Template-based Methods Research Articles

3D Continuously Porous Graphene for Energy Applications.

Constructing bulk graphene materials with well-reserved 2D properties is essential for device and engineering applications of atomically thick graphene. In this article, the recent progress in the fabrications and applications of sterically continuous porous graphene with designable microstructures, chemistries, and properties for energy storage and conversion are reviewed. Both template-based and template-free methods have been developed to synthesize the 3D continuously porous graphene, which typically has the microstructure reminiscent of pseudo-periodic minimal surfaces. The 3D graphene can well preserve the properties of 2D graphene of being highly conductive, surface abundant, and mechanically robust, together with unique 2D electronic behaviors. Additionally, the bicontinuous porosity and large curvature offer new functionalities, such as rapid mass transport, ample open space, mechanical flexibility, and tunable electric/thermal conductivity. Particularly, the 3D curvature provides a new degree of freedom for tailoring the catalysis and transport properties of graphene. The 3D graphene with those extraordinary properties has shown great promises for a wide range of applications, especially for energy conversion and storage. This article overviews the recent advances made in addressing the challenges of developing 3D continuously porous graphene, the benefits and opportunities of the new materials for energy-related applications, and the remaining challenges that warrant future study.

How myocardial work could be relevant in patients with an aortic valve stenosis?

Abstract Funding Acknowledgements Type of funding sources: None. Background Speckle tracking based myocardial work calculation is an attractive method to assess left ventricular (LV) myocardial function. In case of aortic stenosis (AS), assessment of work indices is challenging because it requires an accurate evaluation of LV-pressure curves. Therefore, we sought to evaluate the performances of two distinct methods for the estimation of myocardial work indices and to provide a quantitative comparison with invasively measured data. Methods Model-based and template-based methods were defined and applied for the evaluation of LV pressures on 67 AS patients. Global Constructive (GCW), Wasted (GWW), Positive (GPW), Negative (GNW) myocardial work and Global Work Efficiency (GWE) and Index (GWI) parameters were calculated using the available software computing the indices using brachial blood pressure and trans-aortic mean pressure gradient for estimating the LV pressures versus using a model-based and homemade software. A complete comparison was performed with invasive measurements. Results Patients were characterized by mean pressure gradient of 49.8 ± 14.8 mmHg, LV ejection fraction of 59 ± 8%, the global longitudinal strain was -15.0 ± 4.04%, GCW was 2107 ± 800mmHg.% (model-based method) and 2483 ± 1068mmHg.% (template-based method). The root mean square error (RMSE) and correlation were calculated for each patient and for each pressure estimation methods. The mean RMSE are 33.9mmHg and 40.4mmHg and the mean correlation coefficients are 0.81 and 0.72 for the model-based and template-based methods respectively. Correlation coefficient and Bland-Altman analysis were performed for the six work indices. The two methods present correlation coefficient r2 > 0.75 for almost all the indices. Conclusion The two non-invasive methods of LV pressure estimation and the work indices computation correlate with invasive measurements and computations for AS patients. Although the model-based approach requires less information and is associated with slightly better performances, the implementation of template-based method is easier and seems more appropriate in a clinical practice. Abstract Figure. SUMMARY

High Aspect Ratio Au Microflakes via Gap-Assisted Synthesis

Ultrathin and extra-large single-crystalline Au microflakes (Au MFs) have a huge potential in applications ranging from nanophotonics to catalysis. Yet, wet chemical synthesis approaches cannot access this size range due to the proportionality between growth time, thickness, and lateral size. Concurrently, complexity and small MF areas restrict the use of 2D template-based methods. In all cases, subsequent transfer to a substrate remains challenging. Here, we demonstrate a facile, gap-assisted synthesis method that enables on-substrate growth of ultrathin and extra-large Au MFs. In particular, using a 43 μm gap-size between two glass substrates and leveraging the directed-growth effect of halide ions, we achieve a high yield (∼90%) of Au MFs on glass with lateral sizes as high as 0.25 mm and thicknesses as low as 10 nm. Interestingly, for up to 25 h growth time, we observe a time-independent, ultralow average thickness of just 21 nm. A parametric synthesis study and an in-depth material characterization provide mechanistic insights into this extreme 2D growth mode. Overall, our gap-assisted approach greatly enhances the halide effect and results in a record-high aspect ratio of ∼104. It thus opens new opportunities for on-substrate anisotropic growth strategies that would benefit emerging optoelectronic and photoelectrochemical devices.

Model-driven automatic target recognition of sar images with part-level reasoning

A synthetic aperture radar (SAR) automatic target recognition (ATR) method is proposed based on 3-D scattering center model with part-level reasoning. The scattering centers in the 3-D scattering center model built offline are matched to the test image by a region-to-region matching algorithm at first. Then, a preliminary similarity is defined, in which all the model scattering centers are equally treated. Based on the spatial and physical attributes of the model scattering centers, a spatially constrained similarity and a physically constrained similarity are designed. The three similarities work separately for target recognition and the decision with the highest reliability is adopted. The final decision not only determines the target type but also reflects the possible operating conditions (OCs) of the target such as partial occlusion or articulation, etc. Extensive experiments on the simulated SAR images by electromagnetic (EM) code and measured Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset demonstrate the superior effectiveness and robustness of the proposed method under both standard operating condition (SOC) and several typical extended operating conditions (EOC) compared with several existing template-based and model-based methods.

RC Parasitic-Aware Layout Analysis and Routing Optimization Methodology

A parasitic-aware routing optimization and analysis methodology for integrated circuits is developed based on an incremental parasitic extraction and a fast optimization methodology. Existing routing optimization methodologies rely on many circuit simulations, detailed sensitivity analysis, and inefficient simple parasitic models to optimize routes. Moreover, they do not provide a mechanism to help layout designers in identifying problematic layout geometries that have a bad impact on a route’s performance. The proposed methodology works on overcoming such problems by providing three features. First, it provides novel sensitivity circuit models to analyze the integrity of signals in layout routes. Such circuit models are based on an accurate matrix circuit representation, a cost function, and an accurate parasitic sensitivity extraction. The circuit models identify critical parasitic elements along with the corresponding layout geometries in a certain route, where they measure the sensitivity of a route’s performance to corresponding layout geometries very fast. Therefore, they can correlate the problems of a route’s performance to specific layout geometries. Second, the proposed methodology uses a nonlinear programming technique to optimize problematic routes with pre-determined degrees of freedom using the proposed circuit models. Third, the proposed methodology uses a novel incremental parasitic extraction method to extract parasitic elements of modified geometries efficiently. The incremental extraction is used as a part of the routing optimization process to improve the optimization runtime and increase the optimization accuracy. The proposed methodology is tested over different designs of 7nm and 65nm process nodes. The results show that the proposed methodology managed to identify and optimize the problematic geometries in critical routes efficiently with up to 10% performance improvements and a speedup of 3 to 9X as compared to traditional template-based methods.

Evaluating the Performance of Machine Learning Algorithms in Gaze Gesture Recognition Systems

Despite the utility of gaze gestures as an input method, there is a lack of guidelines available regarding how to design gaze gestures, what algorithms to use for gaze gesture recognition, and how these algorithms compare in terms of performance. To facilitate the development of applications that leverage gaze gestures, we have evaluated the performance of a combination of template-based and data-driven algorithms on two custom gesture sets that can map to user actions. Template-based algorithms had consistently high accuracies but the slowest runtimes, making them best for small gesture sets or accuracy-critical applications. Data-driven algorithms run much faster and scale better to larger gesture sets, but require more training data to achieve the accuracy of the template-based methods. The main takeaways for gesture set design are 1) gestures should have distinct forms even when performed imprecisely and 2) gestures should have clear key-points for the eyes to fixate onto.

Microstructure evolutions in lithium ion battery electrode manufacturing

<p indent="0mm">Since its commercialization in the 1990s, the lithium-ion battery has been a huge success in the energy industry owing to its high energy density and long cycle life. They have been used in national strategic fields, such as satellites and unmanned aircraft, to promote a remarkable leap forward in new energy, new energy vehicles, and other emerging industries. Therefore, the development of lithium-ion batteries is a strategic high ground for competition among countries worldwide. The development and widespread use of lithium-ion batteries is driven by their high energy/power density, long cycle life, and low cost, which requires battery material innovation as well as advancements in manufacturing processes and equipment technology. Particularly, the power and energy storage applications require numbers of battery cells connected in series or parallel. High precision is required to ensure the consistency of the battery cell, to avoid module capacity loss and cycle life attenuation owing to the “shortboard effect,” and to ensure battery safety. Electrode manufacturing, which is the first critical process of lithium-ion battery production, consists of three critical steps: Mixing, coating, and rolling. The positive and negative electrode active materials, conductive agents, binders and solvents are mixed into slurry and coated on copper or aluminum foil. The positive/negative electrodes, which constitute the electrochemical reaction carrier and the battery’s core, are obtained after drying and roller compaction. The porous and multi-component electrode microstructure evolves and is constructed in a complex way during electrode manufacturing. The proportion of electrode slurry, mixing order, coating method, drying strategy, and rolling process can considerably affect the evolution of electrode microstructure, such as pore structure, active particle distribution and, conductive/bonding network. It also influences the lithium-ion battery’s electrochemical performance. Despite tremendous advances in high-energy-density materials, research on lithium-ion battery manufacturing lags, resulting in a large gap between laboratory and production scales. This requires an in-depth understanding of the manufacturing and the relationship between electrode microstructure evolution and battery performance. The advancement and application of cutting-edge slurry mixing, coating, and calendering technologies in electrode manufacturing are thoroughly reviewed in this paper. The evolution of electrode microstructure during manufacturing, in particular, and its impact on the battery’s electrochemical performance, are discussed in detail. Then, various novel electrode manufacturing techniques are summarized in terms of their significance and challenges, covering the innovations based on the current process (aqueous processing, simultaneous double-sided slot coating, multilayer co-coating and, multistage drying), dry processing (electron beam and ultraviolet curing forming, electrostatic dry-powder coating), three-dimensional printing, and template-based methods. We aim to gain a better understanding of electrode structure design, material preparation, and manufacturing processes through the perspective of the “Manufacturing-Microstructure-Performances” relationship and guide the development of high-performance lithium-ion batteries. Finally, perspectives on future developments toward accelerating electrode design and manufacturing process optimization are presented, including three main parts: (1) Developing the multiscale and whole-process simulation platform to connect the electrode manufacturing, microstructure, and battery performance; (2) constructing microstructure-controllable electrode manufacturing technology that is compatible with existing production infrastructure; and (3) researching the microstructure evolution of the post-lithium-ion battery manufacturing.

Reconstruction of three-dimensional lumbar vertebrae from biplanar x-rays

Objective. Vertebrae models from computer tomographic (CT) imaging are extensively used in image-guided surgical systems to deliver percutaneous orthopaedic operations with minimum risks, but patients may be exposed to excess radiation from the pre-operative CT scans. Generating vertebrae models from intra-operative x-rays for image-guided systems can reduce radiation exposure to the patient, and the surgeons can acquire the vertebrae’s relative positions during the operation; therefore, we proposed a lumbar vertebrae reconstruction method from biplanar x-rays. Approach. Non-stereo-corresponding vertebral landmarks on x-rays were identified as targets for deforming a set of template vertebrae; the deformation was formulated as a minimisation problem, and was solved using the augmented Lagrangian method. Mean surface errors between the models reconstructed using the proposed method and CT scans were measured to evaluate the reconstruction accuracy. Main results. The evaluation yielded mean errors of 1.27 mm and 1.50 mm in in vitro experiments on normal vertebrae and pathological vertebrae, respectively; the outcomes were comparable to other template-based methods. Significance. The proposed method is a viable alternative to provide digital lumbar to be used in image-guided systems, where the models can be used as a visual reference in surgical planning and image-guided applications in operations where the reconstruction error is within the allowable surgical error.

Facile fabrication of microporous vitreous carbon for oil/organic solvent absorption

The release of oils/organic solvents into a water body is a serious issue as oils and solvents can adversely affect the environment. In this study, a simple fabrication method of porous vitreous carbon oil/organic solvent absorber was developed, and it shows 7 times higher performance than other activated carbon absorber. Three-dimensional interconnected porous vitreous carbon (VC) has been demonstrated for cleaning spilled oils/organic solvents. The porous VC absorbent was fabricated by carbonizing a porous furan precursor, which was prepared by utilizing organic furan resin and table sugar as template materials. Unlike other template-based methods, no template dissolution processes are required in this study. The carbon content in the fabricated porous VC was 91.6%, as confirmed by X-ray photoelectron spectroscopy. The fabricated porous VC exhibited over-hydrophobic characteristics with a static contact angle of 135.1°, and showed high absorption capacity for a wide range of oils/organic solvents. The absorption capacity ranged from 186% to 290% depending on the viscosity, density, and surface tension of the oils/organic solvents. In the reusability experiment, no significant discrepancies were observed in the absorption capacity even after seven cycles. • A new, promising and bio-inspired porous carbon absorbent material was developed. • Porous carbon was fabricated in a low-cost and scalable manner from furan resin. • Intake capacity was seven times higher than other activated carbon-based absorbents. • Releasing of oils/organic solvents in acetone for fast and complete removal.

A Survey on Various Deep Learning Models for Automatic Image Captioning

Automatic Image captioning means the generation of a caption for an image by a machine. Image captioning is performed by recognizing objects, attributes and interconnection between them. This task involves computer vision for image understanding, natural language processing for syntax and semantics purpose and machine learning for caption generation. Preferably CNN is used to understand features of an image and RNN is used for sentence generation. Earlier, Machine learning approach was used for this purpose. Input data is used to extract the features in traditional machine learning. Extracting features like handcrafted from large dataset is not so easy and feasible. Later on, Various deep learning-based approaches were proposed. In deep learning, retrieval based and template-based methods were proposed but faced some issues like missing important objects and fixed length caption respectively. Then end to end learning approach based on deep learning network came into existence and image captioning task became more efficient. The objective of this paper is to study and compare various end to end learning-based framework for image captioning using standard evaluation metric and to understand how can these frameworks be used for various research applications. Along with the comparison, futuristic challenges have also been discussed.

MULTICOM2 open-source protein structure prediction system powered by deep learning and distance prediction

Protein structure prediction is an important problem in bioinformatics and has been studied for decades. However, there are still few open-source comprehensive protein structure prediction packages publicly available in the field. In this paper, we present our latest open-source protein tertiary structure prediction system—MULTICOM2, an integration of template-based modeling (TBM) and template-free modeling (FM) methods. The template-based modeling uses sequence alignment tools with deep multiple sequence alignments to search for structural templates, which are much faster and more accurate than MULTICOM1. The template-free (ab initio or de novo) modeling uses the inter-residue distances predicted by DeepDist to reconstruct tertiary structure models without using any known structure as template. In the blind CASP14 experiment, the average TM-score of the models predicted by our server predictor based on the MULTICOM2 system is 0.720 for 58 TBM (regular) domains and 0.514 for 38 FM and FM/TBM (hard) domains, indicating that MULTICOM2 is capable of predicting good tertiary structures across the board. It can predict the correct fold for 76 CASP14 domains (95% regular domains and 55% hard domains) if only one prediction is made for a domain. The success rate is increased to 3% for both regular and hard domains if five predictions are made per domain. Moreover, the prediction accuracy of the pure template-free structure modeling method on both TBM and FM targets is very close to the combination of template-based and template-free modeling methods. This demonstrates that the distance-based template-free modeling method powered by deep learning can largely replace the traditional template-based modeling method even on TBM targets that TBM methods used to dominate and therefore provides a uniform structure modeling approach to any protein. Finally, on the 38 CASP14 FM and FM/TBM hard domains, MULTICOM2 server predictors (MULTICOM-HYBRID, MULTICOM-DEEP, MULTICOM-DIST) were ranked among the top 20 automated server predictors in the CASP14 experiment. After combining multiple predictors from the same research group as one entry, MULTICOM-HYBRID was ranked no. 5. The source code of MULTICOM2 is freely available at https://github.com/multicom-toolbox/multicom/tree/multicom_v2.0.

Nanoarchitectured Porous Conducting Polymers: From Controlled Synthesis to Advanced Applications.

Conductive polymers (CPs) integrate the inherent characteristics of conventional polymers and the unique electrical properties of metals. They have aroused tremendous interest over the last decade owing to their high conductivity, robust and flexible properties, facile fabrication, and cost-effectiveness. Compared to bulk CPs, porous CPs with well-defined nano- or microstructures possess open porous architectures, high specific surface areas, more exposed reactive sites, and remarkably enhanced activities. These attractive features have led to their applications in sensors, energy storage and conversion devices, biomedical devices, and so on. In this review article, the different strategies for synthesizing porous CPs, including template-free and template-based methods, are summarized, and the importance of tuning the morphology and pore structure of porous CPs to optimize their functional performance is highlighted. Moreover, their representative applications (energy storage devices, sensors, biomedical devices, etc.) are also discussed. The review is concluded by discussing the current challenges and future developmenttrendinthisfield.

Feature extraction for chart pattern classification in financial time series

Extracting shape-related features from a given query subsequence is a crucial preprocessing step for chart pattern matching in rule-based, template-based and hybrid pattern classification methods. The extracted features can significantly influence the accuracy of pattern recognition tasks during the data mining process. Although shape-related features are widely used for chart pattern matching in financial time series, the intrinsic properties of these features and their relationships to the patterns are rarely investigated in research community. This paper aims to formally identify shape-related features used in chart patterns and investigates their impact on chart pattern classifications in financial time series. In this paper, we describe a comprehensive analysis of 14 shape-related features which can be used to classify 41 known chart patterns in technical analysis domain. In order to evaluate their effectiveness, shape-related features are then translated into rules for chart pattern classification. We perform extensive experiments on real datasets containing historical price data of 24 stocks/indices to analyze the effectiveness of the rules. Experimental results reveal that the features put forward in this paper can be effectively used for recognizing chart patterns in financial time series. Our analysis also reveals that high-level features can be hierarchically composed from low-level features. Hierarchical composition allows construction of complex chart patterns from features identified in this paper. We hope that the features identified in this paper can be used as a reference model for the future research in chart pattern analysis.

Scalable Manufacture of High-Performance Battery Electrodes Enabled by a Template-Free Method.

Ion transport kinetics is identified as the major challenge of thick electrode design for high-energy-density lithium-ion batteries. The introduction of vertically-oriented structure pores, which provide fast transport pathways for Li+ , can maximize the rate-performance of electrodes while holding a high energy density. To overcome the harsh manufacturing requirements of traditional template-based methods for the oriented-pore electrodes, a template-free strategy is developed to meet the large-scale fabrication demand, in which controllable oriented microchannels are facilely constructed by vertically aggregated bubbles generated from thermal decomposition. The proposed method is demonstrated to be applicable for different active materials and compatible with industrial roll-to-roll manufacturing. The oriented-pore electrodes exhibit a seven times higher capacity at 5C rate and show double the power density relative to the state of the art while maintaining a high level of energy density. The balance between the ion transport kinetics through the channels and in the matrix manifests an optimal design of the electrode structures, enabling the desired superior performance of the electrodes toward practical applications.

Deep Learning-Based Automated Extraction of Anthropometric Measurements From a Single 3-D Scan

The appearance of 3-D scanners, generating point clouds, has revolutionized anthropometric data collection systems and their applications. Anthropometric data are of paramount importance in several applications, including fashion design, medical diagnosis, and virtual character modeling, all of which require a fully automatic anthropometric measurement extraction method. 3-D-based methods for anthropometric measurement extraction becomes more and more popular due to their improved accuracy compared to classical image-based approaches. Existing 3-D methods can be mainly classified into two categories: landmark and template-based methods. The former is highly dependent on the estimated landmarks which are highly sensitive to noise in the input or missing data. The latter has to iteratively solve an objective function to deform a body template to fit the scan, which is time-consuming while being also sensitive to noise and missing data. In this study, we propose the first approach for automatic contact-less anthropometric measurements extraction based on deep-learning (AM-DL). A novel module dubbed multiscale EdgeConv is proposed to learn local features from point clouds at multiple scales. Multiscale EdgeConv can be directly integrated with other neural networks for various tasks, e.g., classification of point clouds. We exploit this module to design an encoder–decoder architecture that learns to deform a template model to fit a given scan. The measurement values are then calculated on the deformed template model. To evaluate the proposed method, 27 female and 25 male subjects were scanned using a photogrametry-based scanner and measured by an experienced tailor. Experimental results on the synthetic ModelNet40 dataset and on the real scans demonstrate that the proposed method outperforms state-of-the-art methods, and performs sufficiently close to a professional tailor.

Computer-aided design-CAM-guided endodontic microsurgical localization and retrieval of two separated instruments from the periapical area of a mandibular second molar

Three-dimensional (3D) imaging devices used for the visualization of anatomic structures not only allow for a more accurate diagnosis but also facilitate precise planning of surgical treatments, such as in guided surgery for instrument retrieval using templates. The innovative template-based treatment methods could also play a crucial role in future modern surgical endodontic treatments, enabling exact preplanning and precision-guided surgical interventions, and resulting in greater accuracy and success rates. We present here a case of a patient with a periapical lesion below a right mandibular second molar, with a fractured file segment extruding beyond the apex in the distal canal, and another instrument half-way extruded from the mesial canal, with radiolucencies evident at the mesial and distal root apices. The patient was treated by employing a 3D-guided microsurgical approach. First, 3D optical scans were imported into a guided surgery program. Periapical lesions and extruded fractured instruments were marked within the software. The osteotomy size, apical resection level, and bevel angle were defined pretreatment. This case introduces a novel-guided microsurgical endodontic technique, incorporating recommended guidelines of modern surgical endodontic treatment with the aid of 3D-printed surgical templates, by which minimally invasive surgical treatment was ensured with preservation of tooth, bone, and surrounding anatomical structures.

Ischemic infarct detection, localization, and segmentation in noncontrast CT human brain scans: review of automated methods

Noncontrast Computed Tomography (NCCT) of the brain has been the first-line diagnosis for emergency evaluation of acute stroke, so a rapid and automated detection, localization, and/or segmentation of ischemic lesions is of great importance. We provide the state-of-the-art review of methods for automated detection, localization, and/or segmentation of ischemic lesions on NCCT in human brain scans along with their comparison, evaluation, and classification. Twenty-two methods are (1) reviewed and evaluated; (2) grouped into image processing and analysis-based methods (11 methods), brain atlas-based methods (two methods), intensity template-based methods (1 method), Stroke Imaging Marker-based methods (two methods), and Artificial Intelligence-based methods (six methods); and (3) properties of these groups of methods are characterized. A new method classification scheme is proposed as a 2 × 2 matrix with local versus global processing and analysis, and density versus spatial sampling. Future studies are necessary to develop more efficient methods directed toward deep learning methods as well as combining the global methods with a high sampling both in space and density for the merged radiologic and neurologic data.

Template-based prediction of protein structure with deep learning

BackgroundAccurate prediction of protein structure is fundamentally important to understand biological function of proteins. Template-based modeling, including protein threading and homology modeling, is a popular method for protein tertiary structure prediction. However, accurate template-query alignment and template selection are still very challenging, especially for the proteins with only distant homologs available.ResultsWe propose a new template-based modelling method called ThreaderAI to improve protein tertiary structure prediction. ThreaderAI formulates the task of aligning query sequence with template as the classical pixel classification problem in computer vision and naturally applies deep residual neural network in prediction. ThreaderAI first employs deep learning to predict residue-residue aligning probability matrix by integrating sequence profile, predicted sequential structural features, and predicted residue-residue contacts, and then builds template-query alignment by applying a dynamic programming algorithm on the probability matrix. We evaluated our methods both in generating accurate template-query alignment and protein threading. Experimental results show that ThreaderAI outperforms currently popular template-based modelling methods HHpred, CNFpred, and the latest contact-assisted method CEthreader, especially on the proteins that do not have close homologs with known structures. In particular, in terms of alignment accuracy measured with TM-score, ThreaderAI outperforms HHpred, CNFpred, and CEthreader by 56, 13, and 11%, respectively, on template-query pairs at the similarity of fold level from SCOPe data. And on CASP13’s TBM-hard data, ThreaderAI outperforms HHpred, CNFpred, and CEthreader by 16, 9 and 8% in terms of TM-score, respectively.ConclusionsThese results demonstrate that with the help of deep learning, ThreaderAI can significantly improve the accuracy of template-based structure prediction, especially for distant-homology proteins.

Efficient Detection of Cortical Auditory Evoked Potentials in Adults Using Bootstrapped Methods.

Statistical detection methods are useful tools for assisting clinicians with cortical auditory evoked potential (CAEP) detection, and can help improve the overall efficiency and reliability of the test. However, many of these detection methods rely on parametric distributions when evaluating test significance, and thus make various assumptions regarding the electroencephalogram (EEG) data. When these assumptions are violated, reduced test sensitivities and/or increased or decreased false-positive rates can be expected. As an alternative to the parametric approach, test significance can be evaluated using a bootstrap, which does not require some of the aforementioned assumptions. Bootstrapping also permits a large amount of freedom when choosing or designing the statistical test for response detection, as the distributions underlying the test statistic no longer need to be known prior to the test. To improve the reliability and efficiency of CAEP-related applications by improving the specificity and sensitivity of objective CAEP detection methods. The methods included in the assessment were Hotelling's T2 test, the Fmp, four modified q-sample statistics, and various template-based detection methods (calculated between the ensemble coherent average and some predefined template), including the correlation coefficient, covariance, and dynamic time-warping (DTW). The assessment was carried out using both simulations and a CAEP threshold series collected from 23 adults with normal hearing. The most sensitive method was DTW, evaluated using the bootstrap, with maximum increases in test sensitivity (relative to the conventional Hotelling's T2 test) of up to 30%. An important factor underlying the performance of DTW is that the template adopted for the analysis correlates well with the subjects' CAEP. When subjects' CAEP morphology is approximately known before the test, then the DTW algorithm provides a highly sensitive method for CAEP detection.

MLDH-Fold: Protein fold recognition based on multi-view low-rank modeling

Protein fold recognition is critical for understanding the molecular functions of proteins and drug design. Computational predictors have been proposed to identify protein into one of the known folds based only on the protein sequence information. However, how to combine different features to improve predictive performance remains a challenging problem. In this study, two novel methods (MVLR and MLDH-Fold) were proposed for protein fold recognition. We proposed a novel multi-view learning framework to combine the different views of protein sequences. Each view represents the similarity scores between the target sequences and template sequences calculated by the threading method. The proposed method extracts the low-rank principal features to precisely represent the similarity scores of each view and constructs the latent subspace with the common information of different views to predict the target proteins. Furthermore, we proposed an ensemble method called MLDH-Fold to combine the MVLR with the template-based methods. Predictive results on the two widely used datasets (LE and YK) show that the proposed computational methods outperform other computational predictors, indicating that the MVLR and MLDH-Fold are useful tools for protein fold recognition.