Data Mining in the Big Data Era

Name: Data Mining in the Big Data Era
ISBN: 9787115492395

李涛Posts & Telecom Press · ChinaApr 2019

3.9

Word count: 295K words
Chapters: 284
ISBN: 9787115492395

Report an error Find this book

Summary

This book is organized around currently hot data mining applications. Through detailed case studies of big data mining technology in areas such as system logs, work orders, sustainability research, recommender systems, intelligent question-answering systems, social media, bioinformatics and healthcare, and privacy protection, it explains how to better apply and learn data mining techniques. Incorporating cutting-edge techniques and typical applications in data mining, the book is suited not only to academics and industry professionals who care about and follow data mining but also as a practical textbook and reference for university courses on data mining and machine learning. It helps readers better understand the roots and essence of data mining technology.

Editor's review

Data Mining in the Big Data Era, by renowned scholar Professor Li Tao, is published by Posts & Telecom Press. As a technical monograph, it systematically sets out the core concepts, algorithm principles, and practical applications of data mining in the context of big data. The book holds a steady rating of around 7.5 on Douban and has received favorable reviews within the field, and is listed as a reference by related departments at many universities.

The book's core value lies in its clear hierarchical structure. The author begins with the basic tasks of data mining (such as classification, clustering, and association analysis) and gradually moves into challenges and solutions specific to big data—for example, discussing the adaptation and optimization of classic algorithms under distributed computing frameworks such as Hadoop and Spark. It is not a simple reference manual but focuses on explaining "why" and "how to think," helping readers build a solid theoretical foundation so they can respond flexibly to complex, ever-changing data problems in practice.

Professor Li Tao's deep accumulation in the field gives the book both authority and forward vision. It covers not only traditional machine learning algorithms such as decision trees, neural networks, and support vector machines but also touches on frontier directions such as stream data mining and social network analysis. This arrangement—from fundamentals to frontiers and from theory to practice—means that both learners seeking to consolidate the basics and researchers seeking technical breakthroughs can draw inspiration from it.

Overall, this is a rigorous and systematic professional work. Its reading value lies in providing a complete and clear knowledge map that helps readers see past the hype of "big data" and deeply understand the technical essence and implementation paths of data mining, this core engine. For readers who wish to go deep in data science, it is a foundational text worth careful study.

Who it's for

A good fit for

Undergraduates and graduate students in computer science, statistics, data science, and related fields, as supplementary reading for core courses
Engineers or analysts who already have some programming and mathematics background and wish to systematically study data mining theory and big data technologies
Practitioners in data analysis and machine learning who want to deepen their understanding of how algorithm principles combine with big data platforms
Technology enthusiasts with a strong interest in big data who are not satisfied with surface-level applications and are eager to explore underlying algorithmic logic

Not a good fit for

Complete beginners with no programming or advanced mathematics background who expect to quickly master specific tools through this book
Readers seeking only quick, step-by-step business data analysis cases and not interested in deeper algorithm principles

Reading tips

Read alongside foundational mathematics books such as linear algebra and probability theory to better understand the algorithm derivations
Practice with mainstream big data platforms (such as Spark's MLlib library), turning the book's theoretical algorithms into runnable code
For more difficult chapters (such as advanced optimization algorithms and stream mining), grasp the core ideas first, then read the detailed derivations repeatedly

About the publisher

Posts & Telecom Press China · Founded in 1953

Posts & Telecom Press is known for its strengths in science and technology, computing, and information and communications titles, and has extended its publishing into photography, art, software learning, and inspirational growth, giving it a fairly diverse range. Its catalog includes computing and communications works such as Refactoring and Patterns (Revised Edition) and Huawei Switch Learning Guide (Second Edition), alongside bilingual collector's editions such as The Little Prince (Chinese-English-French illustrated collector's edition), The Great Gatsby, and Three Days to See. Beijing Ten Years: 1980-1990 and Ghost Blade: WLOP Personal Illustration Collection reflect its presence in photography and art. Its authors include Antoine de Saint-Exupéry, Helen Keller, Joshua Kerievsky, Wang Da, Zhang Zhaozeng, and WLOP.

版权信息
内容提要
《国之重器出版工程》编辑委员会
《学术中国·大数据》丛书编辑委员会
丛书总序
前言
第1章数据挖掘简介
1.1 大数据时代的数据挖掘
1.1.1 大数据的特点“4V+4V”
1.1.2 数据挖掘
1.1.3 从数据挖掘应用的角度看大数据
1.2 数据挖掘技术的发展历史
1.3 十大数据挖掘算法简介
1.4 数据挖掘平台：FIU-Miner
1.4.1 FIU-Miner平台简介
1.4.2 FIU-Miner系统架构
1.4.3 FIU-Miner应用实例
参考文献
第2章系统日志和事件的挖掘
2.1 数据驱动的网络运维
2.1.1 网络运维1.0阶段：简单数据处理
2.1.2 网络运维2.0阶段：分布式大数据处理框架
2.1.3 网络运维3.0阶段：网络运维平台套件
2.1.4 网络运维4.0阶段：智能化网络运维
2.2 系统日志分析的目的
2.2.1 系统问题诊断
2.2.2 调试与优化
2.2.3 系统安全维护
2.3 日志数据分析管理系统的架构
2.3.1 日志数据的收集和预处理
2.3.2 历史日志数据存储
2.3.3 日志事件数据的分析以及对分析结果的展示和使用
2.4 系统日志的数据形式
2.4.1 无结构的日志数据
2.4.2 结构化与半结构化的日志数据
2.4.3 非结构化数据的转换
2.5 基于日志数据的异常检测
2.5.1 基于监督学习的异常检测
2.5.2 基于无监督学习的异常检测
2.6 系统故障根源跟踪
2.6.1 日志事件的依赖性挖掘
2.6.2 基于依赖关系的系统故障追踪
2.7 日志事件总结
2.7.1 事件总结算法基本要求及相关工作
2.7.2 基于事件发生频率变迁描述的事件总结
2.7.3 基于马尔可夫模型描述的事件总结
2.7.4 基于事件关系网络描述的事件总结
参考文献
第3章工作票数据挖掘
3.1 工作票简介
3.2 工作票产生机制和亟待解决的问题
3.3 研究现状
3.3.1 工作票分类
3.3.2 工作票推荐
3.3.3 整体解决方案和工具
3.4 工作票漏报和误报检测
3.4.1 漏报和误报
3.4.2 基于规则的误报识别方法
3.4.3 半监督的工作票漏报发现方法
3.4.4 评价
3.5 层次多标签工作票分类
3.5.1 问题描述
3.5.2 层次损失函数和期望损失最小化
3.5.3 算法和解决方案
3.5.4 实验
3.6 工作票解决方案推荐
3.6.1 背景
3.6.2 基于KNN的推荐方法
3.6.3 划分方法
3.6.4 概率融合方法
3.6.5 度量学习方法
3.6.6 实验
参考文献
第4章大数据与计算可持续性研究
4.1 大数据与可持续发展
4.1.1 可持续发展
4.1.2 大数据时代可持续发展面临的机遇和挑战
4.2 计算可持续性
4.2.1 计算可持续性数据及其特征
4.2.2 大数据环境下计算可持续性研究现状
4.3 研究案例
4.3.1 基于数据驱动的气象分析
4.3.2 基于数据驱动的建筑能耗分析
参考文献
第5章推荐系统
5.1个性化推荐系统概述
5.2 推荐技术
5.2.1 基于内容的推荐系统
5.2.2 基于协同过滤的推荐系统
5.2.3 基于知识的推荐系统
5.2.4 基于混合技术的推荐系统
5.2.5 基于计算智能的推荐系统
5.2.6 基于社交网络的推荐系统
5.2.7 基于上下文敏感的推荐系统
5.2.8 基于组群的推荐系统
5.3 推荐系统评测
5.3.1 推荐系统评测环境
5.3.2 推荐系统评测指标
5.4 推荐系统实例
5.4.1 新闻推荐
5.4.2 POI推荐
参考文献
第6章智能问答系统
6.1 发展历史
6.2 句法分析
6.2.1 中文分词技术
6.2.2 词的分类和兼类
6.2.3 汉语句法分析
6.3 问题理解
6.3.1 词法分析
6.3.2 问题分类
6.3.3 关键词扩展与抽取
6.3.4 答案抽取
6.4 问题检索
6.4.1 基于词法的问句检索
6.4.2 基于句法的问句检索
6.4.3 基于语义的问句检索
6.4.4 常见问题集的问句检索
6.5 信息抽取
6.5.1 抽取的对象
6.5.2 抽取的种类
6.5.3 抽取的方法
6.6 知识库构建
6.6.1 基本概念
6.6.2 体系结构
6.6.3 关键技术
6.7 知识推理
6.7.1 线索挖掘
6.7.2 关系推理
6.7.3 关系预测
6.8 案例分析
6.8.1 限定域系统的现有案例分析
6.8.2 开放域系统的现有案例分析
参考文献
第7章文本挖掘
7.1 文本表示
7.2 话题挖掘
7.2.1 非负矩阵分解
7.2.2 概率潜在语义分析
7.2.3 潜在狄利克雷分配模型
7.2.4 分析与实例比较
7.3 多文档自动文摘
7.3.1 目标函数选择：句子重要性评价
7.3.2 优化方法
7.3.3 其他的自动文摘问题
7.3.4 实例分析
7.4 情感分析和摘要
7.4.1 基于频繁项集的方法
7.4.2 实例分析
7.4.3 基于方面的话题模型分析方法
7.5 数据挖掘在专利分析中的应用
7.5.1 专利分析的内容、流程与方法
7.5.2 数据挖掘在专利分析中的应用方向
参考文献
第8章多媒体数据挖掘
8.1 多媒体技术的特点
8.1.1 数字化
8.1.2 多样性
8.1.3 集成性
8.1.4 交互性
8.1.5 非线性
8.1.6 实时性
8.2 多媒体数据挖掘概述
8.2.1 背景
8.2.2 研究及应用现状
8.3 多媒体数据的特征抽取
8.3.1 文本特征抽取
8.3.2 图像特征表示
8.4 数据挖掘在图像检索中的应用
8.4.1 应用背景
8.4.2 数据集描述
8.4.3 数据挖掘在图像检索中的算法分析
8.4.4 图像检索案例
8.5 数据挖掘在多媒体信息融合中的应用
8.5.1 应用背景
8.5.2 数据集描述
8.5.3 数据挖掘在多媒体信息融合中的算法分析
8.5.4 多媒体信息融合案例
8.6 数据挖掘在人脸识别中的应用
8.6.1 应用背景
8.6.2 数据集描述
8.6.3 人脸识别算法分析
8.6.4 分布式人脸识别系统设计
参考文献
第9章社交媒体挖掘
9.1 社交媒体数据挖掘简介
9.1.1 社交媒体分析的特点综述
9.1.2 社交媒体的典型应用
9.2 社交网络数据
9.3 数据挖掘在社交媒体热点问题上的应用
9.3.1 社交媒体数据挖掘需求
9.3.2 信息扩散分析
9.3.3 链接的预测
9.3.4 专家与关键人物的挖掘
9.3.5 搜索
9.3.6 信任
9.3.7 社交网络的内容与情感挖掘
参考文献
第10章时空数据挖掘
10.1 时空数据挖掘的发展背景
10.2 时空数据挖掘的相关研究
10.2.1 时空数据的来源
10.2.2 时空数据的基本性质
10.2.3 时空数据挖掘的方法与任务
10.3 时空数据的模式挖掘
10.3.1 时空数据的频繁模式
10.3.2 时空数据的异常模式
10.4 时空数据的聚类和分类
10.4.1 时空数据的聚类
10.4.2 时空数据的分类
10.5 时空数据预测
10.5.1 位置预测
10.5.2 位置推荐
10.6 时空数据挖掘的案例研究
10.6.1 TerryFly GeoCloud
10.6.2 NUPT-ST-Miner
10.7 时空数据挖掘的挑战和发展
参考文献
第11章生物信息学
11.1 生物医学知识综述
11.2 生物医学大数据
11.3 数据挖掘在蛋白质与核酸相互作用研究中的应用
11.3.1 基于机器学习的蛋白质与核酸相互作用的研究策略
11.3.2 案例分析：蛋白质中RNA—结合残基的预测模型
11.4 数据挖掘在生物医学文献中的应用
11.4.1 生物医学文献挖掘概述
11.4.2 数据挖掘应用方法描述
11.5 数据挖掘在基因表达数据中的应用
11.5.1 基因芯片技术
11.5.2 下一代高通量测序技术
11.5.3 RNA-Seq技术与基因芯片技术的比较
11.5.4 数据挖掘在下一代高通量RNA-Seq测序数据中的应用
参考文献
第12章隐私保护和数据挖掘
12.1 隐私保护概述
12.1.1 隐私侵害事件
12.1.2 隐私保护困境
12.1.3 隐私保护要求
12.1.4 隐私保护水平度量
12.2 隐私保护技术分类
12.2.1 匿名化技术
12.2.2 加密技术
12.2.3 数据扰动技术
12.3 隐私保护数据挖掘方法
12.3.1 隐私保护聚类
12.3.2 隐私保护决策树
12.3.3 隐私保护推荐系统
12.3.4 隐私保护贝叶斯算法
12.3.5 隐私保护支持向量机
12.3.6 隐私保护关联规则挖掘
12.4 复杂数据挖掘场景下的隐私保护
12.4.1 大数据隐私保护
12.4.2 图数据隐私保护
12.4.3 云数据隐私保护
12.4.4 隐私保护深度学习
参考文献
第13章健康医疗大数据中的数据挖掘技术
13.1 健康医疗大数据的含义
13.2 数据特性
13.3 预警系统
13.3.1 数据预处理
13.3.2 Bucketing
13.3.3 Bucket Bagging
13.3.4 特征集构造
13.3.5 特征选择
13.3.6 探索性下采样
13.3.7 指数移动平均
13.4 非结构化文本信息的挖掘
13.5 数据挖掘实例
13.5.1 评价标准
13.5.2 实验设计
13.5.3 逻辑回归模型的实验结果
13.5.4 算法比较
13.5.5 预警时间分析
13.6 应用方向
13.6.1 疾病预警预测及生存期分析
13.6.2 疾病辅助诊断治疗
13.6.3 药物研究
13.6.4 医学影像
13.6.5 医院信息系统
13.6.6 远程医疗
13.6.7 健康数据库管理
13.6.8 医疗健康相关企业经营
参考文献

FAQ

How does this book differ from Andrew Ng's Machine Learning or Zhou Zhihua's Machine Learning (the "Watermelon Book")?

This book focuses more on the specific field of "data mining" and is closely organized around "big data" scenarios. Compared with the more general machine learning frameworks of the former, it elaborates in greater detail on classic data mining tasks such as association rules, sequential patterns, and anomaly detection, and specifically discusses computing and storage challenges in big data environments. It can complement the "Watermelon Book": the latter is a more comprehensive machine learning textbook, while this book focuses deeply on data mining in the context of big data applications.

What language is the code in the book written in? How much programming background is needed?

The book mainly uses pseudocode and algorithm descriptions to explain the core logic and is not tied to any particular programming language. This requires readers to be able to translate algorithmic ideas into code. Generally, mastering either Python or Java and understanding basic data structures and control flow is enough to follow along, but to practice you will need to implement things yourself in the corresponding big data ecosystem (such as PySpark).

Is this book helpful for job hunting (e.g., as a data mining engineer)?

It helps significantly, but its role should be clear. The book builds a solid and systematic data mining knowledge base, which is a great advantage in technical interviews when explaining principles and designing solutions. However, it does not directly provide project resumes or interview question banks. It is recommended to combine the book's theoretical study with actual Kaggle competitions, open-source projects, or work scenarios to turn theoretical strength into practical ability.

Related on WeRead

Comments

Find this book

This site is an index: you start “Search all sources” in your browser, and the entries it lists all point to third-party sites; please judge their availability yourself.

About the author

李涛 Author

Li Tao is an author whose works span a wide range of fields, with 27 titles held in the collection. The subjects he writes on are notably diverse: medical professional titles such as Clinical Psychopathology and the National County-Level Hospital Practical Handbook series volume Psychiatrist's Handbook, as well as clinical technical topics like Minimally Invasive Surgery for Diabetic Retinopathy; education and social issues in The Modernization of Chinese Rural Education; and practical tutorials on software and computing, including Adobe After Effects CC: The Master's Path. He has also written on science popularization and legal thinking, such as Perfect Symmetry: The Accidental Discovery of Fullerenes and 50 Lessons on Cultivating Citizens' Legal Thinking: Think Like a Lawyer, and contributed to applied writing such as the Technical Guidelines for Evaluating Healthy Enterprise Development. Because public information is limited, his personal biography, professional background, and identity remain unclear; from the distribution of his works, one can only see that he combines specialized writing with popular outreach, reaching readers in medicine, education, software, popular science, and law.