A major challenge in indexing unstructured hypertext databases is to automatically extract meta-data that enables structured search using topic taxonomies, circumvents keyword ambiguity, and improves the quality of search and profile-based routing and filtering. Therefore, an accurate classifier is an essential component of a hypertext database. Hyperlinks pose new problems not addressed in the extensive text classification literature. Links clearly contain high-quality semantic clues that are lost upon a purely term-based classifier, but exploiting link information is non-trivial because it is noisy. Naive use of terms in the link neighborhood of a document can even degrade accuracy. Our contribution is to propose robust statistical models and a relaxation labeling technique for better classification by exploiting link information in a small neighborhood around documents. Our technique also adapts gracefully to the fraction of neighboring documents having known topics. We experimented with pre-classified samples from Yahoo! 1 and the US Patent Database 2 . In previous work, we developed a text classifier that misclassified only 13% of the documents in the well-known Reuters benchmark; this was comparable to the best results ever obtained. This classifier misclassified 36% of the patents, indicating that classifying hypertext can be more difficult than classifying text. Naively using terms in neighboring documents increased error to 38%; our hypertext classifier reduced it to 21%. Results with the Yahoo! sample were more dramatic: the text classifier showed 68% error, whereas our hypertext classifier reduced this to only 21%.

-There is a long-standing vision of embedding backscatter nodes like RFIDs into everyday objects to build ultralow power ubiquitous networks. A major problem that has challenged this vision is that backscatter communication is neither reliable nor efficient. Backscatter nodes cannot sense each other, and hence tend to suffer from colliding transmissions. Further, they are ineffective at adapting the bit rate to channel conditions, and thus miss opportunities to increase throughput, or transmit above capacity causing errors. This paper introduces a new approach to backscatter communication. The key idea is to treat all nodes as if they were a single virtual sender. One can then view collisions as a code across the bits transmitted by the nodes. By ensuring only a few nodes collide at any time, we make collisions act as a sparse code and decode them using a new customized compressive sensing algorithm. Further, we can make these collisions act as a rateless code to automatically adapt the bit rate to channel quality -i.e., nodes can keep colliding until the base station has collected enough collisions to decode. Results from a network of backscatter nodes communicating with a USRP backscatter base station demonstrate that the new design produces a 3.5× throughput gain, and due to its rateless code, reduces message loss rate in challenging scenarios from 50% to zero.