help clinicians better understand pain from the patient's perspective. They are dynamic and transcend language. For example, animations are designed to communicate dull pulsating pain, sharp electric pain, or anything in between. “Painimation” does not rely on verbal communication skills, making it ideal for use in the pediatric population. “Painimation” has been validated in adults with SCD and is currently in implementation trials. Our study aims to determine the feasibility and validity of “Painimation” in pediatric SCD. Methods: This is a single site non-randomized cross-sectional feasibility and validity study. Participants were 10 - 21 years old with SCD who presented to clinic in baseline health. Participants completed the Painimation application, which consists of a numeric pain rating scale (1-10), a front and back 2-dimensional body image that can be shaded to indicate areas affected by pain, and eight abstract animations intended to represent different pain qualities (tingling, shooting, stabbing, throbbing, pounding, cramping, electrifying, and burning). The patient chose up to three animations and the intensity of each chosen animation was adjusted using a sliding bar without numeric labels. The animations were presented to the patient without labeling the intended quality. The patients then completed a survey consisting of questions regarding the usability of Painimation, clinical questions regarding their disease, Lansky Play-Performance Scale, and validated patient reported outcomes questions (PedsQL, Ped-PRO-CTCAE, PROMIS). Results: We enrolled 30 participants between April 1 and July 31, 2023, with recruitment ongoing. Five records were incomplete and were not analyzed at this time. The mean ratings when asked whether 1) Painimation was easy to use, 2) the patient enjoyed using Painimation, and 3) the patient would use Painimation to communicate pain with their provider were respectively 3.28±.74 (SD), 3.08±.95, and 3.12±1.17 (scale 0-4), indicating a generally favorable result for feasibility. The median VAS score was 5.10 (IQR = 0.25, 8.25). Pain was most reported in the back lower chest (60%), front stomach (48%), and front chest (44%). The stabbing animation was the most chosen at 56% followed by the cramping animation at 20%. Electrifying and Cramping animations had the highest agreement with their intended McGill descriptors at 40%. VAS scores and Painimation severity scores demonstrated excellent positive correlation (Pearson r=.74). Conclusion: Painimation is a feasible pain assessment tool in pediatric SCD with high user satisfaction. Severity scores on Painimation correlate strongly with VAS scores. The pain characteristic conveyed by each animation adds unique dimensions to this measure and will be further analyzed. Painimation is a novel pediatric pain assessment that holds the promise of greatly improving the communication of pain and transforming care in Pediatric SCD.

Food for thought: Reinforced learning and recall of physical activity calorie equivalent (PACE) and numerical calorie content in an associative learning task

Calorie overconsumption has been proposed as a critical contributing factor to rising obesity rates. To combat this health issue, governments and policymakers have suggested implementing numerical caloric content labels. Alternatively, physical activity calorie equivalent (PACE) labels are being proposed as an easier-to-understand metric, representing the amount of physical activity required to burn off calorie content. This study examined individuals' ability to correctly estimate either the numerical caloric content or the PACE values of food images in an associative learning task. Moreover, it assessed whether this knowledge was learned and retained over time. One hundred and ninety-one participants were instructed to estimate either the numerical caloric content or PACE values of thirty food images. To facilitate learning, feedback on the correct number of calories or PACE values was provided during the first session (Time 1). To assess retention, people re-estimated numerical caloric content or PACE values of the same food pictures three days later (Time 2) and seven days later (Time 3), where feedback was not provided. Results showed that participants in both groups improved their estimations using feedback, with people being consistently more accurate when estimating numerical calorie content. Yet, our results also suggest that participants consolidated their knowledge of PACE values over time. Finally, our findings show that hunger moderates individuals' estimation ability, where hungrier people are less accurate than satiated ones. The results contribute to our understanding of how consumers process, estimate, and learn PACE labels versus numerical caloric content, and provide valuable information for researchers and policymakers to develop and implement nutritional labels as a health strategy.

Enhancing Taxonomic Categorization of DNA Sequences with Deep Learning: A Multi-Label Approach.

The application of deep learning for taxonomic categorization of DNA sequences is investigated in this study. Two deep learning architectures, namely the Stacked Convolutional Autoencoder (SCAE) with Multilabel Extreme Learning Machine (MLELM) and the Variational Convolutional Autoencoder (VCAE) with MLELM, have been proposed. These designs provide precise feature maps for individual and inter-label interactions within DNA sequences, capturing their spatial and temporal properties. The collected features are subsequently fed into MLELM networks, which yield soft classification scores and hard labels. The proposed algorithms underwent thorough training and testing on unsupervised data, whereby one or more labels were concurrently taken into account. The introduction of the clade label resulted in improved accuracy for both models compared to the class or genus labels, probably owing to the occurrence of large clusters of similar nucleotides inside a DNA strand. In all circumstances, the VCAE-MLELM model consistently outperformed the SCAE-MLELM model. The best accuracy attained by the VCAE-MLELM model when the clade and family labels were combined was 94%. However, accuracy ratings for single-label categorization using either approach were less than 65%. The approach's effectiveness is based on MLELM networks, which record connected patterns across classes for accurate label categorization. This study advances deep learning in biological taxonomy by emphasizing the significance of combining numerous labels for increased classification accuracy.

Graph-Based Class-Imbalance Learning With Label Enhancement.

Class imbalance is a common issue in the community of machine learning and data mining. The class-imbalance distribution can make most classical classification algorithms neglect the significance of the minority class and tend toward the majority class. In this article, we propose a label enhancement method to solve the class-imbalance problem in a graph manner, which estimates the numerical label and trains the inductive model simultaneously. It gives a new perspective on the class-imbalance learning based on the numerical label rather than the original logical label. We also present an iterative optimization algorithm and analyze the computation complexity and its convergence. To demonstrate the superiority of the proposed method, several single-label and multilabel datasets are applied in the experiments. The experimental results show that the proposed method achieves a promising performance and outperforms some state-of-the-art single-label and multilabel class-imbalance learning methods.

Classification of Food Additives Using UV Spectroscopy and One-Dimensional Convolutional Neural Network.

Food additives are utilized in countless food products available for sale. They enhance or obtain a specific flavor, extend the storage time, or obtain a desired texture. This paper presents an automatic classification system for five food additives based on their absorbance in the ultraviolet domain. Solutions with different concentrations were created by dissolving a measured additive mass into distilled water. The analyzed samples were either simple (one additive solution) or mixed (two additive solutions). The substances presented absorbance peaks between 190 nm and 360 nm. Each substance presents a certain number of absorbance peaks at specific wavelengths (e.g., acesulfame potassium presents an absorbance peak at 226 nm, whereas the peak associated with potassium sorbate is at 254 nm). Therefore, each additive has a distinctive spectrum that can be used for classification. The sample classification was performed using deep learning techniques. The samples were associated with numerical labels and divided into three datasets (training, validation, and testing). The best classification results were obtained using CNN (convolutional neural network) models. The classification of the 404 spectra with a CNN model with three convolutional layers obtained a mean testing accuracy of 92.38% ± 1.48%, whereas the mean validation accuracy was 93.43% ± 2.01%.