Feature Clustering Approach Research Articles

Wind Speed Forecasting with a Clustering-Based Deep Learning Model

The predictability of wind energy is crucial due to the uncertain and intermittent features of wind energy. This study proposes wind speed forecasting models, which employ time series clustering approaches and deep learning methods. The deep learning (LSTM) model utilizes the preprocessed data as input and returns data features. The Dirichlet mixture model and dynamic time-warping method cluster the time-series data features and then deep learning in forecasting. Particularly, the Dirichlet mixture model and dynamic warping method cluster the time-series data features. Next, the deep learning models use the entire (global) and clustered (local) data to capture the long-term and short-term patterns, respectively. Furthermore, an ensemble model is obtained by integrating the global model and local model results to exploit the advantages of both models. Our models are tested on four different wind data obtained from locations in Turkey with different wind regimes and geographical aspects. The numerical results indicate that the proposed ensemble models achieve the best accuracy compared to the deep learning method (LSTM). The results imply that the feature clustering approach accommodates a promising framework in forecasting.

Airborne Microbial Aerosol Detection by Combining Single Particle Mass Spectrometry and a Fluorescent Aerosol Particle Sizer.

Detection methods for microbiological aerosols based on single particle mass spectrometry (SPAMS) and a fluorescent aerosol particle sizer (FLAPS) have been developed progressively. However, they encounter interference and inefficiency issues. By merging FLAPS and SPAMS technologies, the majority of inorganic ambient aerosols may be eliminated by the FLAPS, thus resolving SPAMS' large data volume. SPAMS, on the other hand, may eliminate the secondary fluorescence interference that plagues the FLAPS. With the addition of the enhanced machine learning classifier, it is possible to extract microbial aerosol signals more precisely. In this work, a FLAPS-SPAMS instrument and a Random Forest classifier based on Kendall's correlation expansion training set approach were built. In addition to analyzing the outdoor microbial proportions, the interference components of non-microbial fluorescent particles were also examined. Results indicate that the fraction of outdoor microbial aerosols in fluorescent particles is 25.72% or roughly 2.57% of total particles. Traditional ART-2A algorithm and semi-empirical feature clustering approaches were used to identify the interference categories of abiotic fluorescent particles, which were mostly constituted of EC/OC, LPG/LNG exhaust, heavy metal organics, nicotine, vinylpyridine, polycyclic aromatic hydrocarbons (PAHs), and polymers, accounting for 68.51% of fluorescent particles.

Tracking the Connection Between Brazilian Agricultural Diversity and Native Vegetation Change by a Machine Learning Approach

In Brazil, agribusiness has a considerable role in the country's GDP. Because of this, the State needs territorial planning to minimize the impacts on natural resources, especially in the Pantanal and Amazon biomes, where agribusiness has expanded. The lower the agricultural diversification, the lower the pattern of land use homogeneity, generally associated with agribusiness, especially when it occupies large areas with more technological productive units. This paper investigates the relationship between spatial diversification patterns and the dynamics of native vegetation in Brazil. We propose a feature engineering and clustering approach for 5570 Brazilian municipalities between 1999 and 2018. It was based on the unsupervised artificial neural network Self-Organizing Map (SOM) to divide the municipalities into homogeneous groups of agricultural products diversity trends. The results were compared with the change in vegetation area using data from the national land use-mapping project called Mapbiomas. The analysis allowed the identification of three different regimes of modification in native vegetation, particularly related to municipalities in Brazil's Midwest and North regions, indicating substantial changes in the Cerrado and Amazon biomes.

The construction of an accurate Arabic sentiment analysis system based on resources alteration and approaches comparison

PurposeThis paper purposed a multi-facet sentiment analysis system.Design/methodology/approachHence, This paper uses multidomain resources to build a sentiment analysis system. The manual lexicon based features that are extracted from the resources are fed into a machine learning classifier to compare their performance afterward. The manual lexicon is replaced with a custom BOW to deal with its time consuming construction. To help the system run faster and make the model interpretable, this will be performed by employing different existing and custom approaches such as term occurrence, information gain, principal component analysis, semantic clustering, and POS tagging filters.FindingsThe proposed system featured by lexicon extraction automation and characteristics size optimization proved its efficiency when applied to multidomain and benchmark datasets by reaching 93.59% accuracy which makes it competitive to the state-of-the-art systems.Originality/valueThe construction of a custom BOW. Optimizing features based on existing and custom feature selection and clustering approaches.

A copula based topology preserving graph convolution network for clustering of single-cell RNA-seq data.

Annotation of cells in single-cell clustering requires a homogeneous grouping of cell populations. There are various issues in single cell sequencing that effect homogeneous grouping (clustering) of cells, such as small amount of starting RNA, limited per-cell sequenced reads, cell-to-cell variability due to cell-cycle, cellular morphology, and variable reagent concentrations. Moreover, single cell data is susceptible to technical noise, which affects the quality of genes (or features) selected/extracted prior to clustering. Here we introduce sc-CGconv (copula based graph convolution network for single clustering), a stepwise robust unsupervised feature extraction and clustering approach that formulates and aggregates cell-cell relationships using copula correlation (Ccor), followed by a graph convolution network based clustering approach. sc-CGconv formulates a cell-cell graph using Ccor that is learned by a graph-based artificial intelligence model, graph convolution network. The learned representation (low dimensional embedding) is utilized for cell clustering. sc-CGconv features the following advantages. a. sc-CGconv works with substantially smaller sample sizes to identify homogeneous clusters. b. sc-CGconv can model the expression co-variability of a large number of genes, thereby outperforming state-of-the-art gene selection/extraction methods for clustering. c. sc-CGconv preserves the cell-to-cell variability within the selected gene set by constructing a cell-cell graph through copula correlation measure. d. sc-CGconv provides a topology-preserving embedding of cells in low dimensional space.

NIMG-58. CANONICAL CORRELATION ANALYSIS IN GLIOBLASTOMA REVEALS ASSOCIATIONS BETWEEN EXPRESSION OF RADIOMIC SIGNATURES AND GENOMICS

Abstract PURPOSE Understanding the molecular underpinnings of imaging signatures of glioblastoma can provide insights into the biologic basis of tumor formation and progression as well as in vivo surrogate markers of molecular events driving the tumor’s phenotype. Through machine learning (ML), this study demonstrates that distinct imaging subtypes of glioblastoma are related to specific molecular alterations. METHODS Pre-operative multi-parametric MRI (T1, T2, T1CE, T2-FLAIR, DSC-MRI, DTI-MRI) of 669 IDH-wildtype subjects with glioblastoma were retrospectively collected and radiomic features, including descriptors of morphology, intensity, histogram, and texture, were extracted. Imaging subtypes were identified by a feature selection and clustering approach. Genomic markers, obtained using next generation sequencing (NGS) panel of 27 key glioblastoma genes, were available in 358/669 patients. Canonical correlation analysis (CCA) was conducted within each imaging subtype between the selected imaging features and genetic variables to seek maximum correlations between combinations of variables in imaging and genomic sets, and hence elucidate the molecular drivers of respective subtypes. RESULTS Three distinct imaging subtypes were identified by clustering on 50 selected features, representing characteristics of morphology, tumor neo-angiogenesis (DSC-derived features), and cellular density (DTI-derived features). These subtypes yielded differentiable overall survival based on Kaplan-Meier analysis. The canonical coefficients of each subtype revealed the distinction of the underlying genomic characteristics: one exhibited frequently mutated [ARID2, NTRK1], another subtype showed increased frequency of mutation in [ATRX, EGFR, PIK3R1], while the third was associated with all these genes and [NF1, PIK3CA, RB1], additionally. CONCLUSION We derived three distinct radiomic MRI subtypes for glioblastoma that highly correlate with the patients' survival and molecular genetic characteristics. Investigating the relationship between imaging and genomic information may enable identification of molecularly- and phenotypically-consistent tumor subtypes, which would offer non-invasive approaches for characterizing heterogeneity of glioblastoma, further facilitating patient stratification and treatment planning.

Application-specific feature selection and clustering approach with HPC system profiling data

Exascale computing, the next-generation computing environment, is expected to be applied to scientific and engineering applications. Accordingly, high-performance computing (HPC) technology is also being developed to improve the performance and high-speed parallelism of many-core processors. Previous researches on improving HPC performance have developed in the form of improving the overall system performance by analyzing the state of the system occurring in the range of the knowledge of expert. However, performance events occurring in a processor in a many-core environment have a large number of indicators, and it is difficult to analyze the correlation between them. In this paper, we propose an application-specific feature selection and clustering approach with HPC system profiling data. The proposed approach performs PCA-based feature selections for efficient performance analysis methods. In addition, the application-specific characteristics from profiling data can be analyzed by unsupervised learning. In our experiments, we evaluated highly parallel supercomputers with NAS parallel benchmark and were able to cluster applications efficiently.

AMC2N: Automatic Modulation Classification Using Feature Clustering-Based Two-Lane Capsule Networks

The automatic modulation classification (AMC) of a detected signal has gained considerable prominence in recent years owing to its numerous facilities. Numerous studies have focused on feature-based AMC. However, improving accuracy under low signal-to-noise ratio (SNR) rates is a serious issue in AMC. Moreover, research on the enhancement of AMC performance under low and high SNR rates is limited. Motivated by these issues, this study proposes AMC using a feature clustering-based two-lane capsule network (AMC2N). In the AMC2N, accuracy of the MC process is improved by designing a new two-layer capsule network (TL-CapsNet), and classification time is reduced by introducing a new feature clustering approach in the TL-CapsNet. Firstly, the AMC2N executes blind equalization, sampling, and quantization in trilevel preprocessing. Blind equalization is executed using a binary constant modulus algorithm to avoid intersymbol interference. To extract features from the preprocessed signal and classify signals accurately, the AMC2N employs the TL-CapsNet, in which individual lanes are incorporated to process the real and imaginary parts of the signal. In addition, it is robust to SNR variations, that is, low and high SNR rates. The TL-CapsNet extracts features from the real and imaginary parts of the given signal, which are then clustered based on feature similarity. For feature extraction and clustering, the dynamic routing procedure of the TL-CapsNet is adopted. Finally, classification is performed in the SoftMax layer of the TL-CapsNet. This study proves that the AMC2N outperforms existing methods, particularly, convolutional neural network(CNN), Robust-CNN (R-CNN), curriculum learning(CL), and Local Binary Pattern (LBP), in terms of accuracy, precision, recall, F-score, and computation time. All metrics are validated in two scenarios, and the proposed method shows promising results in both.

VOCCluster: Untargeted Metabolomics Feature Clustering Approach for Clinical Breath Gas Chromatography/Mass Spectrometry Data.

Metabolic profiling of breath analysis involves processing, alignment, scaling, and clustering of thousands of features extracted from gas chromatography/mass spectrometry (GC/MS) data from hundreds of participants. The multistep data processing is complicated, operator error-prone, and time-consuming. Automated algorithmic clustering methods that are able to cluster features in a fast and reliable way are necessary. These accelerate metabolic profiling and discovery platforms for next-generation medical diagnostic tools. Our unsupervised clustering technique, VOCCluster, prototyped in Python, handles features of deconvolved GC/MS breath data. VOCCluster was created from a heuristic ontology based on the observation of experts undertaking data processing with a suite of software packages. VOCCluster identifies and clusters groups of volatile organic compounds (VOCs) from deconvolved GC/MS breath with similar mass spectra and retention index profiles. VOCCluster was used to cluster more than 15 000 features extracted from 74 GC/MS clinical breath samples obtained from participants with cancer before and after a radiation therapy. Results were evaluated against a panel of ground truth compounds and compared to other clustering methods (DBSCAN and OPTICS) that were used in previous metabolomics studies. VOCCluster was able to cluster those features into 1081 groups (including endogenous and exogenous compounds and instrumental artifacts) with an accuracy rate of 96% (±0.04 at 95% confidence interval).

An Evolutionary Feature Clustering Approach for Anomaly Detection Using Improved Fuzzy Membership Function

Traditionally, IDS have been developed by applying machine learning techniques and followed single learning mechanisms or multiple learning mechanisms. Dimensionality is an important concern which affects classification accuracies and eventually the classifier performance. Feature selection approaches are widely studied and applied in research literature. In this work, a new fuzzy membership function to detect anomalies and intrusions and a method for dimensionality reduction is proposed. CANN could not address R2L and U2R attacks and have completely failed by showing these attack accuracies almost zero. Following CANN, the CLAPP approach has shown better classifier accuracies when compared to classifiers kNN, and SVM. This research aims at improving the accuracy achieved by CLAPP, CANN, and kNN. Experimental results show accuracies obtained using proposed approach is better when compared to other existing approaches. In particular, the detection of U2R and R2L attacks to user accuracies are recorded to be very much promising.

Ensemble decision forest of RBF networks via hybrid feature clustering approach for high-dimensional data classification

Classification of the high-dimensional data is challenging due to the curse of dimensionality, heavy computational burden and decreasing precision of algorithms. In order to mitigate these effects, feature selection approaches that can determine an efficient subset of features are utilized in the processing. However, most of these techniques attain just one subset of non-redundant features including the best ones. Alternatively, clustering approaches can be used to find the most informative clusters of features instead of generating just a single subset. So called, Hybrid Feature Clustering (HFC) method is capable of maximizing the classification accuracy while keeping the amount of redundant features in each cluster low. The patterns of each cluster are classified by a neural tree that employs Radial Basis Function (RBF) for the nodes. Within each neural tree, a hierarchical approach is proposed to transfer the knowledge of synaptic weights from a parent RBF node to each child. A gating network is applied on the forest of these neural trees in order to aggregate the results. By assessing the classification accuracy and the computational complexity on high-dimensional datasets it can be shown that the proposed solution has outperformed the state of the art classifiers. Furthermore, the computational complexity and the convergence of this method are theoretically proven and the robustness analysis under noisy conditions is conducted.

CLAPP: A self constructing feature clustering approach for anomaly detection

The term internet of things is a buzz word these days and as per Google survey conducted recently, it has even dominated the buzz word big data predominantly. However, IoT area is still not matured and is throwing light on lot of research issues towards the data mining researchers. Security in IoT throws several challenges because of limited resources. In this context, IoT gains importance once again from data miners towards anomaly mining or intrusion detection. Intrusion detection is classified as NP-class in the literature even today. Algorithms addressing privacy and security issues in IoT must consider the complexities involved and hence require re-attention from all researchers. One more problem faced when judging for intrusion is the use of high dimensionality, classifier choice, and distance measure. For example, the traditional distance measure, such as Euclidean misjudges the similarity. In this paper, the objective is to design a fuzzy membership function to address both dimensionality and anomaly mining so as reduce the computational complexity and increase computational accuracies of classifier algorithms. We validate the proposed measure using several experimentations on NSL-KDD and DARPA datasets using kNN, J48 and CANN using Gaussian measure. Improved accuracies of classifiers on U2R and R2L attacks have been recorded in the experimental results obtained for experiments conducted.

Feature extraction approaches from natural language requirements for reuse in software product lines: A systematic literature review

Requirements for implemented system can be extracted and reused for a production of a new similar system. Extraction of common and variable features from requirements leverages the benefits of the software product lines engineering (SPLE). Although various approaches have been proposed in feature extractions from natural language (NL) requirements, no related literature review has been published to date for this topic. This paper provides a systematic literature review (SLR) of the state-of-the-art approaches in feature extractions from NL requirements for reuse in SPLE. We have included 13 studies in our synthesis of evidence and the results showed that hybrid natural language processing approaches were found to be in common for overall feature extraction process. A mixture of automated and semi-automated feature clustering approaches from data mining and information retrieval were also used to group common features, with only some approaches coming with support tools. However, most of the support tools proposed in the selected studies were not made available publicly and thus making it hard for practitioners’ adoption. As for the evaluation, this SLR reveals that not all studies employed software metrics as ways to validate experiments and case studies. Finally, the quality assessment conducted confirms that practitioners’ guidelines were absent in the selected studies.

Algorithmic Analysis of Clinical and Neuropsychological Data in Localization-Related Epilepsy

The current study examines algorithmic approaches for analysis of nonimaging (i.e., clinical, electrographic and neuropsychological) attributes in localization-related epilepsy (LRE), specifically, their impact on the selection of patients for surgical consideration. Both invasive electrographic and imaging data are excluded here to concentrate upon the initial clinical presentation and the varied elements of the seizure history, ictal semiology, risk and seizure-precipitating factors and physical findings in addition to several features of the neuropsychological profile including various parameters of cognition and both speech and memory lateralization. The data was accrued in a database of temporal lobe epilepsy patients (HBIDS). Six algorithms comprising feature selection, clustering and classification approaches were used. The Correlation-Based Feature Selection (CFS) and the Classifier Subset Evaluator (CSE) with the Genetic Algorithm (GA) search tool and ReliefF Attribute Evaluation approaches provided for feature selection. The Expectation Maximization (EM) Class Clustering and Incremental Conceptual Clustering (COBWEB) provided data clustering and the Multilayer Perceptron (MLP) Classifier was the classification tool at all stages of the study. The Engel Classification was used as an output of classifier for surgical success. Attributes demonstrating the highest correlation with the outcome class and the least intercorrelation with each other, according to CFS, were selected. These were then ranked using ReliefF and the top rankings chosen. The best attribute combination for each cluster was found by MLP. COBWEB provided the best results showing an association of 56% with Engel class. In conclusion, an algorithmic approach to the study of LRE is feasible with current findings supporting the need for correlative electrographic and imaging data and a greater archival population.

A high-dimensional feature clustering approach to support knowledge-assisted visualization

The ever-growing arsenal of methods and parameters available for data visualization can be daunting to the casual user and even to domain experts. Furthermore, comprehensive expertise is often not available in a centralized venue, but distributed over sub-communities. As a means to overcome this inherent problem, efforts have begun to store visualization expertise directly with the visualization method and possibly the dataset, to then be utilized for user guidance in the data visualization, suggesting to the user both the visualization method and its best parameters for the data and task at hand. While this is certainly an immensely useful and promising development, one requirement remains – the matching of a newly acquired dataset with the appropriate segment of the library storing the expert knowledge. This requires one to detect and recognize the dataset's category at some level of granularity and then use this information as a library index. We describe a possible framework for accomplishing the first stage of this process, namely the data categorization, using data classification via a rich set of feature vectors sufficiently sensitive to detect critical variations. We demonstrate the utility of our framework by ways of a set of medical and computational datasets and visualize the resulting categorization as a layout in 2D.