In smartphone data analysis, both energy consumption modeling and user behavior mining have been explored extensively, but the relationship between energy consumption and user behavior has been rarely studied. Such a relationship is explored over large-scale users in this article. Based on energy consumption data, where each users’ feature vector is represented by energy breakdown on hardware components of different apps, User Behavior Models (UBM) are established to capture user behavior patterns (i.e., app preference, usage time). The challenge lies in the high diversity of user behaviors (i.e., massive apps and usage ways), which leads to high dimension and dispersion of data. To overcome the challenge, three mechanisms are designed. First, to reduce the dimension, apps are ranked with the top ones identified as typical apps to represent all. Second, the dispersion is reduced by scaling each users’ feature vector with typical apps to unit ℓ 1 norm. The scaled vector becomes Usage Pattern, while the ℓ 1 norm of vector before scaling is treated as Usage Intensity. Third, the usage pattern is analyzed with a two-layer clustering approach to further reduce data dispersion. In the upper layer, each typical app is studied across its users with respect to hardware components to identify Typical Hardware Usage Patterns (THUP). In the lower layer, users are studied with respect to these THUPs to identify Typical App Usage Patterns (TAUP). The analytical results of these two layers are consolidated into Usage Pattern Models (UPM), and UBMs are finally established by a union of UPMs and Usage Intensity Distributions (UID). By carrying out experiments on energy consumption data from 18,308 distinct users over 10 days, 33 UBMs are extracted from training data. With the test data, it is proven that these UBMs cover 94% user behaviors and achieve up to 20% improvement in accuracy of energy representation, as compared with the baseline method, PCA. Besides, potential applications and implications of these UBMs are illustrated for smartphone manufacturers, app developers, network providers, and so on.

中文翻译：

---

基于能耗数据建立智能手机用户行为模型

在智能手机数据分析中，无论是能耗建模还是用户行为挖掘都得到了广泛的探索，但对能耗与用户行为的关系却鲜有研究。本文在大规模用户中探讨了这种关系。基于能耗数据，其中每个用户的特征向量由不同应用程序的硬件组件的能量分解来表示，用户行为模型（UBM）被建立以捕获用户行为模式（即，应用程序偏好，使用时间）。挑战在于用户行为的高度多样性（即海量的应用程序和使用方式），这导致数据的高维度和分散性。为了克服这一挑战，设计了三种机制。首先，为了减少维度，将应用程序与被识别为典型应用程序的顶部应用程序进行排名以代表所有应用程序。1规范。缩放后的向量变为使用模式，而 ℓ1缩放前的向量范数被视为使用强度。第三，使用两层聚类方法分析使用模式，以进一步减少数据分散。在上层，每个典型应用程序都在其用户中针对硬件组件进行研究，以识别典型硬件使用模式 (THUP)。在较低层，针对这些 THUP 对用户进行研究，以识别典型应用程序使用模式 (TAUP)。将这两层的分析结果合并为使用模式模型（UPM），最终通过 UPM 和使用强度分布（UID）的联合建立 UBM。通过在 10 天内对 18,308 个不同用户的能耗数据进行实验，从训练数据中提取了 33 个 UBM。有了测试数据，事实证明，与基线方法 PCA 相比，这些 UBM 覆盖了 94% 的用户行为，并且在能量表示的准确性上实现了高达 20% 的提高。此外，还为智能手机制造商、应用程序开发商、网络提供商等说明了这些 UBM 的潜在应用和影响。