Intelligent Classification Method Research Articles

Classification of gastric cancerous tissues by a residual network based on optical coherence tomography images.

Optical coherence tomography (OCT) is a noninvasive, radiation-free, and high-resolution imaging technology. The intraoperative classification of normal and cancerous tissue is critical for surgeons to guide surgical operations. Accurate classification of gastric cancerous OCT images is beneficial to improve the effect of surgical treatment based on the deep learning method. The OCT system was used to collect images of cancerous tissues removed from patients. An intelligent classification method of gastric cancerous tissues based on the residual network is proposed in this study and optimized with the ResNet18 model. Four residual blocks are used to reset the model structure of ResNet18 and reduce the number of network layers to identify cancerous tissues. The model performance of different residual networks is evaluated by accuracy, precision, recall, specificity, F1 value, ROC curve, and model parameters. The classification accuracies of the proposed method and ResNet18 both reach 99.90%. Also, the model parameters of the proposed method are 44% of ResNet18, which occupies fewer system resources and is more efficient. In this study, the proposed deep learning method was used to automatically recognize OCT images of gastric cancerous tissue. This artificial intelligence method could help promote the clinical application of gastric cancerous tissue classification in the future.

An Intelligent Classification Method of Multisource Enterprise Financial Data Based on SAS Model.

An enterprise is often faced with a large amount of financial information and data information. It is inefficient to rely solely on manual work, and the accuracy is difficult to guarantee. For the multisource data of corporate finance, it is more difficult for financial personnel to accurately analyze the connections between the data. For the multisource financial data of enterprise, this is also a time-consuming and laborious task for financial personnel. At the same time, it is difficult to find the correlation between multiple sources of data and then formulate financial data that guides the development of the enterprise. With the advancement of intelligent algorithms, an intelligent classification algorithm similar to the SAS model has emerged, which can realize the intelligent classification of enterprise financial multisource data and accurately predict the future development trend, which is extremely beneficial to the development and performance of the enterprise. This article mainly combines the financial intelligence classification model SAS with clustering and decision tree methods to classify the financial multisource information and uses the neural network method to carry out the future development trend of corporate finance. The research results show that the maximum error of enterprise financial classification after using the intelligent classification method is only 3.71% and that the forecast error of the future development trend of enterprise finance is only 1.77%. This is an acceptable error range, and this intelligent classification method is also greatly improving the efficiency of corporate financial management.

Intelligent rating method of tunnel surrounding rock based on one-dimensional convolutional neural network

Accurate prediction of surrounding rock grades holds great significance to tunnel construction. This paper proposed an intelligent classification method for surrounding rock based on one-dimensional convolutional neural networks (1D CNNs). Six indicators collected in some tunnel construction sites are considered, and the degree of linear correlation between these indicators has been analyzed. The improved one-hot encoding method is put forward for transforming these non-image indicators into one-dimensional structural data and avoiding the sampling error in the indicators of surrounding rock collected in the field. We found that the 1D CNNs model based on the improved one-hot encoding method can best extract the features of surrounding rock classification indicators (in terms of both accuracy and efficiency). We applied the well-trained classification model of tunnel surrounding rock to a series of expressway tunnels in China, and the results show that our model could accurately predict the surrounding rock grade and has great application value in the construction of tunnel engineering. It provides a new research idea for the prediction of surrounding rock grades in tunnel engineering.

An Intelligent Model for Success Prediction of Initial Coin Offerings

Assessment of Initial Coin Offerings (ICOs) is crucial for investment decisions in the ICO market. Since most ICOs succeed in raising funds, failed ICOs must be discriminated against through intelligent classification methods. In this context, this research proposes an intelligent decision model for predicting ICOs’ success that merges both the Information Gain Directed Feature Selection (IGDFS) technique as a features rank procedure to select the discriminative features representing the intial pool of features for Genetic Algorithm (GA) to find the ICO’s optimal feature set and Fuzzy Support Vector Machine for Class Imbalance Learning (FSVM-CIL) to tackle the problem of imbalanced classification. Two benchmark datasets were used to examine the proposed hybrid model referred to as IGDFS-FSVM. The experimental results reveal that the proposed model that employs an intelligent technique for ICO’s feature selection outperforms state-of-the-art classifiers without features selection. In this regard, we conclude that the proposed hybrid model is a practical approach to support investment decisions in the ICO market.

Intelligent Classification Method of Low Occupancy Big Data Based on Grid Index

In order to enhance the load balance in the big data storage process and improve the storage efficiency, an intelligent classification method of low occupancy big data based on grid index is studied. A low occupancy big data classification platform was built, the infrastructure layer was designed using grid technology, grid basic services were provided through grid system management nodes and grid public service nodes, and grid application services were provided using local resource servers and enterprise grid application services. Based on each server node in the infrastructure layer, the basic management layer provides load forecasting, image backup, and other functional services. The application interface layer includes the interfaces required for the connection between the platform and each server node, and the advanced access layer provides the human-computer interaction interface for the operation of the platform. Finally, based on the obtained main structure, the depth confidence network is constructed by stacking several RBM layers, the new samples are expanded by adding adjacent values to obtain the mean value, and the depth confidence network is used to classify them. The experimental results show that the load of different virtual machines in the low occupancy big data storage process is less than 40%, and the load of each virtual machine is basically the same, indicating that this method can enhance the load balance in the data storage process and improve the storage efficiency.

Detection of coal and gangue based on improved YOLOv5.1 which embedded scSE module

Accurate identification of coal-gangue have great significance for separation of coal-gangue. The traditional coal-gangue identification method has the disadvantages of low accuracy and slow speed. Therefore, an intelligent classification method of coal-gangue based on multispectral imaging technology and target detection is proposed in this paper. According to the model structure of YOLOv5, add scSE module in CSPDarknet and CSP module. The improved YOLOv5 is referred to as YOLOv5.1. To begin with, the multispectral data of coal-gangue are collected, and the collected coal-gangue images are screened. Beside, three bands with high recognition rate and correlation are selected from 25 bands to form pseudo-RGB images. Otherwise, the RGB image of coal-gangue was detected by theYOLOv5.1. By detecting the separated single band, the recognition rate and correlation of band 6, 10 and 12 are higher. The experimental results show that the average accuracy of detecting coal-gangue in the test set reaches 98.34 %, and the detection time is about 3.62 s by using the model of YOLOv5.1 to train the RGB image of coal-gangue. This method can not only accurately identify coal-gangue, but also obtain the relative position of coal-gangue, which can be effectively used for coal-gangue identification.

Comparative study of feature extraction and classification based on dispersion Lempel‐Ziv complexity

AbstractAs an important complexity feature of signal, Lempel‐Ziv complexity (LZC) has the advantage of simple‐to‐calculate, but it ignores amplitude information, and has low sensitivity at low amplitude. Dispersion Lempel‐Ziv complexity (DLZC) is a recently proposed nonlinear dynamic method, it has the advantage of immunity to noise even at relatively large proportion of noise and has been used to describe different pathological states. In view of its good performance in the field of biomedicine, we introduce DLZC into the field of underwater acoustic and fault diagnosis, and propose a feature extraction method for ship and gear fault signals based on DLZC, then an intelligent classification method was proposed by combining DLZC with K‐Nearest Neighbor (KNN) to further verify the effectiveness of the proposed feature extraction method, termed DLZC‐KNN. We conducted comparative experiments on feature extraction and classification, respectively: for the feature extraction comparison experiment, we compared the proposed feature extraction method with other feature extraction methods, which are based on Lempel‐Ziv complexity (LZC), permutation entropy (PE), dispersion entropy (DE), and fluctuation‐based dispersion entropy (FDE); for the classification comparison experiment, we compare the impact of different features and different classifiers on the recognition rate and also discussed the influence of different parameters on the experiment. The results show that DLZC has a better representation of signal complexity, and the DLZC‐KNN classification method gets a higher recognition rate than other comparative methods both in the field of fault diagnosis and underwater acoustic.

Study on Intelligent Diagnosis of Rotor Fault Causes with the PSO-XGBoost Algorithm

On basis of fault categories detection, the diagnosis of rotor fault causes is proposed, which has great contributions to the field of intelligent operation and maintenance. To improve the diagnostic accuracy and practical efficiency, a hybrid model based on the particle swarm optimization-extreme gradient boosting algorithm, namely, PSO-XGBoost is designed. XGBoost is used as a classifier to diagnose rotor fault causes, having good performance due to the second-order Taylor expansion and the explicit regularization term. PSO is used to automatically optimize the process of adjusting the XGBoost’s parameters, which overcomes the shortcomings when using the empirical method or the trial-and-error method to adjust parameters of the XGBoost model. The hybrid model combines the advantages of the two algorithms and can diagnose nine rotor fault causes accurately. Following diagnostic results, maintenance measures referring to the corresponding knowledge base are provided intelligently. Finally, the proposed PSO-XGBoost model is compared with five state-of-the-art intelligent classification methods. The experimental results demonstrate that the proposed method has higher diagnostic accuracy and practical efficiency in diagnosing rotor fault causes.

Handwritten dynamics classification of Parkinson’s disease through support vector machine and principal component analysis

Parkinson’s disease is a chronic neurodegenerative disease that affects the daily lives of tens of thousands of middle-aged and elderly people. The intelligent classification method of Parkinson’s disease has received extensive attention in recent years. The paper proposes a new auxiliary classification model of Parkinson’s disease based on principal component analysis and support vector machine. The model first samples and preprocesses the collected handwritten sensor data, then performs dimensionality reduction by principal component analysis, and finally inputs the dimensionality reduction data into a linear kernel support vector machine for Parkinson’s disease classification and prediction. The experiment uses 5-fold cross-validation for dataset segmentation and performance verification. The average performance results obtained on the Meander r dataset are: accuracy is 70.86%, specificity is 67.23%, sensitivity is 75.98%, and F1-Score is 69.72%, and the average performance results obtained on the Spiral dataset are: accuracy is 77.45%, specificity is 70.26%, sensitivity is 85.58%, and F1-Score is 77.10%.

A Review on Vibration-Based Fault Diagnosis Techniques for Wind Turbine Gearboxes Operating Under Nonstationary Conditions

Numerous studies on vibration-based techniques for fault diagnosis of wind turbine gearboxes operating under nonstationary conditions have been reported. In spite, a review on vibration-based condition monitoring and fault diagnosis techniques for gearboxes of wind turbines operating under nonstationary conditions is unavailable. Thus, the objective of this review is to discuss filtering, decomposition, entropy, and cyclostationary analysis techniques, as well as summarizing the remaining issues. This review will discuss various vibration-based diagnostic approaches developed for wind turbine gearboxes under nonstationary conditions, including both simulation and experimental approaches. Studies on dynamic models of gear systems and advanced signal-processing techniques developed for nonstationary conditions are reviewed. Additionally, the importance of multi-sensor and cointegration based approaches is discussed, and intelligent classification methods that have been used to distinguish healthy and faulty gear systems are also reviewed. Finally, the remaining research challenges are outlined.

Intelligent classification of logistics multi-distribution resources based on information fusion

Aiming at the problems of low recall rate and low precision of intelligent classification of logistics multi-distribution resources, an intelligent classification method of logistics multi-distribution resources based on information fusion is proposed. The discrete transformation of measurement equation and state equation is used to describe the state parameters of logistics distribution vehicles and roads. The state estimation component is used to estimate the state of logistics multi-distribution vehicles, and the state equation of logistics multi-distribution vehicles is obtained. The state error of multi-distribution vehicles is used to realise the intelligent classification of logistics multi-distribution resources. The experimental results show that this method has high recall rate and accuracy in intelligent classification of logistics multi-distribution resources, and can get more accurate classification results, at the same time it takes less time to classify resources, which is conducive to promoting the development of logistics distribution technology.

Research on Intelligent Algorithm of Identity Authentication Based on Facial Features

Identity recognition is a research hotspot in the information age. Nowadays, more and more occasions require identity recognition, especially in smart home. Identity recognition of the head of the household can avoid many troubles, such as home identification and network information authentication. Nowadays, in smart home identification, especially based on face recognition, system authentication is basically through feature matching. Although this method is convenient and quick to use, it lacks intelligence. Nowadays, for the make‐up, facelift, posture, and other differences, the accuracy of the system is greatly reduced. In this paper, the face recognition method is used for identity authentication. Firstly, the AdaBoost learning algorithm is used to construct the face detection and eye detection classifier to realize the detection and localization of the face and eyes. Secondly, the two‐dimensional discrete wavelet transform is used to extract facial features and construct a personal face dynamic feature database. Finally, an improved elastic template matching algorithm is used to establish an intelligent classification method for dynamic face elasticity models. The simulation shows that the proposed method can intelligently adapt to various environments without reducing the accuracy.

Intelligent classification of logistics multi-distribution resources based on information fusion

Aiming at the problems of low recall rate and low precision of intelligent classification of logistics multi-distribution resources, an intelligent classification method of logistics multi-distribution resources based on information fusion is proposed. The discrete transformation of measurement equation and state equation is used to describe the state parameters of logistics distribution vehicles and roads. The state estimation component is used to estimate the state of logistics multi-distribution vehicles, and the state equation of logistics multi-distribution vehicles is obtained. The state error of multi-distribution vehicles is used to realise the intelligent classification of logistics multi-distribution resources. The experimental results show that this method has high recall rate and accuracy in intelligent classification of logistics multi-distribution resources, and can get more accurate classification results, at the same time it takes less time to classify resources, which is conducive to promoting the development of logistics distribution technology.

A Novel Intelligent Classification Method for Urban Green Space Based on High-Resolution Remote Sensing Images

The real-time, accurate, and refined monitoring of urban green space status information is of great significance in the construction of urban ecological environment and the improvement of urban ecological benefits. The high-resolution technology can provide abundant information of ground objects, which makes the information of urban green surface more complicated. The existing classification methods are challenging to meet the classification accuracy and automation requirements of high-resolution images. This paper proposed a deep learning classification method for urban green space based on phenological features constraints in order to make full use of the spectral and spatial information of green space provided by high-resolution remote sensing images (GaoFen-2) in different periods. The vegetation phenological features were added as auxiliary bands to the deep learning network for training and classification. We used the HRNet (High-Resolution Network) as our model and introduced the Focal Tversky Loss function to solve the sample imbalance problem. The experimental results show that the introduction of phenological features into HRNet model training can effectively improve urban green space classification accuracy by solving the problem of misclassification of evergreen and deciduous trees. The improvement rate of F1-Score of deciduous trees, evergreen trees, and grassland were 0.48%, 4.77%, and 3.93%, respectively, which proved that the combination of vegetation phenology and high-resolution remote sensing image can improve the results of deep learning urban green space classification.

Intelligent Classification Method for Tunnel Lining Cracks Based on PFC-BP Neural Network

Tunnel lining crack is the most common disease and also the manifestation of other diseases, which widely exists in plain concrete lining structure. Proper evaluation and classification of engineering conditions directly relate to operation safety. Particle flow code (PFC) calculation software is applied in this study, and the simulation reliability is verified by using the laboratory axial compression test and 1 : 10 model experiment to calibrate the calculation parameters. Parameter analysis is carried out focusing on the load parameters, structural parameters, dimension, and direction which affect the crack diseases. Based on that, an evaluation index system represented by tunnel buried depth (H), crack position (P), crack length (L), crack width (W), crack depth (D), and crack direction (A) is put forward. The training data of the back propagation (BP) neural network which takes load-bearing safety and crack stability as the evaluation criteria are obtained. An expert system is introduced into the BP neural network for correction of prediction results, realizing classified dynamic optimization of complex engineering conditions. The results of this study can be used to judge the safety state of cracked lining structure and provide guidance to the prevention and control of crack diseases, which is significant to ensure the safety of tunnel operation.

Underwater Target Noise Recognition and Classification Technology based on Multi-Classes Feature Fusion

As one of the main signal sources of underwater acoustic target recognition, the target noise signal is difficult to characterize the characteristics of the target from clearly comparing with the multi-sensor detection technology, which may lead to lower recognition rate and higher false alarm rate and seriously restricts the function of underwater acoustic detection system. In order to solve this problem, a multi-layers LSTM underwater acoustic target noise feature extraction model is established by using the long short term memory network. The information features such as time-domain envelope of target noise, Demon line spectrum and Mel frequency cepstrum coefficient are extracted, and a subset of multi-classes features is constructed. On this basis, the feature level fusion recognition and classification model based on the multi-classes features subset and the decision level fusion recognition and classification model based on the D-S evidence theory are established, and the above-mentioned models are tested by using the sample database. The difference of classification result between the multi-classes feature fusion and the single class feature recognition classification is compared, and the above model is tested and verified by using the relevant test data of port basin verification experiment. The correlation results show that the present intelligent recognition and classification method of underwater target noise based on the multi-classes feature fusion is more robust, and the recognition rate and false alarm rate of underwater target are better than those of single category feature discrimination method.

Deep Cost Adaptive Convolutional Network: A Classification Method for Imbalanced Mechanical Data

Intelligent diagnosis is an important manner for mechanical fault diagnosis in the era of industrial big data, and deep network has received extensive attention in this field because of automatically learning features and classifying entered samples. As a classic deep learning model, Convolutional Neural Network has been applied in mechanical intelligent fault diagnosis. However, the limitation is that entered samples must be balanced to achieve satisfactory recognition rate. During the operation of machinery, the normal samples are abundant and the fault samples are rare. Therefore, the recognition rate of the minority category is minor when processing the imbalanced data with Convolutional Neural Network. To solve the above problem, an intelligent classification method for imbalanced mechanical data based on Deep Cost Adaptive Convolutional Network is proposed. According to this model, first, it learns intrinsic state characteristics in mechanical raw signals through multiple convolution and pooling operations. Second, it maps these characteristics to mechanical health condition by fully connected layers. Finally, the cost adaptive loss function adaptively assigns different misclassification costs for all categories and keeps updating them in training process to effectively classify the imbalanced mechanical data. The proposed method is verified by bearing data and milling cutter data with different imbalanced ratio, and compared with other methods. The experimental results show that the proposed method is robust and is able to effectively classify the imbalanced mechanical data.

Comparative Study of Full and Reduced Feature Scenarios for Health Index Computation of Power Transformers

Power transformer health index (PTHI) computation is performed based on the results of different tests, such as dissolved gas analysis (DGA), oil quality (OQ) evaluation, and depolarization factor (DP) testing. In this study, PTHI computation is performed using 631 dataset samples from Malaysia and 730 samples from the Gulf Region. A new model is proposed to predict the PTHI state by adopting intelligent classification methods (e.g., decision tree, support vector machine, k-nearest neighbor, and ensemble methods). The model is built via two-stage data processing. The first stage separates the test results into three modules that represent DGA, OQ, and DP factor codes. In the second stage, the output of the three modules is processed to predict the PTHI state. The four classification methods are applied to the proposed model, and the prediction accuracy of the PTHI state is determined. Results indicate that the proposed model has superior classification accuracy for each AI method compared with recent work. Furthermore, feature reductions are applied to minimize the testing time, effort, and costs. The reduced-feature models reveal the effectiveness of the adopted feature reduction technique. A slight difference in accuracy is observed between the full- and reduced-feature scenarios. Thus, the reduced-feature scenario is considered to decrease the effort and time of the computation process and the experimental cost. The proposed model is validated against uncertain noise in features of up to ±20%.

Intelligent Classification of Silicon Photovoltaic Cell Defects Based on Eddy Current Thermography and Convolution Neural Network

In this article, defects in the production process of silicon photovoltaic (Si-PV) cells are urgently needed to be detected due to their serious impact on the normal generation of PV system. In view of the shortcomings, such as low-defect efficiency, few detection data, and high detection error rate in the existing industrial production line, the main research purpose of this article is to complete an intelligent classification method for efficient and innovative defect detection for Si-PV cells and modules. The purpose is to improve the detection efficiency of Si-PV cell, to ensure the safety and reliability of Si-PV cell production process, to achieve large number of Si-PV cell defects detection and classification. First, the eddy current thermography system of Si-PV cells is established. Second, principal component analysis, independent component analysis, and nonnegative matrix factorization algorithms are compared for thermography sequences processing. Third, LeNet-5, VGG-16, and GoogleNet models are compared for Si-PV cell defects classification. Finally, the results show that the proposed method have successful application in Si-PV cell defects detection and classification.

Ultrasound image classification of hepatic echinococcosis using deep learning

Hepatic echinococcosis is a serious regional parasitic disease. The lesion classification mainly relies on the subjective judgment of clinicians on the ultrasonic images, which is very time-consuming and prone to miscalculation in disease screening. This study proposes an intelligent classification method for hepatic echinococcosis lesions based on the ultrasound images. Firstly, the lesion images are cropped from the hepatic echinococcosis ultrasound images directly. The deep convolutional neural network (CNN) extracts the multi-scale features. Then the multi-scale features are combined with the visual attention model to learn the global and local detail features of the image through the the main and auxiliary branches of the classification network, respectively. Finally, we use the metric learning to represent the similar features of the samples of the same category, so as to realize the automatic classification of nine types of echinococcosis lesions. An 18-layer CNN network is constructed, which is trained on 7 000 images. The average accuracy on 2 000 test images is 82% and the average <italic>F</italic>₁ score is 82%. The results demonstrate that the proposed method can be effectively applied to the ultrasound image classification of hepatic echinococcosis.