<p>Several embedded application domains for reconfigurable systems tend to combine <br />frequent changes with high performance demands of their workloads such as image processing, wearable computing and<br />network processors. Time multiplexing of reconfigurable hardware resources raises a number of new issues, ranging <br />from run-time systems to complex programming models that usually form a Reconfigurable<br />hardware Operating System (ROS). The Operating System performs online task scheduling and handles resource management.<br />There are many challenges in adaptive computing and dynamic reconfigurable systems. One of the major understudied challenges<br />is estimating the required resources in terms of soft cores, Programmable Reconfigurable Regions (PRRs), <br />the appropriate communication infrastructure, and to predict a near optimal layout and floor-plan of the reconfigurable logic fabric. <br />Some of these issues are specific to the application being designed, while others are more general and relate to the underlying run-time environment.<br />Static resource allocation for Run-Time Reconfiguration (RTR) often leads to inferior and unacceptable results. <br />In this paper, we present a novel adaptive and dynamic methodology, based on a Machine Learning approach, for predicting and<br />estimating the necessary resources for an application based on past historical information.<br />An important feature of the proposed methodology is that the system is able to learn and generalize and, therefore, is expected to improve <br />its accuracy over time. The goal of the entire process is to extract useful hidden knowledge from the data. This knowledge is the prediction <br />and estimation of the necessary resources for an unknown or not previously seen application.<br /><br /></p>