This paper explores customized scaffolding for pre-service teachers’ problem-solving in technology and engineering discipline. We used clustering analysis to discover natural groupings of scaffolding characteristics which were used in 144 computer-based scaffolding studies from the previous meta-analysis. We first selected input variables based on our research questions which include different scaffolding characteristics, context of use, education level, and effect size. Next, using a two-step clustering algorithm, we found four clusters based on the predominant scaffolding characteristics and profiled each cluster in terms of scaffolding characteristics and their context of use. The resulting cluster solutions indicate what combination of scaffolding characteristics used in different types of problem-centered learning context would be effective for pre-service teachers’ technology- and engineering-related problem-solving.
more »
« less
Machine learning-based design of meta-plasmonic biosensors with negative index metamaterials
In this work, we explore the performance of plasmonic biosensor designs that integrate metamaterials based on machine learning algorithms. The meta-plasmonic biosensors were designed for optimized detection of DNA with a layer of double negative metamaterial modeled by an effective medium. An iterative transfer matrix approach was employed to generate training and test sets of resonance characteristics in the parameter space for machine learning. As a machine learning-based prediction of optical characteristics of a meta-plasmonic biosensor, multilayer perceptron and autoencoder (AE) were used as an algorithm, while the clustering algorithm was constructed by dimensional reduction based on AE and t-Stochastic Neighbor Embedding (t-SNE) as well as k-means clustering. Use of meta-plasmonic structure with analysis based on machine learning has found that enhancement of detection sensitivity by more than 13 times over conventional detection should be achievable with excellent reflectance curves. Further enhancement may be attained by expanding the parameter space.
more »
« less
- Award ID(s):
- 1856165
- NSF-PAR ID:
- 10224830
- Date Published:
- Journal Name:
- Biosensors bioelectronics
- Volume:
- 164
- ISSN:
- 1873-4235
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Among many structural assessment methods, the change of modal characteristics is considered a well‐accepted damage detection method. However, the presence of environmental or operational variations may pollute the baseline and prevent a dependable assessment of the change. In recent years, the use of machine learning algorithms gained interest within structural health community, especially due to their ability and success in the elimination of ambient uncertainty. This paper proposes an end‐to‐end architecture to detect damage reliably by employing machine learning algorithms. The proposed approach streamlines (a) collection of structural response data, (b) modal analysis using system identification, (c) learning model, and (d) novelty detection. The proposed system aims to extract latent features of accessible modal parameters such as natural frequencies and mode shapes measured at undamaged target structure under temperature uncertainty and to reconstruct a new representation of these features that is similar to the original using well‐established machine learning methods for damage detection. The deviation between measured and reconstructed parameters, also known as novelty index, is the essential information for detecting critical changes in the system. The approach is evaluated by analyzing the structural response data obtained from finite element models and experimental structures. For the machine learning component of the approach, both principal component analysis (PCA) and autoencoder (AE) are examined. While mode shapes are known to be a well‐researched damage indicator in the literature, to our best knowledge, this research is the first time that unsupervised machine learning is applied using PCA and AE to utilize mode shapes in addition to natural frequencies for effective damage detection. The detection performance of this pipeline is compared to a similar approach where its learning model does not utilize mode shapes. The results demonstrate that the effectiveness of the damage detection under temperature variability improves significantly when mode shapes are used in the training of learning algorithm. Especially for small damages, the proposed algorithm performs better in discriminating system changes.
-
The comprehensive properties of high-entropy alloys (HEAs) are highly-dependent on their phases. Although a large number of machine learning (ML) algorithms has been successfully applied to the phase prediction of HEAs, the accuracies among different ML algorithms based on the same dataset vary significantly. Therefore, selection of an efficient ML algorithm would significantly reduce the number and cost of the experiments. In this work, phase prediction of HEAs (PPH) is proposed by integrating criterion and machine learning recommendation method (MLRM). First, a meta-knowledge table based on characteristics of HEAs and performance of candidate algorithms is established, and meta-learning based on the meta-knowledge table is adopted to recommend an algorithm with desirable accuracy. Secondly, an MLRM based on improved meta-learning is engineered to recommend a more desirable algorithm for phase prediction. Finally, considering poor interpretability and generalization of single ML algorithms, a PPH combining the advantages of MLRM and criterion is proposed to improve the accuracy of phase prediction. The PPH is validated by 902 samples from 12 datasets, including 405 quinary HEAs, 359 senary HEAs, and 138 septenary HEAs. The experimental results shows that the PPH achieves performance than the traditional meta-learning method. The average prediction accuracy of PPH in all, quinary, senary, and septenary HEAs is 91.6%, 94.3%, 93.1%, and 95.8%, respectively.more » « less
-
Engineering programs must weave coverage of disciplinary content with the ability of students to apply and extend this content knowledge to new contexts and for use in their professional practice as engineers. It is, therefore, necessary for schools to promote and cultivate additional dispositions within their students that better enable them to adapt and employ their disciplinary knowledge. The concept of an “adaptive expert” (AE) has been previously developed within the learning sciences to describe an individual with deep content knowledge but who also displays additional cognitive characteristics that better enable them to employ their knowledge and skills in practice. Four constructs have been identified in the literature as forming the basis of this adaptive expertise: 1) multiple perspectives (MP), 2) metacognition (META), 3) goals and beliefs (GB), and 4) epistemology (EPIST). Upon entry to an engineering program, it is likely that students will present with different levels of development and awareness within these particular dimensions. Baseline levels must, therefore, be measured in order to assess these levels of development and before research-based practices and activities can be designed to promote growth in these constructs. In this work-in-progress study, the “adaptiveness” of incoming undergraduate STEM students (n=711) is measured using a previously developed validated survey instrument used in other studies to measure levels of adaptive expertise amongst undergraduate students by determining their levels along the four identified dimensions of AE. Based on this survey data, statistically significant differences were found in the AE constructs for men and women, with women outscoring men in three of the four AE subscales (MP, META, EPIST) and men outscoring women in goals and beliefs (GB). White students were found to score statistically higher than Asian students in both multiple perspectives (MP) and goals and beliefs (GB), while no statistically significant differences were observed when White and Black/African American students were compared. The mean epistemology (EPIST) scores for White, non-Hispanic students was statistically higher than Hispanic students, with low-income students scoring lower than non-low-income students on this subscale. This project seeks to provide baseline data concerning the adaptivity of incoming first-year students. A structured mentoring program focusing on elements of AE will then be implemented and student growth in the dimensions of AE assessed through their program of study.more » « less
-
null (Ed.)Artificial intelligence nowadays plays an increasingly prominent role in our life since decisions that were once made by humans are now delegated to automated systems. A machine learning algorithm trained based on biased data, however, tends to make unfair predictions. Developing classification algorithms that are fair with respect to protected attributes of the data thus becomes an important problem. Motivated by concerns surrounding the fairness effects of sharing and few-shot machine learning tools, such as the Model Agnostic Meta-Learning [1] framework, we propose a novel fair fast-adapted few-shot meta-learning approach that efficiently mitigates biases during meta train by ensuring controlling the decision boundary covariance that between the protected variable and the signed distance from the feature vectors to the decision boundary. Through extensive experiments on two real-world image benchmarks over three state-of-the-art meta-learning algorithms, we empirically demonstrate that our proposed approach efficiently mitigates biases on model output and generalizes both accuracy and fairness to unseen tasks with a limited amount of training samples.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/https://doi.org/10.1016 /j.bios.2020.112335
