Set Of Features Research Articles

Jake Seller Draw impact structure, Bighorn Basin, Wyoming, USA: The deepest known buried impact structure on Earth and its possible relation to the Wyoming crater field

We provide evidence demonstrating the impact origin of a structure, here named the Jake Seller Draw impact structure, which is buried below the Jake Seller Draw drainage basin, in the Bighorn Basin of Wyoming, western United States. The 4.3-km-diameter structure was first recognized as a seismic disturbance at a depth of ∼6.5 km in two- and three-dimensional seismic profiles. Microstructural analysis of drill cuttings situated in the center and outside of Jake Seller Draw revealed the presence of multiple sets of planar deformation features and planar fractures in nine quartz grains, thereby confirming the hypervelocity impact origin of the structure. The seismic data show that Jake Seller Draw is a complex impact structure containing a 1-km-wide central uplift. The geologic and seismic data suggest that Jake Seller Draw is the most deeply buried impact structure known on Earth to date. The stratigraphic framework suggests that the crater was formed in a nearshore environment at the Pennsylvanian−Permian boundary, ∼280 m.y. ago. This age coincides with the age of the Wyoming crater field 300 km southeast of Jake Seller Draw and may suggest a common origin.

Identifying relevant features of CSE-CIC-IDS2018 dataset for the development of an intrusion detection system

Intrusion detection systems (IDSs) are essential elements of IT systems. Their key component is a classification module that continuously evaluates some features of the network traffic and identifies possible threats. Its efficiency is greatly affected by the right selection of the features to be monitored. Therefore, the identification of a minimal set of features that are necessary to safely distinguish malicious traffic from benign traffic is indispensable in the course of the development of an IDS. This paper presents the preprocessing and feature selection workflow as well as its results in the case of the CSE-CIC-IDS2018 on AWS dataset, focusing on five attack types. To identify the relevant features, six feature selection methods were applied, and the final ranking of the features was elaborated based on their average score. Next, several subsets of the features were formed based on different ranking threshold values, and each subset was tried with five classification algorithms to determine the optimal feature set for each attack type. During the evaluation, four widely used metrics were taken into consideration.

Research on automatic detection of gradual fault of high voltage electric energy metering transformer based on fuzzy rough set and whale optimization algorithm

Based on fuzzy rough set and whale optimization algorithm, the automatic fault detection method of high-voltage electric energy metering transformer is studied to improve the fault diagnosis effect and efficiency. On the basis of constructing the mathematical model of gradual fault of high-voltage electric energy metering transformer, the fuzzy rough set theory is used to reduce the data attributes of fault samples, eliminate similar attributes, determine the minimum fault feature set, and complete the fault feature selection, which is used as the input of the fault detection model based on Whale Optimization Algorithm-based Support Vector Machine (WOA-SVM). After the kernel parameters and penalty factors of SVM are optimized by whale optimization algorithm, the type of gradual fault of high-voltage electric energy metering transformer is identified. The experimental results show that the reduced fault attributes are distributed differently in the sample data, and the fault detection accuracy can be improved by 9.5 % through fault feature selection. The fault diagnosis model with Gaussian radial basis function, kernel parameter of 0.05 and penalty factor of 10 has the best performance. This method can identify the gradual fault types of high-voltage electric energy metering transformers, and the fault diagnosis effect is outstanding.

A machine learning model to predict heart failure readmission: toward optimal feature set.

Hospital readmissions for heart failure patients remain high despite efforts to reduce them. Predictive modeling using big data provides opportunities to identify high-risk patients and inform care management. However, large datasets can constrain performance. This study aimed to develop a machine learning based prediction model leveraging a nationwide hospitalization database to predict 30-day heart failure readmissions. Another objective of this study is to find the optimal feature set that leads to the highest AUC value in the prediction model. Heart failure patient data was extracted from the 2020 Nationwide Readmissions Database. A heuristic feature selection process incrementally incorporated predictors into logistic regression and random forest models, which yields a maximum increase in the AUC metric. Discrimination was evaluated through accuracy, sensitivity, specificity and AUC. A total of 566,019 discharges with heart failure diagnosis were recognized. Readmission rate was 8.9% for same-cause and 20.6% for all-cause diagnoses. Random forest outperformed logistic regression, achieving AUCs of 0.607 and 0.576 for same-cause and all-cause readmissions respectively. Heuristic feature selection resulted in the identification of optimal feature sets including 20 and 22 variables from a pool of 30 and 31 features for the same-cause and all-cause datasets. Key predictors included age, payment method, chronic kidney disease, disposition status, number of ICD-10-CM diagnoses, and post-care encounters. The proposed model attained discrimination comparable to prior analyses that used smaller datasets. However, reducing the sample enhanced performance, indicating big data complexity. Improved techniques like heuristic feature selection enabled effective leveraging of the nationwide data. This study provides meaningful insights into predictive modeling methodologies and influential features for forecasting heart failure readmissions.

Utilization of texture features of volumetric ADC maps in differentiating between serous cystadenoma and intraductal papillary neoplasms.

The rising incidence of incidental detection of pancreatic cystic neoplasms has compelled radiologists to determine new diagnostic methods for the differentiation of various kinds of lesions. We aim to demonstrate the utility of texture features extracted from ADC maps in differentiating intraductal papillary mucinous neoplasms (IPMN) from serous cystadenomas (SCA). This retrospective study was performed on 136 patients (IPMN = 87, SCA = 49) split into testing and training datasets. A total of 851 radiomics features were extracted from volumetric contours drawn by an expert radiologist on ADC maps of the lesions. LASSO regression analysis was used to determine the most predictive set of features and a radiomics score was developed based on their respective coefficients. A hyper-optimized support vector machine was then utilized to classify the lesions based on their radiomics score. A total of four Wavelet features (LHL/GLCM/LCM2, HLL/GLCM/LCM2, /LLL/First Order/90percent, /LLL/GLCM/MCC) were selected from all of the features to be included in our classifier. The classifier was optimized by altering hyperparameters and the trained model was applied to the validation dataset. The model achieved a sensitivity of 92.8, specificity of 90%, and an AUC of 0.97 in the training data set, and a sensitivity of 83.3%, specificity of 66.7%, and AUC of 0.90 in the testing dataset. A support vector machine model trained and validated on volumetric texture features extracted from ADC maps showed the possible beneficence of these features in differentiating IPMNs from SCAs. These results are in line with previous regarding the role of ADC maps in classifying cystic lesions and offers new evidence regarding the role of texture features in differentiation of potentially neoplastic and benign lesions.

Health Management of Bearings Using Adaptive Parametric VMD and Flying Squirrel Search Algorithms to Optimize SVM

Bearing, as one of the core parts of rotating machinery, has a running state which is related to the overall operation of the system. Due to the bearing structure and its complex operating environment, running condition monitoring and fault diagnosis is always a key problem in the field of bearing health management, which is of great significance for bearing maintenance and equipment reliability and safety. In view of the difficulty in parameter selection and poor feature extraction ability of variational mode decomposition (VMD) in existing feature extraction, this paper uses the flying squirrel search algorithm (SSA) to optimize the parametric of decomposition layer k and penalty factor α in VMD, and forms an adaptive VMD signal decomposition method. To solve the problem of high dimensionality and long extraction time of multi-domain fault feature set, kernel principal component analysis (KPCA) is used to reduce feature dimensionality. Then, the processed features are input into the support vector machine (SVM) for fault diagnosis and classification, and the parameter optimization ability of SSA is used again to build the SSA-SVM fault diagnosis model. To evaluate the running state of bearings, an alarm threshold method based on the root mean square value calculated by cosine similarity and 3σ is proposed to divide samples of different health states. Finally, the method constructed in this paper is compared with other methods by using simulation and experimental data sets, and the running condition monitoring and fault diagnosis of rolling bearings are successfully realized, which shows the superiority and effectiveness of the method proposed in this paper.

Distributed Feature Selection for Power System Dynamic Security Region Based on Grid-Partition and Fuzzy-Rough Sets

In order to satisfy the requirements of modern online security assessment of power systems with continuously increasing complexity in terms of structure and scale, it is desirable to develop a power system dynamic security region (DSR) analysis. However, data-driven methods suffer from expensive model training costs and overfitting when determining DSR boundaries with high-dimensional grid features. Given this problem, a distributed feature selection method based on grid partition and fuzzy-rough sets is proposed in this paper. The method first employs the Louvain algorithm to partition the power grid and divide the original feature set so that high-dimensional features can be allocated to multiple computational units for distributed screening. At this point, the connections between features of different computational units are minimized to a relatively low level, thereby avoiding large errors in the distributed results. Then, an incremental search algorithm based on the fuzzy-rough set theory (FRST) is used for feature selection at each computational unit, which can effectively take into account the intrinsic connections between features. Finally, the results of all computational units are integrated in the coordination unit to complete the overall feature selection. The experimental results based on the IEEE-39 bus system show that the proposed method can help simplify the power system DSR analysis with high-dimensional features by screening the critical features. And compared with other commonly used filter methods, it has higher screening accuracy and lower time costs.

Outlier detection using flexible categorization and interrogative agendas

Categorization is one of the basic tasks in machine learning and data analysis. Building on formal concept analysis (FCA), the starting point of the present work is that different ways to categorize a given set of objects exist, which depend on the choice of the sets of features used to classify them, and different such sets of features may yield better or worse categorizations, relative to the task at hand. In their turn, the (a priori) choice of a particular set of features over another might be subjective and express a certain epistemic stance (e.g. interests, relevance, preferences) of an agent or a group of agents, namely, their interrogative agenda. In the present paper, we represent interrogative agendas as sets of features, and explore and compare different ways to categorize objects w.r.t. different sets of features (agendas). We first develop a simple unsupervised FCA-based algorithm for outlier detection which uses categorizations arising from different agendas. We then present a supervised meta-learning algorithm to learn suitable (fuzzy) agendas for categorization as sets of features with different weights or masses. We combine this meta-learning algorithm with the unsupervised outlier detection algorithm to obtain a supervised outlier detection algorithm. We show that these algorithms perform at par with commonly used algorithms for outlier detection on commonly used datasets in outlier detection. These algorithms provide both local and global explanations of their results.

Ranking and filtering of neuropathology features in the machine learning evaluation of dementia studies.

Early diagnosis of dementia diseases, such as Alzheimer's disease, is difficult because of the time and resources needed to perform neuropsychological and pathological assessments. Given the increasing use of machine learning methods to evaluate neuropathology features in the brains of dementia patients, it is important to investigate how the selection of features may be impacted and which features are most important for the classification of dementia. We objectively assessed neuropathology features using machine learning techniques for filtering features in two independent ageing cohorts, the Cognitive Function and Aging Studies (CFAS) and Alzheimer's Disease Neuroimaging Initiative (ADNI). The reliefF and least loss methods were most consistent with their rankings between ADNI and CFAS; however, reliefF was most biassed by feature-feature correlations. Braak stage was consistently the highest ranked feature and its ranking was not correlated with other features, highlighting its unique importance. Using a smaller set of highly ranked features, rather than all features, can achieve a similar or better dementia classification performance in CFAS (60%-70% accuracy with Naïve Bayes). This study showed that specific neuropathology features can be prioritised by feature filtering methods, but they are impacted by feature-feature correlations and their results can vary between cohort studies. By understanding these biases, we can reduce discrepancies in feature ranking and identify a minimal set of features needed for accurate classification of dementia.

Feature selection based on dataset variance optimization using Hybrid Sine Cosine – Firehawk Algorithm (HSCFHA)

Feature selection plays a pivotal role in preprocessing data for machine learning (ML) models. It entails choosing a subset of pertinent features to enhance the model’s accuracy and minimize overfitting. Wrapper methods based on metaheuristics are one approach to feature selection, leveraging the predictive accuracy of a learning algorithm to form a condensed set of features. Traditionally, this method uses K-Nearest Neighbor (KNN) for maximizing accuracy as its cost function. However, this approach often yields less than optimal results in large sample spaces and demands considerable computational resources. To circumvent the shortcomings of this approach, this work proposes a novel metaheuristic algorithm, termed the Hybrid Sine Cosine Firehawk Algorithm. Furthermore, a novel feature selection technique is designed that uses this hybrid algorithm to eliminate insignificant and redundant features by incorporating the minimization of dataset variance in the cost function. Additionally, the hybridization of multiple metaheuristic algorithms produces the best features of each algorithm to improve the exploration ability. The proposed technique is tested on 22 University of California Irvine datasets containing low, medium and high dimensional datasets and compared to the traditional KNN-based approach. The technique is also compared with other state-of-the-art metaheuristic techniques, namely Particle Swarm Optimizer, Grey Wolf Optimizer, Whale Optimization Algorithm, Hybrid Ant Colony Optimizer and Improved Binary Bat Algorithm. The results show significant improvements over previous techniques in terms of minimal loss in essential data while reducing the size of the raw data in considerably less time, as well as a well-balanced confusion matrix.

Engineering Features from Raw Sensor Data to Analyse Player Movements during Competition.

Research in field sports often involves analysis of running performance profiles of players during competitive games with individual, per-position, and time-related descriptive statistics. Data are acquired through wearable technologies, which generally capture simple data points, which in the case of many team-based sports are times, latitudes, and longitudes. While the data capture is simple and in relatively high volumes, the raw data are unsuited to any form of analysis or machine learning functions. The main goal of this research is to develop a multistep feature engineering framework that delivers the transformation of sequential data into feature sets more suited to machine learning applications.

Intelligent assessment of atrial fibrillation gradation based on sinus rhythm electrocardiogram and baseline information

BackgroundAtrial fibrillation (AF) is a progressive arrhythmia that significantly affects a patient's quality of life. The 4S-AF scheme is clinically recommended for AF management; however, the evaluation process is complex and time-consuming. This renders its promotion in primary medical institutions challenging. This retrospective study aimed to simplify the evaluation process and present an objective assessment model for AF gradation. MethodsIn total, 189 12-lead electrocardiogram (ECG) recordings from 64 patients were included in this study. The data were annotated into two groups (mild and severe) according to the 4S-AF scheme. Using a preprocessed ECG during the sinus rhythm (SR), we obtained a synthesized vectorcardiogram (VCG). Subsequently, various features were calculated from both signals, and age, sex, and medical history were included as baseline characteristics. Different machine learning models, including support vector machines, random forests (RF), and logistic regression, were finally tested with a combination of feature selection techniques. ResultsThe proposed method demonstrated excellent performance in the classification of AF gradation. With an optimized feature set of VCG and baseline features, the RF model achieved accuracy, sensitivity, and specificity of 83.02 %, 80.56 %, and 88.24 %, respectively, under the inter-patient paradigm. ConclusionOur results demonstrate the value of physiological signals in AF gradation evaluation, and VCG signals were effective in identifying mild and severe AF. Considering its low computational complexity and high assessment performance, the proposed model is expected to serve as a useful prognostic tool for clinical AF management.

Hybrid deep architecture for software defect prediction with improved feature set

Hybrid deep architecture for software defect prediction with improved feature set

Tuned weighted feature fusion with hybridized DNN-RNN framework for plant disease detection and classification

ABSTRACT In the world economy, agriculture is an essential part among individuals to earn money. But, the farmers face more obstacles because more diseases naturally affect the health of the plant. Hence, to overcome this limitation, automatic plant disease identification techniques are essential to monitor the growth as well as disease-affected plants and leaves. In most plants, symptoms related to plant disease can be identified by considering the leaves. Moreover, plant disease identification became more essential with deep learning architecture. Hence, it is important to enhance the solution for resource-constrained portable devices like smartphones, but it become a complicated issue as the deeply structured methods utilize extensive resources for the analysis. Hence, this paper aims to develop an automated plant disease detection framework with an advanced set of plant features. The plant images are taken from online sources. The acquired plant images undergo image enhancement using the contrast enhancement process. The enhanced images are fed in the feature retrieval phase 1, where the segmentation takes place using the Centre Optimized K-means clustering (CO-KMC) with the Modified Random Variable-based Black Widow Optimization (MRV-BWO). Later, the segmented images obtain the colour, shape, and texture features and they are considered as the first set of features. The second set of features is retrieved from the enhanced images using Multi-scale Dilated Attention CNN (MSDA-CNN). These two features are fused by the weighted feature fusion process using the developed MRV-BWO. Then, the plant diseases are detected using the Hybridized Deep Neural Network with Recurrent Neural Network (HDNN-RNN), which comprises RNN and DNN models. The parameter optimization takes place in the hybrid HDNN-RNN for improving the detection efficiency using MRV-BWO. From the verification of the findings, the recommended model obtains a 96.47 precision and accuracy rate. Therefore, the simulation results of the offered model reveal that it achieves enriched efficacy when comparing other baseline approaches.

Expanded experience with cardiovascular black blood cinematic rendering.

Black blood cinematic rendering (BBCR) is a newly described preset for cinematic rendering, which creates photorealistic displays from volumetric data sets with the contrast-enhanced blood pool displayed as dark and transparent. That set of features potentially provides for enhanced visualization of endomyocardial and intraluminal pathology, as well as cardiac devices. The similarity of the images to black-blood magnetic resonance imaging (MRI) may allow for expansion of the evaluation of certain types of pathology into patient populations unable to undergo MRI. In the emergency setting, the rapid acquisition time and reasonable post-processing time make this technique clinically feasible. In this expanded experience, we demonstrate an expanded clinical experience with the BBCR technique, highlighting the applications for intraluminal cardiovascular evaluation, especially focused on current and potential emergency radiology applications.

Refrigerant leak detection in industrial vapor compression refrigeration systems using machine learning

Efficient detection of refrigerant leakage is of utmost importance for industrial refrigeration systems due to its potential to cause substantial impacts on system performance and the environment. Existing research on fault detection and diagnosis in refrigeration systems primarily revolves around solutions based on experimental or laboratory data. However, in the industrial use case, achieving accurate and early detection poses significant challenges. This paper reports on the development of a novel refrigerant leak detection method for industrial vapor compression refrigeration systems. Our method leverages real-world data obtained from operational installations, enabling us to assess its reliability and applicability. The proposed data-driven approach involves predicting the fault-free liquid level in the installation receiver and comparing the actual and predicted levels. In this work, we place emphasis on features and model selection. Dedicated metrics combined with a model comparison method are proposed to evaluate and compare the performance of commonly used regression models with two sets of features to determine the most effective one. Furthermore, we provide insights into the results obtained from the deployment of the proposed method in real-world industrial installations.

A Generative Approach to Person Reidentification.

Person Re-identification is the task of recognizing comparable subjects across a network of nonoverlapping cameras. This is typically achieved by extracting from the source image a vector of characteristic features of the specific person captured by the camera. Learning a good set of robust, invariant and discriminative features is a complex task, often leveraging contrastive learning. In this article, we explore a different approach, learning the representation of an individual as the conditioning information required to generate images of the specific person starting from random noise. In this way we decouple the identity of the individual from any other information relative to a specific instance (pose, background, etc.), allowing interesting transformations from one identity to another. As generative models, we use the recent diffusion models that have already proven their sensibility to conditioning in many different contexts. The results presented in this article serve as a proof-of-concept. While our current performance on common benchmarks is lower than state-of-the-art techniques, the approach is intriguing and rich of innovative insights, suggesting a wide range of potential improvements along various lines of investigation.

Fault section location in resonant grounding distribution systems based on feature subset optimization of phase current variation

SummaryThe existing single‐phase grounding (SPG) fault section location methods typically suffer from difficulty in feature selection, limited feeder terminal units (FTUs) configuration, and excessive dependence on communication, which weaken their generalization and robustness. To overcome these challenges, an SPG fault section location approach based on feature subset optimization is proposed. First, the relation between the position of FTU and its three‐phase current variation is analyzed, and its fault features are extracted to construct the candidate feature sets as feature subset optimization objects. Then, genetic algorithm and support vector machine (SVM) are combined to select the optimal feature subset with small dimensions and recognition error, which avoids the empirical errors of artificial feature selection. To reduce the cumulative errors, the SVM hyperparameters are simultaneously optimized. Finally, the SVM model is trained based on the optimal feature subset and hyperparameters. In the absence of zero‐sequence current measurement, three‐phase currents measured by FTU are locally processed to locate the fault section by the trained SVM. The experimental results verified the effectiveness and feasibility of the proposed method.

Fast building detection using new feature sets derived from a very high-resolution image, digital elevation and surface model

ABSTRACT Detecting building rooftops with very high-resolution (VHR) images is an important issue in many fields, including disaster management, urban planning, and climate change research. Buildings with varying geometrical features are challenging to detect accurately from VHR image due to complicated image scenes containing spectrally similar objects, illumination, occlusions, viewing angles, and shadows. This study aims to detect building rooftops with high accuracy using a new framework that includes VHR image, visible band difference vegetation index, digital surface and elevation models, the terrain ruggedness and the topographic position index. Five distinct feature sets were generated in order of importance by exposing the ten related stacking features to a feature selection procedure using the maximum relevance minimum redundancy method. Then, Auto-Encoder, k-NN, decision tree, RUSBoost, and random forest machine learning algorithms were utilized for binary classification. Random forest yielded the highest accuracy (97.2% F-score, 98.72% accuracy) when all features (F10) were used, while decision tree was the least successful (59.16% F-score, 83.56% accuracy) for RGB feature set (FRGB). It was revealed that classification of F10 with random forest increased F-score by about 23% compared to classification with FRGB. Additionally, McNemar’s tests showed no statistically significant difference between random forest vs k-NN and decision tree vs RUSBoost.

Rolling bearing fault diagnosis based on improved whale-optimization- algorithm–variational-mode-decomposition method

Rolling bearings are a key component of rotating machinery and their health directly affects the safe operation of mechanical equipment. Therefore, fault diagnose for rolling bearings is very important. The fault diagnosis process of rolling bearings includes three stages: signal decomposition, feature extraction, and pattern recognition. Variational mode decomposition (VMD) can suppress end effects, but improper parameter settings will cause information losses or excessive decomposition. In this work, an improved whale optimization algorithm (IWOA) is applied to parameter settings of VMD. Correspondingly, an IWOA-VMD signal decomposition method is proposed. The decomposed signal is combined with a Laplace score method and classifier to remove the redundancy and noise in the feature set and obtain a low-dimensional sensitive feature subset. Then, aiming at the problem of the parameter settings of a least squares support vector machine (LSSVM) affecting the recognition performance and accuracy, a salp swarm algorithm (SSA) is used to globally optimize the penalty parameter and kernel width in the LSSVM to establish an SSA-LSSVM fault recognition model. This model is applied to the fault diagnosis of rolling bearings. In particular, rolling bearing fault samples at Case Western Reserve University are used to verify the method. The results indicate that the proposed method is effective and improves the speed and accuracy of fault diagnosis.