No abstract

Discusses intelligent materials, intelligent material-based sensors, their transducing methods, and different kinds of transducers used with smart material-based sensors. Assumes that the future of intelligent sensors will almost totally depend on intelligent chemistry and intelligent instrumentation. Molecular recognition will widen the horizons of smart systems with the help of VLSI-based design and fabrication. Discusses different sensor mechanisms, such as ENFETs, immunoFETs, ISFETs and chemFETs and takes a detailed look at potentiometric, amperometric and optical biosensors.

Describes the improvements that smart sensors will bring to electronic measurement and control systems, and the advantages of using integrated sensors. Outlines the problems encountered when designing integrating electronics for use on a smart sensor chip and lists the major functions that smart sensors must perform. Concludes that the solution to many real life sensor problems will only be found when a well designed “care‐free” intelligent sensor can be produced and continues that the way to realize this concept is to combine a sensor device with a number of micro‐electronic components into a single sensor package.

Different electrical models of human heart, partial or complete, with linear or nonlinear models have been developed. In the literature, there are some applications of mathematical and physical analog models of total artificial heart (TAH), a baroreceptor model, a state-space model, an electromechanical biventricular model of the heart, and a mathematical model for the artificial generation of electrocardiogram (ECG) signals. Physical models are suitable to simulate real physiological data based on proper experimental set up present. This paper introduces a new mathematical modelling of human heart as a hydroelectromechanical system (HEMS). This paper simulates the human heart based on three main functions: hydraulic, electrical and mechanical parameters. Hydro-mechanical model developed then has been transformed into electrical domain and simulation has been carried out according to the mathematical model or formulations obtained using Laplace transform. This electrical model / circuit is then tested by MATLAB based simulations and results found are comparable with the normal ECG waveforms so that these simulated results may be useful in clinical experiments. In this model basic electrical components have been used to simulate the physiological functions of the human heart. The result is a simple electrical circuit consisting of main electrical parameters that are transformed from hydraulic models and medical physiological values. Developed MATLAB based mathematical model will primarely help to understand the proper functioning of an artificial heart and its simulated ECG signals. A comprehensive model for generating a wide variety of such signals has been targeted for future in this paper. This research especially focuses on modelling human heart as a hydro-electro-mechanical system with three case studies.

Studies on the detection of early stage melanoma have recently gained significant interest. Computer aided diagnosis systems based on neural networks, machine learning, convolutional neural networks (CNNs), and deep learning help early stage detection considerably. The colour and shapes of the images created by the pixels are crucial for the CNNs, as the pixels and associated pictures are interrelated just as a person’s fingerprint is unique. By observing this relationship, the pixel values of each picture with its neighborhoods were determined by a fuzzy logic-based system and a unique fingerprint matrix named Fuzzy Correlation Map (FCov-Map) was produced. The fuzzy logic system has four inputs and one output. The advantage of CNNs trained with fuzzy covariance maps is to eliminate both the limited availability of medical grade training data and the need for extensive image preprocessing. The fuzzy logic output is fed to the pretrained AlexNet CNN algorithm. To deliver a reliable result, a deep CNN needs a large amount of data to process. However, to obtain and use the required sufficient data for diseases is not cost- and time-effective. Therefore, the suggested fuzzy logic-based fuzzy correlation map is tackling this issue to solve the limitedness of training CNN data set.