Data Classification Methods Research Articles

A network big data classification method based on decision tree algorithm

A network big data classification method based on decision tree algorithm

Airborne LiDAR data classification method combining physical and geometric characteristics

Airborne LiDAR data classification method combining physical and geometric characteristics

Crop Classification of Multitemporal PolSAR Based on 3-D Attention Module With ViT

Multi-temporal polarimertic SAR is considered to be very effective in crop classification and cultivated land detection, which has received much attention from researchers. Currently, for most multi-temporal polarimetric SAR data classification methods, the simultaneous temporal-polarimetric-spatial feature extraction capability has not been exploited sufficiently. Also, the diversity of different time and different polarimetric features has not been taken into account sufficiently. In this paper, we propose a classification model that combines a dual-stream network as a temporal-polarimetric-spatial feature extraction module with Vision Transformer(ViT) called Temporal-Polarimetric-Spatial Transformer(TSPT) to address the above problems. Secondly, a 3 dimension(3D) convolutional attention module that enables the network to weight the temporal dimension, polarimetric feature dimension and spatial dimension is developed, according to their importance. Experimental results on both UAVSAR and RADARSAT-2 datasets show that the proposed method outperforms ResNet.

Effect of Urbanization on Land Surface Temperature: A Case Study of Kathmandu Valley


 
 
 Growth in the population over time is bound to increase the expansion of densely populated areas which will change the dynamics of land use and land cover (LULC) directly or indirectly. The objective of this study is to analyze the effect of urban growth on the land surface temperature (LST) in Kathmandu. We used the maximum likelihood classification method for LULC classification and change detection of pre-monsoon satellite data for the years 2000, 2005, 2010, 2015 and 2020. LST was then calculated using the thermal infrared band from the satellite imagery. Finally, the relationship between urban growth and LST was assessed by correlation and regression analysis. The result shows an increase in urban areas by 13.98% of the total area between 2000 and 2020. The analysis of thermal patterns shows that there is a gradual increase in temperature in the urban area. With an overall accuracy of 89.96% and a Kappa coefficient of 0.86, the study shows high agreement between classified data from images. This study shows that urbanization has a positive impact on surface temperature, yet the relationship is not significant. Sustainable city planning and strict adherence to the Land Use Act and regulations will assist to make the urbanization process more sustainable in the future.
 
 

Prediction of chronic liver disease patients using integrated projection based statistical feature extraction with machine learning algorithms

The healthy liver plays more than 500 organic roles in the human body, while a malfunction may be dangerous or even deadly. Early diagnosis and treatment of liver disease can improve the likelihood of survival. Machine learning (ML) is a powerful tool that can assist healthcare professionals during the diagnostic process for a hepatic patient. The standard ML system includes the methods of data pre-processing, feature extraction, and classification. In the feature extraction stage, ML researchers frequently use projection-based feature extraction approaches to remove data redundancy, but this does not produce the desired results. In addition, most statistical projection methods have different purposes when projecting original features. The Indian liver patient dataset (ILPD) from the University of California, Irvin (UCI) repository is used in this study to classify chronic liver disease. The data set has 583 patient disease records; 416 patients have liver disease, and 167 do not. Using several projection methods, we proposed an integrated feature extraction approach to categorize liver patients. In the pipeline, the proposed method first imputes the missing values and outliers for pre-treatment. Then, integrated feature extraction applies the pre-processed data to extract the significant features for classification. A simulation study is also being conducted to strengthen the suggested methodology. The proposed approach incorporates several ML algorithms, including logistic regression (LR), random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM), multilayer perceptron (MLP), and the ensemble voting classifier. The offered system has an accuracy of 88.10%, a precision of 85.33%, a recall of 92.30%, an F1 score of 88.68%, and an AUC score of 88.20% in predicting liver diseases. Our proposed technique yielded 0.10–18.5% better results than the latest existing studies. The findings suggest that the recommended system could be used to supplement a physician's diagnosis of liver disease.

Coupled adversarial learning for fusion classification of hyperspectral and LiDAR data

Hyperspectral image (HSI) provides rich spectral–spatial information and the light detection and ranging (LiDAR) data reflect the elevation information, which can be jointly exploited for better land-cover classification. However, due to different imaging mechanisms, HSI and LiDAR data always present significant image difference, current pixel-wise feature fusion classification methods relying on concatenation or weighted fusion are not effective. To achieve accurate classification result, it is important to extract and fuse similar high-order semantic information and complementary discriminative information contained in multimodal data. In this paper, we propose a novel coupled adversarial learning based classification (CALC) method for fusion classification of HSI and LiDAR data. In specific, a coupled adversarial feature learning (CAFL) sub-network is first trained, to effectively learn the high-order semantic features from HSI and LiDAR data in an unsupervised manner. On one hand, the proposed CAFL sub-network establishes an adversarial game between dual generators and discriminators, so that the learnt features can preserve detail information in HSI and LiDAR data, respectively. On the other hand, by designing weight-sharing and linear fusion structure in the dual generators, we can simultaneously extract similar high-order semantic information and modal-specific complementary information. Meanwhile, a supervised multi-level feature fusion classification (MFFC) sub-network is trained, to further improve the classification performance via adaptive probability fusion strategy. In brief, the low-level, mid-level and high-level features learnt by the CAFL sub-network lead to multiple class estimation probabilities, which are then adaptively combined to generate a final accurate classification result. Both the CAFL and MFFC sub-networks are collaboratively trained by optimizing a designed joint loss function, which consists of unsupervised adversarial loss and supervised classification loss. Overall, by optimizing the joint loss function, the proposed CALC network is pushed to learn highly discriminative fusion features from multimodal data, leading to higher classification accuracies. Extensive experiments on three well-known HSI and LiDAR data sets demonstrate the superior classification performance by the proposed CALC method than several state-of-the-art methods. The source code of the proposed method will be made publicly available at https://github.com/Ding-Kexin/CALC.

COMPARISON OF FEATURE SELECTION TO PERFORMANCE IMPROVEMENT OF K-NEAREST NEIGHBOR ALGORITHM IN DATA CLASSIFICATION

One of the most widely used data classification methods is the K-Nearest Neighbor (K-NN) algorithm. Classification of data in this method is carried out based on the calculation of the closest distance to the training data as much as the value of K from its neighbors. Then the new data class is determined using the most votes system from the number of K nearest neighbors. However, the performance of this method is still lower than other data classification methods. The cause is the use of the most voting system in determining new data classes and the influence of features less relevant to the dataset. This study compares several feature selection methods in the data set to see their effects on the performance of the K-NN algorithm in data classification. The feature selection methods in this research are Information gain, Gain ratio, and Gini index. The method was tested on the Water Quality dataset from the Kaggle Repository to see the most optimal feature selection method. The test results on the dataset show that the use of the feature selection method affects to increase the performance of the K-NN algorithm. The average increase in the accuracy value obtained from the value of K=1 to K=15 is the Information Gain increased by 1.17%, Gain ratio increased by 0.69%, and the Gini index increased by 1.19%. The highest accuracy value in the classification of the Water Quality dataset is 89.66% at K=13 with the Information Gain feature selection method.

Small samples data augmentation and improved MobileNet for surface defects classification of hot-rolled steel strips

Surface defects in hot-rolled steel strips are one of the common product problems for the steel industry, which harm the product appearance, affect the corrosion and wear resistance, and shorten the product service life. The natural defect samples are sparse, category imbalanced, and expensive manual annotations. Therefore, it is crucial to study the data augmentation and classification methods for small sample surface defects. To solve the above problems and improve the accuracy and real-time performance of defect classification, we propose a random offline data augmentation algorithm (Random-CutMix) and an improved MobileNet architecture (SP-MobileNet). The Random-CutMix algorithm expands the dataset by random sampling to balance the number of each defect class. The SP-MobileNet combines the inverse residual module with the channel shuffle mechanism (CSIn-Module) and pyramid split attention (PSA) module, which facilitates cross-group information flow and improves model representation capability and generalization performance with low computational cost. The accuracy, recall, F1 score, parameter, computational complexity, and frame rate of SP-MobileNet with Random-CutMix on the X-SDD dataset were 95.97%, 95.22%, 95.46%, 6.5 M, and 0.54 G, 72 FPS, respectively. The experiment results indicate that our method outperforms the state-of-the-art methods and provides an effective trade-off between accuracy and instantaneity in actual industrial production.

Data Classification and Demand Prediction Methods Based on Semi-Supervised Agricultural Machinery Spare Parts Data

Because of the continuous improvement of technology, mechanization has emerged in various fields. Due to the different suitable seasons for the growth of agricultural plants, agricultural mechanization faces problems different from other industries. That is, agricultural machinery and equipment may be used frequently for a period of time, or may be idle for a long time. This leads to the aging of equipment no longer becoming regular, the maintenance time of spare parts is not fixed, the number of spare parts stored in the spare parts warehouse cannot be too large to occupy funds, and the number cannot be too small to meet the maintenance needs, so the prediction of agricultural machinery spare parts has become particularly important. Due to the lack of information, the difficulty of labeling, and the imbalance of positive and negative sample classification, this paper used a semi-supervised learning algorithm to solve the problem of agricultural machinery spare parts data classification. In order to forecast the demand for spare parts of agricultural machinery, this paper compared the IPSO-BP neural network algorithm and BP neural network algorithm. It was found that the IPSO-BP neural network was used to forecast the demand for spare parts of agricultural machinery, and the error between the predicted value and the actual value was small and met the accuracy requirements.

An improved GEV boosting method for imbalanced data classification with application to short-term rainfall prediction

This paper considers the imbalanced binary classification problem by focusing on the application of the short-term rainfall forecasting in arid and semi-arid regions. Specifically, we present a novel boosting-type method by utilizing the generalized extreme value (GEV) distribution as the link function and applying a gradient tree boosting algorithm to capture complex interactions among covariates. The proposed method has several appealing advantages such as, it can identify rare rainfall events as well as quantifying the uncertainties; it is data-driven that without any assumption on the relationship between the covariates and the rainfall event; the fitted model is highly interpretable, making it a useful tool for studying the rainfall mechanisms in arid and semi-arid regions. Experiments on two real-world datasets show that our approach outperforms its competing methods.

An Overview on the Application of Chemometrics Tools in Food Authenticity and Traceability.

The use of advanced chemometrics tools in food authenticity research is crucial for managing the huge amount of data that is generated by applying state-of-the-art analytical methods such as chromatographic, spectroscopic, and non-targeted fingerprinting approaches. Thus, this review article provides description, classification, and comparison of the most important statistical techniques that are commonly employed in food authentication and traceability, including methods for exploratory data analysis, discrimination, and classification, as well as for regression and prediction. This literature revision is not intended to be exhaustive, but rather to provide a general overview to non-expert readers in the use of chemometrics in food science. Overall, the available literature suggests that the selection of the most appropriate statistical technique is dependent on the characteristics of the data matrix, but combining complementary tools is usually needed for properly handling data complexity. In that way, chemometrics has become a powerful ally in facilitating the detection of frauds and ensuring the authenticity and traceability of foods.

Classifying Gait Alterations Using an Instrumented Smart Sock and Deep Learning

This article presents a noninvasive method of classifying gait patterns associated with various movement disorders and/or neurological conditions, utilizing unobtrusive, instrumented socks and a deep-learning network. Seamless instrumented socks were fabricated using three accelerometer-embedded yarns, positioned at the toe (hallux), above the heel, and on the lateral malleolus. Human trials were conducted on 12 able-bodied participants, an instrumented sock was worn on each foot. Participants were asked to complete seven trials consisting of their typical gait and six different gait types that mimicked the typical movement patterns associated with various movement disorders and neurological conditions. Four neural networks and an SVM were tested to ascertain the most effective method of automatic data classification. The bi-long short-term memory (LSTM) generated the most accurate results and illustrates that the use of three accelerometers per foot increased classification accuracy compared to a single accelerometer per foot by 11.4%. When only a single accelerometer was utilized for classification, the ankle accelerometer generated the most accurate results in comparison to the other two. The network was able to correctly classify five different gait types: stomp (100%), shuffle (66.8%), diplegic (66.6%), hemiplegic (66.6%), and “normal walking” (58.0%). The network was incapable of correctly differentiating foot slap (21.2%) and steppage gait (4.8%). This work demonstrates that instrumented textile socks incorporating three accelerometer yarns were capable of generating sufficient data to allow a neural network to distinguish between specific gait patterns. This may enable clinicians and therapists to remotely classify gait alterations and observe changes in gait during rehabilitation.

Remote sensing sea ice classification based on DenseNet and heterogeneous data fusion

Most remote sensing sea ice classification methods use single-source remote sensing data, such as synthetic aperture radar (SAR) data and optical remote sensing data. SAR data contain rich sea ice texture information, but the data are relatively single, making it difficult to distinguish detailed sea ice categories. Optical data include abundant spatial-spectral information, but they are often affected by clouds, fog, and severe weather. Hence, given the limitations of single-source data, the remote sensing sea ice classification accuracy cannot be further improved. A sea ice classification method based on deep learning and multisource remote sensing data fusion is proposed utilizing an improved densely connected convolutional neural network (DenseNet) to mine and fuse the multilevel features of sea ice. According to the characteristics of SAR data and optical data, a dual-branch network structure based on an improved DenseNet is employed for feature extraction, and a squeeze-and-excitation attention mechanism is introduced to weight the fusion features to further enhance the feature weights that can effectively distinguish different types of sea ice. The fully connected network is used to perform the deep fusion of features and classify sea ice. To verify the effectiveness of the proposed method, two sets of sea ice data are utilized for sea ice classification. The experimental results show that the proposed method fully excavates and fuses the multilevel characteristics of heterogeneous data using the improved dual-branch network structure, leverages the complementary characteristics of SAR data and optical data, significantly increases the sea ice classification accuracy, and effectively improves the influence of cloud cover on the sea ice classification accuracy. Compared with the typical single-source data classification method and other heterogeneous data fusion classification methods, the proposed method achieves superior overall classification accuracy (98.49% and 98.58%).

Practical Training Mode for Improving Teachers' Data Literacy Ability

Based on the analysis of the research status of university teachers' data literacy at home and abroad, combined with the survey results of university teachers' data literacy ability in China, this paper uses data classification and other methods to mine the core elements of university teachers' data literacy ability; Further use the scoring method to build a multi-level dynamic evaluation system of teachers' data literacy ability; For different levels of data literacy capabilities, we will build a multi-level promotion strategy plan to form a complete set of dynamic strategies for improving college teachers' data literacy capabilities, and promote and apply them.

Comparison of k-Nearest Neighbor and Naive Bayes Methods for SNP Data Classification

In an accident, sometimes the identity of a person who has an accident is hard to know, so it is necessary to use biological data such as Single Nucleotide Polymorphism (SNP) data to identify the person's origin. This research aims to compare the accuracy and the F1 score of the k-Nearest Neighbor method and the Naive Bayes method in classifying SNP data from 120 people who divide into groups, namely European (CEU) and Yoruba (YRI). Determination of the best method based on the average value of accuracy and the average value of F1 score from 1000 iterations with various percentage distributions of training datasets and testing datasets. In this research, the selection of SNP locations for the classification process was carried out by correlation analysis. The average accuracy obtained for the k-Nearest Neighbor method with the value of k=31 is 98.38% where the average F1 score is 98.39% while the Naive Bayes method obtained the average accuracy of 96.74% and the average F1 score of 96.63%. In this case, the k-Nearest Neighbor method is better than the Naive Bayes method in classifying SNP data to determine the origin of a person's ancestor tends to be from CEU or YRI.

Hyperspectral Imaging Zero-Shot Learning for Remote Marine Litter Detection and Classification

This paper addresses the development of a novel zero-shot learning method for remote marine litter hyperspectral imaging data classification. The work consisted of using an airborne acquired marine litter hyperspectral imaging dataset that contains data about different plastic targets and other materials and assessing the viability of detecting and classifying plastic materials without knowing their exact spectral response in an unsupervised manner. The classification of the marine litter samples was divided into known and unknown classes, i.e., classes that were hidden from the dataset during the training phase. The obtained results show a marine litter automated detection for all the classes, including (in the worst case of an unknown class) a precision rate over 56% and an overall accuracy of 98.71%.

Variation pattern classification of functional data

AbstractA new classification method for functional data is proposed in this article. This work is motivated by the need to identify features that discriminate between neurological conditions on which local field potentials (LFPs) were recorded. Regardless of the condition, these LFPs have zero mean, and thus the first moments of these random processes do not have discriminating power. We propose the variation pattern classification (VPC) method which employs the second‐moment structure as the discriminating feature and uses the Hilbert–Schmidt norm to measure the discrepancy between the second‐moment structure of different groups. The proposed VPC method is demonstrated to be sensitive to the discrepancy, potentially leading to a higher rate of classification. One important innovation lies in the dimension reduction where the VPC method adaptively determines the basis functions (discriminative feature functions) that account for the major discrepancy. In addition, the selected discriminative feature functions provide insights into the discrepancy between different groups because they reveal the features of variation pattern that differentiate groups. Consistency properties are established and, furthermore, simulation studies and the analysis of rat brain LFP trajectories empirically demonstrate the advantages and effectiveness of the proposed method.

Video-Based Time-Series Feature Extraction Image Encoding Methods for Enhanced Colorimetric Gas Concentration Estimation

Early detection and intervention of gas leaks can reduce industrial risks. Numerous early detection methods have been developed and applied in the industrial field, but they require professional analysis technology, long analysis time, and relatively expensive equipment. Strategies to reduce industrial gas hazards constantly require the development of new, efficient and reliable devices.In the past few decades, various types of gas sensors have been developed based on semiconductors, optical fibers, acoustic waves and other technologies. A significant amount of work has been done in recent years to make sensors smaller, more sensitive, more visually responsive, more manageable, more personal, and more wearable. However, these functions require expensive equipment, complex skills, and large amounts of power. In this regard, colorimetric sensors are of great interest due to their simplicity, ease of manufacture, low cost, visual response, and ease of interpretation without power consumption. However, current colorimetric sensors have some limitations to overcome, such as sensitivity, high cost, early detection and accuracy for use in industrial safety systems. Conventional colorimetric sensor studies use algorithms to compare discoloration with the naked eye, estimate gas concentrations with simple statistical methods, or estimate simple discoloration information using machine learning algorithms to estimate time-series data. Algorithms are trained on measured images or time series data extracted from images. Signal processing focuses on denoising done by scaling time series data. These studies using machine learning and deep learning-based analytics for colorimetric sensor studies did not give sufficient consideration to data coding. Machine learning of time series data is performed using a time series decomposition method that separates time dependencies. I am trying to analyze time-series data through image encoding.In this study, a time series data analysis technique using CNN (Convolutional Neural Network) including multidimensional image encoding was applied to improve the gas concentration estimation accuracy. The estimation accuracy obtained in this study was higher than the estimation accuracy obtained by applying existing statistical methods such as Auto-Regressive Integrated Moving Average (ARIMA) and Exponential Smoothing (ETS) and machine learning techniques such as Multi-layer Perceptron (MLP).We focused on estimating gas concentrations using a time-series-based colorimetric analysis method developed based on colorimetric fabric detection data. Time series data obtained through gas experiments were encoded into images to classify the color value change trend of gas concentration. Image encoding improves the efficiency of specifying gas-exposed sections and estimating gas concentrations within the entire section. Compared to the concentration estimation accuracy of the existing data classification method, MLP was improved by more than 2.5%. In addition, the accuracy was improved by applying a CNN that learned multidimensional processing of sensor data through image encoding. As a result, it was confirmed that the estimation accuracy was improved by 6.1% compared to the basic estimation technique. Although this method has limited data form and application fields, it is effective for subjects such as ours. The proposed technology can be applied to the next-generation smart industrial safety system. Figure 1

Geographic and cartographic inconsistency factors among different cropland classification datasets: A field validation case in Cambodia

Abstract Cropland cover datasets is of great significance for research on agricultural monitoring. The existing investigations on the inconsistency of different cropland datasets have mainly focused on first-class cropland and only analyzed the causes of this inconsistency in terms of cartography. To date, investigations have neglected the importance of fine cropland types in studies such as global food security assessment, and a comprehensive analysis of the causes of inconsistency from the perspectives of both cartography and geography is lacking. Moreover, the verification samples of existing studies have primarily been collected based on Google Earth. So, we examined the cropland resources of Cambodia using areal, spatial consistency, elevation classification, and field survey data assessment methods for the Global Food Security-support Analysis Data at 30 m for Southeast Asia, Global Land Cover Fine Surface Cover30-2015, Finer Resolution Observation and Monitoring of Global Land Cover2015, and SERVIR-Mekong datasets and comprehensively investigated the causes of inconsistency in terms of geography and cartography. The results revealed that the consistency of the extracted areas of first-class cropland among the four datasets was high. But, the cropland areas and statistical results from the Food and Agriculture Organization (FAO) of the United Nations are quite different. The overall accuracy (OA) for the first-class cropland of GFSAD30SEACE, GLC_FCS30-2015, and SERVIR-Mekong datasets were >82%. For fine cropland types, however, the OA of the SERVIR-Mekong dataset was relatively high, at 74.87%, while the accuracy levels of the global-scale GLC_FCS30-2015 and FROM_GLC2015 datasets were <50% due to the influence of scale size on mapping accuracy. In addition, in the eastern and northern portions of Cambodia with elevations of 50–200 m, the spatial consistency of the four datasets was low due to the serious confusion between cropland and forest, grassland, and shrub types. Therefore, land cover producers should adopt a zonal stratification strategy, focusing on remote sensing extraction techniques for confusing types in areas with high inconsistency to improve the accuracy of cropland.

Deteksi Dini Anak Disleksia dengan metode Support Vector Machine

Dyslexia is a brain disorder caused by genetics. People with dyslexia can live a normal life and even have certain advantages if they get the correct education. People with dyslexia often get the predicate stupid because teachers do not know the case of their students. Early detection of dyslexic children can be done with a series of tests so that the system can conclude that the data is dyslexic or not. Support Vector Machine is a data classification method to share dyslexia test results or not. This system is trained with test results data that are already available using the SVM method. This study uses gamification data to detect dyslexic children or not. SVM proves a good level of accuracy in predictions up to 94%.