Data Classification Methods Research Articles

Intelligent hybrid approaches utilizing time series forecasting error for enhanced structural health monitoring

Over the past decade, the growing importance of machine learning-based structural health monitoring (SHM) for early-stage damage detection has become evident. Time series forecasting, using deep learning, has emerged as a key focus, significantly contributing to improving damage detection, localization, and quantification processes. Researchers in SHM have conducted numerous studies utilizing neural networks based on time series forecasting, grounded in traditional methods. This study diverges from existing research by directly incorporating neural network prediction errors in time series for detecting, localizing, and quantifying damage. The proposed methods are well-suited for online structural monitoring. They eliminate the need for data classification methods and damage-sensitive feature extraction techniques by relying solely on training the neural network with data from structurally sound conditions. However, the testing process does require data from damaged conditions. To address the non-linear and non-stationary characteristics of the signals, the Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) method is applied for signal processing. This method processes response signals (i.e., time series) from three well-known benchmark structures: the University of Central Florida structure, the Qatar University Grandstand Simulator, and the Z24 Bridge. Subsequently, the first intrinsic mode function (IMF) obtained from signal decomposition is independently input into Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural networks for time series prediction. Optimal parameter values for the LSTM and GRU neural networks are chosen using the Bayesian Optimization (BO) algorithm before the prediction process. By introducing three indices—Statistical Distance Function (SDF), error index, and accuracy index—the evaluation not only emphasizes the accuracy of the methods but also explores the localization and quantification of damage. The results demonstrate that both ICEEMDAN-BO-LSTM-SDF and ICEEMDAN-BO-GRU-SDF methods have successfully achieved accurate detection, localization, and quantification without the need for data classification and damage-sensitive feature extraction methods, and merely by utilizing data from healthy states for neural network training.

Joint Classification of Hyperspectral and LiDAR Data via Multiprobability Decision Fusion Method

With the development of sensor technology, the sources of remotely sensed image data for the same region are becoming increasingly diverse. Unlike single-source remote sensing image data, multisource remote sensing image data can provide complementary information for the same feature, promoting its recognition. The effective utilization of remote sensing image data from various sources can enhance the extraction of image features and improve the accuracy of feature recognition. Hyperspectral remote sensing (HSI) data and light detection and ranging (LiDAR) data can provide complementary information from different perspectives and are frequently combined in feature identification tasks. However, the process of joint use suffers from data redundancy, low classification accuracy and high time complexity. To address the aforementioned issues and improve feature recognition in classification tasks, this paper introduces a multiprobability decision fusion (PRDRMF) method for the combined classification of HSI and LiDAR data. First, the original HSI data and LiDAR data are downscaled via the principal component–relative total variation (PRTV) method to remove redundant information. In the multifeature extraction module, the local texture features and spatial features of the image are extracted to consider the local texture and spatial structure of the image data. This is achieved by utilizing the local binary pattern (LBP) and extended multiattribute profile (EMAP) for the two types of data after dimensionality reduction. The four extracted features are subsequently input into the corresponding kernel–extreme learning machine (KELM), which has a simple structure and good classification performance, to obtain four classification probability matrices (CPMs). Finally, the four CPMs are fused via a multiprobability decision fusion method to obtain the optimal classification results. Comparison experiments on four classical HSI and LiDAR datasets demonstrate that the method proposed in this paper achieves high classification performance while reducing the overall time complexity of the method.

Prediction model and technical and tactical decision analysis of women's badminton singles based on machine learning.

In the Paris Olympic cycle, South Korean women's athlete An Se-young rose to the top of the 2023 BWF Olympic points with a win rate of 89.5%. With An Se-young as the subject, this paper aims to carry out technical and tactical analysis of women's badminton singles and formulate a prediction model based on machine learning. Firstly, An's technical and tactical statistics are analyzed and presented in a proposed "three-stage" data classification method. Secondly, we improve our "three-stage" machine learning dataset using video analysis of 10 matches (21 point games) where An Se-young faced off against four other players ranked in the top five of the World Badminton Federation (BWF) in week 44 of 2023. Finally, we establish a prediction model for the scoring and losing of points in the women's badminton singles based on the 'Decision tree', 'Random forest', 'XGBoost', 'Support vector' and 'K-proximity' algorithms, and analyze the effectiveness of this model. The results show that the improved data classification is reasonable and can be used to predict the final score of a match. When the support vector machine uses the RBF function kernel, the accuracy reaches its highest at 87.5%, and the consistency of this prediction model is strong. An's playstyle is sustained and unified; she does not seek continuous pressure, but rather exploits and maximizes her aggression following any mistake made by her opponents, immediately utilizing assault methods such as kills or dives, often resulting in the conversion of points during the subsequent 2-3 strikes.

Cryptocurrency Transaction Fraud Detection Based on Imbalanced Classification With Interpretable Analysis

This study introduces an interpretable imbalanced data classification method for detecting cryptocurrency transaction fraud. We address data imbalance using SMOTE oversampling and data augmentation through contrastive learning. Next, we introduce a Transformer-based deep learning model that learns sample relevance. The model undergoes pre-training with a contrastive loss and fine-tuning through Bayesian optimization to effectively extract high-dimensional, higher-order, and fraud-related features. We employ a SHAP-based interpreter along with attention scores to elucidate the role of various transaction features in fraud detection. Comparative results demonstrate the model's remarkable recall performance in identifying cryptocurrency transaction fraud. Furthermore, it achieves an excellent F1 value, striking a balance between accuracy and recall. This research not only enriches financial fraud detection but also enhances cryptocurrency transaction security, promotes market development, and contributes to economic stability and social security.

A [formula omitted]-means triangular synthesis large margin classifier with unified pinball loss for imbalanced data

Large Margin Distribution Machine (LDM) improves the Support Vector Machine (SVM) by integrating the marginal distribution of samples into the objective function, which exhibits excellent classification and generalization performance. However, most of the existing LDM-based models exhibit inherent flaws: (1) The assumption of a category uniform distribution, resulting in an inability to effectively address the issue of class imbalance. (2) The inheritance of the hinge loss in SVM, leading to inferior anti-noise performance. Given the shortcomings above, this paper constructs a novel K-means Triangular Synthesis (KTS) method for imbalanced data classification and introduces Unified Pinball (UP) loss to ensure robust performance, demonstrated as a novel KTS large margin classifier with UP Loss (KTS-UPLMC) model. Specifically, the KTS method utilizes the triangular synthesis and generates samples based on the cluster density, effectively mitigating the problems of introducing noise samples and strip-shaped sample distribution in the traditional synthetic minority oversampling technique, further alleviating the LDM’s classification line offset. In addition, the UP Loss considers quantile distance, improving the anti-noise performance of the model. Comparative experiments on artificial datasets and benchmark datasets validate the effectiveness and noise resistance of the proposed KTS-UPLMC in imbalanced data classification problems. Furthermore, the stability of the KTS-UPLMC is substantiated by the parameter sensitivity analysis experiment. In conclusion, the KTS method effectively addresses category imbalance, while the integration of the UP Loss enhances noise resistance.

Fuzzy Method for Preliminary Classification of the Micro-Electromechanical Systems Data

Data of micro-electromechanical systems (sensors) are widely used in modern multipurpose intellectual environments, autonomous mobile robots and automated systems possessing intellectual components. Since the amount of data delivered by the sensors is rather considerable and their significance varies we propose a fuzzy method of the data preliminary classification aimed at selection of the data important for the planning and control decisions while meaningless data or data that do not contain new information are discarded. As a result the amount of the resource intensive intellectual processing and the workload in the network infrastructure could be reduced significantly. The paper presents the analysis for the preliminary classification problem, the abstract model of a sensor and classification method. The method is based on the delay which is controlled by multiplicative decrease additive increase rule and expresses the expectation of the context uncertainty. The delay decreases if the variables measured by the sensor presumably change and increases if it keep its value. Numerical examples are presented as well. They consider the set of mount chest accelerometer uncalibrated measurements. We compare source data set and set of the selected values formed by an algorithm implementing fuzzy preliminary classification. Several metrics were used to compare the selected values with the source data and with CMA filter as well.

Development of Robot Feature for Stunting Analysis Using Long-Short Term Memory (LSTM) Algorithm

Stunting prevalence in Indonesia persists as a significant challenge necessitating concerted efforts from all stakeholders. We developed robot for stunting analysis using deep learning algorithm. It aligns with the Sustainable Development Goal (SDG) agenda, specifically targeting SDG 3, which focuses on ensuring good health and well-being for all. Long Short-Term Memory (LSTM) is a type of Recurrent Neural Network (RNN) designed to overcome the vanishing gradient problem in traditional RNNs. In general, either LSTM can be used in analysis. This study aims to classify stunting based on age and height using LSTM. The LSTM model was trained with 50 epochs using datasets collected from the health office and robots. The evaluation results show training accuracy of 96.65% and training validation of 96.61%, with precision, recall and f1-score varying with relevance to the f1-score and support value. This research illustrates the potential for using data classification methods in stunting diagnosis. However, it is necessary to adjust parameters and increase the amount of training data to improve model performance. With good convergence at epoch 50, these results show the model's ability to classify stunting based on age and height. However, further validation and testing on larger datasets is needed to thoroughly test the reliability and generalization of the model. This research can contribute to the development of deep learning regarding robots as a means of testing stunting. This research provides initial evidence of the potential of stunting classification methods using robots. However, parameter adjustments and increasing the amount of training data need to be done to improve the overall model performance.

Wkład ośrodków statystycznych w Krakowie i we Wrocławiu w rozwój metod klasyfikacji i analizy danych

The year 2022 marked the 10th anniversary of the passing of Prof. Kazimierz Zając, the long-standing head of the Department of Statistics and later the director of the Institute of Statistics, Econometrics and Computer Science at Krakow University of Economics, while 2023 marked the 10th year of the passing of Prof. Zdzisław Hellwig, the long-standing head of the Department of Statistics and director of the Institute of Economic Cybernetics at Wroclaw University of Economics. Both professors were the scientific leaders of statistical centres at the above-mentioned universities. The aim of the article is to present the contribution of Polish statisticians to the development of the theoretical foundations and empirical research in the field of numerical taxonomy and methods of data classification and analysis. Particular emphasis is placed on the achievements of Professor Zając and Professor Hellwig and their students and associates. According to the authors of this work, recalling the achievements of these scholars is especially important as most commonly cited sources on data classification and analysis are mainly English-language.

Assessing the Suitability of Data Classification Methods for Choropleth Maps Depicting Population Distribution in South Africa

Assessing the Suitability of Data Classification Methods for Choropleth Maps Depicting Population Distribution in South Africa

Real-time traffic condition uncertainty quantification using adaptive grey prediction interval model

Uncertainty quantification is important for making reliable transportation decisions. For grey-based uncertainty quantification approaches, the data classification methods for most models cannot yield real-time upper and lower limited data sequence, limiting their application in dynamic transportation systems. Therefore, this paper proposes an adaptive grey prediction interval model to quantify real-time traffic condition uncertainty. To this end, polynomial regression is first used to fit the traffic flow trend function in real time, generating dynamically the upper and lower limited data sequence. Then, upper grey (UG) and lower grey (LG) models are built with parameters optimised using particle swarm optimisation. Finally, based on the real-time upper and lower bounds generated by the UG and LG models, prediction intervals are constructed. Using real-world traffic flow data, the proposed model was shown to be able to generate workable prediction intervals in real time. Future studies are recommended to advance traffic condition uncertainty quantification.

An Efficient and Versatile Variational Method for High-Dimensional Data Classification

High-dimensional data classification is a fundamental task in machine learning and imaging science. In this paper, we propose an efficient and versatile multi-class semi-supervised classification method for classifying high-dimensional data and unstructured point clouds. To begin with, a warm initialization is generated by using a fuzzy classification method such as the standard support vector machine or random labeling. Then an unconstraint convex variational model is proposed to purify and smooth the initialization, followed by a step which is to project the smoothed partition obtained previously to a binary partition. These steps can be repeated, with the latest result as a new initialization, to keep improving the classification quality. We show that the convex model of the smoothing step has a unique solution and can be solved by a specifically designed primal–dual algorithm whose convergence is guaranteed. We test our method and compare it with the state-of-the-art methods on several benchmark data sets. Thorough experimental results demonstrate that our method is superior in both the classification accuracy and computation speed for high-dimensional data and point clouds.

Modified data classification for extreme values in Şen’s innovative trend analysis: A comparative trend study for the Aegean and Eastern Anatolia Regions of Türkiye

The increase in greenhouse gases in the atmosphere has worsened global warming, and marked changes have been observed in meteorological and climatic events, especially since the early 2000s. Trend analysis studies are important for determining changes in meteorological and climatic events over time. This study investigated the trends of maximum precipitation and minimum temperature in the Aegean Region and Eastern Anatolia Region of Türkiye by conducting an innovative trend analysis (ITA), the Mann–Kendall (MK) test, and linear regression analysis (LRA). As a method, ITA has been used together with traditional methods in the last decade, and its advantages have been demonstrated in comparative trend studies. An important contribution of ITA is that it can categorize datasets according to their size (low, medium, and high). The classification technique of the ITA method includes dividing the sorted dataset into three equal parts and separately examining the trends of low, medium, and high data values. This approach is reasonable for datasets with low skewness (or normally distributed series). However, the normal distribution acceptance of ITA data classification is insufficient for trend analysis of data series with extreme values. Therefore, we propose a modified data classification method to rationally examine skewed datasets with the use of quartiles. Our study was performed for the trend analysis of maximum rainfall and minimum temperature data in two regions located in the west and east of Türkiye showing different climatic characteristics. In the first part of the study in which the numerical trend analysis of ITA was evaluated, the MK and LRA methods showed similar results, whereas the ITA detected trends at a greater number of stations owing to its sensitivity feature in detecting trends. In the second part, which included data classification in trend analysis, the equal split data classification used in the ITA and the modified data classification proposed in the study were compared. The comparative results of the trend analysis of the maximum rainfall and minimum temperature data showed the superiority of the proposed data classification in examining the trend of extreme values, especially for maximum rainfall data with relatively high skewness.

Study on environmental monitoring classification system based on improved bayesian algorithm

Abstract The commonly used methods for classifying water quality data are based on water quality parameters. The naive Bayesian classification method can be applied to substitute different evaluation criteria and selected water quality parameters for different water bodies. Compared to other water quality data classification methods, naive Bayesian classification methods have advantages such as simple calculation, high classification accuracy, and strong universality. However, this method overlooks the correlation between various water quality parameters and categories. To address the issues of poor universality, computational complexity, and low accuracy of traditional water quality data classification methods, a water quality data classification method based on weighted naive Bayes is proposed. This method comprehensively considers the impact of water quality attributes and their values on the classification results and replaces the original naive Bayes with weighted attribute conditional probabilities to make the classification results as close as possible to the actual category of the sample. The results indicate that this method exceeds 94% accuracy and can be directly utilized as a water quality classification module in water quality monitoring systems.

A Classification Method for Incomplete Mixed Data Using Imputation and Feature Selection

Data missing is a ubiquitous problem in real-world systems that adversely affects the performance of machine learning algorithms. Although many useful imputation methods are available to address this issue, they often fail to consider the information provided by both features and labels. As a result, the performance of these methods might be constrained. Furthermore, feature selection as a data quality improvement technique has been widely used and has demonstrated its efficiency. To overcome the limitation of imputation methods, we propose a novel algorithm that combines data imputation and feature selection to tackle classification problems for mixed data. Based on the mean and standard deviation of quantitative features and the selecting probabilities of unique values of categorical features, our algorithm constructs different imputation models for quantitative and categorical features. Particle swarm optimization is used to optimize the parameters of the imputation models and select feature subsets simultaneously. Additionally, we introduce a legacy learning mechanism to enhance the optimization capability of our method. To evaluate the performance of the proposed method, seven algorithms and twelve datasets are used for comparison. The results show that our algorithm outperforms other algorithms in terms of accuracy and F1 score and has reasonable time overhead.

CMR-net: A cross modality reconstruction network for multi-modality remote sensing classification.

In recent years, the classification and identification of surface materials on earth have emerged as fundamental yet challenging research topics in the fields of geoscience and remote sensing (RS). The classification of multi-modality RS data still poses certain challenges, despite the notable advancements achieved by deep learning technology in RS image classification. In this work, a deep learning architecture based on convolutional neural network (CNN) is proposed for the classification of multimodal RS image data. The network structure introduces a cross modality reconstruction (CMR) module in the multi-modality feature fusion stage, called CMR-Net. In other words, CMR-Net is based on CNN network structure. In the feature fusion stage, a plug-and-play module for cross-modal fusion reconstruction is designed to compactly integrate features extracted from multiple modalities of remote sensing data, enabling effective information exchange and feature integration. In addition, to validate the proposed scheme, extensive experiments were conducted on two multi-modality RS datasets, namely the Houston2013 dataset consisting of hyperspectral (HS) and light detection and ranging (LiDAR) data, as well as the Berlin dataset comprising HS and synthetic aperture radar (SAR) data. The results demonstrate the effectiveness and superiority of our proposed CMR-Net compared to several state-of-the-art methods for multi-modality RS data classification.

Важность коммуникативной составляющей в профессиональной деятельности врача телемедицины

Telehealth is a modern branch of medicine that provides affordable and high-quality healthcare. The doctor-patient communication during an online consultation is just as important as personal bedside communication. A telehealth doctor is a qualified specialist who is able to provide remote assistance to patients using a computer and telecommunication software. Telehealth is especially important to patients in remote or rural areas with limited access to medical service. The article describes the role of the communicative component in effective telehealth interaction. The authors studied various online telehealth services, i.e., the Gostelemed telehealth consultation service provided by state medical organizations, the Miracle Doctor multidisciplinary medical clinic, and the Capsa Healthcare mobile medical platform. The authors used the methods of data analysis, generalization, and classification, as well as terminological analysis of dictionary definitions, to study the basic principles of effective telehealth communication. They identified the provisions and means of effective verbal and non-verbal communication during online consultations. Telehealth proved to be an effective tool that improves the standards and accessibility of medical care, especially during pandemics or crisis. Effective telehealth communication promotes positive relations between patients and specialists.

A modified sequential wavenumber selection-discriminant analysis with Bayesian optimization strategy for detection and identification of chia seed oil adulteration using Raman spectroscopy

The detection of oil fraud can be accomplished through the use of Raman spectroscopy, which is a potent analytical technique for identifying the adulteration of edible oils with inferior or less expensive oils. However, appropriate data reduction and classification methods are required to achieve high accuracy and reliability in the analysis of Raman spectra. In this study, data reduction algorithms such as principal component analysis (PCA) and modified sequential wavenumber selection (MSWS) were applied, along with discriminant analysis (DA) as a classifier for detecting oil fraud. The parameters of DA, such as the discriminant type, the amount of regularization, and the linear coefficient threshold, were optimized using Bayesian optimization. The methods were tested on a dataset of chia oil mixed with 5–40 % sunflower oil, which is a common form of fraud in the market. The results showed that MSWS-DA achieved 100 % classification accuracy, while PCA-DA achieved 91.3 % accuracy. Therefore, it was demonstrated that Raman spectroscopy combined with MSWS-DA and Bayesian optimization can effectively detect oil fraud with high accuracy and robustness.

IFF-Net: Irregular Feature Fusion Network for Multimodal Remote Sensing Image Classification

In recent years, classification and identification of Earth’s surface materials has been a challenging research topic in the field of earth science and remote sensing (RS). Although deep learning techniques have achieved some results in remote sensing image classification, there are still some challenges for multimodal remote sensing data classification, such as information redundancy between multimodal remote sensing images. In this paper, we propose a multimodal remote sensing data classification method IFF-Net based on irregular feature fusion, called IFF-Net. The IFF-Net architecture utilizes weight-shared residual blocks for feature extraction while maintaining the independent batch normalization (BN) layer. During the training phase, the redundancy of the current channel is determined by evaluating the judgement factor of the BN layer. If this judgment factor falls below a predefined threshold, it indicates that the current channel information is redundant and should be substituted with another channel. Sparse constraints are imposed on some of the judgment factors in order to remove extra channels and enhance generalization. Furthermore, a module for feature normalization and calibration has been devised to leverage the spatial interdependence of multimodal features in order to achieve improved discrimination. Two standard datasets are used in the experiments to validate the effectiveness of the proposed method. The experimental results show that the IFF-NET method proposed in this paper exhibits significantly superior performance compared to the state-of-the-art methods.

A novel undersampling method based on data classification method

Data mining is one of the most important research area in literature. Due to the increasing volume of data, which is directly proportional to technological advancements, the number of researches in this field is growing rapidly. The goal of data mining is to extract various insights and obtain information from raw data by leveraging machine learning techniques. The structural characteristics and also class distributions of the datasets used in machine learning techniques significantly affect the performances of the algorithms. In this study, our aim is balancing the imbalanced binary dataset, used in the machine learning techniques, with an undersampling approach including a classification method via polyhedral conic functions.

A seismic ambient noise data classification method based on waveform and frequency-wavenumber analysis: Application to reliable geological interpretation adjacent to Well Songke-2, Northeast China

Passive seismic interferometry techniques enable the retrieval of virtual shot gathers at receiver locations. However, it is difficult to distinguish body waves from surface waves in seismic ambient noise data, which leads to failed dispersion measurements, artificial deep reflections, and misleading geologic interpretations. We develop a new method that uses the waveforms and their corresponding f- k spectra to identify body waves and surface waves. Our technique functions as a data classification procedure before wavefield retrieval and subsequent imaging. A field data example is conducted to test the feasibility of this technique. The field data results demonstrate that our technique can reconstruct satisfactory high signal-to-noise-ratio wavefields for reliable imaging and interpretation purposes. The method can also serve as a validation tool for identifying surface wave-related artificial events in the obtained virtual source reflection image. The marker boundaries of the Songliao Basin in Northeast China are interpreted in the obtained profile and are in agreement with the well-logging data. In addition, two normal faults are detected, which correspond to the extensional rift environment during the early Cretaceous.