Diverse Ensemble Research Articles

Not Strictly STEAM

“That which We Call A Rose,” (“Rose”) is a multi-media performance-as-research project, with puppets and robots, that I devised with a diverse ensemble of undergraduates and professionals to explore questions about planetary nomenclature, climate change, and colonization. “Rose” explicitly challenges andro-and euro-centric hegemonies embedded in 21st century space exploration and invites its audiences to do the same. STEAM (Science, Technology, Engineering, Arts, and Mathematics) has become a popular pedagogy for K-12 education. Many K-12 STEAM programs claim to put art at the heart of STEM, but often prioritize science content over creative process, falling short of the potential that STEAM holds to foster lifelong learners and innovators who are curious, skilled, and literate across a variety of disciplinary and cultural boundaries. The Rhode Island School of Design (RISD), on the other hand, promotes a K-20 STEAM pedagogy that acknowledges the importance of facilitating young learners’ creative inquiry as well as the potential for mature artists to become equally-valued culture creators across arts, science, and social domains.
 In this article, I use “Rose” as a case study to query the possibilities of implementing performance-as-research as an essential component of STEAM pedagogies. I examine the ways that artists can invite audiences across multiple social identities to join in processes of performance creation as a means of critical inquiry of STEM fields. The performance-as-research process encourages participant audiences to authentically engage in arts practices as a means of actively combatting social issues such as climate change, professional gender and racial inequity, and the colonialist traditions implicit to contemporary space exploration.

A GRAMMAR BASED METHODOLOGY TO SUPPORT THE ADAPTIVE REUSE OF HISTORIC BUILDINGS: THE CASE STUDY OF THE SOBRADO BUILDING TYPE

Abstract. The historical center of São Luís is host to a diverse historic and urban ensemble, reminiscent of the 18th and 19th centuries. The architectural typology which can be found there illustrates the strong influence drawn from the Portuguese style known as Pombalino, developed during the reconstruction process of Lisbon after the 1755 earthquake. Due to the historical relevance of these buildings which encapsulate this period in time, it is important to preserve and maintain the buildings located in this region. Adaptive reuse projects have an important role to play in preserving architectural ensembles like this. The first part of the adaptive process is to document and understand the original configuration of the building with the aim of maintaining the elements with historical relevance. Therefore, this project proposes the use of a shape grammar approach to analyze floor plans, aiming to further contribute to adaptive reuse projects for ‘Sobrado’ buildings. The process focuses specifically on a case study building and aims to document and identify the specific placement of elements in the floor plan in an effort to provide a deeper understanding of future adaptive reuse.

Structural 3D Domain Reconstruction of the RNA Genome from Viruses with Secondary Structure Models.

Three-dimensional RNA domain reconstruction is important for the assembly, disassembly and delivery functionalities of a packed proteinaceus capsid. However, to date, the self-association of RNA molecules is still an open problem. Recent chemical probing reports provide, with high reliability, the secondary structure of diverse RNA ensembles, such as those of viral genomes. Here, we present a method for reconstructing the complete 3D structure of RNA genomes, which combines a coarse-grained model with a subdomain composition scheme to obtain the entire genome inside proteinaceus capsids based on secondary structures from experimental techniques. Despite the amount of sampling involved in the folded and also unfolded RNA molecules, advanced microscope techniques can provide points of anchoring, which enhance our model to include interactions between capsid pentamers and RNA subdomains. To test our method, we tackle the satellite tobacco mosaic virus (STMV) genome, which has been widely studied by both experimental and computational communities. We provide not only a methodology to structurally analyze the tertiary conformations of the RNA genome inside capsids, but a flexible platform that allows the easy implementation of features/descriptors coming from both theoretical and experimental approaches.

Detecting rotating machinery faults under different working conditions with cross-domain negative correlated ensemble algorithm

When detecting faults of rotating machinery, variation in working conditions leads to the distribution mismatch between training and test data. Thus, the diagnosis accuracy of existing deep learning models deteriorates greatly. To address that, we propose a novel ensemble algorithm. The ensemble algorithm employs deep convolutional extreme learning machine (DCELM) as base learners to learn representative features from time-frequency images. Then, a selection scheme is designed to select diverse base learners which are negatively correlated. Meanwhile, by calculating the correlation term using both the source and the target domain data, the attained ensemble diversity is also valid in target domains. The proposed ensemble algorithm is applied to detect faults of rotating machinery components in three cases. Results show that it attains the best performance on all cross-condition tasks. On average, its accuracy is 1.9% higher than other state-of-the-art ensemble methods and achieves 3.6% enhancement compared with its base learner.

Evolutionary Diversification of Host-Targeted Bartonella Effectors Proteins Derived from a Conserved FicTA Toxin-Antitoxin Module.

Proteins containing a FIC domain catalyze AMPylation and other post-translational modifications (PTMs). In bacteria, they are typically part of FicTA toxin-antitoxin modules that control conserved biochemical processes such as topoisomerase activity, but they have also repeatedly diversified into host-targeted virulence factors. Among these, Bartonella effector proteins (Beps) comprise a particularly diverse ensemble of FIC domains that subvert various host cellular functions. However, no comprehensive comparative analysis has been performed to infer molecular mechanisms underlying the biochemical and functional diversification of FIC domains in the vast Bep family. Here, we used X-ray crystallography, structural modelling, and phylogenetic analyses to unravel the expansion and diversification of Bep repertoires that evolved in parallel in three Bartonella lineages from a single ancestral FicTA toxin-antitoxin module. Our analysis is based on 99 non-redundant Bep sequences and nine crystal structures. Inferred from the conservation of the FIC signature motif that comprises the catalytic histidine and residues involved in substrate binding, about half of them represent AMP transferases. A quarter of Beps show a glutamate in a strategic position in the putative substrate binding pocket that would interfere with triphosphate-nucleotide binding but may allow binding of an AMPylated target for deAMPylation or another substrate to catalyze a distinct PTM. The β-hairpin flap that registers the modifiable target segment to the active site exhibits remarkable structural variability. The corresponding sequences form few well-defined groups that may recognize distinct target proteins. The binding of Beps to promiscuous FicA antitoxins is well conserved, indicating a role of the antitoxin to inhibit enzymatic activity or to serve as a chaperone for the FIC domain before translocation of the Bep into host cells. Taken together, our analysis indicates a remarkable functional plasticity of Beps that is mostly brought about by structural changes in the substrate pocket and the target dock. These findings may guide future structure–function analyses of the highly versatile FIC domains.

Dynamically Adjusting Diversity in Ensembles for the Classification of Data Streams with Concept Drift

A data stream can be defined as a system that continually generates a lot of data over time. Today, processing data streams requires new demands and challenging tasks in the data mining and machine learning areas. Concept Drift is a problem commonly characterized as changes in the distribution of the data within a data stream. The implementation of new methods for dealing with data streams where concept drifts occur requires algorithms that can adapt to several scenarios to improve its performance in the different experimental situations where they are tested. This research proposes a strategy for dynamic parameter adjustment in the presence of concept drifts. Parameter Estimation Procedure (PEP) is a general method proposed for dynamically adjusting parameters which is applied to the diversity parameter (λ) of several classification ensembles commonly used in the area. To this end, the proposed estimation method (PEP) was used to create Boosting-like Online Learning Ensemble with Parameter Estimation (BOLE-PE), Online AdaBoost-based M1 with Parameter Estimation (OABM1-PE), and Oza and Russell’s Online Bagging with Parameter Estimation (OzaBag-PE), based on the existing ensembles BOLE, OABM1, and OzaBag, respectively. To validate them, experiments were performed with artificial and real-world datasets using Hoeffding Tree (HT) as base classifier. The accuracy results were statistically evaluated using a variation of the Friedman test and the Nemenyi post-hoc test. The experimental results showed that the application of the dynamic estimation in the diversity parameter (λ) produced good results in most scenarios, i.e., the modified methods have improved accuracy in the experiments with both artificial and real-world datasets.

Dynamically adaptive and diverse dual ensemble learning approach for handling concept drift in data streams

AbstractConcept drift refers to the change in data distributions and evolving relationships between input and output variables with the passage of time. To analyze such variations in learning environments and generate models which can accommodate changing performance of predictive systems is one of the challenging machine learning applications. In general, the majority of the existing schemes consider one of the specific drift types: gradual, abrupt, recurring, or mixed, with traditional voting setup. In this work, we propose a novel data stream framework, dynamically adaptive and diverse dual ensemble (DA‐DDE) which responds to multiple drift types in the incoming data streams by combining online and block‐based ensemble techniques. In the proposed scheme, a dual diversified ensemble‐based system is constructed with the combination of active and passive ensembles, updated over a diverse set of resampled input space. The adaptive weight setting method is proposed in this work which utilizes the overall performance of learners on historic as well as recent concepts of distributions. Further a dual voting system has been used for hypothesis generation by considering dynamic adaptive credibility of ensembles in real time. Comparative analysis with 14 state‐of‐the‐art algorithms on 24 artificial and 11 real datasets shows that DA‐DDE is highly effective in handling various drift types.

Altered conformation of α-synuclein drives dysfunction of synaptic vesicles in a synaptosomal model of Parkinson's disease.

SUMMARYWhile misfolding of alpha-synuclein (αSyn) is central to the pathogenesis of Parkinson’s disease (PD), fundamental questions about its structure and function at the synapse remain unanswered. We examine synaptosomes from non-transgenic and transgenic mice expressing wild-type human αSyn, the E46K fPD-causing mutation, or an amplified form of E46K (“3K”). Synaptosomes from mice expressing the 3K mutant show reduced Ca2+-dependent vesicle exocytosis, altered synaptic vesicle ultrastructure, decreased SNARE complexes, and abnormal levels of certain synaptic proteins. With our intra-synaptosomal nuclear magnetic resonance (NMR) method, we reveal that WT αSyn participates in heterogeneous interactions with synaptic components dependent on endogenous αSyn and synaptosomal integrity. The 3K mutation markedly alters these interactions. The synaptic microenvironment is necessary for αSyn to reach its native conformations and establish a physiological interaction network. Its inability to populate diverse conformational ensembles likely represents an early step in αSyn dysfunction that contributes to the synaptotoxicity observed in synucleinopathies.

Incremental learning strategies for credit cards fraud detection

Every second, thousands of credit or debit card transactions are processed in financial institutions. This extensive amount of data and its sequential nature make the problem of fraud detection particularly challenging. Most analytical strategies used in production are still based on batch learning, which is inadequate for two reasons: Models quickly become outdated and require sensitive data storage. The evolving nature of bank fraud enshrines the importance of having up-to-date models, and sensitive data retention makes companies vulnerable to infringements of the European General Data Protection Regulation. For these reasons, evaluating incremental learning strategies is recommended. This paper designs and evaluates incremental learning solutions for real-world fraud detection systems. The aim is to demonstrate the competitiveness of incremental learning over conventional batch approaches and, consequently, improve its accuracy employing ensemble learning, diversity and transfer learning. An experimental analysis is conducted on a full-scale case study including five months of e-commerce transactions and made available by our industry partner, Worldline.

ADES: A New Ensemble Diversity-Based Approach for Handling Concept Drift

Beyond applying machine learning predictive models to static tasks, a significant corpus of research exists that applies machine learning predictive models to streaming environments that incur concept drift. With the prevalence of streaming real-world applications that are associated with changes in the underlying data distribution, the need for applications that are capable of adapting to evolving and time-varying dynamic environments can be hardly overstated. Dynamic environments are nonstationary and change with time and the target variables to be predicted by the learning algorithm and often evolve with time, a phenomenon known as concept drift. Most work in handling concept drift focuses on updating the prediction model so that it can recover from concept drift while little effort has been dedicated to the formulation of a learning system that is capable of learning different types of drifting concepts at any time with minimum overheads. This work proposes a novel and evolving data stream classifier called Adaptive Diversified Ensemble Selection Classifier (ADES) that significantly optimizes adaptation to different types of concept drifts at any time and improves convergence to new concepts by exploiting different amounts of ensemble diversity. The ADES algorithm generates diverse base classifiers, thereby optimizing the margin distribution to exploit ensemble diversity to formulate an ensemble classifier that generalizes well to unseen instances and provides fast recovery from different types of concept drift. Empirical experiments conducted on both artificial and real-world data streams demonstrate that ADES can adapt to different types of drifts at any given time. The prediction performance of ADES is compared to three other ensemble classifiers designed to handle concept drift using both artificial and real-world data streams. The comparative evaluation performed demonstrated the ability of ADES to handle different types of concept drifts. The experimental results, including statistical test results, indicate comparable performances with other algorithms designed to handle concept drift and prove their significance and effectiveness.

Adversarial Defence by Diversified Simultaneous Training of Deep Ensembles

Learning-based classifiers are susceptible to adversarial examples. Existing defence methods are mostly devised on individual classifiers. Recent studies showed that it is viable to increase adversarial robustness by promoting diversity over an ensemble of models. In this paper, we propose adversarial defence by encouraging ensemble diversity on learning high-level feature representations and gradient dispersion in simultaneous training of deep ensemble networks. We perform extensive evaluations under white-box and black-box attacks including transferred examples and adaptive attacks. Our approach achieves a significant gain of up to 52% in adversarial robustness, compared with the baseline and the state-of-the-art method on image benchmarks with complex data scenes. The proposed approach complements the defence paradigm of adversarial training, and can further boost the performance. The source code is available at https://github.com/ALIS-Lab/AAAI2021-PDD.

Error-Correcting Output Codes with Ensemble Diversity for Robust Learning in Neural Networks

Though deep learning has been applied successfully in many scenarios, malicious inputs with human-imperceptible perturbations can make it vulnerable in real applications. This paper proposes an error-correcting neural network (ECNN) that combines a set of binary classifiers to combat adversarial examples in the multi-class classification problem. To build an ECNN, we propose to design a code matrix so that the minimum Hamming distance between any two rows (i.e., two codewords) and the minimum shared information distance between any two columns (i.e., two partitions of class labels) are simultaneously maximized. Maximizing row distances can increase the system fault tolerance while maximizing column distances helps increase the diversity between binary classifiers. We propose an end-to-end training method for our ECNN, which allows further improvement of the diversity between binary classifiers. The end-to-end training renders our proposed ECNN different from the traditional error-correcting output code (ECOC) based methods that train binary classifiers independently. ECNN is complementary to other existing defense approaches such as adversarial training and can be applied in conjunction with them. We empirically demonstrate that our proposed ECNN is effective against the state-of-the-art white-box and black-box attacks on several datasets while maintaining good classification accuracy on normal examples.

Toward Multidiversified Ensemble Clustering of High-Dimensional Data: From Subspaces to Metrics and Beyond

The rapid emergence of high-dimensional data in various areas has brought new challenges to current ensemble clustering research. To deal with the curse of dimensionality, recently considerable efforts in ensemble clustering have been made by means of different subspace-based techniques. However, besides the emphasis on subspaces, rather limited attention has been paid to the potential diversity in similarity/dissimilarity metrics. It remains a surprisingly open problem in ensemble clustering how to create and aggregate a large population of diversified metrics, and furthermore, how to jointly investigate the multilevel diversity in the large populations of metrics, subspaces, and clusters in a unified framework. To tackle this problem, this article proposes a novel multidiversified ensemble clustering approach. In particular, we create a large number of diversified metrics by randomizing a scaled exponential similarity kernel, which are then coupled with random subspaces to form a large set of metric-subspace pairs. Based on the similarity matrices derived from these metric-subspace pairs, an ensemble of diversified base clusterings can be thereby constructed. Furthermore, an entropy-based criterion is utilized to explore the cluster wise diversity in ensembles, based on which three specific ensemble clustering algorithms are presented by incorporating three types of consensus functions. Extensive experiments are conducted on 30 high-dimensional datasets, including 18 cancer gene expression datasets and 12 image/speech datasets, which demonstrate the superiority of our algorithms over the state of the art. The source code is available at https://github.com/huangdonghere/MDEC.

Evolutionary Multiobjective Clustering Algorithms With Ensemble for Patient Stratification.

Patient stratification has been studied widely to tackle subtype diagnosis problems for effective treatment. Due to the dimensionality curse and poor interpretability of data, there is always a long-lasting challenge in constructing a stratification model with high diagnostic ability and good generalization. To address these problems, this article proposes two novel evolutionary multiobjective clustering algorithms with ensemble (NSGA-II-ECFE and MOEA/D-ECFE) with four cluster validity indices used as the objective functions. First, an effective ensemble construction method is developed to enrich the ensemble diversity. After that, an ensemble clustering fitness evaluation (ECFE) method is proposed to evaluate the ensembles by measuring the consensus clustering under those four objective functions. To generate the consensus clustering, ECFE exploits the hybrid co-association matrix from the ensembles and then dynamically selects the suitable clustering algorithm on that matrix. Multiple experiments have been conducted to demonstrate the effectiveness of the proposed algorithm in comparison with seven clustering algorithms, twelve ensemble clustering approaches, and two multiobjective clustering algorithms on 55 synthetic datasets and 35 real patient stratification datasets. The experimental results demonstrate the competitive edges of the proposed algorithms over those compared methods. Furthermore, the proposed algorithm is applied to extend its advantages by identifying cancer subtypes from five cancer-related single-cell RNA-seq datasets.

High‐Resolution Numerical Modeling of Barotropic Global Ocean Tides for Satellite Gravimetry

AbstractThe recently upgraded barotropic tidal model TiME is employed to study the influence of fundamental tidal processes, the chosen model resolution, and the bathymetric map on the achievable model accuracy, exemplary for the M2 tide. Additionally, the newly introduced pole‐rotation scheme allows to estimate the model’s inherent precision (open ocean rms: 0.90 cm) and enables studies of the Arctic domain without numerical deviations originating from pole cap handling. We find that the smallest open ocean rms with respect to the FES14‐atlas (3.39 cm) is obtained when tidal dissipation is carried out to similar parts by quadratic bottom friction, wave drag, and parametrized eddy‐viscosity. This setting proves versatile to obtaining high accuracy values for a diverse ensemble of additional partial tides. Using the preferred model settings, we show that for certain minor tides it is possible to obtain solutions that are more accurate than results derived with admittance assumptions from data‐constrained tidal atlases. As linear admittance derived minor tides are routinely used for de‐aliasing of satellite gravimetric data, this opens the potential for improving gravity field products by employing the solutions from TiME.

Diverse Native Ensembles Dictate the Differential Functional Responses of Nuclear Receptor Ligand-Binding Domains.

Native states of folded proteins are characterized by a large ensemble of conformations whose relative populations and interconversion dynamics determine the functional output. This is more apparent in transcription factors that have evolved to be inherently sensitive to small perturbations, thus fine-tuning gene expression. To explore the extent to which such functional features are imprinted on the folding landscape of transcription factor ligand-binding domains (LBDs), we characterize paralogous LBDs of the nuclear receptor (NR) family employing an energetically detailed and ensemble-based Ising-like statistical mechanical model. We find that the native ensembles of the LBDs from glucocorticoid receptor, PPAγ, and thyroid hormone receptor display a remarkable diversity in the width of the native wells, the number and nature of partially structured states, and hence the degree of conformational order. Monte Carlo simulations employing the full state representation of the ensemble highlight that many of the functional conformations coexist in equilibrium, whose relative populations are sensitive to both temperature and the strength of ligand binding. Allosteric modulation of the degree of structure at a coregulator binding site on ligand binding is shown to arise via a redistribution of populations in the native ensembles of glucocorticoid and PPAγ LBDs. Our results illustrate how functional requirements can drive the evolution of conformationally diverse native ensembles in paralogs.

Classification with ensembles and case study on functional magnetic resonance imaging

The ensemble is a technique that strategically combines basic models to achieve better accuracy rates. Diversity, combination methods, and selection topology are the main factors determining ensemble performance. Consequently, it is a challenging task to design an efficient ensemble scheme. Even though numerous paradigms have been proposed to classify ensemble schemes, there is still much room for improvement. This paper proposes a general framework for creating ensembles in the context of classification. Specifically, the ensemble framework consists of four stages: objectives, data preparing, model training, and model testing. It is comprehensive to design diverse ensembles. The proposed ensemble approach can be used for a wide variety of machine learning tasks. We validate our approach on real-world datasets. The experimental results show the efficiency of the proposed approach.

Molecular Basis of Class B GPCR Selectivity for the Neuropeptides PACAP and VIP.

The related neuropeptides PACAP and VIP, and their shared PAC1, VPAC1 and VPAC2 receptors, regulate a large array of physiological activities in the central and peripheral nervous systems. However, the lack of comparative and molecular mechanistic investigations hinder further understanding of their preferred binding selectivity and function. PACAP and VIP have comparable affinity at the VPAC1 and VPAC2 receptor, but PACAP is 400–1,000 fold more potent than VIP at the PAC1 receptor. A molecular understanding of the differing neuropeptide-receptor interactions and the details underlying the receptor transitions leading to receptor activation are much needed for the rational design of selective ligands. To these ends, we have combined structural information and advanced simulation techniques to study PACAP/VIP binding selectivity, full-length receptor conformation ensembles and transitions of the PACAP/VIP receptor variants and subtypes, and a few key interactions in the orthosteric-binding pocket. Our results reveal differential peptide-receptor interactions (at the atomistic detail) important for PAC1, VPAC1 and VPAC2 receptor ligand selectivity. Using microsecond-long molecular dynamics simulations and the Markov State Models, we have also identified diverse receptor conformational ensembles and microstate transition paths for each receptor, the potential mechanisms underlying receptor open and closed states, and the interactions and dynamics at the transmembrane orthosteric pocket for receptor activation. These analyses reveal important features in class B GPCR structure-dynamics-function relationships, which provide novel insights for structure-based drug discovery.

Sensory motor imagery EEG classification based on non-dyadic wavelets using dynamic weighted majority ensemble classification

The classification accuracy has become a significant challenge and an important task in sensory motor imagery (SMI) electroencephalogram (EEG) based Brain Computer interface (BCI) system. This paper compares ensemble classification framework with individual classifiers. The main objective is to reduce the inference of non-stationary and transient information and improves the classification decision in BCI system. The framework comprises the three phases as follows: (1) the EEG signal first decomposes into triadic frequency bands: low pass band, band pass filter and high pass filter to localize α, β and high γ frequency bands within the EEG signals, (2) Then, Common spatial pattern (CSP) algorithm has been applied on the extracted frequencies in phase I to heave out the important features of EEG signal, (3) Further, an existing Dynamic Weighted Majiority (DWM) ensemble classification algorithm has been implemented using features extracted in phase II, for final class label decision. J48, Naive Bayes, Support Vector Machine, and K-Nearest Neighbor classifiers used as base classifiers for making a diverse ensemble of classifiers. A comparative study between individual classifiers and ensemble framework has been included in the paper. Experimental evaluation and assessment of the performance of the proposed model is done on the publically available datasets: BCI Competition IV dataset IIa and BCI Competition III dataset IVa. The ensemble based learning method gave the highest accuracy among all. The average sensitivity, specificity, and accuracy of 85.4%, 86.5%, and 85.6% were achieved with a kappa value of 0.59 using DWM classification.

An Inception Convolutional Autoencoder Model for Chinese Healthcare Question Clustering.

Healthcare question answering (HQA) system plays a vital role in encouraging patients to inquire for professional consultation. However, there are some challenging factors in learning and representing the question corpus of HQA datasets, such as high dimensionality, sparseness, noise, nonprofessional expression, etc. To address these issues, we propose an inception convolutional autoencoder model for Chinese healthcare question clustering (ICAHC). First, we select a set of kernels with different sizes using convolutional autoencoder networks to explore both the diversity and quality in the clustering ensemble. Thus, these kernels encourage to capture diverse representations. Second, we design four ensemble operators to merge representations based on whether they are independent, and input them into the encoder using different skip connections. Third, it maps features from the encoder into a lower-dimensional space, followed by clustering. We conduct comparative experiments against other clustering algorithms on a Chinese healthcare dataset. Experimental results show the effectiveness of ICAHC in discovering better clustering solutions. The results can be used in the prediction of patients' conditions and the development of an automatic HQA system.