Performance Improvement Research Articles

Predicting antimicrobial resistance in E. coli with discriminative position fused deep learning classifier

Escherichia coli (E. coli) has become a particular concern due to the increasing incidence of antimicrobial resistance (AMR) observed worldwide. Using machine learning (ML) to predict E. coli AMR is a more efficient method than traditional laboratory testing. However, further improvement in the predictive performance of existing models remains challenging. In this study, we collected 1,937 high-quality whole genome sequencing (WGS) data from public databases with an antimicrobial resistance phenotype and modified the existing workflow by adding an attention mechanism to enable the modified workflow to focus more on core single nucleotide polymorphisms (SNPs) that may significantly lead to the development of AMR in E. coli. While comparing the model performance before and after adding the attention mechanism, we also performed a cross-comparison among the published models using random forest (RF), support vector machine (SVM), logistic regression (LR), and convolutional neural network (CNN). Our study demonstrates that the discriminative positional colors of Chaos Game Representation (CGR) images can selectively influence and highlight genome regions without prior knowledge, enhancing prediction accuracy. Furthermore, we developed an online tool (https://github.com/tjiaa/E.coli-ML/tree/main) for assisting clinicians in the rapid prediction of the AMR phenotype of E. coli and accelerating clinical decision-making.

Surfactant-modified zein nanoparticles adsorbents for ultrafast and efficient removal of Cr(VI)

The adsorption and removal of heavy metal ions Cr(VI) is of great significance for human health and ecological environment. Here, an ultrafast and high efficient adsorbent for Cr(VI) was developed based on cetyltrimethylammonium bromide (CTAB)-modified zein nanoparticles (C-ZNPs). In comparison to pristine zein nanoparticles (ZNPs) (11.199 m2 g−1), the surfactant-modified C-ZNPs exhibited larger specific surface area (17.002 m2 g−1). Moreover, C-ZNPs had superior dispersion and more positive charge distribution, which contributed to the improvement for adsorption performance. The results showed that the saturated adsorption of Cr(VI) was reached up to 192.27 mg/g using the C-ZNPs nanosorbent at T = 298 K, pH = 4, t = 10s, and C0 = 125 mg/L. The removal rate was significantly faster than that reported natural polymer-based adsorbents. The experimental values were followed Freundich isothermal model and pseudo-second-order kinetic model, indicating that the adsorption occurred primarily through a multimolecular layer adsorption process, with a strong emphasis on chemisorption. Mechanistic investigations further revealed that the adsorption of Cr(VI) onto C-ZNPs was mediated by various interactions, including electrostatic attraction, complexation, and ion exchange. These findings provide insights into the efficient removal of Cr(VI) by C-ZNPs and suggest potential applications in water treatment and environmental remediation.

A Novel Dynamic Multiobjective Optimization Algorithm With Non-Inductive Transfer Learning Based on Multi-Strategy Adaptive Selection.

In this article, a novel multi-strategy adaptive selection-based dynamic multiobjective optimization algorithm (MSAS-DMOA) is proposed, which adopts the non-inductive transfer learning (TL) paradigm to solve dynamic multiobjective optimization problems (DMOPs). In particular, based on a scoring system that evaluates environmental changes, the source domain is adaptively constructed with several optional groups to enrich the knowledge. Along with a group of guide solutions, the importance of historical experiences is estimated via the kernel mean matching (KMM) method, which avoids designing strategies to label individuals. The proposed MSAS-DMOA is comprehensively evaluated on 14 DMOPs, and the results show an overwhelming performance improvement in terms of both convergence and diversity as compared with other four popular DMOAs. In addition, ablation studies are also conducted to validate the superiority of the applied strategies in MSAS-DMOA, which can effectively alleviate the negative transfer phenomenon. Without the conventional labeling procedure, the proposed method also yields satisfactory results, which can provide valuable reference for designing other evolutionary transfer optimization (ETO) algorithms.

Stochastic properties of musical time series

Musical sequences are correlated dynamical processes that may differ depending on musical styles. We aim to quantify the correlations through power spectral analysis of pitch sequences in a large corpus of musical compositions as well as improvised performances. Using a multitaper method we extend the power spectral estimates down to the smallest possible frequencies optimizing the tradeoff between bias and variance. The power spectral densities reveal a characteristic behavior; they typically follow inverse power laws (1/f β-noise), yet only down to a cutoff frequency, where they end in a plateau. Correspondingly the pitch autocorrelation function exhibits slow power law decays only up to a cutoff time, beyond which the correlations vanish. We determine cutoff times between 4 and 100 quarter note units for the compositions and improvisations of the corpus, serving as a measure for the degree of persistence and predictability in music. The histogram of exponents β for the power law regimes has a pronounced peak near β = 1 for classical compositions, but is much broader for jazz improvisations.

Design and Evaluation of Modular Stator Hybrid-Excitation Switched Reluctance Motor for Torque Performance Improvement

Design and Evaluation of Modular Stator Hybrid-Excitation Switched Reluctance Motor for Torque Performance Improvement

AGNN: Alternating Graph-Regularized Neural Networks to Alleviate Over-Smoothing.

Graph convolutional network (GCN) with the powerful capacity to explore graph-structural data has gained noticeable success in recent years. Nonetheless, most of the existing GCN-based models suffer from the notorious over-smoothing issue, owing to which shallow networks are extensively adopted. This may be problematic for complex graph datasets because a deeper GCN should be beneficial to propagating information across remote neighbors. Recent works have devoted effort to addressing over-smoothing problems, including establishing residual connection structure or fusing predictions from multilayer models. Because of the indistinguishable embeddings from deep layers, it is reasonable to generate more reliable predictions before conducting the combination of outputs from various layers. In light of this, we propose an alternating graph-regularized neural network (AGNN) composed of graph convolutional layer (GCL) and graph embedding layer (GEL). GEL is derived from the graph-regularized optimization containing Laplacian embedding term, which can alleviate the over-smoothing problem by periodic projection from the low-order feature space onto the high-order space. With more distinguishable features of distinct layers, an improved Adaboost strategy is utilized to aggregate outputs from each layer, which explores integrated embeddings of multi-hop neighbors. The proposed model is evaluated via a large number of experiments including performance comparison with some multilayer or multi-order graph neural networks, which reveals the superior performance improvement of AGNN compared with the state-of-the-art models.

TAG: Teacher-Advice Mechanism With Gaussian Process for Reinforcement Learning.

Reinforcement learning (RL) still suffers from the problem of sample inefficiency and struggles with the exploration issue, particularly in situations with long-delayed rewards, sparse rewards, and deep local optimum. Recently, learning from demonstration (LfD) paradigm was proposed to tackle this problem. However, these methods usually require a large number of demonstrations. In this study, we present a sample efficient teacher-advice mechanism with Gaussian process (TAG) by leveraging a few expert demonstrations. In TAG, a teacher model is built to provide both an advice action and its associated confidence value. Then, a guided policy is formulated to guide the agent in the exploration phase via the defined criteria. Through the TAG mechanism, the agent is capable of exploring the environment more intentionally. Moreover, with the confidence value, the guided policy can guide the agent precisely. Also, due to the strong generalization ability of Gaussian process, the teacher model can utilize the demonstrations more effectively. Therefore, substantial improvement in performance and sample efficiency can be attained. Considerable experiments on sparse reward environments demonstrate that the TAG mechanism can help typical RL algorithms achieve significant performance gains. In addition, the TAG mechanism with soft actor-critic algorithm (TAG-SAC) attains the state-of-the-art performance over other LfD counterparts on several delayed reward and complicated continuous control environments.

EgPDE-Net: Building Continuous Neural Networks for Time Series Prediction With Exogenous Variables.

While exogenous variables have a major impact on performance improvement in time series analysis, interseries correlation and time dependence among them are rarely considered in the present continuous methods. The dynamical systems of multivariate time series could be modeled with complex unknown partial differential equations (PDEs) which play a prominent role in many disciplines of science and engineering. In this article, we propose a continuous-time model for arbitrary-step prediction to learn an unknown PDE system in multivariate time series whose governing equations are parameterized by self-attention and gated recurrent neural networks. The proposed model, exogenous-guided PDE network (EgPDE-Net), takes account of the relationships among the exogenous variables and their effects on the target series. Importantly, the model can be reduced into a regularized ordinary differential equation (ODE) problem with specially designed regularization guidance, which makes the PDE problem tractable to obtain numerical solutions and feasible to predict multiple future values of the target series at arbitrary time points. Extensive experiments demonstrate that our proposed model could achieve competitive accuracy over strong baselines: on average, it outperforms the best baseline by reducing 9.85% on RMSE and 13.98% on MAE for arbitrary-step prediction.

Referents in the Palimpsests of Jazz

Jazz analysts have long struggled with the ways in which tunes can be accounted for in analyses of musical structure. When analyzing the utterances jazz musicians make in an improvised performance, it is difficult to disentangle the musical elements related to what Jeff Pressing termed the “referent”—the improviser’s conceptualization of the tune—from those more freely improvised in the moment. Complicating this problem is the fact that standard jazz tunes themselves are not fixed structures with essential, immutable musical components; no definitive version exists of any given tune. Instead, tunes are flexible and malleable, permitting infinite variations. In this article, I develop a methodology that provisionally disentangles jazz improvisations from the tunes on which they are based. I begin by theorizing the structure and function of various tune-referents before outlining a theory of referent defaults. I then present two case studies, one on melody and one on harmony, that examine the relations between different performances in order to arrive at a postulated referent for use in further analysis. Finally, I draw on anthropologist Timothy Ingold’s concept of textility to illuminate the nuanced ways that jazz improvisers engage with referents.

Toward Explainable Multiparty Learning: A Contrastive Knowledge Sharing Framework.

Multiparty learning provides solutions for training joint models with decentralized data under legal and practical constraints. However, traditional multiparty learning approaches are confronted with obstacles, such as system heterogeneity, statistical heterogeneity, and incentive design. Determining how to deal with these challenges and further improve the efficiency and performance of multiparty learning has become an urgent problem to be solved. In this article, we propose a novel contrastive multiparty learning framework for knowledge refinement and sharing with an accountable incentive mechanism. Since the existing parameter averaging method is contradictory to the learning paradigm of neural networks, we simulate the process of human cognition and communication and analogize multiparty learning as a many-to-one knowledge-sharing problem. The approach is capable of integrating the acquired explicit knowledge of each client in a transparent manner without privacy disclosure, and it reduces the dependence on data distribution and communication environments. The proposed scheme achieves significant improvement in model performance in a variety of scenarios, as we demonstrated through experiments on several real-world datasets.

Comprehensive Performance Improvement of Permanent Magnet Vernier Motor for Electric Tractors

Comprehensive Performance Improvement of Permanent Magnet Vernier Motor for Electric Tractors

A DEFESA CIVIL NO CONTEXTO BRASILEIRO

Civil Defense in Brazil plays a fundamental role in protecting the population against natural disasters and emergencies. This article analyzes the structure of Civil Defense in the country, its challenges and future perspectives for improving the effectiveness of prevention and response operations. The research includes a review of current practices using academic sources and official documents, the article provides a comprehensive overview of the functions and challenges of Civil Defense in Brazil. The first part of this study explores the genesis of Civil Defense in Brazil, its main stages of evolution and the legislation that shaped its current structure, implementation and impact of PNPDEC, highlighting its importance for protecting the population and managing disasters in the country. The second part analyzes the challenges of Civil Defense in Brazil. This study provided a comprehensive understanding of Civil Defense in Brazil, which allowed us to analyze its biggest challenges and indicate the main points that require attention and improvement for the effective performance of Civil Defense in the Brazilian context.

Clinical outcome of elbow extension restoration by posterior deltoid-to-triceps transfer in tetraplegia: a retrospective review of 51 patients.

In this study, we report the functional and perceived outcomes of 51 posterior deltoid-to-triceps transfers in patients with tetraplegia. With a minimum follow-up of 12 months, patients were divided into two subcategories based on preoperative posterior deltoid strength: Medical Research Council (MRC) 3 and MRC 4/5. At 12-month follow-up, all patients achieved antigravity elbow extension. Patients with a stronger posterior deltoid (MRC 4/5) attained an elbow extension with a strength grade MRC 3.7 (SD 0.6), while those with a weaker posterior deltoid (MRC 3) reached an elbow extension of MRC 3.1 (SD 0.6). Patient-reported outcome measure was evaluated using the Canadian Occupational Performance Measure (COPM) and demonstrated a significant improvement for both performance and satisfaction. No difference in the COPM scores could be found between the two subcategories. This study indicates that tetraplegic patients with a posterior deltoid strength grade of both MRC 4/5 as well as MRC 3 benefit from the procedure.Level of evidence: III.

Single/Multi-Source Black-Box Domain Adaption for Sensor Time Series Data.

Unsupervised domain adaption (UDA), which transfers knowledge from a labeled source domain to an unlabeled target domain, has attracted tremendous attention in many machine learning applications. Recently, there have been attempts to apply domain adaption for sensor time series data, such as human activity recognition and gesture recognition. However, existing methods suffer from some drawbacks that hinder further performance improvement. They often require access to source data or source models during training, which is unavailable in some fields because of privacy protection and storage limit. Typically, the source domains may only provide an application programming interface (API) for the target domain to call. On the other hand, current UDA methods have not considered the temporal consistency and low-signal-to-noise ratio (SNR) of sensor time series. To address the challenges, this article presents a black-box domain adaption framework for sensor time series data (B2TSDA). First, we propose a single/multi-source teacher-student learning framework to distill the knowledge from the source domains to a customized target model. Then we design a new temporal consistency loss by combining an adaptive mask method and dynamic threshold method to maintain consistent temporal information and balance the learning difficulties of different classes. For the multisource black-box domain adaption, we further propose a Shapley-enhanced method to determine the contribution of each source domain. Experimental results on both single-source and multisource domain adaption show that our framework has superior performance compared to other black-box UDA methods.

Learning Multi-Agent Cooperation via Considering Actions of Teammates.

Recently value-based centralized training with decentralized execution (CTDE) multi-agent reinforcement learning (MARL) methods have achieved excellent performance in cooperative tasks. However, the most representative method among these methods, Q-network MIXing (QMIX), restricts the joint action Q values to be a monotonic mixing of each agent's utilities. Furthermore, current methods cannot generalize to unseen environments or different agent configurations, which is known as ad hoc team play situation. In this work, we propose a novel Q values decomposition that considers both the return of an agent acting on its own and cooperating with other observable agents to address the nonmonotonic problem. Based on the decomposition, we propose a greedy action searching method that can improve exploration and is not affected by changes in observable agents or changes in the order of agents' actions. In this way, our method can adapt to ad hoc team play situation. Furthermore, we utilize an auxiliary loss related to environmental cognition consistency and a modified prioritized experience replay (PER) buffer to assist training. Our extensive experimental results show that our method achieves significant performance improvements in both challenging monotonic and nonmonotonic domains, and can handle the ad hoc team play situation perfectly.

Cross-Image Pixel Contrasting for Semantic Segmentation.

This work studies the problem of image semantic segmentation. Current approaches focus mainly on mining "local" context, i.e., dependencies between pixels within individual images, by specifically-designed, context aggregation modules (e.g., dilated convolution, neural attention) or structure-aware optimization objectives (e.g., IoU-like loss). However, they ignore "global" context of the training data, i.e., rich semantic relations between pixels across different images. Inspired by recent advance in unsupervised contrastive representation learning, we propose a pixel-wise contrastive algorithm, dubbed as PiCo, for semantic segmentation in the fully supervised learning setting. The core idea is to enforce pixel embeddings belonging to a same semantic class to be more similar than embeddings from different classes. It raises a pixel-wise metric learning paradigm for semantic segmentation, by explicitly exploring the structures of labeled pixels, which were rarely studied before. Our training algorithm is compatible with modern segmentation solutions without extra overhead during testing. We experimentally show that, with famous segmentation models (i.e., DeepLabV3, HRNet, OCRNet, SegFormer, Segmenter, MaskFormer) and backbones (i.e., MobileNet, ResNet, HRNet, MiT, ViT), our algorithm brings consistent performance improvements across diverse datasets (i.e., Cityscapes, ADE20 K, PASCAL-Context, COCO-Stuff, CamVid). We expect that this work will encourage our community to rethink the current de facto training paradigm in semantic segmentation.

Risk of Acute Kidney Injury Following IV Iodinated Contrast Media Exposure: 2023 Update, From the AJR Special Series on Contrast Media.

Iodinated contrast material (ICM) has revolutionized the field of diagnostic radiology through improvements in diagnostic performance and the expansion of clinical indications for radiographic and CT examinations. Historically, nephrotoxicity was a feared complication of ICM use, thought to be associated with a significant risk of morbidity and mortality. Such fears often precluded the use of ICM in imaging evaluations, commonly at the expense of diagnostic performance and timely diagnosis. Over the past 20 years, the nephrotoxic risk of ICM has become a topic of debate, as more recent evidence from higher-quality studies now suggests that many cases of what was considered contrast-induced acute kidney injury (CI-AKI) likely were cases of mistaken causal attribution; most of these cases represented either acute kidney injury (AKI) caused by any of myriad other known factors that can adversely affect renal function and were coincidentally present at the time of contrast media exposure (termed "contrast-associated AKI" [CA-AKI]) or a manifestation of the normal variation in renal function that increases with worsening renal function. This Special Series Review discusses the current state of knowledge regarding CI-AKI and CA-AKI, including the incidence, risk factors, outcomes, and prophylactic strategies in the identification and management of these clinical conditions.

Hospital Allocation and Racial Disparities in Health Care

Abstract We develop a framework to measure the role of hospital allocation in racial disparities in health care and use it to study Black and white heart attack patients. Black patients receive care at lower-performing hospitals than white patients. However, over two decades, the performance gap between hospitals treating Black and white patients shrank by over two-thirds. This progress is due to more rapid performance improvement at hospitals that tended to treat Black patients rather than reallocation of patients. Hospital improvement is correlated with adoption of a productivity-raising input, beta blockers. Our work highlights reallocation and performance improvement as future disparity-reduction levers.

Interaction-and-Response Network for Distantly Supervised Relation Extraction.

Distantly supervised relation extraction (DSRE) aims to identify semantic relations from massive plain texts. A broad range of the prior research has leveraged a series of selective attention mechanisms over sentences in a bag to extract relation features without considering dependencies among the relation features. As a result, potential discriminative information existed in the dependencies is ignored, causing a decline in the performance of extracting entity relations. In this article, we focus on going beyond the selective attention mechanisms and propose a new framework termed interaction-and-response network (IR-Net) that adaptively recalibrates the features of sentence, bag, and group levels by explicitly modeling interdependencies among the features on each level. The IR-Net consists of a series of interactive and responsive modules throughout feature hierarchy, seeking to strengthen its power of learning salient discriminative features for distinguishing entity relations. We conduct extensive experiments on three benchmark DSRE datasets, including NYT-10, NYT-16, and Wiki-20m. The experimental results demonstrate that the IR-Net brings obvious improvements in performance when comparing ten state-of-the-art DSRE methods for entity relation extraction.

New Distributed Consensus Schemes With Time Delays and Output Saturation

Estimates of agents in a distributed consensus control are aligned with a particular value through interacting on communication graphs, which are of particular interest for researchers in the field of multi-agent coordination. Following this pattern, a discrete-time constrained consensus issue with generalized time delays is first established in this article, which is manipulated into an optimization problem via a quadratic performance index introduced as a global objective function. Then, a novel consensus scheme is investigated and proposed for handling this problem, enabling the consensus to approach the desired state globally and rapidly with optimal system property ensured. Besides, to advance the convergence speed and stability in resisting constant bias or oscillation, an adjustment control method is explored to construct a modified consensus scheme; further, to enhance the scene adaptability, fix topologies are extended to switching ones, and the latter is involved to develop another scheme on this basis. Moreover, the convergence and robustness of these three proposed consensus schemes are substantiated by theoretical analysis and numerical simulations. To highlight the practical implementations, the proposed consensus schemes are incorporated with a winner-take-all operation to accomplish multi-agent competitive coordination in a distributed way, and the results embody their effectiveness and superior consensus control ability, along with strong plasticity. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper is dedicated to investigating and optimizing distributed consensus schemes with time delays and output saturation with application to the competitive coordination of multi-agent systems. On the one hand, the consensus problem with output saturation receives limited attention, and few consensus algorithms consider both saturation limitation and channel gain. On the other hand, most existing studies on consensus with saturation consider simply the dynamic behaviour of agents without employing optimization, thus limiting further improvement of system performance. In this paper, a consensus algorithm is built from an optimization perspective that guarantees the state consensus of a multi-agent system with output constraints and generalized time delays. In addition, a consensus scheme is designed in a discrete-time framework and further modified and perfected along with the idea of considering time delays and expanding diverse topologies. Finally, experiments are conducted by applying the consensus scheme to a winner-take-all operation, with contributions of this paper verified.