On-demand tunable metamaterials design for noise attenuation with machine learning

Microfluidics has achieved a paradigm-shifting advancement in life sciences, automation, thermal management, and various other engineering streams. In recent years, a considerable amount of research has been conducted on the use of microfluidics in designing novel systems and fabricating next-generation smart materials that are capable of outperforming historical barriers and achieving unprecedented qualities. One such innovative development is the integration of fluidics into building artificially structured smart materials called acoustic metamaterials to achieve active tunability for a real-time controllable manipulation of acoustic waves. Leveraging the capability of microfluidics to automate the manipulation of liquid droplets, fluid streams, or bubbles in a required arrangement has revolutionised the development of actively tunable fluidics-integrated acoustic metamaterials for widescale applications. This review first discusses the prominent microfluidic actuation mechanisms used in the literature to develop fluidics-integrated smart acoustic metamaterials, and then it details integrated metamaterial design and extraordinary applications such as active acoustic wave manipulation or building tunable acoustic holograms etc. The following review concludes by providing the importance and future perspective of integrating microfluidic techniques with novel metamaterial designs, paving the way for innovative futuristic applications.

This comprehensive review explores the design and applications of machine learning (ML) techniques to acoustic metamaterials (AMs) and phononic crystals (PnCs), with a particular focus on deep learning (DL). AMs and PnCs, characterized by artificially designed microstructures and geometries, offer unique acoustic properties for precise control and manipulation of sound waves. ML, including DL, in combination with traditional artificial design have promoted the design process, enabling data-driven approaches for feature identification, design optimization, and intelligent parameter search. ML algorithms process extensive AM data to discover novel structures and properties, enhancing overall acoustic performance. This review presents an in-depth exploration of applications associated with ML techniques in AMs and PnCs, highlighting specific advantages, challenges and potential solutions of applying of using ML algorithms associated with ML techniques. By bridging acoustic engineering and ML, this review paves the way for future breakthroughs in acoustic research and engineering.

There has been an explosion of interest in acoustic metamaterial in the last ten years. The tunable negative acoustic metamaterial is an important issue for designing metamaterials. The acoustic metamaterial is restricted by the narrow bandgap of sound waves for the local resonance of metamaterial unit cells. By shifting the sizes of the unit cell, the acoustic metamaterial could potentially overcome the limit of the narrow resonance frequency. In this research, we focus on the resonant behavior of split hollow sphere (SHS) in the waveguide. Firstly, we analyze the resonance characteristics of SHS and get an analytical formula for the effect of geometrical parameters on the resonance frequency. Furthermore, the resonance frequency of SHS is verified with finite-element method analysis based on COMSOL Multiphysics simulation. The results are in good agreement with theory model. It is observed that there is a blue shift of the resonance frequency with the gradual increase of the neck radius of SHS, a V-type response curve with the increase of inner radius of SHS, and a red shift with the increase of outer radius of SHS. Using the method of estimate of resonance, we could get a precisely controllable unit structure with negative effective modulus and offer a way to optimize the realization of double negative acoustic metamaterial.

Artificial intelligence has been applied in wildfire science and management since the 1990s, with early applications including neural networks and expert systems. Since then, the field has rapidly progressed congruently with the wide adoption of machine learning (ML) methods in the environmental sciences. Here, we present a scoping review of ML applications in wildfire science and management. Our overall objective is to improve awareness of ML methods among wildfire researchers and managers, as well as illustrate the diverse and challenging range of problems in wildfire science available to ML data scientists. To that end, we first present an overview of popular ML approaches used in wildfire science to date and then review the use of ML in wildfire science as broadly categorized into six problem domains, including (i) fuels characterization, fire detection, and mapping; (ii) fire weather and climate change; (iii) fire occurrence, susceptibility, and risk; (iv) fire behavior prediction; (v) fire effects; and (vi) fire management. Furthermore, we discuss the advantages and limitations of various ML approaches relating to data size, computational requirements, generalizability, and interpretability, as well as identify opportunities for future advances in the science and management of wildfires within a data science context. In total, to the end of 2019, we identified 300 relevant publications in which the most frequently used ML methods across problem domains included random forests, MaxEnt, artificial neural networks, decision trees, support vector machines, and genetic algorithms. As such, there exists opportunities to apply more current ML methods — including deep learning and agent-based learning — in the wildfire sciences, especially in instances involving very large multivariate datasets. We must recognize, however, that despite the ability of ML models to learn on their own, expertise in wildfire science is necessary to ensure realistic modelling of fire processes across multiple scales, while the complexity of some ML methods such as deep learning requires a dedicated and sophisticated knowledge of their application. Finally, we stress that the wildfire research and management communities play an active role in providing relevant, high-quality, and freely available wildfire data for use by practitioners of ML methods.

Acoustic metamaterials (AMs) have attracted a substantial amount of attention in recent decades where the parameter design plays an important role. However, conventional design methods generally rely on analytical physical models and require a very large number of evaluations of acoustic performance. Here, we propose and experimentally demonstrate an inverse-design method for AMs based on machine learning using a Gauss–Bayesian model. As a result of the cycle of training and prediction and the use of adaptive acquisition functions, this method allows the parameters of AMs to be efficiently designed for specific functionalities without the need for physical models. Considering the significance of low-frequency ventilated sound absorption, we present a design for a typical acoustic metamaterial absorber with multiple structural parameters that facilitate high sound absorption at low frequencies. In the design process, the parameters were adaptively adjusted to improve the sound absorption performance at low frequencies using only 37 evaluations, and this high absorption performance was verified by the agreement of numerical and experimental results. Because of its low cost, high flexibility, and independence from physical models, this method paves the way for tremendous opportunities in the design of various AMs for particular desired functionalities.

Parameter importance assessment improves efficacy of machine learning methods for predicting snow avalanche sites in Leh-Manali Highway, India

The review focuses on architected acoustic metamaterials to manipulate airborne sound waves, with only limited discussions on elastic metamaterials related to solid media. We review the design of acoustic metamaterials and the physical mechanisms underpinning their performance and related manufacturing methodologies, while also examining potential issues and challenges affecting the use of metamaterials in acoustics. The complexities of several metamaterial architectures are discussed. A new classification system is proposed to distinguish metamaterial configurations based on the typology of the channels inside the acoustic meta-atom. Several types of acoustic metamaterials architectures, such as perforated and micro-perforated panels, acoustic foams, resonators, various geometrical paths, and piezoelectric patches, are also discussed. The fundamental acoustic mechanisms of these classes of metamaterials are identified and commented on. The paper also describes the main measurement techniques used for acoustic metamaterials and the physical quantities evaluated, providing a guide to characterize and assess their performance. The fundamental challenges of the current metamaterials designs are discussed, with a focus on the complex synergy between architectural patterns of acoustic metamaterials and their thickness. We clarify the distinction between acoustic and elastic metamaterials, emphasizing the design and applications of materials that manipulate sound waves in fluid media. The paper also offers further comments about the need for practical design tools to allow the use of acoustic metamaterials in real-world applications.

Machine learning (ML) methods are attracting considerable attention among academics in the field of finance. However, it is commonly believed that ML has not transformed the asset management industry to the same extent as other sectors. This survey focuses on the ML methods and empirical results available in the literature that matter most for active portfolio management. ML has asset management applications for signal generation, portfolio construction, and trade execution, and promising findings have been reported. Reinforcement learning (RL), in particular, is expected to play a more significant role in the industry. Nevertheless, the performance of a sample of active exchange-traded funds (ETF) that use ML in their investments tends to be mixed. Overall, ML techniques show great promise for active portfolio management, but investors should be cautioned against their main potential pitfalls. 
\n
\n

Formal Concept Analysis (FCA) is emerging in Data Science because of its generality, simplicity, and powerful mathematical foundation. It enabled a uniform data clustering methods into structured space of formal concepts. Several FCA based machine learning (ML) methods gave competitive results compared to classical methods. In another side, ensemble approach proved to be effective by aggregating different basic ML methods. Randomness improved other ML approaches. In this paper, we propose a new conceptual ML method by using random conceptual decomposition. This method integrated and experimented in the context of ensemble learning methods, gave encouraging good results, in general.

Developing Theory Using Machine Learning Methods

How Magic a Bullet Is Machine Learning for Credit Analysis? An Exploration with FinTech Lending Data

P125. Development of a novel ensemble machine learning algorithm for prediction of complications and readmission after anterior cervical spinal fusion

Machine learning guided design of functional materials with targeted properties

A dose deposition matrix (DDM) prediction method using several voxel features and a machine learning (ML) approach is proposed for plan optimization in radiation therapy. Head and lung cases with the inhomogeneous medium are used as training and testing data. The prediction model is a cascade forward backprop neural network where the input is the features of the voxel, including 1) voxel to body surface distance along the beamlet axis, 2) voxel to beamlet axis distance, 3) voxel density, 4) heterogeneity corrected voxel to body surface distance, 5) heterogeneity corrected voxel to beamlet axis, and (6) the dose of voxel obtained from the pencil beam (PB) algorithm. The output is the predicted voxel dose corresponding to a beamlet. The predicted DDM was used for plan optimization (ML method) and compared with the dose of MC-based plan optimization (MC method) and the dose of pencil beam-based plan optimization (PB method). The mean absolute error (MAE) value was calculated for full volume relative to the dose of the MC method to evaluate the overall dose performance of the final plan. For patient with head tumor, the ML method achieves MAE value 0.49 × 10-4 and PB has MAE 1.86 × 10-4. For patient with lung tumor, the ML method has MAE 1.42 × 10-4 and PB has MAE 3.72 × 10-4. The maximum percentage difference in PTV dose coverage (D98) between ML and MC methods is no more than 1.2% for patient with head tumor, while the difference is larger than 10% using the PB method. For patient with lung tumor, the maximum percentage difference in PTV dose coverage (D98) between ML and MC methods is no more than 2.1%, while the difference is larger than 16% using the PB method. In this work, a reliable DDM prediction method is established for plan optimization by applying several voxel features and the ML approach. The results show that the ML method based on voxel features can obtain plans comparable to the MC method and is better than the PB method in achieving accurate dose to the patient, which is helpful for rapid plan optimization and accurate dose calculation. Establishment of a new machine learning method based on the relationship between the voxel and beamlet features for dose deposition matrix prediction in radiation therapy.

PurposeInjuries are common in sports and can have significant physical, psychological and financial consequences. Machine learning (ML) methods could be used to improve injury prediction and allow proper approaches to injury prevention. The aim of our study was therefore to perform a systematic review of ML methods in sport injury prediction and prevention.MethodsA search of the PubMed database was performed on March 24th 2020. Eligible articles included original studies investigating the role of ML for sport injury prediction and prevention. Two independent reviewers screened articles, assessed eligibility, risk of bias and extracted data. Methodological quality and risk of bias were determined by the Newcastle–Ottawa Scale. Study quality was evaluated using the GRADE working group methodology.ResultsEleven out of 249 studies met inclusion/exclusion criteria. Different ML methods were used (tree-based ensemble methods (n = 9), Support Vector Machines (n = 4), Artificial Neural Networks (n = 2)). The classification methods were facilitated by preprocessing steps (n = 5) and optimized using over- and undersampling methods (n = 6), hyperparameter tuning (n = 4), feature selection (n = 3) and dimensionality reduction (n = 1). Injury predictive performance ranged from poor (Accuracy = 52%, AUC = 0.52) to strong (AUC = 0.87, f1-score = 85%). ConclusionsCurrent ML methods can be used to identify athletes at high injury risk and be helpful to detect the most important injury risk factors. Methodological quality of the analyses was sufficient in general, but could be further improved. More effort should be put in the interpretation of the ML models.