O'Reilly logo

Mobile Intelligence by Bala Srinivasan, Ling Tan, Jianhua Ma, Agustinus Borgy Waluyo, Laurence T. Yang

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

17.4 CASE STUDY I: DHGN FOR PATTERN RECOGNITION

This case study takes into account two significant factors related to any distributed system, namely the varying capabilities of the participating nodes and the distribution of the computational load. Two different DHGN schemes were simulated to test the effectiveness of our approach as a distributed system. The first test addresses varying processing capabilities within a distributed system through the variable-form DHGN. The second test demonstrates the distributiveness of the approach through the standard-form DHGN.

17.4.1 DHGN Simulator Design

The DHGN simulation program for pattern-recognition application has been developed using C language with message passing interface (MPI) support for internodes communications. Figure 17.10 shows the architecture for the DHGN implementation as a pattern-recognition application. The SI acts as the controller for input and output functions for the DHGN architecture.

images

Figure 17.10 DHGN architecture for pattern recognition.

images

Figure 17.11 Test characters representation in 7 × 5 bit format.

The test data for this simulation comprise a set of alphabet character patterns that can be visually distinguished. The letters A, I, J, S, X, and Z were selected in this regard. These letters were mapped onto 7 ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required