Benchmarking Smoothness of Mobile Browsers

• Main Authors: Chin-Hung Lin, 林金宏
• Other Authors: Edward T.-H. Chu
• Format: Others
• Language: en_US
• Published: 2014
• Online Access: http://ndltd.ncl.edu.tw/handle/db6dpa

碩士 === 國立雲林科技大學 === 資訊工程系 === 102 === Mobile browser plays an important role in smartphones because it provides many valuable applications, such as shopping, news browsing, map navigation, e-mail and video playing. The smoothness of human-browser interaction can significantly affect consumer purchase decisions. As a result, how to objectively evaluate the smoothness of human-browser interaction is an important issue for both consumers and smartphone manufacturers. In order to evaluate smartphones, existing smartphone benchmarks adopted synthetic workloads, such as floating point calculation, random string sorting, memory read/write and image rendering to assess the relative performance. However, these synthetic workloads cannot fully represent the amount of work needed to be done when users interact with a browser. As a result, in this paper, we first design a questionnaire which is answered by a lot of people to collect the most common use scenarios for a mobile browser. We then develop a benchmarking tool, named MoBench, to automatically measure the response time of each use scenarios. Finally, we conduct a questionnaire study to construct the relationship between the response time and the level of smoothness. In our experiment, we rank the smoothness level of seven commercial smartphones. Compared with existing benchmarks, our method is more objective in evaluating the smoothness of human-browser interaction.