The echo captured by an ultrasonic sensor provides details of the geometric shape of objects, this ability common among dolphins and bats is known as echolocation. The signal detected by an ultrasound sensor contains, in addition to the distance from the object, characteristics such as the type of material and internal cracks. This article describes a method for acquiring ultrasonic signals and recognizing them as geometric shapes through the use of a neural network processed by the TensorFlow JS library. The results using basic geometries (rectangular, triangular and spherical parts) showed that TensorFlow JS recognizes their ultrasonic signatures, being an additional solution to those that use cameras for object recognition.

This paper proposes a sensing system for vehicles using an auto- motive scanner with wireless connection for sending data. The connection to the scanner provides data that is sent to a cell phone via a Bluetooth connection and to the cloud . In order to provide a response to the driver as soon as an abnormality appears, an appli- cation was created to emit a synthesized voice warning. The results showed that the driver, through the synthesized voice messages and the system interface, was previously able to become aware of the abnormalities of the vehicle and carry out preventive maintenance.

No abstract