Data Classification Methods Research Articles

A cognitive IoT-based framework for effective diagnosis of COVID-19 using multimodal data

The COVID-19 emerged at the end of 2019 and has become a global pandemic. There are many methods for COVID-19 prediction using a single modality. However, none of them predicts with 100% accuracy, as each individual exhibits varied symptoms for the disease. To decrease the rate of misdiagnosis, multiple modalities can be used for prediction. Besides, there is also a need for a self-diagnosis system to narrow down the risk of virus spread in testing centres. Therefore, we propose a robust IoT and deep learning-based multi-modal data classification method for the accurate prediction of COVID-19. Generally, highly accurate models require deep architectures. In this work, we introduce two lightweight models, namely CovParaNet for audio (cough, speech, breathing) classification and CovTinyNet for image (X-rays, CT scans) classification. These two models were identified as the best unimodal models after comparative analysis with the existing benchmark models. Finally, the obtained results of the five independently trained unimodal models are integrated by a novel dynamic multimodal Random Forest classifier. The lightweight CovParaNet and CovTinyNet models attain a maximum accuracy of 97.45% and 99.19% respectively even with a small dataset. The proposed dynamic multimodal fusion model predicts the final result with 100% accuracy, precision, and recall, and the online retraining mechanism enables it to extend its support even in a noisy environment. Furthermore, the computational complexity of all the unimodal models is minimized tremendously and the system functions effectively with 100% reliability even in the absence of any one of the input modalities during testing.

Mapping essential urban land use categories with open big data: Results for five metropolitan areas in the United States of America

Urban land-use maps outlining the distribution, pattern, and composition of various land use types are critically important for urban planning, environmental management, disaster control, health protection, and biodiversity conservation. Recent advances in remote sensing and social sensing data and methods have shown great potentials in mapping urban land use categories, but they are still constrained by mixed land uses, limited predictors, non-localized models, and often relatively low accuracies. To inform these issues, we proposed a robust and cost-effective framework for mapping urban land use categories using openly available multi-source geospatial “big data”. With street blocks generated from OpenStreetMap (OSM) data as the minimum classification unit, we integrated an expansive set of multi-scale spatially explicit information on land surface, vertical height, socio-economic attributes, social media, demography, and topography. We further proposed to apply the automatic ensemble learning that leverages a bunch of machine learning algorithms in deriving optimal urban land use classification maps. Results of block-level urban land use classification in five metropolitan areas of the United States found the overall accuracies of major-class (Level-I) and minor-class (Level-II) classification could be high as 91% and 86%, respectively. A multi-model comparison revealed that for urban land use classification with high-dimensional features, the multi-layer stacking ensemble models achieved better performance than base models such as random forest, extremely randomized trees, LightGBM, CatBoost, and neural networks. We found without very-high-resolution National Agriculture Imagery Program imagery, the classification results derived from Sentinel-1, Sentinel-2, and other open big data based features could achieve plausible overall accuracies of Level-I and Level-II classification at 88% and 81%, respectively. We also found that model transferability depended highly on the heterogeneity in characteristics of different regions. The methods and findings in this study systematically elucidate the role of data sources, classification methods, and feature transferability in block-level land use classifications, which have important implications for mapping multi-scale essential urban land use categories.

FAST WEAKLY SUPERVISED DETECTION OF RAILWAY-RELATED INFRASTRUCTURES IN LIDAR ACQUISITIONS

Abstract. Railroad environments are peculiar, as they combine dense urban areas, along with rural parts. They also display a very specific spatial organization. In order to monitor a railway network a at country scale, LiDAR sensors can be equipped on a running train, performing a full acquisition of the network. Then most processing steps are manually done. In this paper, we propose to improve performances and production flow by creating a classification of the acquired data. However, there exists no public benchmark, and little work on LiDAR data classification in railroad environments. Thus, we propose a weakly supervised method for the pointwise classification of such data. We show that our method can be improved by using the l0-cut pursuit algorithm and regularize the noisy pointwise classification on the produced segmentation. As production is envisaged in our context, we designed our implementation such that it is computationally efficient. We evaluate our results against a manual classification, and show that our method can reach a FScore of 0.96 with just a few samples of each class.

Recognition of Operating Characteristics of Heavy Trucks Based on the Identification of GPS Trajectory Stay Points

As an emerging data source, feature identification based on GPS trajectory data has become a hot issue in the field of data mining and freight management. A method of trajectory data extraction, classification, and visualization based on stay points was proposed in this paper to analyze the operation characteristics of heavy trucks from the perspectives of intracity transportation, intraprovincial transportation, and interprovincial transportation. The GPS trajectory data of heavy trucks in Sichuan Province in March 2019 were taken as an example to analyze the operation characteristics. The results show that the heavy trucks in Sichuan Province are mainly transported within the province, and the freight efficiency is slightly better than the average level of the national freight trucks in the same period, failing to give full play to the advantages of long transport distance. The manufacturing industry is the main service object of heavy trucks, and the vehicles engaged in transportation within the province are more dependent on logistics enterprises and their ancillary facilities. The north-south longitudinal line and east-west horizontal line are the main interprovincial transport channels, and the provincial and municipal transport is mainly concentrated in some urban trunk lines, ring lines, and express routes. The proposed technical method can describe the operating characteristics of freight trucks from the perspective of microscopic and service market, not only to guide the layout of highway freight yards, logistics parks, and logistics hubs and the determination of service functions but also to provide a reference basis for freight management-related departments and drivers to formulate transportation plans and establish freight information platforms to improve freight efficiency and safety.

Deep supervised learning using self-adaptive auxiliary loss for COVID-19 diagnosis from imbalanced CT images

The outbreak and rapid spread of coronavirus disease 2019 (COVID-19) has had a huge impact on the lives and safety of people around the world. Chest CT is considered an effective tool for the diagnosis and follow-up of COVID-19. For faster examination, automatic COVID-19 diagnostic techniques using deep learning on CT images have received increasing attention. However, the number and category of existing datasets for COVID-19 diagnosis that can be used for training are limited, and the number of initial COVID-19 samples is much smaller than the normal’s, which leads to the problem of class imbalance. It makes the classification algorithms difficult to learn the discriminative boundaries since the data of some classes are rich while others are scarce. Therefore, training robust deep neural networks with imbalanced data is a fundamental challenging but important task in the diagnosis of COVID-19. In this paper, we create a challenging clinical dataset (named COVID19-Diag) with category diversity and propose a novel imbalanced data classification method using deep supervised learning with a self-adaptive auxiliary loss (DSN-SAAL) for COVID-19 diagnosis. The loss function considers both the effects of data overlap between CT slices and possible noisy labels in clinical datasets on a multi-scale, deep supervised network framework by integrating the effective number of samples and a weighting regularization item. The learning process jointly and automatically optimizes all parameters over the deep supervised network, making our model generally applicable to a wide range of datasets. Extensive experiments are conducted on COVID19-Diag and three public COVID-19 diagnosis datasets. The results show that our DSN-SAAL outperforms the state-of-the-art methods and is effective for the diagnosis of COVID-19 in varying degrees of data imbalance.

Areas for the connectivity of Chaco peccary (Catagonus wagneri) populations at the southern limit of their distribution in the Argentine Chaco / Áreas para a conectividade de populações de pecari do Chaco (Catagonus wagneri) no limite sul de sua distribuição no Chaco Argentino

The area of geographical distribution of mammal populations in the Argentine Chaco ecoregion is being increasingly reduced and this is mainly due to the progressive destruction of habitats. In this context, several species have been affected, among which is the endemic Catagonus wagneri (Tayassuidae), currently classified as "endangered" and with a trend of population decline. In this work, the predictions estimated by three algorithms were compared to establish the potential geographic distribution of this species at the southern limit of its natural distribution. Priority locations for landscape connectivity were identified by comparing intrinsic variations in the PC index based on data classification methods. With the use of foot transects, trap cameras and surveys with the local population, the presence of chacoan peccary was recorded on 25 occasions. From the GLM, Random Forest and Maxent algorithms (mean AUC 0.74), a reference model was obtained. Using it as an input and the PC index, the variation in the importance of the connectivity surfaces of the landscape was evaluated using three classification methods: quantile, equal interval and natural breaks. The consensus model (SDM) occupies 55,674 km2 of Argentina, representing 10% of the Chaco Seco ecoregion. The distribution occupies not only forest ecosystems, but also environments with less tree coverage. Coefficients of variation of 170% were recorded between the classification methods for the number of patches of classes 9 and 10 of the priority habitat for landscape connectivity. The SDM shows a fragmented distribution in line with the Chaco's land use change process.The results suggest a great variability of the PC index depending on the method of classifying data in class intervals, an aspect that was not discussed in previous studies.

Three-Way Image Classification with Evidential Deep Convolutional Neural Networks

The farfetched certain classification of uncertain data suffers serious risks. Three-Way Decision (3WD) theory is utilized to implement uncertain data classification methods. Three-way uncertain data classification methods facilitate reducing decision risk and involving human–machine coordination through finding out uncertain cases for abstaining identification. Due to the limitation of traditional classifiers in feature learning, most existing three-way uncertain data classification methods are not good at handling the unstructural data of digital images. This shortage hinders the applications of three-way uncertain data classification in image-based decision support systems, such as the medical decision support systems based on radiographs. In this paper, we adopt deep convolutional neural networks (DCNNs) for feature learning and Dempster–Shafer (D-S) evidence theory as uncertainty measure to implement a three-way method for image classification. We utilize evidence theory to measure the uncertainty of the predictions produced by DCNNs and construct a novel evidential deep convolutional neural network (EviDCNN). Based on this, we propose a Three-Way Classification method with EviDCNN (EviDCNN-3WC). The experiments on massive medical image data sets validate that the proposed three-way classification method with EviDCNN is effective to identify uncertain images and reduce the risk in image classification. The superiorities of the proposed method facilitate its applications in image-based medical decision support systems.

Evaluation of data subsampling and neighbourhood selection for mobile LiDAR data classification

Road features extraction is essential for autonomous driving vehicles and road maintenance. Mobile Laser Scanning (MLS) systems have proven their capability for dense and accurate LiDAR point cloud data acquisition of road features. Usually, MLS data are received in the format of XYZ coordinates and sometimes with intensity values. Thus, the first step in MLS data processing is point classification, which mainly relays on the geometric distribution of surrounding points. However, processing such huge data is costly and time- consuming. Therefore, in this research, different neighborhood selection methods, including k nearest neighbors, spherical and cylindrical methods are evaluated to reveal the suitable method for MLS data classification. In addition, a data sub-sampling method based on minimum point spacing is applied in order to reduce the processing time. A set of point features, including covariance, moment and height was first extracted based on the three neighborhood selection methods. Random forest classifier was then used to classify a part of the benchmark dataset of Paris–Lille-3D, which belongs to NPM3D Benchmark suite research project. The dataset is divided into three main parts; Lille 1, Lille 2 and Paris. Lille 1 and Lille 2 were used in this research with about 1.5 km longitudinal road and about 98.1 million total number of points. Six scenarios were evaluated; three for the full dataset and three for the sub-sampled dataset using the aforementioned neighborhood selection methods. The results showed that the cylindrical neighborhood selection method achieved the highest classification accuracy of 92.39% and 90.26% for the full and sub-sampled datasets, respectively. The data sub-sampling has showed a good performance, whereas the dataset was reduced by about half and processing time was reduced by almost half with close classification accuracy using the cylindrical neighborhood selection method.

A data classification method based on particle swarm optimisation and kernel function extreme learning machine

ABSTRACT Aiming at the problem of data classification in enterprise cloud data, this article proposes a data classifier based on Particle Swarm Optimisation and Kernel Function Extreme Learning Machine (PSO-KELM) is proposed. PSO is utilised to get optimal parameters and the parameters of KELM are obtained accurately, which improves the accuracy of data classification. Through the cloud data test and a comparison with Kernel Function Extreme Learning Machine (KELM), Kernel Function Support Vector Machine (KSVM) and Semi-Supervised and Transfer Learning (SSTL), the better classification effect is obtained. Moreover, this article proposes an effective method for data classification.

Probabilistic learning vector quantization on manifold of symmetric positive definite matrices

In this paper, we develop a new classification method for manifold-valued data in the framework of probabilistic learning vector quantization. In many classification scenarios, the data can be naturally represented by symmetric positive definite matrices, which are inherently points that live on a curved Riemannian manifold. Due to the non-Euclidean geometry of Riemannian manifolds, traditional Euclidean machine learning algorithms yield poor results on such data. In this paper, we generalize the probabilistic learning vector quantization algorithm for data points living on the manifold of symmetric positive definite matrices equipped with Riemannian natural metric (affine-invariant metric). By exploiting the induced Riemannian distance, we derive the probabilistic learning Riemannian space quantization algorithm, obtaining the learning rule through Riemannian gradient descent. Empirical investigations on synthetic data, image data , and motor imagery electroencephalogram (EEG) data demonstrate the superior performance of the proposed method.

Voxel-Wise Feature Selection Method for CNN Binary Classification of Neuroimaging Data

Voxel-wise group analysis is presented as a novel feature selection (FS) technique for a deep learning (DL) approach to brain imaging data classification. The method, based on a voxel-wise two-sample t-test and denoted as t-masking, is integrated into the learning procedure as a data-driven FS strategy. t-Masking has been introduced in a convolutional neural network (CNN) for the test bench of binary classification of very-mild Alzheimer’s disease vs. normal control, using a structural magnetic resonance imaging dataset of 180 subjects. To better characterize the t-masking impact on CNN classification performance, six different experimental configurations were designed. Moreover, the performances of the presented FS method were compared to those of similar machine learning (ML) models that relied on different FS approaches. Overall, our results show an enhancement of about 6% in performance when t-masking was applied. Moreover, the reported performance enhancement was higher with respect to similar FS-based ML models. In addition, evaluation of the impact of t-masking on various selection rates has been provided, serving as a useful characterization for future insights. The proposed approach is also highly generalizable to other DL architectures, neuroimaging modalities, and brain pathologies.

Analysisof Students’ Web Browsing Behaviours Using Data Miningat a Campus Network

Analytics provides insight to people based on the analytics of past usage by using techniques such as statistics, data mining, machine learning and artificial intelligence. Lack of monitoring system of browsing causes low engagements that reduce the growth of certain businesses caused by unnecessary browsing for students learning time. This paper presents an analysis on browsing behavior that classifies browsed words followed their ethical word-groups browsing. An Analytic platform is created as a monitoring system of browsing behavior. Data mining, indexing and classification method are used in this research as data is the essential key of creating a predictive model and four types of ethical groups have been filtered based on the browsing behaviors. The browsed words are categorized into four types of browsing called queries, applications, social media, Campus-related sites. The research method uses software tools and data mining process on the browsing data and analytics is presented on the development of the dashboard mainly using the R programming language. Few unethical words using the indexing method are generated in analytic graphs based on the type of browsing versus time. Data collected from the browsing behaviors of students’analysis taken from browsing database of personal computer and laboratory computer in the campus network. The result shows that othercategories are the highest categories which reached79.6% for personals' computer browsing compared to72.4% browsing at the laboratory computers. It is identified that about 21% of the browsing behavior was filtered during the data mined processed. The other category is still on the research portfolio where these libraries must be filtered in detail to identify whether they are learning or non-learning activities. This research is significant in that helps to increase the effectiveness of suggestions applications, optimize the internet usage by blocking unnecessary words or webpages, and even campus guide systems by monitoring the surrounding browsing behavior of the students’ usages of the campus network computer labs.

Multi-input deep learning approach for Cardiovascular Disease diagnosis using Myocardial Perfusion Imaging and clinical data.

Accurate detection and treatment of Coronary Artery Disease is mainly based on invasive Coronary Angiography, which could be avoided provided that a robust, non-invasive detection methodology emerged. Despite the progress of computational systems, this remains a challenging issue. The present research investigates Machine Learning and Deep Learning methods in competing with the medical experts' diagnostic yield. Although the highly accurate detection of Coronary Artery Disease, even from the experts, is presently implausible, developing Artificial Intelligence models to compete with the human eye and expertise is the first step towards a state-of-the-art Computer-Aided Diagnostic system. A set of 566 patient samples is analysed. The dataset contains Polar Maps derived from scintigraphic Myocardial Perfusion Imaging studies, clinical data, and Coronary Angiography results. The latter is considered as reference standard. For the classification of the medical images, the InceptionV3 Convolutional Neural Network is employed, while, for the categorical and continuous features, Neural Networks and Random Forest classifier are proposed. The research suggests that an optimal strategy competing with the medical expert's accuracy involves a hybrid multi-input network composed of InceptionV3 and a Random Forest. This method matches the expert's accuracy, which is 79.15% in the particular dataset. Image classification using deep learning methods can cooperate with clinical data classification methods to enhance the robustness of the predicting model, aiming to compete with the medical expert's ability to identify Coronary Artery Disease subjects, from a large scale patient dataset.

Present-Day Challenges in Homeschooling Specialists’ Training in Canada

The article deals with the results of the recent scientific research concerning training of experts for homeschooling in general and its today’s challenges in particular. Canada has been chosen as a target country due to its specific attitude towards homeschooling and its significant experience in specialist and/or teacher training for homeschooling. The urgency of the problem has recently aggravated because of the present-day situation with covid-19 worldwide restrictions in education and subsequent increase in the number of homeschooling families that need expert advice from certified specialists. 
 The purpose of the article is to highlight the actual state of homeschooling specialist training in Canada in order to decide on a possibility to apply the experience of Canada in those counties which face similar challenges. 
 To conduct the scientific results such methods as a continuous sampling method and a data classification method were used.
 The present research resulted into revealing current challenges in the realm of teacher training for homeschooling in Canada along with possible ways of overcoming of all the revealed difficulties with the help of various institutions that provide pedagogical education or practical support within the process of specialist training for homeschooling. The article considers acquiring skills and knowledge necessary for organizing family (home) education from colleges, institutes, universities, teacher training courses, associations, homeschooling support groups, etc. Some relevant educational programs provided by these establishments are under consideration as well. 
 Thus, the following conclusions were inferred from the results of the research: the system of Homeschooling Specialists’ Training in Canada is highly-developed and well-prepared to cope with the difficulties connected with the Present-day Challenges.

A survey of dimension reduction and classification methods for RNA-Seq data on malaria vector

Recently unique spans of genetic data are produced by researchers, there is a trend in genetic exploration using machine learning integrated analysis and virtual combination of adaptive data into the solution of classification problems. Detection of ailments and infections at early stage is of key concern and a huge challenge for researchers in the field of machine learning classification and bioinformatics. Considerate genes contributing to diseases are of huge dispute to a lot of researchers. This study reviews various works on Dimensionality reduction techniques for reducing sets of features that groups data effectively with less computational processing time and classification methods that contributes to the advances of RNA-Sequencing approach.

Research on hyper-spectral remote sensing image classification by applying stacked de-noising auto-encoders neural network

Hyper-spectral image can provide precise information on land surface targets identification and classification thanks to its advanced feature on spectral resolution. However, due to its complicated hyper-dimension data structure, greater challenge is put on the conventional image classification methods for hyper-spectral images. To fill this technical knowledge gap, we introduce a deep learning-based feature extraction method for hyper-spectral data classification. Firstly, we used a Stacked De-noising Auto-encoders(SDAE) to extract the in-depth features of hyper-spectral image data: a large amount of unlabeled data was pre-trained to extract the depth characteristics of pixels. We added random noise into the input layer of the network to form a de-noising auto-encoder machine and added treated inputs to reconstruct original data. An L-BFGS (Limited-memory quasi-Newton code) was used to optimize the loss function. In the top layer, deep neural network was fine-tuned by a Softmax regression classifier. All these improvements directed towards the model to obtain the image element abstraction and robust expression in the classification task of the hyper-spectral images. We tested the model performance on a Hyspex imaging spectrometer image and found that the newly introduced model framework outperforms other traditional methods including principal component analysis (PCA), and support vector machine (SVM) classifier, combined PCA-SVM classifier, and Minimum Noise Fraction Rotation (MNF)-SVM classifier.

Satellite time series data classification method based on trend symbolic aggregation approximation

Satellite time series data classification method based on trend symbolic aggregation approximation

Predicting the stochastic behavior of uncertainty sources in planning a stand-alone renewable energy-based microgrid using Metropolis–coupled Markov chain Monte Carlo simulation

Due to the lack of available flexibility sources to cope with different uncertainties in the real-time operation of stand-alone renewable energy-based microgrids, the stochastic behavior of uncertainty sources needs to be included in the planning stage. Since there is a high association between some of the uncertainty sources, defining a proper time series to represent the behavior of each source of uncertainty is a challenging issue. Consequently, uncertainty sources should be modeled in such a way that the designed microgrid be able to cope with all scenarios from probability and impact viewpoints. This paper proposes a modified Metropolis–coupled Markov chain Monte Carlo (MC)3 simulation to predict the stochastic behavior of different uncertainty sources in the planning of a stand-alone renewable energy-based microgrid. Solar radiation, wind speed, the water flow of a river, load consumption, and electricity price have been considered as primary sources of uncertainty. A novel data classification method is introduced within the (MC)3 simulation to model the time-dependency and the association between different uncertainty sources. Moreover, a novel curve-fitting approach is proposed to improve the accuracy of representing the multimodal distribution functions, modeling the Markov chain states, and the long-term probability of uncertainty sources. The predicted representative time series with the proposed modified (MC)3 model is benchmarked against the retrospective model, the long-term historical data, and the simple Monte Carlo simulation model to capture the stochastic behavior of uncertainty sources. The results show that the proposed model represents the probability distribution function of each source of uncertainty, the continuity of samples, time dependency, the association between different uncertainty sources, short-term and long-term trends, and the seasonality of uncertainty sources. Finally, results confirm that the proposed modified (MC)3 can appropriately predict all scenarios with high probability and impact.

R-HEFS: Rough set based heterogeneous ensemble feature selection method for medical data classification

Feature selection is one of the trustworthy processes of dimensionality reduction technique to select a subset of relevant and non-redundant features from large datasets. Ensemble feature selection (EFS) approach is a recent technique aiming at accumulating diversity in the subset of selected features. It improves the performance of learning algorithms and obtains more stable and robust results. In this paper, a novel rough set theory (RST) based heterogeneous EFS method (R-HEFS) is proposed for selecting the less redundant and highly relevant features during the aggregation of diverse feature subsets by applying the feature-class, feature-feature rough dependency and feature-significance measures. In R-HEFS five state-of-the-art RST based filter methods are used as a base feature selectors. Experiments are carried out on 10 benchmark medical datasets collected from the UCI repository. For the imputation of the missing values and discretization of the continuous features, k nearest neighbor (kNN) imputation method and RST based discretization techniques are applied. The effectiveness of the proposed R-HEFS method is evaluated and analyzed by using four benchmark classifiers viz., Naïve Bayes (NB), random forest (RF), support vector machine (SVM), and AdaBoost. The proposed R-HEFS method turns out to be effective by removing the non-relevant and redundant features during the process of aggregation of base feature selectors and it assists to increase the classification accuracy. Out of 10 different medical datasets, on 7 datasets, R-HEFS has achieved better average classification accuracy. So, the overall results strongly suggest that the proposed R-HEFS method can reduce the dimension of large medical datasets and may help the physicians or medical experts to diagnose (classify) different diseases with lesser computational complexities.

Urbanization: definition, components, and classification in context of land and economics sciences

This paper approaches urbanization from the broader context of land and economic sciences, with a focus on the theoretical framework and practical use of data classification. International organizations, official government bodies, and private research institutions have different views on urbanization, rely on various methods for statics research and data classification. In this paper we overviewed the term from several angles, such as land use and settlements area, population dynamics and regional economics, agriculture and resources use, followed by sustainable development in the context of urban development plans and policies. The proposed conceptual model of urbanization inland and economics science context determined urbanization as both state and ongoing process. As a result of research work, urbanization process and state key data and research metrics were presented and categorized by fields of application and research subfield category. The important section of the urbanization definition is a robust multistage research framework. We believe that it can help other researchers, as well as the author, look like urban growth, history, and development prospects with less bias and with a focus on long-term vision, multidisciplinary approach.