Back Propagation Neural Network Classifier Research Articles

Forest fire monitoring via uncrewed aerial vehicle image processing based on a modified machine learning algorithm.

Forests are indispensable links in the ecological chain and important ecosystems in nature. The destruction of forests seriously influences the ecological environment of the Earth. Forest protection plays an important role in human sustainable development, and the most important aspect of forest protection is preventing forest fires. Fire affects the structure and dynamics of forests and also climate and geochemical cycles. Using various technologies to monitor the occurrence of forest fires, quickly finding the source of forest fires, and conducting early intervention are of great significance to reducing the damage caused by forest fires. An improved forest fire risk identification algorithm is established based on a deep learning algorithm to accurately identify forest fire risk in a complex natural environment. First, image enhancement and morphological preprocessing are performed on a forest fire risk image. Second, the suspected forest fire area is segmented. The color segmentation results are compared using the HAF and MCC methods, and the suspected forest fire area features are extracted. Finally, the forest fire risk image recognition processing is conducted. A forest fire risk dataset is constructed to compare different classification methods to predict the occurrence of forest fire risk to improve the backpropagation (BP) neural network forest fire identification algorithm. An improved machine learning algorithm is used to evaluate the classification accuracy. The results reveal that the algorithm changes the learning rate between 0.1 and 0.8, consistent with the cross-index verification of the 10x sampling algorithm. In the combined improved BP neural network and support vector machine (SVM) classifier, forest fire risk is recognized based on feature extraction and the BP network. In total, 1,450 images are used as the training set. The experimental results reveal that in image preprocessing, image enhancement technology using the frequency and spatial domain methods can enhance the useful information of the image and improve its clarity. In the image segmentation stage, MCC is used to evaluate the segmentationresults. The accuracy of this algorithm is high compared with other algorithms, up to 92.73%. Therefore, the improved forest fire risk identification algorithm can accurately identify forest fire risk in the natural environment and contribute to forest protection.

A life-threatening arrhythmia detection method based on pulse rate variability analysis and decision tree.

Extreme bradycardia (EB), extreme tachycardia (ET), ventricular tachycardia (VT), and ventricular flutter (VF) are the four types of life-threatening arrhythmias, which are symptoms of cardiovascular diseases. Therefore, in this study, a method of life-threatening arrhythmia recognition is proposed based on pulse rate variability (PRV). First, noise and interference are wiped out from the arterial blood pressure (ABP), and the PRV signal is extracted. Then, 19 features are extracted from the PRV signal, and 15 features with highly important and significant variation were selected by random forest (RF). Finally, the back-propagation neural network (BPNN), extreme learning machine (ELM), and decision tree (DT) are used to build, train, and test classifiers to detect life-threatening arrhythmias. The experimental data are obtained from the MIMIC/Fantasia and the 2015 Physiology Net/CinC Challenge databases. The experimental results show that the DT classifier has the best average performance with accuracy and kappa coefficient (kappa) of 98.76 ± 0.08% and 97.59 ± 0.15%, which are higher than those of the BPNN (accuracy = 94.85 ± 1.33% and kappa = 89.95 ± 2.62%) and ELM (accuracy = 95.05 ± 0.14% and kappa = 90.28 ± 0.28%) classifiers. The proposed method shows better performance in identifying four life-threatening arrhythmias compared to existing methods and has potential to be used for home monitoring of patients with life-threatening arrhythmias.

A prediction model of wall shear stress for ultra-high-pressure water-jet nozzle based on hybrid BP neural network

ABSTRACT Two hybrid back-propagation neural network (BPNN) models optimized by two heuristic search algorithms, namely genetic algorithm (GA-BP) and particle swarm optimization (PSO-BP), are proposed in this paper to predict radial maximum wall shear stress instead of traditional computational fluid dynamics (CFD) methods. The two proposed models are trained and validated using a database of 150 radial maximum wall-shear-stress values obtained via CFD simulations. The best fit model is identified from various BPNN models based on the Akaike information criterion (AIC) and the Bayesian information criterion (BIC), balancing the trade-off between goodness-of-fit and model complexity. The model performance is evaluated by MAE, RMSE, regression coefficient (R), and Nash-Sutcliffe efficiency (NSE). The best fit model is a three-layered BPNN model consisting of a 4:4:1 topology. In almost all evaluation indicators, the two hybrid BPNN methods outperform three existing algorithms, namely classical BPNN, random forest (RF), and gradient boosting decision tree (GBDT). Both PSO-BP and GA-BP can provide a more precise assessment of radial maximum wall shear stress, with maximum errors being 5.81% and 8.24% respectively. The proposed PSO-BP prediction model is promising and has great feasibility in predicting the radial maximum wall shear stress of UHP water-jet nozzle in engineering applications.

Dual stimuli interface with logical division using local move stimuli.

Improving information transfer rate is a key to prompt the speed of outputting instructions of the event-related potential-based brain-computer interface. Our previous study designed a dual-stimuli interface that simultaneously presents two types of different stimuli to improve the speed. While, adding more stimuli into this interface makes subject easily affected by "flanker effect" that decreases the accuracy of recognizing intention. To achieve high recognition accuracy with many stimuli, this study proposes a dual stimuli interface based on whole flash and local move (DS-WL) and two rules of stimulus arrangement to induce the brain signals. Twenty subjects participated in the experiment, and their signals are recognized by a back propagation neural network classifier. The local move induces larger and later signals of targets to help discriminate the two kinds of stimuli; the rules reduce the N200 and P300 amplitudes of non-target, which improves accuracy. This study demonstrates that the DS-WL is a useful way to shorten the instruction output cycle and speed up the instructions outputting by local move and rules.

VIS-NIR spectroscopy for detection of citrus core rot caused by Alternaria alternata

Non-destructive identification of the fungal disease has great importance as one of the challenges of the citrus post-harvest industry. In order to identify the fungal disease of Alternaria alternata, which occurred internally, the reflectance spectra were collected in 3 areas of the stem-end, equatorial and stylar-end of healthy and fungus-infected oranges using VIS-NIR spectrometer (400–1100 nm). Principal Component Analysis models were extracted from the preprocessed wavelengths after performing various preprocessors such as Savitzky-Gulay, standard normal variate and mean normalization. The classification capability of support vector machine and back-propagation neural network classifiers was evaluated in identifying appropriate preprocessors from the obtained principal components and identifying infected fruits using optimal wavelengths. The highest accuracy of the classification was obtained by the back-propagation neural network classifier using the optimal wavelengths of the stylar-end area. It included training, validation and testing stages for Thompson cultivar that was 94%, 90% and 93% and for Jaffa cultivar, was 97%, 91% and 97%, respectively. Appropriate classification results indicate the generalizability of the models developed to identify internal fungal infection of Alternaria alternata in orange fruit.

New Anomaly Network Intrusion Detection System in Cloud Environment Based on Optimized Back Propagation Neural Network Using Improved Genetic Algorithm

Cloud computing is distributed architecture, providing computing facilities and storage resource as a service over an open environment (Internet), this lead to different matters related to the security and privacy in cloud computing. Thus, defending network accessible Cloud resources and services from various threats and attacks is of great concern. To address this issue, it is essential to create an efficient and effective Network Intrusion System (NIDS) to detect both outsider and insider intruders with high detection precision in the cloud environment. NIDS has become popular as an important component of the network security infrastructure, which detects malicious activities by monitoring network traffic. In this work, we propose to optimize a very popular soft computing tool widely used for intrusion detection namely, Back Propagation Neural Network (BPNN) using an Improved Genetic Algorithm (IGA). Genetic Algorithm (GA) is improved through optimization strategies, namely Parallel Processing and Fitness Value Hashing, which reduce execution time, convergence time and save processing power. Since, Learning rate and Momentum term are among the most relevant parameters that impact the performance of BPNN classifier, we have employed IGA to find the optimal or near-optimal values of these two parameters which ensure high detection rate, high accuracy and low false alarm rate. The CloudSim simulator 4.0 and DARPA’s KDD cup datasets 1999 are used for simulation. From the detailed performance analysis, it is clear that the proposed system called “ANIDS BPNN-IGA” (Anomaly NIDS based on BPNN and IGA) outperforms several state-of-art methods and it is more suitable for network anomaly detection.

Early detection of breast cancer using robust back propagation neural network classifier

Breast cancer is the most widely recognized malignancy in women and is the second most common and important cause of cancer death in women. Currently, there is no e􀵵 ective approach to avoid breast cancer, as its motivation is not yet fully understood. The common problems of women in recent years are breast cancer. The problem of breast cancer classification has been the main problem in recent years. This article gives a reasonable idea of the readiness of the mammogram image to find out the area a􀵵 ected by cancer, which is a vital advance in breast cancer detection. Therefore, the research focuses on examining and analyzing the image processing of cancerous diseases, especially breast cancer. When detecting breast cancer, images are obtained from a mammogram and subjected to treatment. The artificial neural network (ANN) plays an important role in this regard, in particular in the application of biomedical image processing for the early diagnosis of breast cancer. It is actually detected by these steps. Preprocessing, image splitting, attribute extraction and categorization. An average vector filter is used to perform the preprocessing operation. Helps eliminate noise and turn RGB image into grayscale image. Vessel segmentation is used to segment the image. To perform entity extraction, the technique of the Binary Local Scale Model (MLBP) method is used and optimized using the Robust Propagation Neural Network Classifier (RBPNN). Using MLBP, 12 functional derivatives were extracted. The extraction is performed on the basis of color, texture and shape. It plays an important role in detection. Finally, for the classi􀂿 cation of the extracted function, RBPNN is performed and then analyzes the test data with the trained data. To prove its usefulness, it produces great precision compared to other current games. The accuracy of this suggested analysis is 97%.

Liver Cancer Detection and Classification Using Raspberry Pi

In practical radiology, early diagnosis and precise categorization of liver cancer are difficult issues. Manual segmentation is also a time-consuming process. So, utilizing various methodologies based on an embedded system, we detect liver cancer from abdominal CT images using automated liver cancer segmentation and classification. The objective is to categorize CT scan images of primary and secondary liver disease using a Back Propagation Neural Network (BPNN) classifier, which has greater accuracy than previous approaches. In this work, a newly proposed method is shown which has four phases: image preprocessing, image segmentation, extraction of the features, and classification of the liver. Level set segmentation for segmenting the liver from abdominal CT images and Practical Swarm Optimization (PSO) for the tumor segmentation. Then the features from the liver are extracted and given to the BPNN classifier to classify the liver cancer. These algorithms are implemented on the Raspberry Pi. Then it serially interfaces with the MAX3232 protocol via serial communication. The GSM 800C module is connected to the system to send SMS as primary or secondary cancer. The BPNN classification technique achieved an excellent accuracy of 97.98%. The experimental results demonstrate the efficiency of this proposed approach, which provides excellent accuracy with good results.

An Early Prediction of Tumor in Heart by Cardiac Masses Classification in Echocardiogram Images Using Robust Back Propagation Neural Network Classifier

Identification and classification of intracardiac masses in echocardiogram is one of the significant processes in the diagnosis of cardiovascular disease. A robust back propagation neural network (RBPNN) technique is used to conquer every single conventional-issue utilizing the echocardiogram image analysis for this work, which consists of four phases such as noise removal, automatic segmentation, feature extraction, and intracardiac masses classification. Initially, the noise is diminished from the echocardiogram images utilizing the adaptive vector median filter (AVMF). Then, linear iterative vessel segmentation (LIVS) is applied for automatic segmentation of the masses followed by the extraction of texture features using the multiscale local binary pattern (MS-LBP) approach. Finally, RBPNN is employed to classify the heart mass from the images of echocardiogram with the layered kernel for the system combination. Extensive simulation results obtained using proposed AVMF-MS-LBP based RBPNN approach disclosed the superiority over existing intracardiac mass detection and classification approaches in terms of accuracy of 98.85%.

Application of Big Data Unbalanced Classification Algorithm in Credit Risk Analysis of Insurance Companies

The 2008 global financial crisis triggered by subprime mortgage crisis in the United States and the ongoing European debt crisis have urged governments and academics to pay high attention to financial industry risk supervision. The financial industry has actively implemented comprehensive risk management. As an important component of the financial industry, the insurance industry implements comprehensive risk management to control the risks of insurance companies. Propose an integrated learning model based on imbalanced dataset resampling and apply it to UCI dataset (University of California Irvine). First, resampling technology is used to preprocess the unbalanced dataset to obtain a relatively balanced training set. Then, use the classic backpropagation neural network, classic k-nearest neighbor, and classic Naive Bayes three algorithms as the base classifier and use the Bagging strategy to get the ensemble learning model. In order to verify its effectiveness, F‐measure and G‐mean methods are used to measure the performance of the classifier. The subject mainly focuses on the classification of relevance vector machine (RVM) in two types of large‐scale datasets, imbalanced and balanced, and proposes solutions for these two types of data. This explains the effectiveness of the disequilibrium classification algorithm used in the risk analysis of insurance companies.

State Diagnosis of Elevator Control Transformer over Vibration Signal Based on MEA-BP Neural Network

Vibration analysis is considered as an effective and reliable nondestructive technique for monitoring the operation conditions of elevator control transformer. In the paper, a novel model using the Empirical Mode Decomposition (EMD), the empirical wavelet packet transform, the mind evolutionary algorithm (MEA), and the backpropagation (BP) neural network is proposed for elevator control transformer fault diagnosis. Firstly, the collected signal is smoothed by EMD, the intrinsic mode function (IMF) components with large noise are determined according to the correlation coefficient, the wavelet adaptive threshold denoising algorithm is used to process the noisy IMF components, and the IMF components before and after processing and its residual component are reconstructed to obtain the denoised signal. Then, the denoised signal is transformed by empirical wavelet packet transform to extract the energy ratio and energy entropy features in the wavelet packet coefficients. Finally, a fault diagnosis model composed of MEA and BP neural network is developed, which avoids the problems of premature convergence and poor diagnosis effect. The experimental results show that the proposed model has a remarkable performance with an average root mean square error of 0.00672 and the average diagnosis accuracy of 90.8%, which is better than classic BP neural network.

Cotton stubble detection based on wavelet decomposition and texture features

BackgroundAt present, the residual film pollution in cotton fields is crucial. The commonly used recycling method is the manual-driven recycling machine, which is heavy and time-consuming. The development of a visual navigation system for the recovery of residual film is conducive, in order to improve the work efficiency. The key technology in the visual navigation system is the cotton stubble detection. A successful cotton stubble detection can ensure the stability and reliability of the visual navigation system.MethodsFirstly, it extracts the three types of texture features of GLCM, GLRLM and LBP, from the three types of images of stubbles, residual films and broken leaves between rows. It then builds three classifiers: Random Forest, Back Propagation Neural Network and Support Vector Machine in order to classify the sample images. Finally, the possibility of improving the classification accuracy using the texture features extracted from the wavelet decomposition coefficients, is discussed.ResultsThe experiment proves that the GLCM texture feature of the original image has the best performance under the Back Propagation Neural Network classifier. As for the different wavelet bases, the vertical coefficient texture feature of coif3 wavelet decomposition, combined with the texture feature of the original image, is the feature having the best classification effect. Compared with the original image texture features, the classification accuracy is increased by 3.8%, the sensitivity is increased by 4.8%, and the specificity is increased by 1.2%.ConclusionsThe algorithm can complete the task of stubble detection in different locations, different periods and abnormal driving conditions, which shows that the wavelet coefficient texture feature combined with the original image texture feature is a useful fusion feature for detecting stubble and can provide a reference for different crop stubble detection.

RETRACTED ARTICLE: Automatic recognition of tomato leaf disease using fast enhanced learning with image processing

This article has been retracted from publication in the Taylor & Francis journal, Acta Agriculturae Scandinavica, Section B — Soil & Plant Science. Following publication, concerns were raised by multiple third-parties around the content of the special issue and the decision-making process. Following an investigation by the Taylor & Francis Publishing Ethics & Integrity team in full cooperation with the Editor-in-Chief, it was confirmed that this article included in Special Issue titled “ Envisage Computer Modelling and Statistics for Agriculture”, guest edited by Gunasekaran Manogaran was not peer-reviewed appropriately, in line with the Journal's peer review standards and policy. As the stringency of the peer review process is core to the integrity of the publication process, the Editor and Publisher have decided to retract all of the articles within the above-named Special Issue. The journal has not confirmed if the authors were aware of this compromised peer review process. The journal is committed to correcting the scientific record and will fully cooperate with any institutional investigations into this matter. The authors have been informed of this decision. We have been informed in our decision-making by our policy on publishing ethics and integrity and the COPE guidelines.

Classification of Deep-SAT Images under Label Noise

ABSTRACT One of the challenges of training artificial intelligence models for classifying satellite images is the presence of label noise in the datasets that are sometimes crowd-source labeled and as a result, somewhat error prone. In our work, we have utilized three labeled satellite image datasets namely, SAT-6, SAT-4, and EuroSAT. The combined dataset consists of over 900,000 image patches that belong to a land cover class. We have applied some standard pixel-based feature extraction algorithms to extract features from the images and then trained those features with various machine learning algorithms. In our experiment, three types of artificial label noises are injected – Noise Completely at Random (NCAR), Noise at Random (NAR) and Noise Not at Random (NNAR) to the training datasets. The noisy data are used to train the algorithms, and the effect of noise on the algorithm performance are compared with noise-free test sets. From our study, the Random Forest and the Back-propagation Neural Network classifiers are found to be the least sensitive to label noises. As label noise is a common scenario in human-labeled image datasets, the current research initiative will help the development of noise robust classification methods for various relevant applications.

Research on Credit Evaluation of Financial Enterprises Based on the Genetic Backpropagation Neural Network

In this paper, an improved neural network enterprise credit rating model, which is grounded on a genetic algorithm, is suggested. With the characteristics of self-adaptiveness and self-learning, the genetic algorithm is utilized to adjust and enhance the thresholds and weights of the neural network connections. The potential problems of the backpropagation (BP) neural network with slothful speed of convergence and the possibility of falling into the local minimum point are solved to a convinced degree using the genetic algorithm in combination. The hybrid technique of the genetic BP neural network is applied to a credit rating system. Using commercial banks’ datasets, our experimental evaluations suggest that, using a combination of the BP neural network and the genetic algorithm, the proposed model has high accuracy in enterprise credit rating and has good application value. Moreover, the proposed model is approximately 15.9% more accurate than the classical BP neural network approach.

Fault diagnosis of proton exchange membrane fuel cell system of tram based on information fusion and deep learning

The reliability of fuel cell tram depends largely on the normal operation of on-board proton exchange membrane fuel cell (PEMFC) system. Therefore, timely and accurate fault diagnosis is necessary to further commercialize the fuel cell tram. And, a new fault diagnosis method BPNN-InceptionNet based on information fusion and deep learning is proposed in this paper. In this method, high-dimensional abstract features are extracted from the original measurement information by back propagation neural network (BPNN) and converted into feature maps for information fusion in feature level. Then the feature maps are transferred to a proposed Convolutional Neural Network (CNN) based on InceptionNet to realize fault classification. From the experiments, it is found that the kappa coefficient by BPNN-InceptionNet for the test set can reach 0.9884, which is better than that by BPNN, BPNN-VGG, and support vector machine (SVM) classifiers, meaning that the proposed method can achieve better diagnostic performance.

Development of R-Shiny interface for implementation of backpropagation neural network model in breast cancer classification

Artificial Neural Network or Neural Network (NN) is an information processing system that has similar characteristics to the neural network in living things. One type of NN that is often used in classification is Backpropagation Neural Network (BPNN). BPNN is an NN model that is often used for classification because it does not need to use assumptions and has high accuracy. One of the classification problems that can be solved with BPNN is the classification of breast cancer. The breast cancer data used in this study came from the UCI Machine Learning website. The problem with BPNN is that programming is difficult for users who do not understand the program, especially the R program. Therefore, to make it easier for users to analyze BPNN, an R-Shiny application or interface is created using the RStudio program. The application or R-Shiny interface that has been created has several advantages, namely the application process that is fast in displaying classification results, the use of user-friendly applications and the use of applications that are more comfortable when compared to having to write syntax such as in the R program. BPNN classification results use The R-Shiny interface has a different level of accuracy for each experiment due to the random distribution of training & testing data. The experiments conducted in this study resulted in a range of accuracy values ranging from 58.33% to 91.67% with an average accuracy of 74.17%.

Analysis of visual features and classifiers for Fruit classification problem

Analysis of visual cues for fruit classification and sorting allows to automate the visual inspection and packaging process in agricultural applications that is performed so far by human workers. Challenges for automated multi-class sorting systems are similarity in color and shape of different fruit varieties and variation among the same category of fruit. A major constraint in using well known deep neural networks for fruit classification arises because deep neural networks require large training datasets for achieving high accuracies which are generally not available in case of agricultural products especially various fruits and vegetable varieties. A thorough analysis is required to find an appropriate combination of various handcrafted features that could give precise and accurate classification results for small datasets. This paper investigates the use of various handcrafted visual features for fruit classification using traditional machine learning techniques. Different color, shape and texture features are analyzed by comparing the results obtained from six supervised machine learning techniques including K nearest neighbors, Support Vector Machines, Naïve Bayes, Linear Discriminant Analysis, Decision Trees and Feed forward back propagation neural network. We propose a novel combination of Hue, Color-SIFT, Discrete Wavelet Transform and Haralick features in fruit classification problem that outperforms other handcrafted visual features. This feature combination is found to be invariant to rotation and illumination effects and works well with intra class variations providing good results for identifying subcategories of fruits along with high classification accuracies obtained for difficult fruit categories that are visually similar. It is found that Color-SIFT features alone work very well for fruit classification problem by outperforming other individual handcrafted features. Our approach is trained and tested on publicly available Fruits 360 dataset. Out of different classifiers best results are obtained using Back Propagation Neural Network, SVM and KNN classifier with classification accuracies between 99% and 100%.

A tristimulus-formant model for automatic recognition of call types of laying hens

An essential objective of Precision Livestock Farming (PLF) is to use sensors that monitor bio-responses that contain important information on the health, well-being and productivity of farmed animals. In the literature, vocalisations of animals have been shown to contain information that can enable farmers to improve their animal husbandry practices. In this study, we focus on the vocalisation bio-responses of birds and specifically develop a sound recognition technique for continuous and automatic assessment of laying hen vocalisations. This study introduces a novel feature called the “tristimulus-formant” for the recognition of call types of laying hens (i.e., vocalisation types). Tristimulus is considered to be a timbre that is equivalent to the colour attributes of vision. Tristimulus measures the mixture of harmonics in a given sound, which grouped into 3 sections according to the relative weights of the harmonics in the signal. Experiments were designed in which calls from 11 Hy-Line brown hens were recorded in a cage-free setting (4303 vocalisations were labelled from 168 h of sound recordings). Then, sound processing techniques were used to extract the features of each call type and to classify the vocalisations using the LabVIEW® software. For feature extraction, we focused on extracting the Mel frequency cepstral coefficients (MFCCs) and tristimulus-formant (TF) features. Then, two different classifiers, the backpropagation neural network (BPNN) and Gaussian mixture model (GMM), were applied to recognise different call types. Finally, comparative trials were designed to test the different recognition models. The results show that the MFCCs-12+BPNN model (12 variables) had the highest average accuracy of 94.9 ± 1.6% but had the highest model training time (3201 ± 119 ms). At the same time, the MFCCs-3+TF+BPNN model had fewer feature dimensionalities (6 variables) and required less training time (2633 ± 54 ms) than the MFCCs-12+BPNN model and could classify well without compromising accuracy (91.4 ± 1.4%). Additionally, the BPNN classifier was better than the GMM classifier in recognising laying hens’ calls. The novel model can classify chicken sounds effectively at a low computational cost, giving it considerable potential for large data analysis and online monitoring systems.

Research on an Identification Method for Gas Disaster Risk Based on the Selective Ensemble Classification Model.

To improve the accuracy of gas disaster risk identification, a selective ensemble classification model is proposed based on clustering selection and a new degree of combination fitness (CS–NDCF). First, nine base classifiers for gas disasters are constructed on the training data set, including the backpropagation (BP) neural network classifier, naive Bayes (NB) classifier, K-nearest neighbor (KNN) classifier, logistic regression (LR) classifier, decision tree (DT) classifier, support vector machine (SVM) classifier, SVM classifier with cross-validation (SVMCV), random forest (RF) classifier, and gradient boosting DT (GBDT) classifier. Second, the K-means clustering algorithm is used to cluster the base classifiers according to their classification performance. Then, the best performing classifier in each cluster is selected to compose the first selection set. Third, the degree of combination fitness is used to filter the first selection set again to obtain the optimal base classifier result set. Finally, an ensemble classification model is constructed with the optimal base classifier result set. The experimental results on actual mine monitoring data show that compared with the BP, NB, KNN, LR, DT, SVM, SVMCV, RF, and GBDT classifiers, the accuracy of CS–NDCF increases by 7.34, 34.83, 8.28, 12.94, 5.51, 11.72, 6.47, 1.31, and 1.20%, respectively, and CS–NDCF achieves the best forecasting results. Thus, CS–NDCF is an effective method for identifying gas disasters and has a good application value.