空气质量问题一直是交通系统、工业生产、民用建筑等各个工程领域的科学家和工程师们关注的焦点。空气质量监测是大气污染控制和预警的基础。《Data Science in Air Quality Monitoring（空气质量监测与数据科学）》从数据科学的角度介绍了各种工程环境中空气质量监测的一系列最新方法。通过大量的实验模拟，详细阐述了空气质量监测的预处理、分解、识别、聚类、预测和插值等数据驱动的关键技术。《Data Science in Air Quality Monitoring（空气质量监测与数据科学）》可为工程空气质量监测数据科学技术的发展提供重要参考。《Data Science in Air Quality Monitoring（空气质量监测与数据科学）》可供环境、大气、城市气候、民用建筑、交通和车辆等领域的学生、工程师、科学家和管理人员使用。
目錄：
Contents1 Introduction 11.1 Overview of Data Science in Air Quality Monitoring 21.1.1 Importance of Air Quality Monitoring 21.1.2 The Role of Data Science in Environmental Monitoring 61.1.3 Characteristics and Challenges of Air Quality Data 101.1.4 Current Application of Data Science and Technology in Air Quality Monitoring 131.2 Key Problems Data Science in Air Quality Monitoring 161.2.1 Data Processing 161.2.2 Data Decomposition 211.2.3 Data Identification 251.2.4 Data Clustering 271.2.5 Data Forecasting 331.2.6 Data Interpolation 361.3 Scope of the Book 42References 442 Data Preprocessing in Air Quality Monitoring 492.1 Introduction 492.2 Data Acquisition 512.3 Characteristic Analysis of Air Quality Data 522.3.1 Temporal Characteristics 522.3.2 Spatial Characteristics 552.4 Missing Data Imputation of Air Quality Data 562.4.1 Missing Data Imputation Performance Evaluation 582.4.2 Univariate Missing Data Imputation Based on K-Nearest Neighbors 602.4.3 Multivariate Missing Data ImputationBased on Self-Organizing Map 612.5 Outlier Detection of Air Quality Data 652.5.1 Outlier Detection Performance Evaluation 662.5.2 Outlier Detection Based on Unsupervised Isolation Forest 672.5.3 Outlier Detection Based on Hampel Filter 702.5.4 Outlier Detection Based on Deep Learning Forecasting 752.6 Preprocessing Performance Comparison 782.6.1 Performance Comparison of Missing Data Imputation 782.6.2 Performance Comparison of Outlier Detection 812.7 Conclusions 82References 833 Data Decomposition in Air Quality Monitoring 853.1 Introduction 853.1.1 Application of Wavelet Decomposition in Air Quality Data Analysis 863.1.2 Application of Modal Decomposition in Air Quality Data Analysis 863.1.3 Deficiencies and Challenges of Existing Research 873.1.4 Temporal Resolution 873.1.5 Frequency Resolution 873.1.6 Boundary Effect 883.1.7 Noise Reduction Effect 883.2 Wavelet Decomposition of Air Quality Data 903.2.1 Time-Frequency Localization Characteristics 903.2.2 Multi-resolution Analysis 903.2.3 Strong Sparse Representation Capability 913.2.4 Discrete Wavelet Transform 923.3 Top Layer: Approximation Coefficients 973.4 Detail Coefficients 973.4.1 Reconstruction Error 983.4.2 Signal-to-Noise Ratio (SNR) 983.4.3 Correlation Coefficient 993.4.4 Various Wavelet Basis Functions 1003.4.5 Continuous Wavelet Transform 1043.5 Mode Decomposition of Air Quality Data 1063.5.1 Empirical Mode Decomposition 1063.5.2 Variations and Improvements of the Traditional EMD Method 1103.6 Decomposition Performance Comparison 1133.6.1 Decomposition Accuracy 1133.6.2 Computational Complexity 1143.6.3 Boundary Effect 1153.7 Conclusions 116References 1164 Data Identification in Air Quality Monitoring 1194.1 Introduction 1194.1.1 The Importance of Data Identification in Air Quality Monitoring 1204.1.2 Methods for Data Identification in AirQuality Monitoring 1214.2 Data Acquisition 1224.3 Feature Selection of Air Quality Data 1234.3.1 Feature Selection Performance Evaluation 1234.3.2 Filter Methods 1254.3.3 Wrapper Methods 1264.4 Forward Selection 1284.5 Backward Elimination 1284.6 Recursive Feature Elimination (RFE) 1294.6.1 Modeling Step 1294.6.2 Embedded Methods 1314.7 Feature Extraction of Air Quality Data 1314.7.1 Feature Extraction Performance Evaluation 1314.7.2 Statistical Feature Extraction 1324.7.3 Time-Frequency Analysis 1344.8 Identification Performance Comparison 1374.8.1 Performance Comparison of Feature Selection 1374.8.2 Performance Comparison of Feature Extraction 1404.9 Conclusions 143References 1445 Data Preprocessing in Air Quality Monitoring 1475.1 Introduction 1475.2 Data Acquisition 1485.3 Temporal Clustering of Air Quality Data 1515.3.1 Definition and Role of Temporal Clustering 1515.3.2 DBSCAN Temporal Clustering 1525.3.3 AE-DBSCAN Temporal Clustering 1545.3.4 CAE-DBSCAN Temporal Clustering 1575.4 Spatial Clustering of Air Quality Data 1595.4.1 K-Means Clustering 1595.4.2 GMM 1605.4.3 GAE -Kmeans 1625.4.4 Modeling Step 1645.5 Clustering Performance Comparison 1655.5.1 Evaluation with Silhouette Score 1655.5.2 Evaluation with Base Model 1665.5.3 Comparison of Spatial Clustering 1685.6 Conclusions 171References 1716 Data Forecasting in Air Quality Monitoring 1736.1 Introduction 1736.2 Data Acquisition 1766.3 Deterministic Forecasting of Air Quality Data 1786.3.1 Extreme Learning Machine 1786.3.2 Gated Recurrent Unit 1806.3.3 Bidirectional Long Short-term Memory 1826.3.4 Deep Extreme Learning Machine 1846.3.5 Transformer 1856.4 Probabilistic Forecasting of Air Quality Da
購物車/收銀台(0) | 在線留言板
| 付款方式
| 運費計算
| 聯絡我們
| 幫助中心 |
加入書簽
HOME
新書上架
