Combination Of Active Learning Research Articles

Chest Pain in Primary Care: A Systematic Review of Risk Stratification Tools to Rule Out Acute Coronary Syndrome.

Chest pain frequently poses a diagnostic challenge for general practitioners (GPs). Utilizing risk stratification tools might help GPs to rule out acute coronary syndrome (ACS) and make appropriate referral decisions. We conducted a systematic review of studies evaluating risk stratification tools for chest pain in primary care settings, both with and without troponin assays. Our aims were to assess the performance of tools for ruling out ACS and to provide a comprehensive review of the current evidence. We searched PubMed and Embase for articles up to October 9, 2023 concerning adult patients with acute chest pain in primary care settings, for whom risk stratification tools (clinical decision rules [CDRs] and/or single biomarker tests) were used. To identify eligible studies, a combination of active learning and backward snowballing was applied. Screening, data extraction, and quality assessment (following the Quality Assessment of Diagnostic Accuracy Studies-2 tool) were performed independently by 2 researchers. Of the 1,204 studies screened, 14 were included in the final review. Nine studies validated 7 different CDRs without troponin. Sensitivities ranged from 75.0% to 97.0%, and negative predictive values (NPV) ranged from 82.4% to 99.7%. None of the CDRs outperformed the unaided judgment of GP's. Five studies reported on strategies using troponin measurements. Studies using high-sensitivity troponin showed highest diagnostic accuracy with sensitivity 83.3% to 100% and NPV 98.8% to 100%. Clinical decision rules without troponin and the use of conventional troponin showed insufficient sensitivity to rule out ACS in primary care and are not recommended as standalone tools. High-sensitivity troponin strategies are promising, but studies are limited. Further prospective validation in primary care is needed before implementation.

Machine-Learned Potentials by Active Learning from Organic Crystal Structure Prediction Landscapes.

A primary challenge in organic molecular crystal structure prediction (CSP) is accurately ranking the energies of potential structures. While high-level solid-state density functional theory (DFT) methods allow for mostly reliable discrimination of the low-energy structures, their high computational cost is problematic because of the need to evaluate tens to hundreds of thousands of trial crystal structures to fully explore typical crystal energy landscapes. Consequently, lower-cost but less accurate empirical force fields are often used, sometimes as the first stage of a hierarchical scheme involving multiple stages of increasingly accurate energy calculations. Machine-learned interatomic potentials (MLIPs), trained to reproduce the results of ab initio methods with computational costs close to those of force fields, can improve the efficiency of the CSP by reducing or eliminating the need for costly DFT calculations. Here, we investigate active learning methods for training MLIPs with CSP datasets. The combination of active learning with the well-developed sampling methods from CSP yields potentials in a highly automated workflow that are relevant over a wide range of the crystal packing space. To demonstrate these potentials, we illustrate efficiently reranking large, diverse crystal structure landscapes to near-DFT accuracy from force field-based CSP, improving the reliability of the final energy ranking. Furthermore, we demonstrate how these potentials can be extended to more accurately model structures far from lattice energy minima through additional on-the-fly training within Monte Carlo simulations.

Improving Graph Neural Networks by combining active learning with self-training

In this paper, we propose a novel framework, called STAL, which makes use of unlabeled graph data, through a combination of Active Learning and Self-Training, in order to improve node labeling by Graph Neural Networks (GNNs). GNNs have been shown to perform well on many tasks, when sufficient labeled data are available. Such data, however, is often scarce, leading to the need for methods that leverage unlabeled data that are abundant. Active Learning and Self-training are two common approaches towards this goal and we investigate here their combination, in the context of GNN training. Specifically, we propose a new framework that first uses active learning to select highly uncertain unlabeled nodes to be labeled and be included in the training set. In each iteration of active labeling, the proposed method expands also the label set through self-training. In particular, highly certain pseudo-labels are obtained and added automatically to the training set. This process is repeated, leading to good classifiers, with a limited amount of labeled data. Our experimental results on various datasets confirm the efficiency of the proposed approach.

An expected integrated error reduction function for accelerating Bayesian active learning of failure probability

The combination of active learning with surrogate model (e.g., Gaussian Process Regression, GPR) for structural reliability analysis has been extensively studied and proved to be of superiority due to the high efficiency. The performance of an active learning algorithm is determined by the utilized acquisition function, to a great extent, as it dominates the generation of the training data. The traditional acquisition functions usually fail to incorporate the spatial correlation information revealed by the surrogate model, thus still have plenty of room for improvement. We propose a new acquisition function, named as Expected Integrated Error Reduction (EIER) function, for active learning of the failure probability with a smaller number of simulator calls. Mathematically, the value of the EIER function at an unobserved point measures the expected integrated reduction of the probability of mis-classifying all points over the full input space, once this point is added to train the GPR model. The numerical error of the failure probability is evaluated with the posterior confidence intervals and/or coefficient of variation, numerically computed with an efficient sampling strategy, and is then served as the stopping criteria. The superiority of the proposed improvements is demonstrated with a set of numerical and engineering examples. • The EIER acquisition function is devised for active learning of failure probability. • It measures the overall accuracy improvement with any one point being observed. • The posterior variance is utilized for monitoring the convergence. • A sampling method is devised for computing EIER function and posterior variance. • Benchmark studies show the EIER function outperforms the others.

Modeling with Real-Time Informative Feedback: Implementing and Evaluating a New Massive Open Online Course Component.

As part of the design, development, and deployment of a massive open online course (MOOC) on model-based systems engineering, we introduced MORTIF-Modeling with Real-Time Informative Feedback, a new learning-by-doing feature that enables the learner to model, receive detailed feedback, and resubmit improved solutions. We examined the pedagogical usability of MORTIF by investigating characteristics of participants working with it, and their perceived contribution, preferred question type, and learning style. The research included 295 participants and applied the mixed-methods approach, using MOOC server data and online questionnaires. Analyzing 12,095 submissions, we found increasing frequency of using the model resubmitting option. Students ranked MORTIF as the highest of six question types in terms of preference and perceived contribution level. Nine learning style categories were identified and classified based on students' verbal explanations regarding their preference of MORTIF over the other question types. MORTIF has been effective in promoting meaningful learning, supporting our hypothesis that the combination of active learning with real-time informative feedback is a learning mode that students eagerly embrace and benefit from. The benefits we identified for using MORTIF include active learning, provision of meaningful immediate feedback to the learner, the option to use the feedback on the spot and resubmitting an improved model, and its suitability for a variety of learning styles.

Federated Clustering and Semi-Supervised learning: A new partnership for personalized Human Activity Recognition

Federated Learning (FL) is currently studied by several research groups as a promising paradigm for sensor-based Human Activity Recognition (HAR) to mitigate the privacy and scalability issues of classic centralized approaches. However, in the HAR domain, data is non-independently and identically distributed (non-IID), and personalization is one of the major challenges. Federated Clustering has been recently proposed to mitigate this issue by creating specialized global models for groups of similar users. While this approach significantly improves personalization, it assumes that labeled data are available on each client. In this work, we propose SS-FedCLAR, a novel HAR framework that combines Federated Clustering and Semi-Supervised learning. In SS-FedCLAR , each client uses a combination of active learning and label propagation to provide pseudo labels to a large amount of unlabeled data, which is then used to collaboratively train a Federated Clustering model. We evaluated SS-FedCLAR on two well-known public datasets, showing that it outperforms existing semi-supervised FL solutions while reaching recognition rates similar to fully-supervised FL approaches.

Cross-Domain Active Learning for Electronic Nose Drift Compensation.

The problem of drift in the electronic nose (E-nose) is an important factor in the distortion of data. The existing active learning methods do not take into account the misalignment of the data feature distribution between different domains due to drift when selecting samples. For this, we proposed a cross-domain active learning (CDAL) method based on the Hellinger distance (HD) and maximum mean difference (MMD). In this framework, we weighted the HD with the MMD as a criterion for sample selection, which can reflect as much drift information as possible with as few labeled samples as possible. Overall, the CDAL framework has the following advantages: (1) CDAL combines active learning and domain adaptation to better assess the interdomain distribution differences and the amount of information contained in the selected samples. (2) The introduction of a Gaussian kernel function mapping aligns the data distribution between domains as closely as possible. (3) The combination of active learning and domain adaptation can significantly suppress the effects of time drift caused by sensor ageing, thus improving the detection accuracy of the electronic nose system for data collected at different times. The results showed that the proposed CDAL method has a better drift compensation effect compared with several recent methodological frameworks.

Digital Resources for Targeted Mathematics Support

SPIRIT Maths (Students’ Perceptions Informing and Redefining Innovative Teaching of Mathematics in Higher Education) is a project that was established in Munster Technological University (MTU) to investigate students’ attitudes towards mathematics and to explore a more student-centred development of mathematics resources. One of the aims of the project was to create a collection of student-preferred digital materials with a view to improving student engagement, building students’ confidence in mathematics and helping students to succeed in their mathematics modules.The findings of a survey disseminated to first year students in MTU indicated that students would be most likely to use the resources if they were geared towards their specific module; to maximise impact, resources were developed for two modules, one in Engineering and one in Business, that are each taken by large numbers of students. The resources were integrated on the learning management system and are available to all MTU students taking a mathematics module. Three interlinked digital resources were developed: (1) a series of interactive self-assessment questions, (2) corresponding videos showing worked solutions and (3) an associated bank of practice questions developed using a digital tutor to provide instant feedback. It is hoped that the complementary resources will facilitate student learning through a combination of active learning, explicit instruction and the ready availability of the resources.This article describes these resources and how they were developed, and outlines how these are being promoted to students. We also report on the feedback received from a small number of students who tested the resources and discuss how to measure student engagement with the resources.

Positive effect of using just-in-time teaching with part time students in a pedagogical university

This article is centered around the problem of using active learning and online home exercises as an effective means of learning a second language. Just in Time Teaching (JITT) is considered to be the combination of active learning and online exercises which proves its effectiveness. The authors dwell upon the advantages of JIIT in order to give most informative course in the shortest period of time possible. JITT facilitates students’ involving more learning strategies and simple ways to achieve best results and language acquisition. The authors claim that using the new approach makes learning grammar more successful. To find out the data the research was undertaken at the university. It included a survey that was carried out before and after the experiment with JITT. The results of the study showed a large growth in students’ accomplishments and interest to the subject.

IMPEDIMENTS FACED BY TEACHERS IN APPLYING ACTIVE LEARNING STRATEGIES IN LANGUAGE CLASSES IN ENHANCING LISTENING SKILLS

Purpose: The study analyses how active learning strategies can improve the learners’ language skills especially the listening skills with the use of various active learning strategies and blended teaching. It also shed light on the aim and purpose of certain strategies that will make the class more student-centered and engages the learners actively. It supports the constructivist approach a theory that underlies active learning. The study involves a survey conducted in some private, semi-urban, CBSE, middle schools in Chennai on the English teachers in understanding their opinion on using active learning strategies in class to enhance the learners’ language skills in a day-to-day classroom. The data collected from the survey form and details from one-on-one interaction with teachers will help the researcher learn the impediments faced by the teachers in implementing these strategies in the classroom.
 Methodology: The survey sheet is a questionnaire that focuses on the teacher’s classroom practices. It involves certain aspects such as Teaching methodology, teaching strategies, assessments, Feedback and its efficacy and Teacher attitude towards students. The questionnaire besides MCQs also had some one-line questions to which teachers had to answer. The survey was conducted on 50 teachers from 6 different schools teaching English in Middle schools of the semi-urban area of Chennai.
 Main Findings: The various barriers faced by the teachers in implementing active learning strategies are found in the survey conducted. It was also observed that there was some dearth of knowledge among teachers in the contemporary theories that lead to the resistance of the teachers in conducting the activities.
 Application: The methods mentioned in the paper can be adopted by teachers who also feel that the major reasons for their resistance in using active learning strategies in their day-to-day class are categorically similar to the reasons mentioned in the paper.
 Novelty: The methods suggested in the paper are a combination of active learning which is a theory predominantly based on constructivism and blended teaching. Although the reasons mentioned by the teachers in the survey are major limitations in planning an active learning class, these can be controlled to an extent by planning these strategies with resources suitable to one’s learner group and using certain active learning strategies in class with the students.

Combination of Active Learning and Semi-Supervised Learning under a Self-Training Scheme

One of the major aspects affecting the performance of the classification algorithms is the amount of labeled data which is available during the training phase. It is widely accepted that the labeling procedure of vast amounts of data is both expensive and time-consuming since it requires the employment of human expertise. For a wide variety of scientific fields, unlabeled examples are easy to collect but hard to handle in a useful manner, thus improving the contained information for a subject dataset. In this context, a variety of learning methods have been studied in the literature aiming to efficiently utilize the vast amounts of unlabeled data during the learning process. The most common approaches tackle problems of this kind by individually applying active learning or semi-supervised learning methods. In this work, a combination of active learning and semi-supervised learning methods is proposed, under a common self-training scheme, in order to efficiently utilize the available unlabeled data. The effective and robust metrics of the entropy and the distribution of probabilities of the unlabeled set, to select the most sufficient unlabeled examples for the augmentation of the initial labeled set, are used. The superiority of the proposed scheme is validated by comparing it against the base approaches of supervised, semi-supervised, and active learning in the wide range of fifty-five benchmark datasets.

A combination of active learning and self-learning for named entity recognition on Twitter using conditional random fields

In recent years, many applications in natural language processing (NLP) have been developed using the machine learning approach. Annotating data is an important task in applying machine learning to NLP applications. A common approach to improve the system performance is to train on a large and high-quality set of training data that is annotated by experts. Besides, active learning (AL) and self-learning can be utilized to reduce the annotation costs. The self-learning method discovers highly reliable instances based on a trained classifier, while AL queries the most informative instances based on active query algorithms. This paper proposes a method that combines AL and self-learning to reduce the labeling effort for the named entity recognition task from tweet streams by using both machine-labeled and manually-labeled data. We employ AL queries based on the diversity of the context and content of instances to select the most informative instances. The conditional random fields are also chosen as an underlying model to train a classifier for selecting highly reliable instances. The experiments using Twitter data show that the proposed method achieves good results in reducing the human labeling effort, and it can significantly improve the performance of the systems.

A3 Learning System: Advanced Active and Autonomous Learning System

This paper proposes the Advanced-Active-Autonomous (A3) Learning System, which is an educational system based on the use of information and communication technology. The A3 Learning System is a combination of Active Learning (AL), Project/Problem-Based Learning (PBL) and Mastery Learning (ML). We report some uses of the A3 system and implemented AL and ML in foundational learning in the software/hardware information fields. Additionally, we implemented PBL in software design. We implemented two methods; one involves individual students and the other involves a group. Furthermore, to evaluate the benefits of the A3 Learning System, the Progress Report on Generic Skill (PROG) test was carried out; the results of the test are discussed here.

Classification of Crop Cultivation Areas Using Active Learning and Temporal Contextual Information

This paper presents a classification method based on the combination of active learning with temporal contextual information extracted from past land-cover maps for the classification of crop cultivation areas. Iterative classification based on active learning is designed to extract reliable training data and cultivation rules from past land-cover maps are quantified as temporal contextual information to be used for not only assignment of training data but also relaxation of spectral ambiguity. To evaluate the applicability of the classification method proposed in this paper, a case study with MODIS time-series vegetation index data sets and past cropland data layers(CDLs) is carried out for the classification of corn and soybean in Illinois state, USA. Iterative classification based on active learning could reduce misclassification both between corn and soybean and between other crops and non crops. The combination of temporal contextual information also reduced the over-estimation results in major crops and led to the best classification accuracy. Thus, these case study results confirm that the proposed classification method can be effectively applied for crop cultivation areas where it is not easy to collect the sufficient number of reliable training data.

Combination of active learning and self-training for cross-lingual sentiment classification with density analysis of unlabelled samples

In recent years, research in sentiment classification has received considerable attention by natural language processing researchers. Annotated sentiment corpora are the most important resources used in sentiment classification. However, since most recent research works in this field have focused on the English language, there are accordingly not enough annotated sentiment resources in other languages. Manual construction of reliable annotated sentiment corpora for a new language is a labour-intensive and time-consuming task. Projection of sentiment corpus from one language into another language is a natural solution used in cross-lingual sentiment classification. Automatic machine translation services are the most commonly tools used to directly project information from one language into another. However, since term distribution across languages may be different due to variations in linguistic terms and writing styles, cross-lingual methods cannot reach the performance of monolingual methods. In this paper, a novel learning model is proposed based on the combination of uncertainty-based active learning and semi-supervised self-training approaches to incorporate unlabelled sentiment documents from the target language in order to improve the performance of cross-lingual methods. Further, in this model, the density measures of unlabelled examples are considered in active learning part in order to avoid outlier selection. The empirical evaluation on book review datasets in three different languages shows that the proposed model can significantly improve the performance of cross-lingual sentiment classification in comparison with other existing and baseline methods.

Cooperative Learning and its Application to Emotion Recognition from Speech

In this paper, we propose a novel method for highly efficient exploitation of unlabeled data-Cooperative Learning. Our approach consists of combining Active Learning and Semi-Supervised Learning techniques, with the aim of reducing the costly effects of human annotation. The core underlying idea of Cooperative Learning is to share the labeling work between human and machine efficiently in such a way that instances predicted with insufficient confidence value are subject to human labeling, and those with high confidence values are machine labeled. We conducted various test runs on two emotion recognition tasks with a variable number of initial supervised training instances and two different feature sets. The results show that Cooperative Learning consistently outperforms individual Active and Semi-Supervised Learning techniques in all test cases. In particular, we show that our method based on the combination of Active Learning and Co-Training leads to the same performance of a model trained on the whole training set, but using 75% fewer labeled instances. Therefore, our method efficiently and robustly reduces the need for human annotations.

Real-Time Automated Cardiac Health Monitoring by Combination of Active Learning and Adaptive Feature Selection

Electrocardiograms (ECGs) are widely used by clinicians to identify the functional status of the heart. Thus, there is considerable interest in automated systems for real-time monitoring of arrhythmia. However, intra- and inter-patient variability as well as the computational limits of real-time monitoring poses significant challenges for practical implementations. The former requires that the classification model be adjusted continuously, and the latter requires a reduction in the number and types of ECG features, and thus, the computational burden, necessary to classify different arrhythmias. We propose the use of adaptive learning to automatically train the classifier on up-to-date ECG data, and employ adaptive feature selection to define unique feature subsets pertinent to different types of arrhythmia. Experimental results show that this hybrid technique outperforms conventional approaches and is therefore a promising new intelligent diagnostic tool.

Weakly supervised learning of information structure of scientific abstracts—is it accurate enough to benefit real-world tasks in biomedicine?

Many practical tasks in biomedicine require accessing specific types of information in scientific literature; e.g. information about the methods, results or conclusions of the study in question. Several approaches have been developed to identify such information in scientific journal articles. The best of these have yielded promising results and proved useful for biomedical text mining tasks. However, relying on fully supervised machine learning (ml) and a large body of annotated data, existing approaches are expensive to develop and port to different tasks. A potential solution to this problem is to employ weakly supervised learning instead. In this article, we investigate a weakly supervised approach to identifying information structure according to a scheme called Argumentative Zoning (az). We apply four weakly supervised classifiers to biomedical abstracts and evaluate their performance both directly and in a real-life scenario in the context of cancer risk assessment. Our best weakly supervised classifier (based on the combination of active learning and self-training) performs well on the task, outperforming our best supervised classifier: it yields a high accuracy of 81% when just 10% of the labeled data is used for training. When cancer risk assessors are presented with the resulting annotated abstracts, they find relevant information in them significantly faster than when presented with unannotated abstracts. These results suggest that weakly supervised learning could be used to improve the practical usefulness of information structure for real-life tasks in biomedicine.