Data Classification Model Research Articles

‘The more populism types you know, the better political scientist you are?’ Machine-learning based meta-analysis of populism types in the political science literature

ABSTRACT This text builds on existing debates on types of populism in contemporary political science literature. Our premise is that with new types of populism emerging in the debate, and with the significantly increasing number of texts dealing with populism, the types are being hollowed out. Using a dataset consisting of a total of 539 texts published between 2011 and 2020 containing the keyword populism and using a machine-learning based classification model of concordance data, we show that (1.) ambiguities and confusions among the different types of populism become more prominent over the study period, categories become emptier and their usefulness for classification decreases, and (2.) the only stable and consensually defined type in the long run is right-wing populism. We conclude by recommending to depart from creating classifications of types of populism based on specific ideological or non-ideological features and to keep these levels (populism and other features) – within analysis – separate.

Correction: Meta-heuristic endured deep learning model for big data classification: image analytics

Correction: Meta-heuristic endured deep learning model for big data classification: image analytics

A Functional Data Classification Framework Based on Functional Sufficient Dimension Reduction and Model Averaging

With the ever-evolving advancements in data collection and storage technologies, high-frequency data recorded in patterns that change over time have become increasingly common. In many application scenarios for this type of data, functional data classification has emerged as a prominent issue in the field of statistics. In light of this, this paper proposes a functional data classification model based on the functional sufficient dimensionality reduction method and the idea of model averaging. The proposed method utilizes techniques such as Functional Slice Inverse Regression (FSIR) and Functional Average Variance Estimation (FSAVE) to project an infinite-dimensional random function onto a function space spanned by a finite wiki function, ensuring that the original data's effective information for categorical variables is not lost. Additionally, the Bagging algorithm effectively addresses the overfitting and underfitting problems that arise in single predictive models, while employing model averaging instead of model selection to adaptively select the sufficient dimensionality reduction sub-directions. Notably, in the prediction stage, the number and types of base models are flexible. Empirical analysis demonstrates that the proposed method outperforms some comparative methods in terms of prediction accuracy and robustness.

Analisis Sentimen dan Sistem Pendukung Keputusan Menginap di Hotel Menggunakan Metode CRISP-DM dan SAW

Research combining sentiment analysis approaches with decision support systems in the hospitality industry is still very limited. This study aims to analyze hotel guest sentiment based on location, cleanliness, service, and value criteria using Cross Industry Standard Process for Data Mining (CRISP-DM) to identify five and ten famous words based on sentiment data and the sentiment classification model with the best performance. Furthermore, the results of identifying five and ten famous words based on sentiment data related to location, cleanliness, service, and value ratings were processed using the Simple Additive Weighting (SAW) method. The results of this study show that the performance of SVM algorithms using SMOTE operators has accuracy values (99.74%), precision values (100%), recall values (99.48%), f-measure values (99.74%), and AUC (100%). This shows that sentiment classification results using the SVM algorithm with SMOTE operators can be used as a sentiment data classification model with 30% training and 70% test data. This model is relevant to be used as a model for the classification process of 1680 review data obtained from the Tripadvisor website at Grand Zuri Malioboro Hotel Yogyakarta, Tentrem Hotel Yogyakarta, Grand Ambarukmo Hotel, El Royale Yogyakarta Malioboro, and Ceria Hotel @alun alun Yogyakarta. Specifically, aspects that concern guests relate to staff, breakfast, room, and service. In addition, the results of the implementation of the SAW method show that Grand Zuri Malioboro Hotel Yogyakarta ranks first with a total value of 0.907663917. Otherwise, Ceria Hotel @alun Yogyakarta Square ranks second with a total value of 0.897193878. Meanwhile, Hotel Tentrem Yogyakarta ranks third with a total value of 0.861265289. This shows that hotel guests who assess the criteria of location, cleanliness, service, and value by giving value weights as rated on the Tripadvisor website and provide importance weights with similar values, where location (0.20), cleanliness (0.25), service (0.30), value (0.25) then the alternative with the highest weight is Hotel Grand Zuri Malioboro Yogyakarta.

The communication path and improvement strategy of symbolic culture of sneaker consumption culture using the big data analysis.

With the emergence of Artificial Intelligence technology and the advancement of science and technology, the current mainstream path of social development is continuously updating and improving various industries using technology. Therefore, in order to promote the development of sneaker consumer culture, this study explores the use of technological means to improve the dissemination effect of symbolic culture in sneaker consumer culture. Firstly, the development concept and mainstream direction of sneaker consumer culture in the era of big data are discussed, and the application principle of big data technology is introduced. Then, a sneaker culture dissemination model based on big data technology is designed. Finally, the model is optimized using a Convolutional Neural Network (CNN), and its effectiveness is evaluated. The results show that the Convolutional Neural Network-Big Data (CNN-BD) model designed in this study has the highest fitting degree of 93% and a lowest fitting degree of 78% in the UT-Zap50K dataset. In the Ai2 dataset, the highest fitting degree of the big data classification model is 94%, and the lowest is 76%. In the Kaggle Women's Shoe dataset, the highest fitting degree of the big data classification model is 92%, and the lowest is 77%. In the Kaggle Men's Shoe dataset, the highest fitting degree of the big data classification model is 94%, and the lowest is 79%. The designed model has the highest accuracy rate of 93% in sneaker classification, while other models have the highest accuracy rate of around 82% in sneaker classification. Compared with traditional big data technology, the designed model has greatly improved and can adapt to more working environments. This study not only provides technical support for the application of big data technology but also contributes to improving the dissemination effect and promoting the comprehensive development of sneaker consumer culture.

3D target detection and spectral classification for single-photon LiDAR data.

3D single-photon LiDAR imaging has an important role in many applications. However, full deployment of this modality will require the analysis of low signal to noise ratio target returns and very high volume of data. This is particularly evident when imaging through obscurants or in high ambient background light conditions. This paper proposes a multiscale approach for 3D surface detection from the photon timing histogram to permit a significant reduction in data volume. The resulting surfaces are background-free and can be used to infer depth and reflectivity information about the target. We demonstrate this by proposing a hierarchical Bayesian model for 3D reconstruction and spectral classification of multispectral single-photon LiDAR data. The reconstruction method promotes spatial correlation between point-cloud estimates and uses a coordinate gradient descent algorithm for parameter estimation. Results on simulated and real data show the benefits of the proposed target detection and reconstruction approaches when compared to state-of-the-art processing algorithms.

DEEP LEARNING FOR SIMULTANEOUS IMPUTATION AND CLASSIFICATION OF TIME SERIES INCOMPLETE DATA

Classification with time series data has many practical applications in finance, medicine, manufacturing, energy, transportation, and agriculture. However, time series data is often plagued by missing values, which not only decreases the accuracy but also increases the complexity of classification models. A common approach to address classification with missing data is to use imputation methods to estimate the missing values before constructing classification models. Recurrent neural network models have been shown to be effective in estimating missing values for time series data. On the other hand, convolutional neural network models have demonstrated their effectiveness in building classification models for time series data. However, there has been no research that specifically addresses how to combine these two types of models to simultaneously address the problem of time series classification with incomplete data. Therefore, in this paper, a model combining recurrent neural networks and convolutional neural networks is proposed to build a model that can simultaneously estimate missing values and classify time series data. The experimental results demonstrate that the proposed model performs better than the existing methods for time series classification with incomplete data.

Research on multi-class orthodontic image recognition system based on deep learning network model

Objective: To develop a multi-classification orthodontic image recognition system using the SqueezeNet deep learning model for automatic classification of orthodontic image data. Methods: A total of 35 000 clinical orthodontic images were collected in the Department of Orthodontics, Capital Medical University School of Stomatology, from October to November 2020 and June to July 2021. The images were from 490 orthodontic patients with a male-to-female ratio of 49∶51 and the age range of 4 to 45 years. After data cleaning based on inclusion and exclusion criteria, the final image dataset included 17 453 face images (frontal, smiling, 90° right, 90° left, 45° right, and 45° left), 8 026 intraoral images [frontal occlusion, right occlusion, left occlusion, upper occlusal view (original and flipped), lower occlusal view (original and flipped) and coverage of occlusal relationship], 4 115 X-ray images [lateral skull X-ray from the left side, lateral skull X-ray from the right side, frontal skull X-ray, cone-beam CT (CBCT), and wrist bone X-ray] and 684 other non-orthodontic images. A labeling team composed of orthodontic doctoral students, associate professors, and professors used image labeling tools to classify the orthodontic images into 20 categories, including 6 face image categories, 8 intraoral image categories, 5 X-ray image categories, and other images. The data for each label were randomly divided into training, validation, and testing sets in an 8∶1∶1 ratio using the random function in the Python programming language. The improved SqueezeNet deep learning model was used for training, and 13 000 natural images from the ImageNet open-source dataset were used as additional non-orthodontic images for algorithm optimization of anomaly data processing. A multi-classification orthodontic image recognition system based on deep learning models was constructed. The accuracy of the orthodontic image classification was evaluated using precision, recall, F1 score, and confusion matrix based on the prediction results of the test set. The reliability of the model's image classification judgment logic was verified using the gradient-weighted class activation mapping (Grad-CAM) method to generate heat maps. Results: After data cleaning and labeling, a total of 30 278 orthodontic images were included in the dataset. The test set classification results showed that the precision, recall, and F1 scores of most classification labels were 100%, with only 5 misclassified images out of 3 047, resulting in a system accuracy of 99.84%(3 042/3 047). The precision of anomaly data processing was 100% (10 500/10 500). The heat map showed that the judgment basis of the SqueezeNet deep learning model in the image classification process was basically consistent with that of humans. Conclusions: This study developed a multi-classification orthodontic image recognition system for automatic classification of 20 types of orthodontic images based on the improved SqueezeNet deep learning model. The system exhibitted good accuracy in orthodontic image classification.

Electricity theft detection based on hybrid random forest and weighted support vector data description

Improving the detection rate of electricity theft users in smart grids is crucial to the safe operation of the power system and the economic efficiency of the grid. The traditional electricity theft detection relies on manual household inspection, which is costly and inefficient. With the application of smart meters, machine learning-based methods are gradually applied to detect electricity theft users. However, the training of the model is limited by the unbalanced electricity consumption dataset, and the performance of the model is limited in the process of processing high-dimensional data. Therefore, this paper adopts ensemble learning and imbalance data classification model to analyze the electricity theft detection problem in complex grid environment, and proposes an electricity theft detection model based on random forest and weighted support vector description. Firstly, the feature selection algorithm for mixed load data with statistical features based on random forest (FS-MLDRF) is used to extract the features that can best represent the customers’ electricity consumption behavior, so as to reduce the complexity of user data. Finally, an electricity theft detection based on hybrid random forest and weighted support vector data description is constructed (HFR-WSVDD), and the SVDD classifier is trained with the features weighted by feature importance to improve the performance of power theft detection in the case of unbalanced data. The simulation experiment results on the real electricity dataset show that compared with existing feature selection algorithms and anomaly detection algorithms, the algorithms proposed in this paper have excellent feature representation capability and better classification performance.

Deep Learning-Based Big Data Analytics Model Based on Teaching Reforms in Three-Dimensional Composition

With the development of online education and big data analysis, new teaching models and methods have emerged. The integration of online and offline teaching modes based on big data analysis has become an effective way to promote teaching reform and practice in the field of three-dimensional composition. It is important to incorporate teaching reform into the teaching of three-dimensional composition to improve the quality of education and better prepare students for their future careers. This paper evaluated the contribution of teaching reform to the improvement of student performance. This paper designed a Deep Learning (DL) big data analytics model for data clustering and classification. The student performance is monitored for both online teaching and offline teaching classes. The collected data is clustered with the directional clustering process for the computation of feature space. With the estimated feature space value Hidden Markov Model (HMM) is implemented for the estimation of statistical data derived from the feature spaces. The extracted data were applied over the RESENT- 50 model for the classification of students’ performance. The data analysis with DL model stated that student performance in offline teaching is more significant than offline teaching in 3-dimensional aspects.

Meta-heuristic endured deep learning model for big data classification: image analytics

Meta-heuristic endured deep learning model for big data classification: image analytics

The dilemma and path of rural college students returning to their hometowns for employment and entrepreneurship in the post-epidemic period under the background of big data

Abstract The dilemma of exploring the children in institutions of higher learning to find jobs or start their own companies of rural origin and return to their hometown is paving the way for college students to find jobs of rural origin. In this paper, a decision tree optimized by a partial least squares regression algorithm is proposed to construct a DT-PLS data classification model in the case of cloud data, and the performance of the DT-PLS model is evaluated for the DT-PLS model. Using college students’ employment and entrepreneurship data from colleges and universities as examples, two factors that influence college students of rural origin to return to the registered permanent residence to find a job or start a company, namely subjective factors and contextual factors, are mined, and data analysis is carried out for the two influencing factors. From the 12 sub-indicators of subjective factors, the mean values of those considered very unconformable, unconformable, uncertain, conformable and very conformable were 17.87%, 15.38%, 10.82%, 16.09% and 39.84%, respectively. Regarding the 10 sub-indicators of contextual factors, the mean values of the percentages of those considered very non-conforming, non-conforming, uncertain, conforming, and very conforming were 6.56%, 20.95%, 13.69%, 26.13%, and 32.67%, respectively. The DT-PLS classification, the main method here, analyzes the current dilemmas of returning college students of rural origin to entrepreneurship and employment and prompts more college students to invest in the grassroots to provide fresh talent blood for rural revitalization.

Classification of Water Source in Coal Mine Based on PCA-GA-ET

In recent years, inrush water has hampered the regular mining of coal mines, and the proper identification of the source of inrush water is critical to the prevention and management of water hazards in mines. This paper extracts the standard water chemistry discriminating ions Na++K+, Ca2+, Mg2+, Cl−, SO42−, and HCO3− from observed water samples. An improved water source discrimination model is proposed which combines algorithms from data mining, classification models, and learning reinforcement. According to the Pearson correlation coefficient, Na++K+ has a strong correlation with HCO3−. To identify the major metrics, we performed principal component analysis (PCA), and the adaptive differential evolutionary genetic algorithm (GA) was utilized to optimize the depth of the extreme tree (ET) and the number of classifiers. Finally, the model distinguished 25 sets of studied samples from various water sources in the Pingdingshan coalfield. Comparative analysis demonstrated the efficacy of each stage of our work. PCA-GA-ET outperformed the conventional approaches, such as the support vector machine, BP artificial neural network, and random forest. The studies revealed that PCA-GA-ET can eliminate the information overlap between data and simplify the data structure and thereby improve the efficiency and accuracy of water source detection. We discovered that by utilizing the evolutionary algorithm to optimize parameters such as the depth of the extreme trees and the number of decision trees, we could get the model to converge faster and to be more stable and more accurate. The results suggest that PCA-GA-ET has good robustness and accuracy and can meet the needs of water source identification.

오류 라벨을 포함한 분류모형의 강건성 모의실험연구

In order to increase the accuracy and performance of classification models, the quality of data must be guaranteed. There are various factors that affect the quality of these data, such as measurement accuracy, missing value, and sampling biases. This study focuses on the robustness of the classification model for mislabeled data. The reason we are interested in mislabeled data is that it significantly degrades the performance of the model more than other common measurement errors. In this study, the efficiency of various classification methods for data with mislabels is reviewed. Fisher's linear discriminant analysis model (LDA), quadratic discriminant analysis model (QDA), and logistic regression model were considered in the statistical model-based method, and SVM (support vector machine) and boosting are compared in the algorithm-based method. As a result of simulation study, it is found that the statistical model based approaches show better results in terms of robustness in the data assuming various situations of mislabels.

A secure and privacy-preserving data aggregation and classification model for smart grid

A secure and privacy-preserving data aggregation and classification model for smart grid

Fuzzy Neighbors and Deep Learning-Assisted Spark Model for Imbalanced Classification of Big Data

Big data is important in knowledge manipulation, assessment, and prediction. However, extracting and analyzing knowledge through big database are complex because of imbalance data distribution that leads to wrong decisions and biased classification outputs. Hence, an effective and optimal big data classification approach is designed using the proposed Bird Swarm Deer Hunting Optimization-Deep Belief Network (BSDHO-based DBN) algorithm based on spark architecture that follows the master and slave nodes. The proposed BSDHO is obtained by combining Deer Hunting Optimization algorithm and Bird Swarm Algorithm. The developed model poses two nodes, namely slave and master node. The training data is initially given to the master node in the spark architecture to perform transformation of data. Here, the transformation of data is done with an exponential log kernel, and then selection of feature is done with sequential forward selecting for choosing suitable features for enhanced processing. Consequently, oversampling process is performed with Fuzzy K-Nearest Neighbor (Fuzzy KNN) in the slave node using selected features to manage imbalance data. Then, in master node, classification is done with Deep belief Network, and trained using developed Bird swarm Deer Hunting Optimization (BSDHO) algorithm. On the other hand, the test data is taken as input, and is fed to the slave node to perform data transformation. Then, the transformed data is given to the master node for classification based on the proposed BSDHO. At last, the training data and testing data output produced the classified output. The proposed BSDHO-based DBN provided enhanced outcomes with highest specificity of 97.92%, accuracy of 96.92%, and sensitivity of 96.9%.

An Advanced Decision Tree-Based Deep Neural Network in Nonlinear Data Classification

Deep neural networks (DNNs), the integration of neural networks (NNs) and deep learning (DL), have proven highly efficient in executing numerous complex tasks, such as data and image classification. Because the multilayer in a nonlinearly separable data structure is not transparent, it is critical to develop a specific data classification model from a new and unexpected dataset. In this paper, we propose a novel approach using the concepts of DNN and decision tree (DT) for classifying nonlinear data. We first developed a decision tree-based neural network (DTBNN) model. Next, we extend our model to a decision tree-based deep neural network (DTBDNN), in which the multiple hidden layers in DNN are utilized. Using DNN, the DTBDNN model achieved higher accuracy compared to the related and relevant approaches. Our proposal achieves the optimal trainable weights and bias to build an efficient model for nonlinear data classification by combining the benefits of DT and NN. By conducting in-depth performance evaluations, we demonstrate the effectiveness and feasibility of the proposal by achieving good accuracy over different datasets.

High-performance fuzzy optimized deep convolutional neural network model for big data classification based on the social internet of things

High-performance fuzzy optimized deep convolutional neural network model for big data classification based on the social internet of things

A Novel Framework for Classification of Different Alzheimer’s Disease Stages Using CNN Model

Background: Alzheimer’s, the predominant formof dementia, is a neurodegenerative brain disorder with no known cure. With the lack of innovative findings to diagnose and treat Alzheimer’s, the number of middle-aged people with dementia is estimated to hike nearly to 13 million by the end of 2050. The estimated cost of Alzheimer’s and other related ailments is USD321 billion in 2022 and can rise above USD1 trillion by the end of 2050. Therefore, the early prediction of such diseases using computer-aided systems is a topic of considerable interest and substantial study among scholars. The major objective is to develop a comprehensive framework for the earliest onset and categorization of different phases of Alzheimer’s. Methods: Experimental work of this novel approach is performed by implementing neural networks (CNN) on MRI image datasets. Five classes of Alzheimer’s disease subjects are multi-classified. We used the transfer learning determinant to reap the benefits of pre-trained health data classification models such as the MobileNet. Results: For the evaluation and comparison of the proposed model, various performance metrics are used. The test results reveal that the CNN architectures method has the following characteristics: appropriate simple structures that mitigate computational burden, memory usage, and overfitting, as well as offering maintainable time. The MobileNet pre-trained model has been fine-tuned and has achieved 96.6 percent accuracy for multi-class AD stage classifications. Other models, such as VGG16 and ResNet50 models, are applied tothe same dataset whileconducting this research, and it is revealed that this model yields better results than other models. Conclusion: The study develops a novel framework for the identification of different AD stages. The main advantage of this novel approach is the creation of lightweight neural networks. MobileNet model is mostly used for mobile applications and was rarely used for medical image analysis; hence, we implemented this model for disease detection andyieldedbetter results than existing models.

Research on wireless sensor privacy data measurement and classification model based on IoT technology

Traditional wireless sensor privacy data measurement and classification process has the problems of low accuracy and very time-consuming. A new wireless sensor privacy data measurement and classification model is proposed. The measurement module of the model establishes two levels of privacy measurement elements from three dimensions, calculates the weight of level privacy elements by using Shannon information entropy, and obtains the privacy quantity of each data privacy measurement element in the data set. With the help of internet of things technology, the privacy data measurement and classification model of wireless sensor is designed. The experimental results show that the misjudgement rate of this model is very low, less than 5%, and the misjudgement error is kept below 10%. Using this model to protect the wireless sensor privacy data, the data running cost and time cost show a low level, has a certain application value.