Software Design Challenges in Time Series Prediction Systems Using Parallel Implementation of Artificial Neural Networks

<table class="table-group" id="tab1"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td align="left">Factors of heterogeneous design</td><td align="left">Medium</td><td align="left">High</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td align="left">Simplicity</td><td align="left"> </td><td align="left">High because well-known components of different technology can be used together </td></tr><tr><td align="center" colspan="3"><hr/></td></tr><tr><td align="left">Portability</td><td align="left">This design will not fit for implementation in all kinds of platforms</td><td align="left"> </td></tr><tr><td align="center" colspan="3"><hr/></td></tr><tr><td align="left">Modifiability</td><td align="left"> </td><td align="left">Actual design and modified design produced the same results</td></tr><tr><td align="center" colspan="3"><hr/></td></tr><tr><td align="left">Reliability</td><td align="left">Except Japan currency versus USD other predictions are reliable</td><td align="left"> </td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

The Scientific World Journal

tab1

Table 1

Table 1: Software Design Challenges in Time Series Prediction Systems Using Parallel Implementation of Artificial Neural Networks 