《移動通信大數據分析——數據挖掘與機器學習實戰》是清華大學出版社於2020年出版的書籍。
基本介紹
- 中文名：移動通信大數據分析——數據挖掘與機器學習實戰
- 作者：[中]歐陽曄（Ye Ouyang）、[中] 李中源（Zhongyuan Li）、[法]亞歷克西斯·休特（Alexis Huet）、[中]胡曼恬（Mantian Hu）
- 譯者：徐俊傑
- 出版社：清華大學出版社
- 出版時間：2020年12月1日
- 定價：99 元
- ISBN：9787302541240
作者介紹,內容簡介,圖書目錄,
作者介紹
第一作者簡介
歐陽曄 博士
亞信科技首席技術官、高級副總裁
歐陽曄博士目前全面負責亞信科技的技術與產品的研究、開發與創新工作。加入亞信科技之前，歐陽曄博士曾任職於美國第一大移動通信運營商威瑞森電信（Verizon）集團，擔任通信人工智慧系統部經理，是威瑞森電信的Fellow。歐陽曄博士在移動通信領域擁有豐富的研發與大型團隊管理經驗，工作中承擔過科學家、研究員、研發經理、大型研發團隊負責人等多個角色。歐陽曄博士專注於移動通信、數據科學與人工智慧領域跨學科研究，致力於5G網路智慧型化、BSS/OSS融合、通信人工智慧、網路切片、MEC、網路體驗感知、網路智慧型最佳化、5G行業賦能、雲網融合等領域的研發創新與商業化。
內容簡介
本書以4G/5G無線技術、機器學習和數據挖掘的新研究和新套用為基礎，對分析方法和案例進行研究；從工程和社會科學的角度，提高讀者對行業的洞察力，提升運營商的運營效益。本書利用機器學習和數據挖掘技術，研究行動網路中傳統方法無法解決的問題，包括將數據科學與行動網路技術進行完美結合的方法、解決方案和算法。 本書可以作為研究生、本科生、科研人員、行動網路工程師、業務分析師、算法分析師、軟體開發工程師等的參考書，具有很強的實踐指導意義，是不可多得的專業著作。
圖書目錄
第1章概述
1.1 電信業大數據分析 ···························1
1.2 電信大數據分析的驅動力 ················2
1.3 大數據分析對電信產業價值鏈的
益處 ··················································3
1.4 電信大數據的實現範圍····················4
1.4.1 網路分析 ···················································5
1.4.2 用戶與市場分析 ·······································8
1.4.3 創新的商業模式 ·······································91.5 本書概要 ··········································9
參考文獻 ·················································10
第2章電信分析方法論
2.1 回歸方法 ········································12
2.1.1 線性回歸 ··················································13
2.1.2 非線性回歸 ··············································15
2.1.3 特徵選擇 ··················································16
2.2 分類方法 ········································18
2.2.1 邏輯回歸 ··················································18
2.2.2 其他分類方法 ··········································19
2.3 聚類方法 ········································20
2.3.1 K均值聚類 ··············································21
2.3.2 高斯混合模型 ··········································23
2.3.3 其他聚類方法 ··········································24
2.3.4 聚類方法在電信數據中的套用 ·················25
2.4 預測方法 ········································25
2.4.1 時間序列分解 ··········································26
2.4.2 指數平滑模型 ··········································27
2.4.3 ARIMA模型 ············································28
2.5 神經網路和深度學習 ·····················29
2.5.1 神經網路 ··················································29
2.5.2 深度學習 ··················································31
2.6 強化學習 ········································32
2.6.1 模型和策略 ··············································33
2.6.2 強化學習算法 ··········································33
參考文獻 ·················································34
XII
XII
第3章 LTE網路性能趨勢分析
3.1 網路性能預測策略 ·························39
3.1.1 直接預測策略 ··········································39
3.1.2 分析模型 ··················································39
3.2 網路資源與性能指標之間的關係 ···40
3.2.1 LTE網路KPI與資源之間的關係 ···········40
3.2.2 回歸模型 ··················································41
3.3 網路資源預測 ·································43
3.3.1 LTE網路流量與資源預測模型 ···············43
3.3.2 預測網路資源 ··········································43
3.4 評估RRC連線建立的套用 ············46
3.4.1 數據準備與特徵選取 ······························46
3.4.2 LTE KPI與網路資源之間的關係推導 ····47
3.4.3 預測RRC連線建立成功率 ·····················49
參考文獻 ·················································50
第4章熱門設備就緒和返修率分析
4.1 設備返修率與設備就緒的預測
策略 ················································53
4.2 設備返修率和就緒預測模型 ··········54
4.2.1 預測模型的移動通信服務 ························54
4.2.2 參數獲取與存儲 ······································55
4.2.3 分析引擎 ··················································56
4.3 實現和結果 ·····································58
4.3.1 設備返修率預測 ······································58
4.3.2 設備就緒預測 ··········································62
第5章 VoLTE語音質量評估
5.1 套用POLQA評估語音質量··········68
5.1.1 POLQA標準···········································68
5.1.2 語音質量評價中的可擴展性和
可診斷性 ··················································69
5.2 CrowdMi方法論 ····························69
5.2.1 基於RF特徵的分類 ·······························70
5.2.2 網路指標選擇與聚類 ······························70
5.2.3 網路指標與POLQA評分之間的關係····70
5.2.4 模型測試 ··················································70
5.3 CrowdMi中的技術細節 ·················71
5.3.1 記錄分類 ··················································71
5.3.2 網路指標的選擇 ······································71
5.3.3 聚類 ·························································72
5.3.4 回歸 ·························································73
5.4 CrowdMi原型設計與試驗 ·············74
5.4.1 客戶端和伺服器架構 ······························74
5.4.2 測試和結果 ··············································76
參考文獻 ·················································78
目 錄XIII
目 錄XIII
第6章移動APP無線資源使用分析
6.1 起因和系統概述 ·····························80
6.1.1 背景和挑戰 ··············································80
6.1.2 移動資源管理 ··········································81
6.1.3 系統概述 ··················································82
6.2 AppWiR眾包工具 ··························83
6.3 AppWiR挖掘算法 ··························84
6.3.1 網路指標的選擇 ······································84
6.3.2 LOESS方法 ············································87
6.3.3 基於時間序列的網路資源使用預測 ·······87
6.4 實現和試驗 ·····································88
6.4.1 數據收集與研究 ······································88
6.4.2 結果和準確度 ··········································89
參考文獻 ·················································91
