The abundance of information published on the Internet makes filtering of hazardous Web pages a difficult yet important task. Supervised learning methods such as Support Vector Machines (SVMs) can be used to identify hazardous Web content. However, scalability is a big challenge, especially if we have to train multiple classifiers, since different policies exist on what kind of information is hazardous. We therefore propose two different strategies to train multiple SVMs for personalized Web content filters. The first strategy identifies common data clusters and then performs optimization on these clusters in order to obtain good initial solutions for individual problems. This initialization shortens the path to the optimal solutions and reduces the training time on individual training sets. The second approach is to train all SVMs simultaneously. We introduce an SMO-based kernel-biased heuristic that balances the reduction rate of individual objective functions and the computational cost of kernel matrix. The heuristic primarily relies on the optimality conditions of all optimization problems and secondly on the pre-calculated part of the whole kernel matrix. This strategy increases the amount of information sharing among learning tasks, thus reduces the number of kernel calculation and training time. In our experiments on inconsistently labeled training examples, both strategies were able to predict hazardous Web pages accurately (> 91%) with a training time of only 26% and 18% compared to that of the normal sequential training.

For backup of failed VPs (Virtual Paths) in ATM (Asynchronous Transfer Mode) networks, many self-healing algorithms have already been proposed. However, since the existing algorithms recover each failed VP with a single backup VP, a problem arises in that those algorithms cannot necessarily provide a failed VP having a higher recovery priority with a larger recovery ratio, which is the ratio of the bandwidth of a backup VP to that of a failed VP. For a solution to the problem, this paper proposes a new self-healing algorithm which recovers each failed VP with one or more backup VPs. We also evaluate its availability by comparing with an existing algorithm through simulations.

Mobile agent technology is applied to enhance the remote network management of large-scale networks, and real-world oriented entertainment systems, and so forth. In order to communicate, the agents exchange messages mutually and migrate repeatedly among terminals. Although these systems efficiently accomplish the tasks by using a large quantity of mobile agents, they have a serious problem in that the number of messages between agents increases in proportion to the square of the number of agents. These systems have to reduce the communication costs, such as the number of hosts relaying messages; however, the conventional message-delivering schemes alone cannot keep the communication costs to a minimum under all conditions. To minimize the communication costs, we propose a hybrid message-delivering scheme which dynamically selects the optimal message-delivering schemes. Firstly, we evaluate the communication costs of conventional schemes, and we design the hybrid message-delivering scheme. Then we perform simulation evaluations to derive the threshold value for switching a scheme to minimize the communication costs.