Many fault detection algorithms deal with fault signatures that are manifested as step changes. While detection of these step changes can be difficult due to noise and other complicating factors, detecting slowly developing faults is usually even more complicated. Trade-offs between early detection and false positive avoidance are more difficult to establish. Often times, slow drift faults go completely undetected because the monitoring systems assume that they are ordinary system changes. To address this class of problems, we introduce here a set of algorithms that is customized to respond to drift problems of one of two redundant sensors by avoiding the bad sensor, thus indirectly recognizing the aberrant sensor. We utilize hybrid techniques that harness the advantages of learning and sensor validation techniques. Specifically, we employ a data fusion algorithm that is inspired by fuzzy principles. The parameters of this algorithm are learned using competing optimization approaches. Specifically, we compare the results from a particle swarm optimization approach with those obtained from genetic algorithms. Results are shown for an application in the transportation industry