Semantics in Mobile Sensing (Paperback)

The dramatic progress of smartphone technologies has ushered in a new era of mobile sensing, where traditional wearable on-body sensors are being rapidly superseded by various embedded sensors in our smartphones. For example, a typical smartphone today, has at the very least a GPS, WiFi, Bluetooth, triaxial accelerometer, and gyroscope. Alongside, new accessories are emerging such as proximity, magnetometer, barometer, temperature, and pressure sensors. Even the default microphone can act as an acoustic sensor to track noise exposure for example. These sensors act as a "lens" to understand the user's context along different dimensions.

Data can be passively collected from these sensors without interrupting the user. As a result, this new era of mobile sensing has fueled significant interest in understanding what can be extracted from such sensor data both instantaneously as well as considering volumes of time series from these sensors. For example, GPS logs can be used to determine automatically the significant places associated to a user's life (e.g., home, office, shopping areas). The logs may also reveal travel patterns, and how a user moves from one place to another (e.g., driving or using public transport). These may be used to proactively inform the user about delays, relevant promotions from shops, in his "regular" route. Similarly, accelerometer logs can be used to measure a user's average walking speed, compute step counts, gait identification, and estimate calories burnt per day. The key objective is to provide better services to end users.

The objective of this book is to inform the reader of the methodologies and techniques for extracting meaningful information (called "semantics") from sensors on our smartphones. These techniques form the cornerstone of several application areas utilizing smartphone sensor data. We discuss technical challenges and algorithmic solutions for modeling and mining knowledge from smartphone-resident sensor data streams. This book devotes two chapters to dive deep into a set of highly available, commoditized sensors---the positioning sensor (GPS) and motion sensor (accelerometer). Furthermore, this book has a chapter devoted to energy-efficient computation of semantics, as battery life is a major concern on user experience.

Table of Contents: Acknowledgments / Introduction / Semantic Trajectories from Positioning Sensors / Semantic Activities from Motion Sensors / Energy-Efficient Computation of Semantics from Sensors / Conclusion / Bibliography / Authors' Biographies

智慧型手機技術的劇烈進步引領了移動感測的新時代，傳統的可穿戴式身體感測器正迅速被智慧型手機中的各種嵌入式感測器所取代。例如，現今的智慧型手機至少擁有GPS、WiFi、藍牙、三軸加速度計和陀螺儀等功能。同時，還出現了新的配件，如接近感應器、磁力計、氣壓計、溫度計和壓力感測器。甚至預設的麥克風也可以作為聲學感測器，例如追蹤噪音暴露。這些感測器在不同維度上作為「鏡頭」，用於理解使用者的上下文。

可以在不打擾使用者的情況下從這些感測器中被動地收集數據。因此，這個新的移動感測時代引起了對從這些感測器數據中即時提取什麼以及考慮到時間序列數據量的興趣。例如，GPS日誌可以用於自動確定與使用者生活相關的重要地點（例如家、辦公室、購物區域）。日誌還可以揭示出行模式，以及使用者如何從一個地方移動到另一個地方（例如開車或使用公共交通工具）。這些信息可以主動通知使用者有關延誤、商店的相關促銷活動等在他「常規」路線上的信息。同樣，加速度計日誌可以用於測量使用者的平均步行速度、計算步數、步態識別和估計每天燃燒的卡路里。關鍵目標是為最終用戶提供更好的服務。

本書的目標是向讀者介紹從智慧型手機感測器中提取有意義信息（稱為「語義」）的方法和技術。這些技術是利用智慧型手機感測器數據的幾個應用領域的基石。我們討論了從智慧型手機感測器數據流中建模和挖掘知識的技術挑戰和算法解決方案。本書專門探討了兩個章節，深入介紹了一組高度可用的通用感測器——定位感測器（GPS）和運動感測器（加速度計）。此外，本書還有一章專門介紹了節能計算語義的方法，因為電池壽命是用戶體驗的一個主要關注點。

目錄：致謝 / 引言 / 從定位感測器提取語義軌跡 / 從運動感測器提取語義活動 / 從感測器計算節能語義 / 結論 / 參考文獻 / 作者簡介