When it comes to application of computational learning techniques in practical scenarios, like for example adaptive inferential control, it is often difficult to apply the state-of-the-art techniques in a straight forward manner and usually some effort has to be dedicated to tuning either the data, in a form of data pre-processing, or the modelling techniques, in form of optimal parameter searc...

This paper presents a systematic approach for development of a data-driven soft sensor using robust statistical technique. Data preprocessing procedures are described in detail. First, a template is defined based on a key process variable to handle missing data related to severe operation interruption. Second, a univariate, followed by a multivariate principal component analysis (PCA) approach,...

This contribution presents Soft Computing Robot Navigation for mobile robot SCORCAS, a Case Study. The Navigation uses fuzzy logic experienced on mobile robot systems. Fuzzy logic is applied in analogous way into three sub-systems: i. Sensor, consisting of five autonomous sensor sub-systems: visual, acoustic, tactile, thermal and inertial; ii. Sensor fusion that comprise all the robot stimulus ...

This paper presents the use of field-programmable gate array (FPGA) in a miniature Ion Mobility Spectrometer (IMS) sensor system. This IMS sensor is for detection of subsurface gaseous volatile organic compounds (VOCs). This paper describes how an FPGA is used to process the data collected from the sensor and control its overall operation. A Xilinx Microblaze soft-core processor is used to ease...

This paper deals with an estimation problem with two different kinds of sensors. The first sensor is characterized by a relatively fast sampling rate and a small time delay. The second sensor is characterized by a slow sampling rate and a large time delay. A typical example of the latter is a ”soft sensor.” The paper provides a solution to the estimation problem in a Kalman Filtering setup, and...

Typical robot platforms comprise rigid links with fixed degrees-offreedom, solid blocks of transmission and actuator, and superficial positioning of sensors: they are often optimized for the given design criteria but are unable to execute instantaneous changes to the robot's initial mechanism design. The reallife incidences, however, require robots to face complex situations filled with unprogr...

We extend soft lithography microfabrication and design methods to introduce curvature sensors that are elastically soft (modulus 0.1–1 MPa) and stretchable (100–1000% strain). In contrast to existing curvature sensors that measure differential strain, sensors in this new class measure curvature directly and allow for arbitrary gauge factor and film thickness. Moreover, each sensor is composed e...

Abstract This paper investigates different approaches to develop soft sensors from multi-rate sampled data. The data lifting approach consists of two steps, identifying a model with a slow/lifted sampling period and extracting a fast model. Approaches based on direct extraction and linear regression are briefly reviewed, followed by reformulating the task as an unconstrained optimization proble...

Fourteen commercial soft drinks have been analyzed using colorimetric sensor arrays made from a set of 25 chemically responsive dyes printed on a hydrophobic membrane. Digital imaging of the dye array before and after immersion provides a color change profile as a unique fingerprint for each specific analyte. The digital data library generated was analyzed with statistical and chemometric metho...

A wireless, passive, remote-query sensor for monitoring sodium hypochlorite (bleach) solutions is reported. The sensor is comprised of a magnetically-soft ferromagnetic ribbon, coated with a layer of polyurethane and alumina, having a large and nonlinear permeability that supports higher-order harmonics in response to a time varying magnetic field. The hypochlorite ions induce swelling in the c...