Short period prediction is a relevant task for many network applications. Tuning the parameters of the prediction model is very crucial to achieve accurate prediction. This work focuses on the design, the empirical evaluation and the analysis of the behavior of training-based models for predicting the throughput of a single link i.e. the incoming input rate in Megabit per second. In this work, ...

Hawkins, Amy L. M.S., Purdue University, May, 2010. Relationship between Undergraduate Student Activity and Academic Performance. Major Professor: Daniel Lybrook. Research has shown that student involvement enhances the overall college experience and the development of transferable skills for undergraduate students. Participation in student organizations can lead to the development of social an...

This paper describes an improved, IEEE conforming oating-point addition algorithm. This algorithm has only one addition step involving the signi cand in the worst-case path, hence o ering a considerable speed advantage over the existing algorithms, which typically require two to three addition steps.

Based on the γ-ray data of blazars in the third EGRET catalog and radio data at 5 GHz, we studied the correlation between the radio and γ-ray luminosities using two statistical methods. The first method was the partial correlation analysis method, which indicates that there exist correlations between the radio and γ-ray luminosities in both high and low states as well as in the average case. Th...

Transfer learning can counter the heavy-tailed nature of the distribution of training examples over object classes. Here, we study transfer learning for object class detection. Starting from the intuition that “what makes a good detector” should manifest itself in the form of repeatable statistics over existing “good” detectors, we design a lowlevel feature model that can be used as a prior for...

The paper considers two problems associated with the detection and classification of motion in image sequences obtained from a static camera. Motion is detected by differencing a reference and the “current” image frame, and therefore requires a suitable reference image and the selection of an appropriate detection threshold. Several threshold selection methods are investigated, and an algorithm...

The Tower of Knowledge architecture integrates probability theory and logic for making decisions. The scheme models the causal dependencies between the functionalities of objects and their descriptions, and then employs the maximum expected utility principle, which combines probability theory and logic, to select the most appropriate label for the object. Since most existing scene interpretatio...

In this paper we approach the analysis of statistics algorithms from a geometric viewpoint and use techniques from computational geometry to develop new, fast algorithms for computing familiar statistical quantities. Such fundamental procedures as sorting and selection play an important role in nonparametric estimation as well as in correlation and regression and we use known results to obtain ...

This paper addresses the influences of standard operating parameters like backlight, contrast, sharpness, etc. of an autostereoscopic display on subjective quality, in the absence of transmission quality impairments (best case reference). Therefore, a useful test environment is specified and applied. Results show that the influences of different display setups are distinguishable from each othe...

Regression testing is a commonly used activity whose purpose is to determine whether the modifications made to a software system have introduced new faults. Textual differ-encing is a new, safe and fairly precise, selective regression testing technique that works by comparing source files from the old and the new version of the program. We have implemented the textual differencing technique in ...