Score Vector Research Articles

Federated Diverse Self-ensembling Learning Approach for Data Heterogenity in Drive Vision

Federated learning (FL) has developed as an efficient framework that can be used to train models across isolated data sources while also protecting the privacy of the data. In FL a common method is to construct local and global models together, with the global model (server) informing the local models and the local models (clients) updating the global model. Most present works assume clients have labeled datasets and the server has no data for supervised learning (SL) problems. In reality, clients lack the competence and drive to identify their data, while the server may host a tiny amount. How to reasonably use serverlabeled and client-unlabeled data is crucial in semi-supervised learning (SSL) and Cclientdata heterogeneity is widespread in FL. However, inadequate high-quality labels and non-IID client data, especially in autonomous driving, decrease model performance across domains and interact negatively. To solve this Semi-Supervised Federated Learning (SSFL) problem, we come up with a new FL algorithm called FedDSL in this work. We use self-ensemble learning and complementary negative learning in our method to make clients’ unsupervised learning on unlabeled data more accurate and efficient. It also coordinates the model training on both the server side and the clients’ side. In an important distinction to earlier research that kept some subset of labels at each client, our method is the first to implement SSFL for clients with 0% labeled non-IID data. Our contributions include the effectiveness of self-ensemble learning by using confidence score vector for calculating only for the current model performing data filtering and initiated negative learning by showing the data filtering performance in the beginning rounds. Our approach has been rigorously validated on two significant autonomous driving datasets, BDD100K and Cityscapes, proving to be highly effective. We have achieved state-of-the-art results and the metric that is utilized to evaluate the effectiveness of each detection task is mean average precision (mAP@0.5). Astonishingly FedDSL performs nearly as well as fully-supervised centralized training approaches, despite the fact that it only uses 25% of the labels in the Global model.

Evaluating the Improvement of Blend Potency Measurements in the Feed Frame of a Rotary Tablet Press Using Combined NIR and Raman Spectroscopy.

This study investigated the added value of combining both near-infrared (NIR) and Raman spectroscopy into a single NIRaman Combi Fiber Probe for in-line blend potency determination in the feed frame of a rotary tablet press. A five-component platform formulation was used, containing acetylsalicylic acid as the Active Pharmaceutical Ingredient (API). Calibration models for the determination of 1 and 5%w/w label claim tablets were developed using NIR and Raman spectra of powder blends ranging from 0.75 to 1.25%w/w and 3.75 to 6.25%w/w API, respectively. Step-change experiments with deliberate 10% deviation steps from the label claims were performed, from which the collected spectra were used for model validation. For model development and validation, low-level data fusion was explored through concatenation of preprocessed NIR and Raman spectra. Mid-level data fusion was also evaluated, based on extracted features of the preprocessed data. Herewith, score vectors were extracted by transforming preprocessed spectra through Principal Component Analysis, followed by critical feature selection through Elastic Net Regression. Partial Least Squares regression was applied to regress singular, low-level or mid-level fused data versus blend potency. It could be concluded that irrespective of the data fusion technique, an increase in Step-Change Sensitivity (SCS) and decrease in Root Mean Squared Error (RMSE) was observed when predicting the 5%w/w step-change experiment. For the prediction of the 1%w/w step-change experiment, no added benefit with regard to SCS and RMSE was observed due to the addition of the noisy NIR spectra.

Radiomic Features at Contrast-Enhanced CT Predict Virus-Driven Liver Fibrosis: A Multi-Institutional Study.

Liver fibrosis is a major cause of morbidity and mortality among in patients with chronic hepatitis. Radiomics, particularly of the spleen, may improve diagnostic accuracy and treatment strategies. External validations are necessary to ensure reliability and generalizability. In this retrospective study, we developed 3 radiomics models using contrast-enhanced computed tomography scans from 167 patients with liver fibrosis (training group) between January 2020 and December 2021. Radiomic features were extracted from arterial venous, portal venous, and equilibrium phase images. Recursive feature selection random forest and the least absolute shrinkage and selection operator logistic regression were used for feature selection and dimensionality reduction. Performance was assessed by area under the curve, C-index, calibration plots, and decision curve analysis. External validation was performed on 114 patients from 2 institutions. Twenty-five radiomic features were significantly associated with fibrosis stage, with 80% of the top 10 features originating from portal venous phase spleen images. The radiomics models showed good performance in the validation cohort (C-indices 0.723-0.808) and excellent calibration. Decision curve analysis indicated clinical benefits, with machine learning-based radiomics models (Random Forest score and support vector machine based radiomics score) providing more significant advantages. Radiomic features offer significant benefits over existing serum indices for staging virus-driven liver fibrosis, underscoring the value of radiomics in enhancing diagnostic accuracy. Specifically, radiomics analysis of the spleen presents additional noninvasive options for assessing fibrosis, highlighting its potential in improving patient management and outcomes.

A non-linear partial least squares based on monotonic inner relation.

A novel regression model, monotonic inner relation-based non-linear partial least squares (MIR-PLS), is proposed to address complex issues like limited observations, multicollinearity, and nonlinearity in Chinese Medicine (CM) dose-effect relationship experimental data. MIR-PLS uses a piecewise mapping function based on monotonic cubic splines to model the non-linear inner relations between input and output score vectors. Additionally, a new weight updating strategy (WUS) is developed by leveraging the properties of monotonic functions. The proposed MIR-PLS method was compared with five well-known PLS variants: standard PLS, quadratic PLS (QPLS), error-based QPLS (EB-QPLS), neural network PLS (NNPLS), and spline PLS (SPL-PLS), using CM dose-effect relationship datasets and near-infrared (NIR) spectroscopy datasets. Experimental results demonstrate that MIR-PLS exhibits general applicability, achieving excellent predictive performances in the presence or absence of significant non-linear relationships. Furthermore, the model is not limited to CM dose-effect relationship research and can be applied to other regression tasks.

Cube query interestingness: Novelty, relevance, peculiarity and surprise

In this paper, we discuss methods to assess the interestingness of a query in an environment of data cubes. We assume a hierarchical multidimensional database, storing data cubes and level hierarchies. We start with a comprehensive review of related work in the fields of human behavior studies and computer science. We define the interestingness of a query as a vector of scores along different aspects, like novelty, relevance, surprise and peculiarity and complement this definition with a taxonomy of the information that can be used to assess each of these aspects of interestingness. We provide both syntactic (result-independent) and extensional (result-dependent) checks, measures and algorithms for assessing the different aspects of interestingness in a quantitative fashion. We also report our findings from a user study that we conducted, analyzing the significance of each aspect, its evolution over time and the behavior of the study’s participants.

Improving chemical reaction yield prediction using pre-trained graph neural networks

Graph neural networks (GNNs) have proven to be effective in the prediction of chemical reaction yields. However, their performance tends to deteriorate when they are trained using an insufficient training dataset in terms of quantity or diversity. A promising solution to alleviate this issue is to pre-train a GNN on a large-scale molecular database. In this study, we investigate the effectiveness of GNN pre-training in chemical reaction yield prediction. We present a novel GNN pre-training method for performance improvement.Given a molecular database consisting of a large number of molecules, we calculate molecular descriptors for each molecule and reduce the dimensionality of these descriptors by applying principal component analysis. We define a pre-text task by assigning a vector of principal component scores as the pseudo-label to each molecule in the database. A GNN is then pre-trained to perform the pre-text task of predicting the pseudo-label for the input molecule. For chemical reaction yield prediction, a prediction model is initialized using the pre-trained GNN and then fine-tuned with the training dataset containing chemical reactions and their yields. We demonstrate the effectiveness of the proposed method through experimental evaluation on benchmark datasets.

An audio‐based risky flight detection framework for quadrotors

AbstractDrones have increasingly collaborated with human workers in some workspaces, such as warehouses. The failure of a drone flight may bring potential risks to human beings' life safety during some aerial tasks. One of the most common flight failures is triggered by damaged propellers. To quickly detect physical damage to propellers, recognise risky flights, and provide early warnings to surrounding human workers, a new and comprehensive fault diagnosis framework is presented that uses only the audio caused by propeller rotation without accessing any flight data. The diagnosis framework includes three components: leverage convolutional neural networks, transfer learning, and Bayesian optimisation. Particularly, the audio signal from an actual flight is collected and transferred into time–frequency spectrograms. First, a convolutional neural network‐based diagnosis model that utilises these spectrograms is developed to identify whether there is any broken propeller involved in a specific drone flight. Additionally, the authors employ Monte Carlo dropout sampling to obtain the inconsistency of diagnostic results and compute the mean probability score vector's entropy (uncertainty) as another factor to diagnose the drone flight. Next, to reduce data dependence on different drone types, the convolutional neural network‐based diagnosis model is further augmented by transfer learning. That is, the knowledge of a well‐trained diagnosis model is refined by using a small set of data from a different drone. The modified diagnosis model has the ability to detect the broken propeller of the second drone. Thirdly, to reduce the hyperparameters' tuning efforts and reinforce the robustness of the network, Bayesian optimisation takes advantage of the observed diagnosis model performances to construct a Gaussian process model that allows the acquisition function to choose the optimal network hyperparameters. The proposed diagnosis framework is validated via real experimental flight tests and has a reasonably high diagnosis accuracy.

PredIL13: Stacking a variety of machine and deep learning methods with ESM-2 language model for identifying IL13-inducing peptides.

Interleukin (IL)-13 has emerged as one of the recently identified cytokine. Since IL-13 causes the severity of COVID-19 and alters crucial biological processes, it is urgent to explore novel molecules or peptides capable of including IL-13. Computational prediction has received attention as a complementary method to in-vivo and in-vitro experimental identification of IL-13 inducing peptides, because experimental identification is time-consuming, laborious, and expensive. A few computational tools have been presented, including the IL13Pred and iIL13Pred. To increase prediction capability, we have developed PredIL13, a cutting-edge ensemble learning method with the latest ESM-2 protein language model. This method stacked the probability scores outputted by 168 single-feature machine/deep learning models, and then trained a logistic regression-based meta-classifier with the stacked probability score vectors. The key technology was to implement ESM-2 and to select the optimal single-feature models according to their absolute weight coefficient for logistic regression (AWCLR), an indicator of the importance of each single-feature model. Especially, the sequential deletion of single-feature models based on the iterative AWCLR ranking (SDIWC) method constructed the meta-classifier consisting of the top 16 single-feature models, named PredIL13, while considering the model's accuracy. The PredIL13 greatly outperformed the-state-of-the-art predictors, thus is an invaluable tool for accelerating the detection of IL13-inducing peptide within the human genome.

Female Characterization and Cultural Characterization of Water Margin Based on Cognitive Mapping Constructs

Abstract The Water Margin portrays many typical female images, and different female character images make the characters more fleshed out so that the readers will never forget them. In this paper, we construct cognitive mapping based on the cognitive mapping of female characters in Water Margin. In order to more intuitively display female characters and their embedded cultural characteristics, we choose a multilayer perceptual machine to learn the representation of emotion score vectors and combine the temporal and semantic relationships in the text with long and short-term memory networks to construct an emotion dictionary of female characters. GAN is utilized in female characterization to provide a foundation for thoroughly analyzing the cultural characteristics of female character roles. The method given in this paper was validated and analyzed in terms of female characterization and cultural characteristics. The results show that on the EmotionROI dataset, the classification accuracy of the emotion lexicon is 9.34% higher than that of the GOSR algorithm, and the classification accuracy of various emotion categories reaches more than 70%. The image generation quality of the GAN method is 63.96% on the BLUE-4 dataset, and the final CIDER index score on the MSVD dataset tends to be 1.15%. The image of female characters in Water Margin mainly conveys a variety of different images such as heroic, ugly and complex, which represents the real state of women at the bottom of society in the feudal period of the late Yuan and early Ming Dynasties, and provides a certain reference for understanding the cultural traits under the feudal society.

Feature rectification and enhancement for no-reference image quality assessment

The assessment of image is a critical task in computer vision, particularly in a no-referenced context, which presents numerous challenges. Though Deep neural networks have exhibited excellent performance on no-reference quality assessment (NR-IQA), the distortion-aware NR-IQA methods are limited to specific distortion type and struggle to handle realistic distortion scenarios. In this work, we propose a feature rectification and enhancement convolutional neural network namely FREIQA for NR-IQA. Our approach targets to fully utilize the multi-stage semantic features to produce a well fused and rectified score vector for effective image quality regression. Specifically, the multi-stage semantic features extracted by a pre-trained backbone would be rectified with a multi-level channel attention module before integrating to a global score vector. The fused score vector then will be gradually optimized through the perception feature provided by the multi-stage semantic feature, and finally sent to quality regression network to obtain the image quality score. Experimental results on public benchmarks including LIVE, TID2013, CSIQ, LIVEC, KADID-10k, KonIQ-10k and Waterloo exploration database show that our FREIQA achieve the state-of-the-art performance.

Tumor radiogenomics in gliomas with Bayesian layered variable selection.

We propose a statistical framework to analyze radiological magnetic resonance imaging (MRI) and genomic data to identify the underlying radiogenomic associations in lower grade gliomas (LGG). We devise a novel imaging phenotype by dividing the tumor region into concentric spherical layers that mimics the tumor evolution process. MRI data within each layer is represented by voxel-intensity-based probability density functions which capture the complete information about tumor heterogeneity. Under a Riemannian-geometric framework these densities are mapped to a vector of principal component scores which act as imaging phenotypes. Subsequently, we build Bayesian variable selection models for each layer with the imaging phenotypes as the response and the genomic markers as predictors. Our novel hierarchical prior formulation incorporates the interior-to-exterior structure of the layers, and the correlation between the genomic markers. We employ a computationally-efficient Expectation-Maximization-based strategy for estimation. Simulation studies demonstrate the superior performance of our approach compared to other approaches. With a focus on the cancer driver genes in LGG, we discuss some biologically relevant findings. Genes implicated with survival and oncogenesis are identified as being associated with the spherical layers, which could potentially serve as early-stage diagnostic markers for disease monitoring, prior to routine invasive approaches. We provide a R package that can be used to deploy our framework to identify radiogenomic associations.

Assisting pre-delivery firmware quality assessments using ensemble learning

ABSTRACT This study uses retrospective data for firmware tests as the input data sets to train four machine learning models with embedded standalone classifiers. None of these models provide accurate predictions during validation, so model optimization trials adjust the training-validation data portfolio and hyper parameters for each model. Consequently, only the random forest classifier with the best parametric settings just achieves the 90% prediction accuracy required by the standard. Ensemble learning (EL) is then applied using several combinations over the standalone models, and the EL model using logistic regression as the meta classifier increases the accuracy by 6% (i.e. to 96%), which is sufficient for establishing a predictive system. Using the ‘X-minute’ method, it is further identified that the execution period (also the data sampling period) for the sequential read test workload can be reduced from 30 (in current practice) to 20 minutes and that the predictions are sufficiently accurate for system implementation using the EL model. Applying the similarity confirmation method for each pair of ‘score vectors’ (each of which contains a model’s prediction accuracies), several observations distinguishing the performance and the predictive behavioral patterns of the benchmarked models are further confirmed. The knowledge from this advanced research has implications which may benefit future practice in industry.

MMPosE: Movie-Induced Multi-Label Positive Emotion Classification Through EEG Signals

Emotional information plays an important role in various multimedia applications. Movies, as a widely available form of multimedia content, can induce multiple positive emotions and stimulate people's pursuit of a better life. Different from negative emotions, positive emotions are highly correlated and difficult to distinguish in the emotional space. Since different positive emotions are often induced simultaneously by movies, traditional single-target or multi-class methods are not suitable for the classification of movie-induced positive emotions. In this paper, we propose TransEEG, a model for multi-label positive emotion classification from a viewer's brain activities when watching emotional movies. The key features of TransEEG include (1) explicitly modeling the spatial correlation and temporal dependencies of multi-channel EEG signals using the Transformer structure based model, which effectively addresses long-distance dependencies, (2) exploiting the label-label correlations to guide the discriminative EEG representation learning, for that we design an Inter-Emotion Mask for guiding the Multi-Head Attention to learn the inter-emotion correlations, and (3) constructing an attention score vector from the representation-label correlation matrix to refine emotion-relevant EEG features. To evaluate the ability of our model for multi-label positive emotion classification, we demonstrate our model on a state-of-the-art positive emotion database CPED. Extensive experimental results show that our proposed method achieves superior performance over the competitive approaches.

The Chen Autoregressive Moving Average Model for Modeling Asymmetric Positive Continuous Time Series

In this paper, we introduce a new dynamic model for time series based on the Chen distribution, which is useful for modeling asymmetric, positive, continuous, and time-dependent data. The proposed Chen autoregressive moving average (CHARMA) model combines the flexibility of the Chen distribution with the use of covariates and lagged terms to model the conditional median response. We introduce the CHARMA structure and discuss conditional maximum likelihood estimation, hypothesis testing inference along with the estimator asymptotic properties of the estimator, diagnostic analysis, and forecasting. In particular, we provide closed-form expressions for the conditional score vector and the conditional information matrix. We conduct a Monte Carlo experiment to evaluate the introduced theory in finite sample sizes. Finally, we illustrate the usefulness of the proposed model by exploring two empirical applications in a wind-speed and maximum-temperature time-series dataset.

Rapid Fluorescence EEM Spectroscopy Using Super-Cycle Hadamard-Transform Multiplexing.

Hadamard-transform (HT) multiplexing has recently been applied to increasingly complex spectroscopic techniques. It had been shown that the data acquisition time for fluorescence excitation emission matrix (EEM) spectroscopy can be reduced by 1 or 2 orders of magnitude using HT multiplexing of the excitation light using a programmable light source. In these previous studies, the data acquisition rate had been limited by the time it took to record an EEM, that is, to complete one cycle of multiplexed excitation spectra. The extraction of chemical information, such as concentration and chemical identity, is then obtained from parallel factor (PARAFAC) analysis of the sequence of EEMs. In this contribution, we increase the data acquisition rate by another order of magnitude, limited ultimately by the time it takes to record a single excitation spectrum. Our algorithm is entirely based on improved data processing, that is, it can be applied to previously recorded HT multiplexed data sets. The algorithm is based on three previously unexplored approaches: (1) we perform a PARAFAC multivariate analysis on the raw (multiplexed) data set, (2) the time-independent PARAFAC loading vectors are obtained prior to obtaining the time-dependent score vectors, and (3) when loading vectors are difficult to obtain from the EEMs, we instead use a rolling-average approach to considerably increase the stability of the fit. Analysis of experimental data shows that the scores of fluorescence EEMs with seven excitation wavelengths and over 1000 emission wavelengths can be obtained in less than 20 ms.

The Pezeta regression model: an alternative to unit Lindley regression model

A new probability distribution is proposed in this paper. This new distribution has support on the interval and was obtained after transforming the random variable with exponential distribution. The mode, quantile function, median, ordinary moments and density function belongs to exponential family of distributions are demonstrated. The maximum likelihood method is used to obtain the parameter estimate. A regression model for the median of the distribution is also proposed. Closed-form expressions for the score vector and Fisher’s information matrix are demonstrated. A simulation study and an application to real data showed the good performance of the proposed regression model.

Clustering asymmetrical data with outliers: Parsimonious mixtures of contaminated mean-mixture of normal distributions

Mixture modeling has emerged as a statistical tool to perform unsupervised model-based clustering for heterogeneous data. A framework of using contaminated mean-mixture of normal distributions as the components of the mixture model is designed to accommodate asymmetric data with outliers. Fourteen parsimonious variants of the postulated model are introduced by employing an eigenvalue decomposition of the component scale matrices. Simultaneously clustering and outliers detection is an outstanding advantage of the proposed model in analyzing non-normally distributed data. A computationally feasible and flexible EM-type algorithm is outlined for obtaining maximum likelihood parameter estimates. Moreover, the score vector and empirical information matrix for calculating asymptotic standard errors of the parameter estimates are derived by offering an information-based approach. The applicability of the proposed method is demonstrated through the analysis of simulated and real datasets with varying proportions of outliers.

Taxonomic distribution of opsin families inferred from UniProt Reference Proteomes and a suite of opsin-specific hidden Markov models

IntroductionOpsins are a large and sequence-diverse family of light-responsive G-protein coupled receptors involved in vision, circadian rhythm, and other processes. Numerous subfamilies have been defined based on sequence similarity, cell-type localization, signal transduction mechanism, or biological function, but there is no consensus classification system.MethodsWe used multiple hidden Markov models (HMMs) to identify opsins in the UniProt Reference Proteomes database. Opsin-specific HMMs were also used in an annotation procedure that represents sequences as a vector of HMM scores and assess the similarity of these vectors to those of annotated sequences. UniProt Reference Proteomes are built from genome sequences, allowing us to make meaningful comparisons of the number of opsins in each of the 260 species available at the time of the survey in absolute terms and relative to a larger superfamily of which opsins are a member.ResultsMore than 2,000 opsins were retrieved from 262 species (all metazoans).DiscussionMerging opsin counts into higher order taxa paints a broad view of the taxonomic distribution of opsins, and of opsin subfamilies, annotated according to three different schemes.

Purifier: Defending Data Inference Attacks via Transforming Confidence Scores

Neural networks are susceptible to data inference attacks such as the membership inference attack, the adversarial model inversion attack and the attribute inference attack, where the attacker could infer useful information such as the membership, the reconstruction or the sensitive attributes of a data sample from the confidence scores predicted by the target classifier. In this paper, we propose a method, namely PURIFIER, to defend against membership inference attacks. It transforms the confidence score vectors predicted by the target classifier and makes purified confidence scores indistinguishable in individual shape, statistical distribution and prediction label between members and non-members. The experimental results show that PURIFIER helps defend membership inference attacks with high effectiveness and efficiency, outperforming previous defense methods, and also incurs negligible utility loss. Besides, our further experiments show that PURIFIER is also effective in defending adversarial model inversion attacks and attribute inference attacks. For example, the inversion error is raised about 4+ times on the Facescrub530 classifier, and the attribute inference accuracy drops significantly when PURIFIER is deployed in our experiment.

How Should We Score Athletes and Candidates: Geometric Scoring Rules

Scoring in Multi-Event Tournaments How much is a first place worth? Is the athlete who came first once and third twice better than the athlete who came second three times? Different sports value these positions differently: (60, 54, 48) in IBU biathlon, (25, 18, 15) in F1 racing, (8, 7, 6) in Diamond League athletics. Are these choices based on anything? Is there even a rational way to choose a scoring vector of arbitrary length to rank any number of athletes? In “How should we score athletes and candidates: Geometric scoring rules,” authors A.Y. Kondratev, E. Ianovski, and A.S. Nesterov investigate two approaches to how the problem of choosing a scoring vector for a tournament can be reduced to the choice of a single parameter: an axiomatic approach based on eliminating spoilers and an optimization approach based on maximizing the expected quality of the winner. Intriguingly, the vectors generated by the second approach are uncannily similar to those used in real sporting events.