Search for: All records

Observable reading behavior, the act of moving the eyes over lines of text, is highly stereotyped among the users of a language, and this has led to the development of reading detectors–methods that input windows of sequential fixations and output predictions of the fixation behavior during those windows being reading or skimming. The present study introduces a newmethod for reading detection using Region Ranking SVM (RRSVM). An SVM-based classifier learns the local oculomotor features that are important for real-time reading detection while it is optimizing for the global reading/skimming classification, making it unnecessary to hand-label local fixation windows for model training. This RRSVM reading detector was trained and evaluated using eye movement data collected in a laboratory context, where participants viewed modified web news articles and had to either read them carefully for comprehension or skim them quickly for the selection of keywords (separate groups). Ground truth labels were known at the global level (the instructed reading or skimming task), and obtained at the local level in a separate rating task. The RRSVM reading detector accurately predicted 82.5% of the global (article-level) reading/skimming behavior, with accuracy in predicting local window labels ranging from 72-95%, depending on how tuned the RRSVM was for local and global weights. With this RRSVM reading detector, a method now exists for near real-time reading detection without the need for hand-labeling of local fixation windows. With real-time reading detection capability comes the potential for applications ranging from education and training to intelligent interfaces that learn what a user is likely to know based on previous detection of their reading behavior. 

A large fraction of users in developing regions use relatively inexpensive, low-end smartphones. However, the impact of device capabilities on the performance of mobile Internet applications has not been explored. To bridge this gap, we study the QoE of three popular applications -- Web browsing, video streaming, and video telephony -- for different device parameters. Our results demonstrate that the performance of Web browsing is much more sensitive to low-end hardware than that of video applications, especially video streaming. This is because the video applications exploit specialized coprocessors/accelerators and thread-level parallelism on multi-core mobile devices. Even low-end devices are equipped with needed coprocessors and multiple cores. In contrast, Web browsing is largely influenced by clock frequency, but it uses no more than two cores. This makes the performance of Web browsing more vulnerable on low-end smartphones. Based on the lessons learned from studying video applications, we explore offloading Web computation to a coprocessor. Specifically, we explore the offloading of regular expression computation to a DSP coprocessor and show an improvement of 18% in page load time while saving energy by a factor of four.