Technical Reports Published in 2008



BU-CE-0801

TITLE: Counteracting Free Riding in Pure Peer-to-Peer Networks
AUTHOR: K. Murat Karakaya

ABSTRACT: The peer-to-peer (P2P) network paradigm has attracted a significant amount of interest as a popular and successful alternative to traditional client-server model for resource sharing and content distribution. However, researchers have observed the existence of high degrees of free riding in P2P networks which poses a serious threat to effectiveness and efficient operation of these networks, and hence to their future. Therefore, eliminating or reducing the impact of free riding on P2P networks has become an important issue to investigate and a considerable amount of research has been conducted on it.

In this thesis, we propose two novel solutions to reduce the adverse effects of free riding on P2P networks and to motivate peers to contribute to P2P networks. These solutions are also intended to lead to performance gains for contributing peers and to penalize free riders. As the first solution, we propose a distributed and localized scheme, called Detect and Punish Method (DPM), which depends on detection and punishment of free riders. Our second solution to the free riding problem is a connection-time protocol, called P2P Connection Management Protocol (PCMP), which is based on controlling and managing link establishments among peers according to their contributions.

To evaluate the proposed solutions and compare them with other alternatives, we developed a new P2P network simulator and conducted extensive simulation experiments. Our simulation results show that employing our solutions in a P2P network considerably reduces the adverse effects of free riding and improves the overall performance of the network. Furthermore, we observed that P2P networks utilizing the proposed solutions become more robust and scalable.

Keywords: Free riding, Peer-to-Peer networks, distributed computing, performance evaluation.


BU-CE-0802

TITLE: Understanding Human Motion: Recognition and Retrieval of Human Activities
AUTHOR: Nazli Ikizler

ABSTRACT: Within the ever-growing video archives is a vast amount of interesting information regarding human action/activities. In this thesis, we approach the problem of extracting this information and understanding human motion from a computer vision perspective. We propose solutions for two distinct scenarios, ordered from simple to complex. In the first scenario, we deal with the problem of single action recognition in relatively simple settings. We believe that human pose encapsulates many useful clues for recognizing the ongoing action, and we can represent this shape information for 2D single actions in very compact forms, before going into details of complex modeling. We show that high-accuracy single human action recognition is possible 1) using spatial oriented histograms of rectangular regions when the silhouette is extractable, 2) using the distribution of boundary-fitted lines when the silhouette information is missing. We demonstrate that, inside videos, we can further improve recognition accuracy by means of adding local and global motion information. We also show that within a discriminative framework, shape information is quite useful even in the case of human action recognition in still images.

Our second scenario involves recognition and retrieval of complex human activities within more complicated settings, like the presence of changing background and viewpoints. We describe a method of representing human activities in 3D that allows a collection of motions to be queried without examples, using a simple and effective query language. Our approach is based on units of activity at segments of the body, that can be composed across time and across the body to produce complex queries. The presence of search units is inferred automatically by tracking the body, lifting the tracks to 3D and comparing to models trained using motion capture data. Our models of short time scale limb behaviour are built using labelled motion capture set. Our query language makes use of finite state automata and requires simple text encoding and no visual examples. We show results for a large range of queries applied to a collection of complex motion and activity. We compare with discriminative methods applied to tracker data; our method offers significantly improved performance. We show experimental evidence that our method is robust to view direction and is unaffected by some important changes of clothing.

Keywords: Human motion, action recognition, activity recognition, activity retrieval, image and video processing, classification.