Multiple Labels Research Articles

The Implementation of Multi Label K- Nearest Neighbor Algorithm To Classifying Essay Answers

One way of assessing essays is to use the STAR (Situation, Task, Action, Result) method. This method aims to classify whether the essay already reflects the values of the situation, task, action, and outcome labels presented by the prospective driving teacher. Multi-label classification refers to a classification task in which each data sample can be classified into multiple categories or labels simultaneously. Various methods have been developed to perform multi-label text classification, such as MLKNN, MLTSVM, and MLP. This research aims to determine the value of the accuracy of the score. Therefore, the Multi-Label K-Nearest Neighbor, or MLKNN, algorithm can be implemented to classify essays with five labels: no star, situation, task, action, and result. With a total dataset of 110, which will be obtained from one of the assessors from the driving teacher. The MLKNN algorithm produces an accuracy rate with an average value of 15.6%.

Distantly Supervised Relation Extraction via Contextual Information Interaction and Relation Embeddings

Distantly supervised relation extraction (DSRE) utilizes an external knowledge base to automatically label a corpus, which inevitably leads to the problem of mislabeling. Existing approaches utilize BERT to provide instances and relation embeddings to capture a wide set of relations and address the noise problem. However, the method suffers from a single method of textual information processing, underutilizing the feature information of entity pairs in the relation embeddings part and being interfered with by noisy labels when classifying multiple labels. For this reason, we propose the contextual information interaction and relation embeddings (CIRE) method. First, we utilize BERT and Bi-LSTM to construct a neural network model to enhance contextual information interaction by filtering and supplementing sequence information through the error repair capability of the Bi-LSTM gating mechanism. At the same time, we combine the vector difference between entity pairs and entity pairs in the relation embeddings layer to improve the relation embeddings accuracy. Finally, we choose sparse softmax as the classifier, which improves the ability to control the noise categories by controlling the number of output categories. The experimental results show that our method significantly outperforms the baseline method and improves the AUC metric by 2.6% on the NYT2010 dataset.

Robust online hashing with label semantic enhancement for cross-modal retrieval

Online hashing technology has attracted extensive attention owing to its effectiveness and efficiency in processing large-scale streaming data. However, there are still some limitations: (1) In practical applications, the observed labels of multimedia data are obtained through manual annotation, which may inevitably introduce some noises into labels. This may lead to retrieval performance degradation when the noisy labels are directly applied to retrieval tasks. (2) The potential semantic correlation of multi-labels cannot be fully explored. To overcome these limitations, in this paper, we propose robust online hashing with label semantic enhancement (ROHLSE). Specifically, ROHLSE seeks to recover the clean labels from the provided noisy labels by imposing low-rank and sparse constraints. Meanwhile, it employs the representation of samples in the feature space to predict the labels via the dependency between sample instances and labels. To efficiently handle streaming data, ROHLSE preserves the similarity between new data, and establishes the semantic relationships between new and old data through chunk similarity, simultaneously. Furthermore, ROHLSE can fully utilize the semantic correlations between multiple labels of each instance. Extensive experiments are conducted on three benchmark datasets to demonstrate the superiority of the proposed ROHLSE approach.

A Novel Learning-Based PLST Algorithm for Multi-Label Classification

In Multi-Label Classification (MLC), each data sample is characterized by multiple labels. In ML, there is no restriction on the number of classes a data sample could belong to. Various methods are proposed to construct a model to map data samples to the class labels. Transforming the MLC problem into several binary classification problems is the baseline approach, also called the binary relevance technique. As an alternative solution, the label powerset approach transforms the MLC problem into a multi-class classification problem by building a binary classifier for every label composition. However, in Ensemble Methods (EMs), multiple classifiers are consolidated to form a multi-label ensemble classifier. In this case, each classifier predicts a class label. Thereupon, the predicted class labels are joined using an ensemble method. This paper presents a neoteric EM classifier using the Ridge Regression-based Principal Label Space Transformation (RR-PLST). In the proposed model, the PLST utilizes SVD to discover correlations between the labels and data samples. Dimensionality reduction is a well-known technique to enhance the model's precision and diminish execution time. Consequently, the OPLS technique is recruited to reduce data dimensions in the proposed model. Moreover, in the proposed model, a Q-Learning method is used to amend the initially predicted labels. To demonstrate the effectiveness of the proposed model, vast experiments are conducted on the various widely used multi-label datasets. The proposed algorithm results are compared with similar algorithms by the AP, EM, HS, Macro, and Micro F1 metrics. The experimental results demonstrate the superiority of the proposed model.

Work smart, not hard: How array tomography can help increase the ultrastructure data output.

Transmission electron microscopy has been essential for understanding cell biology for over six decades. Volume electron microscopy tools, such as serial block face and focused ion beam scanning electron microscopy acquisition, brought a new era to ultrastructure analysis. 'Array Tomography' (AT) refers to sequential image acquisition of resin-embedded sample sections on a large support (coverslip, glass slide, silicon wafers) for immunolabelling with multiple fluorescent labels, occasionally combined with ultrastructure observation. Subsequently, the term was applied to generating and imaging a series of sections to acquire a 3D representation of a structure using scanning electron microscopy (SEM). Although this is a valuable application, the potential of AT is to facilitate many tasks that are difficult or even impossible to obtain by Transmission Electron Microscopy (TEM). Due to the straightforward nature and versatility of AT sample preparation and image acquisition, the technique can be applied practically to any biological sample for selected sections or volume electron microscopy analysis. Furthermore, in addition to the benefits described here, AT is compatible with morphological analysis, multiplex immunolabelling, immune-gold labelling, and correlative light and electron microscopy workflow applicable for single cells, tissue and small organisms. This versatility makes AT attractive not only for basic research but as a diagnostic tool with a simplified routine.

HAIN: Multilabel Classification With Hierarchical Attention-Based Interaction Network for Multiturn Dialogue Texts

Multi-turn dialogue systems with cognitive capabilities have been popularly used in many applications and generate a large volume of dialogue texts. The dialogue texts of many dialogue systems contain multiple labels, and a typical case is that the customer requirements or complaints in an online multi-turn dialogue service system often need to be classified into multiple categories or forwarded to multiple departments, that is, multi-label classification on multi-turn dialogue texts. Traditional methods treat the dialogue text as the plain text, which makes it difficult for classifiers to learn important features. On the other hand, regarding each utterance as the basic semantic unit may destroy the semantic information integrity of the dialogue. Furthermore, the above methods all ignore the relationship between labels. To address above issues, we propose to use the utterance pair as the basic semantic unit and design a novel multi-label classification model for multi-turn dialogue texts in this paper. Specifically, we propose to use multi-head attention mechanism to learn the key features of multiple labels and design a new method to learn the correlation among labels. Besides, we propose to use penalty term to allow multi-head attention to focus on different semantics. Finally, we conduct sufficient experiments on four real-world multi-turn dialogue datasets and the experimental results show that our model produces superior performance.

COVID-19 Vaccine Adverse Event Detection Based on Multi-Label Classification With Various Label Selection Strategies.

Analyzing massive VAERS reports without medical context may lead to incorrect conclusions about vaccine adverse events (VAE). Facilitating VAE detection promotes continual safety improvement for new vaccines. This study proposes a multi-label classification method with various term-and topic-based label selection strategies to improve the accuracy and efficiency of VAE detection. Topic modeling methods are first used to generate rule-based label dependencies from Medical Dictionary for Regulatory Activities terms in VAE reports with two hyper-parameters. Multiple label selection strategies, namely one-vs-rest (OvsR), problem transformation (PT), algorithm adaption (AA), and deep learning (DL) methods, are used in multi-label classification to examine the model performance, respectively. Experimental results indicated that the topic-based PT methods improve the accuracy by up to 33.69% using a COVID-19 VAE reporting data set, which improves the robustness and interpretability of our models. In addition, the topic-based OvsR methods achieve an optimal accuracy of up to 98.88%. The accuracy of the AA methods with topic-based labels increased by up to 87.36%. By contrast, the state-of-art LSTM- and BERT-based DL methods have relatively poor performance with accuracy rates of 71.89% and 64.63%, respectively. Our findings reveal that the proposed method effectively improves the model accuracy and strengthens VAE interpretability by using different label selection strategies and domain knowledge in multi-label classification for VAE detection.

Monocular 3D-trajectory reconstruction using models-driven weakly supervised learning

Neural networks have demonstrated remarkable success in various computer vision tasks, offering benefits such as self-learning, self-organization, and self-adaptation. To maintain these advantages, a high-quality labeled dataset is essential. However, obtaining such a dataset is particularly challenging in monocular three-dimensional (3D) tracking of transient objects, like welding spatters, which are so complex that no single model can accurately describe them simultaneously. To address the label acquisition issue in this transient process, we introduce a models-driven weakly supervised learning (MsWSL) approach which is achieved by integrating diverse scopes of multiple models and generating multiple labels for weakly supervised learning. The MsWSL is incorporated into a combination of a feature image transformer encoder and a multilayer perceptron with multiple inputs, enhancing the network's ability to automatically adjust the model and adaptively learn the most suitable label. In the experiments on welding spatters, results from MsWSL show better performance than those from individual models, validating the effectiveness and superiority of MsWSL. We believe that the proposed MsWSL will have broader significant applications in monocular 3D-trajectory reconstruction for multiple, intricate, unrepeatable, and transient objects.

Multiplexed Biosensing of Proteins and Virions with Disposable Plasmonic Assays.

Our growing ability to tailor healthcare to the needs of individuals has the potential to transform clinical treatment. However, the measurement of multiple biomarkers to inform clinical decisions requires rapid, effective, and affordable diagnostics. Chronic diseases and rapidly evolving pathogens in a larger population have also escalated the need for improved diagnostic capabilities. Current chemical diagnostics are often performed in centralized facilities and are still dependent on multiple steps, molecular labeling, and detailed analysis, causing the result turnaround time to be over hours and days. Rapid diagnostic kits based on lateral flow devices can return results quickly but are only capable of detecting a handful of pathogens or markers. Herein, we present the use of disposable plasmonics with chiroptical nanostructures as a platform for low-cost, label-free optical biosensing with multiplexing and without the need for flow systems often required in current optical biosensors. We showcase the detection of SARS-CoV-2 in complex media as well as an assay for the Norovirus and Zika virus as an early developmental milestone toward high-throughput, single-step diagnostic kits for differential diagnosis of multiple respiratory viruses and any other emerging diagnostic needs. Diagnostics based on this platform, which we term "disposable plasmonics assays," would be suitable for low-cost screening of multiple pathogens or biomarkers in a near-point-of-care setting.

A novel seminar learning framework for weakly supervised salient object detection

Weakly supervised salient object detection (SOD) is a challenging task and has drawn much attention from several research perspectives, it has revealed two problems while driving the rapid development of saliency detection. (1) Large divergence in the characteristics of saliency regions in terms of location, shape and size makes them difficult to recognize. (2) The properties of convolutional neural networks dictate that it is insensitive to various transformations, which will lead to hardly balance the application of various disturbances. To tackle these limitations, this paper proposes a novel seminar learning framework with consistent transformation ensembling (SLF-CT) for scribble supervised SOD. The framework consists of the teacher–student model and the student–student model for segmenting the salient objects. Specifically, we first design a cross attention guided network (CAGNet) as a baseline model for saliency prediction. Then we assign CAGNet to the teacher–student model, where the teacher network is based on the exponential moving average and guides the training of the student network. Moreover, we adopt multiple pseudo labels to transfer the information among students from different conditions. To further enhance the regularization of the network, a consistency transformation mechanism is also incorporated, which encourages the saliency prediction and input image of the network to be consistent. The experimental results demonstrate that the proposed approach performs favorably comparable with the state-of-the-art weakly supervised methods. As far as we know, the proposed approach is the first application of seminar learning in the SOD area.

Modified boosting and bagging for building tilt rate prediction in tunnel construction

The building tilt rate (BTR) prediction problem is of great importance for safety management in metro tunnel construction. To improve the BTR prediction accuracy, it is pertinent to accurately identify and properly handle less-reliable data which refers to data with an inconsistent input-output relation. A modified boosting and bagging approach is thus proposed, i.e., BooBag. Specifically, modified bagging of BooBag can create multiple artificial labels for differentiating reliable data and less-reliable data while modified boosting can be used for pace management to avoid both underfitting and overfitting. Investigations of a practical BTR prediction case show that BooBag can accurately differentiate reliable data and less-reliable data, which leads to a smaller BTR prediction error, which is further validated via extensive independence, strategy, and resilience comparisons. BooBag can be used for safety management in tunnel construction as a pre-step to be combined with varied machine learning approaches for key safety indicator prediction, irregularity/anomaly detection, fault diagnosis, etc.

Site-Specific and Multiple Fluorogenic Metabolic Glycan Labeling and Glycoproteomic Profiling in Live Cells.

Multicolor labeling for monitoring the intracellular localization of the same target type in the native environment using chemical fluorescent dyes is a challenging task. This approach requires both bioorthogonal and biocompatible ligations with an excellent fluorescence signal-to-noise ratio. Here, we present a metabolic glycan labeling technique that uses homemade fluorogenic dyes to investigate glycosylation patterns in live cells. These dyes allowed us to demonstrate rapid and efficient simultaneous multilabeling of glycoconjugates with minimum fluorescence noise. Our results demonstrate that this approach is capable of not only probing sialylation and GlcNAcylation in cells but also specifically labeling the cell-surface and intracellular sialylated glycoconjugates in live cells. In particular, we performed site-specific dual-channel fluorescence imaging of extra and intracellular sialylated glycans in HeLa and PC9 cancer cells as well as identified fluorescently labeled sialylated glycoproteins and glycans by a direct enrichment approach combined with an MS-based proteomic analysis in the same experiment. In conclusion, this study provides multilabeling tools in cellular systems for simultaneous site-specific glycan imaging and glycoproteomic analysis to study potential cancer- and disease-associated glycoconjugates.

Multi-Label Feature Selection Via Adaptive Label Correlation Estimation

In multi-label learning, each instance is associated with multiple labels simultaneously. Multi-label data often have noisy, irrelevant, and redundant features of high dimensionality. Multi-label feature selection has received considerable attention as an effective means for dealing with high-dimensional multi-label data. Many multi-label feature selection methods exploit label correlations to help select features. However, finding label correlations and selecting features in existing multi-label feature selection methods are often two separate processes, the existence of noises and outliers in training data makes the label correlations exploited from label space less reliable. Therefore, the learned label correlations may mislead the feature selection process and result in the selection of less informative features. This article proposes a novel algorithm named ROAD, i.e., multi-label featuRe selectiOn via ADaptive label correlation estimation. ROAD jointly performs adaptive label correlation exploration and feature selection with alternating optimization to obtain reliable estimation of label correlations, which can more effectively reveal the intrinsic manifold structure among labels and lead to the selection of a more proper feature subset. Comprehensive experiments on several frequently used datasets validate the superiority of ROAD against the state-of-the-art multi-label feature selection algorithms.

Developing Multi-Labelled Corpus of Twitter Short Texts: A Semi-Automatic Method

Facing fast-increasing electronic documents in the Digital Media Age, the need to extract textual features of online texts for better communication is growing. Sentiment classification might be the key method to catch emotions of online communication, and developing corpora with annotation of emotions is the first step to achieving sentiment classification. However, the labour-intensive and costly manual annotation has resulted in the lack of corpora for emotional words. Furthermore, single-label semantic corpora could hardly meet the requirement of modern analysis of complicated user’s emotions, but tagging emotional words with multiple labels is even more difficult than usual. Improvement of the methods of automatic emotion tagging with multiple emotion labels to construct new semantic corpora is urgently needed. Taking Twitter short texts as the case, this study proposes a new semi-automatic method to annotate Internet short texts with multiple labels and form a multi-labelled corpus for further algorithm training. Each sentence is tagged with both the emotional tendency and polarity, and each tweet, which generally contains several sentences, is tagged with the first two major emotional tendencies. The semi-automatic multi-labelled annotation is achieved through the process of selecting the base corpus and emotional tags, data preprocessing, automatic annotation through word matching and weight calculation, and manual correction in case of multiple emotional tendencies are found. The experiments on the Sentiment140 published Twitter corpus demonstrate the effectiveness of the proposed approach and show consistency between the results of semi-automatic annotation and manual annotation. By applying this method, this study summarises the annotation specification and constructs a multi-labelled emotion corpus with 6500 tweets for further algorithm training.

Let’s (Not) Put Another Label on it: Multiple Product Labels on Vice and Virtue Products

Let’s (Not) Put Another Label on it: Multiple Product Labels on Vice and Virtue Products

Biosensors; noninvasive method in detection of C-reactive protein (CRP).

Early diagnosis of C reactive protein (CRP) is critical to applying effective therapies for related diseases. Diagnostic technology in today's healthcare systems is mostly deployed in central laboratories, involves expensive and time-consuming processes, and is operated by specialized personnel. For example, the enzyme-linked immunosorbent assay (ELISA), considered the gold standard diagnostic method, is labor-intensive and requires complex procedures such as multiple washing and labeling steps. Due to these limitations of current diagnostic techniques, it is difficult for people to regularly monitor their health and ultimately the disease is more likely to be diagnosed at a later stage. The problem is exacerbated for economically disadvantaged people living in underdeveloped countries. To address these challenges in the traditional diagnostic field, point-of-care (POC) biosensors have emerged as a promising alternative. This allows patients to have their health checked regularly at or near their bedside without resorting to laboratory tests. Nanotechnology-based methods such as biosensors have been extensively researched and developed. Among biosensors, there are also label-free biosensors with high sensitivity that do not require complicated procedures and reduce test time. However, some drawbacks such as high cost, bulky size and need for trained personnel to operate have not been improved. In this review article, we provide an overview of routine methods in CRP diagnosis and then introduce biosensors as a modern, advanced alternative to older methods. Readers of this article can learn about biosensing and its benefits while being aware of the limitations of routine methods.

Bayesian network model structure based on binary evolutionary algorithm.

With the continuous development of new technologies, the scale of training data is also expanding. Machine learning algorithms are gradually beginning to be studied and applied in places where the scale of data is relatively large. Because the current structure of learning algorithms only focus on the identification of dependencies and ignores the direction of dependencies, it causes multiple labeled samples not to identify categories. Multiple labels need to be classified using techniques such as machine learning and then applied to solve the problem. In the environment of more training data, it is very meaningful to explore the structure extension to identify the dependencies between attributes and take into account the direction of dependencies. In this article, Bayesian network structure learning, analysis of the shortcomings of traditional algorithms, and binary evolutionary algorithm are applied to the randomized algorithm to generate the initial population. In the optimization process of the algorithm, it uses a Bayesian network to do a local search and uses a depth-first algorithm to break the loop. Finally, it finds a higher score for the network structure. In the simulation experiment, the classic data sets, ALARM and INSURANCE, are introduced to verify the effectiveness of the algorithm. Compared with NOTEARS and the Expectation-Maximization (EM) algorithm, the weight evaluation index of this article was 4.5% and 7.3% better than other schemes. The clustering effect was improved by 13.5% and 15.2%. The smallest error and the highest accuracy are also better than other schemes. The discussion of Bayesian reasoning in this article has very important theoretical and practical significance. This article further improves the Bayesian network structure and optimizes the performance of the classifier, which plays a very important role in promoting the expansion of the network structure and provides innovative thinking.

Ensemble of kernel extreme learning machine based elimination optimization for multi-label classification

Multi-label learning is a class of machine learning algorithms that study the classification problem of data associated with multiple labels simultaneously. Ensemble-based method is one of the representative methods in multi-label learning. In the existing ensemble-based multi-label classification methods, the essence of its base learner is still a binary or multi-class classifier. At present, there is no ensemble-based multi-label method that uses a multi-label classifier based on algorithm adaptation as a base learner. Multi-label algorithms suffer from expensive time costs, and ensemble-based methods further exacerbate the time cost. To address these issues, we propose an efficient multi-label classification method based on kernel extreme learning machine and ensemble learning. Firstly, to solve the problem of high time complexity of multi-label classifiers, we use a Gaussian kernel function to generate a kernel extreme learning machine based multi-label classifier (KELM_ML). Then, based on random sampling, we construct the base classifier, i.e., KELM_ML, in ensemble learning. Finally, to build an ensemble model of multi-label classifiers, an elimination optimization ensemble strategy is proposed by defining an encoding vector of the base classifiers and updating it. Although our method is an ensemble model, it inherits the advantages of good time complexity of ELM, i.e., fast learning time. The experimental and statistical results show that compared with baseline methods and other ensemble-based multi-label methods, our proposed method has better classification performance and stable results.

Discovering overlapping communities using a new diffusion approach based on core expanding and local depth traveling in social networks

This paper proposes a local diffusion-based approach to find overlapping communities in social networks based on label expansion using local depth first search and social influence information of nodes, called the LDLF algorithm. It is vital to start the diffusion process in local depth, traveling from specific core nodes based on their local topological features and strategic position for spreading community labels. Correspondingly, to avoid assigning excessive and unessential labels, the LDLF algorithm prudently removes redundant and less frequent labels for nodes with multiple labels. Finally, the proposed method finalizes the node's label based on the Hub Depressed index. Thanks to requiring only two iterations for label updating, the proposed LDLF algorithm runs in low time complexity while eliminating random behavior and achieving acceptable accuracy in finding overlapping communities for large-scale networks. The experiments on benchmark networks prove the effectiveness of the LDLF method compared to state-of-the-art approaches.

Cross-Classification Analysis of Food Products Based on Nutritional Quality and Degree of Processing.

This study aims to compare the classification of foods available in the Portuguese market using Nutri-Score and NOVA classifications and to analyse their ability to discriminate the fat, saturated fat, sugar, and salt content of foods. A sample of 2682 food products was collected. The nutritional quality of foods was established using the Nutri-Score, classifying them into five categories (from A to E). The NOVA classification was used to classify foods according to the degree of food processing into unprocessed/minimally processed foods, processed culinary ingredients, processed foods, and ultra-processed foods (UPF). The nutritional content of food products was classified using a Multiple Traffic Light label system. It was observed that 73.7% of UPF were classified as Nutri-Score C, D, and E, 10.1% as Nutri-Score A, and 16.2% as Nutri-Score B. Nutri-Score was positively correlated with NOVA classification (ρ = 0.140, p < 0.001) and with the Multiple Traffic Lights system (ρTotal Fat = 0.572, ρSaturated Fat = 0.668, ρSugar = 0.215, ρSalt = 0.321, p < 0.001). NOVA classification negatively correlated with the Multiple Traffic Lights system for total fat (ρ = -0.064, p < 0.001). Our findings indicate the presence of many UPFs in all Nutri-Score categories. Since food processing and nutritional quality are complementary, both should be considered in labelling.