Search

Using machine learning in high-speed networks for tasks such as flow classification typically requires either very resource efficient classification approaches, large amounts of computational resources, or specialized hardware. Here we provide a sketch of the discretize-optimize (DISCO) approach which can construct an extremely efficient classifier for low dimensional problems by combining feature selection, efficient discretization, novel bin placement, and lookup. As feature selection and discretization parameters are crucial, appropriate combinatorial optimization is an important aspect of the approach. A performance evaluation is performed for a YouTube classification task using a cellular traffic data set. The initial evaluation results show that the DISCO approach can move the Pareto boundary in the classification performance versus runtime trade-off by up to an order of magnitude compared to runtime optimized random forest and decision tree classifiers.

Pressing a virtual button is still the major interaction method in touchscreen mobile phones. Although phones are becoming more and more powerful, operating system software is getting more and more complex, causing latency in interaction. We were interested in gaining insight into touch-feedback simultaneity and the effects of latency on the perceived quality of touchscreen buttons. In an experiment, we varied the latency between touch and feedback between 0 and 300 ms for tactile, audio, and visual feedback modalities. We modelled the proportion of simultaneity perception as a function of latency for each modality condition. We used a Gaussian model fitted with the maximum likelihood estimation method to the observations. These models showed that the point of subjective simultaneity (PSS) was 5ms for tactile, 19ms for audio, and 32ms for visual feedback. Our study included the scoring of perceived quality for all of the different latency conditions. The perceived quality dropped significantly between latency conditions 70 and 100 ms when the feedback modality was tactile or audio, and between 100 and 150 ms when the feedback modality was visual. When the latency was 300ms for all feedback modalities, the quality of the buttons was rated significantly lower than in all of the other latency conditions, suggesting that a long latency between a touch on the screen and feedback is problematic for users. Together with PSS and these quality ratings, a 75% threshold was established to define a guideline for the recommended latency range between touch and feedback. Our guideline suggests that tactile feedback latency should be between 5 and 50 ms, audio feedback latency between 20 and 70 ms, and visual feedback latency between 30 and 85 ms. Using these values will ensure that users will perceive the feedback as simultaneous with the finger's touch. These values also ensure that the users do not perceive reduced quality. These results will guide engineers and designers of touchscreen interactions by showing the trade-offs between latency and user preference and the effects that their choices might have on the quality of the interactions and feedback they design.

One of the questions that is frequently raised during any serious discussion related to the identity of Information Systems (IS) education is the relationship between the business domain and IS and the role of IS as a business discipline. Naturally, IS as an academic discipline has its strongest roots within the business school community and a history that is closely linked to the rapid growth in the dependence of businesses of all types and sizes on information technology. Particularly in North America, most of the founding academics in the field of IS came from business schools, and information systems as artifacts were seen to exist to support management in organizations. Both in research and in curriculum development, large corporations got more attention than smaller companies because they presented the most interesting and challenging problems to solve and had the most focused demand for graduates. In addition, business schools identified the need to hire academic specialists who are able to integrate issues related to business and technology in their research and teaching. Particularly during the boom years of late 1980s and 1990s, student demand for courses in Information Systems was very high, which obviously raised the level of interest in the discipline among business school administrators. The events of early 2000s led to the rapid declines in enrollments that we all have experienced and are fighting against. Not surprisingly, these developments have made some business schools question the value of IS programs and departments, but the field is still predominantly associated with business schools.