By E.H. Chi

Television audience this present day are uncovered to overwhelming quantities of data, and challenged by means of the plethora of interactive performance supplied through present set-top packing containers. to make sure wide adoption of this know-how through shoppers, destiny electronic tv should take usability matters completely under consideration. particularly, critical realization has to be paid to facilitate the choice of content material on somebody foundation, and to supply easy-to-use interfaces that fulfill audience' interplay requirements.This quantity collects chosen learn stories at the improvement of customized providers for Interactive television. Drawing upon contributions from academia and within the US, Europe and Asia, this e-book represents a finished photo of cutting edge learn in customized tv.

Show description

Read Online or Download Personalized Digital Television: Targeting Programs to Individual Viewers PDF

Best organization and data processing books

Advances in Databases and Information Systems: 12th East European Conference, ADBIS 2008, Pori, Finland, September 5-9, 2008. Proceedings

This e-book constitutes the refereed complaints of the twelfth East ecu convention on Advances in Databases and knowledge platforms, ADBIS 2008, held in Pori, Finland, on September 5-9, 2008. The 22 revised papers have been conscientiously reviewed and chosen from sixty six submissions. Topically, the papers span a large spectrum of the database and knowledge structures box: from question optimisation, and transaction processing through layout how you can program orientated themes like XML and information on the net.

Reconfigurable Computing: Architectures, Tools and Applications: 4th International Workshop, ARC 2008, London, UK, March 26-28, 2008. Proceedings

This publication constitutes the refereed complaints of the 4th overseas Workshop on utilized Reconfigurable Computing, ARC 2008, held in London, united kingdom, in March 2008. The 21 complete papers and 14 brief papers provided including the abstracts of three keynote lectures have been rigorously reviewed and chosen from fifty six submissions.

Data Conversion: Calculating the Monetary Benefits

This ebook tackles the 3rd significant problem and the second one such a lot tricky step within the ROI technique: changing information to financial values. while a specific venture or software is attached to a enterprise degree, the subsequent logical query is: what's the financial worth of that effect? For ROI research, it truly is at this severe element the place the financial advantages are built to match to the prices of this system to calculate the ROI.

Additional info for Personalized Digital Television: Targeting Programs to Individual Viewers

Example text

7 (for each genre). 2. 4. Increasing Accuracy through Fusion Results of testing the explicit and two implicit recommenders with real users (Kurapati et al. 2001) suggested reasonable recommender accuracy. However di¡erent recommenders seemed to perform well for di¡erent users with no easy way to pre-match individual recommenders to individual users. Further analysis revealed that di¡erent recommenders performed well for very di¡erent sets of shows. As a follow-up we attempted to improve accuracy by fusing (combining) recommender outputs using a neural network.

We started from the Stereotypical UM Expert. We simulated an initial scenario where the user has speci¢ed her personal data and general interests, but where she does not declare her TV program preferences. Thus, the recommendations are based only on the stereotypical information. In this ¢rst phase, we evaluated the correctness of the stereotypical classi¢cation and the accuracy of recommendations by feeding the system with the socio-demographic data and the general interests (dataset a) collected by means of the interviews.

However, practically we obtain information only on the classes: Cþ (shows the viewer watched) and CÀ (shows the viewer did not watch), which are approximations of classes C1 and C2. A major element of uncertainty lies in determining what is ‘not-watched’ by users. For each watched showöwhich can be ascertained clearlyöthere are numerous ones ‘not-watched’. The key question is how to sample the universe of shows to appropriately populate the ‘not-watched’ class, CÀ. We recognize that users could be asked to provide information on shows they do not like, thus gathering information directly on shows belonging to class, C2 (shows disliked by the user).

Download PDF sample

Rated 4.53 of 5 – based on 40 votes