Pairs Of Features Research Articles

Feature Selection Ordered By Correlation - FSOC

Data sets have increased in volume and features, yielding longer times for classification and training. Many features usually mean that not all of them are highly correlated with the target class, and that significant correlation may exist between certain pairs of features. The proper reduction of “useless” features saves time and effort at data collection, assures faster learning and classification times, with little or no reduction in classification accuracy. However, algorithms for selecting adequate features have high levels of processing. FSOC achieves this reduction by selecting a subset of the original features. To refrain from reformatting, transforming and combining existing features it is necessary to create a new set with lower cardinality, since the artificially created features mask the relevance of the original for decision making, and causes clarity loss in the built model.This article presents a new filter type method, called FSOC (Feature Selection Ordered by Correlation), to select, with small computational cost, relevant features. FSOC uses correlations between features and the merit heuristic to identify a subset of "good" features. FSOC's reduced computational cost arises from an ordering of the features. To test it, a statistical analysis was performed on a sample comprising 36 data sets from several repositories some with millions of objects. The classification percentages (efficiency) of FSOC were similar to other feature selection features. Nevertheless, FSOC was up to 42 times faster than other algorithms (CFS, FCFB and ECMBF) to obtain the selected features.

Sleep Stage Classification in Children Using Self-Attention and Gaussian Noise Data Augmentation

The analysis of sleep stages for children plays an important role in early diagnosis and treatment. This paper introduces our sleep stage classification method addressing the following two challenges: the first is the data imbalance problem, i.e., the highly skewed class distribution with underrepresented minority classes. For this, a Gaussian Noise Data Augmentation (GNDA) algorithm was applied to polysomnography recordings to seek the balance of data sizes for different sleep stages. The second challenge is the difficulty in identifying a minority class of sleep stages, given their short sleep duration and similarities to other stages in terms of EEG characteristics. To overcome this, we developed a DeConvolution- and Self-Attention-based Model (DCSAM) which can inverse the feature map of a hidden layer to the input space to extract local features and extract the correlations between all possible pairs of features to distinguish sleep stages. The results on our dataset show that DCSAM based on GNDA obtains an accuracy of 90.26% and a macro F1-score of 86.51% which are higher than those of our previous method. We also tested DCSAM on a well-known public dataset-Sleep-EDFX-to prove whether it is applicable to sleep data from adults. It achieves a comparable performance to state-of-the-art methods, especially accuracies of 91.77%, 92.54%, 94.73%, and 95.30% for six-stage, five-stage, four-stage, and three-stage classification, respectively. These results imply that our DCSAM based on GNDA has a great potential to offer performance improvements in various medical domains by considering the data imbalance problems and correlations among features in time series data.

Varied performance of picture description task as a screening tool across MCI subtypes.

A picture description task is a component of Miro Health's platform for self-administration of neurobehavioral assessments. Picture description has been used as a screening tool for identification of individuals with Alzheimer's disease and mild cognitive impairment (MCI), but currently requires in-person administration and scoring by someone with access to and familiarity with a scoring rubric. The Miro Health implementation allows broader use of this assessment through self-administration and automated processing, analysis, and scoring to deliver clinically useful quantifications of the users' speech production, vocal characteristics, and language. Picture description responses were collected from 62 healthy controls (HC), and 33 participants with MCI: 18 with amnestic MCI (aMCI) and 15 with non-amnestic MCI (naMCI). Speech and language features and contrasts between pairs of features were evaluated for differences in their distributions in the participant subgroups. Picture description features were selected and combined using penalized logistic regression to form risk scores for classification of HC versus MCI as well as HC versus specific MCI subtypes. A picture-description based risk score distinguishes MCI and HC with an area under the receiver operator curve (AUROC) of 0.74. When contrasting specific subtypes of MCI and HC, the classifiers have an AUROC of 0.88 for aMCI versus HC and and AUROC of 0.61 for naMCI versus HC. Tests of association of individual features or contrasts of pairs of features with HC versus aMCI identified 20 features with p-values below 5e-3 and False Discovery Rates (FDRs) at or below 0.113, and 61 contrasts with p-values below 5e-4 and FDRs at or below 0.132. Findings suggest that performance of picture description as a screening tool for MCI detection will vary greatly by MCI subtype or by the proportion of various subtypes in an undifferentiated MCI population.

:Souvenirs and the Experience of Empire in Ancient Rome

:<i>Souvenirs and the Experience of Empire in Ancient Rome</i>

Rock Thin Section Image Identification Based on Convolutional Neural Networks of Adaptive and Second-Order Pooling Methods

In order to enhance the ability to represent rock feature information and finally improve the rock identification performance of convolution neural networks (CNN), a new pooling mode was proposed in this paper. According to whether the pooling object was the last convolution layer, it divided pooling layers into the sampling pooling layer and the classification pooling layer. The adaptive pooling method was used in the sampling pooling layer. The pooling kernels adaptively adjusted were designed for each feature map. The second-order pooling method was used by the classification pooling layer. The second-order feature information based on outer products was extracted from the feature pair. The changing process of the two methods in forward and back propagation was deduced. Then, they were embedded into CNN to build a rock thin section image identification model (ASOPCNN). The experiment was conducted on the image set containing 5998 rock thin section images of six rock types. The CNN models using max pooling, average pooling and stochastic pooling were set for comparison. In the results, the ASOPCNN has the highest identification accuracy of 89.08% on the test set. Its indexes are superior to the other three models in precision, recall, F1 score and AUC values. The results reveal that the adaptive and second-order pooling methods are more suitable for CNN model, and CNN based on them could be a reliable model for rock identification.

IGT: Illumination-guided RGB-T object detection with transformers

Multispectral object detection for autonomous driving has gotten significant attention in recent years. Since the complementing visual information provided by multispectral (i.e., RGB and thermal) could produce a more reliable detection result, which is crucial for the safety of autonomous driving. The previous studies have mainly focused on leveraging the illumination information in the decision-level fusion and suffered from generating reasonable illumination weights. In this paper, we propose IGT, an illumination-guided RGB-T object detection framework based on transformers, to effectively generate appropriate illumination weights and use them to guide multispectral feature rectification and fusion processes. Specifically, an illumination-based sub-network (IBSN) is first proposed to produce reasonable illumination weights from the mid-level features of the RGB stream. Then, we design an illumination-guided feature rectification module (IFRM) to determine the utilization level of the thermal modality’s illumination invariance according to the illumination intensity of the RGB image during the rectification process. With the rectified feature pairs, we deploy the illumination-guided feature fusion module (IFFM), which uses a novel illumination-based loss function to promote multispectral feature fusion and generate illumination-invariant fused features. Extensive experiments reveal that IGT achieves state-of-the-art performance on the FLIR dataset. Detailed analyses show that our network is robust under varying illumination conditions.

HMLNet: a hierarchical metric learning network with dual attention for change detection in high-resolution remote sensing images

ABSTRACT Change detection (CD) in high-resolution remote sensing images (RSIs) can be regarded as a binary visual recognition problem. Metric learning (ML) is a reliable method to determine pixel class attributes based on discriminative distance function between learnable image features. However, most related works learn discriminative distance functions in single-scale feature pairs, which suffer from slow convergence and poor local optima, partially due to that the loss function employs only large-scale feature samples while not interacting with the other scale features. Furthermore, more effective features are a prerequisite for improving the performance of ML-based CD. Hence, we propose a novel hierarchical metric learning network (HMLNet) with dual attention for CD in RSIs, where the key point is that hierarchical metric learning is performed in an ensemble manner to improve detection accuracy and accelerate model convergence. Specifically, based on the features extracted from the encoder-decoder backbone, we construct a feature pyramid to handle the complex details of objects at various scales in RSIs, and then perform metric learning between the paired pyramid features at the same scale. In addition, the dual-attention module is proposed to enhance the internal consistency of changed objects and effectively obtain more detailed information by acting on multi-scale pyramid features. Extensive experiments on the two public RSIs CD datasets, and the results demonstrate that the proposed HMLNet can accurately locate changed objects, which consistently outperforms the state-of-the-art CD competitors.

Testing feature‐rich blockchains

Blockchain implementations have become more and more advanced, combining many different features in the same framework (e.g., oracles, names, and state channels). Since the cost of errors in reputation and represented value is high in the blockchain world, software quality is of the utmost importance. One of the main methods used to assure such high software quality is careful testing. However, the number of tests needed to achieve a high level of assurance grows quadratic with the pairs of features of the blockchain, and when testing triples features the growth is cubic. To manually craft the required large number of tests is an almost impossible undertaking in practice. In this article, we describe how property-based testing (PBT) techniques have been used to automate testing of the core part of the Aeternity blockchain, ensuring the high software quality of the blockchain. Even though PBT is a powerful testing technique, applying it to the task of testing a complex system such as a blockchain, is far from trivial. The structure of the Aeternity property-based test model follows the structure of the blockchain, that is, it cleanly separates different blockchain features (e.g., oracles, smart contracts) into different model parts, and moreover, reduces the amount of boilerplate test model code by focusing on the identification of valid blockchain transactions. The test model is evaluated through a careful instrumentation of test code which permits observations of which combinations of features have been tested during a test run, and with which frequency. This article documents the details of how these issues were addressed in the development of the Aeternity test model, providing insights into both the testing of other blockchains as well as the testing of other complex feature based systems.

Validation of automated pipeline for the assessment of a motor speech disorder in amyotrophic lateral sclerosis (ALS).

Amyotrophic lateral sclerosis (ALS) frequently causes speech impairments, which can be valuable early indicators of decline. Automated acoustic assessment of speech in ALS is attractive, and there is a pressing need to validate such tools in line with best practices, including analytical and clinical validation. We hypothesized that data analysis using a novel speech assessment pipeline would correspond strongly to analyses performed using lab-standard practices and that acoustic features from the novel pipeline would correspond to clinical outcomes of interest in ALS. We analyzed data from three standard speech assessment tasks (i.e., vowel phonation, passage reading, and diadochokinesis) in 122 ALS patients. Data were analyzed automatically using a pipeline developed by Winterlight Labs, which yielded 53 acoustic features. First, for analytical validation, data were analyzed using a lab-standard analysis pipeline for comparison. This was followed by univariate analysis (Spearman correlations between individual features in Winterlight and in-lab datasets) and multivariate analysis (sparse canonical correlation analysis (SCCA)). Subsequently, clinical validation was performed. This included univariate analysis (Spearman correlation between automated acoustic features and clinical measures) and multivariate analysis (interpretable autoencoder-based dimensionality reduction). Analytical validity was demonstrated by substantial univariate correlations (Spearman's ρ > 0.70) between corresponding pairs of features from automated and lab-based datasets, as well as interpretable SCCA feature groups. Clinical validity was supported by strong univariate correlations between automated features and clinical measures (Spearman's ρ > 0.70), as well as associations between multivariate outputs and clinical measures. This novel, automated speech assessment feature set demonstrates substantial promise as a valid tool for analyzing impaired speech in ALS patients and for the further development of these technologies.

Preoperative 18F-FDG PET/CT and CT radiomics for identifying aggressive histopathological subtypes in early stage lung adenocarcinoma

Lung adenocarcinoma (ADC) is the most common non-small cell lung cancer. Surgical resection is the primary treatment for early-stage lung ADC while lung-sparing surgery is an alternative for non-aggressive cases. Identifying histopathologic subtypes before surgery helps determine the optimal surgical approach. Predominantly solid or micropapillary (MIP) subtypes are aggressive and associated with a higher likelihood of recurrence and metastasis and lower survival rates. This study aims to non-invasively identify these aggressive subtypes using preoperative 18F-FDG PET/CT and diagnostic CT radiomics analysis. We retrospectively studied 119 patients with stage I lung ADC and tumors ≤ 2 cm, where 23 had aggressive subtypes (18 solid and 5 MIPs). Out of 214 radiomic features from the PET/CT and CT scans and 14 clinical parameters, 78 significant features (3 CT and 75 PET features) were identified through univariate analysis and hierarchical clustering with minimized feature collinearity. A combination of Support Vector Machine classifier and Least Absolute Shrinkage and Selection Operator built predictive models. Ten iterations of 10-fold cross-validation (10 ×10-fold CV) evaluated the model. A pair of texture feature (PET GLCM Correlation) and shape feature (CT Sphericity) emerged as the best predictor. The radiomics model significantly outperformed the conventional predictor SUVmax (accuracy: 83.5% vs. 74.7%, p = 9e-9) and identified aggressive subtypes by evaluating FDG uptake in the tumor and tumor shape. It also demonstrated a high negative predictive value of 95.6% compared to SUVmax (88.2%, p = 2e-10). The proposed radiomics approach could reduce unnecessary extensive surgeries for non-aggressive subtype patients, improving surgical decision-making for early-stage lung ADC patients.

Dense Modality Interaction Network for Audio-Visual Event Localization

Human perception systems can integrate audio and visual information automatically to obtain a profound understanding of real-world events. Accordingly, fusing audio and visual contents is important to solve the audio-visual event (AVE) localization problem. Although most existing works have fused audio and visual modalities to explore their relationship with attention-based networks, we can delve into their relationship more deeply to improve the fusion capability of the two modalities. In this paper, we propose a dense modality interaction network (DMIN) to elegantly leverage audio and visual information by integrating two novel modules, namely, the audio-guided triplet attention (AGTA) module and the dense inter-modality attention (DIMA) module. The AGTA module enables audio information to guide the network to pay more attention to event-relevant visual regions. This guidance is conducted in the channel, temporal, and spatial dimensions, which emphasize informative features, temporal relationships and spatial regions, to boost the capacity of representations. Furthermore, the DIMA module establishes the dense-relationship between audio and visual modalities. Specifically, the DIMA module leverages the information of all channel pairs of audio and visual features to formulate the cross-modality attention weight, which is superior to the multi-head attention module that uses limited information. Moreover, a novel unimodal discrimination loss (UDL) is introduced to exploit the unimodal and fused features together for more exact AVE localization. The experimental results show that our method is remarkably superior to the state-of-the-art methods in fully- and weakly-supervised AVE settings. To further evaluate the model's ability to build audio-visual connections, we design a dense cross modality relation network (DCMR) to solve the cross-modality localization task. DCMR is a simple deformation of a DMIN, and the experimental results further illustrate that DIMA can explore denser relationships between the two modalities. Code is available at https://github.com/weizequan/DMIN.git.

Enhancing Spam Comment Detection on Social Media With Emoji Feature and Post-Comment Pairs Approach Using Ensemble Methods of Machine Learning

Enhancing Spam Comment Detection on Social Media With Emoji Feature and Post-Comment Pairs Approach Using Ensemble Methods of Machine Learning

A method for calculating two-dimensional spatially extension distances and its clustering algorithm

This paper presents a novel method for calculating the extension distance between a point and a two-dimensional convex set. The proposed method builds upon existing techniques by employing a line traversal approach. By traversing the convex set with a line originating from the point of interest, the extension distance is computed based on the intersection points between the line and the set along the two coordinate axes. The weights assigned to the intersection points play a crucial role in the distance calculation. By summing the extension distances in both directions, the overall extension distance of the point with respect to the set is obtained. Furthermore, a clustering algorithm is introduced, which incorporates the concept of an interaction factor commonly used in engineering experiments. The multidimensional data is projected onto feature planes created by combining pairs of features. The calculation method for extension distances between points and convex sets in two dimensions is applied to determine the distances between points and cluster classes (or cluster centers). The distances on each feature plane are then weighted, summed, and analyzed to establish the relationships between points and cluster classes, thereby achieving clustering. The feasibility of the proposed algorithm is validated through comparative experiments k-means algorithm on the iris dataset and the wine dataset. The experimental results confirm the effectiveness and viability of the proposed approach.

Contrastive 3D Human Skeleton Action Representation Learning via CrossMoCo With Spatiotemporal Occlusion Mask Data Augmentation

Self-supervised learning methods for 3D skeleton-based action recognition via contrastive learning have obtained competitive achievements compared to classical supervised methods. Current researches show that adding a Multilayer Perceptron (MLP) to the top of the base encoder can extract high-level and global positive representations. Using a negative memory bank to store negative samples dynamically can balance the ample storage and feature consistency. However, these methods need to consider that the MLP lacks accurate encoding of fine-grained local features, and a memory bank needs rich and diverse negative sample pairs to match positive representations from different encoders. This paper proposes a new method called Cross Momentum Contrast (CrossMoCo), composed of three parts: ST-GCN encoder, ST-GCN encoder with MLP encoder (ST-MLP encoder), and two independent negative memory banks. The two encoders encode the input data into two positive feature pairs. Learning the cross representations of the two positive pairs is helpful for the model to extract both the global and the local information. Two independent negative memory banks update the negative samples according to different positive representations from two encoders, diversifying the negative samples' distribution and making negative representations close to the positive features. The increasing classification difficulty will improve the model's ability of contrastive learning. In addition, the spatiotemporal occlusion mask data augmentation method is used to enhance positive samples' information diversity. This method takes the adjacent skeleton joints that can form a skeleton bone as a mask unit, which can reduce the information redundancy after data augmentation since adjacent joints may carry similar spatiotemporal information. Experiments on the PKU-MMD Part II dataset, the NTU RGB+D 60 dataset, and the NW-UCLA dataset show that the CrossMoCo framework with spatiotemporal occlusion mask data augmentation has achieved a comparable performance.

A half jaw panoramic stitching method of intraoral endoscopy images based on dental arch arrangement.

To address the challenges of repetitive and low-texture features in intraoral endoscopic images, a novel methodology for stitching panoramic half jaw images of the oral cavity is proposed. Initially, an enhanced self-attention mechanism guided by Time-Weighting concepts is employed to augment the clustering potential of feature points, thereby increasing the number of matched features. Subsequently, a combination of the Sinkhorn algorithm and Random Sample Consensus (RANSAC) is utilized to maximize the count of matched feature pairs, accurately remove outliers and minimize error. Last, to address the unique spatial alignment among intraoral endoscopic images, a wavelet transform and weighted fusion algorithm based on dental arch arrangement in intraoral endoscopic images have been developed, specifically for use in the fusion stage of intraoral endoscopic images. This enables the local oral images to be precisely positioned along the dental arch, and seamless stitching is achieved through wavelet transformation and a gradual weighted fusion technique. Experimental results demonstrate that this method yields promising outcomes in panoramic stitching tasks for intraoral endoscopic images, achieving a matching accuracy of 84.6% and a recall rate of 78.4% in a dataset with an average overlap of 35%. A novel solution for panoramic stitching of intraoral endoscopic images is provided by this method.

A radiomics model development via the associations with genomics features in predicting axillary lymph node metastasis of breast cancer: a study based on a public database and single-centre verification

To evaluate the predictive performance of the radiomics model in predicting axillary lymph node (ALN) metastasis through the associations between radiomics features and genomic features in patients with breast cancer. Patients with breast cancer were enrolled retrospectively from a public database (111 patients as training group) and one hospital (15 patients as external validation group). The genomics features from transcriptome data and radiomics features from dynamic contrast-enhanced magnetic resonance imaging (MRI) were collected. Firstly, overlapping genes were identified using the Kyoto Encyclopedia of Genes and Genomes and differentially expressed gene analysis, while radiomics features were reduced using a data-driven method. Then, the associations between overlapping genes and retained radiomics features were assessed to obtain key pairs of radiomics-genomics features. Furthermore, the least absolute shrinkage and selection operator (LASSO) algorithm was used to detect the key-pairs features. Finally, radiomics and genomics models were constructed to predict ALN metastasis. After using the hybrid data- and gene-driven selection method, key pairs of features were detected, which consisted of six radiomic features associated with four genomic features. The radiomics model exhibited comparable performance to the genomics model in predicting ALN metastasis (radiomic model: area under the curve [AUC] = 0.71, sensitivity = 77%, specificity = 56%; genomic model: AUC = 0.72, sensitivity = 85%, specificity = 74%). The four genomic features were enriched in six pathways and related to metabolism and human diseases. The radiomics model established using the gene-driven hybrid selection method could predict ALN metastasis in breast cancer, which showed comparable performance to the genomics model.

A network approach for low dimensional signatures from high throughput data

One of the main objectives of high-throughput genomics studies is to obtain a low-dimensional set of observables—a signature—for sample classification purposes (diagnosis, prognosis, stratification). Biological data, such as gene or protein expression, are commonly characterized by an up/down regulation behavior, for which discriminant-based methods could perform with high accuracy and easy interpretability. To obtain the most out of these methods features selection is even more critical, but it is known to be a NP-hard problem, and thus most feature selection approaches focuses on one feature at the time (k-best, Sequential Feature Selection, recursive feature elimination). We propose DNetPRO, Discriminant Analysis with Network PROcessing, a supervised network-based signature identification method. This method implements a network-based heuristic to generate one or more signatures out of the best performing feature pairs. The algorithm is easily scalable, allowing efficient computing for high number of observables (10^3–10^5). We show applications on real high-throughput genomic datasets in which our method outperforms existing results, or is compatible with them but with a smaller number of selected features. Moreover, the geometrical simplicity of the resulting class-separation surfaces allows a clearer interpretation of the obtained signatures in comparison to nonlinear classification models.

A deep learning approach to estimate the state of health of lithium-ion batteries under varied and incomplete working conditions

The reliable state of health (SOH) estimation of lithium-ion batteries ensures the safety and efficiency of electric vehicles and energy storage systems. However, when the battery is under varied and incomplete working conditions, the estimation of SOH is still challenging due to the diversity and irregularity of the health indicators. Thus, an algorithm with strongly nonlinear capability is required. In this paper, a dilated residual regression network is presented for estimating the SOH of lithium-ion batteries under varied and incomplete charging conditions. The incremental capacity and voltage are extracted as feature pairs from varied conditions with fixed charging ranges to build the feature matrix. Then the dilated convolution initially extracts the shallow features of the feature matrix, which is subsequently fed into the deep residual network to estimate the SOH of the batteries. The accuracy and robustness of the proposed method are verified by comparison with machine learning algorithms and shallow convolutional networks. The interpretability of the proposed deep model is further improved by analyzing the occlusion sensitivity map of shallow and deep layers. These efforts enhance the application of SOH estimation methods in the real world.

Graph Attention Interaction Aggregation Network for Click-Through Rate Prediction

Click-through rate prediction is a critical task for computational advertising and recommendation systems, where the key challenge is to model feature interactions between different feature domains. At present, the main click-through rate prediction models model feature interactions in an implicit way, which leads to poor interpretation of the model, and the interaction between each pair of features may introduce noise into the model, thus limiting the predictive ability of the model. In response to the above problems, this paper proposes a click-through rate prediction model (GAIAN) based on the graph attention interactive aggregation network, which explicitly obtains cross features on the graph structure. Our specific method is to design a feature interactive selection mechanism to select cross features that are beneficial to model prediction, reducing model noise and reducing the risk of model overfitting. On this basis, the bilinear interaction function is integrated into the aggregation strategy of the graph neural network, and the fine-grained intersection features are extracted in a flexible and explicit way, which makes graph neural networks more suitable for modeling feature interactions and enhances the interpretability of the model. Compared with several other state-of-the-art models on the Criteo and Avazu datasets, the experimental results show the superiority of the model.

COVID-19 Progression: A County-Level Analysis of Vaccination and Case Fatality in Mississippi, USA.

The COVID-19 pandemic has created a severe upheaval in the U.S., with a particular burden on the state of Mississippi, which already has an exhausted healthcare burden. The main objectives of this study are: (1) to analyze the county-level COVID-19 cases, deaths, and vaccine distribution and (2) to determine the correlation between various social determinants of health (SDOH) and COVID-19 vaccination coverage. We analyzed COVID-19-associated data and county-level SDOH factors in 82 counties of Mississippi. The cumulative COVID-19 and socio-demographic data variables were grouped into feature and target variables. The statistical and exploratory data analysis (EDA) was conducted using Python 3.8.5. The correlation between the target and feature variables was performed by Pearson Correlation analysis. The heat Map Correlation Matrix was visually presented to illustrate the correlation between each pair of features and each target variable. Results indicated that people of Asian descent had the highest vaccination coverage of 77% fully vaccinated compared to 52%, 46%, 42% and 25% for African Americans, Whites, Hispanics, and American Indians/Alaska Natives, respectively. The county-level vaccination rate was significantly higher among the minority populations than the White population. It was observed that COVID-19 cases and deaths were positively correlated with per capita income and negatively correlated with the percentage of persons without a high school diploma (age 25+). This study strongly demonstrates that different SDOH factors influence the outcome of the COVID-19 vaccination rate, which also affects the total number of COVID-19 cases and deaths. Vaccine promotion should be given to all populations regardless of race and ethnicity to achieve uniform acceptance. Therefore, statewide policy recommendations focusing on specific community needs should help achieve health equity in COVID-19 vaccination management.