Index Classification Research Articles

Predicting acute pancreatitis severity with enhanced computed tomography scans using convolutional neural networks

This study aimed to evaluate acute pancreatitis (AP) severity using convolutional neural network (CNN) models with enhanced computed tomography (CT) scans. Three-dimensional DenseNet CNN models were developed and trained using the enhanced CT scans labeled with two severity assessment methods: the computed tomography severity index (CTSI) and Atlanta classification. Each labeling method was used independently for model training and validation. Model performance was evaluated using confusion matrices, areas under the receiver operating characteristic curve (AUC-ROC), accuracy, precision, recall, F1 score, and respective macro-average metrics. A total of 1,798 enhanced CT scans met the inclusion criteria were included in this study. The dataset was randomly divided into a training dataset (n = 1618) and a test dataset (n = 180) with a ratio of 9:1. The DenseNet model demonstrated promising predictions for both CTSI and Atlanta classification-labeled CT scans, with accuracy greater than 0.7 and AUC-ROC greater than 0.8. Specifically, when trained with CT scans labeled using CTSI, the DenseNet model achieved good performance, with a macro-average F1 score of 0.835 and a macro-average AUC-ROC of 0.980. The findings of this study affirm the feasibility of employing CNN models to predict the severity of AP using enhanced CT scans.

Classification of inelastic deformation and material-intrinsic indices about mechanical performance of general solid matter

Classification of inelastic deformation and material-intrinsic indices about mechanical performance of general solid matter

Remote Sensing Monitoring and Assessment of Global Vegetation Status and Changes during 2016-2020.

Vegetation plays a fundamental role within terrestrial ecosystems, serving as a cornerstone of their functionality. Presently, these crucial ecosystems face a myriad of threats, including deforestation, overgrazing, wildfires, and the impact of climate change. The implementation of remote sensing for monitoring the status and dynamics of vegetation ecosystems has emerged as an indispensable tool for advancing ecological research and effective resource management. This study takes a comprehensive approach by integrating ecosystem monitoring indicators and aligning them with the objectives of SDG15. We conducted a thorough analysis by leveraging global 500 m resolution products for vegetation Leaf Area Index (LAI) and land cover classification spanning the period from 2016 to 2020. This encompassed the calculation of annual average LAI, identification of anomalies, and evaluation of change rates, thereby enabling a comprehensive assessment of the global status and transformations occurring within major vegetation ecosystems. In 2020, a discernible rise in the annual Average LAI of major vegetation ecosystems on a global scale became evident when compared to data from 2016. Notably, the ecosystems demonstrating a slight increase in area constituted the largest proportion (34.23%), while those exhibiting a significant decrease were the least prevalent (6.09%). Within various regions, such as Eastern Europe, Central Africa, and South Asia, substantial increases in both forest ecosystem area and annual Average LAI were observed. Furthermore, Eastern Europe and Central America recorded significant expansions in both grassland ecosystem area and annual average LAI. Similarly, regions experiencing notable growth in both cropland ecosystem areas and annual average LAI encompassed Southern Africa, Northern Europe, and Eastern Africa.

Diagnostic Study of Mandibular Cortical Index Classification Using Dental Cone-Beam Computed Tomography Findings: A Preliminary Cross-Sectional Study

The prevalence of osteoporosis is high, reportedly affecting 200 million people worldwide. A major problem associated with osteoporosis is that femoral fractures cause a decline in general function and loss of independence, greatly reducing patients’ quality of life. Notably, osteoporosis is an asymptomatic chronic metabolic disease, and its detection is thus often delayed. Interestingly, mandibular cortical index (MCI) classification using dental panoramic radiography is reportedly useful for early detection of osteoporosis. However, this visual classification method can lead to differences in diagnoses among surgeons. The aim of this preliminary study was to analyze cone-beam computed tomography (CBCT) data and examine an objective MCI classification using the findings obtained. MCI classification (classified as C1, C2, or C3) was performed by three examiners on 70 women (91 sites) aged ≥20 years. The mandibular cortical width of all sites was measured using CBCT images. The results showed that the mandibular cortical width was not particularly correlated with age or number of present teeth, and no significant quantitative differences were found between C1 and C2. However, coronal CBCT images of C2 revealed multiple characteristic trabecular bone structures. These structures may be an important finding affecting the classification of two-dimensional dental panoramic radiography images.

Research on seismic resilience evaluation index of mid-rise CFS structures

This paper focuses on the deficiencies of Chinese standard GB/T 38591–2020, and combines the mechanical characteristics, post-earthquake damage characteristics, and repair methods of mid-rise cold-formed steel (CFS) structures to define the damage grade of structural components and revise various index parameters in the “Standard”. Based on the calculation results of 120 sets of 6-story CFS composite shear wall structures, the multi-parameter seismic resilience evaluation index and grading criteria applicable to mid-rise CFS structures are fitted, and the index values (R values) for dividing the 5 resilience grades are 0.5, 1.0, 1.25, and 1.7, respectively. By considering different building usage functions and seismic effects, the 5-story CFS structure shaking table test models and the irregular eccentric CFS structure numerical model are used to jointly verify the reasonableness and universality of the seismic resilience evaluation index and grade classification criteria. The multi-parameter resilience evaluation index system lays the foundation for the study of seismic resilience of mid-rise CFS buildings and provides new ideas for establishing quantitative resilience evaluation indexes for different building systems.

Application of Machine Learning Coupled with Stochastic Numerical Analyses for Sizing Hybrid Surge Vessels on Low-Head Pumping Mains

In surge protection, low-head profiles are deemed a challenge in pump failure events since they are prone to severe negative pressure surges that require an uneconomical surge vessel volume. A hybrid surge vessel with a dipping tube can provide required protection with reasonable economic volume. This work presents novel analyses for the hybrid surge vessel and develops a simple model for its optimum sizing using a stochastic numerical approach coupled with machine learning. Practical ranges for correct sizing of vessel components, such as ventilation tube, inlet/outlet air valves, and compression chamber, are presented for optimal protection and performance. The water hammer equations are iteratively solved using the hybrid surge vessel’s revised boundary conditions within the method of characteristics numerical framework to generate 2000 cases representing real pump failures on low-head pipelines. Genetic programming is utilized to develop simple relations for prediction of the hybrid vessel initial and expanded air volumes in addition to the compression chamber volume. Moreover, the developed model presented a classification index for low-head pipelines on which the hybrid vessel would be most economical. The developed model yielded good prediction error statistics. The developed model proves to be more accurate and easier to use than the classical design charts for the low-head pumping mains. The model clearly showed the relation between various hydraulic and pipe parameters, with pipe diameter and static head as the most influencing parameters on compression chamber volume and expanded air volume. The developed model, together with the classification indices, can be used for preliminary surge protection sizing for low-head pipelines.

Federal Enforcement of Pharmaceutical Fraud under the False Claims Act, 2006–2022

Context: The False Claims Act is the US federal government's primary tool for identifying and penalizing pharmaceutical fraud. The Department of Justice uses the False Claims Act to bring civil cases against drug manufacturers that allegedly obtain improper payment from federal programs. Methods: The authors searched the Department of Justice website for press releases published between 2006 and 2022 that announced fraud actions brought against drug companies. They then used the World Health Organization's Anatomical Therapeutic Classification index to identify the classes of prescription drugs implicated in fraud actions. Findings: During fiscal years 2006–2022, payments by six manufacturers amounted to more than 28% of total payments made as a result of federal False Claims Act actions. Nervous system and cardiovascular drugs were the classes of medications most commonly implicated in alleged fraud. Federal officials most frequently alleged that companies improperly promoted nervous system drugs and paid kickbacks to increase revenues from cardiovascular, antineoplastic and immunomodulating, and alimentary tract and metabolism drugs. Conclusions: Despite frequent pharmaceutical fraud settlements and penalties, incidence of alleged fraud among drug companies remains high. Alternative methods for preventing and deterring fraud could help safeguard our health systems and promote public health, and policy makers should ensure that effective fraud enforcement complements preventive public health regulation.

Risk Factors for a High Comprehensive Complication Index after Splenectomy Plus Pericardial Devascularization for Portal Hypertension.

Mathematical integration of all complications from the Clavien-Dindo classification into one number called the comprehensive complication index provides a novel method to capture morbidity. This objective of this study was to compare the evaluations of complications between the novel comprehensive complication index and Clavien-Dindo classification for portal hypertension patients who underwent splenectomy plus pericardial devascularization. Patients treated with either splenectomy plus simplified pericardial devascularization or splenectomy plus traditional pericardial devascularization were included retrospectively. Correlation and logistic regression analyses of the postoperative hospital stay and total hospitalization expense were compared between the comprehensive complication index and Clavien-Dindo classification. The cumulative sum-comprehensive complication index was generated and compared between operation types. The Child-Pugh classification at admission, spleen thickness, and intraoperative blood loss were risk factors for high comprehensive complication index. Comprehensive complication index showed a stronger relationship with the postoperative hospital stay and total hospitalization expense than the Clavien-Dindo classification. Logistic regression analysis of the postoperative hospital stay demonstrated that the R2 values for the comprehensive complication index and Clavien-Dindo classification were 0.15 and 0.14, respectively. The cumulative sum-comprehensive complication index graph showed a steady dynamic decrease in the cumulative sum score for the individual operation type, with splenectomy plus simplified pericardial devascularization revealing a more notable decrease than splenectomy plus traditional pericardial devascularization. Comprehensive complication index is an excellent method to assess postoperative morbidity in portal hypertension patients. The cumulative sum-comprehensive complication index chart can better dynamically monitor and compare different operation types. Splenectomy plus simplified pericardial devascularization is better than splenectomy plus traditional pericardial devascularization at decreasing cumulative sum-comprehensive complication index.

A Neighborhood Covering Classifier Based on Optimal Granularity of Fuzzy Quotient Space

As one of rapidly developing methodology for dealing with complex problems in line with human cognition, granular computing has made significant achievements in knowledge discovery. Neighborhood classifier, as a typical description of granular computing (GrC), is an effective method for classification of continuous data. However, in the phase of constructing neighborhood rules, the existing neighborhood classifiers are divided into the following two modes and both have defects: (1) The strategy driven by center: There are a lot of overlap and inclusion among neighborhood rules, that is, it need to spend much time to reduce redundancy rules; (2) The strategy driven by rule: There are many rules containing only one object, which cannot form an effective covering, and would affect knowledge acquisition in the incremental environment. Therefore, in this paper, fuzzy quotient space theory is introduced to construct neighborhood rules. Based on optimal granularity of fuzzy quotient space, a neighborhood covering classifier, which has no redundant rules and could form the effective covering, is proposed without any artificial parameter. Second, comprehensively considering the knowledge purity and complexity, the quality measure of granularity is proposed, which guides the optimal granularity selection of HQSS. Third, neighborhood rules are constructed in the optimal granularity. Then, the offset of center is introduced to describe the membership degree of the test object to different neighborhood rules, and the neighborhood allocation strategy is proposed accordingly. Next, an algorithm for the neighborhood covering classifier based on these theories is proposed. Finally, experiments on 13 UCI datasets and 3 real datasets are carried out to verify the performance of the proposed classifier from four common classification indexes.

Classification of Nasal Index in Koreans According to Sex

Classification of Nasal Index in Koreans According to Sex

Deep learning based processing framework for spatio-temporal analysis and classification of laser biospeckle data

Laser biospeckle is an advanced optical technique with the ability to non-destructively visualize various transient phenomenon via spatial and temporal statistics. However, accuracy of the existing image processing techniques used to process biospeckle data is hampered by various experimental and processing dependent factors. Therefore, in this work, a novel 3D convolution neural network (3D CNN) based deep learning (DL) architecture is developed for spatio-temporal analysis of biospeckle data in both qualitative and quantitative domains that effectively reduces errors introduced due to the influence of varying experimental parameters. Firstly, 3D CNN based image processing model is proposed for spatio-temporal analysis and classification of biospeckle data. Furthermore, a novel DL based numerical indexing strategy is developed for identification of level of activity in a sample. Finally, impact of varying experimental parameters on accuracy of the proposed technique is analyzed. In this direction, multiple experiments were performed to examine the effect of variation in input data parameters such as frame dimension, frame rate, number of frames, and background noise on accuracy of the trained model. Performance of the proposed model was analyzed and compared with respect to synthetic data generated by using rotating diffuser based simulation model. Robustness of the proposed strategy was also validated experimentally on practical data associated with identification of disease in seeds. Obtained results demonstrated that the proposed technique is accurate and can perform spatio-temporal classification and numerical indexing of the biospeckle data under varying experimental parameters.

Investigation of the relationship between nutritional knowledge and nutritional supplement belief levels and athletic performances of elite cross-country skiers

The use of nutritional supplements provides support to the athlete, while the use of wrong and inappropriate supplements may adversely affect the performance of the athlete. This study investigated the relationship between the nutritional knowledge and nutritional supplement belief levels and athletic performances of elite cross-country skiers. A total of 19 elite cross-country skiers, 8 females and 11 males (mean age of 16.1±1.00 years) competing in the U-16 and U-18 categories, participated in the study. Inbody 120, 10 m, 20 m and 30 m sprint, agility, 20m shuttle run and hand grip tests were used to assess physical and psychological factors. Moreover, the Nutrition for Sports Knowledge Questionnaire (NSKQ) and the Sports Supplements Belief Scale (SSBS) were applied to the athletes. No significance was found in the comparison of the athletes in terms of Body Mass Index (BMI) classification (p>0.05). A positive relationship was found between the NSKQ and age (r=0.466; p=0.044), body fat percentage (r=0.505; p=0.027), and body fat mass (r=0.642; p=0.003) values. On the other hand, a positive relationship was found between the SSBS scale and body weight (r=0.136; p=0.009), body muscle mass (r=0.681; p=0.001), total body water (r=0.647; p=0.003), hand grip strength (right hand r=0.621; p=0.005; left hand r=0.635; p=0.003), while a negative relationship was found between the SSBS scale and 10m sprint (r=-0.589; p=0.008), 20m sprint (r=-0.606; p=0.006), 30m sprint (r=-0.480; p=0.037) and agility values (r=-0.533; p=0.019). These findings demonstrate that the sports nutrition knowledge level does not have a positive effect on athletic performance, but it has a positive effect on body muscle mass, strength, sprint, and agility values that affect athletes’ athletic performances as athletes’ nutritional supplements belief levels increase.

Water quality prediction using machine learning models based on grid search method

Water quality is very dominant for humans, animals, plants, industries, and the environment. In the last decades, the quality of water has been impacted by contamination and pollution. In this paper, the challenge is to anticipate Water Quality Index (WQI) and Water Quality Classification (WQC), such that WQI is a vital indicator for water validity. In this study, parameters optimization and tuning are utilized to improve the accuracy of several machine learning models, where the machine learning techniques are utilized for the process of predicting WQI and WQC. Grid search is a vital method used for optimizing and tuning the parameters for four classification models and also, for optimizing and tuning the parameters for four regression models. Random forest (RF) model, Extreme Gradient Boosting (Xgboost) model, Gradient Boosting (GB) model, and Adaptive Boosting (AdaBoost) model are used as classification models for predicting WQC. K-nearest neighbor (KNN) regressor model, decision tree (DT) regressor model, support vector regressor (SVR) model, and multi-layer perceptron (MLP) regressor model are used as regression models for predicting WQI. In addition, preprocessing step including, data imputation (mean imputation) and data normalization were performed to fit the data and make it convenient for any further processing. The dataset used in this study includes 7 features and 1991 instances. To examine the efficacy of the classification approaches, five assessment metrics were computed: accuracy, recall, precision, Matthews's Correlation Coefficient (MCC), and F1 score. To assess the effectiveness of the regression models, four assessment metrics were computed: Mean Absolute Error (MAE), Median Absolute Error (MedAE), Mean Square Error (MSE), and coefficient of determination (R2). In terms of classification, the testing findings showed that the GB model produced the best results, with an accuracy of 99.50% when predicting WQC values. According to the experimental results, the MLP regressor model outperformed other models in regression and achieved an R2 value of 99.8% while predicting WQI values.

Accounting for the annual variability when assessing non-point source pollution potential in Mediterranean regulated watersheds

The characterization of non-point source pollution at the watershed scale difficult owing to its distributed nature combined with the lack of suitable measurements for validation. This study proposes the classification of land within a Mediterranean watershed according to its potential source of non-point pollution, considering interannual precipitation variability and dam regulation effects. For this purpose, the potential non-point pollution index (PNPI) developed by the Italian Environmental Protection Agency was modified to include annual local precipitation behavior, named local annual PNPI (APNPI). PNPI and APNPI were computed for the Guadalquivir River (Spain), which has a drainage surface of 57,500 km2 and is highly regulated by >60 reservoirs. The results reflect the vulnerability along the Guadalquivir River in terms of the spatially variable non-point pollutant nature of its contributing watersheds. The annual average nitrate concentration values on the southern side exceeded the average value on the northern side by almost five times and showed a statistically significant power fit with the PNPI, with an R2 of 0.65. Long-term available nitrate data (1981/82–2006/07) on a monthly scale at the outlets of some watersheds allowed us to rank priority pollutant source areas within the watershed. The power fits between the annual average nitrate loads and the APNPI (R2 = 0.51–0.99) were statistically significant, which validated the utility of adding the variability of precipitation at an annual scale as a dynamic factor in the index. The APNPI can constitute a simple dynamic classification index for assessing the relative risk of non-point source pollution across a large area, especially in data-scarce situations.

Implementasi Metode Simple Multi Attribute Rating Technique (SMART) dalam Pemilihan Zona Prioritas dan Alternatif Berbasis Data Klasifikasi Indeks Vegetasi

Vegetation index analysis using the Normalized Difference Vegetation Index (NDVI) model needs to be processed using a decision support model to follow up on the Landsat 8/9 Operational Land Imaginer (OLI) satellite image data interpretation results. However, studies using the Simple Multi-Attribute Rating Technique (SMART) method to determine priority zones based on vegetation index classification data are still limited. This study uses the SMART decision support model to process NDVI classification data in mangrove areas. The stages in this study consist of four parts: the data collection stage, the data processing stage; the data analysis stage; and the data interpretation stage. At the data collection stage, the raster data used was sourced from the United States Geology Survey (USGS) platform, namely Landsat 8/9 OLI with coordinate raster data (Lat 01o43'18" N, Lon: 128o04'15" E) in 2013, 2018, and 2023. In addition, video and aerial photographs at the study site were taken using drones (Phantom 4 Version 2). At the data processing stage, the model used in calculating raster data is NDVI using the QGIS 3.30.1 application. This research data analysis and interpretation stage uses the SMART decision support model. The SMART decision support model is used to produce recommendations for priority zones for mangrove ecotourism development based on the results of the NDVI classification (minimum value, average value, maximum value) adjusted to the Decree of the State Minister of Environment Number 201 of 2004 concerning standard criteria and guidelines for mangrove forest destruction (rare, medium, and dense). Based on the calculation of the utility value of criterion C1 as a cost with a weight of 0.50 in the NDVI classification data for 2023, the second observation station is recommended as a priority zone with a total value of 0.50. Meanwhile, the calculation of the utility value of criterion C3 as a cost with a weight of 0.50 in the NDVI classification data in 2023 recommended the third observation station as a priority zone with a total value of 0.88. This means that the SMART method can be used to identify and analyze priority and alternative zones for the sustainable development of mangrove ecotourism areas.

Interpretable artificial intelligence for classification of alveolar bone defect in patients with cleft lip and palate

Cleft lip and/or palate (CLP) is the most common congenital craniofacial anomaly and requires bone grafting of the alveolar cleft. This study aimed to develop a novel classification algorithm to assess the severity of alveolar bone defects in patients with CLP using three-dimensional (3D) surface models and to demonstrate through an interpretable artificial intelligence (AI)-based algorithm the decisions provided by the classifier. Cone-beam computed tomography scans of 194 patients with CLP were used to train and test the performance of an automatic classification of the severity of alveolar bone defect. The shape, height, and width of the alveolar bone defect were assessed in automatically segmented maxillary 3D surface models to determine the ground truth classification index of its severity. The novel classifier algorithm renders the 3D surface models from different viewpoints and captures 2D image snapshots fed into a 2D Convolutional Neural Network. An interpretable AI algorithm was developed that uses features from each view and aggregated via Attention Layers to explain the classification. The precision, recall and F-1 score were 0.823, 0.816, and 0.817, respectively, with agreement ranging from 97.4 to 100% on the severity index within 1 group difference. The new classifier and interpretable AI algorithm presented satisfactory accuracy to classify the severity of alveolar bone defect morphology using 3D surface models of patients with CLP and graphically displaying the features that were considered during the deep learning model's classification decision.

Tongue texture may contribute to the assessment of malignant risk of thyroid nodules.

In the present study, it was aimed to evaluate whether there is an objective tongue image indicator that could be used to evaluate malignant risk of thyroid nodules through a cross sectional study. From December 2018 to December 2020, the TFDA-1 digital tongue-face diagnostic instrument was used to collect the tongue images. TDAS 2.0 software was used for tongue image analysis. A standardized database was constructed by combining patient physical examination results and tongue image analysis results. The relationship between tongue image index and TI-RADS classification of thyroid nodules was tested. A total of 5,900 cases were collected and 4,615 cases were included in the present study after excluding 154 cases due to incomplete information, 1,221 cases with thyroid nodules were separated into 417 cases TI-RADS 2 group, 693 cases in TI-RADS 3 group and 111 cases in TI-RADS 4 group. Without considering confounding factors, tongue image indexes zhiCon, zhiASM, zhiENT, zhiMEAN, zhiClrB, zhiClrR, zhiClrG, zhiClrI, zhiClrL and zhiClrY were significantly different among the three groups (P<0.05). Excluding the influence of age, sex, body mass index, smoking and drinking, the results of one-way variance linear trend analysis showed that the values of zhiCon, zhiENT and zhiMEAN increased with the increasing TI-RADS category, while the values of zhiASM decreased with the increase of TI-RADS category. Tongue texture index may be helpful for differentiating the benign and malignant of thyroid nodules.

Assessment of the nutritional status of school children in Galle Municipality area: A comparison between different body mass index classification systems

Introduction: Asian populations are at an increased risk of cardiometabolic disorders due to higher fat mass at a relatively lower body mass index (BMI). Several discrepancies have been reported in the BMI classification systems currently in practice to assess the nutritional status among children. Aim of this study was to compare the different international BMI based classification systems to identify the nutritional status in a cohort of Sri Lankan children.Methods: A cross sectional study was conducted on 833 (48.37% boys) school children aged 5-15 years in Galle Municipality area, Sri Lanka. The nutritional status of each child was defined according to five BMI classification systems: World Health Organization (WHO), Centers for Disease Control and Prevention(CDC), and International Obesity Task Force (IOTF), Indian and Sri Lankan systems. The agreement between them was tested using Cohen’s kappa coefficient.Results: Prevalence of under-weight, overweight and obesity of children, as determined by the WHO, CDC, IOTF, Indian and the Sri Lankan classification systems showed significant differences. The WHO classification system had the best agreement (k=0.649) with the Indian classification system. A wide difference between the Sri Lankan classification system (24.37%) and the Indian (9.60%) and WHO (5.04%) classification systems in defining obesity were observed.Conclusion &amp; recommendations: A wide difference between different BMI classification systems when determining the nutritional status in children emphasise the importance of developing a country-specific classification system to identify the nutritional status among Sri Lankan children.

Evaluation Method for Rock Burst Hazards in Strip Filling of Working Faces in Deep Coal Mines

The impact risk evaluation for the strip filling of working faces has always been a research hotspot and a difficulty in the field of rock bursts. In this paper, the concept of the critical filling rate is first proposed, and the criterion for identifying the impact risk of the strip filling of a working face is established. Then, the membership function of coal body stress and the coal seam elastic energy index to impact risk was established, and the classification index of the impact risk grade was formed. On this basis, the overall and local evaluation method of the rock burst hazard for the strip filling of working faces was proposed. Finally, the C8301 working face of the Yunhe coal mine was taken as the engineering background, and the impact risk evaluation was carried out. It was found that the overall risk of the C8301 working face was determined as a strong impact risk, and there were six local risk areas, which included two weak impact risk areas, two medium impact risk areas, and two strong impact risk areas. This study can provide guidance and a reference for the impact risk evaluation of strip-filling mining under the same or similar conditions.

Evolution characteristics of ethyl ether spray explosion process in 20L near-spherical vessel

As a biofuel with a wide range of uses, ethyl ether leakage may cause serious spray explosion accidents during storage and transportation, however, the evolution characteristics and process mechanism of ethyl ether spray explosion have not been thoroughly studied. Therefore, the effects of material temperature and ambient temperature on ethyl ether spray explosion at different concentrations are studied by means of spray explosion experiment system. In this paper, the development of ethyl ether spray explosion with a mass concentration range of 107.1–392.7 g/m3 was studied at different ambient temperature and material temperature. Where the ambient temperature range is 298.15–323.15 K, and the material temperature range is 298.15–323.15 K. Moreover, in this paper, the risk of spray explosion is more clearly understood through the classification of deflagration index, and the explosion characteristics of spray explosion are analyzed comprehensively according to the boiling point as the dividing line. The maximum explosion pressure and its arrival time, the rate of rise of the maximum explosion pressure and its arrival time are used as the basis to evaluate the effect of the explosion process of ethyl ether spray. The results show that when the ambient temperature is lower than the boiling point temperature of ethyl ether, the increase of ambient temperature has little effect on the explosion characteristics of ethyl ether spray. When the ambient temperature is higher than 308.15 K, the maximum explosion pressure and maximum rate of pressure rise of ethyl ether spray explosion increase. At medium and low concentrations(107.1 g/m3, 178.5–249.9 g/m3), the increase of ambient temperature is conducive to the rapid development of spray explosion, and the arrival time of maximum explosion pressure and pressure rise rate both show a decreasing trend. However, under the influence of incomplete combustion at high concentration, the explosion development rate is reduced. At lower material temperature, the maximum explosion pressure and the maximum rate of pressure rise increase with the increase of material temperature. When the material temperature is higher than 303.15 K, the ethyl ether droplet temperature is higher than the ambient temperature, and the heat loss of the droplet has a certain inhibition effect on spray explosion. Especially when the material temperature is high, the inhibition effect is more significant, so when the material temperature rises to 323.15 K, the maximum rate of pressure rise decreases. The effect of ambient temperature on the explosion grade is more obvious than that of the material temperature, and the effect on the explosion characteristics of ethyl ether spray is also greater.