Abstract-Searching for a missing person is not an easy task to accomplish,so over the years search methods have been developed, the problem is that the methods currently available have certain limitations and these limitations are reflected in time location. Time location in a person search is a very important factor that rescuers cannot afford to waste because the missing person is exposed to great dangers. In people search the vision system of the human being plays a very important role. The human visual system has the ability to detect and identify objects such as trees, walls, people among others besides to estimate the distance to them, this gives the human being the possibility of moving in their environment. With the development of artificial intelligence primarily to computer vision it is possible to model the human visual perception and generate computer software needed to simulate these capabilities. Using computer vision is expected to search for any missing person designing and implementing algorithms in order to an Unmanned Aerial Vehicle perform this task, also thanks to the speed of this is expected to reduce the time location. By using of a Unmanned Aerial Vehicle is not intended to replace the human being in the difficult task of searching and rescuing people but rather is intended to serve as a support tool in performing this difficult task.

No abstract

No abstract

Thls paper Presents the f lrst verslon of GENES IS, an expert system shell sultable for the development of alarm pattern recogn It Ion expert systems (APRES). GENES IS Includes a series of algorlthms and procedures especially deslgned for a rapld and systematic construct Ion of APRES . The Inputs required by GENESIS are the fault trees of the system under analys Is, the probab I I lty of occurrence of each fault In the trees, and the set of symptoms (alarms and measurements) associated to the occurrence of each Individual fault.Wlth thls lnformat Ion, GENESIS generates a set of productlon rules which relates faults and symptoms. The shell uses these rules and the probability of occurence of each of the faults In order to generate opt lmal alarm pattern recognltlon strategles (algorithm of the Inference engine). A strategy helps the operator to recognize which alarm pattern Is occurrlng wlthout havlng to search the entlre set of patterns. Al I the alarm pattern recognltlon strategtes are generated off-line, as a consequence, the response of the system WI I I be very fast. Thls feature makes GENESIS a powerful tool for the da% lopment of rea l-t I me APRES.